From d9cf593b496f4441990eda7680518418eb80d62e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marc-Andr=C3=A9=20Lemburg?= Date: Mon, 24 Oct 2005 12:14:59 +0000 Subject: Cosmetic change: make all hex literals use upper case hex so that they look more like the Unicode Consortium files. Add ending new-line to all source files. --- Lib/encodings/cp037.py | 729 +++++++++++++++++++++--------------------- Lib/encodings/cp1006.py | 625 ++++++++++++++++++------------------ Lib/encodings/cp1026.py | 729 +++++++++++++++++++++--------------------- Lib/encodings/cp1140.py | 729 +++++++++++++++++++++--------------------- Lib/encodings/cp1250.py | 637 ++++++++++++++++++------------------ Lib/encodings/cp1251.py | 637 ++++++++++++++++++------------------ Lib/encodings/cp1252.py | 635 ++++++++++++++++++------------------ Lib/encodings/cp1253.py | 611 +++++++++++++++++------------------ Lib/encodings/cp1254.py | 631 ++++++++++++++++++------------------ Lib/encodings/cp1255.py | 599 +++++++++++++++++----------------- Lib/encodings/cp1256.py | 645 ++++++++++++++++++------------------- Lib/encodings/cp1257.py | 623 ++++++++++++++++++------------------ Lib/encodings/cp1258.py | 627 ++++++++++++++++++------------------ Lib/encodings/cp424.py | 651 ++++++++++++++++++------------------- Lib/encodings/cp500.py | 729 +++++++++++++++++++++--------------------- Lib/encodings/cp856.py | 585 ++++++++++++++++----------------- Lib/encodings/cp874.py | 593 +++++++++++++++++----------------- Lib/encodings/cp875.py | 691 +++++++++++++++++++-------------------- Lib/encodings/iso8859_1.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_10.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_11.py | 595 +++++++++++++++++----------------- Lib/encodings/iso8859_13.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_14.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_15.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_16.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_2.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_3.py | 599 +++++++++++++++++----------------- Lib/encodings/iso8859_4.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_5.py | 627 ++++++++++++++++++------------------ Lib/encodings/iso8859_6.py | 447 +++++++++++++------------- Lib/encodings/iso8859_7.py | 615 +++++++++++++++++------------------ Lib/encodings/iso8859_8.py | 483 ++++++++++++++-------------- Lib/encodings/iso8859_9.py | 627 ++++++++++++++++++------------------ Lib/encodings/koi8_r.py | 637 ++++++++++++++++++------------------ Lib/encodings/koi8_u.py | 637 ++++++++++++++++++------------------ Lib/encodings/mac_centeuro.py | 651 ++++++++++++++++++------------------- Lib/encodings/mac_croatian.py | 667 +++++++++++++++++++------------------- Lib/encodings/mac_cyrillic.py | 627 ++++++++++++++++++------------------ Lib/encodings/mac_farsi.py | 665 +++++++++++++++++++------------------- Lib/encodings/mac_greek.py | 659 +++++++++++++++++++------------------- Lib/encodings/mac_iceland.py | 667 +++++++++++++++++++------------------- Lib/encodings/mac_roman.py | 667 +++++++++++++++++++------------------- Lib/encodings/mac_romanian.py | 667 +++++++++++++++++++------------------- Lib/encodings/mac_turkish.py | 667 +++++++++++++++++++------------------- Lib/encodings/tis_620.py | 591 +++++++++++++++++----------------- 45 files changed, 14281 insertions(+), 14236 deletions(-) diff --git a/Lib/encodings/cp037.py b/Lib/encodings/cp037.py index 29edbef..3933ec7 100644 --- a/Lib/encodings/cp037.py +++ b/Lib/encodings/cp037.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL - u'\x8e' # 0x0a -> CONTROL - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\x8e' # 0x0A -> CONTROL + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x92' # 0x1a -> CONTROL - u'\x8f' # 0x1b -> CONTROL - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x92' # 0x1A -> CONTROL + u'\x8f' # 0x1B -> CONTROL + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL @@ -74,12 +74,12 @@ decoding_table = ( u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL - u'\x8a' # 0x2a -> CONTROL - u'\x8b' # 0x2b -> CONTROL - u'\x8c' # 0x2c -> CONTROL - u'\x05' # 0x2d -> ENQUIRY - u'\x06' # 0x2e -> ACKNOWLEDGE - u'\x07' # 0x2f -> BELL + u'\x8a' # 0x2A -> CONTROL + u'\x8b' # 0x2B -> CONTROL + u'\x8c' # 0x2C -> CONTROL + u'\x05' # 0x2D -> ENQUIRY + u'\x06' # 0x2E -> ACKNOWLEDGE + u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE @@ -90,12 +90,12 @@ decoding_table = ( u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL - u'\x9a' # 0x3a -> CONTROL - u'\x9b' # 0x3b -> CONTROL - u'\x14' # 0x3c -> DEVICE CONTROL FOUR - u'\x15' # 0x3d -> NEGATIVE ACKNOWLEDGE - u'\x9e' # 0x3e -> CONTROL - u'\x1a' # 0x3f -> SUBSTITUTE + u'\x9a' # 0x3A -> CONTROL + u'\x9b' # 0x3B -> CONTROL + u'\x14' # 0x3C -> DEVICE CONTROL FOUR + u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + u'\x9e' # 0x3E -> CONTROL + u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX @@ -106,12 +106,12 @@ decoding_table = ( u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE - u'\xa2' # 0x4a -> CENT SIGN - u'.' # 0x4b -> FULL STOP - u'<' # 0x4c -> LESS-THAN SIGN - u'(' # 0x4d -> LEFT PARENTHESIS - u'+' # 0x4e -> PLUS SIGN - u'|' # 0x4f -> VERTICAL LINE + u'\xa2' # 0x4A -> CENT SIGN + u'.' # 0x4B -> FULL STOP + u'<' # 0x4C -> LESS-THAN SIGN + u'(' # 0x4D -> LEFT PARENTHESIS + u'+' # 0x4E -> PLUS SIGN + u'|' # 0x4F -> VERTICAL LINE u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX @@ -122,12 +122,12 @@ decoding_table = ( u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) - u'!' # 0x5a -> EXCLAMATION MARK - u'$' # 0x5b -> DOLLAR SIGN - u'*' # 0x5c -> ASTERISK - u')' # 0x5d -> RIGHT PARENTHESIS - u';' # 0x5e -> SEMICOLON - u'\xac' # 0x5f -> NOT SIGN + u'!' # 0x5A -> EXCLAMATION MARK + u'$' # 0x5B -> DOLLAR SIGN + u'*' # 0x5C -> ASTERISK + u')' # 0x5D -> RIGHT PARENTHESIS + u';' # 0x5E -> SEMICOLON + u'\xac' # 0x5F -> NOT SIGN u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX @@ -138,12 +138,12 @@ decoding_table = ( u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xa6' # 0x6a -> BROKEN BAR - u',' # 0x6b -> COMMA - u'%' # 0x6c -> PERCENT SIGN - u'_' # 0x6d -> LOW LINE - u'>' # 0x6e -> GREATER-THAN SIGN - u'?' # 0x6f -> QUESTION MARK + u'\xa6' # 0x6A -> BROKEN BAR + u',' # 0x6B -> COMMA + u'%' # 0x6C -> PERCENT SIGN + u'_' # 0x6D -> LOW LINE + u'>' # 0x6E -> GREATER-THAN SIGN + u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX @@ -154,12 +154,12 @@ decoding_table = ( u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'`' # 0x79 -> GRAVE ACCENT - u':' # 0x7a -> COLON - u'#' # 0x7b -> NUMBER SIGN - u'@' # 0x7c -> COMMERCIAL AT - u"'" # 0x7d -> APOSTROPHE - u'=' # 0x7e -> EQUALS SIGN - u'"' # 0x7f -> QUOTATION MARK + u':' # 0x7A -> COLON + u'#' # 0x7B -> NUMBER SIGN + u'@' # 0x7C -> COMMERCIAL AT + u"'" # 0x7D -> APOSTROPHE + u'=' # 0x7E -> EQUALS SIGN + u'"' # 0x7F -> QUOTATION MARK u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B @@ -170,12 +170,12 @@ decoding_table = ( u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I - u'\xab' # 0x8a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0x8b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xf0' # 0x8c -> LATIN SMALL LETTER ETH (ICELANDIC) - u'\xfd' # 0x8d -> LATIN SMALL LETTER Y WITH ACUTE - u'\xfe' # 0x8e -> LATIN SMALL LETTER THORN (ICELANDIC) - u'\xb1' # 0x8f -> PLUS-MINUS SIGN + u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) + u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE + u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) + u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K @@ -186,108 +186,108 @@ decoding_table = ( u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R - u'\xaa' # 0x9a -> FEMININE ORDINAL INDICATOR - u'\xba' # 0x9b -> MASCULINE ORDINAL INDICATOR - u'\xe6' # 0x9c -> LATIN SMALL LIGATURE AE - u'\xb8' # 0x9d -> CEDILLA - u'\xc6' # 0x9e -> LATIN CAPITAL LIGATURE AE - u'\xa4' # 0x9f -> CURRENCY SIGN - u'\xb5' # 0xa0 -> MICRO SIGN - u'~' # 0xa1 -> TILDE - u's' # 0xa2 -> LATIN SMALL LETTER S - u't' # 0xa3 -> LATIN SMALL LETTER T - u'u' # 0xa4 -> LATIN SMALL LETTER U - u'v' # 0xa5 -> LATIN SMALL LETTER V - u'w' # 0xa6 -> LATIN SMALL LETTER W - u'x' # 0xa7 -> LATIN SMALL LETTER X - u'y' # 0xa8 -> LATIN SMALL LETTER Y - u'z' # 0xa9 -> LATIN SMALL LETTER Z - u'\xa1' # 0xaa -> INVERTED EXCLAMATION MARK - u'\xbf' # 0xab -> INVERTED QUESTION MARK - u'\xd0' # 0xac -> LATIN CAPITAL LETTER ETH (ICELANDIC) - u'\xdd' # 0xad -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xde' # 0xae -> LATIN CAPITAL LETTER THORN (ICELANDIC) - u'\xae' # 0xaf -> REGISTERED SIGN - u'^' # 0xb0 -> CIRCUMFLEX ACCENT - u'\xa3' # 0xb1 -> POUND SIGN - u'\xa5' # 0xb2 -> YEN SIGN - u'\xb7' # 0xb3 -> MIDDLE DOT - u'\xa9' # 0xb4 -> COPYRIGHT SIGN - u'\xa7' # 0xb5 -> SECTION SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xbc' # 0xb7 -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xb8 -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xb9 -> VULGAR FRACTION THREE QUARTERS - u'[' # 0xba -> LEFT SQUARE BRACKET - u']' # 0xbb -> RIGHT SQUARE BRACKET - u'\xaf' # 0xbc -> MACRON - u'\xa8' # 0xbd -> DIAERESIS - u'\xb4' # 0xbe -> ACUTE ACCENT - u'\xd7' # 0xbf -> MULTIPLICATION SIGN - u'{' # 0xc0 -> LEFT CURLY BRACKET - u'A' # 0xc1 -> LATIN CAPITAL LETTER A - u'B' # 0xc2 -> LATIN CAPITAL LETTER B - u'C' # 0xc3 -> LATIN CAPITAL LETTER C - u'D' # 0xc4 -> LATIN CAPITAL LETTER D - u'E' # 0xc5 -> LATIN CAPITAL LETTER E - u'F' # 0xc6 -> LATIN CAPITAL LETTER F - u'G' # 0xc7 -> LATIN CAPITAL LETTER G - u'H' # 0xc8 -> LATIN CAPITAL LETTER H - u'I' # 0xc9 -> LATIN CAPITAL LETTER I - u'\xad' # 0xca -> SOFT HYPHEN - u'\xf4' # 0xcb -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0xcc -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf2' # 0xcd -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xce -> LATIN SMALL LETTER O WITH ACUTE - u'\xf5' # 0xcf -> LATIN SMALL LETTER O WITH TILDE - u'}' # 0xd0 -> RIGHT CURLY BRACKET - u'J' # 0xd1 -> LATIN CAPITAL LETTER J - u'K' # 0xd2 -> LATIN CAPITAL LETTER K - u'L' # 0xd3 -> LATIN CAPITAL LETTER L - u'M' # 0xd4 -> LATIN CAPITAL LETTER M - u'N' # 0xd5 -> LATIN CAPITAL LETTER N - u'O' # 0xd6 -> LATIN CAPITAL LETTER O - u'P' # 0xd7 -> LATIN CAPITAL LETTER P - u'Q' # 0xd8 -> LATIN CAPITAL LETTER Q - u'R' # 0xd9 -> LATIN CAPITAL LETTER R - u'\xb9' # 0xda -> SUPERSCRIPT ONE - u'\xfb' # 0xdb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xdc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xf9' # 0xdd -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xde -> LATIN SMALL LETTER U WITH ACUTE - u'\xff' # 0xdf -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\\' # 0xe0 -> REVERSE SOLIDUS - u'\xf7' # 0xe1 -> DIVISION SIGN - u'S' # 0xe2 -> LATIN CAPITAL LETTER S - u'T' # 0xe3 -> LATIN CAPITAL LETTER T - u'U' # 0xe4 -> LATIN CAPITAL LETTER U - u'V' # 0xe5 -> LATIN CAPITAL LETTER V - u'W' # 0xe6 -> LATIN CAPITAL LETTER W - u'X' # 0xe7 -> LATIN CAPITAL LETTER X - u'Y' # 0xe8 -> LATIN CAPITAL LETTER Y - u'Z' # 0xe9 -> LATIN CAPITAL LETTER Z - u'\xb2' # 0xea -> SUPERSCRIPT TWO - u'\xd4' # 0xeb -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd6' # 0xec -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd2' # 0xed -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd5' # 0xef -> LATIN CAPITAL LETTER O WITH TILDE - u'0' # 0xf0 -> DIGIT ZERO - u'1' # 0xf1 -> DIGIT ONE - u'2' # 0xf2 -> DIGIT TWO - u'3' # 0xf3 -> DIGIT THREE - u'4' # 0xf4 -> DIGIT FOUR - u'5' # 0xf5 -> DIGIT FIVE - u'6' # 0xf6 -> DIGIT SIX - u'7' # 0xf7 -> DIGIT SEVEN - u'8' # 0xf8 -> DIGIT EIGHT - u'9' # 0xf9 -> DIGIT NINE - u'\xb3' # 0xfa -> SUPERSCRIPT THREE - u'\xdb' # 0xfb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xfc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xd9' # 0xfd -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xfe -> LATIN CAPITAL LETTER U WITH ACUTE - u'\x9f' # 0xff -> CONTROL + u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + u'\xb8' # 0x9D -> CEDILLA + u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + u'\xa4' # 0x9F -> CURRENCY SIGN + u'\xb5' # 0xA0 -> MICRO SIGN + u'~' # 0xA1 -> TILDE + u's' # 0xA2 -> LATIN SMALL LETTER S + u't' # 0xA3 -> LATIN SMALL LETTER T + u'u' # 0xA4 -> LATIN SMALL LETTER U + u'v' # 0xA5 -> LATIN SMALL LETTER V + u'w' # 0xA6 -> LATIN SMALL LETTER W + u'x' # 0xA7 -> LATIN SMALL LETTER X + u'y' # 0xA8 -> LATIN SMALL LETTER Y + u'z' # 0xA9 -> LATIN SMALL LETTER Z + u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + u'\xbf' # 0xAB -> INVERTED QUESTION MARK + u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) + u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) + u'\xae' # 0xAF -> REGISTERED SIGN + u'^' # 0xB0 -> CIRCUMFLEX ACCENT + u'\xa3' # 0xB1 -> POUND SIGN + u'\xa5' # 0xB2 -> YEN SIGN + u'\xb7' # 0xB3 -> MIDDLE DOT + u'\xa9' # 0xB4 -> COPYRIGHT SIGN + u'\xa7' # 0xB5 -> SECTION SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + u'[' # 0xBA -> LEFT SQUARE BRACKET + u']' # 0xBB -> RIGHT SQUARE BRACKET + u'\xaf' # 0xBC -> MACRON + u'\xa8' # 0xBD -> DIAERESIS + u'\xb4' # 0xBE -> ACUTE ACCENT + u'\xd7' # 0xBF -> MULTIPLICATION SIGN + u'{' # 0xC0 -> LEFT CURLY BRACKET + u'A' # 0xC1 -> LATIN CAPITAL LETTER A + u'B' # 0xC2 -> LATIN CAPITAL LETTER B + u'C' # 0xC3 -> LATIN CAPITAL LETTER C + u'D' # 0xC4 -> LATIN CAPITAL LETTER D + u'E' # 0xC5 -> LATIN CAPITAL LETTER E + u'F' # 0xC6 -> LATIN CAPITAL LETTER F + u'G' # 0xC7 -> LATIN CAPITAL LETTER G + u'H' # 0xC8 -> LATIN CAPITAL LETTER H + u'I' # 0xC9 -> LATIN CAPITAL LETTER I + u'\xad' # 0xCA -> SOFT HYPHEN + u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + u'}' # 0xD0 -> RIGHT CURLY BRACKET + u'J' # 0xD1 -> LATIN CAPITAL LETTER J + u'K' # 0xD2 -> LATIN CAPITAL LETTER K + u'L' # 0xD3 -> LATIN CAPITAL LETTER L + u'M' # 0xD4 -> LATIN CAPITAL LETTER M + u'N' # 0xD5 -> LATIN CAPITAL LETTER N + u'O' # 0xD6 -> LATIN CAPITAL LETTER O + u'P' # 0xD7 -> LATIN CAPITAL LETTER P + u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + u'R' # 0xD9 -> LATIN CAPITAL LETTER R + u'\xb9' # 0xDA -> SUPERSCRIPT ONE + u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\\' # 0xE0 -> REVERSE SOLIDUS + u'\xf7' # 0xE1 -> DIVISION SIGN + u'S' # 0xE2 -> LATIN CAPITAL LETTER S + u'T' # 0xE3 -> LATIN CAPITAL LETTER T + u'U' # 0xE4 -> LATIN CAPITAL LETTER U + u'V' # 0xE5 -> LATIN CAPITAL LETTER V + u'W' # 0xE6 -> LATIN CAPITAL LETTER W + u'X' # 0xE7 -> LATIN CAPITAL LETTER X + u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + u'\xb2' # 0xEA -> SUPERSCRIPT TWO + u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + u'0' # 0xF0 -> DIGIT ZERO + u'1' # 0xF1 -> DIGIT ONE + u'2' # 0xF2 -> DIGIT TWO + u'3' # 0xF3 -> DIGIT THREE + u'4' # 0xF4 -> DIGIT FOUR + u'5' # 0xF5 -> DIGIT FIVE + u'6' # 0xF6 -> DIGIT SIX + u'7' # 0xF7 -> DIGIT SEVEN + u'8' # 0xF8 -> DIGIT EIGHT + u'9' # 0xF9 -> DIGIT NINE + u'\xb3' # 0xFA -> SUPERSCRIPT THREE + u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + u'\x9f' # 0xFF -> CONTROL ) ### Encoding Map @@ -298,97 +298,97 @@ encoding_map = { 0x0002: 0x02, # START OF TEXT 0x0003: 0x03, # END OF TEXT 0x0004: 0x37, # END OF TRANSMISSION - 0x0005: 0x2d, # ENQUIRY - 0x0006: 0x2e, # ACKNOWLEDGE - 0x0007: 0x2f, # BELL + 0x0005: 0x2D, # ENQUIRY + 0x0006: 0x2E, # ACKNOWLEDGE + 0x0007: 0x2F, # BELL 0x0008: 0x16, # BACKSPACE 0x0009: 0x05, # HORIZONTAL TABULATION - 0x000a: 0x25, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x25, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO 0x0013: 0x13, # DEVICE CONTROL THREE - 0x0014: 0x3c, # DEVICE CONTROL FOUR - 0x0015: 0x3d, # NEGATIVE ACKNOWLEDGE + 0x0014: 0x3C, # DEVICE CONTROL FOUR + 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE 0x0016: 0x32, # SYNCHRONOUS IDLE 0x0017: 0x26, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x3f, # SUBSTITUTE - 0x001b: 0x27, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x3F, # SUBSTITUTE + 0x001B: 0x27, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x40, # SPACE - 0x0021: 0x5a, # EXCLAMATION MARK - 0x0022: 0x7f, # QUOTATION MARK - 0x0023: 0x7b, # NUMBER SIGN - 0x0024: 0x5b, # DOLLAR SIGN - 0x0025: 0x6c, # PERCENT SIGN + 0x0021: 0x5A, # EXCLAMATION MARK + 0x0022: 0x7F, # QUOTATION MARK + 0x0023: 0x7B, # NUMBER SIGN + 0x0024: 0x5B, # DOLLAR SIGN + 0x0025: 0x6C, # PERCENT SIGN 0x0026: 0x50, # AMPERSAND - 0x0027: 0x7d, # APOSTROPHE - 0x0028: 0x4d, # LEFT PARENTHESIS - 0x0029: 0x5d, # RIGHT PARENTHESIS - 0x002a: 0x5c, # ASTERISK - 0x002b: 0x4e, # PLUS SIGN - 0x002c: 0x6b, # COMMA - 0x002d: 0x60, # HYPHEN-MINUS - 0x002e: 0x4b, # FULL STOP - 0x002f: 0x61, # SOLIDUS - 0x0030: 0xf0, # DIGIT ZERO - 0x0031: 0xf1, # DIGIT ONE - 0x0032: 0xf2, # DIGIT TWO - 0x0033: 0xf3, # DIGIT THREE - 0x0034: 0xf4, # DIGIT FOUR - 0x0035: 0xf5, # DIGIT FIVE - 0x0036: 0xf6, # DIGIT SIX - 0x0037: 0xf7, # DIGIT SEVEN - 0x0038: 0xf8, # DIGIT EIGHT - 0x0039: 0xf9, # DIGIT NINE - 0x003a: 0x7a, # COLON - 0x003b: 0x5e, # SEMICOLON - 0x003c: 0x4c, # LESS-THAN SIGN - 0x003d: 0x7e, # EQUALS SIGN - 0x003e: 0x6e, # GREATER-THAN SIGN - 0x003f: 0x6f, # QUESTION MARK - 0x0040: 0x7c, # COMMERCIAL AT - 0x0041: 0xc1, # LATIN CAPITAL LETTER A - 0x0042: 0xc2, # LATIN CAPITAL LETTER B - 0x0043: 0xc3, # LATIN CAPITAL LETTER C - 0x0044: 0xc4, # LATIN CAPITAL LETTER D - 0x0045: 0xc5, # LATIN CAPITAL LETTER E - 0x0046: 0xc6, # LATIN CAPITAL LETTER F - 0x0047: 0xc7, # LATIN CAPITAL LETTER G - 0x0048: 0xc8, # LATIN CAPITAL LETTER H - 0x0049: 0xc9, # LATIN CAPITAL LETTER I - 0x004a: 0xd1, # LATIN CAPITAL LETTER J - 0x004b: 0xd2, # LATIN CAPITAL LETTER K - 0x004c: 0xd3, # LATIN CAPITAL LETTER L - 0x004d: 0xd4, # LATIN CAPITAL LETTER M - 0x004e: 0xd5, # LATIN CAPITAL LETTER N - 0x004f: 0xd6, # LATIN CAPITAL LETTER O - 0x0050: 0xd7, # LATIN CAPITAL LETTER P - 0x0051: 0xd8, # LATIN CAPITAL LETTER Q - 0x0052: 0xd9, # LATIN CAPITAL LETTER R - 0x0053: 0xe2, # LATIN CAPITAL LETTER S - 0x0054: 0xe3, # LATIN CAPITAL LETTER T - 0x0055: 0xe4, # LATIN CAPITAL LETTER U - 0x0056: 0xe5, # LATIN CAPITAL LETTER V - 0x0057: 0xe6, # LATIN CAPITAL LETTER W - 0x0058: 0xe7, # LATIN CAPITAL LETTER X - 0x0059: 0xe8, # LATIN CAPITAL LETTER Y - 0x005a: 0xe9, # LATIN CAPITAL LETTER Z - 0x005b: 0xba, # LEFT SQUARE BRACKET - 0x005c: 0xe0, # REVERSE SOLIDUS - 0x005d: 0xbb, # RIGHT SQUARE BRACKET - 0x005e: 0xb0, # CIRCUMFLEX ACCENT - 0x005f: 0x6d, # LOW LINE + 0x0027: 0x7D, # APOSTROPHE + 0x0028: 0x4D, # LEFT PARENTHESIS + 0x0029: 0x5D, # RIGHT PARENTHESIS + 0x002A: 0x5C, # ASTERISK + 0x002B: 0x4E, # PLUS SIGN + 0x002C: 0x6B, # COMMA + 0x002D: 0x60, # HYPHEN-MINUS + 0x002E: 0x4B, # FULL STOP + 0x002F: 0x61, # SOLIDUS + 0x0030: 0xF0, # DIGIT ZERO + 0x0031: 0xF1, # DIGIT ONE + 0x0032: 0xF2, # DIGIT TWO + 0x0033: 0xF3, # DIGIT THREE + 0x0034: 0xF4, # DIGIT FOUR + 0x0035: 0xF5, # DIGIT FIVE + 0x0036: 0xF6, # DIGIT SIX + 0x0037: 0xF7, # DIGIT SEVEN + 0x0038: 0xF8, # DIGIT EIGHT + 0x0039: 0xF9, # DIGIT NINE + 0x003A: 0x7A, # COLON + 0x003B: 0x5E, # SEMICOLON + 0x003C: 0x4C, # LESS-THAN SIGN + 0x003D: 0x7E, # EQUALS SIGN + 0x003E: 0x6E, # GREATER-THAN SIGN + 0x003F: 0x6F, # QUESTION MARK + 0x0040: 0x7C, # COMMERCIAL AT + 0x0041: 0xC1, # LATIN CAPITAL LETTER A + 0x0042: 0xC2, # LATIN CAPITAL LETTER B + 0x0043: 0xC3, # LATIN CAPITAL LETTER C + 0x0044: 0xC4, # LATIN CAPITAL LETTER D + 0x0045: 0xC5, # LATIN CAPITAL LETTER E + 0x0046: 0xC6, # LATIN CAPITAL LETTER F + 0x0047: 0xC7, # LATIN CAPITAL LETTER G + 0x0048: 0xC8, # LATIN CAPITAL LETTER H + 0x0049: 0xC9, # LATIN CAPITAL LETTER I + 0x004A: 0xD1, # LATIN CAPITAL LETTER J + 0x004B: 0xD2, # LATIN CAPITAL LETTER K + 0x004C: 0xD3, # LATIN CAPITAL LETTER L + 0x004D: 0xD4, # LATIN CAPITAL LETTER M + 0x004E: 0xD5, # LATIN CAPITAL LETTER N + 0x004F: 0xD6, # LATIN CAPITAL LETTER O + 0x0050: 0xD7, # LATIN CAPITAL LETTER P + 0x0051: 0xD8, # LATIN CAPITAL LETTER Q + 0x0052: 0xD9, # LATIN CAPITAL LETTER R + 0x0053: 0xE2, # LATIN CAPITAL LETTER S + 0x0054: 0xE3, # LATIN CAPITAL LETTER T + 0x0055: 0xE4, # LATIN CAPITAL LETTER U + 0x0056: 0xE5, # LATIN CAPITAL LETTER V + 0x0057: 0xE6, # LATIN CAPITAL LETTER W + 0x0058: 0xE7, # LATIN CAPITAL LETTER X + 0x0059: 0xE8, # LATIN CAPITAL LETTER Y + 0x005A: 0xE9, # LATIN CAPITAL LETTER Z + 0x005B: 0xBA, # LEFT SQUARE BRACKET + 0x005C: 0xE0, # REVERSE SOLIDUS + 0x005D: 0xBB, # RIGHT SQUARE BRACKET + 0x005E: 0xB0, # CIRCUMFLEX ACCENT + 0x005F: 0x6D, # LOW LINE 0x0060: 0x79, # GRAVE ACCENT 0x0061: 0x81, # LATIN SMALL LETTER A 0x0062: 0x82, # LATIN SMALL LETTER B @@ -399,28 +399,28 @@ encoding_map = { 0x0067: 0x87, # LATIN SMALL LETTER G 0x0068: 0x88, # LATIN SMALL LETTER H 0x0069: 0x89, # LATIN SMALL LETTER I - 0x006a: 0x91, # LATIN SMALL LETTER J - 0x006b: 0x92, # LATIN SMALL LETTER K - 0x006c: 0x93, # LATIN SMALL LETTER L - 0x006d: 0x94, # LATIN SMALL LETTER M - 0x006e: 0x95, # LATIN SMALL LETTER N - 0x006f: 0x96, # LATIN SMALL LETTER O + 0x006A: 0x91, # LATIN SMALL LETTER J + 0x006B: 0x92, # LATIN SMALL LETTER K + 0x006C: 0x93, # LATIN SMALL LETTER L + 0x006D: 0x94, # LATIN SMALL LETTER M + 0x006E: 0x95, # LATIN SMALL LETTER N + 0x006F: 0x96, # LATIN SMALL LETTER O 0x0070: 0x97, # LATIN SMALL LETTER P 0x0071: 0x98, # LATIN SMALL LETTER Q 0x0072: 0x99, # LATIN SMALL LETTER R - 0x0073: 0xa2, # LATIN SMALL LETTER S - 0x0074: 0xa3, # LATIN SMALL LETTER T - 0x0075: 0xa4, # LATIN SMALL LETTER U - 0x0076: 0xa5, # LATIN SMALL LETTER V - 0x0077: 0xa6, # LATIN SMALL LETTER W - 0x0078: 0xa7, # LATIN SMALL LETTER X - 0x0079: 0xa8, # LATIN SMALL LETTER Y - 0x007a: 0xa9, # LATIN SMALL LETTER Z - 0x007b: 0xc0, # LEFT CURLY BRACKET - 0x007c: 0x4f, # VERTICAL LINE - 0x007d: 0xd0, # RIGHT CURLY BRACKET - 0x007e: 0xa1, # TILDE - 0x007f: 0x07, # DELETE + 0x0073: 0xA2, # LATIN SMALL LETTER S + 0x0074: 0xA3, # LATIN SMALL LETTER T + 0x0075: 0xA4, # LATIN SMALL LETTER U + 0x0076: 0xA5, # LATIN SMALL LETTER V + 0x0077: 0xA6, # LATIN SMALL LETTER W + 0x0078: 0xA7, # LATIN SMALL LETTER X + 0x0079: 0xA8, # LATIN SMALL LETTER Y + 0x007A: 0xA9, # LATIN SMALL LETTER Z + 0x007B: 0xC0, # LEFT CURLY BRACKET + 0x007C: 0x4F, # VERTICAL LINE + 0x007D: 0xD0, # RIGHT CURLY BRACKET + 0x007E: 0xA1, # TILDE + 0x007F: 0x07, # DELETE 0x0080: 0x20, # CONTROL 0x0081: 0x21, # CONTROL 0x0082: 0x22, # CONTROL @@ -431,15 +431,15 @@ encoding_map = { 0x0087: 0x17, # CONTROL 0x0088: 0x28, # CONTROL 0x0089: 0x29, # CONTROL - 0x008a: 0x2a, # CONTROL - 0x008b: 0x2b, # CONTROL - 0x008c: 0x2c, # CONTROL - 0x008d: 0x09, # CONTROL - 0x008e: 0x0a, # CONTROL - 0x008f: 0x1b, # CONTROL + 0x008A: 0x2A, # CONTROL + 0x008B: 0x2B, # CONTROL + 0x008C: 0x2C, # CONTROL + 0x008D: 0x09, # CONTROL + 0x008E: 0x0A, # CONTROL + 0x008F: 0x1B, # CONTROL 0x0090: 0x30, # CONTROL 0x0091: 0x31, # CONTROL - 0x0092: 0x1a, # CONTROL + 0x0092: 0x1A, # CONTROL 0x0093: 0x33, # CONTROL 0x0094: 0x34, # CONTROL 0x0095: 0x35, # CONTROL @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x08, # CONTROL 0x0098: 0x38, # CONTROL 0x0099: 0x39, # CONTROL - 0x009a: 0x3a, # CONTROL - 0x009b: 0x3b, # CONTROL - 0x009c: 0x04, # CONTROL - 0x009d: 0x14, # CONTROL - 0x009e: 0x3e, # CONTROL - 0x009f: 0xff, # CONTROL - 0x00a0: 0x41, # NO-BREAK SPACE - 0x00a1: 0xaa, # INVERTED EXCLAMATION MARK - 0x00a2: 0x4a, # CENT SIGN - 0x00a3: 0xb1, # POUND SIGN - 0x00a4: 0x9f, # CURRENCY SIGN - 0x00a5: 0xb2, # YEN SIGN - 0x00a6: 0x6a, # BROKEN BAR - 0x00a7: 0xb5, # SECTION SIGN - 0x00a8: 0xbd, # DIAERESIS - 0x00a9: 0xb4, # COPYRIGHT SIGN - 0x00aa: 0x9a, # FEMININE ORDINAL INDICATOR - 0x00ab: 0x8a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0x5f, # NOT SIGN - 0x00ad: 0xca, # SOFT HYPHEN - 0x00ae: 0xaf, # REGISTERED SIGN - 0x00af: 0xbc, # MACRON - 0x00b0: 0x90, # DEGREE SIGN - 0x00b1: 0x8f, # PLUS-MINUS SIGN - 0x00b2: 0xea, # SUPERSCRIPT TWO - 0x00b3: 0xfa, # SUPERSCRIPT THREE - 0x00b4: 0xbe, # ACUTE ACCENT - 0x00b5: 0xa0, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb3, # MIDDLE DOT - 0x00b8: 0x9d, # CEDILLA - 0x00b9: 0xda, # SUPERSCRIPT ONE - 0x00ba: 0x9b, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0x8b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xb7, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xb8, # VULGAR FRACTION ONE HALF - 0x00be: 0xb9, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xab, # INVERTED QUESTION MARK - 0x00c0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0x9e, # LATIN CAPITAL LIGATURE AE - 0x00c7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xac, # LATIN CAPITAL LETTER ETH (ICELANDIC) - 0x00d1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xed, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xeb, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xef, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xec, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xbf, # MULTIPLICATION SIGN - 0x00d8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xfd, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xfe, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xfb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xfc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xad, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xae, # LATIN CAPITAL LETTER THORN (ICELANDIC) - 0x00df: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) - 0x00e0: 0x44, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x45, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x46, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0x9c, # LATIN SMALL LIGATURE AE - 0x00e7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x54, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x51, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x58, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x55, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0x8c, # LATIN SMALL LETTER ETH (ICELANDIC) - 0x00f1: 0x49, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xcd, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xce, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xcb, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xcf, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xcc, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xe1, # DIVISION SIGN - 0x00f8: 0x70, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xdd, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xde, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xdb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xdc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0x8d, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0x8e, # LATIN SMALL LETTER THORN (ICELANDIC) - 0x00ff: 0xdf, # LATIN SMALL LETTER Y WITH DIAERESIS -} \ No newline at end of file + 0x009A: 0x3A, # CONTROL + 0x009B: 0x3B, # CONTROL + 0x009C: 0x04, # CONTROL + 0x009D: 0x14, # CONTROL + 0x009E: 0x3E, # CONTROL + 0x009F: 0xFF, # CONTROL + 0x00A0: 0x41, # NO-BREAK SPACE + 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK + 0x00A2: 0x4A, # CENT SIGN + 0x00A3: 0xB1, # POUND SIGN + 0x00A4: 0x9F, # CURRENCY SIGN + 0x00A5: 0xB2, # YEN SIGN + 0x00A6: 0x6A, # BROKEN BAR + 0x00A7: 0xB5, # SECTION SIGN + 0x00A8: 0xBD, # DIAERESIS + 0x00A9: 0xB4, # COPYRIGHT SIGN + 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR + 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0x5F, # NOT SIGN + 0x00AD: 0xCA, # SOFT HYPHEN + 0x00AE: 0xAF, # REGISTERED SIGN + 0x00AF: 0xBC, # MACRON + 0x00B0: 0x90, # DEGREE SIGN + 0x00B1: 0x8F, # PLUS-MINUS SIGN + 0x00B2: 0xEA, # SUPERSCRIPT TWO + 0x00B3: 0xFA, # SUPERSCRIPT THREE + 0x00B4: 0xBE, # ACUTE ACCENT + 0x00B5: 0xA0, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB3, # MIDDLE DOT + 0x00B8: 0x9D, # CEDILLA + 0x00B9: 0xDA, # SUPERSCRIPT ONE + 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF + 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xAB, # INVERTED QUESTION MARK + 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE + 0x00C7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xAC, # LATIN CAPITAL LETTER ETH (ICELANDIC) + 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xEC, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xBF, # MULTIPLICATION SIGN + 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xFC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xAD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xAE, # LATIN CAPITAL LETTER THORN (ICELANDIC) + 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE + 0x00E7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0x8C, # LATIN SMALL LETTER ETH (ICELANDIC) + 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xCC, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xE1, # DIVISION SIGN + 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xDC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0x8D, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0x8E, # LATIN SMALL LETTER THORN (ICELANDIC) + 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS +} + diff --git a/Lib/encodings/cp1006.py b/Lib/encodings/cp1006.py index ca10c54..e5fb0b6 100644 --- a/Lib/encodings/cp1006.py +++ b/Lib/encodings/cp1006.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u06f0' # 0xa1 -> EXTENDED ARABIC-INDIC DIGIT ZERO - u'\u06f1' # 0xa2 -> EXTENDED ARABIC-INDIC DIGIT ONE - u'\u06f2' # 0xa3 -> EXTENDED ARABIC-INDIC DIGIT TWO - u'\u06f3' # 0xa4 -> EXTENDED ARABIC-INDIC DIGIT THREE - u'\u06f4' # 0xa5 -> EXTENDED ARABIC-INDIC DIGIT FOUR - u'\u06f5' # 0xa6 -> EXTENDED ARABIC-INDIC DIGIT FIVE - u'\u06f6' # 0xa7 -> EXTENDED ARABIC-INDIC DIGIT SIX - u'\u06f7' # 0xa8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN - u'\u06f8' # 0xa9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT - u'\u06f9' # 0xaa -> EXTENDED ARABIC-INDIC DIGIT NINE - u'\u060c' # 0xab -> ARABIC COMMA - u'\u061b' # 0xac -> ARABIC SEMICOLON - u'\xad' # 0xad -> SOFT HYPHEN - u'\u061f' # 0xae -> ARABIC QUESTION MARK - u'\ufe81' # 0xaf -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM - u'\ufe8d' # 0xb0 -> ARABIC LETTER ALEF ISOLATED FORM - u'\ufe8e' # 0xb1 -> ARABIC LETTER ALEF FINAL FORM - u'\ufe8e' # 0xb2 -> ARABIC LETTER ALEF FINAL FORM - u'\ufe8f' # 0xb3 -> ARABIC LETTER BEH ISOLATED FORM - u'\ufe91' # 0xb4 -> ARABIC LETTER BEH INITIAL FORM - u'\ufb56' # 0xb5 -> ARABIC LETTER PEH ISOLATED FORM - u'\ufb58' # 0xb6 -> ARABIC LETTER PEH INITIAL FORM - u'\ufe93' # 0xb7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM - u'\ufe95' # 0xb8 -> ARABIC LETTER TEH ISOLATED FORM - u'\ufe97' # 0xb9 -> ARABIC LETTER TEH INITIAL FORM - u'\ufb66' # 0xba -> ARABIC LETTER TTEH ISOLATED FORM - u'\ufb68' # 0xbb -> ARABIC LETTER TTEH INITIAL FORM - u'\ufe99' # 0xbc -> ARABIC LETTER THEH ISOLATED FORM - u'\ufe9b' # 0xbd -> ARABIC LETTER THEH INITIAL FORM - u'\ufe9d' # 0xbe -> ARABIC LETTER JEEM ISOLATED FORM - u'\ufe9f' # 0xbf -> ARABIC LETTER JEEM INITIAL FORM - u'\ufb7a' # 0xc0 -> ARABIC LETTER TCHEH ISOLATED FORM - u'\ufb7c' # 0xc1 -> ARABIC LETTER TCHEH INITIAL FORM - u'\ufea1' # 0xc2 -> ARABIC LETTER HAH ISOLATED FORM - u'\ufea3' # 0xc3 -> ARABIC LETTER HAH INITIAL FORM - u'\ufea5' # 0xc4 -> ARABIC LETTER KHAH ISOLATED FORM - u'\ufea7' # 0xc5 -> ARABIC LETTER KHAH INITIAL FORM - u'\ufea9' # 0xc6 -> ARABIC LETTER DAL ISOLATED FORM - u'\ufb84' # 0xc7 -> ARABIC LETTER DAHAL ISOLATED FORMN - u'\ufeab' # 0xc8 -> ARABIC LETTER THAL ISOLATED FORM - u'\ufead' # 0xc9 -> ARABIC LETTER REH ISOLATED FORM - u'\ufb8c' # 0xca -> ARABIC LETTER RREH ISOLATED FORM - u'\ufeaf' # 0xcb -> ARABIC LETTER ZAIN ISOLATED FORM - u'\ufb8a' # 0xcc -> ARABIC LETTER JEH ISOLATED FORM - u'\ufeb1' # 0xcd -> ARABIC LETTER SEEN ISOLATED FORM - u'\ufeb3' # 0xce -> ARABIC LETTER SEEN INITIAL FORM - u'\ufeb5' # 0xcf -> ARABIC LETTER SHEEN ISOLATED FORM - u'\ufeb7' # 0xd0 -> ARABIC LETTER SHEEN INITIAL FORM - u'\ufeb9' # 0xd1 -> ARABIC LETTER SAD ISOLATED FORM - u'\ufebb' # 0xd2 -> ARABIC LETTER SAD INITIAL FORM - u'\ufebd' # 0xd3 -> ARABIC LETTER DAD ISOLATED FORM - u'\ufebf' # 0xd4 -> ARABIC LETTER DAD INITIAL FORM - u'\ufec1' # 0xd5 -> ARABIC LETTER TAH ISOLATED FORM - u'\ufec5' # 0xd6 -> ARABIC LETTER ZAH ISOLATED FORM - u'\ufec9' # 0xd7 -> ARABIC LETTER AIN ISOLATED FORM - u'\ufeca' # 0xd8 -> ARABIC LETTER AIN FINAL FORM - u'\ufecb' # 0xd9 -> ARABIC LETTER AIN INITIAL FORM - u'\ufecc' # 0xda -> ARABIC LETTER AIN MEDIAL FORM - u'\ufecd' # 0xdb -> ARABIC LETTER GHAIN ISOLATED FORM - u'\ufece' # 0xdc -> ARABIC LETTER GHAIN FINAL FORM - u'\ufecf' # 0xdd -> ARABIC LETTER GHAIN INITIAL FORM - u'\ufed0' # 0xde -> ARABIC LETTER GHAIN MEDIAL FORM - u'\ufed1' # 0xdf -> ARABIC LETTER FEH ISOLATED FORM - u'\ufed3' # 0xe0 -> ARABIC LETTER FEH INITIAL FORM - u'\ufed5' # 0xe1 -> ARABIC LETTER QAF ISOLATED FORM - u'\ufed7' # 0xe2 -> ARABIC LETTER QAF INITIAL FORM - u'\ufed9' # 0xe3 -> ARABIC LETTER KAF ISOLATED FORM - u'\ufedb' # 0xe4 -> ARABIC LETTER KAF INITIAL FORM - u'\ufb92' # 0xe5 -> ARABIC LETTER GAF ISOLATED FORM - u'\ufb94' # 0xe6 -> ARABIC LETTER GAF INITIAL FORM - u'\ufedd' # 0xe7 -> ARABIC LETTER LAM ISOLATED FORM - u'\ufedf' # 0xe8 -> ARABIC LETTER LAM INITIAL FORM - u'\ufee0' # 0xe9 -> ARABIC LETTER LAM MEDIAL FORM - u'\ufee1' # 0xea -> ARABIC LETTER MEEM ISOLATED FORM - u'\ufee3' # 0xeb -> ARABIC LETTER MEEM INITIAL FORM - u'\ufb9e' # 0xec -> ARABIC LETTER NOON GHUNNA ISOLATED FORM - u'\ufee5' # 0xed -> ARABIC LETTER NOON ISOLATED FORM - u'\ufee7' # 0xee -> ARABIC LETTER NOON INITIAL FORM - u'\ufe85' # 0xef -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM - u'\ufeed' # 0xf0 -> ARABIC LETTER WAW ISOLATED FORM - u'\ufba6' # 0xf1 -> ARABIC LETTER HEH GOAL ISOLATED FORM - u'\ufba8' # 0xf2 -> ARABIC LETTER HEH GOAL INITIAL FORM - u'\ufba9' # 0xf3 -> ARABIC LETTER HEH GOAL MEDIAL FORM - u'\ufbaa' # 0xf4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM - u'\ufe80' # 0xf5 -> ARABIC LETTER HAMZA ISOLATED FORM - u'\ufe89' # 0xf6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM - u'\ufe8a' # 0xf7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM - u'\ufe8b' # 0xf8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM - u'\ufef1' # 0xf9 -> ARABIC LETTER YEH ISOLATED FORM - u'\ufef2' # 0xfa -> ARABIC LETTER YEH FINAL FORM - u'\ufef3' # 0xfb -> ARABIC LETTER YEH INITIAL FORM - u'\ufbb0' # 0xfc -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM - u'\ufbae' # 0xfd -> ARABIC LETTER YEH BARREE ISOLATED FORM - u'\ufe7c' # 0xfe -> ARABIC SHADDA ISOLATED FORM - u'\ufe7d' # 0xff -> ARABIC SHADDA MEDIAL FORM + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u06f0' # 0xA1 -> EXTENDED ARABIC-INDIC DIGIT ZERO + u'\u06f1' # 0xA2 -> EXTENDED ARABIC-INDIC DIGIT ONE + u'\u06f2' # 0xA3 -> EXTENDED ARABIC-INDIC DIGIT TWO + u'\u06f3' # 0xA4 -> EXTENDED ARABIC-INDIC DIGIT THREE + u'\u06f4' # 0xA5 -> EXTENDED ARABIC-INDIC DIGIT FOUR + u'\u06f5' # 0xA6 -> EXTENDED ARABIC-INDIC DIGIT FIVE + u'\u06f6' # 0xA7 -> EXTENDED ARABIC-INDIC DIGIT SIX + u'\u06f7' # 0xA8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN + u'\u06f8' # 0xA9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT + u'\u06f9' # 0xAA -> EXTENDED ARABIC-INDIC DIGIT NINE + u'\u060c' # 0xAB -> ARABIC COMMA + u'\u061b' # 0xAC -> ARABIC SEMICOLON + u'\xad' # 0xAD -> SOFT HYPHEN + u'\u061f' # 0xAE -> ARABIC QUESTION MARK + u'\ufe81' # 0xAF -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM + u'\ufe8d' # 0xB0 -> ARABIC LETTER ALEF ISOLATED FORM + u'\ufe8e' # 0xB1 -> ARABIC LETTER ALEF FINAL FORM + u'\ufe8e' # 0xB2 -> ARABIC LETTER ALEF FINAL FORM + u'\ufe8f' # 0xB3 -> ARABIC LETTER BEH ISOLATED FORM + u'\ufe91' # 0xB4 -> ARABIC LETTER BEH INITIAL FORM + u'\ufb56' # 0xB5 -> ARABIC LETTER PEH ISOLATED FORM + u'\ufb58' # 0xB6 -> ARABIC LETTER PEH INITIAL FORM + u'\ufe93' # 0xB7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM + u'\ufe95' # 0xB8 -> ARABIC LETTER TEH ISOLATED FORM + u'\ufe97' # 0xB9 -> ARABIC LETTER TEH INITIAL FORM + u'\ufb66' # 0xBA -> ARABIC LETTER TTEH ISOLATED FORM + u'\ufb68' # 0xBB -> ARABIC LETTER TTEH INITIAL FORM + u'\ufe99' # 0xBC -> ARABIC LETTER THEH ISOLATED FORM + u'\ufe9b' # 0xBD -> ARABIC LETTER THEH INITIAL FORM + u'\ufe9d' # 0xBE -> ARABIC LETTER JEEM ISOLATED FORM + u'\ufe9f' # 0xBF -> ARABIC LETTER JEEM INITIAL FORM + u'\ufb7a' # 0xC0 -> ARABIC LETTER TCHEH ISOLATED FORM + u'\ufb7c' # 0xC1 -> ARABIC LETTER TCHEH INITIAL FORM + u'\ufea1' # 0xC2 -> ARABIC LETTER HAH ISOLATED FORM + u'\ufea3' # 0xC3 -> ARABIC LETTER HAH INITIAL FORM + u'\ufea5' # 0xC4 -> ARABIC LETTER KHAH ISOLATED FORM + u'\ufea7' # 0xC5 -> ARABIC LETTER KHAH INITIAL FORM + u'\ufea9' # 0xC6 -> ARABIC LETTER DAL ISOLATED FORM + u'\ufb84' # 0xC7 -> ARABIC LETTER DAHAL ISOLATED FORMN + u'\ufeab' # 0xC8 -> ARABIC LETTER THAL ISOLATED FORM + u'\ufead' # 0xC9 -> ARABIC LETTER REH ISOLATED FORM + u'\ufb8c' # 0xCA -> ARABIC LETTER RREH ISOLATED FORM + u'\ufeaf' # 0xCB -> ARABIC LETTER ZAIN ISOLATED FORM + u'\ufb8a' # 0xCC -> ARABIC LETTER JEH ISOLATED FORM + u'\ufeb1' # 0xCD -> ARABIC LETTER SEEN ISOLATED FORM + u'\ufeb3' # 0xCE -> ARABIC LETTER SEEN INITIAL FORM + u'\ufeb5' # 0xCF -> ARABIC LETTER SHEEN ISOLATED FORM + u'\ufeb7' # 0xD0 -> ARABIC LETTER SHEEN INITIAL FORM + u'\ufeb9' # 0xD1 -> ARABIC LETTER SAD ISOLATED FORM + u'\ufebb' # 0xD2 -> ARABIC LETTER SAD INITIAL FORM + u'\ufebd' # 0xD3 -> ARABIC LETTER DAD ISOLATED FORM + u'\ufebf' # 0xD4 -> ARABIC LETTER DAD INITIAL FORM + u'\ufec1' # 0xD5 -> ARABIC LETTER TAH ISOLATED FORM + u'\ufec5' # 0xD6 -> ARABIC LETTER ZAH ISOLATED FORM + u'\ufec9' # 0xD7 -> ARABIC LETTER AIN ISOLATED FORM + u'\ufeca' # 0xD8 -> ARABIC LETTER AIN FINAL FORM + u'\ufecb' # 0xD9 -> ARABIC LETTER AIN INITIAL FORM + u'\ufecc' # 0xDA -> ARABIC LETTER AIN MEDIAL FORM + u'\ufecd' # 0xDB -> ARABIC LETTER GHAIN ISOLATED FORM + u'\ufece' # 0xDC -> ARABIC LETTER GHAIN FINAL FORM + u'\ufecf' # 0xDD -> ARABIC LETTER GHAIN INITIAL FORM + u'\ufed0' # 0xDE -> ARABIC LETTER GHAIN MEDIAL FORM + u'\ufed1' # 0xDF -> ARABIC LETTER FEH ISOLATED FORM + u'\ufed3' # 0xE0 -> ARABIC LETTER FEH INITIAL FORM + u'\ufed5' # 0xE1 -> ARABIC LETTER QAF ISOLATED FORM + u'\ufed7' # 0xE2 -> ARABIC LETTER QAF INITIAL FORM + u'\ufed9' # 0xE3 -> ARABIC LETTER KAF ISOLATED FORM + u'\ufedb' # 0xE4 -> ARABIC LETTER KAF INITIAL FORM + u'\ufb92' # 0xE5 -> ARABIC LETTER GAF ISOLATED FORM + u'\ufb94' # 0xE6 -> ARABIC LETTER GAF INITIAL FORM + u'\ufedd' # 0xE7 -> ARABIC LETTER LAM ISOLATED FORM + u'\ufedf' # 0xE8 -> ARABIC LETTER LAM INITIAL FORM + u'\ufee0' # 0xE9 -> ARABIC LETTER LAM MEDIAL FORM + u'\ufee1' # 0xEA -> ARABIC LETTER MEEM ISOLATED FORM + u'\ufee3' # 0xEB -> ARABIC LETTER MEEM INITIAL FORM + u'\ufb9e' # 0xEC -> ARABIC LETTER NOON GHUNNA ISOLATED FORM + u'\ufee5' # 0xED -> ARABIC LETTER NOON ISOLATED FORM + u'\ufee7' # 0xEE -> ARABIC LETTER NOON INITIAL FORM + u'\ufe85' # 0xEF -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM + u'\ufeed' # 0xF0 -> ARABIC LETTER WAW ISOLATED FORM + u'\ufba6' # 0xF1 -> ARABIC LETTER HEH GOAL ISOLATED FORM + u'\ufba8' # 0xF2 -> ARABIC LETTER HEH GOAL INITIAL FORM + u'\ufba9' # 0xF3 -> ARABIC LETTER HEH GOAL MEDIAL FORM + u'\ufbaa' # 0xF4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM + u'\ufe80' # 0xF5 -> ARABIC LETTER HAMZA ISOLATED FORM + u'\ufe89' # 0xF6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM + u'\ufe8a' # 0xF7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM + u'\ufe8b' # 0xF8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM + u'\ufef1' # 0xF9 -> ARABIC LETTER YEH ISOLATED FORM + u'\ufef2' # 0xFA -> ARABIC LETTER YEH FINAL FORM + u'\ufef3' # 0xFB -> ARABIC LETTER YEH INITIAL FORM + u'\ufbb0' # 0xFC -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM + u'\ufbae' # 0xFD -> ARABIC LETTER YEH BARREE ISOLATED FORM + u'\ufe7c' # 0xFE -> ARABIC SHADDA ISOLATED FORM + u'\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,105 +447,106 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00ad: 0xad, # SOFT HYPHEN - 0x060c: 0xab, # ARABIC COMMA - 0x061b: 0xac, # ARABIC SEMICOLON - 0x061f: 0xae, # ARABIC QUESTION MARK - 0x06f0: 0xa1, # EXTENDED ARABIC-INDIC DIGIT ZERO - 0x06f1: 0xa2, # EXTENDED ARABIC-INDIC DIGIT ONE - 0x06f2: 0xa3, # EXTENDED ARABIC-INDIC DIGIT TWO - 0x06f3: 0xa4, # EXTENDED ARABIC-INDIC DIGIT THREE - 0x06f4: 0xa5, # EXTENDED ARABIC-INDIC DIGIT FOUR - 0x06f5: 0xa6, # EXTENDED ARABIC-INDIC DIGIT FIVE - 0x06f6: 0xa7, # EXTENDED ARABIC-INDIC DIGIT SIX - 0x06f7: 0xa8, # EXTENDED ARABIC-INDIC DIGIT SEVEN - 0x06f8: 0xa9, # EXTENDED ARABIC-INDIC DIGIT EIGHT - 0x06f9: 0xaa, # EXTENDED ARABIC-INDIC DIGIT NINE - 0xfb56: 0xb5, # ARABIC LETTER PEH ISOLATED FORM - 0xfb58: 0xb6, # ARABIC LETTER PEH INITIAL FORM - 0xfb66: 0xba, # ARABIC LETTER TTEH ISOLATED FORM - 0xfb68: 0xbb, # ARABIC LETTER TTEH INITIAL FORM - 0xfb7a: 0xc0, # ARABIC LETTER TCHEH ISOLATED FORM - 0xfb7c: 0xc1, # ARABIC LETTER TCHEH INITIAL FORM - 0xfb84: 0xc7, # ARABIC LETTER DAHAL ISOLATED FORMN - 0xfb8a: 0xcc, # ARABIC LETTER JEH ISOLATED FORM - 0xfb8c: 0xca, # ARABIC LETTER RREH ISOLATED FORM - 0xfb92: 0xe5, # ARABIC LETTER GAF ISOLATED FORM - 0xfb94: 0xe6, # ARABIC LETTER GAF INITIAL FORM - 0xfb9e: 0xec, # ARABIC LETTER NOON GHUNNA ISOLATED FORM - 0xfba6: 0xf1, # ARABIC LETTER HEH GOAL ISOLATED FORM - 0xfba8: 0xf2, # ARABIC LETTER HEH GOAL INITIAL FORM - 0xfba9: 0xf3, # ARABIC LETTER HEH GOAL MEDIAL FORM - 0xfbaa: 0xf4, # ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM - 0xfbae: 0xfd, # ARABIC LETTER YEH BARREE ISOLATED FORM - 0xfbb0: 0xfc, # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM - 0xfe7c: 0xfe, # ARABIC SHADDA ISOLATED FORM - 0xfe7d: 0xff, # ARABIC SHADDA MEDIAL FORM - 0xfe80: 0xf5, # ARABIC LETTER HAMZA ISOLATED FORM - 0xfe81: 0xaf, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM - 0xfe85: 0xef, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM - 0xfe89: 0xf6, # ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM - 0xfe8a: 0xf7, # ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM - 0xfe8b: 0xf8, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM - 0xfe8d: 0xb0, # ARABIC LETTER ALEF ISOLATED FORM - 0xfe8e: None, # ARABIC LETTER ALEF FINAL FORM - 0xfe8f: 0xb3, # ARABIC LETTER BEH ISOLATED FORM - 0xfe91: 0xb4, # ARABIC LETTER BEH INITIAL FORM - 0xfe93: 0xb7, # ARABIC LETTER TEH MARBUTA ISOLATED FORM - 0xfe95: 0xb8, # ARABIC LETTER TEH ISOLATED FORM - 0xfe97: 0xb9, # ARABIC LETTER TEH INITIAL FORM - 0xfe99: 0xbc, # ARABIC LETTER THEH ISOLATED FORM - 0xfe9b: 0xbd, # ARABIC LETTER THEH INITIAL FORM - 0xfe9d: 0xbe, # ARABIC LETTER JEEM ISOLATED FORM - 0xfe9f: 0xbf, # ARABIC LETTER JEEM INITIAL FORM - 0xfea1: 0xc2, # ARABIC LETTER HAH ISOLATED FORM - 0xfea3: 0xc3, # ARABIC LETTER HAH INITIAL FORM - 0xfea5: 0xc4, # ARABIC LETTER KHAH ISOLATED FORM - 0xfea7: 0xc5, # ARABIC LETTER KHAH INITIAL FORM - 0xfea9: 0xc6, # ARABIC LETTER DAL ISOLATED FORM - 0xfeab: 0xc8, # ARABIC LETTER THAL ISOLATED FORM - 0xfead: 0xc9, # ARABIC LETTER REH ISOLATED FORM - 0xfeaf: 0xcb, # ARABIC LETTER ZAIN ISOLATED FORM - 0xfeb1: 0xcd, # ARABIC LETTER SEEN ISOLATED FORM - 0xfeb3: 0xce, # ARABIC LETTER SEEN INITIAL FORM - 0xfeb5: 0xcf, # ARABIC LETTER SHEEN ISOLATED FORM - 0xfeb7: 0xd0, # ARABIC LETTER SHEEN INITIAL FORM - 0xfeb9: 0xd1, # ARABIC LETTER SAD ISOLATED FORM - 0xfebb: 0xd2, # ARABIC LETTER SAD INITIAL FORM - 0xfebd: 0xd3, # ARABIC LETTER DAD ISOLATED FORM - 0xfebf: 0xd4, # ARABIC LETTER DAD INITIAL FORM - 0xfec1: 0xd5, # ARABIC LETTER TAH ISOLATED FORM - 0xfec5: 0xd6, # ARABIC LETTER ZAH ISOLATED FORM - 0xfec9: 0xd7, # ARABIC LETTER AIN ISOLATED FORM - 0xfeca: 0xd8, # ARABIC LETTER AIN FINAL FORM - 0xfecb: 0xd9, # ARABIC LETTER AIN INITIAL FORM - 0xfecc: 0xda, # ARABIC LETTER AIN MEDIAL FORM - 0xfecd: 0xdb, # ARABIC LETTER GHAIN ISOLATED FORM - 0xfece: 0xdc, # ARABIC LETTER GHAIN FINAL FORM - 0xfecf: 0xdd, # ARABIC LETTER GHAIN INITIAL FORM - 0xfed0: 0xde, # ARABIC LETTER GHAIN MEDIAL FORM - 0xfed1: 0xdf, # ARABIC LETTER FEH ISOLATED FORM - 0xfed3: 0xe0, # ARABIC LETTER FEH INITIAL FORM - 0xfed5: 0xe1, # ARABIC LETTER QAF ISOLATED FORM - 0xfed7: 0xe2, # ARABIC LETTER QAF INITIAL FORM - 0xfed9: 0xe3, # ARABIC LETTER KAF ISOLATED FORM - 0xfedb: 0xe4, # ARABIC LETTER KAF INITIAL FORM - 0xfedd: 0xe7, # ARABIC LETTER LAM ISOLATED FORM - 0xfedf: 0xe8, # ARABIC LETTER LAM INITIAL FORM - 0xfee0: 0xe9, # ARABIC LETTER LAM MEDIAL FORM - 0xfee1: 0xea, # ARABIC LETTER MEEM ISOLATED FORM - 0xfee3: 0xeb, # ARABIC LETTER MEEM INITIAL FORM - 0xfee5: 0xed, # ARABIC LETTER NOON ISOLATED FORM - 0xfee7: 0xee, # ARABIC LETTER NOON INITIAL FORM - 0xfeed: 0xf0, # ARABIC LETTER WAW ISOLATED FORM - 0xfef1: 0xf9, # ARABIC LETTER YEH ISOLATED FORM - 0xfef2: 0xfa, # ARABIC LETTER YEH FINAL FORM - 0xfef3: 0xfb, # ARABIC LETTER YEH INITIAL FORM -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00AD: 0xAD, # SOFT HYPHEN + 0x060C: 0xAB, # ARABIC COMMA + 0x061B: 0xAC, # ARABIC SEMICOLON + 0x061F: 0xAE, # ARABIC QUESTION MARK + 0x06F0: 0xA1, # EXTENDED ARABIC-INDIC DIGIT ZERO + 0x06F1: 0xA2, # EXTENDED ARABIC-INDIC DIGIT ONE + 0x06F2: 0xA3, # EXTENDED ARABIC-INDIC DIGIT TWO + 0x06F3: 0xA4, # EXTENDED ARABIC-INDIC DIGIT THREE + 0x06F4: 0xA5, # EXTENDED ARABIC-INDIC DIGIT FOUR + 0x06F5: 0xA6, # EXTENDED ARABIC-INDIC DIGIT FIVE + 0x06F6: 0xA7, # EXTENDED ARABIC-INDIC DIGIT SIX + 0x06F7: 0xA8, # EXTENDED ARABIC-INDIC DIGIT SEVEN + 0x06F8: 0xA9, # EXTENDED ARABIC-INDIC DIGIT EIGHT + 0x06F9: 0xAA, # EXTENDED ARABIC-INDIC DIGIT NINE + 0xFB56: 0xB5, # ARABIC LETTER PEH ISOLATED FORM + 0xFB58: 0xB6, # ARABIC LETTER PEH INITIAL FORM + 0xFB66: 0xBA, # ARABIC LETTER TTEH ISOLATED FORM + 0xFB68: 0xBB, # ARABIC LETTER TTEH INITIAL FORM + 0xFB7A: 0xC0, # ARABIC LETTER TCHEH ISOLATED FORM + 0xFB7C: 0xC1, # ARABIC LETTER TCHEH INITIAL FORM + 0xFB84: 0xC7, # ARABIC LETTER DAHAL ISOLATED FORMN + 0xFB8A: 0xCC, # ARABIC LETTER JEH ISOLATED FORM + 0xFB8C: 0xCA, # ARABIC LETTER RREH ISOLATED FORM + 0xFB92: 0xE5, # ARABIC LETTER GAF ISOLATED FORM + 0xFB94: 0xE6, # ARABIC LETTER GAF INITIAL FORM + 0xFB9E: 0xEC, # ARABIC LETTER NOON GHUNNA ISOLATED FORM + 0xFBA6: 0xF1, # ARABIC LETTER HEH GOAL ISOLATED FORM + 0xFBA8: 0xF2, # ARABIC LETTER HEH GOAL INITIAL FORM + 0xFBA9: 0xF3, # ARABIC LETTER HEH GOAL MEDIAL FORM + 0xFBAA: 0xF4, # ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM + 0xFBAE: 0xFD, # ARABIC LETTER YEH BARREE ISOLATED FORM + 0xFBB0: 0xFC, # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM + 0xFE7C: 0xFE, # ARABIC SHADDA ISOLATED FORM + 0xFE7D: 0xFF, # ARABIC SHADDA MEDIAL FORM + 0xFE80: 0xF5, # ARABIC LETTER HAMZA ISOLATED FORM + 0xFE81: 0xAF, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM + 0xFE85: 0xEF, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM + 0xFE89: 0xF6, # ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM + 0xFE8A: 0xF7, # ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM + 0xFE8B: 0xF8, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM + 0xFE8D: 0xB0, # ARABIC LETTER ALEF ISOLATED FORM + 0xFE8E: None, # ARABIC LETTER ALEF FINAL FORM + 0xFE8F: 0xB3, # ARABIC LETTER BEH ISOLATED FORM + 0xFE91: 0xB4, # ARABIC LETTER BEH INITIAL FORM + 0xFE93: 0xB7, # ARABIC LETTER TEH MARBUTA ISOLATED FORM + 0xFE95: 0xB8, # ARABIC LETTER TEH ISOLATED FORM + 0xFE97: 0xB9, # ARABIC LETTER TEH INITIAL FORM + 0xFE99: 0xBC, # ARABIC LETTER THEH ISOLATED FORM + 0xFE9B: 0xBD, # ARABIC LETTER THEH INITIAL FORM + 0xFE9D: 0xBE, # ARABIC LETTER JEEM ISOLATED FORM + 0xFE9F: 0xBF, # ARABIC LETTER JEEM INITIAL FORM + 0xFEA1: 0xC2, # ARABIC LETTER HAH ISOLATED FORM + 0xFEA3: 0xC3, # ARABIC LETTER HAH INITIAL FORM + 0xFEA5: 0xC4, # ARABIC LETTER KHAH ISOLATED FORM + 0xFEA7: 0xC5, # ARABIC LETTER KHAH INITIAL FORM + 0xFEA9: 0xC6, # ARABIC LETTER DAL ISOLATED FORM + 0xFEAB: 0xC8, # ARABIC LETTER THAL ISOLATED FORM + 0xFEAD: 0xC9, # ARABIC LETTER REH ISOLATED FORM + 0xFEAF: 0xCB, # ARABIC LETTER ZAIN ISOLATED FORM + 0xFEB1: 0xCD, # ARABIC LETTER SEEN ISOLATED FORM + 0xFEB3: 0xCE, # ARABIC LETTER SEEN INITIAL FORM + 0xFEB5: 0xCF, # ARABIC LETTER SHEEN ISOLATED FORM + 0xFEB7: 0xD0, # ARABIC LETTER SHEEN INITIAL FORM + 0xFEB9: 0xD1, # ARABIC LETTER SAD ISOLATED FORM + 0xFEBB: 0xD2, # ARABIC LETTER SAD INITIAL FORM + 0xFEBD: 0xD3, # ARABIC LETTER DAD ISOLATED FORM + 0xFEBF: 0xD4, # ARABIC LETTER DAD INITIAL FORM + 0xFEC1: 0xD5, # ARABIC LETTER TAH ISOLATED FORM + 0xFEC5: 0xD6, # ARABIC LETTER ZAH ISOLATED FORM + 0xFEC9: 0xD7, # ARABIC LETTER AIN ISOLATED FORM + 0xFECA: 0xD8, # ARABIC LETTER AIN FINAL FORM + 0xFECB: 0xD9, # ARABIC LETTER AIN INITIAL FORM + 0xFECC: 0xDA, # ARABIC LETTER AIN MEDIAL FORM + 0xFECD: 0xDB, # ARABIC LETTER GHAIN ISOLATED FORM + 0xFECE: 0xDC, # ARABIC LETTER GHAIN FINAL FORM + 0xFECF: 0xDD, # ARABIC LETTER GHAIN INITIAL FORM + 0xFED0: 0xDE, # ARABIC LETTER GHAIN MEDIAL FORM + 0xFED1: 0xDF, # ARABIC LETTER FEH ISOLATED FORM + 0xFED3: 0xE0, # ARABIC LETTER FEH INITIAL FORM + 0xFED5: 0xE1, # ARABIC LETTER QAF ISOLATED FORM + 0xFED7: 0xE2, # ARABIC LETTER QAF INITIAL FORM + 0xFED9: 0xE3, # ARABIC LETTER KAF ISOLATED FORM + 0xFEDB: 0xE4, # ARABIC LETTER KAF INITIAL FORM + 0xFEDD: 0xE7, # ARABIC LETTER LAM ISOLATED FORM + 0xFEDF: 0xE8, # ARABIC LETTER LAM INITIAL FORM + 0xFEE0: 0xE9, # ARABIC LETTER LAM MEDIAL FORM + 0xFEE1: 0xEA, # ARABIC LETTER MEEM ISOLATED FORM + 0xFEE3: 0xEB, # ARABIC LETTER MEEM INITIAL FORM + 0xFEE5: 0xED, # ARABIC LETTER NOON ISOLATED FORM + 0xFEE7: 0xEE, # ARABIC LETTER NOON INITIAL FORM + 0xFEED: 0xF0, # ARABIC LETTER WAW ISOLATED FORM + 0xFEF1: 0xF9, # ARABIC LETTER YEH ISOLATED FORM + 0xFEF2: 0xFA, # ARABIC LETTER YEH FINAL FORM + 0xFEF3: 0xFB, # ARABIC LETTER YEH INITIAL FORM +} + diff --git a/Lib/encodings/cp1026.py b/Lib/encodings/cp1026.py index 463008d..83e6429 100644 --- a/Lib/encodings/cp1026.py +++ b/Lib/encodings/cp1026.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL - u'\x8e' # 0x0a -> CONTROL - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\x8e' # 0x0A -> CONTROL + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x92' # 0x1a -> CONTROL - u'\x8f' # 0x1b -> CONTROL - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x92' # 0x1A -> CONTROL + u'\x8f' # 0x1B -> CONTROL + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL @@ -74,12 +74,12 @@ decoding_table = ( u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL - u'\x8a' # 0x2a -> CONTROL - u'\x8b' # 0x2b -> CONTROL - u'\x8c' # 0x2c -> CONTROL - u'\x05' # 0x2d -> ENQUIRY - u'\x06' # 0x2e -> ACKNOWLEDGE - u'\x07' # 0x2f -> BELL + u'\x8a' # 0x2A -> CONTROL + u'\x8b' # 0x2B -> CONTROL + u'\x8c' # 0x2C -> CONTROL + u'\x05' # 0x2D -> ENQUIRY + u'\x06' # 0x2E -> ACKNOWLEDGE + u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE @@ -90,12 +90,12 @@ decoding_table = ( u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL - u'\x9a' # 0x3a -> CONTROL - u'\x9b' # 0x3b -> CONTROL - u'\x14' # 0x3c -> DEVICE CONTROL FOUR - u'\x15' # 0x3d -> NEGATIVE ACKNOWLEDGE - u'\x9e' # 0x3e -> CONTROL - u'\x1a' # 0x3f -> SUBSTITUTE + u'\x9a' # 0x3A -> CONTROL + u'\x9b' # 0x3B -> CONTROL + u'\x14' # 0x3C -> DEVICE CONTROL FOUR + u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + u'\x9e' # 0x3E -> CONTROL + u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX @@ -106,12 +106,12 @@ decoding_table = ( u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'{' # 0x48 -> LEFT CURLY BRACKET u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE - u'\xc7' # 0x4a -> LATIN CAPITAL LETTER C WITH CEDILLA - u'.' # 0x4b -> FULL STOP - u'<' # 0x4c -> LESS-THAN SIGN - u'(' # 0x4d -> LEFT PARENTHESIS - u'+' # 0x4e -> PLUS SIGN - u'!' # 0x4f -> EXCLAMATION MARK + u'\xc7' # 0x4A -> LATIN CAPITAL LETTER C WITH CEDILLA + u'.' # 0x4B -> FULL STOP + u'<' # 0x4C -> LESS-THAN SIGN + u'(' # 0x4D -> LEFT PARENTHESIS + u'+' # 0x4E -> PLUS SIGN + u'!' # 0x4F -> EXCLAMATION MARK u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX @@ -122,12 +122,12 @@ decoding_table = ( u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) - u'\u011e' # 0x5a -> LATIN CAPITAL LETTER G WITH BREVE - u'\u0130' # 0x5b -> LATIN CAPITAL LETTER I WITH DOT ABOVE - u'*' # 0x5c -> ASTERISK - u')' # 0x5d -> RIGHT PARENTHESIS - u';' # 0x5e -> SEMICOLON - u'^' # 0x5f -> CIRCUMFLEX ACCENT + u'\u011e' # 0x5A -> LATIN CAPITAL LETTER G WITH BREVE + u'\u0130' # 0x5B -> LATIN CAPITAL LETTER I WITH DOT ABOVE + u'*' # 0x5C -> ASTERISK + u')' # 0x5D -> RIGHT PARENTHESIS + u';' # 0x5E -> SEMICOLON + u'^' # 0x5F -> CIRCUMFLEX ACCENT u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX @@ -138,12 +138,12 @@ decoding_table = ( u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'[' # 0x68 -> LEFT SQUARE BRACKET u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE - u'\u015f' # 0x6a -> LATIN SMALL LETTER S WITH CEDILLA - u',' # 0x6b -> COMMA - u'%' # 0x6c -> PERCENT SIGN - u'_' # 0x6d -> LOW LINE - u'>' # 0x6e -> GREATER-THAN SIGN - u'?' # 0x6f -> QUESTION MARK + u'\u015f' # 0x6A -> LATIN SMALL LETTER S WITH CEDILLA + u',' # 0x6B -> COMMA + u'%' # 0x6C -> PERCENT SIGN + u'_' # 0x6D -> LOW LINE + u'>' # 0x6E -> GREATER-THAN SIGN + u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX @@ -154,12 +154,12 @@ decoding_table = ( u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'\u0131' # 0x79 -> LATIN SMALL LETTER DOTLESS I - u':' # 0x7a -> COLON - u'\xd6' # 0x7b -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\u015e' # 0x7c -> LATIN CAPITAL LETTER S WITH CEDILLA - u"'" # 0x7d -> APOSTROPHE - u'=' # 0x7e -> EQUALS SIGN - u'\xdc' # 0x7f -> LATIN CAPITAL LETTER U WITH DIAERESIS + u':' # 0x7A -> COLON + u'\xd6' # 0x7B -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\u015e' # 0x7C -> LATIN CAPITAL LETTER S WITH CEDILLA + u"'" # 0x7D -> APOSTROPHE + u'=' # 0x7E -> EQUALS SIGN + u'\xdc' # 0x7F -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B @@ -170,12 +170,12 @@ decoding_table = ( u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I - u'\xab' # 0x8a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0x8b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'}' # 0x8c -> RIGHT CURLY BRACKET - u'`' # 0x8d -> GRAVE ACCENT - u'\xa6' # 0x8e -> BROKEN BAR - u'\xb1' # 0x8f -> PLUS-MINUS SIGN + u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'}' # 0x8C -> RIGHT CURLY BRACKET + u'`' # 0x8D -> GRAVE ACCENT + u'\xa6' # 0x8E -> BROKEN BAR + u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K @@ -186,108 +186,108 @@ decoding_table = ( u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R - u'\xaa' # 0x9a -> FEMININE ORDINAL INDICATOR - u'\xba' # 0x9b -> MASCULINE ORDINAL INDICATOR - u'\xe6' # 0x9c -> LATIN SMALL LIGATURE AE - u'\xb8' # 0x9d -> CEDILLA - u'\xc6' # 0x9e -> LATIN CAPITAL LIGATURE AE - u'\xa4' # 0x9f -> CURRENCY SIGN - u'\xb5' # 0xa0 -> MICRO SIGN - u'\xf6' # 0xa1 -> LATIN SMALL LETTER O WITH DIAERESIS - u's' # 0xa2 -> LATIN SMALL LETTER S - u't' # 0xa3 -> LATIN SMALL LETTER T - u'u' # 0xa4 -> LATIN SMALL LETTER U - u'v' # 0xa5 -> LATIN SMALL LETTER V - u'w' # 0xa6 -> LATIN SMALL LETTER W - u'x' # 0xa7 -> LATIN SMALL LETTER X - u'y' # 0xa8 -> LATIN SMALL LETTER Y - u'z' # 0xa9 -> LATIN SMALL LETTER Z - u'\xa1' # 0xaa -> INVERTED EXCLAMATION MARK - u'\xbf' # 0xab -> INVERTED QUESTION MARK - u']' # 0xac -> RIGHT SQUARE BRACKET - u'$' # 0xad -> DOLLAR SIGN - u'@' # 0xae -> COMMERCIAL AT - u'\xae' # 0xaf -> REGISTERED SIGN - u'\xa2' # 0xb0 -> CENT SIGN - u'\xa3' # 0xb1 -> POUND SIGN - u'\xa5' # 0xb2 -> YEN SIGN - u'\xb7' # 0xb3 -> MIDDLE DOT - u'\xa9' # 0xb4 -> COPYRIGHT SIGN - u'\xa7' # 0xb5 -> SECTION SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xbc' # 0xb7 -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xb8 -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xb9 -> VULGAR FRACTION THREE QUARTERS - u'\xac' # 0xba -> NOT SIGN - u'|' # 0xbb -> VERTICAL LINE - u'\xaf' # 0xbc -> MACRON - u'\xa8' # 0xbd -> DIAERESIS - u'\xb4' # 0xbe -> ACUTE ACCENT - u'\xd7' # 0xbf -> MULTIPLICATION SIGN - u'\xe7' # 0xc0 -> LATIN SMALL LETTER C WITH CEDILLA - u'A' # 0xc1 -> LATIN CAPITAL LETTER A - u'B' # 0xc2 -> LATIN CAPITAL LETTER B - u'C' # 0xc3 -> LATIN CAPITAL LETTER C - u'D' # 0xc4 -> LATIN CAPITAL LETTER D - u'E' # 0xc5 -> LATIN CAPITAL LETTER E - u'F' # 0xc6 -> LATIN CAPITAL LETTER F - u'G' # 0xc7 -> LATIN CAPITAL LETTER G - u'H' # 0xc8 -> LATIN CAPITAL LETTER H - u'I' # 0xc9 -> LATIN CAPITAL LETTER I - u'\xad' # 0xca -> SOFT HYPHEN - u'\xf4' # 0xcb -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'~' # 0xcc -> TILDE - u'\xf2' # 0xcd -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xce -> LATIN SMALL LETTER O WITH ACUTE - u'\xf5' # 0xcf -> LATIN SMALL LETTER O WITH TILDE - u'\u011f' # 0xd0 -> LATIN SMALL LETTER G WITH BREVE - u'J' # 0xd1 -> LATIN CAPITAL LETTER J - u'K' # 0xd2 -> LATIN CAPITAL LETTER K - u'L' # 0xd3 -> LATIN CAPITAL LETTER L - u'M' # 0xd4 -> LATIN CAPITAL LETTER M - u'N' # 0xd5 -> LATIN CAPITAL LETTER N - u'O' # 0xd6 -> LATIN CAPITAL LETTER O - u'P' # 0xd7 -> LATIN CAPITAL LETTER P - u'Q' # 0xd8 -> LATIN CAPITAL LETTER Q - u'R' # 0xd9 -> LATIN CAPITAL LETTER R - u'\xb9' # 0xda -> SUPERSCRIPT ONE - u'\xfb' # 0xdb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\\' # 0xdc -> REVERSE SOLIDUS - u'\xf9' # 0xdd -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xde -> LATIN SMALL LETTER U WITH ACUTE - u'\xff' # 0xdf -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\xfc' # 0xe0 -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xf7' # 0xe1 -> DIVISION SIGN - u'S' # 0xe2 -> LATIN CAPITAL LETTER S - u'T' # 0xe3 -> LATIN CAPITAL LETTER T - u'U' # 0xe4 -> LATIN CAPITAL LETTER U - u'V' # 0xe5 -> LATIN CAPITAL LETTER V - u'W' # 0xe6 -> LATIN CAPITAL LETTER W - u'X' # 0xe7 -> LATIN CAPITAL LETTER X - u'Y' # 0xe8 -> LATIN CAPITAL LETTER Y - u'Z' # 0xe9 -> LATIN CAPITAL LETTER Z - u'\xb2' # 0xea -> SUPERSCRIPT TWO - u'\xd4' # 0xeb -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'#' # 0xec -> NUMBER SIGN - u'\xd2' # 0xed -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd5' # 0xef -> LATIN CAPITAL LETTER O WITH TILDE - u'0' # 0xf0 -> DIGIT ZERO - u'1' # 0xf1 -> DIGIT ONE - u'2' # 0xf2 -> DIGIT TWO - u'3' # 0xf3 -> DIGIT THREE - u'4' # 0xf4 -> DIGIT FOUR - u'5' # 0xf5 -> DIGIT FIVE - u'6' # 0xf6 -> DIGIT SIX - u'7' # 0xf7 -> DIGIT SEVEN - u'8' # 0xf8 -> DIGIT EIGHT - u'9' # 0xf9 -> DIGIT NINE - u'\xb3' # 0xfa -> SUPERSCRIPT THREE - u'\xdb' # 0xfb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'"' # 0xfc -> QUOTATION MARK - u'\xd9' # 0xfd -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xfe -> LATIN CAPITAL LETTER U WITH ACUTE - u'\x9f' # 0xff -> CONTROL + u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + u'\xb8' # 0x9D -> CEDILLA + u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + u'\xa4' # 0x9F -> CURRENCY SIGN + u'\xb5' # 0xA0 -> MICRO SIGN + u'\xf6' # 0xA1 -> LATIN SMALL LETTER O WITH DIAERESIS + u's' # 0xA2 -> LATIN SMALL LETTER S + u't' # 0xA3 -> LATIN SMALL LETTER T + u'u' # 0xA4 -> LATIN SMALL LETTER U + u'v' # 0xA5 -> LATIN SMALL LETTER V + u'w' # 0xA6 -> LATIN SMALL LETTER W + u'x' # 0xA7 -> LATIN SMALL LETTER X + u'y' # 0xA8 -> LATIN SMALL LETTER Y + u'z' # 0xA9 -> LATIN SMALL LETTER Z + u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + u'\xbf' # 0xAB -> INVERTED QUESTION MARK + u']' # 0xAC -> RIGHT SQUARE BRACKET + u'$' # 0xAD -> DOLLAR SIGN + u'@' # 0xAE -> COMMERCIAL AT + u'\xae' # 0xAF -> REGISTERED SIGN + u'\xa2' # 0xB0 -> CENT SIGN + u'\xa3' # 0xB1 -> POUND SIGN + u'\xa5' # 0xB2 -> YEN SIGN + u'\xb7' # 0xB3 -> MIDDLE DOT + u'\xa9' # 0xB4 -> COPYRIGHT SIGN + u'\xa7' # 0xB5 -> SECTION SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + u'\xac' # 0xBA -> NOT SIGN + u'|' # 0xBB -> VERTICAL LINE + u'\xaf' # 0xBC -> MACRON + u'\xa8' # 0xBD -> DIAERESIS + u'\xb4' # 0xBE -> ACUTE ACCENT + u'\xd7' # 0xBF -> MULTIPLICATION SIGN + u'\xe7' # 0xC0 -> LATIN SMALL LETTER C WITH CEDILLA + u'A' # 0xC1 -> LATIN CAPITAL LETTER A + u'B' # 0xC2 -> LATIN CAPITAL LETTER B + u'C' # 0xC3 -> LATIN CAPITAL LETTER C + u'D' # 0xC4 -> LATIN CAPITAL LETTER D + u'E' # 0xC5 -> LATIN CAPITAL LETTER E + u'F' # 0xC6 -> LATIN CAPITAL LETTER F + u'G' # 0xC7 -> LATIN CAPITAL LETTER G + u'H' # 0xC8 -> LATIN CAPITAL LETTER H + u'I' # 0xC9 -> LATIN CAPITAL LETTER I + u'\xad' # 0xCA -> SOFT HYPHEN + u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'~' # 0xCC -> TILDE + u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + u'\u011f' # 0xD0 -> LATIN SMALL LETTER G WITH BREVE + u'J' # 0xD1 -> LATIN CAPITAL LETTER J + u'K' # 0xD2 -> LATIN CAPITAL LETTER K + u'L' # 0xD3 -> LATIN CAPITAL LETTER L + u'M' # 0xD4 -> LATIN CAPITAL LETTER M + u'N' # 0xD5 -> LATIN CAPITAL LETTER N + u'O' # 0xD6 -> LATIN CAPITAL LETTER O + u'P' # 0xD7 -> LATIN CAPITAL LETTER P + u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + u'R' # 0xD9 -> LATIN CAPITAL LETTER R + u'\xb9' # 0xDA -> SUPERSCRIPT ONE + u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\\' # 0xDC -> REVERSE SOLIDUS + u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\xfc' # 0xE0 -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xf7' # 0xE1 -> DIVISION SIGN + u'S' # 0xE2 -> LATIN CAPITAL LETTER S + u'T' # 0xE3 -> LATIN CAPITAL LETTER T + u'U' # 0xE4 -> LATIN CAPITAL LETTER U + u'V' # 0xE5 -> LATIN CAPITAL LETTER V + u'W' # 0xE6 -> LATIN CAPITAL LETTER W + u'X' # 0xE7 -> LATIN CAPITAL LETTER X + u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + u'\xb2' # 0xEA -> SUPERSCRIPT TWO + u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'#' # 0xEC -> NUMBER SIGN + u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + u'0' # 0xF0 -> DIGIT ZERO + u'1' # 0xF1 -> DIGIT ONE + u'2' # 0xF2 -> DIGIT TWO + u'3' # 0xF3 -> DIGIT THREE + u'4' # 0xF4 -> DIGIT FOUR + u'5' # 0xF5 -> DIGIT FIVE + u'6' # 0xF6 -> DIGIT SIX + u'7' # 0xF7 -> DIGIT SEVEN + u'8' # 0xF8 -> DIGIT EIGHT + u'9' # 0xF9 -> DIGIT NINE + u'\xb3' # 0xFA -> SUPERSCRIPT THREE + u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'"' # 0xFC -> QUOTATION MARK + u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + u'\x9f' # 0xFF -> CONTROL ) ### Encoding Map @@ -298,98 +298,98 @@ encoding_map = { 0x0002: 0x02, # START OF TEXT 0x0003: 0x03, # END OF TEXT 0x0004: 0x37, # END OF TRANSMISSION - 0x0005: 0x2d, # ENQUIRY - 0x0006: 0x2e, # ACKNOWLEDGE - 0x0007: 0x2f, # BELL + 0x0005: 0x2D, # ENQUIRY + 0x0006: 0x2E, # ACKNOWLEDGE + 0x0007: 0x2F, # BELL 0x0008: 0x16, # BACKSPACE 0x0009: 0x05, # HORIZONTAL TABULATION - 0x000a: 0x25, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x25, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO 0x0013: 0x13, # DEVICE CONTROL THREE - 0x0014: 0x3c, # DEVICE CONTROL FOUR - 0x0015: 0x3d, # NEGATIVE ACKNOWLEDGE + 0x0014: 0x3C, # DEVICE CONTROL FOUR + 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE 0x0016: 0x32, # SYNCHRONOUS IDLE 0x0017: 0x26, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x3f, # SUBSTITUTE - 0x001b: 0x27, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x3F, # SUBSTITUTE + 0x001B: 0x27, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x40, # SPACE - 0x0021: 0x4f, # EXCLAMATION MARK - 0x0022: 0xfc, # QUOTATION MARK - 0x0023: 0xec, # NUMBER SIGN - 0x0024: 0xad, # DOLLAR SIGN - 0x0025: 0x6c, # PERCENT SIGN + 0x0021: 0x4F, # EXCLAMATION MARK + 0x0022: 0xFC, # QUOTATION MARK + 0x0023: 0xEC, # NUMBER SIGN + 0x0024: 0xAD, # DOLLAR SIGN + 0x0025: 0x6C, # PERCENT SIGN 0x0026: 0x50, # AMPERSAND - 0x0027: 0x7d, # APOSTROPHE - 0x0028: 0x4d, # LEFT PARENTHESIS - 0x0029: 0x5d, # RIGHT PARENTHESIS - 0x002a: 0x5c, # ASTERISK - 0x002b: 0x4e, # PLUS SIGN - 0x002c: 0x6b, # COMMA - 0x002d: 0x60, # HYPHEN-MINUS - 0x002e: 0x4b, # FULL STOP - 0x002f: 0x61, # SOLIDUS - 0x0030: 0xf0, # DIGIT ZERO - 0x0031: 0xf1, # DIGIT ONE - 0x0032: 0xf2, # DIGIT TWO - 0x0033: 0xf3, # DIGIT THREE - 0x0034: 0xf4, # DIGIT FOUR - 0x0035: 0xf5, # DIGIT FIVE - 0x0036: 0xf6, # DIGIT SIX - 0x0037: 0xf7, # DIGIT SEVEN - 0x0038: 0xf8, # DIGIT EIGHT - 0x0039: 0xf9, # DIGIT NINE - 0x003a: 0x7a, # COLON - 0x003b: 0x5e, # SEMICOLON - 0x003c: 0x4c, # LESS-THAN SIGN - 0x003d: 0x7e, # EQUALS SIGN - 0x003e: 0x6e, # GREATER-THAN SIGN - 0x003f: 0x6f, # QUESTION MARK - 0x0040: 0xae, # COMMERCIAL AT - 0x0041: 0xc1, # LATIN CAPITAL LETTER A - 0x0042: 0xc2, # LATIN CAPITAL LETTER B - 0x0043: 0xc3, # LATIN CAPITAL LETTER C - 0x0044: 0xc4, # LATIN CAPITAL LETTER D - 0x0045: 0xc5, # LATIN CAPITAL LETTER E - 0x0046: 0xc6, # LATIN CAPITAL LETTER F - 0x0047: 0xc7, # LATIN CAPITAL LETTER G - 0x0048: 0xc8, # LATIN CAPITAL LETTER H - 0x0049: 0xc9, # LATIN CAPITAL LETTER I - 0x004a: 0xd1, # LATIN CAPITAL LETTER J - 0x004b: 0xd2, # LATIN CAPITAL LETTER K - 0x004c: 0xd3, # LATIN CAPITAL LETTER L - 0x004d: 0xd4, # LATIN CAPITAL LETTER M - 0x004e: 0xd5, # LATIN CAPITAL LETTER N - 0x004f: 0xd6, # LATIN CAPITAL LETTER O - 0x0050: 0xd7, # LATIN CAPITAL LETTER P - 0x0051: 0xd8, # LATIN CAPITAL LETTER Q - 0x0052: 0xd9, # LATIN CAPITAL LETTER R - 0x0053: 0xe2, # LATIN CAPITAL LETTER S - 0x0054: 0xe3, # LATIN CAPITAL LETTER T - 0x0055: 0xe4, # LATIN CAPITAL LETTER U - 0x0056: 0xe5, # LATIN CAPITAL LETTER V - 0x0057: 0xe6, # LATIN CAPITAL LETTER W - 0x0058: 0xe7, # LATIN CAPITAL LETTER X - 0x0059: 0xe8, # LATIN CAPITAL LETTER Y - 0x005a: 0xe9, # LATIN CAPITAL LETTER Z - 0x005b: 0x68, # LEFT SQUARE BRACKET - 0x005c: 0xdc, # REVERSE SOLIDUS - 0x005d: 0xac, # RIGHT SQUARE BRACKET - 0x005e: 0x5f, # CIRCUMFLEX ACCENT - 0x005f: 0x6d, # LOW LINE - 0x0060: 0x8d, # GRAVE ACCENT + 0x0027: 0x7D, # APOSTROPHE + 0x0028: 0x4D, # LEFT PARENTHESIS + 0x0029: 0x5D, # RIGHT PARENTHESIS + 0x002A: 0x5C, # ASTERISK + 0x002B: 0x4E, # PLUS SIGN + 0x002C: 0x6B, # COMMA + 0x002D: 0x60, # HYPHEN-MINUS + 0x002E: 0x4B, # FULL STOP + 0x002F: 0x61, # SOLIDUS + 0x0030: 0xF0, # DIGIT ZERO + 0x0031: 0xF1, # DIGIT ONE + 0x0032: 0xF2, # DIGIT TWO + 0x0033: 0xF3, # DIGIT THREE + 0x0034: 0xF4, # DIGIT FOUR + 0x0035: 0xF5, # DIGIT FIVE + 0x0036: 0xF6, # DIGIT SIX + 0x0037: 0xF7, # DIGIT SEVEN + 0x0038: 0xF8, # DIGIT EIGHT + 0x0039: 0xF9, # DIGIT NINE + 0x003A: 0x7A, # COLON + 0x003B: 0x5E, # SEMICOLON + 0x003C: 0x4C, # LESS-THAN SIGN + 0x003D: 0x7E, # EQUALS SIGN + 0x003E: 0x6E, # GREATER-THAN SIGN + 0x003F: 0x6F, # QUESTION MARK + 0x0040: 0xAE, # COMMERCIAL AT + 0x0041: 0xC1, # LATIN CAPITAL LETTER A + 0x0042: 0xC2, # LATIN CAPITAL LETTER B + 0x0043: 0xC3, # LATIN CAPITAL LETTER C + 0x0044: 0xC4, # LATIN CAPITAL LETTER D + 0x0045: 0xC5, # LATIN CAPITAL LETTER E + 0x0046: 0xC6, # LATIN CAPITAL LETTER F + 0x0047: 0xC7, # LATIN CAPITAL LETTER G + 0x0048: 0xC8, # LATIN CAPITAL LETTER H + 0x0049: 0xC9, # LATIN CAPITAL LETTER I + 0x004A: 0xD1, # LATIN CAPITAL LETTER J + 0x004B: 0xD2, # LATIN CAPITAL LETTER K + 0x004C: 0xD3, # LATIN CAPITAL LETTER L + 0x004D: 0xD4, # LATIN CAPITAL LETTER M + 0x004E: 0xD5, # LATIN CAPITAL LETTER N + 0x004F: 0xD6, # LATIN CAPITAL LETTER O + 0x0050: 0xD7, # LATIN CAPITAL LETTER P + 0x0051: 0xD8, # LATIN CAPITAL LETTER Q + 0x0052: 0xD9, # LATIN CAPITAL LETTER R + 0x0053: 0xE2, # LATIN CAPITAL LETTER S + 0x0054: 0xE3, # LATIN CAPITAL LETTER T + 0x0055: 0xE4, # LATIN CAPITAL LETTER U + 0x0056: 0xE5, # LATIN CAPITAL LETTER V + 0x0057: 0xE6, # LATIN CAPITAL LETTER W + 0x0058: 0xE7, # LATIN CAPITAL LETTER X + 0x0059: 0xE8, # LATIN CAPITAL LETTER Y + 0x005A: 0xE9, # LATIN CAPITAL LETTER Z + 0x005B: 0x68, # LEFT SQUARE BRACKET + 0x005C: 0xDC, # REVERSE SOLIDUS + 0x005D: 0xAC, # RIGHT SQUARE BRACKET + 0x005E: 0x5F, # CIRCUMFLEX ACCENT + 0x005F: 0x6D, # LOW LINE + 0x0060: 0x8D, # GRAVE ACCENT 0x0061: 0x81, # LATIN SMALL LETTER A 0x0062: 0x82, # LATIN SMALL LETTER B 0x0063: 0x83, # LATIN SMALL LETTER C @@ -399,28 +399,28 @@ encoding_map = { 0x0067: 0x87, # LATIN SMALL LETTER G 0x0068: 0x88, # LATIN SMALL LETTER H 0x0069: 0x89, # LATIN SMALL LETTER I - 0x006a: 0x91, # LATIN SMALL LETTER J - 0x006b: 0x92, # LATIN SMALL LETTER K - 0x006c: 0x93, # LATIN SMALL LETTER L - 0x006d: 0x94, # LATIN SMALL LETTER M - 0x006e: 0x95, # LATIN SMALL LETTER N - 0x006f: 0x96, # LATIN SMALL LETTER O + 0x006A: 0x91, # LATIN SMALL LETTER J + 0x006B: 0x92, # LATIN SMALL LETTER K + 0x006C: 0x93, # LATIN SMALL LETTER L + 0x006D: 0x94, # LATIN SMALL LETTER M + 0x006E: 0x95, # LATIN SMALL LETTER N + 0x006F: 0x96, # LATIN SMALL LETTER O 0x0070: 0x97, # LATIN SMALL LETTER P 0x0071: 0x98, # LATIN SMALL LETTER Q 0x0072: 0x99, # LATIN SMALL LETTER R - 0x0073: 0xa2, # LATIN SMALL LETTER S - 0x0074: 0xa3, # LATIN SMALL LETTER T - 0x0075: 0xa4, # LATIN SMALL LETTER U - 0x0076: 0xa5, # LATIN SMALL LETTER V - 0x0077: 0xa6, # LATIN SMALL LETTER W - 0x0078: 0xa7, # LATIN SMALL LETTER X - 0x0079: 0xa8, # LATIN SMALL LETTER Y - 0x007a: 0xa9, # LATIN SMALL LETTER Z - 0x007b: 0x48, # LEFT CURLY BRACKET - 0x007c: 0xbb, # VERTICAL LINE - 0x007d: 0x8c, # RIGHT CURLY BRACKET - 0x007e: 0xcc, # TILDE - 0x007f: 0x07, # DELETE + 0x0073: 0xA2, # LATIN SMALL LETTER S + 0x0074: 0xA3, # LATIN SMALL LETTER T + 0x0075: 0xA4, # LATIN SMALL LETTER U + 0x0076: 0xA5, # LATIN SMALL LETTER V + 0x0077: 0xA6, # LATIN SMALL LETTER W + 0x0078: 0xA7, # LATIN SMALL LETTER X + 0x0079: 0xA8, # LATIN SMALL LETTER Y + 0x007A: 0xA9, # LATIN SMALL LETTER Z + 0x007B: 0x48, # LEFT CURLY BRACKET + 0x007C: 0xBB, # VERTICAL LINE + 0x007D: 0x8C, # RIGHT CURLY BRACKET + 0x007E: 0xCC, # TILDE + 0x007F: 0x07, # DELETE 0x0080: 0x20, # CONTROL 0x0081: 0x21, # CONTROL 0x0082: 0x22, # CONTROL @@ -431,15 +431,15 @@ encoding_map = { 0x0087: 0x17, # CONTROL 0x0088: 0x28, # CONTROL 0x0089: 0x29, # CONTROL - 0x008a: 0x2a, # CONTROL - 0x008b: 0x2b, # CONTROL - 0x008c: 0x2c, # CONTROL - 0x008d: 0x09, # CONTROL - 0x008e: 0x0a, # CONTROL - 0x008f: 0x1b, # CONTROL + 0x008A: 0x2A, # CONTROL + 0x008B: 0x2B, # CONTROL + 0x008C: 0x2C, # CONTROL + 0x008D: 0x09, # CONTROL + 0x008E: 0x0A, # CONTROL + 0x008F: 0x1B, # CONTROL 0x0090: 0x30, # CONTROL 0x0091: 0x31, # CONTROL - 0x0092: 0x1a, # CONTROL + 0x0092: 0x1A, # CONTROL 0x0093: 0x33, # CONTROL 0x0094: 0x34, # CONTROL 0x0095: 0x35, # CONTROL @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x08, # CONTROL 0x0098: 0x38, # CONTROL 0x0099: 0x39, # CONTROL - 0x009a: 0x3a, # CONTROL - 0x009b: 0x3b, # CONTROL - 0x009c: 0x04, # CONTROL - 0x009d: 0x14, # CONTROL - 0x009e: 0x3e, # CONTROL - 0x009f: 0xff, # CONTROL - 0x00a0: 0x41, # NO-BREAK SPACE - 0x00a1: 0xaa, # INVERTED EXCLAMATION MARK - 0x00a2: 0xb0, # CENT SIGN - 0x00a3: 0xb1, # POUND SIGN - 0x00a4: 0x9f, # CURRENCY SIGN - 0x00a5: 0xb2, # YEN SIGN - 0x00a6: 0x8e, # BROKEN BAR - 0x00a7: 0xb5, # SECTION SIGN - 0x00a8: 0xbd, # DIAERESIS - 0x00a9: 0xb4, # COPYRIGHT SIGN - 0x00aa: 0x9a, # FEMININE ORDINAL INDICATOR - 0x00ab: 0x8a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xba, # NOT SIGN - 0x00ad: 0xca, # SOFT HYPHEN - 0x00ae: 0xaf, # REGISTERED SIGN - 0x00af: 0xbc, # MACRON - 0x00b0: 0x90, # DEGREE SIGN - 0x00b1: 0x8f, # PLUS-MINUS SIGN - 0x00b2: 0xea, # SUPERSCRIPT TWO - 0x00b3: 0xfa, # SUPERSCRIPT THREE - 0x00b4: 0xbe, # ACUTE ACCENT - 0x00b5: 0xa0, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb3, # MIDDLE DOT - 0x00b8: 0x9d, # CEDILLA - 0x00b9: 0xda, # SUPERSCRIPT ONE - 0x00ba: 0x9b, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0x8b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xb7, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xb8, # VULGAR FRACTION ONE HALF - 0x00be: 0xb9, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xab, # INVERTED QUESTION MARK - 0x00c0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0x9e, # LATIN CAPITAL LIGATURE AE - 0x00c7: 0x4a, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xed, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xeb, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xef, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0x7b, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xbf, # MULTIPLICATION SIGN - 0x00d8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xfd, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xfe, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xfb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0x7f, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) - 0x00e0: 0x44, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x45, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x46, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0x9c, # LATIN SMALL LIGATURE AE - 0x00e7: 0xc0, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x54, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x51, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x58, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x55, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0x49, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xcd, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xce, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xcb, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xcf, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xa1, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xe1, # DIVISION SIGN - 0x00f8: 0x70, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xdd, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xde, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xdb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xe0, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xdf, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x011e: 0x5a, # LATIN CAPITAL LETTER G WITH BREVE - 0x011f: 0xd0, # LATIN SMALL LETTER G WITH BREVE - 0x0130: 0x5b, # LATIN CAPITAL LETTER I WITH DOT ABOVE + 0x009A: 0x3A, # CONTROL + 0x009B: 0x3B, # CONTROL + 0x009C: 0x04, # CONTROL + 0x009D: 0x14, # CONTROL + 0x009E: 0x3E, # CONTROL + 0x009F: 0xFF, # CONTROL + 0x00A0: 0x41, # NO-BREAK SPACE + 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK + 0x00A2: 0xB0, # CENT SIGN + 0x00A3: 0xB1, # POUND SIGN + 0x00A4: 0x9F, # CURRENCY SIGN + 0x00A5: 0xB2, # YEN SIGN + 0x00A6: 0x8E, # BROKEN BAR + 0x00A7: 0xB5, # SECTION SIGN + 0x00A8: 0xBD, # DIAERESIS + 0x00A9: 0xB4, # COPYRIGHT SIGN + 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR + 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xBA, # NOT SIGN + 0x00AD: 0xCA, # SOFT HYPHEN + 0x00AE: 0xAF, # REGISTERED SIGN + 0x00AF: 0xBC, # MACRON + 0x00B0: 0x90, # DEGREE SIGN + 0x00B1: 0x8F, # PLUS-MINUS SIGN + 0x00B2: 0xEA, # SUPERSCRIPT TWO + 0x00B3: 0xFA, # SUPERSCRIPT THREE + 0x00B4: 0xBE, # ACUTE ACCENT + 0x00B5: 0xA0, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB3, # MIDDLE DOT + 0x00B8: 0x9D, # CEDILLA + 0x00B9: 0xDA, # SUPERSCRIPT ONE + 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF + 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xAB, # INVERTED QUESTION MARK + 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE + 0x00C7: 0x4A, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0x7B, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xBF, # MULTIPLICATION SIGN + 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0x7F, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE + 0x00E7: 0xC0, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xA1, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xE1, # DIVISION SIGN + 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xE0, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x011E: 0x5A, # LATIN CAPITAL LETTER G WITH BREVE + 0x011F: 0xD0, # LATIN SMALL LETTER G WITH BREVE + 0x0130: 0x5B, # LATIN CAPITAL LETTER I WITH DOT ABOVE 0x0131: 0x79, # LATIN SMALL LETTER DOTLESS I - 0x015e: 0x7c, # LATIN CAPITAL LETTER S WITH CEDILLA - 0x015f: 0x6a, # LATIN SMALL LETTER S WITH CEDILLA -} \ No newline at end of file + 0x015E: 0x7C, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015F: 0x6A, # LATIN SMALL LETTER S WITH CEDILLA +} + diff --git a/Lib/encodings/cp1140.py b/Lib/encodings/cp1140.py index 7267507..a3c5cb9 100644 --- a/Lib/encodings/cp1140.py +++ b/Lib/encodings/cp1140.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL - u'\x8e' # 0x0a -> CONTROL - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\x8e' # 0x0A -> CONTROL + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x92' # 0x1a -> CONTROL - u'\x8f' # 0x1b -> CONTROL - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x92' # 0x1A -> CONTROL + u'\x8f' # 0x1B -> CONTROL + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL @@ -74,12 +74,12 @@ decoding_table = ( u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL - u'\x8a' # 0x2a -> CONTROL - u'\x8b' # 0x2b -> CONTROL - u'\x8c' # 0x2c -> CONTROL - u'\x05' # 0x2d -> ENQUIRY - u'\x06' # 0x2e -> ACKNOWLEDGE - u'\x07' # 0x2f -> BELL + u'\x8a' # 0x2A -> CONTROL + u'\x8b' # 0x2B -> CONTROL + u'\x8c' # 0x2C -> CONTROL + u'\x05' # 0x2D -> ENQUIRY + u'\x06' # 0x2E -> ACKNOWLEDGE + u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE @@ -90,12 +90,12 @@ decoding_table = ( u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL - u'\x9a' # 0x3a -> CONTROL - u'\x9b' # 0x3b -> CONTROL - u'\x14' # 0x3c -> DEVICE CONTROL FOUR - u'\x15' # 0x3d -> NEGATIVE ACKNOWLEDGE - u'\x9e' # 0x3e -> CONTROL - u'\x1a' # 0x3f -> SUBSTITUTE + u'\x9a' # 0x3A -> CONTROL + u'\x9b' # 0x3B -> CONTROL + u'\x14' # 0x3C -> DEVICE CONTROL FOUR + u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + u'\x9e' # 0x3E -> CONTROL + u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX @@ -106,12 +106,12 @@ decoding_table = ( u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE - u'\xa2' # 0x4a -> CENT SIGN - u'.' # 0x4b -> FULL STOP - u'<' # 0x4c -> LESS-THAN SIGN - u'(' # 0x4d -> LEFT PARENTHESIS - u'+' # 0x4e -> PLUS SIGN - u'|' # 0x4f -> VERTICAL LINE + u'\xa2' # 0x4A -> CENT SIGN + u'.' # 0x4B -> FULL STOP + u'<' # 0x4C -> LESS-THAN SIGN + u'(' # 0x4D -> LEFT PARENTHESIS + u'+' # 0x4E -> PLUS SIGN + u'|' # 0x4F -> VERTICAL LINE u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX @@ -122,12 +122,12 @@ decoding_table = ( u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) - u'!' # 0x5a -> EXCLAMATION MARK - u'$' # 0x5b -> DOLLAR SIGN - u'*' # 0x5c -> ASTERISK - u')' # 0x5d -> RIGHT PARENTHESIS - u';' # 0x5e -> SEMICOLON - u'\xac' # 0x5f -> NOT SIGN + u'!' # 0x5A -> EXCLAMATION MARK + u'$' # 0x5B -> DOLLAR SIGN + u'*' # 0x5C -> ASTERISK + u')' # 0x5D -> RIGHT PARENTHESIS + u';' # 0x5E -> SEMICOLON + u'\xac' # 0x5F -> NOT SIGN u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX @@ -138,12 +138,12 @@ decoding_table = ( u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xa6' # 0x6a -> BROKEN BAR - u',' # 0x6b -> COMMA - u'%' # 0x6c -> PERCENT SIGN - u'_' # 0x6d -> LOW LINE - u'>' # 0x6e -> GREATER-THAN SIGN - u'?' # 0x6f -> QUESTION MARK + u'\xa6' # 0x6A -> BROKEN BAR + u',' # 0x6B -> COMMA + u'%' # 0x6C -> PERCENT SIGN + u'_' # 0x6D -> LOW LINE + u'>' # 0x6E -> GREATER-THAN SIGN + u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX @@ -154,12 +154,12 @@ decoding_table = ( u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'`' # 0x79 -> GRAVE ACCENT - u':' # 0x7a -> COLON - u'#' # 0x7b -> NUMBER SIGN - u'@' # 0x7c -> COMMERCIAL AT - u"'" # 0x7d -> APOSTROPHE - u'=' # 0x7e -> EQUALS SIGN - u'"' # 0x7f -> QUOTATION MARK + u':' # 0x7A -> COLON + u'#' # 0x7B -> NUMBER SIGN + u'@' # 0x7C -> COMMERCIAL AT + u"'" # 0x7D -> APOSTROPHE + u'=' # 0x7E -> EQUALS SIGN + u'"' # 0x7F -> QUOTATION MARK u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B @@ -170,12 +170,12 @@ decoding_table = ( u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I - u'\xab' # 0x8a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0x8b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xf0' # 0x8c -> LATIN SMALL LETTER ETH (ICELANDIC) - u'\xfd' # 0x8d -> LATIN SMALL LETTER Y WITH ACUTE - u'\xfe' # 0x8e -> LATIN SMALL LETTER THORN (ICELANDIC) - u'\xb1' # 0x8f -> PLUS-MINUS SIGN + u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) + u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE + u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) + u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K @@ -186,108 +186,108 @@ decoding_table = ( u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R - u'\xaa' # 0x9a -> FEMININE ORDINAL INDICATOR - u'\xba' # 0x9b -> MASCULINE ORDINAL INDICATOR - u'\xe6' # 0x9c -> LATIN SMALL LIGATURE AE - u'\xb8' # 0x9d -> CEDILLA - u'\xc6' # 0x9e -> LATIN CAPITAL LIGATURE AE - u'\u20ac' # 0x9f -> EURO SIGN - u'\xb5' # 0xa0 -> MICRO SIGN - u'~' # 0xa1 -> TILDE - u's' # 0xa2 -> LATIN SMALL LETTER S - u't' # 0xa3 -> LATIN SMALL LETTER T - u'u' # 0xa4 -> LATIN SMALL LETTER U - u'v' # 0xa5 -> LATIN SMALL LETTER V - u'w' # 0xa6 -> LATIN SMALL LETTER W - u'x' # 0xa7 -> LATIN SMALL LETTER X - u'y' # 0xa8 -> LATIN SMALL LETTER Y - u'z' # 0xa9 -> LATIN SMALL LETTER Z - u'\xa1' # 0xaa -> INVERTED EXCLAMATION MARK - u'\xbf' # 0xab -> INVERTED QUESTION MARK - u'\xd0' # 0xac -> LATIN CAPITAL LETTER ETH (ICELANDIC) - u'\xdd' # 0xad -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xde' # 0xae -> LATIN CAPITAL LETTER THORN (ICELANDIC) - u'\xae' # 0xaf -> REGISTERED SIGN - u'^' # 0xb0 -> CIRCUMFLEX ACCENT - u'\xa3' # 0xb1 -> POUND SIGN - u'\xa5' # 0xb2 -> YEN SIGN - u'\xb7' # 0xb3 -> MIDDLE DOT - u'\xa9' # 0xb4 -> COPYRIGHT SIGN - u'\xa7' # 0xb5 -> SECTION SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xbc' # 0xb7 -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xb8 -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xb9 -> VULGAR FRACTION THREE QUARTERS - u'[' # 0xba -> LEFT SQUARE BRACKET - u']' # 0xbb -> RIGHT SQUARE BRACKET - u'\xaf' # 0xbc -> MACRON - u'\xa8' # 0xbd -> DIAERESIS - u'\xb4' # 0xbe -> ACUTE ACCENT - u'\xd7' # 0xbf -> MULTIPLICATION SIGN - u'{' # 0xc0 -> LEFT CURLY BRACKET - u'A' # 0xc1 -> LATIN CAPITAL LETTER A - u'B' # 0xc2 -> LATIN CAPITAL LETTER B - u'C' # 0xc3 -> LATIN CAPITAL LETTER C - u'D' # 0xc4 -> LATIN CAPITAL LETTER D - u'E' # 0xc5 -> LATIN CAPITAL LETTER E - u'F' # 0xc6 -> LATIN CAPITAL LETTER F - u'G' # 0xc7 -> LATIN CAPITAL LETTER G - u'H' # 0xc8 -> LATIN CAPITAL LETTER H - u'I' # 0xc9 -> LATIN CAPITAL LETTER I - u'\xad' # 0xca -> SOFT HYPHEN - u'\xf4' # 0xcb -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0xcc -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf2' # 0xcd -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xce -> LATIN SMALL LETTER O WITH ACUTE - u'\xf5' # 0xcf -> LATIN SMALL LETTER O WITH TILDE - u'}' # 0xd0 -> RIGHT CURLY BRACKET - u'J' # 0xd1 -> LATIN CAPITAL LETTER J - u'K' # 0xd2 -> LATIN CAPITAL LETTER K - u'L' # 0xd3 -> LATIN CAPITAL LETTER L - u'M' # 0xd4 -> LATIN CAPITAL LETTER M - u'N' # 0xd5 -> LATIN CAPITAL LETTER N - u'O' # 0xd6 -> LATIN CAPITAL LETTER O - u'P' # 0xd7 -> LATIN CAPITAL LETTER P - u'Q' # 0xd8 -> LATIN CAPITAL LETTER Q - u'R' # 0xd9 -> LATIN CAPITAL LETTER R - u'\xb9' # 0xda -> SUPERSCRIPT ONE - u'\xfb' # 0xdb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xdc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xf9' # 0xdd -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xde -> LATIN SMALL LETTER U WITH ACUTE - u'\xff' # 0xdf -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\\' # 0xe0 -> REVERSE SOLIDUS - u'\xf7' # 0xe1 -> DIVISION SIGN - u'S' # 0xe2 -> LATIN CAPITAL LETTER S - u'T' # 0xe3 -> LATIN CAPITAL LETTER T - u'U' # 0xe4 -> LATIN CAPITAL LETTER U - u'V' # 0xe5 -> LATIN CAPITAL LETTER V - u'W' # 0xe6 -> LATIN CAPITAL LETTER W - u'X' # 0xe7 -> LATIN CAPITAL LETTER X - u'Y' # 0xe8 -> LATIN CAPITAL LETTER Y - u'Z' # 0xe9 -> LATIN CAPITAL LETTER Z - u'\xb2' # 0xea -> SUPERSCRIPT TWO - u'\xd4' # 0xeb -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd6' # 0xec -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd2' # 0xed -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd5' # 0xef -> LATIN CAPITAL LETTER O WITH TILDE - u'0' # 0xf0 -> DIGIT ZERO - u'1' # 0xf1 -> DIGIT ONE - u'2' # 0xf2 -> DIGIT TWO - u'3' # 0xf3 -> DIGIT THREE - u'4' # 0xf4 -> DIGIT FOUR - u'5' # 0xf5 -> DIGIT FIVE - u'6' # 0xf6 -> DIGIT SIX - u'7' # 0xf7 -> DIGIT SEVEN - u'8' # 0xf8 -> DIGIT EIGHT - u'9' # 0xf9 -> DIGIT NINE - u'\xb3' # 0xfa -> SUPERSCRIPT THREE - u'\xdb' # 0xfb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xfc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xd9' # 0xfd -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xfe -> LATIN CAPITAL LETTER U WITH ACUTE - u'\x9f' # 0xff -> CONTROL + u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + u'\xb8' # 0x9D -> CEDILLA + u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + u'\u20ac' # 0x9F -> EURO SIGN + u'\xb5' # 0xA0 -> MICRO SIGN + u'~' # 0xA1 -> TILDE + u's' # 0xA2 -> LATIN SMALL LETTER S + u't' # 0xA3 -> LATIN SMALL LETTER T + u'u' # 0xA4 -> LATIN SMALL LETTER U + u'v' # 0xA5 -> LATIN SMALL LETTER V + u'w' # 0xA6 -> LATIN SMALL LETTER W + u'x' # 0xA7 -> LATIN SMALL LETTER X + u'y' # 0xA8 -> LATIN SMALL LETTER Y + u'z' # 0xA9 -> LATIN SMALL LETTER Z + u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + u'\xbf' # 0xAB -> INVERTED QUESTION MARK + u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) + u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) + u'\xae' # 0xAF -> REGISTERED SIGN + u'^' # 0xB0 -> CIRCUMFLEX ACCENT + u'\xa3' # 0xB1 -> POUND SIGN + u'\xa5' # 0xB2 -> YEN SIGN + u'\xb7' # 0xB3 -> MIDDLE DOT + u'\xa9' # 0xB4 -> COPYRIGHT SIGN + u'\xa7' # 0xB5 -> SECTION SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + u'[' # 0xBA -> LEFT SQUARE BRACKET + u']' # 0xBB -> RIGHT SQUARE BRACKET + u'\xaf' # 0xBC -> MACRON + u'\xa8' # 0xBD -> DIAERESIS + u'\xb4' # 0xBE -> ACUTE ACCENT + u'\xd7' # 0xBF -> MULTIPLICATION SIGN + u'{' # 0xC0 -> LEFT CURLY BRACKET + u'A' # 0xC1 -> LATIN CAPITAL LETTER A + u'B' # 0xC2 -> LATIN CAPITAL LETTER B + u'C' # 0xC3 -> LATIN CAPITAL LETTER C + u'D' # 0xC4 -> LATIN CAPITAL LETTER D + u'E' # 0xC5 -> LATIN CAPITAL LETTER E + u'F' # 0xC6 -> LATIN CAPITAL LETTER F + u'G' # 0xC7 -> LATIN CAPITAL LETTER G + u'H' # 0xC8 -> LATIN CAPITAL LETTER H + u'I' # 0xC9 -> LATIN CAPITAL LETTER I + u'\xad' # 0xCA -> SOFT HYPHEN + u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + u'}' # 0xD0 -> RIGHT CURLY BRACKET + u'J' # 0xD1 -> LATIN CAPITAL LETTER J + u'K' # 0xD2 -> LATIN CAPITAL LETTER K + u'L' # 0xD3 -> LATIN CAPITAL LETTER L + u'M' # 0xD4 -> LATIN CAPITAL LETTER M + u'N' # 0xD5 -> LATIN CAPITAL LETTER N + u'O' # 0xD6 -> LATIN CAPITAL LETTER O + u'P' # 0xD7 -> LATIN CAPITAL LETTER P + u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + u'R' # 0xD9 -> LATIN CAPITAL LETTER R + u'\xb9' # 0xDA -> SUPERSCRIPT ONE + u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\\' # 0xE0 -> REVERSE SOLIDUS + u'\xf7' # 0xE1 -> DIVISION SIGN + u'S' # 0xE2 -> LATIN CAPITAL LETTER S + u'T' # 0xE3 -> LATIN CAPITAL LETTER T + u'U' # 0xE4 -> LATIN CAPITAL LETTER U + u'V' # 0xE5 -> LATIN CAPITAL LETTER V + u'W' # 0xE6 -> LATIN CAPITAL LETTER W + u'X' # 0xE7 -> LATIN CAPITAL LETTER X + u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + u'\xb2' # 0xEA -> SUPERSCRIPT TWO + u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + u'0' # 0xF0 -> DIGIT ZERO + u'1' # 0xF1 -> DIGIT ONE + u'2' # 0xF2 -> DIGIT TWO + u'3' # 0xF3 -> DIGIT THREE + u'4' # 0xF4 -> DIGIT FOUR + u'5' # 0xF5 -> DIGIT FIVE + u'6' # 0xF6 -> DIGIT SIX + u'7' # 0xF7 -> DIGIT SEVEN + u'8' # 0xF8 -> DIGIT EIGHT + u'9' # 0xF9 -> DIGIT NINE + u'\xb3' # 0xFA -> SUPERSCRIPT THREE + u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + u'\x9f' # 0xFF -> CONTROL ) ### Encoding Map @@ -298,97 +298,97 @@ encoding_map = { 0x0002: 0x02, # START OF TEXT 0x0003: 0x03, # END OF TEXT 0x0004: 0x37, # END OF TRANSMISSION - 0x0005: 0x2d, # ENQUIRY - 0x0006: 0x2e, # ACKNOWLEDGE - 0x0007: 0x2f, # BELL + 0x0005: 0x2D, # ENQUIRY + 0x0006: 0x2E, # ACKNOWLEDGE + 0x0007: 0x2F, # BELL 0x0008: 0x16, # BACKSPACE 0x0009: 0x05, # HORIZONTAL TABULATION - 0x000a: 0x25, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x25, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO 0x0013: 0x13, # DEVICE CONTROL THREE - 0x0014: 0x3c, # DEVICE CONTROL FOUR - 0x0015: 0x3d, # NEGATIVE ACKNOWLEDGE + 0x0014: 0x3C, # DEVICE CONTROL FOUR + 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE 0x0016: 0x32, # SYNCHRONOUS IDLE 0x0017: 0x26, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x3f, # SUBSTITUTE - 0x001b: 0x27, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x3F, # SUBSTITUTE + 0x001B: 0x27, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x40, # SPACE - 0x0021: 0x5a, # EXCLAMATION MARK - 0x0022: 0x7f, # QUOTATION MARK - 0x0023: 0x7b, # NUMBER SIGN - 0x0024: 0x5b, # DOLLAR SIGN - 0x0025: 0x6c, # PERCENT SIGN + 0x0021: 0x5A, # EXCLAMATION MARK + 0x0022: 0x7F, # QUOTATION MARK + 0x0023: 0x7B, # NUMBER SIGN + 0x0024: 0x5B, # DOLLAR SIGN + 0x0025: 0x6C, # PERCENT SIGN 0x0026: 0x50, # AMPERSAND - 0x0027: 0x7d, # APOSTROPHE - 0x0028: 0x4d, # LEFT PARENTHESIS - 0x0029: 0x5d, # RIGHT PARENTHESIS - 0x002a: 0x5c, # ASTERISK - 0x002b: 0x4e, # PLUS SIGN - 0x002c: 0x6b, # COMMA - 0x002d: 0x60, # HYPHEN-MINUS - 0x002e: 0x4b, # FULL STOP - 0x002f: 0x61, # SOLIDUS - 0x0030: 0xf0, # DIGIT ZERO - 0x0031: 0xf1, # DIGIT ONE - 0x0032: 0xf2, # DIGIT TWO - 0x0033: 0xf3, # DIGIT THREE - 0x0034: 0xf4, # DIGIT FOUR - 0x0035: 0xf5, # DIGIT FIVE - 0x0036: 0xf6, # DIGIT SIX - 0x0037: 0xf7, # DIGIT SEVEN - 0x0038: 0xf8, # DIGIT EIGHT - 0x0039: 0xf9, # DIGIT NINE - 0x003a: 0x7a, # COLON - 0x003b: 0x5e, # SEMICOLON - 0x003c: 0x4c, # LESS-THAN SIGN - 0x003d: 0x7e, # EQUALS SIGN - 0x003e: 0x6e, # GREATER-THAN SIGN - 0x003f: 0x6f, # QUESTION MARK - 0x0040: 0x7c, # COMMERCIAL AT - 0x0041: 0xc1, # LATIN CAPITAL LETTER A - 0x0042: 0xc2, # LATIN CAPITAL LETTER B - 0x0043: 0xc3, # LATIN CAPITAL LETTER C - 0x0044: 0xc4, # LATIN CAPITAL LETTER D - 0x0045: 0xc5, # LATIN CAPITAL LETTER E - 0x0046: 0xc6, # LATIN CAPITAL LETTER F - 0x0047: 0xc7, # LATIN CAPITAL LETTER G - 0x0048: 0xc8, # LATIN CAPITAL LETTER H - 0x0049: 0xc9, # LATIN CAPITAL LETTER I - 0x004a: 0xd1, # LATIN CAPITAL LETTER J - 0x004b: 0xd2, # LATIN CAPITAL LETTER K - 0x004c: 0xd3, # LATIN CAPITAL LETTER L - 0x004d: 0xd4, # LATIN CAPITAL LETTER M - 0x004e: 0xd5, # LATIN CAPITAL LETTER N - 0x004f: 0xd6, # LATIN CAPITAL LETTER O - 0x0050: 0xd7, # LATIN CAPITAL LETTER P - 0x0051: 0xd8, # LATIN CAPITAL LETTER Q - 0x0052: 0xd9, # LATIN CAPITAL LETTER R - 0x0053: 0xe2, # LATIN CAPITAL LETTER S - 0x0054: 0xe3, # LATIN CAPITAL LETTER T - 0x0055: 0xe4, # LATIN CAPITAL LETTER U - 0x0056: 0xe5, # LATIN CAPITAL LETTER V - 0x0057: 0xe6, # LATIN CAPITAL LETTER W - 0x0058: 0xe7, # LATIN CAPITAL LETTER X - 0x0059: 0xe8, # LATIN CAPITAL LETTER Y - 0x005a: 0xe9, # LATIN CAPITAL LETTER Z - 0x005b: 0xba, # LEFT SQUARE BRACKET - 0x005c: 0xe0, # REVERSE SOLIDUS - 0x005d: 0xbb, # RIGHT SQUARE BRACKET - 0x005e: 0xb0, # CIRCUMFLEX ACCENT - 0x005f: 0x6d, # LOW LINE + 0x0027: 0x7D, # APOSTROPHE + 0x0028: 0x4D, # LEFT PARENTHESIS + 0x0029: 0x5D, # RIGHT PARENTHESIS + 0x002A: 0x5C, # ASTERISK + 0x002B: 0x4E, # PLUS SIGN + 0x002C: 0x6B, # COMMA + 0x002D: 0x60, # HYPHEN-MINUS + 0x002E: 0x4B, # FULL STOP + 0x002F: 0x61, # SOLIDUS + 0x0030: 0xF0, # DIGIT ZERO + 0x0031: 0xF1, # DIGIT ONE + 0x0032: 0xF2, # DIGIT TWO + 0x0033: 0xF3, # DIGIT THREE + 0x0034: 0xF4, # DIGIT FOUR + 0x0035: 0xF5, # DIGIT FIVE + 0x0036: 0xF6, # DIGIT SIX + 0x0037: 0xF7, # DIGIT SEVEN + 0x0038: 0xF8, # DIGIT EIGHT + 0x0039: 0xF9, # DIGIT NINE + 0x003A: 0x7A, # COLON + 0x003B: 0x5E, # SEMICOLON + 0x003C: 0x4C, # LESS-THAN SIGN + 0x003D: 0x7E, # EQUALS SIGN + 0x003E: 0x6E, # GREATER-THAN SIGN + 0x003F: 0x6F, # QUESTION MARK + 0x0040: 0x7C, # COMMERCIAL AT + 0x0041: 0xC1, # LATIN CAPITAL LETTER A + 0x0042: 0xC2, # LATIN CAPITAL LETTER B + 0x0043: 0xC3, # LATIN CAPITAL LETTER C + 0x0044: 0xC4, # LATIN CAPITAL LETTER D + 0x0045: 0xC5, # LATIN CAPITAL LETTER E + 0x0046: 0xC6, # LATIN CAPITAL LETTER F + 0x0047: 0xC7, # LATIN CAPITAL LETTER G + 0x0048: 0xC8, # LATIN CAPITAL LETTER H + 0x0049: 0xC9, # LATIN CAPITAL LETTER I + 0x004A: 0xD1, # LATIN CAPITAL LETTER J + 0x004B: 0xD2, # LATIN CAPITAL LETTER K + 0x004C: 0xD3, # LATIN CAPITAL LETTER L + 0x004D: 0xD4, # LATIN CAPITAL LETTER M + 0x004E: 0xD5, # LATIN CAPITAL LETTER N + 0x004F: 0xD6, # LATIN CAPITAL LETTER O + 0x0050: 0xD7, # LATIN CAPITAL LETTER P + 0x0051: 0xD8, # LATIN CAPITAL LETTER Q + 0x0052: 0xD9, # LATIN CAPITAL LETTER R + 0x0053: 0xE2, # LATIN CAPITAL LETTER S + 0x0054: 0xE3, # LATIN CAPITAL LETTER T + 0x0055: 0xE4, # LATIN CAPITAL LETTER U + 0x0056: 0xE5, # LATIN CAPITAL LETTER V + 0x0057: 0xE6, # LATIN CAPITAL LETTER W + 0x0058: 0xE7, # LATIN CAPITAL LETTER X + 0x0059: 0xE8, # LATIN CAPITAL LETTER Y + 0x005A: 0xE9, # LATIN CAPITAL LETTER Z + 0x005B: 0xBA, # LEFT SQUARE BRACKET + 0x005C: 0xE0, # REVERSE SOLIDUS + 0x005D: 0xBB, # RIGHT SQUARE BRACKET + 0x005E: 0xB0, # CIRCUMFLEX ACCENT + 0x005F: 0x6D, # LOW LINE 0x0060: 0x79, # GRAVE ACCENT 0x0061: 0x81, # LATIN SMALL LETTER A 0x0062: 0x82, # LATIN SMALL LETTER B @@ -399,28 +399,28 @@ encoding_map = { 0x0067: 0x87, # LATIN SMALL LETTER G 0x0068: 0x88, # LATIN SMALL LETTER H 0x0069: 0x89, # LATIN SMALL LETTER I - 0x006a: 0x91, # LATIN SMALL LETTER J - 0x006b: 0x92, # LATIN SMALL LETTER K - 0x006c: 0x93, # LATIN SMALL LETTER L - 0x006d: 0x94, # LATIN SMALL LETTER M - 0x006e: 0x95, # LATIN SMALL LETTER N - 0x006f: 0x96, # LATIN SMALL LETTER O + 0x006A: 0x91, # LATIN SMALL LETTER J + 0x006B: 0x92, # LATIN SMALL LETTER K + 0x006C: 0x93, # LATIN SMALL LETTER L + 0x006D: 0x94, # LATIN SMALL LETTER M + 0x006E: 0x95, # LATIN SMALL LETTER N + 0x006F: 0x96, # LATIN SMALL LETTER O 0x0070: 0x97, # LATIN SMALL LETTER P 0x0071: 0x98, # LATIN SMALL LETTER Q 0x0072: 0x99, # LATIN SMALL LETTER R - 0x0073: 0xa2, # LATIN SMALL LETTER S - 0x0074: 0xa3, # LATIN SMALL LETTER T - 0x0075: 0xa4, # LATIN SMALL LETTER U - 0x0076: 0xa5, # LATIN SMALL LETTER V - 0x0077: 0xa6, # LATIN SMALL LETTER W - 0x0078: 0xa7, # LATIN SMALL LETTER X - 0x0079: 0xa8, # LATIN SMALL LETTER Y - 0x007a: 0xa9, # LATIN SMALL LETTER Z - 0x007b: 0xc0, # LEFT CURLY BRACKET - 0x007c: 0x4f, # VERTICAL LINE - 0x007d: 0xd0, # RIGHT CURLY BRACKET - 0x007e: 0xa1, # TILDE - 0x007f: 0x07, # DELETE + 0x0073: 0xA2, # LATIN SMALL LETTER S + 0x0074: 0xA3, # LATIN SMALL LETTER T + 0x0075: 0xA4, # LATIN SMALL LETTER U + 0x0076: 0xA5, # LATIN SMALL LETTER V + 0x0077: 0xA6, # LATIN SMALL LETTER W + 0x0078: 0xA7, # LATIN SMALL LETTER X + 0x0079: 0xA8, # LATIN SMALL LETTER Y + 0x007A: 0xA9, # LATIN SMALL LETTER Z + 0x007B: 0xC0, # LEFT CURLY BRACKET + 0x007C: 0x4F, # VERTICAL LINE + 0x007D: 0xD0, # RIGHT CURLY BRACKET + 0x007E: 0xA1, # TILDE + 0x007F: 0x07, # DELETE 0x0080: 0x20, # CONTROL 0x0081: 0x21, # CONTROL 0x0082: 0x22, # CONTROL @@ -431,15 +431,15 @@ encoding_map = { 0x0087: 0x17, # CONTROL 0x0088: 0x28, # CONTROL 0x0089: 0x29, # CONTROL - 0x008a: 0x2a, # CONTROL - 0x008b: 0x2b, # CONTROL - 0x008c: 0x2c, # CONTROL - 0x008d: 0x09, # CONTROL - 0x008e: 0x0a, # CONTROL - 0x008f: 0x1b, # CONTROL + 0x008A: 0x2A, # CONTROL + 0x008B: 0x2B, # CONTROL + 0x008C: 0x2C, # CONTROL + 0x008D: 0x09, # CONTROL + 0x008E: 0x0A, # CONTROL + 0x008F: 0x1B, # CONTROL 0x0090: 0x30, # CONTROL 0x0091: 0x31, # CONTROL - 0x0092: 0x1a, # CONTROL + 0x0092: 0x1A, # CONTROL 0x0093: 0x33, # CONTROL 0x0094: 0x34, # CONTROL 0x0095: 0x35, # CONTROL @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x08, # CONTROL 0x0098: 0x38, # CONTROL 0x0099: 0x39, # CONTROL - 0x009a: 0x3a, # CONTROL - 0x009b: 0x3b, # CONTROL - 0x009c: 0x04, # CONTROL - 0x009d: 0x14, # CONTROL - 0x009e: 0x3e, # CONTROL - 0x009f: 0xff, # CONTROL - 0x00a0: 0x41, # NO-BREAK SPACE - 0x00a1: 0xaa, # INVERTED EXCLAMATION MARK - 0x00a2: 0x4a, # CENT SIGN - 0x00a3: 0xb1, # POUND SIGN - 0x00a5: 0xb2, # YEN SIGN - 0x00a6: 0x6a, # BROKEN BAR - 0x00a7: 0xb5, # SECTION SIGN - 0x00a8: 0xbd, # DIAERESIS - 0x00a9: 0xb4, # COPYRIGHT SIGN - 0x00aa: 0x9a, # FEMININE ORDINAL INDICATOR - 0x00ab: 0x8a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0x5f, # NOT SIGN - 0x00ad: 0xca, # SOFT HYPHEN - 0x00ae: 0xaf, # REGISTERED SIGN - 0x00af: 0xbc, # MACRON - 0x00b0: 0x90, # DEGREE SIGN - 0x00b1: 0x8f, # PLUS-MINUS SIGN - 0x00b2: 0xea, # SUPERSCRIPT TWO - 0x00b3: 0xfa, # SUPERSCRIPT THREE - 0x00b4: 0xbe, # ACUTE ACCENT - 0x00b5: 0xa0, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb3, # MIDDLE DOT - 0x00b8: 0x9d, # CEDILLA - 0x00b9: 0xda, # SUPERSCRIPT ONE - 0x00ba: 0x9b, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0x8b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xb7, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xb8, # VULGAR FRACTION ONE HALF - 0x00be: 0xb9, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xab, # INVERTED QUESTION MARK - 0x00c0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0x9e, # LATIN CAPITAL LIGATURE AE - 0x00c7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xac, # LATIN CAPITAL LETTER ETH (ICELANDIC) - 0x00d1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xed, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xeb, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xef, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xec, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xbf, # MULTIPLICATION SIGN - 0x00d8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xfd, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xfe, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xfb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xfc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xad, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xae, # LATIN CAPITAL LETTER THORN (ICELANDIC) - 0x00df: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) - 0x00e0: 0x44, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x45, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x46, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0x9c, # LATIN SMALL LIGATURE AE - 0x00e7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x54, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x51, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x58, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x55, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0x8c, # LATIN SMALL LETTER ETH (ICELANDIC) - 0x00f1: 0x49, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xcd, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xce, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xcb, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xcf, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xcc, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xe1, # DIVISION SIGN - 0x00f8: 0x70, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xdd, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xde, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xdb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xdc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0x8d, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0x8e, # LATIN SMALL LETTER THORN (ICELANDIC) - 0x00ff: 0xdf, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x20ac: 0x9f, # EURO SIGN -} \ No newline at end of file + 0x009A: 0x3A, # CONTROL + 0x009B: 0x3B, # CONTROL + 0x009C: 0x04, # CONTROL + 0x009D: 0x14, # CONTROL + 0x009E: 0x3E, # CONTROL + 0x009F: 0xFF, # CONTROL + 0x00A0: 0x41, # NO-BREAK SPACE + 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK + 0x00A2: 0x4A, # CENT SIGN + 0x00A3: 0xB1, # POUND SIGN + 0x00A5: 0xB2, # YEN SIGN + 0x00A6: 0x6A, # BROKEN BAR + 0x00A7: 0xB5, # SECTION SIGN + 0x00A8: 0xBD, # DIAERESIS + 0x00A9: 0xB4, # COPYRIGHT SIGN + 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR + 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0x5F, # NOT SIGN + 0x00AD: 0xCA, # SOFT HYPHEN + 0x00AE: 0xAF, # REGISTERED SIGN + 0x00AF: 0xBC, # MACRON + 0x00B0: 0x90, # DEGREE SIGN + 0x00B1: 0x8F, # PLUS-MINUS SIGN + 0x00B2: 0xEA, # SUPERSCRIPT TWO + 0x00B3: 0xFA, # SUPERSCRIPT THREE + 0x00B4: 0xBE, # ACUTE ACCENT + 0x00B5: 0xA0, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB3, # MIDDLE DOT + 0x00B8: 0x9D, # CEDILLA + 0x00B9: 0xDA, # SUPERSCRIPT ONE + 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF + 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xAB, # INVERTED QUESTION MARK + 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE + 0x00C7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xAC, # LATIN CAPITAL LETTER ETH (ICELANDIC) + 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xEC, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xBF, # MULTIPLICATION SIGN + 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xFC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xAD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xAE, # LATIN CAPITAL LETTER THORN (ICELANDIC) + 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE + 0x00E7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0x8C, # LATIN SMALL LETTER ETH (ICELANDIC) + 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xCC, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xE1, # DIVISION SIGN + 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xDC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0x8D, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0x8E, # LATIN SMALL LETTER THORN (ICELANDIC) + 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x20AC: 0x9F, # EURO SIGN +} + diff --git a/Lib/encodings/cp1250.py b/Lib/encodings/cp1250.py index 3068d1d..3aa78a8 100644 --- a/Lib/encodings/cp1250.py +++ b/Lib/encodings/cp1250.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\ufffe' # 0x88 -> UNDEFINED u'\u2030' # 0x89 -> PER MILLE SIGN - u'\u0160' # 0x8a -> LATIN CAPITAL LETTER S WITH CARON - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u015a' # 0x8c -> LATIN CAPITAL LETTER S WITH ACUTE - u'\u0164' # 0x8d -> LATIN CAPITAL LETTER T WITH CARON - u'\u017d' # 0x8e -> LATIN CAPITAL LETTER Z WITH CARON - u'\u0179' # 0x8f -> LATIN CAPITAL LETTER Z WITH ACUTE + u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u015a' # 0x8C -> LATIN CAPITAL LETTER S WITH ACUTE + u'\u0164' # 0x8D -> LATIN CAPITAL LETTER T WITH CARON + u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON + u'\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\u0161' # 0x9a -> LATIN SMALL LETTER S WITH CARON - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u015b' # 0x9c -> LATIN SMALL LETTER S WITH ACUTE - u'\u0165' # 0x9d -> LATIN SMALL LETTER T WITH CARON - u'\u017e' # 0x9e -> LATIN SMALL LETTER Z WITH CARON - u'\u017a' # 0x9f -> LATIN SMALL LETTER Z WITH ACUTE - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u02c7' # 0xa1 -> CARON - u'\u02d8' # 0xa2 -> BREVE - u'\u0141' # 0xa3 -> LATIN CAPITAL LETTER L WITH STROKE - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\u0104' # 0xa5 -> LATIN CAPITAL LETTER A WITH OGONEK - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u015e' # 0xaa -> LATIN CAPITAL LETTER S WITH CEDILLA - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\u017b' # 0xaf -> LATIN CAPITAL LETTER Z WITH DOT ABOVE - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u02db' # 0xb2 -> OGONEK - u'\u0142' # 0xb3 -> LATIN SMALL LETTER L WITH STROKE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\u0105' # 0xb9 -> LATIN SMALL LETTER A WITH OGONEK - u'\u015f' # 0xba -> LATIN SMALL LETTER S WITH CEDILLA - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u013d' # 0xbc -> LATIN CAPITAL LETTER L WITH CARON - u'\u02dd' # 0xbd -> DOUBLE ACUTE ACCENT - u'\u013e' # 0xbe -> LATIN SMALL LETTER L WITH CARON - u'\u017c' # 0xbf -> LATIN SMALL LETTER Z WITH DOT ABOVE - u'\u0154' # 0xc0 -> LATIN CAPITAL LETTER R WITH ACUTE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\u0102' # 0xc3 -> LATIN CAPITAL LETTER A WITH BREVE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\u0139' # 0xc5 -> LATIN CAPITAL LETTER L WITH ACUTE - u'\u0106' # 0xc6 -> LATIN CAPITAL LETTER C WITH ACUTE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\u010c' # 0xc8 -> LATIN CAPITAL LETTER C WITH CARON - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\u0118' # 0xca -> LATIN CAPITAL LETTER E WITH OGONEK - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\u011a' # 0xcc -> LATIN CAPITAL LETTER E WITH CARON - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\u010e' # 0xcf -> LATIN CAPITAL LETTER D WITH CARON - u'\u0110' # 0xd0 -> LATIN CAPITAL LETTER D WITH STROKE - u'\u0143' # 0xd1 -> LATIN CAPITAL LETTER N WITH ACUTE - u'\u0147' # 0xd2 -> LATIN CAPITAL LETTER N WITH CARON - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\u0150' # 0xd5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\u0158' # 0xd8 -> LATIN CAPITAL LETTER R WITH CARON - u'\u016e' # 0xd9 -> LATIN CAPITAL LETTER U WITH RING ABOVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\u0170' # 0xdb -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xdd' # 0xdd -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\u0162' # 0xde -> LATIN CAPITAL LETTER T WITH CEDILLA - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\u0155' # 0xe0 -> LATIN SMALL LETTER R WITH ACUTE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\u0103' # 0xe3 -> LATIN SMALL LETTER A WITH BREVE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\u013a' # 0xe5 -> LATIN SMALL LETTER L WITH ACUTE - u'\u0107' # 0xe6 -> LATIN SMALL LETTER C WITH ACUTE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\u010d' # 0xe8 -> LATIN SMALL LETTER C WITH CARON - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\u0119' # 0xea -> LATIN SMALL LETTER E WITH OGONEK - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\u011b' # 0xec -> LATIN SMALL LETTER E WITH CARON - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\u010f' # 0xef -> LATIN SMALL LETTER D WITH CARON - u'\u0111' # 0xf0 -> LATIN SMALL LETTER D WITH STROKE - u'\u0144' # 0xf1 -> LATIN SMALL LETTER N WITH ACUTE - u'\u0148' # 0xf2 -> LATIN SMALL LETTER N WITH CARON - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\u0151' # 0xf5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\u0159' # 0xf8 -> LATIN SMALL LETTER R WITH CARON - u'\u016f' # 0xf9 -> LATIN SMALL LETTER U WITH RING ABOVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\u0171' # 0xfb -> LATIN SMALL LETTER U WITH DOUBLE ACUTE - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xfd' # 0xfd -> LATIN SMALL LETTER Y WITH ACUTE - u'\u0163' # 0xfe -> LATIN SMALL LETTER T WITH CEDILLA - u'\u02d9' # 0xff -> DOT ABOVE + u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u015b' # 0x9C -> LATIN SMALL LETTER S WITH ACUTE + u'\u0165' # 0x9D -> LATIN SMALL LETTER T WITH CARON + u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON + u'\u017a' # 0x9F -> LATIN SMALL LETTER Z WITH ACUTE + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u02c7' # 0xA1 -> CARON + u'\u02d8' # 0xA2 -> BREVE + u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\u0104' # 0xA5 -> LATIN CAPITAL LETTER A WITH OGONEK + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u02db' # 0xB2 -> OGONEK + u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\u0105' # 0xB9 -> LATIN SMALL LETTER A WITH OGONEK + u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u013d' # 0xBC -> LATIN CAPITAL LETTER L WITH CARON + u'\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT + u'\u013e' # 0xBE -> LATIN SMALL LETTER L WITH CARON + u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + u'\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE + u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON + u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + u'\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON + u'\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE + u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON + u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + u'\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON + u'\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + u'\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA + u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,133 +415,134 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xdd, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xfd, # LATIN SMALL LETTER Y WITH ACUTE - 0x0102: 0xc3, # LATIN CAPITAL LETTER A WITH BREVE - 0x0103: 0xe3, # LATIN SMALL LETTER A WITH BREVE - 0x0104: 0xa5, # LATIN CAPITAL LETTER A WITH OGONEK - 0x0105: 0xb9, # LATIN SMALL LETTER A WITH OGONEK - 0x0106: 0xc6, # LATIN CAPITAL LETTER C WITH ACUTE - 0x0107: 0xe6, # LATIN SMALL LETTER C WITH ACUTE - 0x010c: 0xc8, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xe8, # LATIN SMALL LETTER C WITH CARON - 0x010e: 0xcf, # LATIN CAPITAL LETTER D WITH CARON - 0x010f: 0xef, # LATIN SMALL LETTER D WITH CARON - 0x0110: 0xd0, # LATIN CAPITAL LETTER D WITH STROKE - 0x0111: 0xf0, # LATIN SMALL LETTER D WITH STROKE - 0x0118: 0xca, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xea, # LATIN SMALL LETTER E WITH OGONEK - 0x011a: 0xcc, # LATIN CAPITAL LETTER E WITH CARON - 0x011b: 0xec, # LATIN SMALL LETTER E WITH CARON - 0x0139: 0xc5, # LATIN CAPITAL LETTER L WITH ACUTE - 0x013a: 0xe5, # LATIN SMALL LETTER L WITH ACUTE - 0x013d: 0xbc, # LATIN CAPITAL LETTER L WITH CARON - 0x013e: 0xbe, # LATIN SMALL LETTER L WITH CARON - 0x0141: 0xa3, # LATIN CAPITAL LETTER L WITH STROKE - 0x0142: 0xb3, # LATIN SMALL LETTER L WITH STROKE - 0x0143: 0xd1, # LATIN CAPITAL LETTER N WITH ACUTE - 0x0144: 0xf1, # LATIN SMALL LETTER N WITH ACUTE - 0x0147: 0xd2, # LATIN CAPITAL LETTER N WITH CARON - 0x0148: 0xf2, # LATIN SMALL LETTER N WITH CARON - 0x0150: 0xd5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - 0x0151: 0xf5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE - 0x0154: 0xc0, # LATIN CAPITAL LETTER R WITH ACUTE - 0x0155: 0xe0, # LATIN SMALL LETTER R WITH ACUTE - 0x0158: 0xd8, # LATIN CAPITAL LETTER R WITH CARON - 0x0159: 0xf8, # LATIN SMALL LETTER R WITH CARON - 0x015a: 0x8c, # LATIN CAPITAL LETTER S WITH ACUTE - 0x015b: 0x9c, # LATIN SMALL LETTER S WITH ACUTE - 0x015e: 0xaa, # LATIN CAPITAL LETTER S WITH CEDILLA - 0x015f: 0xba, # LATIN SMALL LETTER S WITH CEDILLA - 0x0160: 0x8a, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0x9a, # LATIN SMALL LETTER S WITH CARON - 0x0162: 0xde, # LATIN CAPITAL LETTER T WITH CEDILLA - 0x0163: 0xfe, # LATIN SMALL LETTER T WITH CEDILLA - 0x0164: 0x8d, # LATIN CAPITAL LETTER T WITH CARON - 0x0165: 0x9d, # LATIN SMALL LETTER T WITH CARON - 0x016e: 0xd9, # LATIN CAPITAL LETTER U WITH RING ABOVE - 0x016f: 0xf9, # LATIN SMALL LETTER U WITH RING ABOVE - 0x0170: 0xdb, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - 0x0171: 0xfb, # LATIN SMALL LETTER U WITH DOUBLE ACUTE - 0x0179: 0x8f, # LATIN CAPITAL LETTER Z WITH ACUTE - 0x017a: 0x9f, # LATIN SMALL LETTER Z WITH ACUTE - 0x017b: 0xaf, # LATIN CAPITAL LETTER Z WITH DOT ABOVE - 0x017c: 0xbf, # LATIN SMALL LETTER Z WITH DOT ABOVE - 0x017d: 0x8e, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0x9e, # LATIN SMALL LETTER Z WITH CARON - 0x02c7: 0xa1, # CARON - 0x02d8: 0xa2, # BREVE - 0x02d9: 0xff, # DOT ABOVE - 0x02db: 0xb2, # OGONEK - 0x02dd: 0xbd, # DOUBLE ACUTE ACCENT + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE + 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE + 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE + 0x0104: 0xA5, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0xB9, # LATIN SMALL LETTER A WITH OGONEK + 0x0106: 0xC6, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0xE6, # LATIN SMALL LETTER C WITH ACUTE + 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON + 0x010E: 0xCF, # LATIN CAPITAL LETTER D WITH CARON + 0x010F: 0xEF, # LATIN SMALL LETTER D WITH CARON + 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE + 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK + 0x011A: 0xCC, # LATIN CAPITAL LETTER E WITH CARON + 0x011B: 0xEC, # LATIN SMALL LETTER E WITH CARON + 0x0139: 0xC5, # LATIN CAPITAL LETTER L WITH ACUTE + 0x013A: 0xE5, # LATIN SMALL LETTER L WITH ACUTE + 0x013D: 0xBC, # LATIN CAPITAL LETTER L WITH CARON + 0x013E: 0xBE, # LATIN SMALL LETTER L WITH CARON + 0x0141: 0xA3, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0xB3, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE + 0x0147: 0xD2, # LATIN CAPITAL LETTER N WITH CARON + 0x0148: 0xF2, # LATIN SMALL LETTER N WITH CARON + 0x0150: 0xD5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + 0x0151: 0xF5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE + 0x0154: 0xC0, # LATIN CAPITAL LETTER R WITH ACUTE + 0x0155: 0xE0, # LATIN SMALL LETTER R WITH ACUTE + 0x0158: 0xD8, # LATIN CAPITAL LETTER R WITH CARON + 0x0159: 0xF8, # LATIN SMALL LETTER R WITH CARON + 0x015A: 0x8C, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015B: 0x9C, # LATIN SMALL LETTER S WITH ACUTE + 0x015E: 0xAA, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015F: 0xBA, # LATIN SMALL LETTER S WITH CEDILLA + 0x0160: 0x8A, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0x9A, # LATIN SMALL LETTER S WITH CARON + 0x0162: 0xDE, # LATIN CAPITAL LETTER T WITH CEDILLA + 0x0163: 0xFE, # LATIN SMALL LETTER T WITH CEDILLA + 0x0164: 0x8D, # LATIN CAPITAL LETTER T WITH CARON + 0x0165: 0x9D, # LATIN SMALL LETTER T WITH CARON + 0x016E: 0xD9, # LATIN CAPITAL LETTER U WITH RING ABOVE + 0x016F: 0xF9, # LATIN SMALL LETTER U WITH RING ABOVE + 0x0170: 0xDB, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + 0x0171: 0xFB, # LATIN SMALL LETTER U WITH DOUBLE ACUTE + 0x0179: 0x8F, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017A: 0x9F, # LATIN SMALL LETTER Z WITH ACUTE + 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017D: 0x8E, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0x9E, # LATIN SMALL LETTER Z WITH CARON + 0x02C7: 0xA1, # CARON + 0x02D8: 0xA2, # BREVE + 0x02D9: 0xFF, # DOT ABOVE + 0x02DB: 0xB2, # OGONEK + 0x02DD: 0xBD, # DOUBLE ACUTE ACCENT 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1251.py b/Lib/encodings/cp1251.py index 4707303..e62806d 100644 --- a/Lib/encodings/cp1251.py +++ b/Lib/encodings/cp1251.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE u'\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u20ac' # 0x88 -> EURO SIGN u'\u2030' # 0x89 -> PER MILLE SIGN - u'\u0409' # 0x8a -> CYRILLIC CAPITAL LETTER LJE - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u040a' # 0x8c -> CYRILLIC CAPITAL LETTER NJE - u'\u040c' # 0x8d -> CYRILLIC CAPITAL LETTER KJE - u'\u040b' # 0x8e -> CYRILLIC CAPITAL LETTER TSHE - u'\u040f' # 0x8f -> CYRILLIC CAPITAL LETTER DZHE + u'\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE + u'\u040c' # 0x8D -> CYRILLIC CAPITAL LETTER KJE + u'\u040b' # 0x8E -> CYRILLIC CAPITAL LETTER TSHE + u'\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE u'\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\u0459' # 0x9a -> CYRILLIC SMALL LETTER LJE - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u045a' # 0x9c -> CYRILLIC SMALL LETTER NJE - u'\u045c' # 0x9d -> CYRILLIC SMALL LETTER KJE - u'\u045b' # 0x9e -> CYRILLIC SMALL LETTER TSHE - u'\u045f' # 0x9f -> CYRILLIC SMALL LETTER DZHE - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u040e' # 0xa1 -> CYRILLIC CAPITAL LETTER SHORT U - u'\u045e' # 0xa2 -> CYRILLIC SMALL LETTER SHORT U - u'\u0408' # 0xa3 -> CYRILLIC CAPITAL LETTER JE - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\u0490' # 0xa5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\u0401' # 0xa8 -> CYRILLIC CAPITAL LETTER IO - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u0404' # 0xaa -> CYRILLIC CAPITAL LETTER UKRAINIAN IE - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\u0407' # 0xaf -> CYRILLIC CAPITAL LETTER YI - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u0406' # 0xb2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - u'\u0456' # 0xb3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - u'\u0491' # 0xb4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\u0451' # 0xb8 -> CYRILLIC SMALL LETTER IO - u'\u2116' # 0xb9 -> NUMERO SIGN - u'\u0454' # 0xba -> CYRILLIC SMALL LETTER UKRAINIAN IE - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u0458' # 0xbc -> CYRILLIC SMALL LETTER JE - u'\u0405' # 0xbd -> CYRILLIC CAPITAL LETTER DZE - u'\u0455' # 0xbe -> CYRILLIC SMALL LETTER DZE - u'\u0457' # 0xbf -> CYRILLIC SMALL LETTER YI - u'\u0410' # 0xc0 -> CYRILLIC CAPITAL LETTER A - u'\u0411' # 0xc1 -> CYRILLIC CAPITAL LETTER BE - u'\u0412' # 0xc2 -> CYRILLIC CAPITAL LETTER VE - u'\u0413' # 0xc3 -> CYRILLIC CAPITAL LETTER GHE - u'\u0414' # 0xc4 -> CYRILLIC CAPITAL LETTER DE - u'\u0415' # 0xc5 -> CYRILLIC CAPITAL LETTER IE - u'\u0416' # 0xc6 -> CYRILLIC CAPITAL LETTER ZHE - u'\u0417' # 0xc7 -> CYRILLIC CAPITAL LETTER ZE - u'\u0418' # 0xc8 -> CYRILLIC CAPITAL LETTER I - u'\u0419' # 0xc9 -> CYRILLIC CAPITAL LETTER SHORT I - u'\u041a' # 0xca -> CYRILLIC CAPITAL LETTER KA - u'\u041b' # 0xcb -> CYRILLIC CAPITAL LETTER EL - u'\u041c' # 0xcc -> CYRILLIC CAPITAL LETTER EM - u'\u041d' # 0xcd -> CYRILLIC CAPITAL LETTER EN - u'\u041e' # 0xce -> CYRILLIC CAPITAL LETTER O - u'\u041f' # 0xcf -> CYRILLIC CAPITAL LETTER PE - u'\u0420' # 0xd0 -> CYRILLIC CAPITAL LETTER ER - u'\u0421' # 0xd1 -> CYRILLIC CAPITAL LETTER ES - u'\u0422' # 0xd2 -> CYRILLIC CAPITAL LETTER TE - u'\u0423' # 0xd3 -> CYRILLIC CAPITAL LETTER U - u'\u0424' # 0xd4 -> CYRILLIC CAPITAL LETTER EF - u'\u0425' # 0xd5 -> CYRILLIC CAPITAL LETTER HA - u'\u0426' # 0xd6 -> CYRILLIC CAPITAL LETTER TSE - u'\u0427' # 0xd7 -> CYRILLIC CAPITAL LETTER CHE - u'\u0428' # 0xd8 -> CYRILLIC CAPITAL LETTER SHA - u'\u0429' # 0xd9 -> CYRILLIC CAPITAL LETTER SHCHA - u'\u042a' # 0xda -> CYRILLIC CAPITAL LETTER HARD SIGN - u'\u042b' # 0xdb -> CYRILLIC CAPITAL LETTER YERU - u'\u042c' # 0xdc -> CYRILLIC CAPITAL LETTER SOFT SIGN - u'\u042d' # 0xdd -> CYRILLIC CAPITAL LETTER E - u'\u042e' # 0xde -> CYRILLIC CAPITAL LETTER YU - u'\u042f' # 0xdf -> CYRILLIC CAPITAL LETTER YA - u'\u0430' # 0xe0 -> CYRILLIC SMALL LETTER A - u'\u0431' # 0xe1 -> CYRILLIC SMALL LETTER BE - u'\u0432' # 0xe2 -> CYRILLIC SMALL LETTER VE - u'\u0433' # 0xe3 -> CYRILLIC SMALL LETTER GHE - u'\u0434' # 0xe4 -> CYRILLIC SMALL LETTER DE - u'\u0435' # 0xe5 -> CYRILLIC SMALL LETTER IE - u'\u0436' # 0xe6 -> CYRILLIC SMALL LETTER ZHE - u'\u0437' # 0xe7 -> CYRILLIC SMALL LETTER ZE - u'\u0438' # 0xe8 -> CYRILLIC SMALL LETTER I - u'\u0439' # 0xe9 -> CYRILLIC SMALL LETTER SHORT I - u'\u043a' # 0xea -> CYRILLIC SMALL LETTER KA - u'\u043b' # 0xeb -> CYRILLIC SMALL LETTER EL - u'\u043c' # 0xec -> CYRILLIC SMALL LETTER EM - u'\u043d' # 0xed -> CYRILLIC SMALL LETTER EN - u'\u043e' # 0xee -> CYRILLIC SMALL LETTER O - u'\u043f' # 0xef -> CYRILLIC SMALL LETTER PE - u'\u0440' # 0xf0 -> CYRILLIC SMALL LETTER ER - u'\u0441' # 0xf1 -> CYRILLIC SMALL LETTER ES - u'\u0442' # 0xf2 -> CYRILLIC SMALL LETTER TE - u'\u0443' # 0xf3 -> CYRILLIC SMALL LETTER U - u'\u0444' # 0xf4 -> CYRILLIC SMALL LETTER EF - u'\u0445' # 0xf5 -> CYRILLIC SMALL LETTER HA - u'\u0446' # 0xf6 -> CYRILLIC SMALL LETTER TSE - u'\u0447' # 0xf7 -> CYRILLIC SMALL LETTER CHE - u'\u0448' # 0xf8 -> CYRILLIC SMALL LETTER SHA - u'\u0449' # 0xf9 -> CYRILLIC SMALL LETTER SHCHA - u'\u044a' # 0xfa -> CYRILLIC SMALL LETTER HARD SIGN - u'\u044b' # 0xfb -> CYRILLIC SMALL LETTER YERU - u'\u044c' # 0xfc -> CYRILLIC SMALL LETTER SOFT SIGN - u'\u044d' # 0xfd -> CYRILLIC SMALL LETTER E - u'\u044e' # 0xfe -> CYRILLIC SMALL LETTER YU - u'\u044f' # 0xff -> CYRILLIC SMALL LETTER YA + u'\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE + u'\u045c' # 0x9D -> CYRILLIC SMALL LETTER KJE + u'\u045b' # 0x9E -> CYRILLIC SMALL LETTER TSHE + u'\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U + u'\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U + u'\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\u0490' # 0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u0404' # 0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\u0407' # 0xAF -> CYRILLIC CAPITAL LETTER YI + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + u'\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + u'\u0491' # 0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO + u'\u2116' # 0xB9 -> NUMERO SIGN + u'\u0454' # 0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE + u'\u0405' # 0xBD -> CYRILLIC CAPITAL LETTER DZE + u'\u0455' # 0xBE -> CYRILLIC SMALL LETTER DZE + u'\u0457' # 0xBF -> CYRILLIC SMALL LETTER YI + u'\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A + u'\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE + u'\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE + u'\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE + u'\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE + u'\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE + u'\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE + u'\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE + u'\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I + u'\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I + u'\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA + u'\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL + u'\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM + u'\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN + u'\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O + u'\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE + u'\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER + u'\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES + u'\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE + u'\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U + u'\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF + u'\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA + u'\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE + u'\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE + u'\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA + u'\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA + u'\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN + u'\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU + u'\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN + u'\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E + u'\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU + u'\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA + u'\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A + u'\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE + u'\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE + u'\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE + u'\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE + u'\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE + u'\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE + u'\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE + u'\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I + u'\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I + u'\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA + u'\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL + u'\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM + u'\u043d' # 0xED -> CYRILLIC SMALL LETTER EN + u'\u043e' # 0xEE -> CYRILLIC SMALL LETTER O + u'\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE + u'\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER + u'\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES + u'\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE + u'\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U + u'\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF + u'\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA + u'\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE + u'\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE + u'\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA + u'\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA + u'\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN + u'\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU + u'\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN + u'\u044d' # 0xFD -> CYRILLIC SMALL LETTER E + u'\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU + u'\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,137 +415,138 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x0401: 0xa8, # CYRILLIC CAPITAL LETTER IO + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x0401: 0xA8, # CYRILLIC CAPITAL LETTER IO 0x0402: 0x80, # CYRILLIC CAPITAL LETTER DJE 0x0403: 0x81, # CYRILLIC CAPITAL LETTER GJE - 0x0404: 0xaa, # CYRILLIC CAPITAL LETTER UKRAINIAN IE - 0x0405: 0xbd, # CYRILLIC CAPITAL LETTER DZE - 0x0406: 0xb2, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0407: 0xaf, # CYRILLIC CAPITAL LETTER YI - 0x0408: 0xa3, # CYRILLIC CAPITAL LETTER JE - 0x0409: 0x8a, # CYRILLIC CAPITAL LETTER LJE - 0x040a: 0x8c, # CYRILLIC CAPITAL LETTER NJE - 0x040b: 0x8e, # CYRILLIC CAPITAL LETTER TSHE - 0x040c: 0x8d, # CYRILLIC CAPITAL LETTER KJE - 0x040e: 0xa1, # CYRILLIC CAPITAL LETTER SHORT U - 0x040f: 0x8f, # CYRILLIC CAPITAL LETTER DZHE - 0x0410: 0xc0, # CYRILLIC CAPITAL LETTER A - 0x0411: 0xc1, # CYRILLIC CAPITAL LETTER BE - 0x0412: 0xc2, # CYRILLIC CAPITAL LETTER VE - 0x0413: 0xc3, # CYRILLIC CAPITAL LETTER GHE - 0x0414: 0xc4, # CYRILLIC CAPITAL LETTER DE - 0x0415: 0xc5, # CYRILLIC CAPITAL LETTER IE - 0x0416: 0xc6, # CYRILLIC CAPITAL LETTER ZHE - 0x0417: 0xc7, # CYRILLIC CAPITAL LETTER ZE - 0x0418: 0xc8, # CYRILLIC CAPITAL LETTER I - 0x0419: 0xc9, # CYRILLIC CAPITAL LETTER SHORT I - 0x041a: 0xca, # CYRILLIC CAPITAL LETTER KA - 0x041b: 0xcb, # CYRILLIC CAPITAL LETTER EL - 0x041c: 0xcc, # CYRILLIC CAPITAL LETTER EM - 0x041d: 0xcd, # CYRILLIC CAPITAL LETTER EN - 0x041e: 0xce, # CYRILLIC CAPITAL LETTER O - 0x041f: 0xcf, # CYRILLIC CAPITAL LETTER PE - 0x0420: 0xd0, # CYRILLIC CAPITAL LETTER ER - 0x0421: 0xd1, # CYRILLIC CAPITAL LETTER ES - 0x0422: 0xd2, # CYRILLIC CAPITAL LETTER TE - 0x0423: 0xd3, # CYRILLIC CAPITAL LETTER U - 0x0424: 0xd4, # CYRILLIC CAPITAL LETTER EF - 0x0425: 0xd5, # CYRILLIC CAPITAL LETTER HA - 0x0426: 0xd6, # CYRILLIC CAPITAL LETTER TSE - 0x0427: 0xd7, # CYRILLIC CAPITAL LETTER CHE - 0x0428: 0xd8, # CYRILLIC CAPITAL LETTER SHA - 0x0429: 0xd9, # CYRILLIC CAPITAL LETTER SHCHA - 0x042a: 0xda, # CYRILLIC CAPITAL LETTER HARD SIGN - 0x042b: 0xdb, # CYRILLIC CAPITAL LETTER YERU - 0x042c: 0xdc, # CYRILLIC CAPITAL LETTER SOFT SIGN - 0x042d: 0xdd, # CYRILLIC CAPITAL LETTER E - 0x042e: 0xde, # CYRILLIC CAPITAL LETTER YU - 0x042f: 0xdf, # CYRILLIC CAPITAL LETTER YA - 0x0430: 0xe0, # CYRILLIC SMALL LETTER A - 0x0431: 0xe1, # CYRILLIC SMALL LETTER BE - 0x0432: 0xe2, # CYRILLIC SMALL LETTER VE - 0x0433: 0xe3, # CYRILLIC SMALL LETTER GHE - 0x0434: 0xe4, # CYRILLIC SMALL LETTER DE - 0x0435: 0xe5, # CYRILLIC SMALL LETTER IE - 0x0436: 0xe6, # CYRILLIC SMALL LETTER ZHE - 0x0437: 0xe7, # CYRILLIC SMALL LETTER ZE - 0x0438: 0xe8, # CYRILLIC SMALL LETTER I - 0x0439: 0xe9, # CYRILLIC SMALL LETTER SHORT I - 0x043a: 0xea, # CYRILLIC SMALL LETTER KA - 0x043b: 0xeb, # CYRILLIC SMALL LETTER EL - 0x043c: 0xec, # CYRILLIC SMALL LETTER EM - 0x043d: 0xed, # CYRILLIC SMALL LETTER EN - 0x043e: 0xee, # CYRILLIC SMALL LETTER O - 0x043f: 0xef, # CYRILLIC SMALL LETTER PE - 0x0440: 0xf0, # CYRILLIC SMALL LETTER ER - 0x0441: 0xf1, # CYRILLIC SMALL LETTER ES - 0x0442: 0xf2, # CYRILLIC SMALL LETTER TE - 0x0443: 0xf3, # CYRILLIC SMALL LETTER U - 0x0444: 0xf4, # CYRILLIC SMALL LETTER EF - 0x0445: 0xf5, # CYRILLIC SMALL LETTER HA - 0x0446: 0xf6, # CYRILLIC SMALL LETTER TSE - 0x0447: 0xf7, # CYRILLIC SMALL LETTER CHE - 0x0448: 0xf8, # CYRILLIC SMALL LETTER SHA - 0x0449: 0xf9, # CYRILLIC SMALL LETTER SHCHA - 0x044a: 0xfa, # CYRILLIC SMALL LETTER HARD SIGN - 0x044b: 0xfb, # CYRILLIC SMALL LETTER YERU - 0x044c: 0xfc, # CYRILLIC SMALL LETTER SOFT SIGN - 0x044d: 0xfd, # CYRILLIC SMALL LETTER E - 0x044e: 0xfe, # CYRILLIC SMALL LETTER YU - 0x044f: 0xff, # CYRILLIC SMALL LETTER YA - 0x0451: 0xb8, # CYRILLIC SMALL LETTER IO + 0x0404: 0xAA, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0405: 0xBD, # CYRILLIC CAPITAL LETTER DZE + 0x0406: 0xB2, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0407: 0xAF, # CYRILLIC CAPITAL LETTER YI + 0x0408: 0xA3, # CYRILLIC CAPITAL LETTER JE + 0x0409: 0x8A, # CYRILLIC CAPITAL LETTER LJE + 0x040A: 0x8C, # CYRILLIC CAPITAL LETTER NJE + 0x040B: 0x8E, # CYRILLIC CAPITAL LETTER TSHE + 0x040C: 0x8D, # CYRILLIC CAPITAL LETTER KJE + 0x040E: 0xA1, # CYRILLIC CAPITAL LETTER SHORT U + 0x040F: 0x8F, # CYRILLIC CAPITAL LETTER DZHE + 0x0410: 0xC0, # CYRILLIC CAPITAL LETTER A + 0x0411: 0xC1, # CYRILLIC CAPITAL LETTER BE + 0x0412: 0xC2, # CYRILLIC CAPITAL LETTER VE + 0x0413: 0xC3, # CYRILLIC CAPITAL LETTER GHE + 0x0414: 0xC4, # CYRILLIC CAPITAL LETTER DE + 0x0415: 0xC5, # CYRILLIC CAPITAL LETTER IE + 0x0416: 0xC6, # CYRILLIC CAPITAL LETTER ZHE + 0x0417: 0xC7, # CYRILLIC CAPITAL LETTER ZE + 0x0418: 0xC8, # CYRILLIC CAPITAL LETTER I + 0x0419: 0xC9, # CYRILLIC CAPITAL LETTER SHORT I + 0x041A: 0xCA, # CYRILLIC CAPITAL LETTER KA + 0x041B: 0xCB, # CYRILLIC CAPITAL LETTER EL + 0x041C: 0xCC, # CYRILLIC CAPITAL LETTER EM + 0x041D: 0xCD, # CYRILLIC CAPITAL LETTER EN + 0x041E: 0xCE, # CYRILLIC CAPITAL LETTER O + 0x041F: 0xCF, # CYRILLIC CAPITAL LETTER PE + 0x0420: 0xD0, # CYRILLIC CAPITAL LETTER ER + 0x0421: 0xD1, # CYRILLIC CAPITAL LETTER ES + 0x0422: 0xD2, # CYRILLIC CAPITAL LETTER TE + 0x0423: 0xD3, # CYRILLIC CAPITAL LETTER U + 0x0424: 0xD4, # CYRILLIC CAPITAL LETTER EF + 0x0425: 0xD5, # CYRILLIC CAPITAL LETTER HA + 0x0426: 0xD6, # CYRILLIC CAPITAL LETTER TSE + 0x0427: 0xD7, # CYRILLIC CAPITAL LETTER CHE + 0x0428: 0xD8, # CYRILLIC CAPITAL LETTER SHA + 0x0429: 0xD9, # CYRILLIC CAPITAL LETTER SHCHA + 0x042A: 0xDA, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042B: 0xDB, # CYRILLIC CAPITAL LETTER YERU + 0x042C: 0xDC, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042D: 0xDD, # CYRILLIC CAPITAL LETTER E + 0x042E: 0xDE, # CYRILLIC CAPITAL LETTER YU + 0x042F: 0xDF, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0xE0, # CYRILLIC SMALL LETTER A + 0x0431: 0xE1, # CYRILLIC SMALL LETTER BE + 0x0432: 0xE2, # CYRILLIC SMALL LETTER VE + 0x0433: 0xE3, # CYRILLIC SMALL LETTER GHE + 0x0434: 0xE4, # CYRILLIC SMALL LETTER DE + 0x0435: 0xE5, # CYRILLIC SMALL LETTER IE + 0x0436: 0xE6, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0xE7, # CYRILLIC SMALL LETTER ZE + 0x0438: 0xE8, # CYRILLIC SMALL LETTER I + 0x0439: 0xE9, # CYRILLIC SMALL LETTER SHORT I + 0x043A: 0xEA, # CYRILLIC SMALL LETTER KA + 0x043B: 0xEB, # CYRILLIC SMALL LETTER EL + 0x043C: 0xEC, # CYRILLIC SMALL LETTER EM + 0x043D: 0xED, # CYRILLIC SMALL LETTER EN + 0x043E: 0xEE, # CYRILLIC SMALL LETTER O + 0x043F: 0xEF, # CYRILLIC SMALL LETTER PE + 0x0440: 0xF0, # CYRILLIC SMALL LETTER ER + 0x0441: 0xF1, # CYRILLIC SMALL LETTER ES + 0x0442: 0xF2, # CYRILLIC SMALL LETTER TE + 0x0443: 0xF3, # CYRILLIC SMALL LETTER U + 0x0444: 0xF4, # CYRILLIC SMALL LETTER EF + 0x0445: 0xF5, # CYRILLIC SMALL LETTER HA + 0x0446: 0xF6, # CYRILLIC SMALL LETTER TSE + 0x0447: 0xF7, # CYRILLIC SMALL LETTER CHE + 0x0448: 0xF8, # CYRILLIC SMALL LETTER SHA + 0x0449: 0xF9, # CYRILLIC SMALL LETTER SHCHA + 0x044A: 0xFA, # CYRILLIC SMALL LETTER HARD SIGN + 0x044B: 0xFB, # CYRILLIC SMALL LETTER YERU + 0x044C: 0xFC, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044D: 0xFD, # CYRILLIC SMALL LETTER E + 0x044E: 0xFE, # CYRILLIC SMALL LETTER YU + 0x044F: 0xFF, # CYRILLIC SMALL LETTER YA + 0x0451: 0xB8, # CYRILLIC SMALL LETTER IO 0x0452: 0x90, # CYRILLIC SMALL LETTER DJE 0x0453: 0x83, # CYRILLIC SMALL LETTER GJE - 0x0454: 0xba, # CYRILLIC SMALL LETTER UKRAINIAN IE - 0x0455: 0xbe, # CYRILLIC SMALL LETTER DZE - 0x0456: 0xb3, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0457: 0xbf, # CYRILLIC SMALL LETTER YI - 0x0458: 0xbc, # CYRILLIC SMALL LETTER JE - 0x0459: 0x9a, # CYRILLIC SMALL LETTER LJE - 0x045a: 0x9c, # CYRILLIC SMALL LETTER NJE - 0x045b: 0x9e, # CYRILLIC SMALL LETTER TSHE - 0x045c: 0x9d, # CYRILLIC SMALL LETTER KJE - 0x045e: 0xa2, # CYRILLIC SMALL LETTER SHORT U - 0x045f: 0x9f, # CYRILLIC SMALL LETTER DZHE - 0x0490: 0xa5, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN - 0x0491: 0xb4, # CYRILLIC SMALL LETTER GHE WITH UPTURN + 0x0454: 0xBA, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0455: 0xBE, # CYRILLIC SMALL LETTER DZE + 0x0456: 0xB3, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0457: 0xBF, # CYRILLIC SMALL LETTER YI + 0x0458: 0xBC, # CYRILLIC SMALL LETTER JE + 0x0459: 0x9A, # CYRILLIC SMALL LETTER LJE + 0x045A: 0x9C, # CYRILLIC SMALL LETTER NJE + 0x045B: 0x9E, # CYRILLIC SMALL LETTER TSHE + 0x045C: 0x9D, # CYRILLIC SMALL LETTER KJE + 0x045E: 0xA2, # CYRILLIC SMALL LETTER SHORT U + 0x045F: 0x9F, # CYRILLIC SMALL LETTER DZHE + 0x0490: 0xA5, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN + 0x0491: 0xB4, # CYRILLIC SMALL LETTER GHE WITH UPTURN 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ac: 0x88, # EURO SIGN - 0x2116: 0xb9, # NUMERO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AC: 0x88, # EURO SIGN + 0x2116: 0xB9, # NUMERO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1252.py b/Lib/encodings/cp1252.py index 0f6160d..3d7f541 100644 --- a/Lib/encodings/cp1252.py +++ b/Lib/encodings/cp1252.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN - u'\u0160' # 0x8a -> LATIN CAPITAL LETTER S WITH CARON - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u0152' # 0x8c -> LATIN CAPITAL LIGATURE OE - u'\ufffe' # 0x8d -> UNDEFINED - u'\u017d' # 0x8e -> LATIN CAPITAL LETTER Z WITH CARON - u'\ufffe' # 0x8f -> UNDEFINED + u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + u'\ufffe' # 0x8D -> UNDEFINED + u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON + u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\u0161' # 0x9a -> LATIN SMALL LETTER S WITH CARON - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u0153' # 0x9c -> LATIN SMALL LIGATURE OE - u'\ufffe' # 0x9d -> UNDEFINED - u'\u017e' # 0x9e -> LATIN SMALL LETTER Z WITH CARON - u'\u0178' # 0x9f -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\xa1' # 0xa1 -> INVERTED EXCLAMATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xaa' # 0xaa -> FEMININE ORDINAL INDICATOR - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xba' # 0xba -> MASCULINE ORDINAL INDICATOR - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xbf' # 0xbf -> INVERTED QUESTION MARK - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xd0' # 0xd0 -> LATIN CAPITAL LETTER ETH - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xdd' # 0xdd -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xde' # 0xde -> LATIN CAPITAL LETTER THORN - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\xf0' # 0xf0 -> LATIN SMALL LETTER ETH - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xfd' # 0xfd -> LATIN SMALL LETTER Y WITH ACUTE - u'\xfe' # 0xfe -> LATIN SMALL LETTER THORN - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + u'\ufffe' # 0x9D -> UNDEFINED + u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON + u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xbf' # 0xBF -> INVERTED QUESTION MARK + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,133 +415,134 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a1: 0xa1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xaa, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00ba: 0xba, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xbf, # INVERTED QUESTION MARK - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xd0, # LATIN CAPITAL LETTER ETH - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xdd, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xde, # LATIN CAPITAL LETTER THORN - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0xf0, # LATIN SMALL LETTER ETH - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xfd, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0xfe, # LATIN SMALL LETTER THORN - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x0152: 0x8c, # LATIN CAPITAL LIGATURE OE - 0x0153: 0x9c, # LATIN SMALL LIGATURE OE - 0x0160: 0x8a, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0x9a, # LATIN SMALL LETTER S WITH CARON - 0x0178: 0x9f, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x017d: 0x8e, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0x9e, # LATIN SMALL LETTER Z WITH CARON + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xBF, # INVERTED QUESTION MARK + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0xF0, # LATIN SMALL LETTER ETH + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0xFE, # LATIN SMALL LETTER THORN + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE + 0x0153: 0x9C, # LATIN SMALL LIGATURE OE + 0x0160: 0x8A, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0x9A, # LATIN SMALL LETTER S WITH CARON + 0x0178: 0x9F, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x017D: 0x8E, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0x9E, # LATIN SMALL LETTER Z WITH CARON 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02dc: 0x98, # SMALL TILDE + 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02DC: 0x98, # SMALL TILDE 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1253.py b/Lib/encodings/cp1253.py index 01dc304..d0f6847 100644 --- a/Lib/encodings/cp1253.py +++ b/Lib/encodings/cp1253.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\ufffe' # 0x88 -> UNDEFINED u'\u2030' # 0x89 -> PER MILLE SIGN - u'\ufffe' # 0x8a -> UNDEFINED - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\ufffe' # 0x8c -> UNDEFINED - u'\ufffe' # 0x8d -> UNDEFINED - u'\ufffe' # 0x8e -> UNDEFINED - u'\ufffe' # 0x8f -> UNDEFINED + u'\ufffe' # 0x8A -> UNDEFINED + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\ufffe' # 0x8C -> UNDEFINED + u'\ufffe' # 0x8D -> UNDEFINED + u'\ufffe' # 0x8E -> UNDEFINED + u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\ufffe' # 0x9a -> UNDEFINED - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\ufffe' # 0x9c -> UNDEFINED - u'\ufffe' # 0x9d -> UNDEFINED - u'\ufffe' # 0x9e -> UNDEFINED - u'\ufffe' # 0x9f -> UNDEFINED - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0385' # 0xa1 -> GREEK DIALYTIKA TONOS - u'\u0386' # 0xa2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\ufffe' # 0xaa -> UNDEFINED - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\u2015' # 0xaf -> HORIZONTAL BAR - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\u0384' # 0xb4 -> GREEK TONOS - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\u0388' # 0xb8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS - u'\u0389' # 0xb9 -> GREEK CAPITAL LETTER ETA WITH TONOS - u'\u038a' # 0xba -> GREEK CAPITAL LETTER IOTA WITH TONOS - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u038c' # 0xbc -> GREEK CAPITAL LETTER OMICRON WITH TONOS - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\u038e' # 0xbe -> GREEK CAPITAL LETTER UPSILON WITH TONOS - u'\u038f' # 0xbf -> GREEK CAPITAL LETTER OMEGA WITH TONOS - u'\u0390' # 0xc0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS - u'\u0391' # 0xc1 -> GREEK CAPITAL LETTER ALPHA - u'\u0392' # 0xc2 -> GREEK CAPITAL LETTER BETA - u'\u0393' # 0xc3 -> GREEK CAPITAL LETTER GAMMA - u'\u0394' # 0xc4 -> GREEK CAPITAL LETTER DELTA - u'\u0395' # 0xc5 -> GREEK CAPITAL LETTER EPSILON - u'\u0396' # 0xc6 -> GREEK CAPITAL LETTER ZETA - u'\u0397' # 0xc7 -> GREEK CAPITAL LETTER ETA - u'\u0398' # 0xc8 -> GREEK CAPITAL LETTER THETA - u'\u0399' # 0xc9 -> GREEK CAPITAL LETTER IOTA - u'\u039a' # 0xca -> GREEK CAPITAL LETTER KAPPA - u'\u039b' # 0xcb -> GREEK CAPITAL LETTER LAMDA - u'\u039c' # 0xcc -> GREEK CAPITAL LETTER MU - u'\u039d' # 0xcd -> GREEK CAPITAL LETTER NU - u'\u039e' # 0xce -> GREEK CAPITAL LETTER XI - u'\u039f' # 0xcf -> GREEK CAPITAL LETTER OMICRON - u'\u03a0' # 0xd0 -> GREEK CAPITAL LETTER PI - u'\u03a1' # 0xd1 -> GREEK CAPITAL LETTER RHO - u'\ufffe' # 0xd2 -> UNDEFINED - u'\u03a3' # 0xd3 -> GREEK CAPITAL LETTER SIGMA - u'\u03a4' # 0xd4 -> GREEK CAPITAL LETTER TAU - u'\u03a5' # 0xd5 -> GREEK CAPITAL LETTER UPSILON - u'\u03a6' # 0xd6 -> GREEK CAPITAL LETTER PHI - u'\u03a7' # 0xd7 -> GREEK CAPITAL LETTER CHI - u'\u03a8' # 0xd8 -> GREEK CAPITAL LETTER PSI - u'\u03a9' # 0xd9 -> GREEK CAPITAL LETTER OMEGA - u'\u03aa' # 0xda -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - u'\u03ab' # 0xdb -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - u'\u03ac' # 0xdc -> GREEK SMALL LETTER ALPHA WITH TONOS - u'\u03ad' # 0xdd -> GREEK SMALL LETTER EPSILON WITH TONOS - u'\u03ae' # 0xde -> GREEK SMALL LETTER ETA WITH TONOS - u'\u03af' # 0xdf -> GREEK SMALL LETTER IOTA WITH TONOS - u'\u03b0' # 0xe0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - u'\u03b1' # 0xe1 -> GREEK SMALL LETTER ALPHA - u'\u03b2' # 0xe2 -> GREEK SMALL LETTER BETA - u'\u03b3' # 0xe3 -> GREEK SMALL LETTER GAMMA - u'\u03b4' # 0xe4 -> GREEK SMALL LETTER DELTA - u'\u03b5' # 0xe5 -> GREEK SMALL LETTER EPSILON - u'\u03b6' # 0xe6 -> GREEK SMALL LETTER ZETA - u'\u03b7' # 0xe7 -> GREEK SMALL LETTER ETA - u'\u03b8' # 0xe8 -> GREEK SMALL LETTER THETA - u'\u03b9' # 0xe9 -> GREEK SMALL LETTER IOTA - u'\u03ba' # 0xea -> GREEK SMALL LETTER KAPPA - u'\u03bb' # 0xeb -> GREEK SMALL LETTER LAMDA - u'\u03bc' # 0xec -> GREEK SMALL LETTER MU - u'\u03bd' # 0xed -> GREEK SMALL LETTER NU - u'\u03be' # 0xee -> GREEK SMALL LETTER XI - u'\u03bf' # 0xef -> GREEK SMALL LETTER OMICRON - u'\u03c0' # 0xf0 -> GREEK SMALL LETTER PI - u'\u03c1' # 0xf1 -> GREEK SMALL LETTER RHO - u'\u03c2' # 0xf2 -> GREEK SMALL LETTER FINAL SIGMA - u'\u03c3' # 0xf3 -> GREEK SMALL LETTER SIGMA - u'\u03c4' # 0xf4 -> GREEK SMALL LETTER TAU - u'\u03c5' # 0xf5 -> GREEK SMALL LETTER UPSILON - u'\u03c6' # 0xf6 -> GREEK SMALL LETTER PHI - u'\u03c7' # 0xf7 -> GREEK SMALL LETTER CHI - u'\u03c8' # 0xf8 -> GREEK SMALL LETTER PSI - u'\u03c9' # 0xf9 -> GREEK SMALL LETTER OMEGA - u'\u03ca' # 0xfa -> GREEK SMALL LETTER IOTA WITH DIALYTIKA - u'\u03cb' # 0xfb -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA - u'\u03cc' # 0xfc -> GREEK SMALL LETTER OMICRON WITH TONOS - u'\u03cd' # 0xfd -> GREEK SMALL LETTER UPSILON WITH TONOS - u'\u03ce' # 0xfe -> GREEK SMALL LETTER OMEGA WITH TONOS - u'\ufffe' # 0xff -> UNDEFINED + u'\ufffe' # 0x9A -> UNDEFINED + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\ufffe' # 0x9C -> UNDEFINED + u'\ufffe' # 0x9D -> UNDEFINED + u'\ufffe' # 0x9E -> UNDEFINED + u'\ufffe' # 0x9F -> UNDEFINED + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0385' # 0xA1 -> GREEK DIALYTIKA TONOS + u'\u0386' # 0xA2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\ufffe' # 0xAA -> UNDEFINED + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\u2015' # 0xAF -> HORIZONTAL BAR + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\u0384' # 0xB4 -> GREEK TONOS + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS + u'\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS + u'\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS + u'\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS + u'\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + u'\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA + u'\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA + u'\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA + u'\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA + u'\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON + u'\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA + u'\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA + u'\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA + u'\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA + u'\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA + u'\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA + u'\u039c' # 0xCC -> GREEK CAPITAL LETTER MU + u'\u039d' # 0xCD -> GREEK CAPITAL LETTER NU + u'\u039e' # 0xCE -> GREEK CAPITAL LETTER XI + u'\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON + u'\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI + u'\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO + u'\ufffe' # 0xD2 -> UNDEFINED + u'\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA + u'\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU + u'\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON + u'\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI + u'\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI + u'\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI + u'\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA + u'\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + u'\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + u'\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS + u'\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS + u'\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS + u'\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS + u'\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA + u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA + u'\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA + u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA + u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON + u'\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA + u'\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA + u'\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA + u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA + u'\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA + u'\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA + u'\u03bc' # 0xEC -> GREEK SMALL LETTER MU + u'\u03bd' # 0xED -> GREEK SMALL LETTER NU + u'\u03be' # 0xEE -> GREEK SMALL LETTER XI + u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON + u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI + u'\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO + u'\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA + u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA + u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU + u'\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON + u'\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI + u'\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI + u'\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI + u'\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA + u'\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + u'\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + u'\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS + u'\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS + u'\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS + u'\ufffe' # 0xFF -> UNDEFINED ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,121 +415,122 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK - 0x0384: 0xb4, # GREEK TONOS - 0x0385: 0xa1, # GREEK DIALYTIKA TONOS - 0x0386: 0xa2, # GREEK CAPITAL LETTER ALPHA WITH TONOS - 0x0388: 0xb8, # GREEK CAPITAL LETTER EPSILON WITH TONOS - 0x0389: 0xb9, # GREEK CAPITAL LETTER ETA WITH TONOS - 0x038a: 0xba, # GREEK CAPITAL LETTER IOTA WITH TONOS - 0x038c: 0xbc, # GREEK CAPITAL LETTER OMICRON WITH TONOS - 0x038e: 0xbe, # GREEK CAPITAL LETTER UPSILON WITH TONOS - 0x038f: 0xbf, # GREEK CAPITAL LETTER OMEGA WITH TONOS - 0x0390: 0xc0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS - 0x0391: 0xc1, # GREEK CAPITAL LETTER ALPHA - 0x0392: 0xc2, # GREEK CAPITAL LETTER BETA - 0x0393: 0xc3, # GREEK CAPITAL LETTER GAMMA - 0x0394: 0xc4, # GREEK CAPITAL LETTER DELTA - 0x0395: 0xc5, # GREEK CAPITAL LETTER EPSILON - 0x0396: 0xc6, # GREEK CAPITAL LETTER ZETA - 0x0397: 0xc7, # GREEK CAPITAL LETTER ETA - 0x0398: 0xc8, # GREEK CAPITAL LETTER THETA - 0x0399: 0xc9, # GREEK CAPITAL LETTER IOTA - 0x039a: 0xca, # GREEK CAPITAL LETTER KAPPA - 0x039b: 0xcb, # GREEK CAPITAL LETTER LAMDA - 0x039c: 0xcc, # GREEK CAPITAL LETTER MU - 0x039d: 0xcd, # GREEK CAPITAL LETTER NU - 0x039e: 0xce, # GREEK CAPITAL LETTER XI - 0x039f: 0xcf, # GREEK CAPITAL LETTER OMICRON - 0x03a0: 0xd0, # GREEK CAPITAL LETTER PI - 0x03a1: 0xd1, # GREEK CAPITAL LETTER RHO - 0x03a3: 0xd3, # GREEK CAPITAL LETTER SIGMA - 0x03a4: 0xd4, # GREEK CAPITAL LETTER TAU - 0x03a5: 0xd5, # GREEK CAPITAL LETTER UPSILON - 0x03a6: 0xd6, # GREEK CAPITAL LETTER PHI - 0x03a7: 0xd7, # GREEK CAPITAL LETTER CHI - 0x03a8: 0xd8, # GREEK CAPITAL LETTER PSI - 0x03a9: 0xd9, # GREEK CAPITAL LETTER OMEGA - 0x03aa: 0xda, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - 0x03ab: 0xdb, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - 0x03ac: 0xdc, # GREEK SMALL LETTER ALPHA WITH TONOS - 0x03ad: 0xdd, # GREEK SMALL LETTER EPSILON WITH TONOS - 0x03ae: 0xde, # GREEK SMALL LETTER ETA WITH TONOS - 0x03af: 0xdf, # GREEK SMALL LETTER IOTA WITH TONOS - 0x03b0: 0xe0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - 0x03b1: 0xe1, # GREEK SMALL LETTER ALPHA - 0x03b2: 0xe2, # GREEK SMALL LETTER BETA - 0x03b3: 0xe3, # GREEK SMALL LETTER GAMMA - 0x03b4: 0xe4, # GREEK SMALL LETTER DELTA - 0x03b5: 0xe5, # GREEK SMALL LETTER EPSILON - 0x03b6: 0xe6, # GREEK SMALL LETTER ZETA - 0x03b7: 0xe7, # GREEK SMALL LETTER ETA - 0x03b8: 0xe8, # GREEK SMALL LETTER THETA - 0x03b9: 0xe9, # GREEK SMALL LETTER IOTA - 0x03ba: 0xea, # GREEK SMALL LETTER KAPPA - 0x03bb: 0xeb, # GREEK SMALL LETTER LAMDA - 0x03bc: 0xec, # GREEK SMALL LETTER MU - 0x03bd: 0xed, # GREEK SMALL LETTER NU - 0x03be: 0xee, # GREEK SMALL LETTER XI - 0x03bf: 0xef, # GREEK SMALL LETTER OMICRON - 0x03c0: 0xf0, # GREEK SMALL LETTER PI - 0x03c1: 0xf1, # GREEK SMALL LETTER RHO - 0x03c2: 0xf2, # GREEK SMALL LETTER FINAL SIGMA - 0x03c3: 0xf3, # GREEK SMALL LETTER SIGMA - 0x03c4: 0xf4, # GREEK SMALL LETTER TAU - 0x03c5: 0xf5, # GREEK SMALL LETTER UPSILON - 0x03c6: 0xf6, # GREEK SMALL LETTER PHI - 0x03c7: 0xf7, # GREEK SMALL LETTER CHI - 0x03c8: 0xf8, # GREEK SMALL LETTER PSI - 0x03c9: 0xf9, # GREEK SMALL LETTER OMEGA - 0x03ca: 0xfa, # GREEK SMALL LETTER IOTA WITH DIALYTIKA - 0x03cb: 0xfb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA - 0x03cc: 0xfc, # GREEK SMALL LETTER OMICRON WITH TONOS - 0x03cd: 0xfd, # GREEK SMALL LETTER UPSILON WITH TONOS - 0x03ce: 0xfe, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x0384: 0xB4, # GREEK TONOS + 0x0385: 0xA1, # GREEK DIALYTIKA TONOS + 0x0386: 0xA2, # GREEK CAPITAL LETTER ALPHA WITH TONOS + 0x0388: 0xB8, # GREEK CAPITAL LETTER EPSILON WITH TONOS + 0x0389: 0xB9, # GREEK CAPITAL LETTER ETA WITH TONOS + 0x038A: 0xBA, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x038C: 0xBC, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x038E: 0xBE, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x038F: 0xBF, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x0390: 0xC0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + 0x0391: 0xC1, # GREEK CAPITAL LETTER ALPHA + 0x0392: 0xC2, # GREEK CAPITAL LETTER BETA + 0x0393: 0xC3, # GREEK CAPITAL LETTER GAMMA + 0x0394: 0xC4, # GREEK CAPITAL LETTER DELTA + 0x0395: 0xC5, # GREEK CAPITAL LETTER EPSILON + 0x0396: 0xC6, # GREEK CAPITAL LETTER ZETA + 0x0397: 0xC7, # GREEK CAPITAL LETTER ETA + 0x0398: 0xC8, # GREEK CAPITAL LETTER THETA + 0x0399: 0xC9, # GREEK CAPITAL LETTER IOTA + 0x039A: 0xCA, # GREEK CAPITAL LETTER KAPPA + 0x039B: 0xCB, # GREEK CAPITAL LETTER LAMDA + 0x039C: 0xCC, # GREEK CAPITAL LETTER MU + 0x039D: 0xCD, # GREEK CAPITAL LETTER NU + 0x039E: 0xCE, # GREEK CAPITAL LETTER XI + 0x039F: 0xCF, # GREEK CAPITAL LETTER OMICRON + 0x03A0: 0xD0, # GREEK CAPITAL LETTER PI + 0x03A1: 0xD1, # GREEK CAPITAL LETTER RHO + 0x03A3: 0xD3, # GREEK CAPITAL LETTER SIGMA + 0x03A4: 0xD4, # GREEK CAPITAL LETTER TAU + 0x03A5: 0xD5, # GREEK CAPITAL LETTER UPSILON + 0x03A6: 0xD6, # GREEK CAPITAL LETTER PHI + 0x03A7: 0xD7, # GREEK CAPITAL LETTER CHI + 0x03A8: 0xD8, # GREEK CAPITAL LETTER PSI + 0x03A9: 0xD9, # GREEK CAPITAL LETTER OMEGA + 0x03AA: 0xDA, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x03AB: 0xDB, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x03AC: 0xDC, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x03AD: 0xDD, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x03AE: 0xDE, # GREEK SMALL LETTER ETA WITH TONOS + 0x03AF: 0xDF, # GREEK SMALL LETTER IOTA WITH TONOS + 0x03B0: 0xE0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + 0x03B1: 0xE1, # GREEK SMALL LETTER ALPHA + 0x03B2: 0xE2, # GREEK SMALL LETTER BETA + 0x03B3: 0xE3, # GREEK SMALL LETTER GAMMA + 0x03B4: 0xE4, # GREEK SMALL LETTER DELTA + 0x03B5: 0xE5, # GREEK SMALL LETTER EPSILON + 0x03B6: 0xE6, # GREEK SMALL LETTER ZETA + 0x03B7: 0xE7, # GREEK SMALL LETTER ETA + 0x03B8: 0xE8, # GREEK SMALL LETTER THETA + 0x03B9: 0xE9, # GREEK SMALL LETTER IOTA + 0x03BA: 0xEA, # GREEK SMALL LETTER KAPPA + 0x03BB: 0xEB, # GREEK SMALL LETTER LAMDA + 0x03BC: 0xEC, # GREEK SMALL LETTER MU + 0x03BD: 0xED, # GREEK SMALL LETTER NU + 0x03BE: 0xEE, # GREEK SMALL LETTER XI + 0x03BF: 0xEF, # GREEK SMALL LETTER OMICRON + 0x03C0: 0xF0, # GREEK SMALL LETTER PI + 0x03C1: 0xF1, # GREEK SMALL LETTER RHO + 0x03C2: 0xF2, # GREEK SMALL LETTER FINAL SIGMA + 0x03C3: 0xF3, # GREEK SMALL LETTER SIGMA + 0x03C4: 0xF4, # GREEK SMALL LETTER TAU + 0x03C5: 0xF5, # GREEK SMALL LETTER UPSILON + 0x03C6: 0xF6, # GREEK SMALL LETTER PHI + 0x03C7: 0xF7, # GREEK SMALL LETTER CHI + 0x03C8: 0xF8, # GREEK SMALL LETTER PSI + 0x03C9: 0xF9, # GREEK SMALL LETTER OMEGA + 0x03CA: 0xFA, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x03CB: 0xFB, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x03CC: 0xFC, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x03CD: 0xFD, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x03CE: 0xFE, # GREEK SMALL LETTER OMEGA WITH TONOS 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH - 0x2015: 0xaf, # HORIZONTAL BAR + 0x2015: 0xAF, # HORIZONTAL BAR 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1254.py b/Lib/encodings/cp1254.py index 2dd48c1..e6242cb 100644 --- a/Lib/encodings/cp1254.py +++ b/Lib/encodings/cp1254.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN - u'\u0160' # 0x8a -> LATIN CAPITAL LETTER S WITH CARON - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u0152' # 0x8c -> LATIN CAPITAL LIGATURE OE - u'\ufffe' # 0x8d -> UNDEFINED - u'\ufffe' # 0x8e -> UNDEFINED - u'\ufffe' # 0x8f -> UNDEFINED + u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + u'\ufffe' # 0x8D -> UNDEFINED + u'\ufffe' # 0x8E -> UNDEFINED + u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\u0161' # 0x9a -> LATIN SMALL LETTER S WITH CARON - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u0153' # 0x9c -> LATIN SMALL LIGATURE OE - u'\ufffe' # 0x9d -> UNDEFINED - u'\ufffe' # 0x9e -> UNDEFINED - u'\u0178' # 0x9f -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\xa1' # 0xa1 -> INVERTED EXCLAMATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xaa' # 0xaa -> FEMININE ORDINAL INDICATOR - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xba' # 0xba -> MASCULINE ORDINAL INDICATOR - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xbf' # 0xbf -> INVERTED QUESTION MARK - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\u011e' # 0xd0 -> LATIN CAPITAL LETTER G WITH BREVE - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u0130' # 0xdd -> LATIN CAPITAL LETTER I WITH DOT ABOVE - u'\u015e' # 0xde -> LATIN CAPITAL LETTER S WITH CEDILLA - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\u011f' # 0xf0 -> LATIN SMALL LETTER G WITH BREVE - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u0131' # 0xfd -> LATIN SMALL LETTER DOTLESS I - u'\u015f' # 0xfe -> LATIN SMALL LETTER S WITH CEDILLA - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + u'\ufffe' # 0x9D -> UNDEFINED + u'\ufffe' # 0x9E -> UNDEFINED + u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xbf' # 0xBF -> INVERTED QUESTION MARK + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE + u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I + u'\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,131 +415,132 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a1: 0xa1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xaa, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00ba: 0xba, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xbf, # INVERTED QUESTION MARK - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x011e: 0xd0, # LATIN CAPITAL LETTER G WITH BREVE - 0x011f: 0xf0, # LATIN SMALL LETTER G WITH BREVE - 0x0130: 0xdd, # LATIN CAPITAL LETTER I WITH DOT ABOVE - 0x0131: 0xfd, # LATIN SMALL LETTER DOTLESS I - 0x0152: 0x8c, # LATIN CAPITAL LIGATURE OE - 0x0153: 0x9c, # LATIN SMALL LIGATURE OE - 0x015e: 0xde, # LATIN CAPITAL LETTER S WITH CEDILLA - 0x015f: 0xfe, # LATIN SMALL LETTER S WITH CEDILLA - 0x0160: 0x8a, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0x9a, # LATIN SMALL LETTER S WITH CARON - 0x0178: 0x9f, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xBF, # INVERTED QUESTION MARK + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x011E: 0xD0, # LATIN CAPITAL LETTER G WITH BREVE + 0x011F: 0xF0, # LATIN SMALL LETTER G WITH BREVE + 0x0130: 0xDD, # LATIN CAPITAL LETTER I WITH DOT ABOVE + 0x0131: 0xFD, # LATIN SMALL LETTER DOTLESS I + 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE + 0x0153: 0x9C, # LATIN SMALL LIGATURE OE + 0x015E: 0xDE, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015F: 0xFE, # LATIN SMALL LETTER S WITH CEDILLA + 0x0160: 0x8A, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0x9A, # LATIN SMALL LETTER S WITH CARON + 0x0178: 0x9F, # LATIN CAPITAL LETTER Y WITH DIAERESIS 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02dc: 0x98, # SMALL TILDE + 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02DC: 0x98, # SMALL TILDE 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1255.py b/Lib/encodings/cp1255.py index 8f4c290..65f021a 100644 --- a/Lib/encodings/cp1255.py +++ b/Lib/encodings/cp1255.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN - u'\ufffe' # 0x8a -> UNDEFINED - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\ufffe' # 0x8c -> UNDEFINED - u'\ufffe' # 0x8d -> UNDEFINED - u'\ufffe' # 0x8e -> UNDEFINED - u'\ufffe' # 0x8f -> UNDEFINED + u'\ufffe' # 0x8A -> UNDEFINED + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\ufffe' # 0x8C -> UNDEFINED + u'\ufffe' # 0x8D -> UNDEFINED + u'\ufffe' # 0x8E -> UNDEFINED + u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\ufffe' # 0x9a -> UNDEFINED - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\ufffe' # 0x9c -> UNDEFINED - u'\ufffe' # 0x9d -> UNDEFINED - u'\ufffe' # 0x9e -> UNDEFINED - u'\ufffe' # 0x9f -> UNDEFINED - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\xa1' # 0xa1 -> INVERTED EXCLAMATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\u20aa' # 0xa4 -> NEW SHEQEL SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xd7' # 0xaa -> MULTIPLICATION SIGN - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xf7' # 0xba -> DIVISION SIGN - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xbf' # 0xbf -> INVERTED QUESTION MARK - u'\u05b0' # 0xc0 -> HEBREW POINT SHEVA - u'\u05b1' # 0xc1 -> HEBREW POINT HATAF SEGOL - u'\u05b2' # 0xc2 -> HEBREW POINT HATAF PATAH - u'\u05b3' # 0xc3 -> HEBREW POINT HATAF QAMATS - u'\u05b4' # 0xc4 -> HEBREW POINT HIRIQ - u'\u05b5' # 0xc5 -> HEBREW POINT TSERE - u'\u05b6' # 0xc6 -> HEBREW POINT SEGOL - u'\u05b7' # 0xc7 -> HEBREW POINT PATAH - u'\u05b8' # 0xc8 -> HEBREW POINT QAMATS - u'\u05b9' # 0xc9 -> HEBREW POINT HOLAM - u'\ufffe' # 0xca -> UNDEFINED - u'\u05bb' # 0xcb -> HEBREW POINT QUBUTS - u'\u05bc' # 0xcc -> HEBREW POINT DAGESH OR MAPIQ - u'\u05bd' # 0xcd -> HEBREW POINT METEG - u'\u05be' # 0xce -> HEBREW PUNCTUATION MAQAF - u'\u05bf' # 0xcf -> HEBREW POINT RAFE - u'\u05c0' # 0xd0 -> HEBREW PUNCTUATION PASEQ - u'\u05c1' # 0xd1 -> HEBREW POINT SHIN DOT - u'\u05c2' # 0xd2 -> HEBREW POINT SIN DOT - u'\u05c3' # 0xd3 -> HEBREW PUNCTUATION SOF PASUQ - u'\u05f0' # 0xd4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV - u'\u05f1' # 0xd5 -> HEBREW LIGATURE YIDDISH VAV YOD - u'\u05f2' # 0xd6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD - u'\u05f3' # 0xd7 -> HEBREW PUNCTUATION GERESH - u'\u05f4' # 0xd8 -> HEBREW PUNCTUATION GERSHAYIM - u'\ufffe' # 0xd9 -> UNDEFINED - u'\ufffe' # 0xda -> UNDEFINED - u'\ufffe' # 0xdb -> UNDEFINED - u'\ufffe' # 0xdc -> UNDEFINED - u'\ufffe' # 0xdd -> UNDEFINED - u'\ufffe' # 0xde -> UNDEFINED - u'\ufffe' # 0xdf -> UNDEFINED - u'\u05d0' # 0xe0 -> HEBREW LETTER ALEF - u'\u05d1' # 0xe1 -> HEBREW LETTER BET - u'\u05d2' # 0xe2 -> HEBREW LETTER GIMEL - u'\u05d3' # 0xe3 -> HEBREW LETTER DALET - u'\u05d4' # 0xe4 -> HEBREW LETTER HE - u'\u05d5' # 0xe5 -> HEBREW LETTER VAV - u'\u05d6' # 0xe6 -> HEBREW LETTER ZAYIN - u'\u05d7' # 0xe7 -> HEBREW LETTER HET - u'\u05d8' # 0xe8 -> HEBREW LETTER TET - u'\u05d9' # 0xe9 -> HEBREW LETTER YOD - u'\u05da' # 0xea -> HEBREW LETTER FINAL KAF - u'\u05db' # 0xeb -> HEBREW LETTER KAF - u'\u05dc' # 0xec -> HEBREW LETTER LAMED - u'\u05dd' # 0xed -> HEBREW LETTER FINAL MEM - u'\u05de' # 0xee -> HEBREW LETTER MEM - u'\u05df' # 0xef -> HEBREW LETTER FINAL NUN - u'\u05e0' # 0xf0 -> HEBREW LETTER NUN - u'\u05e1' # 0xf1 -> HEBREW LETTER SAMEKH - u'\u05e2' # 0xf2 -> HEBREW LETTER AYIN - u'\u05e3' # 0xf3 -> HEBREW LETTER FINAL PE - u'\u05e4' # 0xf4 -> HEBREW LETTER PE - u'\u05e5' # 0xf5 -> HEBREW LETTER FINAL TSADI - u'\u05e6' # 0xf6 -> HEBREW LETTER TSADI - u'\u05e7' # 0xf7 -> HEBREW LETTER QOF - u'\u05e8' # 0xf8 -> HEBREW LETTER RESH - u'\u05e9' # 0xf9 -> HEBREW LETTER SHIN - u'\u05ea' # 0xfa -> HEBREW LETTER TAV - u'\ufffe' # 0xfb -> UNDEFINED - u'\ufffe' # 0xfc -> UNDEFINED - u'\u200e' # 0xfd -> LEFT-TO-RIGHT MARK - u'\u200f' # 0xfe -> RIGHT-TO-LEFT MARK - u'\ufffe' # 0xff -> UNDEFINED + u'\ufffe' # 0x9A -> UNDEFINED + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\ufffe' # 0x9C -> UNDEFINED + u'\ufffe' # 0x9D -> UNDEFINED + u'\ufffe' # 0x9E -> UNDEFINED + u'\ufffe' # 0x9F -> UNDEFINED + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\u20aa' # 0xA4 -> NEW SHEQEL SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xd7' # 0xAA -> MULTIPLICATION SIGN + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xf7' # 0xBA -> DIVISION SIGN + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xbf' # 0xBF -> INVERTED QUESTION MARK + u'\u05b0' # 0xC0 -> HEBREW POINT SHEVA + u'\u05b1' # 0xC1 -> HEBREW POINT HATAF SEGOL + u'\u05b2' # 0xC2 -> HEBREW POINT HATAF PATAH + u'\u05b3' # 0xC3 -> HEBREW POINT HATAF QAMATS + u'\u05b4' # 0xC4 -> HEBREW POINT HIRIQ + u'\u05b5' # 0xC5 -> HEBREW POINT TSERE + u'\u05b6' # 0xC6 -> HEBREW POINT SEGOL + u'\u05b7' # 0xC7 -> HEBREW POINT PATAH + u'\u05b8' # 0xC8 -> HEBREW POINT QAMATS + u'\u05b9' # 0xC9 -> HEBREW POINT HOLAM + u'\ufffe' # 0xCA -> UNDEFINED + u'\u05bb' # 0xCB -> HEBREW POINT QUBUTS + u'\u05bc' # 0xCC -> HEBREW POINT DAGESH OR MAPIQ + u'\u05bd' # 0xCD -> HEBREW POINT METEG + u'\u05be' # 0xCE -> HEBREW PUNCTUATION MAQAF + u'\u05bf' # 0xCF -> HEBREW POINT RAFE + u'\u05c0' # 0xD0 -> HEBREW PUNCTUATION PASEQ + u'\u05c1' # 0xD1 -> HEBREW POINT SHIN DOT + u'\u05c2' # 0xD2 -> HEBREW POINT SIN DOT + u'\u05c3' # 0xD3 -> HEBREW PUNCTUATION SOF PASUQ + u'\u05f0' # 0xD4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV + u'\u05f1' # 0xD5 -> HEBREW LIGATURE YIDDISH VAV YOD + u'\u05f2' # 0xD6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD + u'\u05f3' # 0xD7 -> HEBREW PUNCTUATION GERESH + u'\u05f4' # 0xD8 -> HEBREW PUNCTUATION GERSHAYIM + u'\ufffe' # 0xD9 -> UNDEFINED + u'\ufffe' # 0xDA -> UNDEFINED + u'\ufffe' # 0xDB -> UNDEFINED + u'\ufffe' # 0xDC -> UNDEFINED + u'\ufffe' # 0xDD -> UNDEFINED + u'\ufffe' # 0xDE -> UNDEFINED + u'\ufffe' # 0xDF -> UNDEFINED + u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF + u'\u05d1' # 0xE1 -> HEBREW LETTER BET + u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL + u'\u05d3' # 0xE3 -> HEBREW LETTER DALET + u'\u05d4' # 0xE4 -> HEBREW LETTER HE + u'\u05d5' # 0xE5 -> HEBREW LETTER VAV + u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN + u'\u05d7' # 0xE7 -> HEBREW LETTER HET + u'\u05d8' # 0xE8 -> HEBREW LETTER TET + u'\u05d9' # 0xE9 -> HEBREW LETTER YOD + u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF + u'\u05db' # 0xEB -> HEBREW LETTER KAF + u'\u05dc' # 0xEC -> HEBREW LETTER LAMED + u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM + u'\u05de' # 0xEE -> HEBREW LETTER MEM + u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN + u'\u05e0' # 0xF0 -> HEBREW LETTER NUN + u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH + u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN + u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE + u'\u05e4' # 0xF4 -> HEBREW LETTER PE + u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI + u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI + u'\u05e7' # 0xF7 -> HEBREW LETTER QOF + u'\u05e8' # 0xF8 -> HEBREW LETTER RESH + u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN + u'\u05ea' # 0xFA -> HEBREW LETTER TAV + u'\ufffe' # 0xFB -> UNDEFINED + u'\ufffe' # 0xFC -> UNDEFINED + u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK + u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK + u'\ufffe' # 0xFF -> UNDEFINED ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,115 +415,116 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a1: 0xa1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xbf, # INVERTED QUESTION MARK - 0x00d7: 0xaa, # MULTIPLICATION SIGN - 0x00f7: 0xba, # DIVISION SIGN + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xBF, # INVERTED QUESTION MARK + 0x00D7: 0xAA, # MULTIPLICATION SIGN + 0x00F7: 0xBA, # DIVISION SIGN 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02dc: 0x98, # SMALL TILDE - 0x05b0: 0xc0, # HEBREW POINT SHEVA - 0x05b1: 0xc1, # HEBREW POINT HATAF SEGOL - 0x05b2: 0xc2, # HEBREW POINT HATAF PATAH - 0x05b3: 0xc3, # HEBREW POINT HATAF QAMATS - 0x05b4: 0xc4, # HEBREW POINT HIRIQ - 0x05b5: 0xc5, # HEBREW POINT TSERE - 0x05b6: 0xc6, # HEBREW POINT SEGOL - 0x05b7: 0xc7, # HEBREW POINT PATAH - 0x05b8: 0xc8, # HEBREW POINT QAMATS - 0x05b9: 0xc9, # HEBREW POINT HOLAM - 0x05bb: 0xcb, # HEBREW POINT QUBUTS - 0x05bc: 0xcc, # HEBREW POINT DAGESH OR MAPIQ - 0x05bd: 0xcd, # HEBREW POINT METEG - 0x05be: 0xce, # HEBREW PUNCTUATION MAQAF - 0x05bf: 0xcf, # HEBREW POINT RAFE - 0x05c0: 0xd0, # HEBREW PUNCTUATION PASEQ - 0x05c1: 0xd1, # HEBREW POINT SHIN DOT - 0x05c2: 0xd2, # HEBREW POINT SIN DOT - 0x05c3: 0xd3, # HEBREW PUNCTUATION SOF PASUQ - 0x05d0: 0xe0, # HEBREW LETTER ALEF - 0x05d1: 0xe1, # HEBREW LETTER BET - 0x05d2: 0xe2, # HEBREW LETTER GIMEL - 0x05d3: 0xe3, # HEBREW LETTER DALET - 0x05d4: 0xe4, # HEBREW LETTER HE - 0x05d5: 0xe5, # HEBREW LETTER VAV - 0x05d6: 0xe6, # HEBREW LETTER ZAYIN - 0x05d7: 0xe7, # HEBREW LETTER HET - 0x05d8: 0xe8, # HEBREW LETTER TET - 0x05d9: 0xe9, # HEBREW LETTER YOD - 0x05da: 0xea, # HEBREW LETTER FINAL KAF - 0x05db: 0xeb, # HEBREW LETTER KAF - 0x05dc: 0xec, # HEBREW LETTER LAMED - 0x05dd: 0xed, # HEBREW LETTER FINAL MEM - 0x05de: 0xee, # HEBREW LETTER MEM - 0x05df: 0xef, # HEBREW LETTER FINAL NUN - 0x05e0: 0xf0, # HEBREW LETTER NUN - 0x05e1: 0xf1, # HEBREW LETTER SAMEKH - 0x05e2: 0xf2, # HEBREW LETTER AYIN - 0x05e3: 0xf3, # HEBREW LETTER FINAL PE - 0x05e4: 0xf4, # HEBREW LETTER PE - 0x05e5: 0xf5, # HEBREW LETTER FINAL TSADI - 0x05e6: 0xf6, # HEBREW LETTER TSADI - 0x05e7: 0xf7, # HEBREW LETTER QOF - 0x05e8: 0xf8, # HEBREW LETTER RESH - 0x05e9: 0xf9, # HEBREW LETTER SHIN - 0x05ea: 0xfa, # HEBREW LETTER TAV - 0x05f0: 0xd4, # HEBREW LIGATURE YIDDISH DOUBLE VAV - 0x05f1: 0xd5, # HEBREW LIGATURE YIDDISH VAV YOD - 0x05f2: 0xd6, # HEBREW LIGATURE YIDDISH DOUBLE YOD - 0x05f3: 0xd7, # HEBREW PUNCTUATION GERESH - 0x05f4: 0xd8, # HEBREW PUNCTUATION GERSHAYIM - 0x200e: 0xfd, # LEFT-TO-RIGHT MARK - 0x200f: 0xfe, # RIGHT-TO-LEFT MARK + 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02DC: 0x98, # SMALL TILDE + 0x05B0: 0xC0, # HEBREW POINT SHEVA + 0x05B1: 0xC1, # HEBREW POINT HATAF SEGOL + 0x05B2: 0xC2, # HEBREW POINT HATAF PATAH + 0x05B3: 0xC3, # HEBREW POINT HATAF QAMATS + 0x05B4: 0xC4, # HEBREW POINT HIRIQ + 0x05B5: 0xC5, # HEBREW POINT TSERE + 0x05B6: 0xC6, # HEBREW POINT SEGOL + 0x05B7: 0xC7, # HEBREW POINT PATAH + 0x05B8: 0xC8, # HEBREW POINT QAMATS + 0x05B9: 0xC9, # HEBREW POINT HOLAM + 0x05BB: 0xCB, # HEBREW POINT QUBUTS + 0x05BC: 0xCC, # HEBREW POINT DAGESH OR MAPIQ + 0x05BD: 0xCD, # HEBREW POINT METEG + 0x05BE: 0xCE, # HEBREW PUNCTUATION MAQAF + 0x05BF: 0xCF, # HEBREW POINT RAFE + 0x05C0: 0xD0, # HEBREW PUNCTUATION PASEQ + 0x05C1: 0xD1, # HEBREW POINT SHIN DOT + 0x05C2: 0xD2, # HEBREW POINT SIN DOT + 0x05C3: 0xD3, # HEBREW PUNCTUATION SOF PASUQ + 0x05D0: 0xE0, # HEBREW LETTER ALEF + 0x05D1: 0xE1, # HEBREW LETTER BET + 0x05D2: 0xE2, # HEBREW LETTER GIMEL + 0x05D3: 0xE3, # HEBREW LETTER DALET + 0x05D4: 0xE4, # HEBREW LETTER HE + 0x05D5: 0xE5, # HEBREW LETTER VAV + 0x05D6: 0xE6, # HEBREW LETTER ZAYIN + 0x05D7: 0xE7, # HEBREW LETTER HET + 0x05D8: 0xE8, # HEBREW LETTER TET + 0x05D9: 0xE9, # HEBREW LETTER YOD + 0x05DA: 0xEA, # HEBREW LETTER FINAL KAF + 0x05DB: 0xEB, # HEBREW LETTER KAF + 0x05DC: 0xEC, # HEBREW LETTER LAMED + 0x05DD: 0xED, # HEBREW LETTER FINAL MEM + 0x05DE: 0xEE, # HEBREW LETTER MEM + 0x05DF: 0xEF, # HEBREW LETTER FINAL NUN + 0x05E0: 0xF0, # HEBREW LETTER NUN + 0x05E1: 0xF1, # HEBREW LETTER SAMEKH + 0x05E2: 0xF2, # HEBREW LETTER AYIN + 0x05E3: 0xF3, # HEBREW LETTER FINAL PE + 0x05E4: 0xF4, # HEBREW LETTER PE + 0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI + 0x05E6: 0xF6, # HEBREW LETTER TSADI + 0x05E7: 0xF7, # HEBREW LETTER QOF + 0x05E8: 0xF8, # HEBREW LETTER RESH + 0x05E9: 0xF9, # HEBREW LETTER SHIN + 0x05EA: 0xFA, # HEBREW LETTER TAV + 0x05F0: 0xD4, # HEBREW LIGATURE YIDDISH DOUBLE VAV + 0x05F1: 0xD5, # HEBREW LIGATURE YIDDISH VAV YOD + 0x05F2: 0xD6, # HEBREW LIGATURE YIDDISH DOUBLE YOD + 0x05F3: 0xD7, # HEBREW PUNCTUATION GERESH + 0x05F4: 0xD8, # HEBREW PUNCTUATION GERSHAYIM + 0x200E: 0xFD, # LEFT-TO-RIGHT MARK + 0x200F: 0xFE, # RIGHT-TO-LEFT MARK 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20aa: 0xa4, # NEW SHEQEL SIGN - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AA: 0xA4, # NEW SHEQEL SIGN + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1256.py b/Lib/encodings/cp1256.py index 17fa930..6d58fbe 100644 --- a/Lib/encodings/cp1256.py +++ b/Lib/encodings/cp1256.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\u067e' # 0x81 -> ARABIC LETTER PEH u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN - u'\u0679' # 0x8a -> ARABIC LETTER TTEH - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u0152' # 0x8c -> LATIN CAPITAL LIGATURE OE - u'\u0686' # 0x8d -> ARABIC LETTER TCHEH - u'\u0698' # 0x8e -> ARABIC LETTER JEH - u'\u0688' # 0x8f -> ARABIC LETTER DDAL + u'\u0679' # 0x8A -> ARABIC LETTER TTEH + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + u'\u0686' # 0x8D -> ARABIC LETTER TCHEH + u'\u0698' # 0x8E -> ARABIC LETTER JEH + u'\u0688' # 0x8F -> ARABIC LETTER DDAL u'\u06af' # 0x90 -> ARABIC LETTER GAF u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\u06a9' # 0x98 -> ARABIC LETTER KEHEH u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\u0691' # 0x9a -> ARABIC LETTER RREH - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u0153' # 0x9c -> LATIN SMALL LIGATURE OE - u'\u200c' # 0x9d -> ZERO WIDTH NON-JOINER - u'\u200d' # 0x9e -> ZERO WIDTH JOINER - u'\u06ba' # 0x9f -> ARABIC LETTER NOON GHUNNA - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u060c' # 0xa1 -> ARABIC COMMA - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u06be' # 0xaa -> ARABIC LETTER HEH DOACHASHMEE - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\u061b' # 0xba -> ARABIC SEMICOLON - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\u061f' # 0xbf -> ARABIC QUESTION MARK - u'\u06c1' # 0xc0 -> ARABIC LETTER HEH GOAL - u'\u0621' # 0xc1 -> ARABIC LETTER HAMZA - u'\u0622' # 0xc2 -> ARABIC LETTER ALEF WITH MADDA ABOVE - u'\u0623' # 0xc3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE - u'\u0624' # 0xc4 -> ARABIC LETTER WAW WITH HAMZA ABOVE - u'\u0625' # 0xc5 -> ARABIC LETTER ALEF WITH HAMZA BELOW - u'\u0626' # 0xc6 -> ARABIC LETTER YEH WITH HAMZA ABOVE - u'\u0627' # 0xc7 -> ARABIC LETTER ALEF - u'\u0628' # 0xc8 -> ARABIC LETTER BEH - u'\u0629' # 0xc9 -> ARABIC LETTER TEH MARBUTA - u'\u062a' # 0xca -> ARABIC LETTER TEH - u'\u062b' # 0xcb -> ARABIC LETTER THEH - u'\u062c' # 0xcc -> ARABIC LETTER JEEM - u'\u062d' # 0xcd -> ARABIC LETTER HAH - u'\u062e' # 0xce -> ARABIC LETTER KHAH - u'\u062f' # 0xcf -> ARABIC LETTER DAL - u'\u0630' # 0xd0 -> ARABIC LETTER THAL - u'\u0631' # 0xd1 -> ARABIC LETTER REH - u'\u0632' # 0xd2 -> ARABIC LETTER ZAIN - u'\u0633' # 0xd3 -> ARABIC LETTER SEEN - u'\u0634' # 0xd4 -> ARABIC LETTER SHEEN - u'\u0635' # 0xd5 -> ARABIC LETTER SAD - u'\u0636' # 0xd6 -> ARABIC LETTER DAD - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\u0637' # 0xd8 -> ARABIC LETTER TAH - u'\u0638' # 0xd9 -> ARABIC LETTER ZAH - u'\u0639' # 0xda -> ARABIC LETTER AIN - u'\u063a' # 0xdb -> ARABIC LETTER GHAIN - u'\u0640' # 0xdc -> ARABIC TATWEEL - u'\u0641' # 0xdd -> ARABIC LETTER FEH - u'\u0642' # 0xde -> ARABIC LETTER QAF - u'\u0643' # 0xdf -> ARABIC LETTER KAF - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\u0644' # 0xe1 -> ARABIC LETTER LAM - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\u0645' # 0xe3 -> ARABIC LETTER MEEM - u'\u0646' # 0xe4 -> ARABIC LETTER NOON - u'\u0647' # 0xe5 -> ARABIC LETTER HEH - u'\u0648' # 0xe6 -> ARABIC LETTER WAW - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\u0649' # 0xec -> ARABIC LETTER ALEF MAKSURA - u'\u064a' # 0xed -> ARABIC LETTER YEH - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\u064b' # 0xf0 -> ARABIC FATHATAN - u'\u064c' # 0xf1 -> ARABIC DAMMATAN - u'\u064d' # 0xf2 -> ARABIC KASRATAN - u'\u064e' # 0xf3 -> ARABIC FATHA - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\u064f' # 0xf5 -> ARABIC DAMMA - u'\u0650' # 0xf6 -> ARABIC KASRA - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\u0651' # 0xf8 -> ARABIC SHADDA - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\u0652' # 0xfa -> ARABIC SUKUN - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u200e' # 0xfd -> LEFT-TO-RIGHT MARK - u'\u200f' # 0xfe -> RIGHT-TO-LEFT MARK - u'\u06d2' # 0xff -> ARABIC LETTER YEH BARREE + u'\u0691' # 0x9A -> ARABIC LETTER RREH + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + u'\u200c' # 0x9D -> ZERO WIDTH NON-JOINER + u'\u200d' # 0x9E -> ZERO WIDTH JOINER + u'\u06ba' # 0x9F -> ARABIC LETTER NOON GHUNNA + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u060c' # 0xA1 -> ARABIC COMMA + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u06be' # 0xAA -> ARABIC LETTER HEH DOACHASHMEE + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\u061b' # 0xBA -> ARABIC SEMICOLON + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\u061f' # 0xBF -> ARABIC QUESTION MARK + u'\u06c1' # 0xC0 -> ARABIC LETTER HEH GOAL + u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA + u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE + u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE + u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE + u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW + u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE + u'\u0627' # 0xC7 -> ARABIC LETTER ALEF + u'\u0628' # 0xC8 -> ARABIC LETTER BEH + u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA + u'\u062a' # 0xCA -> ARABIC LETTER TEH + u'\u062b' # 0xCB -> ARABIC LETTER THEH + u'\u062c' # 0xCC -> ARABIC LETTER JEEM + u'\u062d' # 0xCD -> ARABIC LETTER HAH + u'\u062e' # 0xCE -> ARABIC LETTER KHAH + u'\u062f' # 0xCF -> ARABIC LETTER DAL + u'\u0630' # 0xD0 -> ARABIC LETTER THAL + u'\u0631' # 0xD1 -> ARABIC LETTER REH + u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN + u'\u0633' # 0xD3 -> ARABIC LETTER SEEN + u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN + u'\u0635' # 0xD5 -> ARABIC LETTER SAD + u'\u0636' # 0xD6 -> ARABIC LETTER DAD + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\u0637' # 0xD8 -> ARABIC LETTER TAH + u'\u0638' # 0xD9 -> ARABIC LETTER ZAH + u'\u0639' # 0xDA -> ARABIC LETTER AIN + u'\u063a' # 0xDB -> ARABIC LETTER GHAIN + u'\u0640' # 0xDC -> ARABIC TATWEEL + u'\u0641' # 0xDD -> ARABIC LETTER FEH + u'\u0642' # 0xDE -> ARABIC LETTER QAF + u'\u0643' # 0xDF -> ARABIC LETTER KAF + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\u0644' # 0xE1 -> ARABIC LETTER LAM + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\u0645' # 0xE3 -> ARABIC LETTER MEEM + u'\u0646' # 0xE4 -> ARABIC LETTER NOON + u'\u0647' # 0xE5 -> ARABIC LETTER HEH + u'\u0648' # 0xE6 -> ARABIC LETTER WAW + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\u0649' # 0xEC -> ARABIC LETTER ALEF MAKSURA + u'\u064a' # 0xED -> ARABIC LETTER YEH + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\u064b' # 0xF0 -> ARABIC FATHATAN + u'\u064c' # 0xF1 -> ARABIC DAMMATAN + u'\u064d' # 0xF2 -> ARABIC KASRATAN + u'\u064e' # 0xF3 -> ARABIC FATHA + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\u064f' # 0xF5 -> ARABIC DAMMA + u'\u0650' # 0xF6 -> ARABIC KASRA + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\u0651' # 0xF8 -> ARABIC SHADDA + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\u0652' # 0xFA -> ARABIC SUKUN + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK + u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK + u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x0152: 0x8c, # LATIN CAPITAL LIGATURE OE - 0x0153: 0x9c, # LATIN SMALL LIGATURE OE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE + 0x0153: 0x9C, # LATIN SMALL LIGATURE OE 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x060c: 0xa1, # ARABIC COMMA - 0x061b: 0xba, # ARABIC SEMICOLON - 0x061f: 0xbf, # ARABIC QUESTION MARK - 0x0621: 0xc1, # ARABIC LETTER HAMZA - 0x0622: 0xc2, # ARABIC LETTER ALEF WITH MADDA ABOVE - 0x0623: 0xc3, # ARABIC LETTER ALEF WITH HAMZA ABOVE - 0x0624: 0xc4, # ARABIC LETTER WAW WITH HAMZA ABOVE - 0x0625: 0xc5, # ARABIC LETTER ALEF WITH HAMZA BELOW - 0x0626: 0xc6, # ARABIC LETTER YEH WITH HAMZA ABOVE - 0x0627: 0xc7, # ARABIC LETTER ALEF - 0x0628: 0xc8, # ARABIC LETTER BEH - 0x0629: 0xc9, # ARABIC LETTER TEH MARBUTA - 0x062a: 0xca, # ARABIC LETTER TEH - 0x062b: 0xcb, # ARABIC LETTER THEH - 0x062c: 0xcc, # ARABIC LETTER JEEM - 0x062d: 0xcd, # ARABIC LETTER HAH - 0x062e: 0xce, # ARABIC LETTER KHAH - 0x062f: 0xcf, # ARABIC LETTER DAL - 0x0630: 0xd0, # ARABIC LETTER THAL - 0x0631: 0xd1, # ARABIC LETTER REH - 0x0632: 0xd2, # ARABIC LETTER ZAIN - 0x0633: 0xd3, # ARABIC LETTER SEEN - 0x0634: 0xd4, # ARABIC LETTER SHEEN - 0x0635: 0xd5, # ARABIC LETTER SAD - 0x0636: 0xd6, # ARABIC LETTER DAD - 0x0637: 0xd8, # ARABIC LETTER TAH - 0x0638: 0xd9, # ARABIC LETTER ZAH - 0x0639: 0xda, # ARABIC LETTER AIN - 0x063a: 0xdb, # ARABIC LETTER GHAIN - 0x0640: 0xdc, # ARABIC TATWEEL - 0x0641: 0xdd, # ARABIC LETTER FEH - 0x0642: 0xde, # ARABIC LETTER QAF - 0x0643: 0xdf, # ARABIC LETTER KAF - 0x0644: 0xe1, # ARABIC LETTER LAM - 0x0645: 0xe3, # ARABIC LETTER MEEM - 0x0646: 0xe4, # ARABIC LETTER NOON - 0x0647: 0xe5, # ARABIC LETTER HEH - 0x0648: 0xe6, # ARABIC LETTER WAW - 0x0649: 0xec, # ARABIC LETTER ALEF MAKSURA - 0x064a: 0xed, # ARABIC LETTER YEH - 0x064b: 0xf0, # ARABIC FATHATAN - 0x064c: 0xf1, # ARABIC DAMMATAN - 0x064d: 0xf2, # ARABIC KASRATAN - 0x064e: 0xf3, # ARABIC FATHA - 0x064f: 0xf5, # ARABIC DAMMA - 0x0650: 0xf6, # ARABIC KASRA - 0x0651: 0xf8, # ARABIC SHADDA - 0x0652: 0xfa, # ARABIC SUKUN - 0x0679: 0x8a, # ARABIC LETTER TTEH - 0x067e: 0x81, # ARABIC LETTER PEH - 0x0686: 0x8d, # ARABIC LETTER TCHEH - 0x0688: 0x8f, # ARABIC LETTER DDAL - 0x0691: 0x9a, # ARABIC LETTER RREH - 0x0698: 0x8e, # ARABIC LETTER JEH - 0x06a9: 0x98, # ARABIC LETTER KEHEH - 0x06af: 0x90, # ARABIC LETTER GAF - 0x06ba: 0x9f, # ARABIC LETTER NOON GHUNNA - 0x06be: 0xaa, # ARABIC LETTER HEH DOACHASHMEE - 0x06c1: 0xc0, # ARABIC LETTER HEH GOAL - 0x06d2: 0xff, # ARABIC LETTER YEH BARREE - 0x200c: 0x9d, # ZERO WIDTH NON-JOINER - 0x200d: 0x9e, # ZERO WIDTH JOINER - 0x200e: 0xfd, # LEFT-TO-RIGHT MARK - 0x200f: 0xfe, # RIGHT-TO-LEFT MARK + 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x060C: 0xA1, # ARABIC COMMA + 0x061B: 0xBA, # ARABIC SEMICOLON + 0x061F: 0xBF, # ARABIC QUESTION MARK + 0x0621: 0xC1, # ARABIC LETTER HAMZA + 0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE + 0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE + 0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE + 0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW + 0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE + 0x0627: 0xC7, # ARABIC LETTER ALEF + 0x0628: 0xC8, # ARABIC LETTER BEH + 0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA + 0x062A: 0xCA, # ARABIC LETTER TEH + 0x062B: 0xCB, # ARABIC LETTER THEH + 0x062C: 0xCC, # ARABIC LETTER JEEM + 0x062D: 0xCD, # ARABIC LETTER HAH + 0x062E: 0xCE, # ARABIC LETTER KHAH + 0x062F: 0xCF, # ARABIC LETTER DAL + 0x0630: 0xD0, # ARABIC LETTER THAL + 0x0631: 0xD1, # ARABIC LETTER REH + 0x0632: 0xD2, # ARABIC LETTER ZAIN + 0x0633: 0xD3, # ARABIC LETTER SEEN + 0x0634: 0xD4, # ARABIC LETTER SHEEN + 0x0635: 0xD5, # ARABIC LETTER SAD + 0x0636: 0xD6, # ARABIC LETTER DAD + 0x0637: 0xD8, # ARABIC LETTER TAH + 0x0638: 0xD9, # ARABIC LETTER ZAH + 0x0639: 0xDA, # ARABIC LETTER AIN + 0x063A: 0xDB, # ARABIC LETTER GHAIN + 0x0640: 0xDC, # ARABIC TATWEEL + 0x0641: 0xDD, # ARABIC LETTER FEH + 0x0642: 0xDE, # ARABIC LETTER QAF + 0x0643: 0xDF, # ARABIC LETTER KAF + 0x0644: 0xE1, # ARABIC LETTER LAM + 0x0645: 0xE3, # ARABIC LETTER MEEM + 0x0646: 0xE4, # ARABIC LETTER NOON + 0x0647: 0xE5, # ARABIC LETTER HEH + 0x0648: 0xE6, # ARABIC LETTER WAW + 0x0649: 0xEC, # ARABIC LETTER ALEF MAKSURA + 0x064A: 0xED, # ARABIC LETTER YEH + 0x064B: 0xF0, # ARABIC FATHATAN + 0x064C: 0xF1, # ARABIC DAMMATAN + 0x064D: 0xF2, # ARABIC KASRATAN + 0x064E: 0xF3, # ARABIC FATHA + 0x064F: 0xF5, # ARABIC DAMMA + 0x0650: 0xF6, # ARABIC KASRA + 0x0651: 0xF8, # ARABIC SHADDA + 0x0652: 0xFA, # ARABIC SUKUN + 0x0679: 0x8A, # ARABIC LETTER TTEH + 0x067E: 0x81, # ARABIC LETTER PEH + 0x0686: 0x8D, # ARABIC LETTER TCHEH + 0x0688: 0x8F, # ARABIC LETTER DDAL + 0x0691: 0x9A, # ARABIC LETTER RREH + 0x0698: 0x8E, # ARABIC LETTER JEH + 0x06A9: 0x98, # ARABIC LETTER KEHEH + 0x06AF: 0x90, # ARABIC LETTER GAF + 0x06BA: 0x9F, # ARABIC LETTER NOON GHUNNA + 0x06BE: 0xAA, # ARABIC LETTER HEH DOACHASHMEE + 0x06C1: 0xC0, # ARABIC LETTER HEH GOAL + 0x06D2: 0xFF, # ARABIC LETTER YEH BARREE + 0x200C: 0x9D, # ZERO WIDTH NON-JOINER + 0x200D: 0x9E, # ZERO WIDTH JOINER + 0x200E: 0xFD, # LEFT-TO-RIGHT MARK + 0x200F: 0xFE, # RIGHT-TO-LEFT MARK 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1257.py b/Lib/encodings/cp1257.py index 2aeab21..dee8fd4 100644 --- a/Lib/encodings/cp1257.py +++ b/Lib/encodings/cp1257.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\ufffe' # 0x88 -> UNDEFINED u'\u2030' # 0x89 -> PER MILLE SIGN - u'\ufffe' # 0x8a -> UNDEFINED - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\ufffe' # 0x8c -> UNDEFINED - u'\xa8' # 0x8d -> DIAERESIS - u'\u02c7' # 0x8e -> CARON - u'\xb8' # 0x8f -> CEDILLA + u'\ufffe' # 0x8A -> UNDEFINED + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\ufffe' # 0x8C -> UNDEFINED + u'\xa8' # 0x8D -> DIAERESIS + u'\u02c7' # 0x8E -> CARON + u'\xb8' # 0x8F -> CEDILLA u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\ufffe' # 0x9a -> UNDEFINED - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\ufffe' # 0x9c -> UNDEFINED - u'\xaf' # 0x9d -> MACRON - u'\u02db' # 0x9e -> OGONEK - u'\ufffe' # 0x9f -> UNDEFINED - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\ufffe' # 0xa1 -> UNDEFINED - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\ufffe' # 0xa5 -> UNDEFINED - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xd8' # 0xa8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u0156' # 0xaa -> LATIN CAPITAL LETTER R WITH CEDILLA - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xc6' # 0xaf -> LATIN CAPITAL LETTER AE - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xf8' # 0xb8 -> LATIN SMALL LETTER O WITH STROKE - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\u0157' # 0xba -> LATIN SMALL LETTER R WITH CEDILLA - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xe6' # 0xbf -> LATIN SMALL LETTER AE - u'\u0104' # 0xc0 -> LATIN CAPITAL LETTER A WITH OGONEK - u'\u012e' # 0xc1 -> LATIN CAPITAL LETTER I WITH OGONEK - u'\u0100' # 0xc2 -> LATIN CAPITAL LETTER A WITH MACRON - u'\u0106' # 0xc3 -> LATIN CAPITAL LETTER C WITH ACUTE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\u0118' # 0xc6 -> LATIN CAPITAL LETTER E WITH OGONEK - u'\u0112' # 0xc7 -> LATIN CAPITAL LETTER E WITH MACRON - u'\u010c' # 0xc8 -> LATIN CAPITAL LETTER C WITH CARON - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\u0179' # 0xca -> LATIN CAPITAL LETTER Z WITH ACUTE - u'\u0116' # 0xcb -> LATIN CAPITAL LETTER E WITH DOT ABOVE - u'\u0122' # 0xcc -> LATIN CAPITAL LETTER G WITH CEDILLA - u'\u0136' # 0xcd -> LATIN CAPITAL LETTER K WITH CEDILLA - u'\u012a' # 0xce -> LATIN CAPITAL LETTER I WITH MACRON - u'\u013b' # 0xcf -> LATIN CAPITAL LETTER L WITH CEDILLA - u'\u0160' # 0xd0 -> LATIN CAPITAL LETTER S WITH CARON - u'\u0143' # 0xd1 -> LATIN CAPITAL LETTER N WITH ACUTE - u'\u0145' # 0xd2 -> LATIN CAPITAL LETTER N WITH CEDILLA - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\u014c' # 0xd4 -> LATIN CAPITAL LETTER O WITH MACRON - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\u0172' # 0xd8 -> LATIN CAPITAL LETTER U WITH OGONEK - u'\u0141' # 0xd9 -> LATIN CAPITAL LETTER L WITH STROKE - u'\u015a' # 0xda -> LATIN CAPITAL LETTER S WITH ACUTE - u'\u016a' # 0xdb -> LATIN CAPITAL LETTER U WITH MACRON - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u017b' # 0xdd -> LATIN CAPITAL LETTER Z WITH DOT ABOVE - u'\u017d' # 0xde -> LATIN CAPITAL LETTER Z WITH CARON - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\u0105' # 0xe0 -> LATIN SMALL LETTER A WITH OGONEK - u'\u012f' # 0xe1 -> LATIN SMALL LETTER I WITH OGONEK - u'\u0101' # 0xe2 -> LATIN SMALL LETTER A WITH MACRON - u'\u0107' # 0xe3 -> LATIN SMALL LETTER C WITH ACUTE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\u0119' # 0xe6 -> LATIN SMALL LETTER E WITH OGONEK - u'\u0113' # 0xe7 -> LATIN SMALL LETTER E WITH MACRON - u'\u010d' # 0xe8 -> LATIN SMALL LETTER C WITH CARON - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\u017a' # 0xea -> LATIN SMALL LETTER Z WITH ACUTE - u'\u0117' # 0xeb -> LATIN SMALL LETTER E WITH DOT ABOVE - u'\u0123' # 0xec -> LATIN SMALL LETTER G WITH CEDILLA - u'\u0137' # 0xed -> LATIN SMALL LETTER K WITH CEDILLA - u'\u012b' # 0xee -> LATIN SMALL LETTER I WITH MACRON - u'\u013c' # 0xef -> LATIN SMALL LETTER L WITH CEDILLA - u'\u0161' # 0xf0 -> LATIN SMALL LETTER S WITH CARON - u'\u0144' # 0xf1 -> LATIN SMALL LETTER N WITH ACUTE - u'\u0146' # 0xf2 -> LATIN SMALL LETTER N WITH CEDILLA - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\u014d' # 0xf4 -> LATIN SMALL LETTER O WITH MACRON - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\u0173' # 0xf8 -> LATIN SMALL LETTER U WITH OGONEK - u'\u0142' # 0xf9 -> LATIN SMALL LETTER L WITH STROKE - u'\u015b' # 0xfa -> LATIN SMALL LETTER S WITH ACUTE - u'\u016b' # 0xfb -> LATIN SMALL LETTER U WITH MACRON - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u017c' # 0xfd -> LATIN SMALL LETTER Z WITH DOT ABOVE - u'\u017e' # 0xfe -> LATIN SMALL LETTER Z WITH CARON - u'\u02d9' # 0xff -> DOT ABOVE + u'\ufffe' # 0x9A -> UNDEFINED + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\ufffe' # 0x9C -> UNDEFINED + u'\xaf' # 0x9D -> MACRON + u'\u02db' # 0x9E -> OGONEK + u'\ufffe' # 0x9F -> UNDEFINED + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\ufffe' # 0xA1 -> UNDEFINED + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\ufffe' # 0xA5 -> UNDEFINED + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xc6' # 0xAF -> LATIN CAPITAL LETTER AE + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xe6' # 0xBF -> LATIN SMALL LETTER AE + u'\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK + u'\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK + u'\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON + u'\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK + u'\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON + u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE + u'\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE + u'\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA + u'\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA + u'\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON + u'\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA + u'\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON + u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + u'\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK + u'\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE + u'\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE + u'\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + u'\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK + u'\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK + u'\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON + u'\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK + u'\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON + u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE + u'\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE + u'\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA + u'\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA + u'\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON + u'\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA + u'\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON + u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + u'\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK + u'\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE + u'\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE + u'\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE + u'\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON + u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,126 +415,127 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0x8d, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0x9d, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0x8f, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xaf, # LATIN CAPITAL LETTER AE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xa8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xbf, # LATIN SMALL LETTER AE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xb8, # LATIN SMALL LETTER O WITH STROKE - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x0100: 0xc2, # LATIN CAPITAL LETTER A WITH MACRON - 0x0101: 0xe2, # LATIN SMALL LETTER A WITH MACRON - 0x0104: 0xc0, # LATIN CAPITAL LETTER A WITH OGONEK - 0x0105: 0xe0, # LATIN SMALL LETTER A WITH OGONEK - 0x0106: 0xc3, # LATIN CAPITAL LETTER C WITH ACUTE - 0x0107: 0xe3, # LATIN SMALL LETTER C WITH ACUTE - 0x010c: 0xc8, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xe8, # LATIN SMALL LETTER C WITH CARON - 0x0112: 0xc7, # LATIN CAPITAL LETTER E WITH MACRON - 0x0113: 0xe7, # LATIN SMALL LETTER E WITH MACRON - 0x0116: 0xcb, # LATIN CAPITAL LETTER E WITH DOT ABOVE - 0x0117: 0xeb, # LATIN SMALL LETTER E WITH DOT ABOVE - 0x0118: 0xc6, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xe6, # LATIN SMALL LETTER E WITH OGONEK - 0x0122: 0xcc, # LATIN CAPITAL LETTER G WITH CEDILLA - 0x0123: 0xec, # LATIN SMALL LETTER G WITH CEDILLA - 0x012a: 0xce, # LATIN CAPITAL LETTER I WITH MACRON - 0x012b: 0xee, # LATIN SMALL LETTER I WITH MACRON - 0x012e: 0xc1, # LATIN CAPITAL LETTER I WITH OGONEK - 0x012f: 0xe1, # LATIN SMALL LETTER I WITH OGONEK - 0x0136: 0xcd, # LATIN CAPITAL LETTER K WITH CEDILLA - 0x0137: 0xed, # LATIN SMALL LETTER K WITH CEDILLA - 0x013b: 0xcf, # LATIN CAPITAL LETTER L WITH CEDILLA - 0x013c: 0xef, # LATIN SMALL LETTER L WITH CEDILLA - 0x0141: 0xd9, # LATIN CAPITAL LETTER L WITH STROKE - 0x0142: 0xf9, # LATIN SMALL LETTER L WITH STROKE - 0x0143: 0xd1, # LATIN CAPITAL LETTER N WITH ACUTE - 0x0144: 0xf1, # LATIN SMALL LETTER N WITH ACUTE - 0x0145: 0xd2, # LATIN CAPITAL LETTER N WITH CEDILLA - 0x0146: 0xf2, # LATIN SMALL LETTER N WITH CEDILLA - 0x014c: 0xd4, # LATIN CAPITAL LETTER O WITH MACRON - 0x014d: 0xf4, # LATIN SMALL LETTER O WITH MACRON - 0x0156: 0xaa, # LATIN CAPITAL LETTER R WITH CEDILLA - 0x0157: 0xba, # LATIN SMALL LETTER R WITH CEDILLA - 0x015a: 0xda, # LATIN CAPITAL LETTER S WITH ACUTE - 0x015b: 0xfa, # LATIN SMALL LETTER S WITH ACUTE - 0x0160: 0xd0, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xf0, # LATIN SMALL LETTER S WITH CARON - 0x016a: 0xdb, # LATIN CAPITAL LETTER U WITH MACRON - 0x016b: 0xfb, # LATIN SMALL LETTER U WITH MACRON - 0x0172: 0xd8, # LATIN CAPITAL LETTER U WITH OGONEK - 0x0173: 0xf8, # LATIN SMALL LETTER U WITH OGONEK - 0x0179: 0xca, # LATIN CAPITAL LETTER Z WITH ACUTE - 0x017a: 0xea, # LATIN SMALL LETTER Z WITH ACUTE - 0x017b: 0xdd, # LATIN CAPITAL LETTER Z WITH DOT ABOVE - 0x017c: 0xfd, # LATIN SMALL LETTER Z WITH DOT ABOVE - 0x017d: 0xde, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xfe, # LATIN SMALL LETTER Z WITH CARON - 0x02c7: 0x8e, # CARON - 0x02d9: 0xff, # DOT ABOVE - 0x02db: 0x9e, # OGONEK + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0x8D, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0x9D, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0x8F, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xAF, # LATIN CAPITAL LETTER AE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xA8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xBF, # LATIN SMALL LETTER AE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xB8, # LATIN SMALL LETTER O WITH STROKE + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0100: 0xC2, # LATIN CAPITAL LETTER A WITH MACRON + 0x0101: 0xE2, # LATIN SMALL LETTER A WITH MACRON + 0x0104: 0xC0, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0xE0, # LATIN SMALL LETTER A WITH OGONEK + 0x0106: 0xC3, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0xE3, # LATIN SMALL LETTER C WITH ACUTE + 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON + 0x0112: 0xC7, # LATIN CAPITAL LETTER E WITH MACRON + 0x0113: 0xE7, # LATIN SMALL LETTER E WITH MACRON + 0x0116: 0xCB, # LATIN CAPITAL LETTER E WITH DOT ABOVE + 0x0117: 0xEB, # LATIN SMALL LETTER E WITH DOT ABOVE + 0x0118: 0xC6, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xE6, # LATIN SMALL LETTER E WITH OGONEK + 0x0122: 0xCC, # LATIN CAPITAL LETTER G WITH CEDILLA + 0x0123: 0xEC, # LATIN SMALL LETTER G WITH CEDILLA + 0x012A: 0xCE, # LATIN CAPITAL LETTER I WITH MACRON + 0x012B: 0xEE, # LATIN SMALL LETTER I WITH MACRON + 0x012E: 0xC1, # LATIN CAPITAL LETTER I WITH OGONEK + 0x012F: 0xE1, # LATIN SMALL LETTER I WITH OGONEK + 0x0136: 0xCD, # LATIN CAPITAL LETTER K WITH CEDILLA + 0x0137: 0xED, # LATIN SMALL LETTER K WITH CEDILLA + 0x013B: 0xCF, # LATIN CAPITAL LETTER L WITH CEDILLA + 0x013C: 0xEF, # LATIN SMALL LETTER L WITH CEDILLA + 0x0141: 0xD9, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0xF9, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE + 0x0145: 0xD2, # LATIN CAPITAL LETTER N WITH CEDILLA + 0x0146: 0xF2, # LATIN SMALL LETTER N WITH CEDILLA + 0x014C: 0xD4, # LATIN CAPITAL LETTER O WITH MACRON + 0x014D: 0xF4, # LATIN SMALL LETTER O WITH MACRON + 0x0156: 0xAA, # LATIN CAPITAL LETTER R WITH CEDILLA + 0x0157: 0xBA, # LATIN SMALL LETTER R WITH CEDILLA + 0x015A: 0xDA, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015B: 0xFA, # LATIN SMALL LETTER S WITH ACUTE + 0x0160: 0xD0, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xF0, # LATIN SMALL LETTER S WITH CARON + 0x016A: 0xDB, # LATIN CAPITAL LETTER U WITH MACRON + 0x016B: 0xFB, # LATIN SMALL LETTER U WITH MACRON + 0x0172: 0xD8, # LATIN CAPITAL LETTER U WITH OGONEK + 0x0173: 0xF8, # LATIN SMALL LETTER U WITH OGONEK + 0x0179: 0xCA, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017A: 0xEA, # LATIN SMALL LETTER Z WITH ACUTE + 0x017B: 0xDD, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017C: 0xFD, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017D: 0xDE, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xFE, # LATIN SMALL LETTER Z WITH CARON + 0x02C7: 0x8E, # CARON + 0x02D9: 0xFF, # DOT ABOVE + 0x02DB: 0x9E, # OGONEK 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp1258.py b/Lib/encodings/cp1258.py index 67f04de..43a9ba1 100644 --- a/Lib/encodings/cp1258.py +++ b/Lib/encodings/cp1258.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK @@ -170,12 +170,12 @@ decoding_table = ( u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN - u'\ufffe' # 0x8a -> UNDEFINED - u'\u2039' # 0x8b -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u0152' # 0x8c -> LATIN CAPITAL LIGATURE OE - u'\ufffe' # 0x8d -> UNDEFINED - u'\ufffe' # 0x8e -> UNDEFINED - u'\ufffe' # 0x8f -> UNDEFINED + u'\ufffe' # 0x8A -> UNDEFINED + u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + u'\ufffe' # 0x8D -> UNDEFINED + u'\ufffe' # 0x8E -> UNDEFINED + u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN - u'\ufffe' # 0x9a -> UNDEFINED - u'\u203a' # 0x9b -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u0153' # 0x9c -> LATIN SMALL LIGATURE OE - u'\ufffe' # 0x9d -> UNDEFINED - u'\ufffe' # 0x9e -> UNDEFINED - u'\u0178' # 0x9f -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\xa1' # 0xa1 -> INVERTED EXCLAMATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xaa' # 0xaa -> FEMININE ORDINAL INDICATOR - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xba' # 0xba -> MASCULINE ORDINAL INDICATOR - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xbf' # 0xbf -> INVERTED QUESTION MARK - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\u0102' # 0xc3 -> LATIN CAPITAL LETTER A WITH BREVE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\u0300' # 0xcc -> COMBINING GRAVE ACCENT - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\u0110' # 0xd0 -> LATIN CAPITAL LETTER D WITH STROKE - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\u0309' # 0xd2 -> COMBINING HOOK ABOVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\u01a0' # 0xd5 -> LATIN CAPITAL LETTER O WITH HORN - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u01af' # 0xdd -> LATIN CAPITAL LETTER U WITH HORN - u'\u0303' # 0xde -> COMBINING TILDE - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\u0103' # 0xe3 -> LATIN SMALL LETTER A WITH BREVE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\u0301' # 0xec -> COMBINING ACUTE ACCENT - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\u0111' # 0xf0 -> LATIN SMALL LETTER D WITH STROKE - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\u0323' # 0xf2 -> COMBINING DOT BELOW - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\u01a1' # 0xf5 -> LATIN SMALL LETTER O WITH HORN - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u01b0' # 0xfd -> LATIN SMALL LETTER U WITH HORN - u'\u20ab' # 0xfe -> DONG SIGN - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\ufffe' # 0x9A -> UNDEFINED + u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + u'\ufffe' # 0x9D -> UNDEFINED + u'\ufffe' # 0x9E -> UNDEFINED + u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xbf' # 0xBF -> INVERTED QUESTION MARK + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\u0300' # 0xCC -> COMBINING GRAVE ACCENT + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\u0309' # 0xD2 -> COMBINING HOOK ABOVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\u01a0' # 0xD5 -> LATIN CAPITAL LETTER O WITH HORN + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u01af' # 0xDD -> LATIN CAPITAL LETTER U WITH HORN + u'\u0303' # 0xDE -> COMBINING TILDE + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\u0301' # 0xEC -> COMBINING ACUTE ACCENT + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\u0323' # 0xF2 -> COMBINING DOT BELOW + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\u01a1' # 0xF5 -> LATIN SMALL LETTER O WITH HORN + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u01b0' # 0xFD -> LATIN SMALL LETTER U WITH HORN + u'\u20ab' # 0xFE -> DONG SIGN + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,129 +415,130 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a1: 0xa1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xaa, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00ba: 0xba, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xbf, # INVERTED QUESTION MARK - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x0102: 0xc3, # LATIN CAPITAL LETTER A WITH BREVE - 0x0103: 0xe3, # LATIN SMALL LETTER A WITH BREVE - 0x0110: 0xd0, # LATIN CAPITAL LETTER D WITH STROKE - 0x0111: 0xf0, # LATIN SMALL LETTER D WITH STROKE - 0x0152: 0x8c, # LATIN CAPITAL LIGATURE OE - 0x0153: 0x9c, # LATIN SMALL LIGATURE OE - 0x0178: 0x9f, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xBF, # INVERTED QUESTION MARK + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE + 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE + 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE + 0x0152: 0x8C, # LATIN CAPITAL LIGATURE OE + 0x0153: 0x9C, # LATIN SMALL LIGATURE OE + 0x0178: 0x9F, # LATIN CAPITAL LETTER Y WITH DIAERESIS 0x0192: 0x83, # LATIN SMALL LETTER F WITH HOOK - 0x01a0: 0xd5, # LATIN CAPITAL LETTER O WITH HORN - 0x01a1: 0xf5, # LATIN SMALL LETTER O WITH HORN - 0x01af: 0xdd, # LATIN CAPITAL LETTER U WITH HORN - 0x01b0: 0xfd, # LATIN SMALL LETTER U WITH HORN - 0x02c6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02dc: 0x98, # SMALL TILDE - 0x0300: 0xcc, # COMBINING GRAVE ACCENT - 0x0301: 0xec, # COMBINING ACUTE ACCENT - 0x0303: 0xde, # COMBINING TILDE - 0x0309: 0xd2, # COMBINING HOOK ABOVE - 0x0323: 0xf2, # COMBINING DOT BELOW + 0x01A0: 0xD5, # LATIN CAPITAL LETTER O WITH HORN + 0x01A1: 0xF5, # LATIN SMALL LETTER O WITH HORN + 0x01AF: 0xDD, # LATIN CAPITAL LETTER U WITH HORN + 0x01B0: 0xFD, # LATIN SMALL LETTER U WITH HORN + 0x02C6: 0x88, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02DC: 0x98, # SMALL TILDE + 0x0300: 0xCC, # COMBINING GRAVE ACCENT + 0x0301: 0xEC, # COMBINING ACUTE ACCENT + 0x0303: 0xDE, # COMBINING TILDE + 0x0309: 0xD2, # COMBINING HOOK ABOVE + 0x0323: 0xF2, # COMBINING DOT BELOW 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0x82, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0x84, # DOUBLE LOW-9 QUOTATION MARK + 0x201A: 0x82, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0x84, # DOUBLE LOW-9 QUOTATION MARK 0x2020: 0x86, # DAGGER 0x2021: 0x87, # DOUBLE DAGGER 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS 0x2030: 0x89, # PER MILLE SIGN - 0x2039: 0x8b, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0x9b, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x20ab: 0xfe, # DONG SIGN - 0x20ac: 0x80, # EURO SIGN + 0x2039: 0x8B, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0x9B, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x20AB: 0xFE, # DONG SIGN + 0x20AC: 0x80, # EURO SIGN 0x2122: 0x99, # TRADE MARK SIGN -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp424.py b/Lib/encodings/cp424.py index 4748690..60082e8 100644 --- a/Lib/encodings/cp424.py +++ b/Lib/encodings/cp424.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> GRAPHIC ESCAPE u'\x8d' # 0x09 -> SUPERSCRIPT - u'\x8e' # 0x0a -> REPEAT - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\x8e' # 0x0A -> REPEAT + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x92' # 0x1a -> UNIT BACK SPACE - u'\x8f' # 0x1b -> CUSTOMER USE ONE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x92' # 0x1A -> UNIT BACK SPACE + u'\x8f' # 0x1B -> CUSTOMER USE ONE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> DIGIT SELECT u'\x81' # 0x21 -> START OF SIGNIFICANCE u'\x82' # 0x22 -> FIELD SEPARATOR @@ -74,12 +74,12 @@ decoding_table = ( u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> SET ATTRIBUTE u'\x89' # 0x29 -> START FIELD EXTENDED - u'\x8a' # 0x2a -> SET MODE OR SWITCH - u'\x8b' # 0x2b -> CONTROL SEQUENCE PREFIX - u'\x8c' # 0x2c -> MODIFY FIELD ATTRIBUTE - u'\x05' # 0x2d -> ENQUIRY - u'\x06' # 0x2e -> ACKNOWLEDGE - u'\x07' # 0x2f -> BELL + u'\x8a' # 0x2A -> SET MODE OR SWITCH + u'\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX + u'\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE + u'\x05' # 0x2D -> ENQUIRY + u'\x06' # 0x2E -> ACKNOWLEDGE + u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> u'\x91' # 0x31 -> u'\x16' # 0x32 -> SYNCHRONOUS IDLE @@ -90,12 +90,12 @@ decoding_table = ( u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> SUBSCRIPT u'\x99' # 0x39 -> INDENT TABULATION - u'\x9a' # 0x3a -> REVERSE FORM FEED - u'\x9b' # 0x3b -> CUSTOMER USE THREE - u'\x14' # 0x3c -> DEVICE CONTROL FOUR - u'\x15' # 0x3d -> NEGATIVE ACKNOWLEDGE - u'\x9e' # 0x3e -> - u'\x1a' # 0x3f -> SUBSTITUTE + u'\x9a' # 0x3A -> REVERSE FORM FEED + u'\x9b' # 0x3B -> CUSTOMER USE THREE + u'\x14' # 0x3C -> DEVICE CONTROL FOUR + u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + u'\x9e' # 0x3E -> + u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\u05d0' # 0x41 -> HEBREW LETTER ALEF u'\u05d1' # 0x42 -> HEBREW LETTER BET @@ -106,12 +106,12 @@ decoding_table = ( u'\u05d6' # 0x47 -> HEBREW LETTER ZAYIN u'\u05d7' # 0x48 -> HEBREW LETTER HET u'\u05d8' # 0x49 -> HEBREW LETTER TET - u'\xa2' # 0x4a -> CENT SIGN - u'.' # 0x4b -> FULL STOP - u'<' # 0x4c -> LESS-THAN SIGN - u'(' # 0x4d -> LEFT PARENTHESIS - u'+' # 0x4e -> PLUS SIGN - u'|' # 0x4f -> VERTICAL LINE + u'\xa2' # 0x4A -> CENT SIGN + u'.' # 0x4B -> FULL STOP + u'<' # 0x4C -> LESS-THAN SIGN + u'(' # 0x4D -> LEFT PARENTHESIS + u'+' # 0x4E -> PLUS SIGN + u'|' # 0x4F -> VERTICAL LINE u'&' # 0x50 -> AMPERSAND u'\u05d9' # 0x51 -> HEBREW LETTER YOD u'\u05da' # 0x52 -> HEBREW LETTER FINAL KAF @@ -122,12 +122,12 @@ decoding_table = ( u'\u05df' # 0x57 -> HEBREW LETTER FINAL NUN u'\u05e0' # 0x58 -> HEBREW LETTER NUN u'\u05e1' # 0x59 -> HEBREW LETTER SAMEKH - u'!' # 0x5a -> EXCLAMATION MARK - u'$' # 0x5b -> DOLLAR SIGN - u'*' # 0x5c -> ASTERISK - u')' # 0x5d -> RIGHT PARENTHESIS - u';' # 0x5e -> SEMICOLON - u'\xac' # 0x5f -> NOT SIGN + u'!' # 0x5A -> EXCLAMATION MARK + u'$' # 0x5B -> DOLLAR SIGN + u'*' # 0x5C -> ASTERISK + u')' # 0x5D -> RIGHT PARENTHESIS + u';' # 0x5E -> SEMICOLON + u'\xac' # 0x5F -> NOT SIGN u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\u05e2' # 0x62 -> HEBREW LETTER AYIN @@ -138,12 +138,12 @@ decoding_table = ( u'\u05e7' # 0x67 -> HEBREW LETTER QOF u'\u05e8' # 0x68 -> HEBREW LETTER RESH u'\u05e9' # 0x69 -> HEBREW LETTER SHIN - u'\xa6' # 0x6a -> BROKEN BAR - u',' # 0x6b -> COMMA - u'%' # 0x6c -> PERCENT SIGN - u'_' # 0x6d -> LOW LINE - u'>' # 0x6e -> GREATER-THAN SIGN - u'?' # 0x6f -> QUESTION MARK + u'\xa6' # 0x6A -> BROKEN BAR + u',' # 0x6B -> COMMA + u'%' # 0x6C -> PERCENT SIGN + u'_' # 0x6D -> LOW LINE + u'>' # 0x6E -> GREATER-THAN SIGN + u'?' # 0x6F -> QUESTION MARK u'\ufffe' # 0x70 -> UNDEFINED u'\u05ea' # 0x71 -> HEBREW LETTER TAV u'\ufffe' # 0x72 -> UNDEFINED @@ -154,12 +154,12 @@ decoding_table = ( u'\ufffe' # 0x77 -> UNDEFINED u'\u2017' # 0x78 -> DOUBLE LOW LINE u'`' # 0x79 -> GRAVE ACCENT - u':' # 0x7a -> COLON - u'#' # 0x7b -> NUMBER SIGN - u'@' # 0x7c -> COMMERCIAL AT - u"'" # 0x7d -> APOSTROPHE - u'=' # 0x7e -> EQUALS SIGN - u'"' # 0x7f -> QUOTATION MARK + u':' # 0x7A -> COLON + u'#' # 0x7B -> NUMBER SIGN + u'@' # 0x7C -> COMMERCIAL AT + u"'" # 0x7D -> APOSTROPHE + u'=' # 0x7E -> EQUALS SIGN + u'"' # 0x7F -> QUOTATION MARK u'\ufffe' # 0x80 -> UNDEFINED u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B @@ -170,12 +170,12 @@ decoding_table = ( u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I - u'\xab' # 0x8a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0x8b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\ufffe' # 0x8c -> UNDEFINED - u'\ufffe' # 0x8d -> UNDEFINED - u'\ufffe' # 0x8e -> UNDEFINED - u'\xb1' # 0x8f -> PLUS-MINUS SIGN + u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\ufffe' # 0x8C -> UNDEFINED + u'\ufffe' # 0x8D -> UNDEFINED + u'\ufffe' # 0x8E -> UNDEFINED + u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K @@ -186,108 +186,108 @@ decoding_table = ( u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R - u'\ufffe' # 0x9a -> UNDEFINED - u'\ufffe' # 0x9b -> UNDEFINED - u'\ufffe' # 0x9c -> UNDEFINED - u'\xb8' # 0x9d -> CEDILLA - u'\ufffe' # 0x9e -> UNDEFINED - u'\xa4' # 0x9f -> CURRENCY SIGN - u'\xb5' # 0xa0 -> MICRO SIGN - u'~' # 0xa1 -> TILDE - u's' # 0xa2 -> LATIN SMALL LETTER S - u't' # 0xa3 -> LATIN SMALL LETTER T - u'u' # 0xa4 -> LATIN SMALL LETTER U - u'v' # 0xa5 -> LATIN SMALL LETTER V - u'w' # 0xa6 -> LATIN SMALL LETTER W - u'x' # 0xa7 -> LATIN SMALL LETTER X - u'y' # 0xa8 -> LATIN SMALL LETTER Y - u'z' # 0xa9 -> LATIN SMALL LETTER Z - u'\ufffe' # 0xaa -> UNDEFINED - u'\ufffe' # 0xab -> UNDEFINED - u'\ufffe' # 0xac -> UNDEFINED - u'\ufffe' # 0xad -> UNDEFINED - u'\ufffe' # 0xae -> UNDEFINED - u'\xae' # 0xaf -> REGISTERED SIGN - u'^' # 0xb0 -> CIRCUMFLEX ACCENT - u'\xa3' # 0xb1 -> POUND SIGN - u'\xa5' # 0xb2 -> YEN SIGN - u'\xb7' # 0xb3 -> MIDDLE DOT - u'\xa9' # 0xb4 -> COPYRIGHT SIGN - u'\xa7' # 0xb5 -> SECTION SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xbc' # 0xb7 -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xb8 -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xb9 -> VULGAR FRACTION THREE QUARTERS - u'[' # 0xba -> LEFT SQUARE BRACKET - u']' # 0xbb -> RIGHT SQUARE BRACKET - u'\xaf' # 0xbc -> MACRON - u'\xa8' # 0xbd -> DIAERESIS - u'\xb4' # 0xbe -> ACUTE ACCENT - u'\xd7' # 0xbf -> MULTIPLICATION SIGN - u'{' # 0xc0 -> LEFT CURLY BRACKET - u'A' # 0xc1 -> LATIN CAPITAL LETTER A - u'B' # 0xc2 -> LATIN CAPITAL LETTER B - u'C' # 0xc3 -> LATIN CAPITAL LETTER C - u'D' # 0xc4 -> LATIN CAPITAL LETTER D - u'E' # 0xc5 -> LATIN CAPITAL LETTER E - u'F' # 0xc6 -> LATIN CAPITAL LETTER F - u'G' # 0xc7 -> LATIN CAPITAL LETTER G - u'H' # 0xc8 -> LATIN CAPITAL LETTER H - u'I' # 0xc9 -> LATIN CAPITAL LETTER I - u'\xad' # 0xca -> SOFT HYPHEN - u'\ufffe' # 0xcb -> UNDEFINED - u'\ufffe' # 0xcc -> UNDEFINED - u'\ufffe' # 0xcd -> UNDEFINED - u'\ufffe' # 0xce -> UNDEFINED - u'\ufffe' # 0xcf -> UNDEFINED - u'}' # 0xd0 -> RIGHT CURLY BRACKET - u'J' # 0xd1 -> LATIN CAPITAL LETTER J - u'K' # 0xd2 -> LATIN CAPITAL LETTER K - u'L' # 0xd3 -> LATIN CAPITAL LETTER L - u'M' # 0xd4 -> LATIN CAPITAL LETTER M - u'N' # 0xd5 -> LATIN CAPITAL LETTER N - u'O' # 0xd6 -> LATIN CAPITAL LETTER O - u'P' # 0xd7 -> LATIN CAPITAL LETTER P - u'Q' # 0xd8 -> LATIN CAPITAL LETTER Q - u'R' # 0xd9 -> LATIN CAPITAL LETTER R - u'\xb9' # 0xda -> SUPERSCRIPT ONE - u'\ufffe' # 0xdb -> UNDEFINED - u'\ufffe' # 0xdc -> UNDEFINED - u'\ufffe' # 0xdd -> UNDEFINED - u'\ufffe' # 0xde -> UNDEFINED - u'\ufffe' # 0xdf -> UNDEFINED - u'\\' # 0xe0 -> REVERSE SOLIDUS - u'\xf7' # 0xe1 -> DIVISION SIGN - u'S' # 0xe2 -> LATIN CAPITAL LETTER S - u'T' # 0xe3 -> LATIN CAPITAL LETTER T - u'U' # 0xe4 -> LATIN CAPITAL LETTER U - u'V' # 0xe5 -> LATIN CAPITAL LETTER V - u'W' # 0xe6 -> LATIN CAPITAL LETTER W - u'X' # 0xe7 -> LATIN CAPITAL LETTER X - u'Y' # 0xe8 -> LATIN CAPITAL LETTER Y - u'Z' # 0xe9 -> LATIN CAPITAL LETTER Z - u'\xb2' # 0xea -> SUPERSCRIPT TWO - u'\ufffe' # 0xeb -> UNDEFINED - u'\ufffe' # 0xec -> UNDEFINED - u'\ufffe' # 0xed -> UNDEFINED - u'\ufffe' # 0xee -> UNDEFINED - u'\ufffe' # 0xef -> UNDEFINED - u'0' # 0xf0 -> DIGIT ZERO - u'1' # 0xf1 -> DIGIT ONE - u'2' # 0xf2 -> DIGIT TWO - u'3' # 0xf3 -> DIGIT THREE - u'4' # 0xf4 -> DIGIT FOUR - u'5' # 0xf5 -> DIGIT FIVE - u'6' # 0xf6 -> DIGIT SIX - u'7' # 0xf7 -> DIGIT SEVEN - u'8' # 0xf8 -> DIGIT EIGHT - u'9' # 0xf9 -> DIGIT NINE - u'\xb3' # 0xfa -> SUPERSCRIPT THREE - u'\ufffe' # 0xfb -> UNDEFINED - u'\ufffe' # 0xfc -> UNDEFINED - u'\ufffe' # 0xfd -> UNDEFINED - u'\ufffe' # 0xfe -> UNDEFINED - u'\x9f' # 0xff -> EIGHT ONES + u'\ufffe' # 0x9A -> UNDEFINED + u'\ufffe' # 0x9B -> UNDEFINED + u'\ufffe' # 0x9C -> UNDEFINED + u'\xb8' # 0x9D -> CEDILLA + u'\ufffe' # 0x9E -> UNDEFINED + u'\xa4' # 0x9F -> CURRENCY SIGN + u'\xb5' # 0xA0 -> MICRO SIGN + u'~' # 0xA1 -> TILDE + u's' # 0xA2 -> LATIN SMALL LETTER S + u't' # 0xA3 -> LATIN SMALL LETTER T + u'u' # 0xA4 -> LATIN SMALL LETTER U + u'v' # 0xA5 -> LATIN SMALL LETTER V + u'w' # 0xA6 -> LATIN SMALL LETTER W + u'x' # 0xA7 -> LATIN SMALL LETTER X + u'y' # 0xA8 -> LATIN SMALL LETTER Y + u'z' # 0xA9 -> LATIN SMALL LETTER Z + u'\ufffe' # 0xAA -> UNDEFINED + u'\ufffe' # 0xAB -> UNDEFINED + u'\ufffe' # 0xAC -> UNDEFINED + u'\ufffe' # 0xAD -> UNDEFINED + u'\ufffe' # 0xAE -> UNDEFINED + u'\xae' # 0xAF -> REGISTERED SIGN + u'^' # 0xB0 -> CIRCUMFLEX ACCENT + u'\xa3' # 0xB1 -> POUND SIGN + u'\xa5' # 0xB2 -> YEN SIGN + u'\xb7' # 0xB3 -> MIDDLE DOT + u'\xa9' # 0xB4 -> COPYRIGHT SIGN + u'\xa7' # 0xB5 -> SECTION SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + u'[' # 0xBA -> LEFT SQUARE BRACKET + u']' # 0xBB -> RIGHT SQUARE BRACKET + u'\xaf' # 0xBC -> MACRON + u'\xa8' # 0xBD -> DIAERESIS + u'\xb4' # 0xBE -> ACUTE ACCENT + u'\xd7' # 0xBF -> MULTIPLICATION SIGN + u'{' # 0xC0 -> LEFT CURLY BRACKET + u'A' # 0xC1 -> LATIN CAPITAL LETTER A + u'B' # 0xC2 -> LATIN CAPITAL LETTER B + u'C' # 0xC3 -> LATIN CAPITAL LETTER C + u'D' # 0xC4 -> LATIN CAPITAL LETTER D + u'E' # 0xC5 -> LATIN CAPITAL LETTER E + u'F' # 0xC6 -> LATIN CAPITAL LETTER F + u'G' # 0xC7 -> LATIN CAPITAL LETTER G + u'H' # 0xC8 -> LATIN CAPITAL LETTER H + u'I' # 0xC9 -> LATIN CAPITAL LETTER I + u'\xad' # 0xCA -> SOFT HYPHEN + u'\ufffe' # 0xCB -> UNDEFINED + u'\ufffe' # 0xCC -> UNDEFINED + u'\ufffe' # 0xCD -> UNDEFINED + u'\ufffe' # 0xCE -> UNDEFINED + u'\ufffe' # 0xCF -> UNDEFINED + u'}' # 0xD0 -> RIGHT CURLY BRACKET + u'J' # 0xD1 -> LATIN CAPITAL LETTER J + u'K' # 0xD2 -> LATIN CAPITAL LETTER K + u'L' # 0xD3 -> LATIN CAPITAL LETTER L + u'M' # 0xD4 -> LATIN CAPITAL LETTER M + u'N' # 0xD5 -> LATIN CAPITAL LETTER N + u'O' # 0xD6 -> LATIN CAPITAL LETTER O + u'P' # 0xD7 -> LATIN CAPITAL LETTER P + u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + u'R' # 0xD9 -> LATIN CAPITAL LETTER R + u'\xb9' # 0xDA -> SUPERSCRIPT ONE + u'\ufffe' # 0xDB -> UNDEFINED + u'\ufffe' # 0xDC -> UNDEFINED + u'\ufffe' # 0xDD -> UNDEFINED + u'\ufffe' # 0xDE -> UNDEFINED + u'\ufffe' # 0xDF -> UNDEFINED + u'\\' # 0xE0 -> REVERSE SOLIDUS + u'\xf7' # 0xE1 -> DIVISION SIGN + u'S' # 0xE2 -> LATIN CAPITAL LETTER S + u'T' # 0xE3 -> LATIN CAPITAL LETTER T + u'U' # 0xE4 -> LATIN CAPITAL LETTER U + u'V' # 0xE5 -> LATIN CAPITAL LETTER V + u'W' # 0xE6 -> LATIN CAPITAL LETTER W + u'X' # 0xE7 -> LATIN CAPITAL LETTER X + u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + u'\xb2' # 0xEA -> SUPERSCRIPT TWO + u'\ufffe' # 0xEB -> UNDEFINED + u'\ufffe' # 0xEC -> UNDEFINED + u'\ufffe' # 0xED -> UNDEFINED + u'\ufffe' # 0xEE -> UNDEFINED + u'\ufffe' # 0xEF -> UNDEFINED + u'0' # 0xF0 -> DIGIT ZERO + u'1' # 0xF1 -> DIGIT ONE + u'2' # 0xF2 -> DIGIT TWO + u'3' # 0xF3 -> DIGIT THREE + u'4' # 0xF4 -> DIGIT FOUR + u'5' # 0xF5 -> DIGIT FIVE + u'6' # 0xF6 -> DIGIT SIX + u'7' # 0xF7 -> DIGIT SEVEN + u'8' # 0xF8 -> DIGIT EIGHT + u'9' # 0xF9 -> DIGIT NINE + u'\xb3' # 0xFA -> SUPERSCRIPT THREE + u'\ufffe' # 0xFB -> UNDEFINED + u'\ufffe' # 0xFC -> UNDEFINED + u'\ufffe' # 0xFD -> UNDEFINED + u'\ufffe' # 0xFE -> UNDEFINED + u'\x9f' # 0xFF -> EIGHT ONES ) ### Encoding Map @@ -298,97 +298,97 @@ encoding_map = { 0x0002: 0x02, # START OF TEXT 0x0003: 0x03, # END OF TEXT 0x0004: 0x37, # END OF TRANSMISSION - 0x0005: 0x2d, # ENQUIRY - 0x0006: 0x2e, # ACKNOWLEDGE - 0x0007: 0x2f, # BELL + 0x0005: 0x2D, # ENQUIRY + 0x0006: 0x2E, # ACKNOWLEDGE + 0x0007: 0x2F, # BELL 0x0008: 0x16, # BACKSPACE 0x0009: 0x05, # HORIZONTAL TABULATION - 0x000a: 0x25, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x25, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO 0x0013: 0x13, # DEVICE CONTROL THREE - 0x0014: 0x3c, # DEVICE CONTROL FOUR - 0x0015: 0x3d, # NEGATIVE ACKNOWLEDGE + 0x0014: 0x3C, # DEVICE CONTROL FOUR + 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE 0x0016: 0x32, # SYNCHRONOUS IDLE 0x0017: 0x26, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x3f, # SUBSTITUTE - 0x001b: 0x27, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x3F, # SUBSTITUTE + 0x001B: 0x27, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x40, # SPACE - 0x0021: 0x5a, # EXCLAMATION MARK - 0x0022: 0x7f, # QUOTATION MARK - 0x0023: 0x7b, # NUMBER SIGN - 0x0024: 0x5b, # DOLLAR SIGN - 0x0025: 0x6c, # PERCENT SIGN + 0x0021: 0x5A, # EXCLAMATION MARK + 0x0022: 0x7F, # QUOTATION MARK + 0x0023: 0x7B, # NUMBER SIGN + 0x0024: 0x5B, # DOLLAR SIGN + 0x0025: 0x6C, # PERCENT SIGN 0x0026: 0x50, # AMPERSAND - 0x0027: 0x7d, # APOSTROPHE - 0x0028: 0x4d, # LEFT PARENTHESIS - 0x0029: 0x5d, # RIGHT PARENTHESIS - 0x002a: 0x5c, # ASTERISK - 0x002b: 0x4e, # PLUS SIGN - 0x002c: 0x6b, # COMMA - 0x002d: 0x60, # HYPHEN-MINUS - 0x002e: 0x4b, # FULL STOP - 0x002f: 0x61, # SOLIDUS - 0x0030: 0xf0, # DIGIT ZERO - 0x0031: 0xf1, # DIGIT ONE - 0x0032: 0xf2, # DIGIT TWO - 0x0033: 0xf3, # DIGIT THREE - 0x0034: 0xf4, # DIGIT FOUR - 0x0035: 0xf5, # DIGIT FIVE - 0x0036: 0xf6, # DIGIT SIX - 0x0037: 0xf7, # DIGIT SEVEN - 0x0038: 0xf8, # DIGIT EIGHT - 0x0039: 0xf9, # DIGIT NINE - 0x003a: 0x7a, # COLON - 0x003b: 0x5e, # SEMICOLON - 0x003c: 0x4c, # LESS-THAN SIGN - 0x003d: 0x7e, # EQUALS SIGN - 0x003e: 0x6e, # GREATER-THAN SIGN - 0x003f: 0x6f, # QUESTION MARK - 0x0040: 0x7c, # COMMERCIAL AT - 0x0041: 0xc1, # LATIN CAPITAL LETTER A - 0x0042: 0xc2, # LATIN CAPITAL LETTER B - 0x0043: 0xc3, # LATIN CAPITAL LETTER C - 0x0044: 0xc4, # LATIN CAPITAL LETTER D - 0x0045: 0xc5, # LATIN CAPITAL LETTER E - 0x0046: 0xc6, # LATIN CAPITAL LETTER F - 0x0047: 0xc7, # LATIN CAPITAL LETTER G - 0x0048: 0xc8, # LATIN CAPITAL LETTER H - 0x0049: 0xc9, # LATIN CAPITAL LETTER I - 0x004a: 0xd1, # LATIN CAPITAL LETTER J - 0x004b: 0xd2, # LATIN CAPITAL LETTER K - 0x004c: 0xd3, # LATIN CAPITAL LETTER L - 0x004d: 0xd4, # LATIN CAPITAL LETTER M - 0x004e: 0xd5, # LATIN CAPITAL LETTER N - 0x004f: 0xd6, # LATIN CAPITAL LETTER O - 0x0050: 0xd7, # LATIN CAPITAL LETTER P - 0x0051: 0xd8, # LATIN CAPITAL LETTER Q - 0x0052: 0xd9, # LATIN CAPITAL LETTER R - 0x0053: 0xe2, # LATIN CAPITAL LETTER S - 0x0054: 0xe3, # LATIN CAPITAL LETTER T - 0x0055: 0xe4, # LATIN CAPITAL LETTER U - 0x0056: 0xe5, # LATIN CAPITAL LETTER V - 0x0057: 0xe6, # LATIN CAPITAL LETTER W - 0x0058: 0xe7, # LATIN CAPITAL LETTER X - 0x0059: 0xe8, # LATIN CAPITAL LETTER Y - 0x005a: 0xe9, # LATIN CAPITAL LETTER Z - 0x005b: 0xba, # LEFT SQUARE BRACKET - 0x005c: 0xe0, # REVERSE SOLIDUS - 0x005d: 0xbb, # RIGHT SQUARE BRACKET - 0x005e: 0xb0, # CIRCUMFLEX ACCENT - 0x005f: 0x6d, # LOW LINE + 0x0027: 0x7D, # APOSTROPHE + 0x0028: 0x4D, # LEFT PARENTHESIS + 0x0029: 0x5D, # RIGHT PARENTHESIS + 0x002A: 0x5C, # ASTERISK + 0x002B: 0x4E, # PLUS SIGN + 0x002C: 0x6B, # COMMA + 0x002D: 0x60, # HYPHEN-MINUS + 0x002E: 0x4B, # FULL STOP + 0x002F: 0x61, # SOLIDUS + 0x0030: 0xF0, # DIGIT ZERO + 0x0031: 0xF1, # DIGIT ONE + 0x0032: 0xF2, # DIGIT TWO + 0x0033: 0xF3, # DIGIT THREE + 0x0034: 0xF4, # DIGIT FOUR + 0x0035: 0xF5, # DIGIT FIVE + 0x0036: 0xF6, # DIGIT SIX + 0x0037: 0xF7, # DIGIT SEVEN + 0x0038: 0xF8, # DIGIT EIGHT + 0x0039: 0xF9, # DIGIT NINE + 0x003A: 0x7A, # COLON + 0x003B: 0x5E, # SEMICOLON + 0x003C: 0x4C, # LESS-THAN SIGN + 0x003D: 0x7E, # EQUALS SIGN + 0x003E: 0x6E, # GREATER-THAN SIGN + 0x003F: 0x6F, # QUESTION MARK + 0x0040: 0x7C, # COMMERCIAL AT + 0x0041: 0xC1, # LATIN CAPITAL LETTER A + 0x0042: 0xC2, # LATIN CAPITAL LETTER B + 0x0043: 0xC3, # LATIN CAPITAL LETTER C + 0x0044: 0xC4, # LATIN CAPITAL LETTER D + 0x0045: 0xC5, # LATIN CAPITAL LETTER E + 0x0046: 0xC6, # LATIN CAPITAL LETTER F + 0x0047: 0xC7, # LATIN CAPITAL LETTER G + 0x0048: 0xC8, # LATIN CAPITAL LETTER H + 0x0049: 0xC9, # LATIN CAPITAL LETTER I + 0x004A: 0xD1, # LATIN CAPITAL LETTER J + 0x004B: 0xD2, # LATIN CAPITAL LETTER K + 0x004C: 0xD3, # LATIN CAPITAL LETTER L + 0x004D: 0xD4, # LATIN CAPITAL LETTER M + 0x004E: 0xD5, # LATIN CAPITAL LETTER N + 0x004F: 0xD6, # LATIN CAPITAL LETTER O + 0x0050: 0xD7, # LATIN CAPITAL LETTER P + 0x0051: 0xD8, # LATIN CAPITAL LETTER Q + 0x0052: 0xD9, # LATIN CAPITAL LETTER R + 0x0053: 0xE2, # LATIN CAPITAL LETTER S + 0x0054: 0xE3, # LATIN CAPITAL LETTER T + 0x0055: 0xE4, # LATIN CAPITAL LETTER U + 0x0056: 0xE5, # LATIN CAPITAL LETTER V + 0x0057: 0xE6, # LATIN CAPITAL LETTER W + 0x0058: 0xE7, # LATIN CAPITAL LETTER X + 0x0059: 0xE8, # LATIN CAPITAL LETTER Y + 0x005A: 0xE9, # LATIN CAPITAL LETTER Z + 0x005B: 0xBA, # LEFT SQUARE BRACKET + 0x005C: 0xE0, # REVERSE SOLIDUS + 0x005D: 0xBB, # RIGHT SQUARE BRACKET + 0x005E: 0xB0, # CIRCUMFLEX ACCENT + 0x005F: 0x6D, # LOW LINE 0x0060: 0x79, # GRAVE ACCENT 0x0061: 0x81, # LATIN SMALL LETTER A 0x0062: 0x82, # LATIN SMALL LETTER B @@ -399,28 +399,28 @@ encoding_map = { 0x0067: 0x87, # LATIN SMALL LETTER G 0x0068: 0x88, # LATIN SMALL LETTER H 0x0069: 0x89, # LATIN SMALL LETTER I - 0x006a: 0x91, # LATIN SMALL LETTER J - 0x006b: 0x92, # LATIN SMALL LETTER K - 0x006c: 0x93, # LATIN SMALL LETTER L - 0x006d: 0x94, # LATIN SMALL LETTER M - 0x006e: 0x95, # LATIN SMALL LETTER N - 0x006f: 0x96, # LATIN SMALL LETTER O + 0x006A: 0x91, # LATIN SMALL LETTER J + 0x006B: 0x92, # LATIN SMALL LETTER K + 0x006C: 0x93, # LATIN SMALL LETTER L + 0x006D: 0x94, # LATIN SMALL LETTER M + 0x006E: 0x95, # LATIN SMALL LETTER N + 0x006F: 0x96, # LATIN SMALL LETTER O 0x0070: 0x97, # LATIN SMALL LETTER P 0x0071: 0x98, # LATIN SMALL LETTER Q 0x0072: 0x99, # LATIN SMALL LETTER R - 0x0073: 0xa2, # LATIN SMALL LETTER S - 0x0074: 0xa3, # LATIN SMALL LETTER T - 0x0075: 0xa4, # LATIN SMALL LETTER U - 0x0076: 0xa5, # LATIN SMALL LETTER V - 0x0077: 0xa6, # LATIN SMALL LETTER W - 0x0078: 0xa7, # LATIN SMALL LETTER X - 0x0079: 0xa8, # LATIN SMALL LETTER Y - 0x007a: 0xa9, # LATIN SMALL LETTER Z - 0x007b: 0xc0, # LEFT CURLY BRACKET - 0x007c: 0x4f, # VERTICAL LINE - 0x007d: 0xd0, # RIGHT CURLY BRACKET - 0x007e: 0xa1, # TILDE - 0x007f: 0x07, # DELETE + 0x0073: 0xA2, # LATIN SMALL LETTER S + 0x0074: 0xA3, # LATIN SMALL LETTER T + 0x0075: 0xA4, # LATIN SMALL LETTER U + 0x0076: 0xA5, # LATIN SMALL LETTER V + 0x0077: 0xA6, # LATIN SMALL LETTER W + 0x0078: 0xA7, # LATIN SMALL LETTER X + 0x0079: 0xA8, # LATIN SMALL LETTER Y + 0x007A: 0xA9, # LATIN SMALL LETTER Z + 0x007B: 0xC0, # LEFT CURLY BRACKET + 0x007C: 0x4F, # VERTICAL LINE + 0x007D: 0xD0, # RIGHT CURLY BRACKET + 0x007E: 0xA1, # TILDE + 0x007F: 0x07, # DELETE 0x0080: 0x20, # DIGIT SELECT 0x0081: 0x21, # START OF SIGNIFICANCE 0x0082: 0x22, # FIELD SEPARATOR @@ -431,15 +431,15 @@ encoding_map = { 0x0087: 0x17, # PROGRAM OPERATOR COMMUNICATION 0x0088: 0x28, # SET ATTRIBUTE 0x0089: 0x29, # START FIELD EXTENDED - 0x008a: 0x2a, # SET MODE OR SWITCH - 0x008b: 0x2b, # CONTROL SEQUENCE PREFIX - 0x008c: 0x2c, # MODIFY FIELD ATTRIBUTE - 0x008d: 0x09, # SUPERSCRIPT - 0x008e: 0x0a, # REPEAT - 0x008f: 0x1b, # CUSTOMER USE ONE + 0x008A: 0x2A, # SET MODE OR SWITCH + 0x008B: 0x2B, # CONTROL SEQUENCE PREFIX + 0x008C: 0x2C, # MODIFY FIELD ATTRIBUTE + 0x008D: 0x09, # SUPERSCRIPT + 0x008E: 0x0A, # REPEAT + 0x008F: 0x1B, # CUSTOMER USE ONE 0x0090: 0x30, # 0x0091: 0x31, # - 0x0092: 0x1a, # UNIT BACK SPACE + 0x0092: 0x1A, # UNIT BACK SPACE 0x0093: 0x33, # INDEX RETURN 0x0094: 0x34, # PRESENTATION POSITION 0x0095: 0x35, # TRANSPARENT @@ -447,68 +447,69 @@ encoding_map = { 0x0097: 0x08, # GRAPHIC ESCAPE 0x0098: 0x38, # SUBSCRIPT 0x0099: 0x39, # INDENT TABULATION - 0x009a: 0x3a, # REVERSE FORM FEED - 0x009b: 0x3b, # CUSTOMER USE THREE - 0x009c: 0x04, # SELECT - 0x009d: 0x14, # RESTORE/ENABLE PRESENTATION - 0x009e: 0x3e, # - 0x009f: 0xff, # EIGHT ONES - 0x00a0: 0x74, # NO-BREAK SPACE - 0x00a2: 0x4a, # CENT SIGN - 0x00a3: 0xb1, # POUND SIGN - 0x00a4: 0x9f, # CURRENCY SIGN - 0x00a5: 0xb2, # YEN SIGN - 0x00a6: 0x6a, # BROKEN BAR - 0x00a7: 0xb5, # SECTION SIGN - 0x00a8: 0xbd, # DIAERESIS - 0x00a9: 0xb4, # COPYRIGHT SIGN - 0x00ab: 0x8a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0x5f, # NOT SIGN - 0x00ad: 0xca, # SOFT HYPHEN - 0x00ae: 0xaf, # REGISTERED SIGN - 0x00af: 0xbc, # MACRON - 0x00b0: 0x90, # DEGREE SIGN - 0x00b1: 0x8f, # PLUS-MINUS SIGN - 0x00b2: 0xea, # SUPERSCRIPT TWO - 0x00b3: 0xfa, # SUPERSCRIPT THREE - 0x00b4: 0xbe, # ACUTE ACCENT - 0x00b5: 0xa0, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb3, # MIDDLE DOT - 0x00b8: 0x9d, # CEDILLA - 0x00b9: 0xda, # SUPERSCRIPT ONE - 0x00bb: 0x8b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xb7, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xb8, # VULGAR FRACTION ONE HALF - 0x00be: 0xb9, # VULGAR FRACTION THREE QUARTERS - 0x00d7: 0xbf, # MULTIPLICATION SIGN - 0x00f7: 0xe1, # DIVISION SIGN - 0x05d0: 0x41, # HEBREW LETTER ALEF - 0x05d1: 0x42, # HEBREW LETTER BET - 0x05d2: 0x43, # HEBREW LETTER GIMEL - 0x05d3: 0x44, # HEBREW LETTER DALET - 0x05d4: 0x45, # HEBREW LETTER HE - 0x05d5: 0x46, # HEBREW LETTER VAV - 0x05d6: 0x47, # HEBREW LETTER ZAYIN - 0x05d7: 0x48, # HEBREW LETTER HET - 0x05d8: 0x49, # HEBREW LETTER TET - 0x05d9: 0x51, # HEBREW LETTER YOD - 0x05da: 0x52, # HEBREW LETTER FINAL KAF - 0x05db: 0x53, # HEBREW LETTER KAF - 0x05dc: 0x54, # HEBREW LETTER LAMED - 0x05dd: 0x55, # HEBREW LETTER FINAL MEM - 0x05de: 0x56, # HEBREW LETTER MEM - 0x05df: 0x57, # HEBREW LETTER FINAL NUN - 0x05e0: 0x58, # HEBREW LETTER NUN - 0x05e1: 0x59, # HEBREW LETTER SAMEKH - 0x05e2: 0x62, # HEBREW LETTER AYIN - 0x05e3: 0x63, # HEBREW LETTER FINAL PE - 0x05e4: 0x64, # HEBREW LETTER PE - 0x05e5: 0x65, # HEBREW LETTER FINAL TSADI - 0x05e6: 0x66, # HEBREW LETTER TSADI - 0x05e7: 0x67, # HEBREW LETTER QOF - 0x05e8: 0x68, # HEBREW LETTER RESH - 0x05e9: 0x69, # HEBREW LETTER SHIN - 0x05ea: 0x71, # HEBREW LETTER TAV + 0x009A: 0x3A, # REVERSE FORM FEED + 0x009B: 0x3B, # CUSTOMER USE THREE + 0x009C: 0x04, # SELECT + 0x009D: 0x14, # RESTORE/ENABLE PRESENTATION + 0x009E: 0x3E, # + 0x009F: 0xFF, # EIGHT ONES + 0x00A0: 0x74, # NO-BREAK SPACE + 0x00A2: 0x4A, # CENT SIGN + 0x00A3: 0xB1, # POUND SIGN + 0x00A4: 0x9F, # CURRENCY SIGN + 0x00A5: 0xB2, # YEN SIGN + 0x00A6: 0x6A, # BROKEN BAR + 0x00A7: 0xB5, # SECTION SIGN + 0x00A8: 0xBD, # DIAERESIS + 0x00A9: 0xB4, # COPYRIGHT SIGN + 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0x5F, # NOT SIGN + 0x00AD: 0xCA, # SOFT HYPHEN + 0x00AE: 0xAF, # REGISTERED SIGN + 0x00AF: 0xBC, # MACRON + 0x00B0: 0x90, # DEGREE SIGN + 0x00B1: 0x8F, # PLUS-MINUS SIGN + 0x00B2: 0xEA, # SUPERSCRIPT TWO + 0x00B3: 0xFA, # SUPERSCRIPT THREE + 0x00B4: 0xBE, # ACUTE ACCENT + 0x00B5: 0xA0, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB3, # MIDDLE DOT + 0x00B8: 0x9D, # CEDILLA + 0x00B9: 0xDA, # SUPERSCRIPT ONE + 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF + 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS + 0x00D7: 0xBF, # MULTIPLICATION SIGN + 0x00F7: 0xE1, # DIVISION SIGN + 0x05D0: 0x41, # HEBREW LETTER ALEF + 0x05D1: 0x42, # HEBREW LETTER BET + 0x05D2: 0x43, # HEBREW LETTER GIMEL + 0x05D3: 0x44, # HEBREW LETTER DALET + 0x05D4: 0x45, # HEBREW LETTER HE + 0x05D5: 0x46, # HEBREW LETTER VAV + 0x05D6: 0x47, # HEBREW LETTER ZAYIN + 0x05D7: 0x48, # HEBREW LETTER HET + 0x05D8: 0x49, # HEBREW LETTER TET + 0x05D9: 0x51, # HEBREW LETTER YOD + 0x05DA: 0x52, # HEBREW LETTER FINAL KAF + 0x05DB: 0x53, # HEBREW LETTER KAF + 0x05DC: 0x54, # HEBREW LETTER LAMED + 0x05DD: 0x55, # HEBREW LETTER FINAL MEM + 0x05DE: 0x56, # HEBREW LETTER MEM + 0x05DF: 0x57, # HEBREW LETTER FINAL NUN + 0x05E0: 0x58, # HEBREW LETTER NUN + 0x05E1: 0x59, # HEBREW LETTER SAMEKH + 0x05E2: 0x62, # HEBREW LETTER AYIN + 0x05E3: 0x63, # HEBREW LETTER FINAL PE + 0x05E4: 0x64, # HEBREW LETTER PE + 0x05E5: 0x65, # HEBREW LETTER FINAL TSADI + 0x05E6: 0x66, # HEBREW LETTER TSADI + 0x05E7: 0x67, # HEBREW LETTER QOF + 0x05E8: 0x68, # HEBREW LETTER RESH + 0x05E9: 0x69, # HEBREW LETTER SHIN + 0x05EA: 0x71, # HEBREW LETTER TAV 0x2017: 0x78, # DOUBLE LOW LINE -} \ No newline at end of file +} + diff --git a/Lib/encodings/cp500.py b/Lib/encodings/cp500.py index ab3042c..562bc9c 100644 --- a/Lib/encodings/cp500.py +++ b/Lib/encodings/cp500.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL - u'\x8e' # 0x0a -> CONTROL - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\x8e' # 0x0A -> CONTROL + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x92' # 0x1a -> CONTROL - u'\x8f' # 0x1b -> CONTROL - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x92' # 0x1A -> CONTROL + u'\x8f' # 0x1B -> CONTROL + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL @@ -74,12 +74,12 @@ decoding_table = ( u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL - u'\x8a' # 0x2a -> CONTROL - u'\x8b' # 0x2b -> CONTROL - u'\x8c' # 0x2c -> CONTROL - u'\x05' # 0x2d -> ENQUIRY - u'\x06' # 0x2e -> ACKNOWLEDGE - u'\x07' # 0x2f -> BELL + u'\x8a' # 0x2A -> CONTROL + u'\x8b' # 0x2B -> CONTROL + u'\x8c' # 0x2C -> CONTROL + u'\x05' # 0x2D -> ENQUIRY + u'\x06' # 0x2E -> ACKNOWLEDGE + u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE @@ -90,12 +90,12 @@ decoding_table = ( u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL - u'\x9a' # 0x3a -> CONTROL - u'\x9b' # 0x3b -> CONTROL - u'\x14' # 0x3c -> DEVICE CONTROL FOUR - u'\x15' # 0x3d -> NEGATIVE ACKNOWLEDGE - u'\x9e' # 0x3e -> CONTROL - u'\x1a' # 0x3f -> SUBSTITUTE + u'\x9a' # 0x3A -> CONTROL + u'\x9b' # 0x3B -> CONTROL + u'\x14' # 0x3C -> DEVICE CONTROL FOUR + u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + u'\x9e' # 0x3E -> CONTROL + u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX @@ -106,12 +106,12 @@ decoding_table = ( u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE - u'[' # 0x4a -> LEFT SQUARE BRACKET - u'.' # 0x4b -> FULL STOP - u'<' # 0x4c -> LESS-THAN SIGN - u'(' # 0x4d -> LEFT PARENTHESIS - u'+' # 0x4e -> PLUS SIGN - u'!' # 0x4f -> EXCLAMATION MARK + u'[' # 0x4A -> LEFT SQUARE BRACKET + u'.' # 0x4B -> FULL STOP + u'<' # 0x4C -> LESS-THAN SIGN + u'(' # 0x4D -> LEFT PARENTHESIS + u'+' # 0x4E -> PLUS SIGN + u'!' # 0x4F -> EXCLAMATION MARK u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX @@ -122,12 +122,12 @@ decoding_table = ( u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) - u']' # 0x5a -> RIGHT SQUARE BRACKET - u'$' # 0x5b -> DOLLAR SIGN - u'*' # 0x5c -> ASTERISK - u')' # 0x5d -> RIGHT PARENTHESIS - u';' # 0x5e -> SEMICOLON - u'^' # 0x5f -> CIRCUMFLEX ACCENT + u']' # 0x5A -> RIGHT SQUARE BRACKET + u'$' # 0x5B -> DOLLAR SIGN + u'*' # 0x5C -> ASTERISK + u')' # 0x5D -> RIGHT PARENTHESIS + u';' # 0x5E -> SEMICOLON + u'^' # 0x5F -> CIRCUMFLEX ACCENT u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX @@ -138,12 +138,12 @@ decoding_table = ( u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xa6' # 0x6a -> BROKEN BAR - u',' # 0x6b -> COMMA - u'%' # 0x6c -> PERCENT SIGN - u'_' # 0x6d -> LOW LINE - u'>' # 0x6e -> GREATER-THAN SIGN - u'?' # 0x6f -> QUESTION MARK + u'\xa6' # 0x6A -> BROKEN BAR + u',' # 0x6B -> COMMA + u'%' # 0x6C -> PERCENT SIGN + u'_' # 0x6D -> LOW LINE + u'>' # 0x6E -> GREATER-THAN SIGN + u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX @@ -154,12 +154,12 @@ decoding_table = ( u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'`' # 0x79 -> GRAVE ACCENT - u':' # 0x7a -> COLON - u'#' # 0x7b -> NUMBER SIGN - u'@' # 0x7c -> COMMERCIAL AT - u"'" # 0x7d -> APOSTROPHE - u'=' # 0x7e -> EQUALS SIGN - u'"' # 0x7f -> QUOTATION MARK + u':' # 0x7A -> COLON + u'#' # 0x7B -> NUMBER SIGN + u'@' # 0x7C -> COMMERCIAL AT + u"'" # 0x7D -> APOSTROPHE + u'=' # 0x7E -> EQUALS SIGN + u'"' # 0x7F -> QUOTATION MARK u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B @@ -170,12 +170,12 @@ decoding_table = ( u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I - u'\xab' # 0x8a -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0x8b -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xf0' # 0x8c -> LATIN SMALL LETTER ETH (ICELANDIC) - u'\xfd' # 0x8d -> LATIN SMALL LETTER Y WITH ACUTE - u'\xfe' # 0x8e -> LATIN SMALL LETTER THORN (ICELANDIC) - u'\xb1' # 0x8f -> PLUS-MINUS SIGN + u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) + u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE + u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) + u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K @@ -186,108 +186,108 @@ decoding_table = ( u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R - u'\xaa' # 0x9a -> FEMININE ORDINAL INDICATOR - u'\xba' # 0x9b -> MASCULINE ORDINAL INDICATOR - u'\xe6' # 0x9c -> LATIN SMALL LIGATURE AE - u'\xb8' # 0x9d -> CEDILLA - u'\xc6' # 0x9e -> LATIN CAPITAL LIGATURE AE - u'\xa4' # 0x9f -> CURRENCY SIGN - u'\xb5' # 0xa0 -> MICRO SIGN - u'~' # 0xa1 -> TILDE - u's' # 0xa2 -> LATIN SMALL LETTER S - u't' # 0xa3 -> LATIN SMALL LETTER T - u'u' # 0xa4 -> LATIN SMALL LETTER U - u'v' # 0xa5 -> LATIN SMALL LETTER V - u'w' # 0xa6 -> LATIN SMALL LETTER W - u'x' # 0xa7 -> LATIN SMALL LETTER X - u'y' # 0xa8 -> LATIN SMALL LETTER Y - u'z' # 0xa9 -> LATIN SMALL LETTER Z - u'\xa1' # 0xaa -> INVERTED EXCLAMATION MARK - u'\xbf' # 0xab -> INVERTED QUESTION MARK - u'\xd0' # 0xac -> LATIN CAPITAL LETTER ETH (ICELANDIC) - u'\xdd' # 0xad -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xde' # 0xae -> LATIN CAPITAL LETTER THORN (ICELANDIC) - u'\xae' # 0xaf -> REGISTERED SIGN - u'\xa2' # 0xb0 -> CENT SIGN - u'\xa3' # 0xb1 -> POUND SIGN - u'\xa5' # 0xb2 -> YEN SIGN - u'\xb7' # 0xb3 -> MIDDLE DOT - u'\xa9' # 0xb4 -> COPYRIGHT SIGN - u'\xa7' # 0xb5 -> SECTION SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xbc' # 0xb7 -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xb8 -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xb9 -> VULGAR FRACTION THREE QUARTERS - u'\xac' # 0xba -> NOT SIGN - u'|' # 0xbb -> VERTICAL LINE - u'\xaf' # 0xbc -> MACRON - u'\xa8' # 0xbd -> DIAERESIS - u'\xb4' # 0xbe -> ACUTE ACCENT - u'\xd7' # 0xbf -> MULTIPLICATION SIGN - u'{' # 0xc0 -> LEFT CURLY BRACKET - u'A' # 0xc1 -> LATIN CAPITAL LETTER A - u'B' # 0xc2 -> LATIN CAPITAL LETTER B - u'C' # 0xc3 -> LATIN CAPITAL LETTER C - u'D' # 0xc4 -> LATIN CAPITAL LETTER D - u'E' # 0xc5 -> LATIN CAPITAL LETTER E - u'F' # 0xc6 -> LATIN CAPITAL LETTER F - u'G' # 0xc7 -> LATIN CAPITAL LETTER G - u'H' # 0xc8 -> LATIN CAPITAL LETTER H - u'I' # 0xc9 -> LATIN CAPITAL LETTER I - u'\xad' # 0xca -> SOFT HYPHEN - u'\xf4' # 0xcb -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0xcc -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf2' # 0xcd -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xce -> LATIN SMALL LETTER O WITH ACUTE - u'\xf5' # 0xcf -> LATIN SMALL LETTER O WITH TILDE - u'}' # 0xd0 -> RIGHT CURLY BRACKET - u'J' # 0xd1 -> LATIN CAPITAL LETTER J - u'K' # 0xd2 -> LATIN CAPITAL LETTER K - u'L' # 0xd3 -> LATIN CAPITAL LETTER L - u'M' # 0xd4 -> LATIN CAPITAL LETTER M - u'N' # 0xd5 -> LATIN CAPITAL LETTER N - u'O' # 0xd6 -> LATIN CAPITAL LETTER O - u'P' # 0xd7 -> LATIN CAPITAL LETTER P - u'Q' # 0xd8 -> LATIN CAPITAL LETTER Q - u'R' # 0xd9 -> LATIN CAPITAL LETTER R - u'\xb9' # 0xda -> SUPERSCRIPT ONE - u'\xfb' # 0xdb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xdc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xf9' # 0xdd -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xde -> LATIN SMALL LETTER U WITH ACUTE - u'\xff' # 0xdf -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\\' # 0xe0 -> REVERSE SOLIDUS - u'\xf7' # 0xe1 -> DIVISION SIGN - u'S' # 0xe2 -> LATIN CAPITAL LETTER S - u'T' # 0xe3 -> LATIN CAPITAL LETTER T - u'U' # 0xe4 -> LATIN CAPITAL LETTER U - u'V' # 0xe5 -> LATIN CAPITAL LETTER V - u'W' # 0xe6 -> LATIN CAPITAL LETTER W - u'X' # 0xe7 -> LATIN CAPITAL LETTER X - u'Y' # 0xe8 -> LATIN CAPITAL LETTER Y - u'Z' # 0xe9 -> LATIN CAPITAL LETTER Z - u'\xb2' # 0xea -> SUPERSCRIPT TWO - u'\xd4' # 0xeb -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd6' # 0xec -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd2' # 0xed -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd5' # 0xef -> LATIN CAPITAL LETTER O WITH TILDE - u'0' # 0xf0 -> DIGIT ZERO - u'1' # 0xf1 -> DIGIT ONE - u'2' # 0xf2 -> DIGIT TWO - u'3' # 0xf3 -> DIGIT THREE - u'4' # 0xf4 -> DIGIT FOUR - u'5' # 0xf5 -> DIGIT FIVE - u'6' # 0xf6 -> DIGIT SIX - u'7' # 0xf7 -> DIGIT SEVEN - u'8' # 0xf8 -> DIGIT EIGHT - u'9' # 0xf9 -> DIGIT NINE - u'\xb3' # 0xfa -> SUPERSCRIPT THREE - u'\xdb' # 0xfb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xfc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xd9' # 0xfd -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xfe -> LATIN CAPITAL LETTER U WITH ACUTE - u'\x9f' # 0xff -> CONTROL + u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + u'\xb8' # 0x9D -> CEDILLA + u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + u'\xa4' # 0x9F -> CURRENCY SIGN + u'\xb5' # 0xA0 -> MICRO SIGN + u'~' # 0xA1 -> TILDE + u's' # 0xA2 -> LATIN SMALL LETTER S + u't' # 0xA3 -> LATIN SMALL LETTER T + u'u' # 0xA4 -> LATIN SMALL LETTER U + u'v' # 0xA5 -> LATIN SMALL LETTER V + u'w' # 0xA6 -> LATIN SMALL LETTER W + u'x' # 0xA7 -> LATIN SMALL LETTER X + u'y' # 0xA8 -> LATIN SMALL LETTER Y + u'z' # 0xA9 -> LATIN SMALL LETTER Z + u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + u'\xbf' # 0xAB -> INVERTED QUESTION MARK + u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) + u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) + u'\xae' # 0xAF -> REGISTERED SIGN + u'\xa2' # 0xB0 -> CENT SIGN + u'\xa3' # 0xB1 -> POUND SIGN + u'\xa5' # 0xB2 -> YEN SIGN + u'\xb7' # 0xB3 -> MIDDLE DOT + u'\xa9' # 0xB4 -> COPYRIGHT SIGN + u'\xa7' # 0xB5 -> SECTION SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + u'\xac' # 0xBA -> NOT SIGN + u'|' # 0xBB -> VERTICAL LINE + u'\xaf' # 0xBC -> MACRON + u'\xa8' # 0xBD -> DIAERESIS + u'\xb4' # 0xBE -> ACUTE ACCENT + u'\xd7' # 0xBF -> MULTIPLICATION SIGN + u'{' # 0xC0 -> LEFT CURLY BRACKET + u'A' # 0xC1 -> LATIN CAPITAL LETTER A + u'B' # 0xC2 -> LATIN CAPITAL LETTER B + u'C' # 0xC3 -> LATIN CAPITAL LETTER C + u'D' # 0xC4 -> LATIN CAPITAL LETTER D + u'E' # 0xC5 -> LATIN CAPITAL LETTER E + u'F' # 0xC6 -> LATIN CAPITAL LETTER F + u'G' # 0xC7 -> LATIN CAPITAL LETTER G + u'H' # 0xC8 -> LATIN CAPITAL LETTER H + u'I' # 0xC9 -> LATIN CAPITAL LETTER I + u'\xad' # 0xCA -> SOFT HYPHEN + u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + u'}' # 0xD0 -> RIGHT CURLY BRACKET + u'J' # 0xD1 -> LATIN CAPITAL LETTER J + u'K' # 0xD2 -> LATIN CAPITAL LETTER K + u'L' # 0xD3 -> LATIN CAPITAL LETTER L + u'M' # 0xD4 -> LATIN CAPITAL LETTER M + u'N' # 0xD5 -> LATIN CAPITAL LETTER N + u'O' # 0xD6 -> LATIN CAPITAL LETTER O + u'P' # 0xD7 -> LATIN CAPITAL LETTER P + u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + u'R' # 0xD9 -> LATIN CAPITAL LETTER R + u'\xb9' # 0xDA -> SUPERSCRIPT ONE + u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\\' # 0xE0 -> REVERSE SOLIDUS + u'\xf7' # 0xE1 -> DIVISION SIGN + u'S' # 0xE2 -> LATIN CAPITAL LETTER S + u'T' # 0xE3 -> LATIN CAPITAL LETTER T + u'U' # 0xE4 -> LATIN CAPITAL LETTER U + u'V' # 0xE5 -> LATIN CAPITAL LETTER V + u'W' # 0xE6 -> LATIN CAPITAL LETTER W + u'X' # 0xE7 -> LATIN CAPITAL LETTER X + u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + u'\xb2' # 0xEA -> SUPERSCRIPT TWO + u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + u'0' # 0xF0 -> DIGIT ZERO + u'1' # 0xF1 -> DIGIT ONE + u'2' # 0xF2 -> DIGIT TWO + u'3' # 0xF3 -> DIGIT THREE + u'4' # 0xF4 -> DIGIT FOUR + u'5' # 0xF5 -> DIGIT FIVE + u'6' # 0xF6 -> DIGIT SIX + u'7' # 0xF7 -> DIGIT SEVEN + u'8' # 0xF8 -> DIGIT EIGHT + u'9' # 0xF9 -> DIGIT NINE + u'\xb3' # 0xFA -> SUPERSCRIPT THREE + u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + u'\x9f' # 0xFF -> CONTROL ) ### Encoding Map @@ -298,97 +298,97 @@ encoding_map = { 0x0002: 0x02, # START OF TEXT 0x0003: 0x03, # END OF TEXT 0x0004: 0x37, # END OF TRANSMISSION - 0x0005: 0x2d, # ENQUIRY - 0x0006: 0x2e, # ACKNOWLEDGE - 0x0007: 0x2f, # BELL + 0x0005: 0x2D, # ENQUIRY + 0x0006: 0x2E, # ACKNOWLEDGE + 0x0007: 0x2F, # BELL 0x0008: 0x16, # BACKSPACE 0x0009: 0x05, # HORIZONTAL TABULATION - 0x000a: 0x25, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x25, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO 0x0013: 0x13, # DEVICE CONTROL THREE - 0x0014: 0x3c, # DEVICE CONTROL FOUR - 0x0015: 0x3d, # NEGATIVE ACKNOWLEDGE + 0x0014: 0x3C, # DEVICE CONTROL FOUR + 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE 0x0016: 0x32, # SYNCHRONOUS IDLE 0x0017: 0x26, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x3f, # SUBSTITUTE - 0x001b: 0x27, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x3F, # SUBSTITUTE + 0x001B: 0x27, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x40, # SPACE - 0x0021: 0x4f, # EXCLAMATION MARK - 0x0022: 0x7f, # QUOTATION MARK - 0x0023: 0x7b, # NUMBER SIGN - 0x0024: 0x5b, # DOLLAR SIGN - 0x0025: 0x6c, # PERCENT SIGN + 0x0021: 0x4F, # EXCLAMATION MARK + 0x0022: 0x7F, # QUOTATION MARK + 0x0023: 0x7B, # NUMBER SIGN + 0x0024: 0x5B, # DOLLAR SIGN + 0x0025: 0x6C, # PERCENT SIGN 0x0026: 0x50, # AMPERSAND - 0x0027: 0x7d, # APOSTROPHE - 0x0028: 0x4d, # LEFT PARENTHESIS - 0x0029: 0x5d, # RIGHT PARENTHESIS - 0x002a: 0x5c, # ASTERISK - 0x002b: 0x4e, # PLUS SIGN - 0x002c: 0x6b, # COMMA - 0x002d: 0x60, # HYPHEN-MINUS - 0x002e: 0x4b, # FULL STOP - 0x002f: 0x61, # SOLIDUS - 0x0030: 0xf0, # DIGIT ZERO - 0x0031: 0xf1, # DIGIT ONE - 0x0032: 0xf2, # DIGIT TWO - 0x0033: 0xf3, # DIGIT THREE - 0x0034: 0xf4, # DIGIT FOUR - 0x0035: 0xf5, # DIGIT FIVE - 0x0036: 0xf6, # DIGIT SIX - 0x0037: 0xf7, # DIGIT SEVEN - 0x0038: 0xf8, # DIGIT EIGHT - 0x0039: 0xf9, # DIGIT NINE - 0x003a: 0x7a, # COLON - 0x003b: 0x5e, # SEMICOLON - 0x003c: 0x4c, # LESS-THAN SIGN - 0x003d: 0x7e, # EQUALS SIGN - 0x003e: 0x6e, # GREATER-THAN SIGN - 0x003f: 0x6f, # QUESTION MARK - 0x0040: 0x7c, # COMMERCIAL AT - 0x0041: 0xc1, # LATIN CAPITAL LETTER A - 0x0042: 0xc2, # LATIN CAPITAL LETTER B - 0x0043: 0xc3, # LATIN CAPITAL LETTER C - 0x0044: 0xc4, # LATIN CAPITAL LETTER D - 0x0045: 0xc5, # LATIN CAPITAL LETTER E - 0x0046: 0xc6, # LATIN CAPITAL LETTER F - 0x0047: 0xc7, # LATIN CAPITAL LETTER G - 0x0048: 0xc8, # LATIN CAPITAL LETTER H - 0x0049: 0xc9, # LATIN CAPITAL LETTER I - 0x004a: 0xd1, # LATIN CAPITAL LETTER J - 0x004b: 0xd2, # LATIN CAPITAL LETTER K - 0x004c: 0xd3, # LATIN CAPITAL LETTER L - 0x004d: 0xd4, # LATIN CAPITAL LETTER M - 0x004e: 0xd5, # LATIN CAPITAL LETTER N - 0x004f: 0xd6, # LATIN CAPITAL LETTER O - 0x0050: 0xd7, # LATIN CAPITAL LETTER P - 0x0051: 0xd8, # LATIN CAPITAL LETTER Q - 0x0052: 0xd9, # LATIN CAPITAL LETTER R - 0x0053: 0xe2, # LATIN CAPITAL LETTER S - 0x0054: 0xe3, # LATIN CAPITAL LETTER T - 0x0055: 0xe4, # LATIN CAPITAL LETTER U - 0x0056: 0xe5, # LATIN CAPITAL LETTER V - 0x0057: 0xe6, # LATIN CAPITAL LETTER W - 0x0058: 0xe7, # LATIN CAPITAL LETTER X - 0x0059: 0xe8, # LATIN CAPITAL LETTER Y - 0x005a: 0xe9, # LATIN CAPITAL LETTER Z - 0x005b: 0x4a, # LEFT SQUARE BRACKET - 0x005c: 0xe0, # REVERSE SOLIDUS - 0x005d: 0x5a, # RIGHT SQUARE BRACKET - 0x005e: 0x5f, # CIRCUMFLEX ACCENT - 0x005f: 0x6d, # LOW LINE + 0x0027: 0x7D, # APOSTROPHE + 0x0028: 0x4D, # LEFT PARENTHESIS + 0x0029: 0x5D, # RIGHT PARENTHESIS + 0x002A: 0x5C, # ASTERISK + 0x002B: 0x4E, # PLUS SIGN + 0x002C: 0x6B, # COMMA + 0x002D: 0x60, # HYPHEN-MINUS + 0x002E: 0x4B, # FULL STOP + 0x002F: 0x61, # SOLIDUS + 0x0030: 0xF0, # DIGIT ZERO + 0x0031: 0xF1, # DIGIT ONE + 0x0032: 0xF2, # DIGIT TWO + 0x0033: 0xF3, # DIGIT THREE + 0x0034: 0xF4, # DIGIT FOUR + 0x0035: 0xF5, # DIGIT FIVE + 0x0036: 0xF6, # DIGIT SIX + 0x0037: 0xF7, # DIGIT SEVEN + 0x0038: 0xF8, # DIGIT EIGHT + 0x0039: 0xF9, # DIGIT NINE + 0x003A: 0x7A, # COLON + 0x003B: 0x5E, # SEMICOLON + 0x003C: 0x4C, # LESS-THAN SIGN + 0x003D: 0x7E, # EQUALS SIGN + 0x003E: 0x6E, # GREATER-THAN SIGN + 0x003F: 0x6F, # QUESTION MARK + 0x0040: 0x7C, # COMMERCIAL AT + 0x0041: 0xC1, # LATIN CAPITAL LETTER A + 0x0042: 0xC2, # LATIN CAPITAL LETTER B + 0x0043: 0xC3, # LATIN CAPITAL LETTER C + 0x0044: 0xC4, # LATIN CAPITAL LETTER D + 0x0045: 0xC5, # LATIN CAPITAL LETTER E + 0x0046: 0xC6, # LATIN CAPITAL LETTER F + 0x0047: 0xC7, # LATIN CAPITAL LETTER G + 0x0048: 0xC8, # LATIN CAPITAL LETTER H + 0x0049: 0xC9, # LATIN CAPITAL LETTER I + 0x004A: 0xD1, # LATIN CAPITAL LETTER J + 0x004B: 0xD2, # LATIN CAPITAL LETTER K + 0x004C: 0xD3, # LATIN CAPITAL LETTER L + 0x004D: 0xD4, # LATIN CAPITAL LETTER M + 0x004E: 0xD5, # LATIN CAPITAL LETTER N + 0x004F: 0xD6, # LATIN CAPITAL LETTER O + 0x0050: 0xD7, # LATIN CAPITAL LETTER P + 0x0051: 0xD8, # LATIN CAPITAL LETTER Q + 0x0052: 0xD9, # LATIN CAPITAL LETTER R + 0x0053: 0xE2, # LATIN CAPITAL LETTER S + 0x0054: 0xE3, # LATIN CAPITAL LETTER T + 0x0055: 0xE4, # LATIN CAPITAL LETTER U + 0x0056: 0xE5, # LATIN CAPITAL LETTER V + 0x0057: 0xE6, # LATIN CAPITAL LETTER W + 0x0058: 0xE7, # LATIN CAPITAL LETTER X + 0x0059: 0xE8, # LATIN CAPITAL LETTER Y + 0x005A: 0xE9, # LATIN CAPITAL LETTER Z + 0x005B: 0x4A, # LEFT SQUARE BRACKET + 0x005C: 0xE0, # REVERSE SOLIDUS + 0x005D: 0x5A, # RIGHT SQUARE BRACKET + 0x005E: 0x5F, # CIRCUMFLEX ACCENT + 0x005F: 0x6D, # LOW LINE 0x0060: 0x79, # GRAVE ACCENT 0x0061: 0x81, # LATIN SMALL LETTER A 0x0062: 0x82, # LATIN SMALL LETTER B @@ -399,28 +399,28 @@ encoding_map = { 0x0067: 0x87, # LATIN SMALL LETTER G 0x0068: 0x88, # LATIN SMALL LETTER H 0x0069: 0x89, # LATIN SMALL LETTER I - 0x006a: 0x91, # LATIN SMALL LETTER J - 0x006b: 0x92, # LATIN SMALL LETTER K - 0x006c: 0x93, # LATIN SMALL LETTER L - 0x006d: 0x94, # LATIN SMALL LETTER M - 0x006e: 0x95, # LATIN SMALL LETTER N - 0x006f: 0x96, # LATIN SMALL LETTER O + 0x006A: 0x91, # LATIN SMALL LETTER J + 0x006B: 0x92, # LATIN SMALL LETTER K + 0x006C: 0x93, # LATIN SMALL LETTER L + 0x006D: 0x94, # LATIN SMALL LETTER M + 0x006E: 0x95, # LATIN SMALL LETTER N + 0x006F: 0x96, # LATIN SMALL LETTER O 0x0070: 0x97, # LATIN SMALL LETTER P 0x0071: 0x98, # LATIN SMALL LETTER Q 0x0072: 0x99, # LATIN SMALL LETTER R - 0x0073: 0xa2, # LATIN SMALL LETTER S - 0x0074: 0xa3, # LATIN SMALL LETTER T - 0x0075: 0xa4, # LATIN SMALL LETTER U - 0x0076: 0xa5, # LATIN SMALL LETTER V - 0x0077: 0xa6, # LATIN SMALL LETTER W - 0x0078: 0xa7, # LATIN SMALL LETTER X - 0x0079: 0xa8, # LATIN SMALL LETTER Y - 0x007a: 0xa9, # LATIN SMALL LETTER Z - 0x007b: 0xc0, # LEFT CURLY BRACKET - 0x007c: 0xbb, # VERTICAL LINE - 0x007d: 0xd0, # RIGHT CURLY BRACKET - 0x007e: 0xa1, # TILDE - 0x007f: 0x07, # DELETE + 0x0073: 0xA2, # LATIN SMALL LETTER S + 0x0074: 0xA3, # LATIN SMALL LETTER T + 0x0075: 0xA4, # LATIN SMALL LETTER U + 0x0076: 0xA5, # LATIN SMALL LETTER V + 0x0077: 0xA6, # LATIN SMALL LETTER W + 0x0078: 0xA7, # LATIN SMALL LETTER X + 0x0079: 0xA8, # LATIN SMALL LETTER Y + 0x007A: 0xA9, # LATIN SMALL LETTER Z + 0x007B: 0xC0, # LEFT CURLY BRACKET + 0x007C: 0xBB, # VERTICAL LINE + 0x007D: 0xD0, # RIGHT CURLY BRACKET + 0x007E: 0xA1, # TILDE + 0x007F: 0x07, # DELETE 0x0080: 0x20, # CONTROL 0x0081: 0x21, # CONTROL 0x0082: 0x22, # CONTROL @@ -431,15 +431,15 @@ encoding_map = { 0x0087: 0x17, # CONTROL 0x0088: 0x28, # CONTROL 0x0089: 0x29, # CONTROL - 0x008a: 0x2a, # CONTROL - 0x008b: 0x2b, # CONTROL - 0x008c: 0x2c, # CONTROL - 0x008d: 0x09, # CONTROL - 0x008e: 0x0a, # CONTROL - 0x008f: 0x1b, # CONTROL + 0x008A: 0x2A, # CONTROL + 0x008B: 0x2B, # CONTROL + 0x008C: 0x2C, # CONTROL + 0x008D: 0x09, # CONTROL + 0x008E: 0x0A, # CONTROL + 0x008F: 0x1B, # CONTROL 0x0090: 0x30, # CONTROL 0x0091: 0x31, # CONTROL - 0x0092: 0x1a, # CONTROL + 0x0092: 0x1A, # CONTROL 0x0093: 0x33, # CONTROL 0x0094: 0x34, # CONTROL 0x0095: 0x35, # CONTROL @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x08, # CONTROL 0x0098: 0x38, # CONTROL 0x0099: 0x39, # CONTROL - 0x009a: 0x3a, # CONTROL - 0x009b: 0x3b, # CONTROL - 0x009c: 0x04, # CONTROL - 0x009d: 0x14, # CONTROL - 0x009e: 0x3e, # CONTROL - 0x009f: 0xff, # CONTROL - 0x00a0: 0x41, # NO-BREAK SPACE - 0x00a1: 0xaa, # INVERTED EXCLAMATION MARK - 0x00a2: 0xb0, # CENT SIGN - 0x00a3: 0xb1, # POUND SIGN - 0x00a4: 0x9f, # CURRENCY SIGN - 0x00a5: 0xb2, # YEN SIGN - 0x00a6: 0x6a, # BROKEN BAR - 0x00a7: 0xb5, # SECTION SIGN - 0x00a8: 0xbd, # DIAERESIS - 0x00a9: 0xb4, # COPYRIGHT SIGN - 0x00aa: 0x9a, # FEMININE ORDINAL INDICATOR - 0x00ab: 0x8a, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xba, # NOT SIGN - 0x00ad: 0xca, # SOFT HYPHEN - 0x00ae: 0xaf, # REGISTERED SIGN - 0x00af: 0xbc, # MACRON - 0x00b0: 0x90, # DEGREE SIGN - 0x00b1: 0x8f, # PLUS-MINUS SIGN - 0x00b2: 0xea, # SUPERSCRIPT TWO - 0x00b3: 0xfa, # SUPERSCRIPT THREE - 0x00b4: 0xbe, # ACUTE ACCENT - 0x00b5: 0xa0, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb3, # MIDDLE DOT - 0x00b8: 0x9d, # CEDILLA - 0x00b9: 0xda, # SUPERSCRIPT ONE - 0x00ba: 0x9b, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0x8b, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xb7, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xb8, # VULGAR FRACTION ONE HALF - 0x00be: 0xb9, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xab, # INVERTED QUESTION MARK - 0x00c0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0x9e, # LATIN CAPITAL LIGATURE AE - 0x00c7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xac, # LATIN CAPITAL LETTER ETH (ICELANDIC) - 0x00d1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xed, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xeb, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xef, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xec, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xbf, # MULTIPLICATION SIGN - 0x00d8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xfd, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xfe, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xfb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xfc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xad, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xae, # LATIN CAPITAL LETTER THORN (ICELANDIC) - 0x00df: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) - 0x00e0: 0x44, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x45, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x46, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0x9c, # LATIN SMALL LIGATURE AE - 0x00e7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x54, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x51, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x58, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x55, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0x8c, # LATIN SMALL LETTER ETH (ICELANDIC) - 0x00f1: 0x49, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xcd, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xce, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xcb, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xcf, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xcc, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xe1, # DIVISION SIGN - 0x00f8: 0x70, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xdd, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xde, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xdb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xdc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0x8d, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0x8e, # LATIN SMALL LETTER THORN (ICELANDIC) - 0x00ff: 0xdf, # LATIN SMALL LETTER Y WITH DIAERESIS -} \ No newline at end of file + 0x009A: 0x3A, # CONTROL + 0x009B: 0x3B, # CONTROL + 0x009C: 0x04, # CONTROL + 0x009D: 0x14, # CONTROL + 0x009E: 0x3E, # CONTROL + 0x009F: 0xFF, # CONTROL + 0x00A0: 0x41, # NO-BREAK SPACE + 0x00A1: 0xAA, # INVERTED EXCLAMATION MARK + 0x00A2: 0xB0, # CENT SIGN + 0x00A3: 0xB1, # POUND SIGN + 0x00A4: 0x9F, # CURRENCY SIGN + 0x00A5: 0xB2, # YEN SIGN + 0x00A6: 0x6A, # BROKEN BAR + 0x00A7: 0xB5, # SECTION SIGN + 0x00A8: 0xBD, # DIAERESIS + 0x00A9: 0xB4, # COPYRIGHT SIGN + 0x00AA: 0x9A, # FEMININE ORDINAL INDICATOR + 0x00AB: 0x8A, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xBA, # NOT SIGN + 0x00AD: 0xCA, # SOFT HYPHEN + 0x00AE: 0xAF, # REGISTERED SIGN + 0x00AF: 0xBC, # MACRON + 0x00B0: 0x90, # DEGREE SIGN + 0x00B1: 0x8F, # PLUS-MINUS SIGN + 0x00B2: 0xEA, # SUPERSCRIPT TWO + 0x00B3: 0xFA, # SUPERSCRIPT THREE + 0x00B4: 0xBE, # ACUTE ACCENT + 0x00B5: 0xA0, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB3, # MIDDLE DOT + 0x00B8: 0x9D, # CEDILLA + 0x00B9: 0xDA, # SUPERSCRIPT ONE + 0x00BA: 0x9B, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0x8B, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xB7, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xB8, # VULGAR FRACTION ONE HALF + 0x00BE: 0xB9, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xAB, # INVERTED QUESTION MARK + 0x00C0: 0x64, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0x65, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0x62, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0x66, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x63, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x67, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0x9E, # LATIN CAPITAL LIGATURE AE + 0x00C7: 0x68, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0x74, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x71, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0x72, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0x73, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0x78, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0x75, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0x76, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0x77, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xAC, # LATIN CAPITAL LETTER ETH (ICELANDIC) + 0x00D1: 0x69, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xED, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEB, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xEF, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xEC, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xBF, # MULTIPLICATION SIGN + 0x00D8: 0x80, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xFD, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xFE, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xFB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xFC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xAD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xAE, # LATIN CAPITAL LETTER THORN (ICELANDIC) + 0x00DF: 0x59, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00E0: 0x44, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x45, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x42, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x46, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x43, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x47, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0x9C, # LATIN SMALL LIGATURE AE + 0x00E7: 0x48, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x54, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x51, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x52, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x53, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x58, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x55, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x56, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x57, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0x8C, # LATIN SMALL LETTER ETH (ICELANDIC) + 0x00F1: 0x49, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xCD, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xCE, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xCB, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xCF, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xCC, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xE1, # DIVISION SIGN + 0x00F8: 0x70, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xDD, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xDE, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xDB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xDC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0x8D, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0x8E, # LATIN SMALL LETTER THORN (ICELANDIC) + 0x00FF: 0xDF, # LATIN SMALL LETTER Y WITH DIAERESIS +} + diff --git a/Lib/encodings/cp856.py b/Lib/encodings/cp856.py index 3b7cbd0..fd515b0 100644 --- a/Lib/encodings/cp856.py +++ b/Lib/encodings/cp856.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u05d0' # 0x80 -> HEBREW LETTER ALEF u'\u05d1' # 0x81 -> HEBREW LETTER BET u'\u05d2' # 0x82 -> HEBREW LETTER GIMEL @@ -170,12 +170,12 @@ decoding_table = ( u'\u05d7' # 0x87 -> HEBREW LETTER HET u'\u05d8' # 0x88 -> HEBREW LETTER TET u'\u05d9' # 0x89 -> HEBREW LETTER YOD - u'\u05da' # 0x8a -> HEBREW LETTER FINAL KAF - u'\u05db' # 0x8b -> HEBREW LETTER KAF - u'\u05dc' # 0x8c -> HEBREW LETTER LAMED - u'\u05dd' # 0x8d -> HEBREW LETTER FINAL MEM - u'\u05de' # 0x8e -> HEBREW LETTER MEM - u'\u05df' # 0x8f -> HEBREW LETTER FINAL NUN + u'\u05da' # 0x8A -> HEBREW LETTER FINAL KAF + u'\u05db' # 0x8B -> HEBREW LETTER KAF + u'\u05dc' # 0x8C -> HEBREW LETTER LAMED + u'\u05dd' # 0x8D -> HEBREW LETTER FINAL MEM + u'\u05de' # 0x8E -> HEBREW LETTER MEM + u'\u05df' # 0x8F -> HEBREW LETTER FINAL NUN u'\u05e0' # 0x90 -> HEBREW LETTER NUN u'\u05e1' # 0x91 -> HEBREW LETTER SAMEKH u'\u05e2' # 0x92 -> HEBREW LETTER AYIN @@ -186,108 +186,108 @@ decoding_table = ( u'\u05e7' # 0x97 -> HEBREW LETTER QOF u'\u05e8' # 0x98 -> HEBREW LETTER RESH u'\u05e9' # 0x99 -> HEBREW LETTER SHIN - u'\u05ea' # 0x9a -> HEBREW LETTER TAV - u'\ufffe' # 0x9b -> UNDEFINED - u'\xa3' # 0x9c -> POUND SIGN - u'\ufffe' # 0x9d -> UNDEFINED - u'\xd7' # 0x9e -> MULTIPLICATION SIGN - u'\ufffe' # 0x9f -> UNDEFINED - u'\ufffe' # 0xa0 -> UNDEFINED - u'\ufffe' # 0xa1 -> UNDEFINED - u'\ufffe' # 0xa2 -> UNDEFINED - u'\ufffe' # 0xa3 -> UNDEFINED - u'\ufffe' # 0xa4 -> UNDEFINED - u'\ufffe' # 0xa5 -> UNDEFINED - u'\ufffe' # 0xa6 -> UNDEFINED - u'\ufffe' # 0xa7 -> UNDEFINED - u'\ufffe' # 0xa8 -> UNDEFINED - u'\xae' # 0xa9 -> REGISTERED SIGN - u'\xac' # 0xaa -> NOT SIGN - u'\xbd' # 0xab -> VULGAR FRACTION ONE HALF - u'\xbc' # 0xac -> VULGAR FRACTION ONE QUARTER - u'\ufffe' # 0xad -> UNDEFINED - u'\xab' # 0xae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xaf -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2591' # 0xb0 -> LIGHT SHADE - u'\u2592' # 0xb1 -> MEDIUM SHADE - u'\u2593' # 0xb2 -> DARK SHADE - u'\u2502' # 0xb3 -> BOX DRAWINGS LIGHT VERTICAL - u'\u2524' # 0xb4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT - u'\ufffe' # 0xb5 -> UNDEFINED - u'\ufffe' # 0xb6 -> UNDEFINED - u'\ufffe' # 0xb7 -> UNDEFINED - u'\xa9' # 0xb8 -> COPYRIGHT SIGN - u'\u2563' # 0xb9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT - u'\u2551' # 0xba -> BOX DRAWINGS DOUBLE VERTICAL - u'\u2557' # 0xbb -> BOX DRAWINGS DOUBLE DOWN AND LEFT - u'\u255d' # 0xbc -> BOX DRAWINGS DOUBLE UP AND LEFT - u'\xa2' # 0xbd -> CENT SIGN - u'\xa5' # 0xbe -> YEN SIGN - u'\u2510' # 0xbf -> BOX DRAWINGS LIGHT DOWN AND LEFT - u'\u2514' # 0xc0 -> BOX DRAWINGS LIGHT UP AND RIGHT - u'\u2534' # 0xc1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL - u'\u252c' # 0xc2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL - u'\u251c' # 0xc3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT - u'\u2500' # 0xc4 -> BOX DRAWINGS LIGHT HORIZONTAL - u'\u253c' # 0xc5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL - u'\ufffe' # 0xc6 -> UNDEFINED - u'\ufffe' # 0xc7 -> UNDEFINED - u'\u255a' # 0xc8 -> BOX DRAWINGS DOUBLE UP AND RIGHT - u'\u2554' # 0xc9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT - u'\u2569' # 0xca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL - u'\u2566' # 0xcb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL - u'\u2560' # 0xcc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT - u'\u2550' # 0xcd -> BOX DRAWINGS DOUBLE HORIZONTAL - u'\u256c' # 0xce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL - u'\xa4' # 0xcf -> CURRENCY SIGN - u'\ufffe' # 0xd0 -> UNDEFINED - u'\ufffe' # 0xd1 -> UNDEFINED - u'\ufffe' # 0xd2 -> UNDEFINED - u'\ufffe' # 0xd3 -> UNDEFINEDS - u'\ufffe' # 0xd4 -> UNDEFINED - u'\ufffe' # 0xd5 -> UNDEFINED - u'\ufffe' # 0xd6 -> UNDEFINEDE - u'\ufffe' # 0xd7 -> UNDEFINED - u'\ufffe' # 0xd8 -> UNDEFINED - u'\u2518' # 0xd9 -> BOX DRAWINGS LIGHT UP AND LEFT - u'\u250c' # 0xda -> BOX DRAWINGS LIGHT DOWN AND RIGHT - u'\u2588' # 0xdb -> FULL BLOCK - u'\u2584' # 0xdc -> LOWER HALF BLOCK - u'\xa6' # 0xdd -> BROKEN BAR - u'\ufffe' # 0xde -> UNDEFINED - u'\u2580' # 0xdf -> UPPER HALF BLOCK - u'\ufffe' # 0xe0 -> UNDEFINED - u'\ufffe' # 0xe1 -> UNDEFINED - u'\ufffe' # 0xe2 -> UNDEFINED - u'\ufffe' # 0xe3 -> UNDEFINED - u'\ufffe' # 0xe4 -> UNDEFINED - u'\ufffe' # 0xe5 -> UNDEFINED - u'\xb5' # 0xe6 -> MICRO SIGN - u'\ufffe' # 0xe7 -> UNDEFINED - u'\ufffe' # 0xe8 -> UNDEFINED - u'\ufffe' # 0xe9 -> UNDEFINED - u'\ufffe' # 0xea -> UNDEFINED - u'\ufffe' # 0xeb -> UNDEFINED - u'\ufffe' # 0xec -> UNDEFINED - u'\ufffe' # 0xed -> UNDEFINED - u'\xaf' # 0xee -> MACRON - u'\xb4' # 0xef -> ACUTE ACCENT - u'\xad' # 0xf0 -> SOFT HYPHEN - u'\xb1' # 0xf1 -> PLUS-MINUS SIGN - u'\u2017' # 0xf2 -> DOUBLE LOW LINE - u'\xbe' # 0xf3 -> VULGAR FRACTION THREE QUARTERS - u'\xb6' # 0xf4 -> PILCROW SIGN - u'\xa7' # 0xf5 -> SECTION SIGN - u'\xf7' # 0xf6 -> DIVISION SIGN - u'\xb8' # 0xf7 -> CEDILLA - u'\xb0' # 0xf8 -> DEGREE SIGN - u'\xa8' # 0xf9 -> DIAERESIS - u'\xb7' # 0xfa -> MIDDLE DOT - u'\xb9' # 0xfb -> SUPERSCRIPT ONE - u'\xb3' # 0xfc -> SUPERSCRIPT THREE - u'\xb2' # 0xfd -> SUPERSCRIPT TWO - u'\u25a0' # 0xfe -> BLACK SQUARE - u'\xa0' # 0xff -> NO-BREAK SPACE + u'\u05ea' # 0x9A -> HEBREW LETTER TAV + u'\ufffe' # 0x9B -> UNDEFINED + u'\xa3' # 0x9C -> POUND SIGN + u'\ufffe' # 0x9D -> UNDEFINED + u'\xd7' # 0x9E -> MULTIPLICATION SIGN + u'\ufffe' # 0x9F -> UNDEFINED + u'\ufffe' # 0xA0 -> UNDEFINED + u'\ufffe' # 0xA1 -> UNDEFINED + u'\ufffe' # 0xA2 -> UNDEFINED + u'\ufffe' # 0xA3 -> UNDEFINED + u'\ufffe' # 0xA4 -> UNDEFINED + u'\ufffe' # 0xA5 -> UNDEFINED + u'\ufffe' # 0xA6 -> UNDEFINED + u'\ufffe' # 0xA7 -> UNDEFINED + u'\ufffe' # 0xA8 -> UNDEFINED + u'\xae' # 0xA9 -> REGISTERED SIGN + u'\xac' # 0xAA -> NOT SIGN + u'\xbd' # 0xAB -> VULGAR FRACTION ONE HALF + u'\xbc' # 0xAC -> VULGAR FRACTION ONE QUARTER + u'\ufffe' # 0xAD -> UNDEFINED + u'\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2591' # 0xB0 -> LIGHT SHADE + u'\u2592' # 0xB1 -> MEDIUM SHADE + u'\u2593' # 0xB2 -> DARK SHADE + u'\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL + u'\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + u'\ufffe' # 0xB5 -> UNDEFINED + u'\ufffe' # 0xB6 -> UNDEFINED + u'\ufffe' # 0xB7 -> UNDEFINED + u'\xa9' # 0xB8 -> COPYRIGHT SIGN + u'\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + u'\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL + u'\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT + u'\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT + u'\xa2' # 0xBD -> CENT SIGN + u'\xa5' # 0xBE -> YEN SIGN + u'\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT + u'\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT + u'\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + u'\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + u'\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + u'\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL + u'\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + u'\ufffe' # 0xC6 -> UNDEFINED + u'\ufffe' # 0xC7 -> UNDEFINED + u'\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + u'\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + u'\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + u'\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + u'\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + u'\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL + u'\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + u'\xa4' # 0xCF -> CURRENCY SIGN + u'\ufffe' # 0xD0 -> UNDEFINED + u'\ufffe' # 0xD1 -> UNDEFINED + u'\ufffe' # 0xD2 -> UNDEFINED + u'\ufffe' # 0xD3 -> UNDEFINEDS + u'\ufffe' # 0xD4 -> UNDEFINED + u'\ufffe' # 0xD5 -> UNDEFINED + u'\ufffe' # 0xD6 -> UNDEFINEDE + u'\ufffe' # 0xD7 -> UNDEFINED + u'\ufffe' # 0xD8 -> UNDEFINED + u'\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT + u'\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT + u'\u2588' # 0xDB -> FULL BLOCK + u'\u2584' # 0xDC -> LOWER HALF BLOCK + u'\xa6' # 0xDD -> BROKEN BAR + u'\ufffe' # 0xDE -> UNDEFINED + u'\u2580' # 0xDF -> UPPER HALF BLOCK + u'\ufffe' # 0xE0 -> UNDEFINED + u'\ufffe' # 0xE1 -> UNDEFINED + u'\ufffe' # 0xE2 -> UNDEFINED + u'\ufffe' # 0xE3 -> UNDEFINED + u'\ufffe' # 0xE4 -> UNDEFINED + u'\ufffe' # 0xE5 -> UNDEFINED + u'\xb5' # 0xE6 -> MICRO SIGN + u'\ufffe' # 0xE7 -> UNDEFINED + u'\ufffe' # 0xE8 -> UNDEFINED + u'\ufffe' # 0xE9 -> UNDEFINED + u'\ufffe' # 0xEA -> UNDEFINED + u'\ufffe' # 0xEB -> UNDEFINED + u'\ufffe' # 0xEC -> UNDEFINED + u'\ufffe' # 0xED -> UNDEFINED + u'\xaf' # 0xEE -> MACRON + u'\xb4' # 0xEF -> ACUTE ACCENT + u'\xad' # 0xF0 -> SOFT HYPHEN + u'\xb1' # 0xF1 -> PLUS-MINUS SIGN + u'\u2017' # 0xF2 -> DOUBLE LOW LINE + u'\xbe' # 0xF3 -> VULGAR FRACTION THREE QUARTERS + u'\xb6' # 0xF4 -> PILCROW SIGN + u'\xa7' # 0xF5 -> SECTION SIGN + u'\xf7' # 0xF6 -> DIVISION SIGN + u'\xb8' # 0xF7 -> CEDILLA + u'\xb0' # 0xF8 -> DEGREE SIGN + u'\xa8' # 0xF9 -> DIAERESIS + u'\xb7' # 0xFA -> MIDDLE DOT + u'\xb9' # 0xFB -> SUPERSCRIPT ONE + u'\xb3' # 0xFC -> SUPERSCRIPT THREE + u'\xb2' # 0xFD -> SUPERSCRIPT TWO + u'\u25a0' # 0xFE -> BLACK SQUARE + u'\xa0' # 0xFF -> NO-BREAK SPACE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,97 +415,98 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xff, # NO-BREAK SPACE - 0x00a2: 0xbd, # CENT SIGN - 0x00a3: 0x9c, # POUND SIGN - 0x00a4: 0xcf, # CURRENCY SIGN - 0x00a5: 0xbe, # YEN SIGN - 0x00a6: 0xdd, # BROKEN BAR - 0x00a7: 0xf5, # SECTION SIGN - 0x00a8: 0xf9, # DIAERESIS - 0x00a9: 0xb8, # COPYRIGHT SIGN - 0x00ab: 0xae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xaa, # NOT SIGN - 0x00ad: 0xf0, # SOFT HYPHEN - 0x00ae: 0xa9, # REGISTERED SIGN - 0x00af: 0xee, # MACRON - 0x00b0: 0xf8, # DEGREE SIGN - 0x00b1: 0xf1, # PLUS-MINUS SIGN - 0x00b2: 0xfd, # SUPERSCRIPT TWO - 0x00b3: 0xfc, # SUPERSCRIPT THREE - 0x00b4: 0xef, # ACUTE ACCENT - 0x00b5: 0xe6, # MICRO SIGN - 0x00b6: 0xf4, # PILCROW SIGN - 0x00b7: 0xfa, # MIDDLE DOT - 0x00b8: 0xf7, # CEDILLA - 0x00b9: 0xfb, # SUPERSCRIPT ONE - 0x00bb: 0xaf, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xac, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xab, # VULGAR FRACTION ONE HALF - 0x00be: 0xf3, # VULGAR FRACTION THREE QUARTERS - 0x00d7: 0x9e, # MULTIPLICATION SIGN - 0x00f7: 0xf6, # DIVISION SIGN - 0x05d0: 0x80, # HEBREW LETTER ALEF - 0x05d1: 0x81, # HEBREW LETTER BET - 0x05d2: 0x82, # HEBREW LETTER GIMEL - 0x05d3: 0x83, # HEBREW LETTER DALET - 0x05d4: 0x84, # HEBREW LETTER HE - 0x05d5: 0x85, # HEBREW LETTER VAV - 0x05d6: 0x86, # HEBREW LETTER ZAYIN - 0x05d7: 0x87, # HEBREW LETTER HET - 0x05d8: 0x88, # HEBREW LETTER TET - 0x05d9: 0x89, # HEBREW LETTER YOD - 0x05da: 0x8a, # HEBREW LETTER FINAL KAF - 0x05db: 0x8b, # HEBREW LETTER KAF - 0x05dc: 0x8c, # HEBREW LETTER LAMED - 0x05dd: 0x8d, # HEBREW LETTER FINAL MEM - 0x05de: 0x8e, # HEBREW LETTER MEM - 0x05df: 0x8f, # HEBREW LETTER FINAL NUN - 0x05e0: 0x90, # HEBREW LETTER NUN - 0x05e1: 0x91, # HEBREW LETTER SAMEKH - 0x05e2: 0x92, # HEBREW LETTER AYIN - 0x05e3: 0x93, # HEBREW LETTER FINAL PE - 0x05e4: 0x94, # HEBREW LETTER PE - 0x05e5: 0x95, # HEBREW LETTER FINAL TSADI - 0x05e6: 0x96, # HEBREW LETTER TSADI - 0x05e7: 0x97, # HEBREW LETTER QOF - 0x05e8: 0x98, # HEBREW LETTER RESH - 0x05e9: 0x99, # HEBREW LETTER SHIN - 0x05ea: 0x9a, # HEBREW LETTER TAV - 0x2017: 0xf2, # DOUBLE LOW LINE - 0x2500: 0xc4, # BOX DRAWINGS LIGHT HORIZONTAL - 0x2502: 0xb3, # BOX DRAWINGS LIGHT VERTICAL - 0x250c: 0xda, # BOX DRAWINGS LIGHT DOWN AND RIGHT - 0x2510: 0xbf, # BOX DRAWINGS LIGHT DOWN AND LEFT - 0x2514: 0xc0, # BOX DRAWINGS LIGHT UP AND RIGHT - 0x2518: 0xd9, # BOX DRAWINGS LIGHT UP AND LEFT - 0x251c: 0xc3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT - 0x2524: 0xb4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT - 0x252c: 0xc2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL - 0x2534: 0xc1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL - 0x253c: 0xc5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL - 0x2550: 0xcd, # BOX DRAWINGS DOUBLE HORIZONTAL - 0x2551: 0xba, # BOX DRAWINGS DOUBLE VERTICAL - 0x2554: 0xc9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT - 0x2557: 0xbb, # BOX DRAWINGS DOUBLE DOWN AND LEFT - 0x255a: 0xc8, # BOX DRAWINGS DOUBLE UP AND RIGHT - 0x255d: 0xbc, # BOX DRAWINGS DOUBLE UP AND LEFT - 0x2560: 0xcc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT - 0x2563: 0xb9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT - 0x2566: 0xcb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL - 0x2569: 0xca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL - 0x256c: 0xce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL - 0x2580: 0xdf, # UPPER HALF BLOCK - 0x2584: 0xdc, # LOWER HALF BLOCK - 0x2588: 0xdb, # FULL BLOCK - 0x2591: 0xb0, # LIGHT SHADE - 0x2592: 0xb1, # MEDIUM SHADE - 0x2593: 0xb2, # DARK SHADE - 0x25a0: 0xfe, # BLACK SQUARE -} \ No newline at end of file + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xFF, # NO-BREAK SPACE + 0x00A2: 0xBD, # CENT SIGN + 0x00A3: 0x9C, # POUND SIGN + 0x00A4: 0xCF, # CURRENCY SIGN + 0x00A5: 0xBE, # YEN SIGN + 0x00A6: 0xDD, # BROKEN BAR + 0x00A7: 0xF5, # SECTION SIGN + 0x00A8: 0xF9, # DIAERESIS + 0x00A9: 0xB8, # COPYRIGHT SIGN + 0x00AB: 0xAE, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAA, # NOT SIGN + 0x00AD: 0xF0, # SOFT HYPHEN + 0x00AE: 0xA9, # REGISTERED SIGN + 0x00AF: 0xEE, # MACRON + 0x00B0: 0xF8, # DEGREE SIGN + 0x00B1: 0xF1, # PLUS-MINUS SIGN + 0x00B2: 0xFD, # SUPERSCRIPT TWO + 0x00B3: 0xFC, # SUPERSCRIPT THREE + 0x00B4: 0xEF, # ACUTE ACCENT + 0x00B5: 0xE6, # MICRO SIGN + 0x00B6: 0xF4, # PILCROW SIGN + 0x00B7: 0xFA, # MIDDLE DOT + 0x00B8: 0xF7, # CEDILLA + 0x00B9: 0xFB, # SUPERSCRIPT ONE + 0x00BB: 0xAF, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xAC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xAB, # VULGAR FRACTION ONE HALF + 0x00BE: 0xF3, # VULGAR FRACTION THREE QUARTERS + 0x00D7: 0x9E, # MULTIPLICATION SIGN + 0x00F7: 0xF6, # DIVISION SIGN + 0x05D0: 0x80, # HEBREW LETTER ALEF + 0x05D1: 0x81, # HEBREW LETTER BET + 0x05D2: 0x82, # HEBREW LETTER GIMEL + 0x05D3: 0x83, # HEBREW LETTER DALET + 0x05D4: 0x84, # HEBREW LETTER HE + 0x05D5: 0x85, # HEBREW LETTER VAV + 0x05D6: 0x86, # HEBREW LETTER ZAYIN + 0x05D7: 0x87, # HEBREW LETTER HET + 0x05D8: 0x88, # HEBREW LETTER TET + 0x05D9: 0x89, # HEBREW LETTER YOD + 0x05DA: 0x8A, # HEBREW LETTER FINAL KAF + 0x05DB: 0x8B, # HEBREW LETTER KAF + 0x05DC: 0x8C, # HEBREW LETTER LAMED + 0x05DD: 0x8D, # HEBREW LETTER FINAL MEM + 0x05DE: 0x8E, # HEBREW LETTER MEM + 0x05DF: 0x8F, # HEBREW LETTER FINAL NUN + 0x05E0: 0x90, # HEBREW LETTER NUN + 0x05E1: 0x91, # HEBREW LETTER SAMEKH + 0x05E2: 0x92, # HEBREW LETTER AYIN + 0x05E3: 0x93, # HEBREW LETTER FINAL PE + 0x05E4: 0x94, # HEBREW LETTER PE + 0x05E5: 0x95, # HEBREW LETTER FINAL TSADI + 0x05E6: 0x96, # HEBREW LETTER TSADI + 0x05E7: 0x97, # HEBREW LETTER QOF + 0x05E8: 0x98, # HEBREW LETTER RESH + 0x05E9: 0x99, # HEBREW LETTER SHIN + 0x05EA: 0x9A, # HEBREW LETTER TAV + 0x2017: 0xF2, # DOUBLE LOW LINE + 0x2500: 0xC4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0xB3, # BOX DRAWINGS LIGHT VERTICAL + 0x250C: 0xDA, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0xBF, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0xC0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0xD9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251C: 0xC3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0xB4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252C: 0xC2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0xC1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253C: 0xC5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0xCD, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0xBA, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0xC9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0xBB, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255A: 0xC8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255D: 0xBC, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0xCC, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0xB9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0xCB, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0xCA, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256C: 0xCE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0xDF, # UPPER HALF BLOCK + 0x2584: 0xDC, # LOWER HALF BLOCK + 0x2588: 0xDB, # FULL BLOCK + 0x2591: 0xB0, # LIGHT SHADE + 0x2592: 0xB1, # MEDIUM SHADE + 0x2593: 0xB2, # DARK SHADE + 0x25A0: 0xFE, # BLACK SQUARE +} + diff --git a/Lib/encodings/cp874.py b/Lib/encodings/cp874.py index e7348d0..0a49cce 100644 --- a/Lib/encodings/cp874.py +++ b/Lib/encodings/cp874.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\ufffe' # 0x82 -> UNDEFINED @@ -170,12 +170,12 @@ decoding_table = ( u'\ufffe' # 0x87 -> UNDEFINED u'\ufffe' # 0x88 -> UNDEFINED u'\ufffe' # 0x89 -> UNDEFINED - u'\ufffe' # 0x8a -> UNDEFINED - u'\ufffe' # 0x8b -> UNDEFINED - u'\ufffe' # 0x8c -> UNDEFINED - u'\ufffe' # 0x8d -> UNDEFINED - u'\ufffe' # 0x8e -> UNDEFINED - u'\ufffe' # 0x8f -> UNDEFINED + u'\ufffe' # 0x8A -> UNDEFINED + u'\ufffe' # 0x8B -> UNDEFINED + u'\ufffe' # 0x8C -> UNDEFINED + u'\ufffe' # 0x8D -> UNDEFINED + u'\ufffe' # 0x8E -> UNDEFINED + u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK @@ -186,108 +186,108 @@ decoding_table = ( u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\ufffe' # 0x99 -> UNDEFINED - u'\ufffe' # 0x9a -> UNDEFINED - u'\ufffe' # 0x9b -> UNDEFINED - u'\ufffe' # 0x9c -> UNDEFINED - u'\ufffe' # 0x9d -> UNDEFINED - u'\ufffe' # 0x9e -> UNDEFINED - u'\ufffe' # 0x9f -> UNDEFINED - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0e01' # 0xa1 -> THAI CHARACTER KO KAI - u'\u0e02' # 0xa2 -> THAI CHARACTER KHO KHAI - u'\u0e03' # 0xa3 -> THAI CHARACTER KHO KHUAT - u'\u0e04' # 0xa4 -> THAI CHARACTER KHO KHWAI - u'\u0e05' # 0xa5 -> THAI CHARACTER KHO KHON - u'\u0e06' # 0xa6 -> THAI CHARACTER KHO RAKHANG - u'\u0e07' # 0xa7 -> THAI CHARACTER NGO NGU - u'\u0e08' # 0xa8 -> THAI CHARACTER CHO CHAN - u'\u0e09' # 0xa9 -> THAI CHARACTER CHO CHING - u'\u0e0a' # 0xaa -> THAI CHARACTER CHO CHANG - u'\u0e0b' # 0xab -> THAI CHARACTER SO SO - u'\u0e0c' # 0xac -> THAI CHARACTER CHO CHOE - u'\u0e0d' # 0xad -> THAI CHARACTER YO YING - u'\u0e0e' # 0xae -> THAI CHARACTER DO CHADA - u'\u0e0f' # 0xaf -> THAI CHARACTER TO PATAK - u'\u0e10' # 0xb0 -> THAI CHARACTER THO THAN - u'\u0e11' # 0xb1 -> THAI CHARACTER THO NANGMONTHO - u'\u0e12' # 0xb2 -> THAI CHARACTER THO PHUTHAO - u'\u0e13' # 0xb3 -> THAI CHARACTER NO NEN - u'\u0e14' # 0xb4 -> THAI CHARACTER DO DEK - u'\u0e15' # 0xb5 -> THAI CHARACTER TO TAO - u'\u0e16' # 0xb6 -> THAI CHARACTER THO THUNG - u'\u0e17' # 0xb7 -> THAI CHARACTER THO THAHAN - u'\u0e18' # 0xb8 -> THAI CHARACTER THO THONG - u'\u0e19' # 0xb9 -> THAI CHARACTER NO NU - u'\u0e1a' # 0xba -> THAI CHARACTER BO BAIMAI - u'\u0e1b' # 0xbb -> THAI CHARACTER PO PLA - u'\u0e1c' # 0xbc -> THAI CHARACTER PHO PHUNG - u'\u0e1d' # 0xbd -> THAI CHARACTER FO FA - u'\u0e1e' # 0xbe -> THAI CHARACTER PHO PHAN - u'\u0e1f' # 0xbf -> THAI CHARACTER FO FAN - u'\u0e20' # 0xc0 -> THAI CHARACTER PHO SAMPHAO - u'\u0e21' # 0xc1 -> THAI CHARACTER MO MA - u'\u0e22' # 0xc2 -> THAI CHARACTER YO YAK - u'\u0e23' # 0xc3 -> THAI CHARACTER RO RUA - u'\u0e24' # 0xc4 -> THAI CHARACTER RU - u'\u0e25' # 0xc5 -> THAI CHARACTER LO LING - u'\u0e26' # 0xc6 -> THAI CHARACTER LU - u'\u0e27' # 0xc7 -> THAI CHARACTER WO WAEN - u'\u0e28' # 0xc8 -> THAI CHARACTER SO SALA - u'\u0e29' # 0xc9 -> THAI CHARACTER SO RUSI - u'\u0e2a' # 0xca -> THAI CHARACTER SO SUA - u'\u0e2b' # 0xcb -> THAI CHARACTER HO HIP - u'\u0e2c' # 0xcc -> THAI CHARACTER LO CHULA - u'\u0e2d' # 0xcd -> THAI CHARACTER O ANG - u'\u0e2e' # 0xce -> THAI CHARACTER HO NOKHUK - u'\u0e2f' # 0xcf -> THAI CHARACTER PAIYANNOI - u'\u0e30' # 0xd0 -> THAI CHARACTER SARA A - u'\u0e31' # 0xd1 -> THAI CHARACTER MAI HAN-AKAT - u'\u0e32' # 0xd2 -> THAI CHARACTER SARA AA - u'\u0e33' # 0xd3 -> THAI CHARACTER SARA AM - u'\u0e34' # 0xd4 -> THAI CHARACTER SARA I - u'\u0e35' # 0xd5 -> THAI CHARACTER SARA II - u'\u0e36' # 0xd6 -> THAI CHARACTER SARA UE - u'\u0e37' # 0xd7 -> THAI CHARACTER SARA UEE - u'\u0e38' # 0xd8 -> THAI CHARACTER SARA U - u'\u0e39' # 0xd9 -> THAI CHARACTER SARA UU - u'\u0e3a' # 0xda -> THAI CHARACTER PHINTHU - u'\ufffe' # 0xdb -> UNDEFINED - u'\ufffe' # 0xdc -> UNDEFINED - u'\ufffe' # 0xdd -> UNDEFINED - u'\ufffe' # 0xde -> UNDEFINED - u'\u0e3f' # 0xdf -> THAI CURRENCY SYMBOL BAHT - u'\u0e40' # 0xe0 -> THAI CHARACTER SARA E - u'\u0e41' # 0xe1 -> THAI CHARACTER SARA AE - u'\u0e42' # 0xe2 -> THAI CHARACTER SARA O - u'\u0e43' # 0xe3 -> THAI CHARACTER SARA AI MAIMUAN - u'\u0e44' # 0xe4 -> THAI CHARACTER SARA AI MAIMALAI - u'\u0e45' # 0xe5 -> THAI CHARACTER LAKKHANGYAO - u'\u0e46' # 0xe6 -> THAI CHARACTER MAIYAMOK - u'\u0e47' # 0xe7 -> THAI CHARACTER MAITAIKHU - u'\u0e48' # 0xe8 -> THAI CHARACTER MAI EK - u'\u0e49' # 0xe9 -> THAI CHARACTER MAI THO - u'\u0e4a' # 0xea -> THAI CHARACTER MAI TRI - u'\u0e4b' # 0xeb -> THAI CHARACTER MAI CHATTAWA - u'\u0e4c' # 0xec -> THAI CHARACTER THANTHAKHAT - u'\u0e4d' # 0xed -> THAI CHARACTER NIKHAHIT - u'\u0e4e' # 0xee -> THAI CHARACTER YAMAKKAN - u'\u0e4f' # 0xef -> THAI CHARACTER FONGMAN - u'\u0e50' # 0xf0 -> THAI DIGIT ZERO - u'\u0e51' # 0xf1 -> THAI DIGIT ONE - u'\u0e52' # 0xf2 -> THAI DIGIT TWO - u'\u0e53' # 0xf3 -> THAI DIGIT THREE - u'\u0e54' # 0xf4 -> THAI DIGIT FOUR - u'\u0e55' # 0xf5 -> THAI DIGIT FIVE - u'\u0e56' # 0xf6 -> THAI DIGIT SIX - u'\u0e57' # 0xf7 -> THAI DIGIT SEVEN - u'\u0e58' # 0xf8 -> THAI DIGIT EIGHT - u'\u0e59' # 0xf9 -> THAI DIGIT NINE - u'\u0e5a' # 0xfa -> THAI CHARACTER ANGKHANKHU - u'\u0e5b' # 0xfb -> THAI CHARACTER KHOMUT - u'\ufffe' # 0xfc -> UNDEFINED - u'\ufffe' # 0xfd -> UNDEFINED - u'\ufffe' # 0xfe -> UNDEFINED - u'\ufffe' # 0xff -> UNDEFINED + u'\ufffe' # 0x9A -> UNDEFINED + u'\ufffe' # 0x9B -> UNDEFINED + u'\ufffe' # 0x9C -> UNDEFINED + u'\ufffe' # 0x9D -> UNDEFINED + u'\ufffe' # 0x9E -> UNDEFINED + u'\ufffe' # 0x9F -> UNDEFINED + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI + u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI + u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT + u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI + u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON + u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG + u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU + u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN + u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING + u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG + u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO + u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE + u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING + u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA + u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK + u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN + u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO + u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO + u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN + u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK + u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO + u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG + u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN + u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG + u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU + u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI + u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA + u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG + u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA + u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN + u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN + u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO + u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA + u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK + u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA + u'\u0e24' # 0xC4 -> THAI CHARACTER RU + u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING + u'\u0e26' # 0xC6 -> THAI CHARACTER LU + u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN + u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA + u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI + u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA + u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP + u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA + u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG + u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK + u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI + u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A + u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT + u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA + u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM + u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I + u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II + u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE + u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE + u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U + u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU + u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU + u'\ufffe' # 0xDB -> UNDEFINED + u'\ufffe' # 0xDC -> UNDEFINED + u'\ufffe' # 0xDD -> UNDEFINED + u'\ufffe' # 0xDE -> UNDEFINED + u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT + u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E + u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE + u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O + u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN + u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI + u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO + u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK + u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU + u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK + u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO + u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI + u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA + u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT + u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT + u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN + u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN + u'\u0e50' # 0xF0 -> THAI DIGIT ZERO + u'\u0e51' # 0xF1 -> THAI DIGIT ONE + u'\u0e52' # 0xF2 -> THAI DIGIT TWO + u'\u0e53' # 0xF3 -> THAI DIGIT THREE + u'\u0e54' # 0xF4 -> THAI DIGIT FOUR + u'\u0e55' # 0xF5 -> THAI DIGIT FIVE + u'\u0e56' # 0xF6 -> THAI DIGIT SIX + u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN + u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT + u'\u0e59' # 0xF9 -> THAI DIGIT NINE + u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU + u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT + u'\ufffe' # 0xFC -> UNDEFINED + u'\ufffe' # 0xFD -> UNDEFINED + u'\ufffe' # 0xFE -> UNDEFINED + u'\ufffe' # 0xFF -> UNDEFINED ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,107 +415,108 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x0e01: 0xa1, # THAI CHARACTER KO KAI - 0x0e02: 0xa2, # THAI CHARACTER KHO KHAI - 0x0e03: 0xa3, # THAI CHARACTER KHO KHUAT - 0x0e04: 0xa4, # THAI CHARACTER KHO KHWAI - 0x0e05: 0xa5, # THAI CHARACTER KHO KHON - 0x0e06: 0xa6, # THAI CHARACTER KHO RAKHANG - 0x0e07: 0xa7, # THAI CHARACTER NGO NGU - 0x0e08: 0xa8, # THAI CHARACTER CHO CHAN - 0x0e09: 0xa9, # THAI CHARACTER CHO CHING - 0x0e0a: 0xaa, # THAI CHARACTER CHO CHANG - 0x0e0b: 0xab, # THAI CHARACTER SO SO - 0x0e0c: 0xac, # THAI CHARACTER CHO CHOE - 0x0e0d: 0xad, # THAI CHARACTER YO YING - 0x0e0e: 0xae, # THAI CHARACTER DO CHADA - 0x0e0f: 0xaf, # THAI CHARACTER TO PATAK - 0x0e10: 0xb0, # THAI CHARACTER THO THAN - 0x0e11: 0xb1, # THAI CHARACTER THO NANGMONTHO - 0x0e12: 0xb2, # THAI CHARACTER THO PHUTHAO - 0x0e13: 0xb3, # THAI CHARACTER NO NEN - 0x0e14: 0xb4, # THAI CHARACTER DO DEK - 0x0e15: 0xb5, # THAI CHARACTER TO TAO - 0x0e16: 0xb6, # THAI CHARACTER THO THUNG - 0x0e17: 0xb7, # THAI CHARACTER THO THAHAN - 0x0e18: 0xb8, # THAI CHARACTER THO THONG - 0x0e19: 0xb9, # THAI CHARACTER NO NU - 0x0e1a: 0xba, # THAI CHARACTER BO BAIMAI - 0x0e1b: 0xbb, # THAI CHARACTER PO PLA - 0x0e1c: 0xbc, # THAI CHARACTER PHO PHUNG - 0x0e1d: 0xbd, # THAI CHARACTER FO FA - 0x0e1e: 0xbe, # THAI CHARACTER PHO PHAN - 0x0e1f: 0xbf, # THAI CHARACTER FO FAN - 0x0e20: 0xc0, # THAI CHARACTER PHO SAMPHAO - 0x0e21: 0xc1, # THAI CHARACTER MO MA - 0x0e22: 0xc2, # THAI CHARACTER YO YAK - 0x0e23: 0xc3, # THAI CHARACTER RO RUA - 0x0e24: 0xc4, # THAI CHARACTER RU - 0x0e25: 0xc5, # THAI CHARACTER LO LING - 0x0e26: 0xc6, # THAI CHARACTER LU - 0x0e27: 0xc7, # THAI CHARACTER WO WAEN - 0x0e28: 0xc8, # THAI CHARACTER SO SALA - 0x0e29: 0xc9, # THAI CHARACTER SO RUSI - 0x0e2a: 0xca, # THAI CHARACTER SO SUA - 0x0e2b: 0xcb, # THAI CHARACTER HO HIP - 0x0e2c: 0xcc, # THAI CHARACTER LO CHULA - 0x0e2d: 0xcd, # THAI CHARACTER O ANG - 0x0e2e: 0xce, # THAI CHARACTER HO NOKHUK - 0x0e2f: 0xcf, # THAI CHARACTER PAIYANNOI - 0x0e30: 0xd0, # THAI CHARACTER SARA A - 0x0e31: 0xd1, # THAI CHARACTER MAI HAN-AKAT - 0x0e32: 0xd2, # THAI CHARACTER SARA AA - 0x0e33: 0xd3, # THAI CHARACTER SARA AM - 0x0e34: 0xd4, # THAI CHARACTER SARA I - 0x0e35: 0xd5, # THAI CHARACTER SARA II - 0x0e36: 0xd6, # THAI CHARACTER SARA UE - 0x0e37: 0xd7, # THAI CHARACTER SARA UEE - 0x0e38: 0xd8, # THAI CHARACTER SARA U - 0x0e39: 0xd9, # THAI CHARACTER SARA UU - 0x0e3a: 0xda, # THAI CHARACTER PHINTHU - 0x0e3f: 0xdf, # THAI CURRENCY SYMBOL BAHT - 0x0e40: 0xe0, # THAI CHARACTER SARA E - 0x0e41: 0xe1, # THAI CHARACTER SARA AE - 0x0e42: 0xe2, # THAI CHARACTER SARA O - 0x0e43: 0xe3, # THAI CHARACTER SARA AI MAIMUAN - 0x0e44: 0xe4, # THAI CHARACTER SARA AI MAIMALAI - 0x0e45: 0xe5, # THAI CHARACTER LAKKHANGYAO - 0x0e46: 0xe6, # THAI CHARACTER MAIYAMOK - 0x0e47: 0xe7, # THAI CHARACTER MAITAIKHU - 0x0e48: 0xe8, # THAI CHARACTER MAI EK - 0x0e49: 0xe9, # THAI CHARACTER MAI THO - 0x0e4a: 0xea, # THAI CHARACTER MAI TRI - 0x0e4b: 0xeb, # THAI CHARACTER MAI CHATTAWA - 0x0e4c: 0xec, # THAI CHARACTER THANTHAKHAT - 0x0e4d: 0xed, # THAI CHARACTER NIKHAHIT - 0x0e4e: 0xee, # THAI CHARACTER YAMAKKAN - 0x0e4f: 0xef, # THAI CHARACTER FONGMAN - 0x0e50: 0xf0, # THAI DIGIT ZERO - 0x0e51: 0xf1, # THAI DIGIT ONE - 0x0e52: 0xf2, # THAI DIGIT TWO - 0x0e53: 0xf3, # THAI DIGIT THREE - 0x0e54: 0xf4, # THAI DIGIT FOUR - 0x0e55: 0xf5, # THAI DIGIT FIVE - 0x0e56: 0xf6, # THAI DIGIT SIX - 0x0e57: 0xf7, # THAI DIGIT SEVEN - 0x0e58: 0xf8, # THAI DIGIT EIGHT - 0x0e59: 0xf9, # THAI DIGIT NINE - 0x0e5a: 0xfa, # THAI CHARACTER ANGKHANKHU - 0x0e5b: 0xfb, # THAI CHARACTER KHOMUT + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x0E01: 0xA1, # THAI CHARACTER KO KAI + 0x0E02: 0xA2, # THAI CHARACTER KHO KHAI + 0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT + 0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI + 0x0E05: 0xA5, # THAI CHARACTER KHO KHON + 0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG + 0x0E07: 0xA7, # THAI CHARACTER NGO NGU + 0x0E08: 0xA8, # THAI CHARACTER CHO CHAN + 0x0E09: 0xA9, # THAI CHARACTER CHO CHING + 0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG + 0x0E0B: 0xAB, # THAI CHARACTER SO SO + 0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE + 0x0E0D: 0xAD, # THAI CHARACTER YO YING + 0x0E0E: 0xAE, # THAI CHARACTER DO CHADA + 0x0E0F: 0xAF, # THAI CHARACTER TO PATAK + 0x0E10: 0xB0, # THAI CHARACTER THO THAN + 0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO + 0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO + 0x0E13: 0xB3, # THAI CHARACTER NO NEN + 0x0E14: 0xB4, # THAI CHARACTER DO DEK + 0x0E15: 0xB5, # THAI CHARACTER TO TAO + 0x0E16: 0xB6, # THAI CHARACTER THO THUNG + 0x0E17: 0xB7, # THAI CHARACTER THO THAHAN + 0x0E18: 0xB8, # THAI CHARACTER THO THONG + 0x0E19: 0xB9, # THAI CHARACTER NO NU + 0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI + 0x0E1B: 0xBB, # THAI CHARACTER PO PLA + 0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG + 0x0E1D: 0xBD, # THAI CHARACTER FO FA + 0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN + 0x0E1F: 0xBF, # THAI CHARACTER FO FAN + 0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO + 0x0E21: 0xC1, # THAI CHARACTER MO MA + 0x0E22: 0xC2, # THAI CHARACTER YO YAK + 0x0E23: 0xC3, # THAI CHARACTER RO RUA + 0x0E24: 0xC4, # THAI CHARACTER RU + 0x0E25: 0xC5, # THAI CHARACTER LO LING + 0x0E26: 0xC6, # THAI CHARACTER LU + 0x0E27: 0xC7, # THAI CHARACTER WO WAEN + 0x0E28: 0xC8, # THAI CHARACTER SO SALA + 0x0E29: 0xC9, # THAI CHARACTER SO RUSI + 0x0E2A: 0xCA, # THAI CHARACTER SO SUA + 0x0E2B: 0xCB, # THAI CHARACTER HO HIP + 0x0E2C: 0xCC, # THAI CHARACTER LO CHULA + 0x0E2D: 0xCD, # THAI CHARACTER O ANG + 0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK + 0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI + 0x0E30: 0xD0, # THAI CHARACTER SARA A + 0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT + 0x0E32: 0xD2, # THAI CHARACTER SARA AA + 0x0E33: 0xD3, # THAI CHARACTER SARA AM + 0x0E34: 0xD4, # THAI CHARACTER SARA I + 0x0E35: 0xD5, # THAI CHARACTER SARA II + 0x0E36: 0xD6, # THAI CHARACTER SARA UE + 0x0E37: 0xD7, # THAI CHARACTER SARA UEE + 0x0E38: 0xD8, # THAI CHARACTER SARA U + 0x0E39: 0xD9, # THAI CHARACTER SARA UU + 0x0E3A: 0xDA, # THAI CHARACTER PHINTHU + 0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT + 0x0E40: 0xE0, # THAI CHARACTER SARA E + 0x0E41: 0xE1, # THAI CHARACTER SARA AE + 0x0E42: 0xE2, # THAI CHARACTER SARA O + 0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN + 0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI + 0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO + 0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK + 0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU + 0x0E48: 0xE8, # THAI CHARACTER MAI EK + 0x0E49: 0xE9, # THAI CHARACTER MAI THO + 0x0E4A: 0xEA, # THAI CHARACTER MAI TRI + 0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA + 0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT + 0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT + 0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN + 0x0E4F: 0xEF, # THAI CHARACTER FONGMAN + 0x0E50: 0xF0, # THAI DIGIT ZERO + 0x0E51: 0xF1, # THAI DIGIT ONE + 0x0E52: 0xF2, # THAI DIGIT TWO + 0x0E53: 0xF3, # THAI DIGIT THREE + 0x0E54: 0xF4, # THAI DIGIT FOUR + 0x0E55: 0xF5, # THAI DIGIT FIVE + 0x0E56: 0xF6, # THAI DIGIT SIX + 0x0E57: 0xF7, # THAI DIGIT SEVEN + 0x0E58: 0xF8, # THAI DIGIT EIGHT + 0x0E59: 0xF9, # THAI DIGIT NINE + 0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU + 0x0E5B: 0xFB, # THAI CHARACTER KHOMUT 0x2013: 0x96, # EN DASH 0x2014: 0x97, # EM DASH 0x2018: 0x91, # LEFT SINGLE QUOTATION MARK 0x2019: 0x92, # RIGHT SINGLE QUOTATION MARK - 0x201c: 0x93, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0x94, # RIGHT DOUBLE QUOTATION MARK + 0x201C: 0x93, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0x94, # RIGHT DOUBLE QUOTATION MARK 0x2022: 0x95, # BULLET 0x2026: 0x85, # HORIZONTAL ELLIPSIS - 0x20ac: 0x80, # EURO SIGN -} \ No newline at end of file + 0x20AC: 0x80, # EURO SIGN +} + diff --git a/Lib/encodings/cp875.py b/Lib/encodings/cp875.py index ce3962b..7cfdcf4 100644 --- a/Lib/encodings/cp875.py +++ b/Lib/encodings/cp875.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL - u'\x8e' # 0x0a -> CONTROL - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\x8e' # 0x0A -> CONTROL + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x92' # 0x1a -> CONTROL - u'\x8f' # 0x1b -> CONTROL - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x92' # 0x1A -> CONTROL + u'\x8f' # 0x1B -> CONTROL + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL @@ -74,12 +74,12 @@ decoding_table = ( u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL - u'\x8a' # 0x2a -> CONTROL - u'\x8b' # 0x2b -> CONTROL - u'\x8c' # 0x2c -> CONTROL - u'\x05' # 0x2d -> ENQUIRY - u'\x06' # 0x2e -> ACKNOWLEDGE - u'\x07' # 0x2f -> BELL + u'\x8a' # 0x2A -> CONTROL + u'\x8b' # 0x2B -> CONTROL + u'\x8c' # 0x2C -> CONTROL + u'\x05' # 0x2D -> ENQUIRY + u'\x06' # 0x2E -> ACKNOWLEDGE + u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE @@ -90,12 +90,12 @@ decoding_table = ( u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL - u'\x9a' # 0x3a -> CONTROL - u'\x9b' # 0x3b -> CONTROL - u'\x14' # 0x3c -> DEVICE CONTROL FOUR - u'\x15' # 0x3d -> NEGATIVE ACKNOWLEDGE - u'\x9e' # 0x3e -> CONTROL - u'\x1a' # 0x3f -> SUBSTITUTE + u'\x9a' # 0x3A -> CONTROL + u'\x9b' # 0x3B -> CONTROL + u'\x14' # 0x3C -> DEVICE CONTROL FOUR + u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + u'\x9e' # 0x3E -> CONTROL + u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\u0391' # 0x41 -> GREEK CAPITAL LETTER ALPHA u'\u0392' # 0x42 -> GREEK CAPITAL LETTER BETA @@ -106,12 +106,12 @@ decoding_table = ( u'\u0397' # 0x47 -> GREEK CAPITAL LETTER ETA u'\u0398' # 0x48 -> GREEK CAPITAL LETTER THETA u'\u0399' # 0x49 -> GREEK CAPITAL LETTER IOTA - u'[' # 0x4a -> LEFT SQUARE BRACKET - u'.' # 0x4b -> FULL STOP - u'<' # 0x4c -> LESS-THAN SIGN - u'(' # 0x4d -> LEFT PARENTHESIS - u'+' # 0x4e -> PLUS SIGN - u'!' # 0x4f -> EXCLAMATION MARK + u'[' # 0x4A -> LEFT SQUARE BRACKET + u'.' # 0x4B -> FULL STOP + u'<' # 0x4C -> LESS-THAN SIGN + u'(' # 0x4D -> LEFT PARENTHESIS + u'+' # 0x4E -> PLUS SIGN + u'!' # 0x4F -> EXCLAMATION MARK u'&' # 0x50 -> AMPERSAND u'\u039a' # 0x51 -> GREEK CAPITAL LETTER KAPPA u'\u039b' # 0x52 -> GREEK CAPITAL LETTER LAMDA @@ -122,12 +122,12 @@ decoding_table = ( u'\u03a0' # 0x57 -> GREEK CAPITAL LETTER PI u'\u03a1' # 0x58 -> GREEK CAPITAL LETTER RHO u'\u03a3' # 0x59 -> GREEK CAPITAL LETTER SIGMA - u']' # 0x5a -> RIGHT SQUARE BRACKET - u'$' # 0x5b -> DOLLAR SIGN - u'*' # 0x5c -> ASTERISK - u')' # 0x5d -> RIGHT PARENTHESIS - u';' # 0x5e -> SEMICOLON - u'^' # 0x5f -> CIRCUMFLEX ACCENT + u']' # 0x5A -> RIGHT SQUARE BRACKET + u'$' # 0x5B -> DOLLAR SIGN + u'*' # 0x5C -> ASTERISK + u')' # 0x5D -> RIGHT PARENTHESIS + u';' # 0x5E -> SEMICOLON + u'^' # 0x5F -> CIRCUMFLEX ACCENT u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\u03a4' # 0x62 -> GREEK CAPITAL LETTER TAU @@ -138,12 +138,12 @@ decoding_table = ( u'\u03a9' # 0x67 -> GREEK CAPITAL LETTER OMEGA u'\u03aa' # 0x68 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA u'\u03ab' # 0x69 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - u'|' # 0x6a -> VERTICAL LINE - u',' # 0x6b -> COMMA - u'%' # 0x6c -> PERCENT SIGN - u'_' # 0x6d -> LOW LINE - u'>' # 0x6e -> GREATER-THAN SIGN - u'?' # 0x6f -> QUESTION MARK + u'|' # 0x6A -> VERTICAL LINE + u',' # 0x6B -> COMMA + u'%' # 0x6C -> PERCENT SIGN + u'_' # 0x6D -> LOW LINE + u'>' # 0x6E -> GREATER-THAN SIGN + u'?' # 0x6F -> QUESTION MARK u'\xa8' # 0x70 -> DIAERESIS u'\u0386' # 0x71 -> GREEK CAPITAL LETTER ALPHA WITH TONOS u'\u0388' # 0x72 -> GREEK CAPITAL LETTER EPSILON WITH TONOS @@ -154,12 +154,12 @@ decoding_table = ( u'\u038e' # 0x77 -> GREEK CAPITAL LETTER UPSILON WITH TONOS u'\u038f' # 0x78 -> GREEK CAPITAL LETTER OMEGA WITH TONOS u'`' # 0x79 -> GRAVE ACCENT - u':' # 0x7a -> COLON - u'#' # 0x7b -> NUMBER SIGN - u'@' # 0x7c -> COMMERCIAL AT - u"'" # 0x7d -> APOSTROPHE - u'=' # 0x7e -> EQUALS SIGN - u'"' # 0x7f -> QUOTATION MARK + u':' # 0x7A -> COLON + u'#' # 0x7B -> NUMBER SIGN + u'@' # 0x7C -> COMMERCIAL AT + u"'" # 0x7D -> APOSTROPHE + u'=' # 0x7E -> EQUALS SIGN + u'"' # 0x7F -> QUOTATION MARK u'\u0385' # 0x80 -> GREEK DIALYTIKA TONOS u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B @@ -170,12 +170,12 @@ decoding_table = ( u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I - u'\u03b1' # 0x8a -> GREEK SMALL LETTER ALPHA - u'\u03b2' # 0x8b -> GREEK SMALL LETTER BETA - u'\u03b3' # 0x8c -> GREEK SMALL LETTER GAMMA - u'\u03b4' # 0x8d -> GREEK SMALL LETTER DELTA - u'\u03b5' # 0x8e -> GREEK SMALL LETTER EPSILON - u'\u03b6' # 0x8f -> GREEK SMALL LETTER ZETA + u'\u03b1' # 0x8A -> GREEK SMALL LETTER ALPHA + u'\u03b2' # 0x8B -> GREEK SMALL LETTER BETA + u'\u03b3' # 0x8C -> GREEK SMALL LETTER GAMMA + u'\u03b4' # 0x8D -> GREEK SMALL LETTER DELTA + u'\u03b5' # 0x8E -> GREEK SMALL LETTER EPSILON + u'\u03b6' # 0x8F -> GREEK SMALL LETTER ZETA u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K @@ -186,108 +186,108 @@ decoding_table = ( u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R - u'\u03b7' # 0x9a -> GREEK SMALL LETTER ETA - u'\u03b8' # 0x9b -> GREEK SMALL LETTER THETA - u'\u03b9' # 0x9c -> GREEK SMALL LETTER IOTA - u'\u03ba' # 0x9d -> GREEK SMALL LETTER KAPPA - u'\u03bb' # 0x9e -> GREEK SMALL LETTER LAMDA - u'\u03bc' # 0x9f -> GREEK SMALL LETTER MU - u'\xb4' # 0xa0 -> ACUTE ACCENT - u'~' # 0xa1 -> TILDE - u's' # 0xa2 -> LATIN SMALL LETTER S - u't' # 0xa3 -> LATIN SMALL LETTER T - u'u' # 0xa4 -> LATIN SMALL LETTER U - u'v' # 0xa5 -> LATIN SMALL LETTER V - u'w' # 0xa6 -> LATIN SMALL LETTER W - u'x' # 0xa7 -> LATIN SMALL LETTER X - u'y' # 0xa8 -> LATIN SMALL LETTER Y - u'z' # 0xa9 -> LATIN SMALL LETTER Z - u'\u03bd' # 0xaa -> GREEK SMALL LETTER NU - u'\u03be' # 0xab -> GREEK SMALL LETTER XI - u'\u03bf' # 0xac -> GREEK SMALL LETTER OMICRON - u'\u03c0' # 0xad -> GREEK SMALL LETTER PI - u'\u03c1' # 0xae -> GREEK SMALL LETTER RHO - u'\u03c3' # 0xaf -> GREEK SMALL LETTER SIGMA - u'\xa3' # 0xb0 -> POUND SIGN - u'\u03ac' # 0xb1 -> GREEK SMALL LETTER ALPHA WITH TONOS - u'\u03ad' # 0xb2 -> GREEK SMALL LETTER EPSILON WITH TONOS - u'\u03ae' # 0xb3 -> GREEK SMALL LETTER ETA WITH TONOS - u'\u03ca' # 0xb4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA - u'\u03af' # 0xb5 -> GREEK SMALL LETTER IOTA WITH TONOS - u'\u03cc' # 0xb6 -> GREEK SMALL LETTER OMICRON WITH TONOS - u'\u03cd' # 0xb7 -> GREEK SMALL LETTER UPSILON WITH TONOS - u'\u03cb' # 0xb8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA - u'\u03ce' # 0xb9 -> GREEK SMALL LETTER OMEGA WITH TONOS - u'\u03c2' # 0xba -> GREEK SMALL LETTER FINAL SIGMA - u'\u03c4' # 0xbb -> GREEK SMALL LETTER TAU - u'\u03c5' # 0xbc -> GREEK SMALL LETTER UPSILON - u'\u03c6' # 0xbd -> GREEK SMALL LETTER PHI - u'\u03c7' # 0xbe -> GREEK SMALL LETTER CHI - u'\u03c8' # 0xbf -> GREEK SMALL LETTER PSI - u'{' # 0xc0 -> LEFT CURLY BRACKET - u'A' # 0xc1 -> LATIN CAPITAL LETTER A - u'B' # 0xc2 -> LATIN CAPITAL LETTER B - u'C' # 0xc3 -> LATIN CAPITAL LETTER C - u'D' # 0xc4 -> LATIN CAPITAL LETTER D - u'E' # 0xc5 -> LATIN CAPITAL LETTER E - u'F' # 0xc6 -> LATIN CAPITAL LETTER F - u'G' # 0xc7 -> LATIN CAPITAL LETTER G - u'H' # 0xc8 -> LATIN CAPITAL LETTER H - u'I' # 0xc9 -> LATIN CAPITAL LETTER I - u'\xad' # 0xca -> SOFT HYPHEN - u'\u03c9' # 0xcb -> GREEK SMALL LETTER OMEGA - u'\u0390' # 0xcc -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS - u'\u03b0' # 0xcd -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - u'\u2018' # 0xce -> LEFT SINGLE QUOTATION MARK - u'\u2015' # 0xcf -> HORIZONTAL BAR - u'}' # 0xd0 -> RIGHT CURLY BRACKET - u'J' # 0xd1 -> LATIN CAPITAL LETTER J - u'K' # 0xd2 -> LATIN CAPITAL LETTER K - u'L' # 0xd3 -> LATIN CAPITAL LETTER L - u'M' # 0xd4 -> LATIN CAPITAL LETTER M - u'N' # 0xd5 -> LATIN CAPITAL LETTER N - u'O' # 0xd6 -> LATIN CAPITAL LETTER O - u'P' # 0xd7 -> LATIN CAPITAL LETTER P - u'Q' # 0xd8 -> LATIN CAPITAL LETTER Q - u'R' # 0xd9 -> LATIN CAPITAL LETTER R - u'\xb1' # 0xda -> PLUS-MINUS SIGN - u'\xbd' # 0xdb -> VULGAR FRACTION ONE HALF - u'\x1a' # 0xdc -> SUBSTITUTE - u'\u0387' # 0xdd -> GREEK ANO TELEIA - u'\u2019' # 0xde -> RIGHT SINGLE QUOTATION MARK - u'\xa6' # 0xdf -> BROKEN BAR - u'\\' # 0xe0 -> REVERSE SOLIDUS - u'\x1a' # 0xe1 -> SUBSTITUTE - u'S' # 0xe2 -> LATIN CAPITAL LETTER S - u'T' # 0xe3 -> LATIN CAPITAL LETTER T - u'U' # 0xe4 -> LATIN CAPITAL LETTER U - u'V' # 0xe5 -> LATIN CAPITAL LETTER V - u'W' # 0xe6 -> LATIN CAPITAL LETTER W - u'X' # 0xe7 -> LATIN CAPITAL LETTER X - u'Y' # 0xe8 -> LATIN CAPITAL LETTER Y - u'Z' # 0xe9 -> LATIN CAPITAL LETTER Z - u'\xb2' # 0xea -> SUPERSCRIPT TWO - u'\xa7' # 0xeb -> SECTION SIGN - u'\x1a' # 0xec -> SUBSTITUTE - u'\x1a' # 0xed -> SUBSTITUTE - u'\xab' # 0xee -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xef -> NOT SIGN - u'0' # 0xf0 -> DIGIT ZERO - u'1' # 0xf1 -> DIGIT ONE - u'2' # 0xf2 -> DIGIT TWO - u'3' # 0xf3 -> DIGIT THREE - u'4' # 0xf4 -> DIGIT FOUR - u'5' # 0xf5 -> DIGIT FIVE - u'6' # 0xf6 -> DIGIT SIX - u'7' # 0xf7 -> DIGIT SEVEN - u'8' # 0xf8 -> DIGIT EIGHT - u'9' # 0xf9 -> DIGIT NINE - u'\xb3' # 0xfa -> SUPERSCRIPT THREE - u'\xa9' # 0xfb -> COPYRIGHT SIGN - u'\x1a' # 0xfc -> SUBSTITUTE - u'\x1a' # 0xfd -> SUBSTITUTE - u'\xbb' # 0xfe -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\x9f' # 0xff -> CONTROL + u'\u03b7' # 0x9A -> GREEK SMALL LETTER ETA + u'\u03b8' # 0x9B -> GREEK SMALL LETTER THETA + u'\u03b9' # 0x9C -> GREEK SMALL LETTER IOTA + u'\u03ba' # 0x9D -> GREEK SMALL LETTER KAPPA + u'\u03bb' # 0x9E -> GREEK SMALL LETTER LAMDA + u'\u03bc' # 0x9F -> GREEK SMALL LETTER MU + u'\xb4' # 0xA0 -> ACUTE ACCENT + u'~' # 0xA1 -> TILDE + u's' # 0xA2 -> LATIN SMALL LETTER S + u't' # 0xA3 -> LATIN SMALL LETTER T + u'u' # 0xA4 -> LATIN SMALL LETTER U + u'v' # 0xA5 -> LATIN SMALL LETTER V + u'w' # 0xA6 -> LATIN SMALL LETTER W + u'x' # 0xA7 -> LATIN SMALL LETTER X + u'y' # 0xA8 -> LATIN SMALL LETTER Y + u'z' # 0xA9 -> LATIN SMALL LETTER Z + u'\u03bd' # 0xAA -> GREEK SMALL LETTER NU + u'\u03be' # 0xAB -> GREEK SMALL LETTER XI + u'\u03bf' # 0xAC -> GREEK SMALL LETTER OMICRON + u'\u03c0' # 0xAD -> GREEK SMALL LETTER PI + u'\u03c1' # 0xAE -> GREEK SMALL LETTER RHO + u'\u03c3' # 0xAF -> GREEK SMALL LETTER SIGMA + u'\xa3' # 0xB0 -> POUND SIGN + u'\u03ac' # 0xB1 -> GREEK SMALL LETTER ALPHA WITH TONOS + u'\u03ad' # 0xB2 -> GREEK SMALL LETTER EPSILON WITH TONOS + u'\u03ae' # 0xB3 -> GREEK SMALL LETTER ETA WITH TONOS + u'\u03ca' # 0xB4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + u'\u03af' # 0xB5 -> GREEK SMALL LETTER IOTA WITH TONOS + u'\u03cc' # 0xB6 -> GREEK SMALL LETTER OMICRON WITH TONOS + u'\u03cd' # 0xB7 -> GREEK SMALL LETTER UPSILON WITH TONOS + u'\u03cb' # 0xB8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + u'\u03ce' # 0xB9 -> GREEK SMALL LETTER OMEGA WITH TONOS + u'\u03c2' # 0xBA -> GREEK SMALL LETTER FINAL SIGMA + u'\u03c4' # 0xBB -> GREEK SMALL LETTER TAU + u'\u03c5' # 0xBC -> GREEK SMALL LETTER UPSILON + u'\u03c6' # 0xBD -> GREEK SMALL LETTER PHI + u'\u03c7' # 0xBE -> GREEK SMALL LETTER CHI + u'\u03c8' # 0xBF -> GREEK SMALL LETTER PSI + u'{' # 0xC0 -> LEFT CURLY BRACKET + u'A' # 0xC1 -> LATIN CAPITAL LETTER A + u'B' # 0xC2 -> LATIN CAPITAL LETTER B + u'C' # 0xC3 -> LATIN CAPITAL LETTER C + u'D' # 0xC4 -> LATIN CAPITAL LETTER D + u'E' # 0xC5 -> LATIN CAPITAL LETTER E + u'F' # 0xC6 -> LATIN CAPITAL LETTER F + u'G' # 0xC7 -> LATIN CAPITAL LETTER G + u'H' # 0xC8 -> LATIN CAPITAL LETTER H + u'I' # 0xC9 -> LATIN CAPITAL LETTER I + u'\xad' # 0xCA -> SOFT HYPHEN + u'\u03c9' # 0xCB -> GREEK SMALL LETTER OMEGA + u'\u0390' # 0xCC -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + u'\u03b0' # 0xCD -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + u'\u2018' # 0xCE -> LEFT SINGLE QUOTATION MARK + u'\u2015' # 0xCF -> HORIZONTAL BAR + u'}' # 0xD0 -> RIGHT CURLY BRACKET + u'J' # 0xD1 -> LATIN CAPITAL LETTER J + u'K' # 0xD2 -> LATIN CAPITAL LETTER K + u'L' # 0xD3 -> LATIN CAPITAL LETTER L + u'M' # 0xD4 -> LATIN CAPITAL LETTER M + u'N' # 0xD5 -> LATIN CAPITAL LETTER N + u'O' # 0xD6 -> LATIN CAPITAL LETTER O + u'P' # 0xD7 -> LATIN CAPITAL LETTER P + u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + u'R' # 0xD9 -> LATIN CAPITAL LETTER R + u'\xb1' # 0xDA -> PLUS-MINUS SIGN + u'\xbd' # 0xDB -> VULGAR FRACTION ONE HALF + u'\x1a' # 0xDC -> SUBSTITUTE + u'\u0387' # 0xDD -> GREEK ANO TELEIA + u'\u2019' # 0xDE -> RIGHT SINGLE QUOTATION MARK + u'\xa6' # 0xDF -> BROKEN BAR + u'\\' # 0xE0 -> REVERSE SOLIDUS + u'\x1a' # 0xE1 -> SUBSTITUTE + u'S' # 0xE2 -> LATIN CAPITAL LETTER S + u'T' # 0xE3 -> LATIN CAPITAL LETTER T + u'U' # 0xE4 -> LATIN CAPITAL LETTER U + u'V' # 0xE5 -> LATIN CAPITAL LETTER V + u'W' # 0xE6 -> LATIN CAPITAL LETTER W + u'X' # 0xE7 -> LATIN CAPITAL LETTER X + u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + u'\xb2' # 0xEA -> SUPERSCRIPT TWO + u'\xa7' # 0xEB -> SECTION SIGN + u'\x1a' # 0xEC -> SUBSTITUTE + u'\x1a' # 0xED -> SUBSTITUTE + u'\xab' # 0xEE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xEF -> NOT SIGN + u'0' # 0xF0 -> DIGIT ZERO + u'1' # 0xF1 -> DIGIT ONE + u'2' # 0xF2 -> DIGIT TWO + u'3' # 0xF3 -> DIGIT THREE + u'4' # 0xF4 -> DIGIT FOUR + u'5' # 0xF5 -> DIGIT FIVE + u'6' # 0xF6 -> DIGIT SIX + u'7' # 0xF7 -> DIGIT SEVEN + u'8' # 0xF8 -> DIGIT EIGHT + u'9' # 0xF9 -> DIGIT NINE + u'\xb3' # 0xFA -> SUPERSCRIPT THREE + u'\xa9' # 0xFB -> COPYRIGHT SIGN + u'\x1a' # 0xFC -> SUBSTITUTE + u'\x1a' # 0xFD -> SUBSTITUTE + u'\xbb' # 0xFE -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\x9f' # 0xFF -> CONTROL ) ### Encoding Map @@ -298,97 +298,97 @@ encoding_map = { 0x0002: 0x02, # START OF TEXT 0x0003: 0x03, # END OF TEXT 0x0004: 0x37, # END OF TRANSMISSION - 0x0005: 0x2d, # ENQUIRY - 0x0006: 0x2e, # ACKNOWLEDGE - 0x0007: 0x2f, # BELL + 0x0005: 0x2D, # ENQUIRY + 0x0006: 0x2E, # ACKNOWLEDGE + 0x0007: 0x2F, # BELL 0x0008: 0x16, # BACKSPACE 0x0009: 0x05, # HORIZONTAL TABULATION - 0x000a: 0x25, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x25, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO 0x0013: 0x13, # DEVICE CONTROL THREE - 0x0014: 0x3c, # DEVICE CONTROL FOUR - 0x0015: 0x3d, # NEGATIVE ACKNOWLEDGE + 0x0014: 0x3C, # DEVICE CONTROL FOUR + 0x0015: 0x3D, # NEGATIVE ACKNOWLEDGE 0x0016: 0x32, # SYNCHRONOUS IDLE 0x0017: 0x26, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: None, # SUBSTITUTE - 0x001b: 0x27, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: None, # SUBSTITUTE + 0x001B: 0x27, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x40, # SPACE - 0x0021: 0x4f, # EXCLAMATION MARK - 0x0022: 0x7f, # QUOTATION MARK - 0x0023: 0x7b, # NUMBER SIGN - 0x0024: 0x5b, # DOLLAR SIGN - 0x0025: 0x6c, # PERCENT SIGN + 0x0021: 0x4F, # EXCLAMATION MARK + 0x0022: 0x7F, # QUOTATION MARK + 0x0023: 0x7B, # NUMBER SIGN + 0x0024: 0x5B, # DOLLAR SIGN + 0x0025: 0x6C, # PERCENT SIGN 0x0026: 0x50, # AMPERSAND - 0x0027: 0x7d, # APOSTROPHE - 0x0028: 0x4d, # LEFT PARENTHESIS - 0x0029: 0x5d, # RIGHT PARENTHESIS - 0x002a: 0x5c, # ASTERISK - 0x002b: 0x4e, # PLUS SIGN - 0x002c: 0x6b, # COMMA - 0x002d: 0x60, # HYPHEN-MINUS - 0x002e: 0x4b, # FULL STOP - 0x002f: 0x61, # SOLIDUS - 0x0030: 0xf0, # DIGIT ZERO - 0x0031: 0xf1, # DIGIT ONE - 0x0032: 0xf2, # DIGIT TWO - 0x0033: 0xf3, # DIGIT THREE - 0x0034: 0xf4, # DIGIT FOUR - 0x0035: 0xf5, # DIGIT FIVE - 0x0036: 0xf6, # DIGIT SIX - 0x0037: 0xf7, # DIGIT SEVEN - 0x0038: 0xf8, # DIGIT EIGHT - 0x0039: 0xf9, # DIGIT NINE - 0x003a: 0x7a, # COLON - 0x003b: 0x5e, # SEMICOLON - 0x003c: 0x4c, # LESS-THAN SIGN - 0x003d: 0x7e, # EQUALS SIGN - 0x003e: 0x6e, # GREATER-THAN SIGN - 0x003f: 0x6f, # QUESTION MARK - 0x0040: 0x7c, # COMMERCIAL AT - 0x0041: 0xc1, # LATIN CAPITAL LETTER A - 0x0042: 0xc2, # LATIN CAPITAL LETTER B - 0x0043: 0xc3, # LATIN CAPITAL LETTER C - 0x0044: 0xc4, # LATIN CAPITAL LETTER D - 0x0045: 0xc5, # LATIN CAPITAL LETTER E - 0x0046: 0xc6, # LATIN CAPITAL LETTER F - 0x0047: 0xc7, # LATIN CAPITAL LETTER G - 0x0048: 0xc8, # LATIN CAPITAL LETTER H - 0x0049: 0xc9, # LATIN CAPITAL LETTER I - 0x004a: 0xd1, # LATIN CAPITAL LETTER J - 0x004b: 0xd2, # LATIN CAPITAL LETTER K - 0x004c: 0xd3, # LATIN CAPITAL LETTER L - 0x004d: 0xd4, # LATIN CAPITAL LETTER M - 0x004e: 0xd5, # LATIN CAPITAL LETTER N - 0x004f: 0xd6, # LATIN CAPITAL LETTER O - 0x0050: 0xd7, # LATIN CAPITAL LETTER P - 0x0051: 0xd8, # LATIN CAPITAL LETTER Q - 0x0052: 0xd9, # LATIN CAPITAL LETTER R - 0x0053: 0xe2, # LATIN CAPITAL LETTER S - 0x0054: 0xe3, # LATIN CAPITAL LETTER T - 0x0055: 0xe4, # LATIN CAPITAL LETTER U - 0x0056: 0xe5, # LATIN CAPITAL LETTER V - 0x0057: 0xe6, # LATIN CAPITAL LETTER W - 0x0058: 0xe7, # LATIN CAPITAL LETTER X - 0x0059: 0xe8, # LATIN CAPITAL LETTER Y - 0x005a: 0xe9, # LATIN CAPITAL LETTER Z - 0x005b: 0x4a, # LEFT SQUARE BRACKET - 0x005c: 0xe0, # REVERSE SOLIDUS - 0x005d: 0x5a, # RIGHT SQUARE BRACKET - 0x005e: 0x5f, # CIRCUMFLEX ACCENT - 0x005f: 0x6d, # LOW LINE + 0x0027: 0x7D, # APOSTROPHE + 0x0028: 0x4D, # LEFT PARENTHESIS + 0x0029: 0x5D, # RIGHT PARENTHESIS + 0x002A: 0x5C, # ASTERISK + 0x002B: 0x4E, # PLUS SIGN + 0x002C: 0x6B, # COMMA + 0x002D: 0x60, # HYPHEN-MINUS + 0x002E: 0x4B, # FULL STOP + 0x002F: 0x61, # SOLIDUS + 0x0030: 0xF0, # DIGIT ZERO + 0x0031: 0xF1, # DIGIT ONE + 0x0032: 0xF2, # DIGIT TWO + 0x0033: 0xF3, # DIGIT THREE + 0x0034: 0xF4, # DIGIT FOUR + 0x0035: 0xF5, # DIGIT FIVE + 0x0036: 0xF6, # DIGIT SIX + 0x0037: 0xF7, # DIGIT SEVEN + 0x0038: 0xF8, # DIGIT EIGHT + 0x0039: 0xF9, # DIGIT NINE + 0x003A: 0x7A, # COLON + 0x003B: 0x5E, # SEMICOLON + 0x003C: 0x4C, # LESS-THAN SIGN + 0x003D: 0x7E, # EQUALS SIGN + 0x003E: 0x6E, # GREATER-THAN SIGN + 0x003F: 0x6F, # QUESTION MARK + 0x0040: 0x7C, # COMMERCIAL AT + 0x0041: 0xC1, # LATIN CAPITAL LETTER A + 0x0042: 0xC2, # LATIN CAPITAL LETTER B + 0x0043: 0xC3, # LATIN CAPITAL LETTER C + 0x0044: 0xC4, # LATIN CAPITAL LETTER D + 0x0045: 0xC5, # LATIN CAPITAL LETTER E + 0x0046: 0xC6, # LATIN CAPITAL LETTER F + 0x0047: 0xC7, # LATIN CAPITAL LETTER G + 0x0048: 0xC8, # LATIN CAPITAL LETTER H + 0x0049: 0xC9, # LATIN CAPITAL LETTER I + 0x004A: 0xD1, # LATIN CAPITAL LETTER J + 0x004B: 0xD2, # LATIN CAPITAL LETTER K + 0x004C: 0xD3, # LATIN CAPITAL LETTER L + 0x004D: 0xD4, # LATIN CAPITAL LETTER M + 0x004E: 0xD5, # LATIN CAPITAL LETTER N + 0x004F: 0xD6, # LATIN CAPITAL LETTER O + 0x0050: 0xD7, # LATIN CAPITAL LETTER P + 0x0051: 0xD8, # LATIN CAPITAL LETTER Q + 0x0052: 0xD9, # LATIN CAPITAL LETTER R + 0x0053: 0xE2, # LATIN CAPITAL LETTER S + 0x0054: 0xE3, # LATIN CAPITAL LETTER T + 0x0055: 0xE4, # LATIN CAPITAL LETTER U + 0x0056: 0xE5, # LATIN CAPITAL LETTER V + 0x0057: 0xE6, # LATIN CAPITAL LETTER W + 0x0058: 0xE7, # LATIN CAPITAL LETTER X + 0x0059: 0xE8, # LATIN CAPITAL LETTER Y + 0x005A: 0xE9, # LATIN CAPITAL LETTER Z + 0x005B: 0x4A, # LEFT SQUARE BRACKET + 0x005C: 0xE0, # REVERSE SOLIDUS + 0x005D: 0x5A, # RIGHT SQUARE BRACKET + 0x005E: 0x5F, # CIRCUMFLEX ACCENT + 0x005F: 0x6D, # LOW LINE 0x0060: 0x79, # GRAVE ACCENT 0x0061: 0x81, # LATIN SMALL LETTER A 0x0062: 0x82, # LATIN SMALL LETTER B @@ -399,28 +399,28 @@ encoding_map = { 0x0067: 0x87, # LATIN SMALL LETTER G 0x0068: 0x88, # LATIN SMALL LETTER H 0x0069: 0x89, # LATIN SMALL LETTER I - 0x006a: 0x91, # LATIN SMALL LETTER J - 0x006b: 0x92, # LATIN SMALL LETTER K - 0x006c: 0x93, # LATIN SMALL LETTER L - 0x006d: 0x94, # LATIN SMALL LETTER M - 0x006e: 0x95, # LATIN SMALL LETTER N - 0x006f: 0x96, # LATIN SMALL LETTER O + 0x006A: 0x91, # LATIN SMALL LETTER J + 0x006B: 0x92, # LATIN SMALL LETTER K + 0x006C: 0x93, # LATIN SMALL LETTER L + 0x006D: 0x94, # LATIN SMALL LETTER M + 0x006E: 0x95, # LATIN SMALL LETTER N + 0x006F: 0x96, # LATIN SMALL LETTER O 0x0070: 0x97, # LATIN SMALL LETTER P 0x0071: 0x98, # LATIN SMALL LETTER Q 0x0072: 0x99, # LATIN SMALL LETTER R - 0x0073: 0xa2, # LATIN SMALL LETTER S - 0x0074: 0xa3, # LATIN SMALL LETTER T - 0x0075: 0xa4, # LATIN SMALL LETTER U - 0x0076: 0xa5, # LATIN SMALL LETTER V - 0x0077: 0xa6, # LATIN SMALL LETTER W - 0x0078: 0xa7, # LATIN SMALL LETTER X - 0x0079: 0xa8, # LATIN SMALL LETTER Y - 0x007a: 0xa9, # LATIN SMALL LETTER Z - 0x007b: 0xc0, # LEFT CURLY BRACKET - 0x007c: 0x6a, # VERTICAL LINE - 0x007d: 0xd0, # RIGHT CURLY BRACKET - 0x007e: 0xa1, # TILDE - 0x007f: 0x07, # DELETE + 0x0073: 0xA2, # LATIN SMALL LETTER S + 0x0074: 0xA3, # LATIN SMALL LETTER T + 0x0075: 0xA4, # LATIN SMALL LETTER U + 0x0076: 0xA5, # LATIN SMALL LETTER V + 0x0077: 0xA6, # LATIN SMALL LETTER W + 0x0078: 0xA7, # LATIN SMALL LETTER X + 0x0079: 0xA8, # LATIN SMALL LETTER Y + 0x007A: 0xA9, # LATIN SMALL LETTER Z + 0x007B: 0xC0, # LEFT CURLY BRACKET + 0x007C: 0x6A, # VERTICAL LINE + 0x007D: 0xD0, # RIGHT CURLY BRACKET + 0x007E: 0xA1, # TILDE + 0x007F: 0x07, # DELETE 0x0080: 0x20, # CONTROL 0x0081: 0x21, # CONTROL 0x0082: 0x22, # CONTROL @@ -431,15 +431,15 @@ encoding_map = { 0x0087: 0x17, # CONTROL 0x0088: 0x28, # CONTROL 0x0089: 0x29, # CONTROL - 0x008a: 0x2a, # CONTROL - 0x008b: 0x2b, # CONTROL - 0x008c: 0x2c, # CONTROL - 0x008d: 0x09, # CONTROL - 0x008e: 0x0a, # CONTROL - 0x008f: 0x1b, # CONTROL + 0x008A: 0x2A, # CONTROL + 0x008B: 0x2B, # CONTROL + 0x008C: 0x2C, # CONTROL + 0x008D: 0x09, # CONTROL + 0x008E: 0x0A, # CONTROL + 0x008F: 0x1B, # CONTROL 0x0090: 0x30, # CONTROL 0x0091: 0x31, # CONTROL - 0x0092: 0x1a, # CONTROL + 0x0092: 0x1A, # CONTROL 0x0093: 0x33, # CONTROL 0x0094: 0x34, # CONTROL 0x0095: 0x35, # CONTROL @@ -447,38 +447,38 @@ encoding_map = { 0x0097: 0x08, # CONTROL 0x0098: 0x38, # CONTROL 0x0099: 0x39, # CONTROL - 0x009a: 0x3a, # CONTROL - 0x009b: 0x3b, # CONTROL - 0x009c: 0x04, # CONTROL - 0x009d: 0x14, # CONTROL - 0x009e: 0x3e, # CONTROL - 0x009f: 0xff, # CONTROL - 0x00a0: 0x74, # NO-BREAK SPACE - 0x00a3: 0xb0, # POUND SIGN - 0x00a6: 0xdf, # BROKEN BAR - 0x00a7: 0xeb, # SECTION SIGN - 0x00a8: 0x70, # DIAERESIS - 0x00a9: 0xfb, # COPYRIGHT SIGN - 0x00ab: 0xee, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xef, # NOT SIGN - 0x00ad: 0xca, # SOFT HYPHEN - 0x00b0: 0x90, # DEGREE SIGN - 0x00b1: 0xda, # PLUS-MINUS SIGN - 0x00b2: 0xea, # SUPERSCRIPT TWO - 0x00b3: 0xfa, # SUPERSCRIPT THREE - 0x00b4: 0xa0, # ACUTE ACCENT - 0x00bb: 0xfe, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bd: 0xdb, # VULGAR FRACTION ONE HALF + 0x009A: 0x3A, # CONTROL + 0x009B: 0x3B, # CONTROL + 0x009C: 0x04, # CONTROL + 0x009D: 0x14, # CONTROL + 0x009E: 0x3E, # CONTROL + 0x009F: 0xFF, # CONTROL + 0x00A0: 0x74, # NO-BREAK SPACE + 0x00A3: 0xB0, # POUND SIGN + 0x00A6: 0xDF, # BROKEN BAR + 0x00A7: 0xEB, # SECTION SIGN + 0x00A8: 0x70, # DIAERESIS + 0x00A9: 0xFB, # COPYRIGHT SIGN + 0x00AB: 0xEE, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xEF, # NOT SIGN + 0x00AD: 0xCA, # SOFT HYPHEN + 0x00B0: 0x90, # DEGREE SIGN + 0x00B1: 0xDA, # PLUS-MINUS SIGN + 0x00B2: 0xEA, # SUPERSCRIPT TWO + 0x00B3: 0xFA, # SUPERSCRIPT THREE + 0x00B4: 0xA0, # ACUTE ACCENT + 0x00BB: 0xFE, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BD: 0xDB, # VULGAR FRACTION ONE HALF 0x0385: 0x80, # GREEK DIALYTIKA TONOS 0x0386: 0x71, # GREEK CAPITAL LETTER ALPHA WITH TONOS - 0x0387: 0xdd, # GREEK ANO TELEIA + 0x0387: 0xDD, # GREEK ANO TELEIA 0x0388: 0x72, # GREEK CAPITAL LETTER EPSILON WITH TONOS 0x0389: 0x73, # GREEK CAPITAL LETTER ETA WITH TONOS - 0x038a: 0x75, # GREEK CAPITAL LETTER IOTA WITH TONOS - 0x038c: 0x76, # GREEK CAPITAL LETTER OMICRON WITH TONOS - 0x038e: 0x77, # GREEK CAPITAL LETTER UPSILON WITH TONOS - 0x038f: 0x78, # GREEK CAPITAL LETTER OMEGA WITH TONOS - 0x0390: 0xcc, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + 0x038A: 0x75, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x038C: 0x76, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x038E: 0x77, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x038F: 0x78, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x0390: 0xCC, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS 0x0391: 0x41, # GREEK CAPITAL LETTER ALPHA 0x0392: 0x42, # GREEK CAPITAL LETTER BETA 0x0393: 0x43, # GREEK CAPITAL LETTER GAMMA @@ -488,59 +488,60 @@ encoding_map = { 0x0397: 0x47, # GREEK CAPITAL LETTER ETA 0x0398: 0x48, # GREEK CAPITAL LETTER THETA 0x0399: 0x49, # GREEK CAPITAL LETTER IOTA - 0x039a: 0x51, # GREEK CAPITAL LETTER KAPPA - 0x039b: 0x52, # GREEK CAPITAL LETTER LAMDA - 0x039c: 0x53, # GREEK CAPITAL LETTER MU - 0x039d: 0x54, # GREEK CAPITAL LETTER NU - 0x039e: 0x55, # GREEK CAPITAL LETTER XI - 0x039f: 0x56, # GREEK CAPITAL LETTER OMICRON - 0x03a0: 0x57, # GREEK CAPITAL LETTER PI - 0x03a1: 0x58, # GREEK CAPITAL LETTER RHO - 0x03a3: 0x59, # GREEK CAPITAL LETTER SIGMA - 0x03a4: 0x62, # GREEK CAPITAL LETTER TAU - 0x03a5: 0x63, # GREEK CAPITAL LETTER UPSILON - 0x03a6: 0x64, # GREEK CAPITAL LETTER PHI - 0x03a7: 0x65, # GREEK CAPITAL LETTER CHI - 0x03a8: 0x66, # GREEK CAPITAL LETTER PSI - 0x03a9: 0x67, # GREEK CAPITAL LETTER OMEGA - 0x03aa: 0x68, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - 0x03ab: 0x69, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - 0x03ac: 0xb1, # GREEK SMALL LETTER ALPHA WITH TONOS - 0x03ad: 0xb2, # GREEK SMALL LETTER EPSILON WITH TONOS - 0x03ae: 0xb3, # GREEK SMALL LETTER ETA WITH TONOS - 0x03af: 0xb5, # GREEK SMALL LETTER IOTA WITH TONOS - 0x03b0: 0xcd, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - 0x03b1: 0x8a, # GREEK SMALL LETTER ALPHA - 0x03b2: 0x8b, # GREEK SMALL LETTER BETA - 0x03b3: 0x8c, # GREEK SMALL LETTER GAMMA - 0x03b4: 0x8d, # GREEK SMALL LETTER DELTA - 0x03b5: 0x8e, # GREEK SMALL LETTER EPSILON - 0x03b6: 0x8f, # GREEK SMALL LETTER ZETA - 0x03b7: 0x9a, # GREEK SMALL LETTER ETA - 0x03b8: 0x9b, # GREEK SMALL LETTER THETA - 0x03b9: 0x9c, # GREEK SMALL LETTER IOTA - 0x03ba: 0x9d, # GREEK SMALL LETTER KAPPA - 0x03bb: 0x9e, # GREEK SMALL LETTER LAMDA - 0x03bc: 0x9f, # GREEK SMALL LETTER MU - 0x03bd: 0xaa, # GREEK SMALL LETTER NU - 0x03be: 0xab, # GREEK SMALL LETTER XI - 0x03bf: 0xac, # GREEK SMALL LETTER OMICRON - 0x03c0: 0xad, # GREEK SMALL LETTER PI - 0x03c1: 0xae, # GREEK SMALL LETTER RHO - 0x03c2: 0xba, # GREEK SMALL LETTER FINAL SIGMA - 0x03c3: 0xaf, # GREEK SMALL LETTER SIGMA - 0x03c4: 0xbb, # GREEK SMALL LETTER TAU - 0x03c5: 0xbc, # GREEK SMALL LETTER UPSILON - 0x03c6: 0xbd, # GREEK SMALL LETTER PHI - 0x03c7: 0xbe, # GREEK SMALL LETTER CHI - 0x03c8: 0xbf, # GREEK SMALL LETTER PSI - 0x03c9: 0xcb, # GREEK SMALL LETTER OMEGA - 0x03ca: 0xb4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA - 0x03cb: 0xb8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA - 0x03cc: 0xb6, # GREEK SMALL LETTER OMICRON WITH TONOS - 0x03cd: 0xb7, # GREEK SMALL LETTER UPSILON WITH TONOS - 0x03ce: 0xb9, # GREEK SMALL LETTER OMEGA WITH TONOS - 0x2015: 0xcf, # HORIZONTAL BAR - 0x2018: 0xce, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xde, # RIGHT SINGLE QUOTATION MARK -} \ No newline at end of file + 0x039A: 0x51, # GREEK CAPITAL LETTER KAPPA + 0x039B: 0x52, # GREEK CAPITAL LETTER LAMDA + 0x039C: 0x53, # GREEK CAPITAL LETTER MU + 0x039D: 0x54, # GREEK CAPITAL LETTER NU + 0x039E: 0x55, # GREEK CAPITAL LETTER XI + 0x039F: 0x56, # GREEK CAPITAL LETTER OMICRON + 0x03A0: 0x57, # GREEK CAPITAL LETTER PI + 0x03A1: 0x58, # GREEK CAPITAL LETTER RHO + 0x03A3: 0x59, # GREEK CAPITAL LETTER SIGMA + 0x03A4: 0x62, # GREEK CAPITAL LETTER TAU + 0x03A5: 0x63, # GREEK CAPITAL LETTER UPSILON + 0x03A6: 0x64, # GREEK CAPITAL LETTER PHI + 0x03A7: 0x65, # GREEK CAPITAL LETTER CHI + 0x03A8: 0x66, # GREEK CAPITAL LETTER PSI + 0x03A9: 0x67, # GREEK CAPITAL LETTER OMEGA + 0x03AA: 0x68, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x03AB: 0x69, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x03AC: 0xB1, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x03AD: 0xB2, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x03AE: 0xB3, # GREEK SMALL LETTER ETA WITH TONOS + 0x03AF: 0xB5, # GREEK SMALL LETTER IOTA WITH TONOS + 0x03B0: 0xCD, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + 0x03B1: 0x8A, # GREEK SMALL LETTER ALPHA + 0x03B2: 0x8B, # GREEK SMALL LETTER BETA + 0x03B3: 0x8C, # GREEK SMALL LETTER GAMMA + 0x03B4: 0x8D, # GREEK SMALL LETTER DELTA + 0x03B5: 0x8E, # GREEK SMALL LETTER EPSILON + 0x03B6: 0x8F, # GREEK SMALL LETTER ZETA + 0x03B7: 0x9A, # GREEK SMALL LETTER ETA + 0x03B8: 0x9B, # GREEK SMALL LETTER THETA + 0x03B9: 0x9C, # GREEK SMALL LETTER IOTA + 0x03BA: 0x9D, # GREEK SMALL LETTER KAPPA + 0x03BB: 0x9E, # GREEK SMALL LETTER LAMDA + 0x03BC: 0x9F, # GREEK SMALL LETTER MU + 0x03BD: 0xAA, # GREEK SMALL LETTER NU + 0x03BE: 0xAB, # GREEK SMALL LETTER XI + 0x03BF: 0xAC, # GREEK SMALL LETTER OMICRON + 0x03C0: 0xAD, # GREEK SMALL LETTER PI + 0x03C1: 0xAE, # GREEK SMALL LETTER RHO + 0x03C2: 0xBA, # GREEK SMALL LETTER FINAL SIGMA + 0x03C3: 0xAF, # GREEK SMALL LETTER SIGMA + 0x03C4: 0xBB, # GREEK SMALL LETTER TAU + 0x03C5: 0xBC, # GREEK SMALL LETTER UPSILON + 0x03C6: 0xBD, # GREEK SMALL LETTER PHI + 0x03C7: 0xBE, # GREEK SMALL LETTER CHI + 0x03C8: 0xBF, # GREEK SMALL LETTER PSI + 0x03C9: 0xCB, # GREEK SMALL LETTER OMEGA + 0x03CA: 0xB4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x03CB: 0xB8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x03CC: 0xB6, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x03CD: 0xB7, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x03CE: 0xB9, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x2015: 0xCF, # HORIZONTAL BAR + 0x2018: 0xCE, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xDE, # RIGHT SINGLE QUOTATION MARK +} + diff --git a/Lib/encodings/iso8859_1.py b/Lib/encodings/iso8859_1.py index 04836d4..ecd3730 100644 --- a/Lib/encodings/iso8859_1.py +++ b/Lib/encodings/iso8859_1.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\xa1' # 0xa1 -> INVERTED EXCLAMATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xaa' # 0xaa -> FEMININE ORDINAL INDICATOR - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xba' # 0xba -> MASCULINE ORDINAL INDICATOR - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xbf' # 0xbf -> INVERTED QUESTION MARK - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xd0' # 0xd0 -> LATIN CAPITAL LETTER ETH (Icelandic) - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xdd' # 0xdd -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xde' # 0xde -> LATIN CAPITAL LETTER THORN (Icelandic) - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S (German) - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\xf0' # 0xf0 -> LATIN SMALL LETTER ETH (Icelandic) - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xfd' # 0xfd -> LATIN SMALL LETTER Y WITH ACUTE - u'\xfe' # 0xfe -> LATIN SMALL LETTER THORN (Icelandic) - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xbf' # 0xBF -> INVERTED QUESTION MARK + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic) + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic) + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic) + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic) + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a1: 0xa1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xaa, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00ba: 0xba, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xbf, # INVERTED QUESTION MARK - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xd0, # LATIN CAPITAL LETTER ETH (Icelandic) - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xdd, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xde, # LATIN CAPITAL LETTER THORN (Icelandic) - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S (German) - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0xf0, # LATIN SMALL LETTER ETH (Icelandic) - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xfd, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0xfe, # LATIN SMALL LETTER THORN (Icelandic) - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xBF, # INVERTED QUESTION MARK + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH (Icelandic) + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN (Icelandic) + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S (German) + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0xF0, # LATIN SMALL LETTER ETH (Icelandic) + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0xFE, # LATIN SMALL LETTER THORN (Icelandic) + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS +} + diff --git a/Lib/encodings/iso8859_10.py b/Lib/encodings/iso8859_10.py index 4c5aae2..86a3cc8 100644 --- a/Lib/encodings/iso8859_10.py +++ b/Lib/encodings/iso8859_10.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0104' # 0xa1 -> LATIN CAPITAL LETTER A WITH OGONEK - u'\u0112' # 0xa2 -> LATIN CAPITAL LETTER E WITH MACRON - u'\u0122' # 0xa3 -> LATIN CAPITAL LETTER G WITH CEDILLA - u'\u012a' # 0xa4 -> LATIN CAPITAL LETTER I WITH MACRON - u'\u0128' # 0xa5 -> LATIN CAPITAL LETTER I WITH TILDE - u'\u0136' # 0xa6 -> LATIN CAPITAL LETTER K WITH CEDILLA - u'\xa7' # 0xa7 -> SECTION SIGN - u'\u013b' # 0xa8 -> LATIN CAPITAL LETTER L WITH CEDILLA - u'\u0110' # 0xa9 -> LATIN CAPITAL LETTER D WITH STROKE - u'\u0160' # 0xaa -> LATIN CAPITAL LETTER S WITH CARON - u'\u0166' # 0xab -> LATIN CAPITAL LETTER T WITH STROKE - u'\u017d' # 0xac -> LATIN CAPITAL LETTER Z WITH CARON - u'\xad' # 0xad -> SOFT HYPHEN - u'\u016a' # 0xae -> LATIN CAPITAL LETTER U WITH MACRON - u'\u014a' # 0xaf -> LATIN CAPITAL LETTER ENG - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\u0105' # 0xb1 -> LATIN SMALL LETTER A WITH OGONEK - u'\u0113' # 0xb2 -> LATIN SMALL LETTER E WITH MACRON - u'\u0123' # 0xb3 -> LATIN SMALL LETTER G WITH CEDILLA - u'\u012b' # 0xb4 -> LATIN SMALL LETTER I WITH MACRON - u'\u0129' # 0xb5 -> LATIN SMALL LETTER I WITH TILDE - u'\u0137' # 0xb6 -> LATIN SMALL LETTER K WITH CEDILLA - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\u013c' # 0xb8 -> LATIN SMALL LETTER L WITH CEDILLA - u'\u0111' # 0xb9 -> LATIN SMALL LETTER D WITH STROKE - u'\u0161' # 0xba -> LATIN SMALL LETTER S WITH CARON - u'\u0167' # 0xbb -> LATIN SMALL LETTER T WITH STROKE - u'\u017e' # 0xbc -> LATIN SMALL LETTER Z WITH CARON - u'\u2015' # 0xbd -> HORIZONTAL BAR - u'\u016b' # 0xbe -> LATIN SMALL LETTER U WITH MACRON - u'\u014b' # 0xbf -> LATIN SMALL LETTER ENG - u'\u0100' # 0xc0 -> LATIN CAPITAL LETTER A WITH MACRON - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\u012e' # 0xc7 -> LATIN CAPITAL LETTER I WITH OGONEK - u'\u010c' # 0xc8 -> LATIN CAPITAL LETTER C WITH CARON - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\u0118' # 0xca -> LATIN CAPITAL LETTER E WITH OGONEK - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\u0116' # 0xcc -> LATIN CAPITAL LETTER E WITH DOT ABOVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xd0' # 0xd0 -> LATIN CAPITAL LETTER ETH (Icelandic) - u'\u0145' # 0xd1 -> LATIN CAPITAL LETTER N WITH CEDILLA - u'\u014c' # 0xd2 -> LATIN CAPITAL LETTER O WITH MACRON - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\u0168' # 0xd7 -> LATIN CAPITAL LETTER U WITH TILDE - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\u0172' # 0xd9 -> LATIN CAPITAL LETTER U WITH OGONEK - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xdd' # 0xdd -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xde' # 0xde -> LATIN CAPITAL LETTER THORN (Icelandic) - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S (German) - u'\u0101' # 0xe0 -> LATIN SMALL LETTER A WITH MACRON - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\u012f' # 0xe7 -> LATIN SMALL LETTER I WITH OGONEK - u'\u010d' # 0xe8 -> LATIN SMALL LETTER C WITH CARON - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\u0119' # 0xea -> LATIN SMALL LETTER E WITH OGONEK - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\u0117' # 0xec -> LATIN SMALL LETTER E WITH DOT ABOVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\xf0' # 0xf0 -> LATIN SMALL LETTER ETH (Icelandic) - u'\u0146' # 0xf1 -> LATIN SMALL LETTER N WITH CEDILLA - u'\u014d' # 0xf2 -> LATIN SMALL LETTER O WITH MACRON - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\u0169' # 0xf7 -> LATIN SMALL LETTER U WITH TILDE - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\u0173' # 0xf9 -> LATIN SMALL LETTER U WITH OGONEK - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xfd' # 0xfd -> LATIN SMALL LETTER Y WITH ACUTE - u'\xfe' # 0xfe -> LATIN SMALL LETTER THORN (Icelandic) - u'\u0138' # 0xff -> LATIN SMALL LETTER KRA + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + u'\u0112' # 0xA2 -> LATIN CAPITAL LETTER E WITH MACRON + u'\u0122' # 0xA3 -> LATIN CAPITAL LETTER G WITH CEDILLA + u'\u012a' # 0xA4 -> LATIN CAPITAL LETTER I WITH MACRON + u'\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE + u'\u0136' # 0xA6 -> LATIN CAPITAL LETTER K WITH CEDILLA + u'\xa7' # 0xA7 -> SECTION SIGN + u'\u013b' # 0xA8 -> LATIN CAPITAL LETTER L WITH CEDILLA + u'\u0110' # 0xA9 -> LATIN CAPITAL LETTER D WITH STROKE + u'\u0160' # 0xAA -> LATIN CAPITAL LETTER S WITH CARON + u'\u0166' # 0xAB -> LATIN CAPITAL LETTER T WITH STROKE + u'\u017d' # 0xAC -> LATIN CAPITAL LETTER Z WITH CARON + u'\xad' # 0xAD -> SOFT HYPHEN + u'\u016a' # 0xAE -> LATIN CAPITAL LETTER U WITH MACRON + u'\u014a' # 0xAF -> LATIN CAPITAL LETTER ENG + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK + u'\u0113' # 0xB2 -> LATIN SMALL LETTER E WITH MACRON + u'\u0123' # 0xB3 -> LATIN SMALL LETTER G WITH CEDILLA + u'\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON + u'\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE + u'\u0137' # 0xB6 -> LATIN SMALL LETTER K WITH CEDILLA + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\u013c' # 0xB8 -> LATIN SMALL LETTER L WITH CEDILLA + u'\u0111' # 0xB9 -> LATIN SMALL LETTER D WITH STROKE + u'\u0161' # 0xBA -> LATIN SMALL LETTER S WITH CARON + u'\u0167' # 0xBB -> LATIN SMALL LETTER T WITH STROKE + u'\u017e' # 0xBC -> LATIN SMALL LETTER Z WITH CARON + u'\u2015' # 0xBD -> HORIZONTAL BAR + u'\u016b' # 0xBE -> LATIN SMALL LETTER U WITH MACRON + u'\u014b' # 0xBF -> LATIN SMALL LETTER ENG + u'\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK + u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic) + u'\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA + u'\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\u0168' # 0xD7 -> LATIN CAPITAL LETTER U WITH TILDE + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic) + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) + u'\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK + u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic) + u'\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA + u'\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\u0169' # 0xF7 -> LATIN SMALL LETTER U WITH TILDE + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic) + u'\u0138' # 0xFF -> LATIN SMALL LETTER KRA ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a7: 0xa7, # SECTION SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xd0, # LATIN CAPITAL LETTER ETH (Icelandic) - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xdd, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xde, # LATIN CAPITAL LETTER THORN (Icelandic) - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S (German) - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0xf0, # LATIN SMALL LETTER ETH (Icelandic) - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xfd, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0xfe, # LATIN SMALL LETTER THORN (Icelandic) - 0x0100: 0xc0, # LATIN CAPITAL LETTER A WITH MACRON - 0x0101: 0xe0, # LATIN SMALL LETTER A WITH MACRON - 0x0104: 0xa1, # LATIN CAPITAL LETTER A WITH OGONEK - 0x0105: 0xb1, # LATIN SMALL LETTER A WITH OGONEK - 0x010c: 0xc8, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xe8, # LATIN SMALL LETTER C WITH CARON - 0x0110: 0xa9, # LATIN CAPITAL LETTER D WITH STROKE - 0x0111: 0xb9, # LATIN SMALL LETTER D WITH STROKE - 0x0112: 0xa2, # LATIN CAPITAL LETTER E WITH MACRON - 0x0113: 0xb2, # LATIN SMALL LETTER E WITH MACRON - 0x0116: 0xcc, # LATIN CAPITAL LETTER E WITH DOT ABOVE - 0x0117: 0xec, # LATIN SMALL LETTER E WITH DOT ABOVE - 0x0118: 0xca, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xea, # LATIN SMALL LETTER E WITH OGONEK - 0x0122: 0xa3, # LATIN CAPITAL LETTER G WITH CEDILLA - 0x0123: 0xb3, # LATIN SMALL LETTER G WITH CEDILLA - 0x0128: 0xa5, # LATIN CAPITAL LETTER I WITH TILDE - 0x0129: 0xb5, # LATIN SMALL LETTER I WITH TILDE - 0x012a: 0xa4, # LATIN CAPITAL LETTER I WITH MACRON - 0x012b: 0xb4, # LATIN SMALL LETTER I WITH MACRON - 0x012e: 0xc7, # LATIN CAPITAL LETTER I WITH OGONEK - 0x012f: 0xe7, # LATIN SMALL LETTER I WITH OGONEK - 0x0136: 0xa6, # LATIN CAPITAL LETTER K WITH CEDILLA - 0x0137: 0xb6, # LATIN SMALL LETTER K WITH CEDILLA - 0x0138: 0xff, # LATIN SMALL LETTER KRA - 0x013b: 0xa8, # LATIN CAPITAL LETTER L WITH CEDILLA - 0x013c: 0xb8, # LATIN SMALL LETTER L WITH CEDILLA - 0x0145: 0xd1, # LATIN CAPITAL LETTER N WITH CEDILLA - 0x0146: 0xf1, # LATIN SMALL LETTER N WITH CEDILLA - 0x014a: 0xaf, # LATIN CAPITAL LETTER ENG - 0x014b: 0xbf, # LATIN SMALL LETTER ENG - 0x014c: 0xd2, # LATIN CAPITAL LETTER O WITH MACRON - 0x014d: 0xf2, # LATIN SMALL LETTER O WITH MACRON - 0x0160: 0xaa, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xba, # LATIN SMALL LETTER S WITH CARON - 0x0166: 0xab, # LATIN CAPITAL LETTER T WITH STROKE - 0x0167: 0xbb, # LATIN SMALL LETTER T WITH STROKE - 0x0168: 0xd7, # LATIN CAPITAL LETTER U WITH TILDE - 0x0169: 0xf7, # LATIN SMALL LETTER U WITH TILDE - 0x016a: 0xae, # LATIN CAPITAL LETTER U WITH MACRON - 0x016b: 0xbe, # LATIN SMALL LETTER U WITH MACRON - 0x0172: 0xd9, # LATIN CAPITAL LETTER U WITH OGONEK - 0x0173: 0xf9, # LATIN SMALL LETTER U WITH OGONEK - 0x017d: 0xac, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xbc, # LATIN SMALL LETTER Z WITH CARON - 0x2015: 0xbd, # HORIZONTAL BAR -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A7: 0xA7, # SECTION SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH (Icelandic) + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN (Icelandic) + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S (German) + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0xF0, # LATIN SMALL LETTER ETH (Icelandic) + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0xFE, # LATIN SMALL LETTER THORN (Icelandic) + 0x0100: 0xC0, # LATIN CAPITAL LETTER A WITH MACRON + 0x0101: 0xE0, # LATIN SMALL LETTER A WITH MACRON + 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0xB1, # LATIN SMALL LETTER A WITH OGONEK + 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON + 0x0110: 0xA9, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0xB9, # LATIN SMALL LETTER D WITH STROKE + 0x0112: 0xA2, # LATIN CAPITAL LETTER E WITH MACRON + 0x0113: 0xB2, # LATIN SMALL LETTER E WITH MACRON + 0x0116: 0xCC, # LATIN CAPITAL LETTER E WITH DOT ABOVE + 0x0117: 0xEC, # LATIN SMALL LETTER E WITH DOT ABOVE + 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK + 0x0122: 0xA3, # LATIN CAPITAL LETTER G WITH CEDILLA + 0x0123: 0xB3, # LATIN SMALL LETTER G WITH CEDILLA + 0x0128: 0xA5, # LATIN CAPITAL LETTER I WITH TILDE + 0x0129: 0xB5, # LATIN SMALL LETTER I WITH TILDE + 0x012A: 0xA4, # LATIN CAPITAL LETTER I WITH MACRON + 0x012B: 0xB4, # LATIN SMALL LETTER I WITH MACRON + 0x012E: 0xC7, # LATIN CAPITAL LETTER I WITH OGONEK + 0x012F: 0xE7, # LATIN SMALL LETTER I WITH OGONEK + 0x0136: 0xA6, # LATIN CAPITAL LETTER K WITH CEDILLA + 0x0137: 0xB6, # LATIN SMALL LETTER K WITH CEDILLA + 0x0138: 0xFF, # LATIN SMALL LETTER KRA + 0x013B: 0xA8, # LATIN CAPITAL LETTER L WITH CEDILLA + 0x013C: 0xB8, # LATIN SMALL LETTER L WITH CEDILLA + 0x0145: 0xD1, # LATIN CAPITAL LETTER N WITH CEDILLA + 0x0146: 0xF1, # LATIN SMALL LETTER N WITH CEDILLA + 0x014A: 0xAF, # LATIN CAPITAL LETTER ENG + 0x014B: 0xBF, # LATIN SMALL LETTER ENG + 0x014C: 0xD2, # LATIN CAPITAL LETTER O WITH MACRON + 0x014D: 0xF2, # LATIN SMALL LETTER O WITH MACRON + 0x0160: 0xAA, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xBA, # LATIN SMALL LETTER S WITH CARON + 0x0166: 0xAB, # LATIN CAPITAL LETTER T WITH STROKE + 0x0167: 0xBB, # LATIN SMALL LETTER T WITH STROKE + 0x0168: 0xD7, # LATIN CAPITAL LETTER U WITH TILDE + 0x0169: 0xF7, # LATIN SMALL LETTER U WITH TILDE + 0x016A: 0xAE, # LATIN CAPITAL LETTER U WITH MACRON + 0x016B: 0xBE, # LATIN SMALL LETTER U WITH MACRON + 0x0172: 0xD9, # LATIN CAPITAL LETTER U WITH OGONEK + 0x0173: 0xF9, # LATIN SMALL LETTER U WITH OGONEK + 0x017D: 0xAC, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xBC, # LATIN SMALL LETTER Z WITH CARON + 0x2015: 0xBD, # HORIZONTAL BAR +} + diff --git a/Lib/encodings/iso8859_11.py b/Lib/encodings/iso8859_11.py index 33e9bf2..69b3765 100644 --- a/Lib/encodings/iso8859_11.py +++ b/Lib/encodings/iso8859_11.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,104 +186,104 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0e01' # 0xa1 -> THAI CHARACTER KO KAI - u'\u0e02' # 0xa2 -> THAI CHARACTER KHO KHAI - u'\u0e03' # 0xa3 -> THAI CHARACTER KHO KHUAT - u'\u0e04' # 0xa4 -> THAI CHARACTER KHO KHWAI - u'\u0e05' # 0xa5 -> THAI CHARACTER KHO KHON - u'\u0e06' # 0xa6 -> THAI CHARACTER KHO RAKHANG - u'\u0e07' # 0xa7 -> THAI CHARACTER NGO NGU - u'\u0e08' # 0xa8 -> THAI CHARACTER CHO CHAN - u'\u0e09' # 0xa9 -> THAI CHARACTER CHO CHING - u'\u0e0a' # 0xaa -> THAI CHARACTER CHO CHANG - u'\u0e0b' # 0xab -> THAI CHARACTER SO SO - u'\u0e0c' # 0xac -> THAI CHARACTER CHO CHOE - u'\u0e0d' # 0xad -> THAI CHARACTER YO YING - u'\u0e0e' # 0xae -> THAI CHARACTER DO CHADA - u'\u0e0f' # 0xaf -> THAI CHARACTER TO PATAK - u'\u0e10' # 0xb0 -> THAI CHARACTER THO THAN - u'\u0e11' # 0xb1 -> THAI CHARACTER THO NANGMONTHO - u'\u0e12' # 0xb2 -> THAI CHARACTER THO PHUTHAO - u'\u0e13' # 0xb3 -> THAI CHARACTER NO NEN - u'\u0e14' # 0xb4 -> THAI CHARACTER DO DEK - u'\u0e15' # 0xb5 -> THAI CHARACTER TO TAO - u'\u0e16' # 0xb6 -> THAI CHARACTER THO THUNG - u'\u0e17' # 0xb7 -> THAI CHARACTER THO THAHAN - u'\u0e18' # 0xb8 -> THAI CHARACTER THO THONG - u'\u0e19' # 0xb9 -> THAI CHARACTER NO NU - u'\u0e1a' # 0xba -> THAI CHARACTER BO BAIMAI - u'\u0e1b' # 0xbb -> THAI CHARACTER PO PLA - u'\u0e1c' # 0xbc -> THAI CHARACTER PHO PHUNG - u'\u0e1d' # 0xbd -> THAI CHARACTER FO FA - u'\u0e1e' # 0xbe -> THAI CHARACTER PHO PHAN - u'\u0e1f' # 0xbf -> THAI CHARACTER FO FAN - u'\u0e20' # 0xc0 -> THAI CHARACTER PHO SAMPHAO - u'\u0e21' # 0xc1 -> THAI CHARACTER MO MA - u'\u0e22' # 0xc2 -> THAI CHARACTER YO YAK - u'\u0e23' # 0xc3 -> THAI CHARACTER RO RUA - u'\u0e24' # 0xc4 -> THAI CHARACTER RU - u'\u0e25' # 0xc5 -> THAI CHARACTER LO LING - u'\u0e26' # 0xc6 -> THAI CHARACTER LU - u'\u0e27' # 0xc7 -> THAI CHARACTER WO WAEN - u'\u0e28' # 0xc8 -> THAI CHARACTER SO SALA - u'\u0e29' # 0xc9 -> THAI CHARACTER SO RUSI - u'\u0e2a' # 0xca -> THAI CHARACTER SO SUA - u'\u0e2b' # 0xcb -> THAI CHARACTER HO HIP - u'\u0e2c' # 0xcc -> THAI CHARACTER LO CHULA - u'\u0e2d' # 0xcd -> THAI CHARACTER O ANG - u'\u0e2e' # 0xce -> THAI CHARACTER HO NOKHUK - u'\u0e2f' # 0xcf -> THAI CHARACTER PAIYANNOI - u'\u0e30' # 0xd0 -> THAI CHARACTER SARA A - u'\u0e31' # 0xd1 -> THAI CHARACTER MAI HAN-AKAT - u'\u0e32' # 0xd2 -> THAI CHARACTER SARA AA - u'\u0e33' # 0xd3 -> THAI CHARACTER SARA AM - u'\u0e34' # 0xd4 -> THAI CHARACTER SARA I - u'\u0e35' # 0xd5 -> THAI CHARACTER SARA II - u'\u0e36' # 0xd6 -> THAI CHARACTER SARA UE - u'\u0e37' # 0xd7 -> THAI CHARACTER SARA UEE - u'\u0e38' # 0xd8 -> THAI CHARACTER SARA U - u'\u0e39' # 0xd9 -> THAI CHARACTER SARA UU - u'\u0e3a' # 0xda -> THAI CHARACTER PHINTHU + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI + u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI + u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT + u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI + u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON + u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG + u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU + u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN + u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING + u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG + u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO + u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE + u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING + u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA + u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK + u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN + u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO + u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO + u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN + u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK + u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO + u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG + u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN + u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG + u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU + u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI + u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA + u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG + u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA + u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN + u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN + u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO + u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA + u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK + u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA + u'\u0e24' # 0xC4 -> THAI CHARACTER RU + u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING + u'\u0e26' # 0xC6 -> THAI CHARACTER LU + u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN + u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA + u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI + u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA + u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP + u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA + u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG + u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK + u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI + u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A + u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT + u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA + u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM + u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I + u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II + u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE + u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE + u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U + u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU + u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' - u'\u0e3f' # 0xdf -> THAI CURRENCY SYMBOL BAHT - u'\u0e40' # 0xe0 -> THAI CHARACTER SARA E - u'\u0e41' # 0xe1 -> THAI CHARACTER SARA AE - u'\u0e42' # 0xe2 -> THAI CHARACTER SARA O - u'\u0e43' # 0xe3 -> THAI CHARACTER SARA AI MAIMUAN - u'\u0e44' # 0xe4 -> THAI CHARACTER SARA AI MAIMALAI - u'\u0e45' # 0xe5 -> THAI CHARACTER LAKKHANGYAO - u'\u0e46' # 0xe6 -> THAI CHARACTER MAIYAMOK - u'\u0e47' # 0xe7 -> THAI CHARACTER MAITAIKHU - u'\u0e48' # 0xe8 -> THAI CHARACTER MAI EK - u'\u0e49' # 0xe9 -> THAI CHARACTER MAI THO - u'\u0e4a' # 0xea -> THAI CHARACTER MAI TRI - u'\u0e4b' # 0xeb -> THAI CHARACTER MAI CHATTAWA - u'\u0e4c' # 0xec -> THAI CHARACTER THANTHAKHAT - u'\u0e4d' # 0xed -> THAI CHARACTER NIKHAHIT - u'\u0e4e' # 0xee -> THAI CHARACTER YAMAKKAN - u'\u0e4f' # 0xef -> THAI CHARACTER FONGMAN - u'\u0e50' # 0xf0 -> THAI DIGIT ZERO - u'\u0e51' # 0xf1 -> THAI DIGIT ONE - u'\u0e52' # 0xf2 -> THAI DIGIT TWO - u'\u0e53' # 0xf3 -> THAI DIGIT THREE - u'\u0e54' # 0xf4 -> THAI DIGIT FOUR - u'\u0e55' # 0xf5 -> THAI DIGIT FIVE - u'\u0e56' # 0xf6 -> THAI DIGIT SIX - u'\u0e57' # 0xf7 -> THAI DIGIT SEVEN - u'\u0e58' # 0xf8 -> THAI DIGIT EIGHT - u'\u0e59' # 0xf9 -> THAI DIGIT NINE - u'\u0e5a' # 0xfa -> THAI CHARACTER ANGKHANKHU - u'\u0e5b' # 0xfb -> THAI CHARACTER KHOMUT + u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT + u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E + u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE + u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O + u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN + u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI + u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO + u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK + u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU + u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK + u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO + u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI + u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA + u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT + u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT + u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN + u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN + u'\u0e50' # 0xF0 -> THAI DIGIT ZERO + u'\u0e51' # 0xF1 -> THAI DIGIT ONE + u'\u0e52' # 0xF2 -> THAI DIGIT TWO + u'\u0e53' # 0xF3 -> THAI DIGIT THREE + u'\u0e54' # 0xF4 -> THAI DIGIT FOUR + u'\u0e55' # 0xF5 -> THAI DIGIT FIVE + u'\u0e56' # 0xF6 -> THAI DIGIT SIX + u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN + u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT + u'\u0e59' # 0xF9 -> THAI DIGIT NINE + u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU + u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT u'\ufffe' u'\ufffe' u'\ufffe' @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,98 +447,99 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x0e01: 0xa1, # THAI CHARACTER KO KAI - 0x0e02: 0xa2, # THAI CHARACTER KHO KHAI - 0x0e03: 0xa3, # THAI CHARACTER KHO KHUAT - 0x0e04: 0xa4, # THAI CHARACTER KHO KHWAI - 0x0e05: 0xa5, # THAI CHARACTER KHO KHON - 0x0e06: 0xa6, # THAI CHARACTER KHO RAKHANG - 0x0e07: 0xa7, # THAI CHARACTER NGO NGU - 0x0e08: 0xa8, # THAI CHARACTER CHO CHAN - 0x0e09: 0xa9, # THAI CHARACTER CHO CHING - 0x0e0a: 0xaa, # THAI CHARACTER CHO CHANG - 0x0e0b: 0xab, # THAI CHARACTER SO SO - 0x0e0c: 0xac, # THAI CHARACTER CHO CHOE - 0x0e0d: 0xad, # THAI CHARACTER YO YING - 0x0e0e: 0xae, # THAI CHARACTER DO CHADA - 0x0e0f: 0xaf, # THAI CHARACTER TO PATAK - 0x0e10: 0xb0, # THAI CHARACTER THO THAN - 0x0e11: 0xb1, # THAI CHARACTER THO NANGMONTHO - 0x0e12: 0xb2, # THAI CHARACTER THO PHUTHAO - 0x0e13: 0xb3, # THAI CHARACTER NO NEN - 0x0e14: 0xb4, # THAI CHARACTER DO DEK - 0x0e15: 0xb5, # THAI CHARACTER TO TAO - 0x0e16: 0xb6, # THAI CHARACTER THO THUNG - 0x0e17: 0xb7, # THAI CHARACTER THO THAHAN - 0x0e18: 0xb8, # THAI CHARACTER THO THONG - 0x0e19: 0xb9, # THAI CHARACTER NO NU - 0x0e1a: 0xba, # THAI CHARACTER BO BAIMAI - 0x0e1b: 0xbb, # THAI CHARACTER PO PLA - 0x0e1c: 0xbc, # THAI CHARACTER PHO PHUNG - 0x0e1d: 0xbd, # THAI CHARACTER FO FA - 0x0e1e: 0xbe, # THAI CHARACTER PHO PHAN - 0x0e1f: 0xbf, # THAI CHARACTER FO FAN - 0x0e20: 0xc0, # THAI CHARACTER PHO SAMPHAO - 0x0e21: 0xc1, # THAI CHARACTER MO MA - 0x0e22: 0xc2, # THAI CHARACTER YO YAK - 0x0e23: 0xc3, # THAI CHARACTER RO RUA - 0x0e24: 0xc4, # THAI CHARACTER RU - 0x0e25: 0xc5, # THAI CHARACTER LO LING - 0x0e26: 0xc6, # THAI CHARACTER LU - 0x0e27: 0xc7, # THAI CHARACTER WO WAEN - 0x0e28: 0xc8, # THAI CHARACTER SO SALA - 0x0e29: 0xc9, # THAI CHARACTER SO RUSI - 0x0e2a: 0xca, # THAI CHARACTER SO SUA - 0x0e2b: 0xcb, # THAI CHARACTER HO HIP - 0x0e2c: 0xcc, # THAI CHARACTER LO CHULA - 0x0e2d: 0xcd, # THAI CHARACTER O ANG - 0x0e2e: 0xce, # THAI CHARACTER HO NOKHUK - 0x0e2f: 0xcf, # THAI CHARACTER PAIYANNOI - 0x0e30: 0xd0, # THAI CHARACTER SARA A - 0x0e31: 0xd1, # THAI CHARACTER MAI HAN-AKAT - 0x0e32: 0xd2, # THAI CHARACTER SARA AA - 0x0e33: 0xd3, # THAI CHARACTER SARA AM - 0x0e34: 0xd4, # THAI CHARACTER SARA I - 0x0e35: 0xd5, # THAI CHARACTER SARA II - 0x0e36: 0xd6, # THAI CHARACTER SARA UE - 0x0e37: 0xd7, # THAI CHARACTER SARA UEE - 0x0e38: 0xd8, # THAI CHARACTER SARA U - 0x0e39: 0xd9, # THAI CHARACTER SARA UU - 0x0e3a: 0xda, # THAI CHARACTER PHINTHU - 0x0e3f: 0xdf, # THAI CURRENCY SYMBOL BAHT - 0x0e40: 0xe0, # THAI CHARACTER SARA E - 0x0e41: 0xe1, # THAI CHARACTER SARA AE - 0x0e42: 0xe2, # THAI CHARACTER SARA O - 0x0e43: 0xe3, # THAI CHARACTER SARA AI MAIMUAN - 0x0e44: 0xe4, # THAI CHARACTER SARA AI MAIMALAI - 0x0e45: 0xe5, # THAI CHARACTER LAKKHANGYAO - 0x0e46: 0xe6, # THAI CHARACTER MAIYAMOK - 0x0e47: 0xe7, # THAI CHARACTER MAITAIKHU - 0x0e48: 0xe8, # THAI CHARACTER MAI EK - 0x0e49: 0xe9, # THAI CHARACTER MAI THO - 0x0e4a: 0xea, # THAI CHARACTER MAI TRI - 0x0e4b: 0xeb, # THAI CHARACTER MAI CHATTAWA - 0x0e4c: 0xec, # THAI CHARACTER THANTHAKHAT - 0x0e4d: 0xed, # THAI CHARACTER NIKHAHIT - 0x0e4e: 0xee, # THAI CHARACTER YAMAKKAN - 0x0e4f: 0xef, # THAI CHARACTER FONGMAN - 0x0e50: 0xf0, # THAI DIGIT ZERO - 0x0e51: 0xf1, # THAI DIGIT ONE - 0x0e52: 0xf2, # THAI DIGIT TWO - 0x0e53: 0xf3, # THAI DIGIT THREE - 0x0e54: 0xf4, # THAI DIGIT FOUR - 0x0e55: 0xf5, # THAI DIGIT FIVE - 0x0e56: 0xf6, # THAI DIGIT SIX - 0x0e57: 0xf7, # THAI DIGIT SEVEN - 0x0e58: 0xf8, # THAI DIGIT EIGHT - 0x0e59: 0xf9, # THAI DIGIT NINE - 0x0e5a: 0xfa, # THAI CHARACTER ANGKHANKHU - 0x0e5b: 0xfb, # THAI CHARACTER KHOMUT -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x0E01: 0xA1, # THAI CHARACTER KO KAI + 0x0E02: 0xA2, # THAI CHARACTER KHO KHAI + 0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT + 0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI + 0x0E05: 0xA5, # THAI CHARACTER KHO KHON + 0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG + 0x0E07: 0xA7, # THAI CHARACTER NGO NGU + 0x0E08: 0xA8, # THAI CHARACTER CHO CHAN + 0x0E09: 0xA9, # THAI CHARACTER CHO CHING + 0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG + 0x0E0B: 0xAB, # THAI CHARACTER SO SO + 0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE + 0x0E0D: 0xAD, # THAI CHARACTER YO YING + 0x0E0E: 0xAE, # THAI CHARACTER DO CHADA + 0x0E0F: 0xAF, # THAI CHARACTER TO PATAK + 0x0E10: 0xB0, # THAI CHARACTER THO THAN + 0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO + 0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO + 0x0E13: 0xB3, # THAI CHARACTER NO NEN + 0x0E14: 0xB4, # THAI CHARACTER DO DEK + 0x0E15: 0xB5, # THAI CHARACTER TO TAO + 0x0E16: 0xB6, # THAI CHARACTER THO THUNG + 0x0E17: 0xB7, # THAI CHARACTER THO THAHAN + 0x0E18: 0xB8, # THAI CHARACTER THO THONG + 0x0E19: 0xB9, # THAI CHARACTER NO NU + 0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI + 0x0E1B: 0xBB, # THAI CHARACTER PO PLA + 0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG + 0x0E1D: 0xBD, # THAI CHARACTER FO FA + 0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN + 0x0E1F: 0xBF, # THAI CHARACTER FO FAN + 0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO + 0x0E21: 0xC1, # THAI CHARACTER MO MA + 0x0E22: 0xC2, # THAI CHARACTER YO YAK + 0x0E23: 0xC3, # THAI CHARACTER RO RUA + 0x0E24: 0xC4, # THAI CHARACTER RU + 0x0E25: 0xC5, # THAI CHARACTER LO LING + 0x0E26: 0xC6, # THAI CHARACTER LU + 0x0E27: 0xC7, # THAI CHARACTER WO WAEN + 0x0E28: 0xC8, # THAI CHARACTER SO SALA + 0x0E29: 0xC9, # THAI CHARACTER SO RUSI + 0x0E2A: 0xCA, # THAI CHARACTER SO SUA + 0x0E2B: 0xCB, # THAI CHARACTER HO HIP + 0x0E2C: 0xCC, # THAI CHARACTER LO CHULA + 0x0E2D: 0xCD, # THAI CHARACTER O ANG + 0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK + 0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI + 0x0E30: 0xD0, # THAI CHARACTER SARA A + 0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT + 0x0E32: 0xD2, # THAI CHARACTER SARA AA + 0x0E33: 0xD3, # THAI CHARACTER SARA AM + 0x0E34: 0xD4, # THAI CHARACTER SARA I + 0x0E35: 0xD5, # THAI CHARACTER SARA II + 0x0E36: 0xD6, # THAI CHARACTER SARA UE + 0x0E37: 0xD7, # THAI CHARACTER SARA UEE + 0x0E38: 0xD8, # THAI CHARACTER SARA U + 0x0E39: 0xD9, # THAI CHARACTER SARA UU + 0x0E3A: 0xDA, # THAI CHARACTER PHINTHU + 0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT + 0x0E40: 0xE0, # THAI CHARACTER SARA E + 0x0E41: 0xE1, # THAI CHARACTER SARA AE + 0x0E42: 0xE2, # THAI CHARACTER SARA O + 0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN + 0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI + 0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO + 0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK + 0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU + 0x0E48: 0xE8, # THAI CHARACTER MAI EK + 0x0E49: 0xE9, # THAI CHARACTER MAI THO + 0x0E4A: 0xEA, # THAI CHARACTER MAI TRI + 0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA + 0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT + 0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT + 0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN + 0x0E4F: 0xEF, # THAI CHARACTER FONGMAN + 0x0E50: 0xF0, # THAI DIGIT ZERO + 0x0E51: 0xF1, # THAI DIGIT ONE + 0x0E52: 0xF2, # THAI DIGIT TWO + 0x0E53: 0xF3, # THAI DIGIT THREE + 0x0E54: 0xF4, # THAI DIGIT FOUR + 0x0E55: 0xF5, # THAI DIGIT FIVE + 0x0E56: 0xF6, # THAI DIGIT SIX + 0x0E57: 0xF7, # THAI DIGIT SEVEN + 0x0E58: 0xF8, # THAI DIGIT EIGHT + 0x0E59: 0xF9, # THAI DIGIT NINE + 0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU + 0x0E5B: 0xFB, # THAI CHARACTER KHOMUT +} + diff --git a/Lib/encodings/iso8859_13.py b/Lib/encodings/iso8859_13.py index e48552b..099c9b8 100644 --- a/Lib/encodings/iso8859_13.py +++ b/Lib/encodings/iso8859_13.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u201d' # 0xa1 -> RIGHT DOUBLE QUOTATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\u201e' # 0xa5 -> DOUBLE LOW-9 QUOTATION MARK - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xd8' # 0xa8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u0156' # 0xaa -> LATIN CAPITAL LETTER R WITH CEDILLA - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xc6' # 0xaf -> LATIN CAPITAL LETTER AE - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\u201c' # 0xb4 -> LEFT DOUBLE QUOTATION MARK - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xf8' # 0xb8 -> LATIN SMALL LETTER O WITH STROKE - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\u0157' # 0xba -> LATIN SMALL LETTER R WITH CEDILLA - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xe6' # 0xbf -> LATIN SMALL LETTER AE - u'\u0104' # 0xc0 -> LATIN CAPITAL LETTER A WITH OGONEK - u'\u012e' # 0xc1 -> LATIN CAPITAL LETTER I WITH OGONEK - u'\u0100' # 0xc2 -> LATIN CAPITAL LETTER A WITH MACRON - u'\u0106' # 0xc3 -> LATIN CAPITAL LETTER C WITH ACUTE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\u0118' # 0xc6 -> LATIN CAPITAL LETTER E WITH OGONEK - u'\u0112' # 0xc7 -> LATIN CAPITAL LETTER E WITH MACRON - u'\u010c' # 0xc8 -> LATIN CAPITAL LETTER C WITH CARON - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\u0179' # 0xca -> LATIN CAPITAL LETTER Z WITH ACUTE - u'\u0116' # 0xcb -> LATIN CAPITAL LETTER E WITH DOT ABOVE - u'\u0122' # 0xcc -> LATIN CAPITAL LETTER G WITH CEDILLA - u'\u0136' # 0xcd -> LATIN CAPITAL LETTER K WITH CEDILLA - u'\u012a' # 0xce -> LATIN CAPITAL LETTER I WITH MACRON - u'\u013b' # 0xcf -> LATIN CAPITAL LETTER L WITH CEDILLA - u'\u0160' # 0xd0 -> LATIN CAPITAL LETTER S WITH CARON - u'\u0143' # 0xd1 -> LATIN CAPITAL LETTER N WITH ACUTE - u'\u0145' # 0xd2 -> LATIN CAPITAL LETTER N WITH CEDILLA - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\u014c' # 0xd4 -> LATIN CAPITAL LETTER O WITH MACRON - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\u0172' # 0xd8 -> LATIN CAPITAL LETTER U WITH OGONEK - u'\u0141' # 0xd9 -> LATIN CAPITAL LETTER L WITH STROKE - u'\u015a' # 0xda -> LATIN CAPITAL LETTER S WITH ACUTE - u'\u016a' # 0xdb -> LATIN CAPITAL LETTER U WITH MACRON - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u017b' # 0xdd -> LATIN CAPITAL LETTER Z WITH DOT ABOVE - u'\u017d' # 0xde -> LATIN CAPITAL LETTER Z WITH CARON - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S (German) - u'\u0105' # 0xe0 -> LATIN SMALL LETTER A WITH OGONEK - u'\u012f' # 0xe1 -> LATIN SMALL LETTER I WITH OGONEK - u'\u0101' # 0xe2 -> LATIN SMALL LETTER A WITH MACRON - u'\u0107' # 0xe3 -> LATIN SMALL LETTER C WITH ACUTE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\u0119' # 0xe6 -> LATIN SMALL LETTER E WITH OGONEK - u'\u0113' # 0xe7 -> LATIN SMALL LETTER E WITH MACRON - u'\u010d' # 0xe8 -> LATIN SMALL LETTER C WITH CARON - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\u017a' # 0xea -> LATIN SMALL LETTER Z WITH ACUTE - u'\u0117' # 0xeb -> LATIN SMALL LETTER E WITH DOT ABOVE - u'\u0123' # 0xec -> LATIN SMALL LETTER G WITH CEDILLA - u'\u0137' # 0xed -> LATIN SMALL LETTER K WITH CEDILLA - u'\u012b' # 0xee -> LATIN SMALL LETTER I WITH MACRON - u'\u013c' # 0xef -> LATIN SMALL LETTER L WITH CEDILLA - u'\u0161' # 0xf0 -> LATIN SMALL LETTER S WITH CARON - u'\u0144' # 0xf1 -> LATIN SMALL LETTER N WITH ACUTE - u'\u0146' # 0xf2 -> LATIN SMALL LETTER N WITH CEDILLA - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\u014d' # 0xf4 -> LATIN SMALL LETTER O WITH MACRON - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\u0173' # 0xf8 -> LATIN SMALL LETTER U WITH OGONEK - u'\u0142' # 0xf9 -> LATIN SMALL LETTER L WITH STROKE - u'\u015b' # 0xfa -> LATIN SMALL LETTER S WITH ACUTE - u'\u016b' # 0xfb -> LATIN SMALL LETTER U WITH MACRON - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u017c' # 0xfd -> LATIN SMALL LETTER Z WITH DOT ABOVE - u'\u017e' # 0xfe -> LATIN SMALL LETTER Z WITH CARON - u'\u2019' # 0xff -> RIGHT SINGLE QUOTATION MARK + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u201d' # 0xA1 -> RIGHT DOUBLE QUOTATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xc6' # 0xAF -> LATIN CAPITAL LETTER AE + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\u201c' # 0xB4 -> LEFT DOUBLE QUOTATION MARK + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xe6' # 0xBF -> LATIN SMALL LETTER AE + u'\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK + u'\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK + u'\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON + u'\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK + u'\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON + u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE + u'\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE + u'\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA + u'\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA + u'\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON + u'\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA + u'\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON + u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + u'\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK + u'\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE + u'\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE + u'\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + u'\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) + u'\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK + u'\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK + u'\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON + u'\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK + u'\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON + u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE + u'\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE + u'\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA + u'\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA + u'\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON + u'\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA + u'\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON + u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + u'\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK + u'\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE + u'\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE + u'\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE + u'\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON + u'\u2019' # 0xFF -> RIGHT SINGLE QUOTATION MARK ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xaf, # LATIN CAPITAL LETTER AE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xa8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S (German) - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xbf, # LATIN SMALL LETTER AE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xb8, # LATIN SMALL LETTER O WITH STROKE - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x0100: 0xc2, # LATIN CAPITAL LETTER A WITH MACRON - 0x0101: 0xe2, # LATIN SMALL LETTER A WITH MACRON - 0x0104: 0xc0, # LATIN CAPITAL LETTER A WITH OGONEK - 0x0105: 0xe0, # LATIN SMALL LETTER A WITH OGONEK - 0x0106: 0xc3, # LATIN CAPITAL LETTER C WITH ACUTE - 0x0107: 0xe3, # LATIN SMALL LETTER C WITH ACUTE - 0x010c: 0xc8, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xe8, # LATIN SMALL LETTER C WITH CARON - 0x0112: 0xc7, # LATIN CAPITAL LETTER E WITH MACRON - 0x0113: 0xe7, # LATIN SMALL LETTER E WITH MACRON - 0x0116: 0xcb, # LATIN CAPITAL LETTER E WITH DOT ABOVE - 0x0117: 0xeb, # LATIN SMALL LETTER E WITH DOT ABOVE - 0x0118: 0xc6, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xe6, # LATIN SMALL LETTER E WITH OGONEK - 0x0122: 0xcc, # LATIN CAPITAL LETTER G WITH CEDILLA - 0x0123: 0xec, # LATIN SMALL LETTER G WITH CEDILLA - 0x012a: 0xce, # LATIN CAPITAL LETTER I WITH MACRON - 0x012b: 0xee, # LATIN SMALL LETTER I WITH MACRON - 0x012e: 0xc1, # LATIN CAPITAL LETTER I WITH OGONEK - 0x012f: 0xe1, # LATIN SMALL LETTER I WITH OGONEK - 0x0136: 0xcd, # LATIN CAPITAL LETTER K WITH CEDILLA - 0x0137: 0xed, # LATIN SMALL LETTER K WITH CEDILLA - 0x013b: 0xcf, # LATIN CAPITAL LETTER L WITH CEDILLA - 0x013c: 0xef, # LATIN SMALL LETTER L WITH CEDILLA - 0x0141: 0xd9, # LATIN CAPITAL LETTER L WITH STROKE - 0x0142: 0xf9, # LATIN SMALL LETTER L WITH STROKE - 0x0143: 0xd1, # LATIN CAPITAL LETTER N WITH ACUTE - 0x0144: 0xf1, # LATIN SMALL LETTER N WITH ACUTE - 0x0145: 0xd2, # LATIN CAPITAL LETTER N WITH CEDILLA - 0x0146: 0xf2, # LATIN SMALL LETTER N WITH CEDILLA - 0x014c: 0xd4, # LATIN CAPITAL LETTER O WITH MACRON - 0x014d: 0xf4, # LATIN SMALL LETTER O WITH MACRON - 0x0156: 0xaa, # LATIN CAPITAL LETTER R WITH CEDILLA - 0x0157: 0xba, # LATIN SMALL LETTER R WITH CEDILLA - 0x015a: 0xda, # LATIN CAPITAL LETTER S WITH ACUTE - 0x015b: 0xfa, # LATIN SMALL LETTER S WITH ACUTE - 0x0160: 0xd0, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xf0, # LATIN SMALL LETTER S WITH CARON - 0x016a: 0xdb, # LATIN CAPITAL LETTER U WITH MACRON - 0x016b: 0xfb, # LATIN SMALL LETTER U WITH MACRON - 0x0172: 0xd8, # LATIN CAPITAL LETTER U WITH OGONEK - 0x0173: 0xf8, # LATIN SMALL LETTER U WITH OGONEK - 0x0179: 0xca, # LATIN CAPITAL LETTER Z WITH ACUTE - 0x017a: 0xea, # LATIN SMALL LETTER Z WITH ACUTE - 0x017b: 0xdd, # LATIN CAPITAL LETTER Z WITH DOT ABOVE - 0x017c: 0xfd, # LATIN SMALL LETTER Z WITH DOT ABOVE - 0x017d: 0xde, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xfe, # LATIN SMALL LETTER Z WITH CARON - 0x2019: 0xff, # RIGHT SINGLE QUOTATION MARK - 0x201c: 0xb4, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xa1, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xa5, # DOUBLE LOW-9 QUOTATION MARK -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xAF, # LATIN CAPITAL LETTER AE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xA8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S (German) + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xBF, # LATIN SMALL LETTER AE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xB8, # LATIN SMALL LETTER O WITH STROKE + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0100: 0xC2, # LATIN CAPITAL LETTER A WITH MACRON + 0x0101: 0xE2, # LATIN SMALL LETTER A WITH MACRON + 0x0104: 0xC0, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0xE0, # LATIN SMALL LETTER A WITH OGONEK + 0x0106: 0xC3, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0xE3, # LATIN SMALL LETTER C WITH ACUTE + 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON + 0x0112: 0xC7, # LATIN CAPITAL LETTER E WITH MACRON + 0x0113: 0xE7, # LATIN SMALL LETTER E WITH MACRON + 0x0116: 0xCB, # LATIN CAPITAL LETTER E WITH DOT ABOVE + 0x0117: 0xEB, # LATIN SMALL LETTER E WITH DOT ABOVE + 0x0118: 0xC6, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xE6, # LATIN SMALL LETTER E WITH OGONEK + 0x0122: 0xCC, # LATIN CAPITAL LETTER G WITH CEDILLA + 0x0123: 0xEC, # LATIN SMALL LETTER G WITH CEDILLA + 0x012A: 0xCE, # LATIN CAPITAL LETTER I WITH MACRON + 0x012B: 0xEE, # LATIN SMALL LETTER I WITH MACRON + 0x012E: 0xC1, # LATIN CAPITAL LETTER I WITH OGONEK + 0x012F: 0xE1, # LATIN SMALL LETTER I WITH OGONEK + 0x0136: 0xCD, # LATIN CAPITAL LETTER K WITH CEDILLA + 0x0137: 0xED, # LATIN SMALL LETTER K WITH CEDILLA + 0x013B: 0xCF, # LATIN CAPITAL LETTER L WITH CEDILLA + 0x013C: 0xEF, # LATIN SMALL LETTER L WITH CEDILLA + 0x0141: 0xD9, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0xF9, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE + 0x0145: 0xD2, # LATIN CAPITAL LETTER N WITH CEDILLA + 0x0146: 0xF2, # LATIN SMALL LETTER N WITH CEDILLA + 0x014C: 0xD4, # LATIN CAPITAL LETTER O WITH MACRON + 0x014D: 0xF4, # LATIN SMALL LETTER O WITH MACRON + 0x0156: 0xAA, # LATIN CAPITAL LETTER R WITH CEDILLA + 0x0157: 0xBA, # LATIN SMALL LETTER R WITH CEDILLA + 0x015A: 0xDA, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015B: 0xFA, # LATIN SMALL LETTER S WITH ACUTE + 0x0160: 0xD0, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xF0, # LATIN SMALL LETTER S WITH CARON + 0x016A: 0xDB, # LATIN CAPITAL LETTER U WITH MACRON + 0x016B: 0xFB, # LATIN SMALL LETTER U WITH MACRON + 0x0172: 0xD8, # LATIN CAPITAL LETTER U WITH OGONEK + 0x0173: 0xF8, # LATIN SMALL LETTER U WITH OGONEK + 0x0179: 0xCA, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017A: 0xEA, # LATIN SMALL LETTER Z WITH ACUTE + 0x017B: 0xDD, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017C: 0xFD, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017D: 0xDE, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xFE, # LATIN SMALL LETTER Z WITH CARON + 0x2019: 0xFF, # RIGHT SINGLE QUOTATION MARK + 0x201C: 0xB4, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xA1, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xA5, # DOUBLE LOW-9 QUOTATION MARK +} + diff --git a/Lib/encodings/iso8859_14.py b/Lib/encodings/iso8859_14.py index 2622cce..6cc6636 100644 --- a/Lib/encodings/iso8859_14.py +++ b/Lib/encodings/iso8859_14.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u1e02' # 0xa1 -> LATIN CAPITAL LETTER B WITH DOT ABOVE - u'\u1e03' # 0xa2 -> LATIN SMALL LETTER B WITH DOT ABOVE - u'\xa3' # 0xa3 -> POUND SIGN - u'\u010a' # 0xa4 -> LATIN CAPITAL LETTER C WITH DOT ABOVE - u'\u010b' # 0xa5 -> LATIN SMALL LETTER C WITH DOT ABOVE - u'\u1e0a' # 0xa6 -> LATIN CAPITAL LETTER D WITH DOT ABOVE - u'\xa7' # 0xa7 -> SECTION SIGN - u'\u1e80' # 0xa8 -> LATIN CAPITAL LETTER W WITH GRAVE - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u1e82' # 0xaa -> LATIN CAPITAL LETTER W WITH ACUTE - u'\u1e0b' # 0xab -> LATIN SMALL LETTER D WITH DOT ABOVE - u'\u1ef2' # 0xac -> LATIN CAPITAL LETTER Y WITH GRAVE - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\u0178' # 0xaf -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\u1e1e' # 0xb0 -> LATIN CAPITAL LETTER F WITH DOT ABOVE - u'\u1e1f' # 0xb1 -> LATIN SMALL LETTER F WITH DOT ABOVE - u'\u0120' # 0xb2 -> LATIN CAPITAL LETTER G WITH DOT ABOVE - u'\u0121' # 0xb3 -> LATIN SMALL LETTER G WITH DOT ABOVE - u'\u1e40' # 0xb4 -> LATIN CAPITAL LETTER M WITH DOT ABOVE - u'\u1e41' # 0xb5 -> LATIN SMALL LETTER M WITH DOT ABOVE - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\u1e56' # 0xb7 -> LATIN CAPITAL LETTER P WITH DOT ABOVE - u'\u1e81' # 0xb8 -> LATIN SMALL LETTER W WITH GRAVE - u'\u1e57' # 0xb9 -> LATIN SMALL LETTER P WITH DOT ABOVE - u'\u1e83' # 0xba -> LATIN SMALL LETTER W WITH ACUTE - u'\u1e60' # 0xbb -> LATIN CAPITAL LETTER S WITH DOT ABOVE - u'\u1ef3' # 0xbc -> LATIN SMALL LETTER Y WITH GRAVE - u'\u1e84' # 0xbd -> LATIN CAPITAL LETTER W WITH DIAERESIS - u'\u1e85' # 0xbe -> LATIN SMALL LETTER W WITH DIAERESIS - u'\u1e61' # 0xbf -> LATIN SMALL LETTER S WITH DOT ABOVE - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\u0174' # 0xd0 -> LATIN CAPITAL LETTER W WITH CIRCUMFLEX - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\u1e6a' # 0xd7 -> LATIN CAPITAL LETTER T WITH DOT ABOVE - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xdd' # 0xdd -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\u0176' # 0xde -> LATIN CAPITAL LETTER Y WITH CIRCUMFLEX - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\u0175' # 0xf0 -> LATIN SMALL LETTER W WITH CIRCUMFLEX - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\u1e6b' # 0xf7 -> LATIN SMALL LETTER T WITH DOT ABOVE - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xfd' # 0xfd -> LATIN SMALL LETTER Y WITH ACUTE - u'\u0177' # 0xfe -> LATIN SMALL LETTER Y WITH CIRCUMFLEX - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u1e02' # 0xA1 -> LATIN CAPITAL LETTER B WITH DOT ABOVE + u'\u1e03' # 0xA2 -> LATIN SMALL LETTER B WITH DOT ABOVE + u'\xa3' # 0xA3 -> POUND SIGN + u'\u010a' # 0xA4 -> LATIN CAPITAL LETTER C WITH DOT ABOVE + u'\u010b' # 0xA5 -> LATIN SMALL LETTER C WITH DOT ABOVE + u'\u1e0a' # 0xA6 -> LATIN CAPITAL LETTER D WITH DOT ABOVE + u'\xa7' # 0xA7 -> SECTION SIGN + u'\u1e80' # 0xA8 -> LATIN CAPITAL LETTER W WITH GRAVE + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u1e82' # 0xAA -> LATIN CAPITAL LETTER W WITH ACUTE + u'\u1e0b' # 0xAB -> LATIN SMALL LETTER D WITH DOT ABOVE + u'\u1ef2' # 0xAC -> LATIN CAPITAL LETTER Y WITH GRAVE + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\u0178' # 0xAF -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\u1e1e' # 0xB0 -> LATIN CAPITAL LETTER F WITH DOT ABOVE + u'\u1e1f' # 0xB1 -> LATIN SMALL LETTER F WITH DOT ABOVE + u'\u0120' # 0xB2 -> LATIN CAPITAL LETTER G WITH DOT ABOVE + u'\u0121' # 0xB3 -> LATIN SMALL LETTER G WITH DOT ABOVE + u'\u1e40' # 0xB4 -> LATIN CAPITAL LETTER M WITH DOT ABOVE + u'\u1e41' # 0xB5 -> LATIN SMALL LETTER M WITH DOT ABOVE + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\u1e56' # 0xB7 -> LATIN CAPITAL LETTER P WITH DOT ABOVE + u'\u1e81' # 0xB8 -> LATIN SMALL LETTER W WITH GRAVE + u'\u1e57' # 0xB9 -> LATIN SMALL LETTER P WITH DOT ABOVE + u'\u1e83' # 0xBA -> LATIN SMALL LETTER W WITH ACUTE + u'\u1e60' # 0xBB -> LATIN CAPITAL LETTER S WITH DOT ABOVE + u'\u1ef3' # 0xBC -> LATIN SMALL LETTER Y WITH GRAVE + u'\u1e84' # 0xBD -> LATIN CAPITAL LETTER W WITH DIAERESIS + u'\u1e85' # 0xBE -> LATIN SMALL LETTER W WITH DIAERESIS + u'\u1e61' # 0xBF -> LATIN SMALL LETTER S WITH DOT ABOVE + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\u0174' # 0xD0 -> LATIN CAPITAL LETTER W WITH CIRCUMFLEX + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\u1e6a' # 0xD7 -> LATIN CAPITAL LETTER T WITH DOT ABOVE + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\u0176' # 0xDE -> LATIN CAPITAL LETTER Y WITH CIRCUMFLEX + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\u0175' # 0xF0 -> LATIN SMALL LETTER W WITH CIRCUMFLEX + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\u1e6b' # 0xF7 -> LATIN SMALL LETTER T WITH DOT ABOVE + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + u'\u0177' # 0xFE -> LATIN SMALL LETTER Y WITH CIRCUMFLEX + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a3: 0xa3, # POUND SIGN - 0x00a7: 0xa7, # SECTION SIGN - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xdd, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xfd, # LATIN SMALL LETTER Y WITH ACUTE - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x010a: 0xa4, # LATIN CAPITAL LETTER C WITH DOT ABOVE - 0x010b: 0xa5, # LATIN SMALL LETTER C WITH DOT ABOVE - 0x0120: 0xb2, # LATIN CAPITAL LETTER G WITH DOT ABOVE - 0x0121: 0xb3, # LATIN SMALL LETTER G WITH DOT ABOVE - 0x0174: 0xd0, # LATIN CAPITAL LETTER W WITH CIRCUMFLEX - 0x0175: 0xf0, # LATIN SMALL LETTER W WITH CIRCUMFLEX - 0x0176: 0xde, # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX - 0x0177: 0xfe, # LATIN SMALL LETTER Y WITH CIRCUMFLEX - 0x0178: 0xaf, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x1e02: 0xa1, # LATIN CAPITAL LETTER B WITH DOT ABOVE - 0x1e03: 0xa2, # LATIN SMALL LETTER B WITH DOT ABOVE - 0x1e0a: 0xa6, # LATIN CAPITAL LETTER D WITH DOT ABOVE - 0x1e0b: 0xab, # LATIN SMALL LETTER D WITH DOT ABOVE - 0x1e1e: 0xb0, # LATIN CAPITAL LETTER F WITH DOT ABOVE - 0x1e1f: 0xb1, # LATIN SMALL LETTER F WITH DOT ABOVE - 0x1e40: 0xb4, # LATIN CAPITAL LETTER M WITH DOT ABOVE - 0x1e41: 0xb5, # LATIN SMALL LETTER M WITH DOT ABOVE - 0x1e56: 0xb7, # LATIN CAPITAL LETTER P WITH DOT ABOVE - 0x1e57: 0xb9, # LATIN SMALL LETTER P WITH DOT ABOVE - 0x1e60: 0xbb, # LATIN CAPITAL LETTER S WITH DOT ABOVE - 0x1e61: 0xbf, # LATIN SMALL LETTER S WITH DOT ABOVE - 0x1e6a: 0xd7, # LATIN CAPITAL LETTER T WITH DOT ABOVE - 0x1e6b: 0xf7, # LATIN SMALL LETTER T WITH DOT ABOVE - 0x1e80: 0xa8, # LATIN CAPITAL LETTER W WITH GRAVE - 0x1e81: 0xb8, # LATIN SMALL LETTER W WITH GRAVE - 0x1e82: 0xaa, # LATIN CAPITAL LETTER W WITH ACUTE - 0x1e83: 0xba, # LATIN SMALL LETTER W WITH ACUTE - 0x1e84: 0xbd, # LATIN CAPITAL LETTER W WITH DIAERESIS - 0x1e85: 0xbe, # LATIN SMALL LETTER W WITH DIAERESIS - 0x1ef2: 0xac, # LATIN CAPITAL LETTER Y WITH GRAVE - 0x1ef3: 0xbc, # LATIN SMALL LETTER Y WITH GRAVE -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A3: 0xA3, # POUND SIGN + 0x00A7: 0xA7, # SECTION SIGN + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x010A: 0xA4, # LATIN CAPITAL LETTER C WITH DOT ABOVE + 0x010B: 0xA5, # LATIN SMALL LETTER C WITH DOT ABOVE + 0x0120: 0xB2, # LATIN CAPITAL LETTER G WITH DOT ABOVE + 0x0121: 0xB3, # LATIN SMALL LETTER G WITH DOT ABOVE + 0x0174: 0xD0, # LATIN CAPITAL LETTER W WITH CIRCUMFLEX + 0x0175: 0xF0, # LATIN SMALL LETTER W WITH CIRCUMFLEX + 0x0176: 0xDE, # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX + 0x0177: 0xFE, # LATIN SMALL LETTER Y WITH CIRCUMFLEX + 0x0178: 0xAF, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x1E02: 0xA1, # LATIN CAPITAL LETTER B WITH DOT ABOVE + 0x1E03: 0xA2, # LATIN SMALL LETTER B WITH DOT ABOVE + 0x1E0A: 0xA6, # LATIN CAPITAL LETTER D WITH DOT ABOVE + 0x1E0B: 0xAB, # LATIN SMALL LETTER D WITH DOT ABOVE + 0x1E1E: 0xB0, # LATIN CAPITAL LETTER F WITH DOT ABOVE + 0x1E1F: 0xB1, # LATIN SMALL LETTER F WITH DOT ABOVE + 0x1E40: 0xB4, # LATIN CAPITAL LETTER M WITH DOT ABOVE + 0x1E41: 0xB5, # LATIN SMALL LETTER M WITH DOT ABOVE + 0x1E56: 0xB7, # LATIN CAPITAL LETTER P WITH DOT ABOVE + 0x1E57: 0xB9, # LATIN SMALL LETTER P WITH DOT ABOVE + 0x1E60: 0xBB, # LATIN CAPITAL LETTER S WITH DOT ABOVE + 0x1E61: 0xBF, # LATIN SMALL LETTER S WITH DOT ABOVE + 0x1E6A: 0xD7, # LATIN CAPITAL LETTER T WITH DOT ABOVE + 0x1E6B: 0xF7, # LATIN SMALL LETTER T WITH DOT ABOVE + 0x1E80: 0xA8, # LATIN CAPITAL LETTER W WITH GRAVE + 0x1E81: 0xB8, # LATIN SMALL LETTER W WITH GRAVE + 0x1E82: 0xAA, # LATIN CAPITAL LETTER W WITH ACUTE + 0x1E83: 0xBA, # LATIN SMALL LETTER W WITH ACUTE + 0x1E84: 0xBD, # LATIN CAPITAL LETTER W WITH DIAERESIS + 0x1E85: 0xBE, # LATIN SMALL LETTER W WITH DIAERESIS + 0x1EF2: 0xAC, # LATIN CAPITAL LETTER Y WITH GRAVE + 0x1EF3: 0xBC, # LATIN SMALL LETTER Y WITH GRAVE +} + diff --git a/Lib/encodings/iso8859_15.py b/Lib/encodings/iso8859_15.py index b1f4e67..204954b 100644 --- a/Lib/encodings/iso8859_15.py +++ b/Lib/encodings/iso8859_15.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\xa1' # 0xa1 -> INVERTED EXCLAMATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\u20ac' # 0xa4 -> EURO SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\u0160' # 0xa6 -> LATIN CAPITAL LETTER S WITH CARON - u'\xa7' # 0xa7 -> SECTION SIGN - u'\u0161' # 0xa8 -> LATIN SMALL LETTER S WITH CARON - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xaa' # 0xaa -> FEMININE ORDINAL INDICATOR - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\u017d' # 0xb4 -> LATIN CAPITAL LETTER Z WITH CARON - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\u017e' # 0xb8 -> LATIN SMALL LETTER Z WITH CARON - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xba' # 0xba -> MASCULINE ORDINAL INDICATOR - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u0152' # 0xbc -> LATIN CAPITAL LIGATURE OE - u'\u0153' # 0xbd -> LATIN SMALL LIGATURE OE - u'\u0178' # 0xbe -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\xbf' # 0xbf -> INVERTED QUESTION MARK - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xd0' # 0xd0 -> LATIN CAPITAL LETTER ETH - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xdd' # 0xdd -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xde' # 0xde -> LATIN CAPITAL LETTER THORN - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\xf0' # 0xf0 -> LATIN SMALL LETTER ETH - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xfd' # 0xfd -> LATIN SMALL LETTER Y WITH ACUTE - u'\xfe' # 0xfe -> LATIN SMALL LETTER THORN - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\u20ac' # 0xA4 -> EURO SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON + u'\xa7' # 0xA7 -> SECTION SIGN + u'\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE + u'\u0153' # 0xBD -> LATIN SMALL LIGATURE OE + u'\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\xbf' # 0xBF -> INVERTED QUESTION MARK + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a1: 0xa1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a7: 0xa7, # SECTION SIGN - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xaa, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00ba: 0xba, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bf: 0xbf, # INVERTED QUESTION MARK - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xd0, # LATIN CAPITAL LETTER ETH - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xdd, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xde, # LATIN CAPITAL LETTER THORN - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0xf0, # LATIN SMALL LETTER ETH - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xfd, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0xfe, # LATIN SMALL LETTER THORN - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x0152: 0xbc, # LATIN CAPITAL LIGATURE OE - 0x0153: 0xbd, # LATIN SMALL LIGATURE OE - 0x0160: 0xa6, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xa8, # LATIN SMALL LETTER S WITH CARON - 0x0178: 0xbe, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x017d: 0xb4, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xb8, # LATIN SMALL LETTER Z WITH CARON - 0x20ac: 0xa4, # EURO SIGN -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A7: 0xA7, # SECTION SIGN + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BF: 0xBF, # INVERTED QUESTION MARK + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xD0, # LATIN CAPITAL LETTER ETH + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0xF0, # LATIN SMALL LETTER ETH + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0xFE, # LATIN SMALL LETTER THORN + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0152: 0xBC, # LATIN CAPITAL LIGATURE OE + 0x0153: 0xBD, # LATIN SMALL LIGATURE OE + 0x0160: 0xA6, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xA8, # LATIN SMALL LETTER S WITH CARON + 0x0178: 0xBE, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x017D: 0xB4, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xB8, # LATIN SMALL LETTER Z WITH CARON + 0x20AC: 0xA4, # EURO SIGN +} + diff --git a/Lib/encodings/iso8859_16.py b/Lib/encodings/iso8859_16.py index 38f649d..756665b 100644 --- a/Lib/encodings/iso8859_16.py +++ b/Lib/encodings/iso8859_16.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0104' # 0xa1 -> LATIN CAPITAL LETTER A WITH OGONEK - u'\u0105' # 0xa2 -> LATIN SMALL LETTER A WITH OGONEK - u'\u0141' # 0xa3 -> LATIN CAPITAL LETTER L WITH STROKE - u'\u20ac' # 0xa4 -> EURO SIGN - u'\u201e' # 0xa5 -> DOUBLE LOW-9 QUOTATION MARK - u'\u0160' # 0xa6 -> LATIN CAPITAL LETTER S WITH CARON - u'\xa7' # 0xa7 -> SECTION SIGN - u'\u0161' # 0xa8 -> LATIN SMALL LETTER S WITH CARON - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u0218' # 0xaa -> LATIN CAPITAL LETTER S WITH COMMA BELOW - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u0179' # 0xac -> LATIN CAPITAL LETTER Z WITH ACUTE - u'\xad' # 0xad -> SOFT HYPHEN - u'\u017a' # 0xae -> LATIN SMALL LETTER Z WITH ACUTE - u'\u017b' # 0xaf -> LATIN CAPITAL LETTER Z WITH DOT ABOVE - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u010c' # 0xb2 -> LATIN CAPITAL LETTER C WITH CARON - u'\u0142' # 0xb3 -> LATIN SMALL LETTER L WITH STROKE - u'\u017d' # 0xb4 -> LATIN CAPITAL LETTER Z WITH CARON - u'\u201d' # 0xb5 -> RIGHT DOUBLE QUOTATION MARK - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\u017e' # 0xb8 -> LATIN SMALL LETTER Z WITH CARON - u'\u010d' # 0xb9 -> LATIN SMALL LETTER C WITH CARON - u'\u0219' # 0xba -> LATIN SMALL LETTER S WITH COMMA BELOW - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u0152' # 0xbc -> LATIN CAPITAL LIGATURE OE - u'\u0153' # 0xbd -> LATIN SMALL LIGATURE OE - u'\u0178' # 0xbe -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\u017c' # 0xbf -> LATIN SMALL LETTER Z WITH DOT ABOVE - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\u0102' # 0xc3 -> LATIN CAPITAL LETTER A WITH BREVE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\u0106' # 0xc5 -> LATIN CAPITAL LETTER C WITH ACUTE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\u0110' # 0xd0 -> LATIN CAPITAL LETTER D WITH STROKE - u'\u0143' # 0xd1 -> LATIN CAPITAL LETTER N WITH ACUTE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\u0150' # 0xd5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\u015a' # 0xd7 -> LATIN CAPITAL LETTER S WITH ACUTE - u'\u0170' # 0xd8 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u0118' # 0xdd -> LATIN CAPITAL LETTER E WITH OGONEK - u'\u021a' # 0xde -> LATIN CAPITAL LETTER T WITH COMMA BELOW - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\u0103' # 0xe3 -> LATIN SMALL LETTER A WITH BREVE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\u0107' # 0xe5 -> LATIN SMALL LETTER C WITH ACUTE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\u0111' # 0xf0 -> LATIN SMALL LETTER D WITH STROKE - u'\u0144' # 0xf1 -> LATIN SMALL LETTER N WITH ACUTE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\u0151' # 0xf5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\u015b' # 0xf7 -> LATIN SMALL LETTER S WITH ACUTE - u'\u0171' # 0xf8 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u0119' # 0xfd -> LATIN SMALL LETTER E WITH OGONEK - u'\u021b' # 0xfe -> LATIN SMALL LETTER T WITH COMMA BELOW - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + u'\u0105' # 0xA2 -> LATIN SMALL LETTER A WITH OGONEK + u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE + u'\u20ac' # 0xA4 -> EURO SIGN + u'\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK + u'\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON + u'\xa7' # 0xA7 -> SECTION SIGN + u'\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u0218' # 0xAA -> LATIN CAPITAL LETTER S WITH COMMA BELOW + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE + u'\xad' # 0xAD -> SOFT HYPHEN + u'\u017a' # 0xAE -> LATIN SMALL LETTER Z WITH ACUTE + u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u010c' # 0xB2 -> LATIN CAPITAL LETTER C WITH CARON + u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE + u'\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON + u'\u201d' # 0xB5 -> RIGHT DOUBLE QUOTATION MARK + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON + u'\u010d' # 0xB9 -> LATIN SMALL LETTER C WITH CARON + u'\u0219' # 0xBA -> LATIN SMALL LETTER S WITH COMMA BELOW + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE + u'\u0153' # 0xBD -> LATIN SMALL LIGATURE OE + u'\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\u0106' # 0xC5 -> LATIN CAPITAL LETTER C WITH ACUTE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\u015a' # 0xD7 -> LATIN CAPITAL LETTER S WITH ACUTE + u'\u0170' # 0xD8 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u0118' # 0xDD -> LATIN CAPITAL LETTER E WITH OGONEK + u'\u021a' # 0xDE -> LATIN CAPITAL LETTER T WITH COMMA BELOW + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\u0107' # 0xE5 -> LATIN SMALL LETTER C WITH ACUTE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\u015b' # 0xF7 -> LATIN SMALL LETTER S WITH ACUTE + u'\u0171' # 0xF8 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u0119' # 0xFD -> LATIN SMALL LETTER E WITH OGONEK + u'\u021b' # 0xFE -> LATIN SMALL LETTER T WITH COMMA BELOW + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a7: 0xa7, # SECTION SIGN - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ad: 0xad, # SOFT HYPHEN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x0102: 0xc3, # LATIN CAPITAL LETTER A WITH BREVE - 0x0103: 0xe3, # LATIN SMALL LETTER A WITH BREVE - 0x0104: 0xa1, # LATIN CAPITAL LETTER A WITH OGONEK - 0x0105: 0xa2, # LATIN SMALL LETTER A WITH OGONEK - 0x0106: 0xc5, # LATIN CAPITAL LETTER C WITH ACUTE - 0x0107: 0xe5, # LATIN SMALL LETTER C WITH ACUTE - 0x010c: 0xb2, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xb9, # LATIN SMALL LETTER C WITH CARON - 0x0110: 0xd0, # LATIN CAPITAL LETTER D WITH STROKE - 0x0111: 0xf0, # LATIN SMALL LETTER D WITH STROKE - 0x0118: 0xdd, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xfd, # LATIN SMALL LETTER E WITH OGONEK - 0x0141: 0xa3, # LATIN CAPITAL LETTER L WITH STROKE - 0x0142: 0xb3, # LATIN SMALL LETTER L WITH STROKE - 0x0143: 0xd1, # LATIN CAPITAL LETTER N WITH ACUTE - 0x0144: 0xf1, # LATIN SMALL LETTER N WITH ACUTE - 0x0150: 0xd5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - 0x0151: 0xf5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE - 0x0152: 0xbc, # LATIN CAPITAL LIGATURE OE - 0x0153: 0xbd, # LATIN SMALL LIGATURE OE - 0x015a: 0xd7, # LATIN CAPITAL LETTER S WITH ACUTE - 0x015b: 0xf7, # LATIN SMALL LETTER S WITH ACUTE - 0x0160: 0xa6, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xa8, # LATIN SMALL LETTER S WITH CARON - 0x0170: 0xd8, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - 0x0171: 0xf8, # LATIN SMALL LETTER U WITH DOUBLE ACUTE - 0x0178: 0xbe, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x0179: 0xac, # LATIN CAPITAL LETTER Z WITH ACUTE - 0x017a: 0xae, # LATIN SMALL LETTER Z WITH ACUTE - 0x017b: 0xaf, # LATIN CAPITAL LETTER Z WITH DOT ABOVE - 0x017c: 0xbf, # LATIN SMALL LETTER Z WITH DOT ABOVE - 0x017d: 0xb4, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xb8, # LATIN SMALL LETTER Z WITH CARON - 0x0218: 0xaa, # LATIN CAPITAL LETTER S WITH COMMA BELOW - 0x0219: 0xba, # LATIN SMALL LETTER S WITH COMMA BELOW - 0x021a: 0xde, # LATIN CAPITAL LETTER T WITH COMMA BELOW - 0x021b: 0xfe, # LATIN SMALL LETTER T WITH COMMA BELOW - 0x201d: 0xb5, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xa5, # DOUBLE LOW-9 QUOTATION MARK - 0x20ac: 0xa4, # EURO SIGN -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A7: 0xA7, # SECTION SIGN + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE + 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE + 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0xA2, # LATIN SMALL LETTER A WITH OGONEK + 0x0106: 0xC5, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0xE5, # LATIN SMALL LETTER C WITH ACUTE + 0x010C: 0xB2, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xB9, # LATIN SMALL LETTER C WITH CARON + 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE + 0x0118: 0xDD, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xFD, # LATIN SMALL LETTER E WITH OGONEK + 0x0141: 0xA3, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0xB3, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE + 0x0150: 0xD5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + 0x0151: 0xF5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE + 0x0152: 0xBC, # LATIN CAPITAL LIGATURE OE + 0x0153: 0xBD, # LATIN SMALL LIGATURE OE + 0x015A: 0xD7, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015B: 0xF7, # LATIN SMALL LETTER S WITH ACUTE + 0x0160: 0xA6, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xA8, # LATIN SMALL LETTER S WITH CARON + 0x0170: 0xD8, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + 0x0171: 0xF8, # LATIN SMALL LETTER U WITH DOUBLE ACUTE + 0x0178: 0xBE, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x0179: 0xAC, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017A: 0xAE, # LATIN SMALL LETTER Z WITH ACUTE + 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017D: 0xB4, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xB8, # LATIN SMALL LETTER Z WITH CARON + 0x0218: 0xAA, # LATIN CAPITAL LETTER S WITH COMMA BELOW + 0x0219: 0xBA, # LATIN SMALL LETTER S WITH COMMA BELOW + 0x021A: 0xDE, # LATIN CAPITAL LETTER T WITH COMMA BELOW + 0x021B: 0xFE, # LATIN SMALL LETTER T WITH COMMA BELOW + 0x201D: 0xB5, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xA5, # DOUBLE LOW-9 QUOTATION MARK + 0x20AC: 0xA4, # EURO SIGN +} + diff --git a/Lib/encodings/iso8859_2.py b/Lib/encodings/iso8859_2.py index a985306..f4eef98 100644 --- a/Lib/encodings/iso8859_2.py +++ b/Lib/encodings/iso8859_2.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0104' # 0xa1 -> LATIN CAPITAL LETTER A WITH OGONEK - u'\u02d8' # 0xa2 -> BREVE - u'\u0141' # 0xa3 -> LATIN CAPITAL LETTER L WITH STROKE - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\u013d' # 0xa5 -> LATIN CAPITAL LETTER L WITH CARON - u'\u015a' # 0xa6 -> LATIN CAPITAL LETTER S WITH ACUTE - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\u0160' # 0xa9 -> LATIN CAPITAL LETTER S WITH CARON - u'\u015e' # 0xaa -> LATIN CAPITAL LETTER S WITH CEDILLA - u'\u0164' # 0xab -> LATIN CAPITAL LETTER T WITH CARON - u'\u0179' # 0xac -> LATIN CAPITAL LETTER Z WITH ACUTE - u'\xad' # 0xad -> SOFT HYPHEN - u'\u017d' # 0xae -> LATIN CAPITAL LETTER Z WITH CARON - u'\u017b' # 0xaf -> LATIN CAPITAL LETTER Z WITH DOT ABOVE - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\u0105' # 0xb1 -> LATIN SMALL LETTER A WITH OGONEK - u'\u02db' # 0xb2 -> OGONEK - u'\u0142' # 0xb3 -> LATIN SMALL LETTER L WITH STROKE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\u013e' # 0xb5 -> LATIN SMALL LETTER L WITH CARON - u'\u015b' # 0xb6 -> LATIN SMALL LETTER S WITH ACUTE - u'\u02c7' # 0xb7 -> CARON - u'\xb8' # 0xb8 -> CEDILLA - u'\u0161' # 0xb9 -> LATIN SMALL LETTER S WITH CARON - u'\u015f' # 0xba -> LATIN SMALL LETTER S WITH CEDILLA - u'\u0165' # 0xbb -> LATIN SMALL LETTER T WITH CARON - u'\u017a' # 0xbc -> LATIN SMALL LETTER Z WITH ACUTE - u'\u02dd' # 0xbd -> DOUBLE ACUTE ACCENT - u'\u017e' # 0xbe -> LATIN SMALL LETTER Z WITH CARON - u'\u017c' # 0xbf -> LATIN SMALL LETTER Z WITH DOT ABOVE - u'\u0154' # 0xc0 -> LATIN CAPITAL LETTER R WITH ACUTE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\u0102' # 0xc3 -> LATIN CAPITAL LETTER A WITH BREVE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\u0139' # 0xc5 -> LATIN CAPITAL LETTER L WITH ACUTE - u'\u0106' # 0xc6 -> LATIN CAPITAL LETTER C WITH ACUTE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\u010c' # 0xc8 -> LATIN CAPITAL LETTER C WITH CARON - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\u0118' # 0xca -> LATIN CAPITAL LETTER E WITH OGONEK - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\u011a' # 0xcc -> LATIN CAPITAL LETTER E WITH CARON - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\u010e' # 0xcf -> LATIN CAPITAL LETTER D WITH CARON - u'\u0110' # 0xd0 -> LATIN CAPITAL LETTER D WITH STROKE - u'\u0143' # 0xd1 -> LATIN CAPITAL LETTER N WITH ACUTE - u'\u0147' # 0xd2 -> LATIN CAPITAL LETTER N WITH CARON - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\u0150' # 0xd5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\u0158' # 0xd8 -> LATIN CAPITAL LETTER R WITH CARON - u'\u016e' # 0xd9 -> LATIN CAPITAL LETTER U WITH RING ABOVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\u0170' # 0xdb -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\xdd' # 0xdd -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\u0162' # 0xde -> LATIN CAPITAL LETTER T WITH CEDILLA - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\u0155' # 0xe0 -> LATIN SMALL LETTER R WITH ACUTE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\u0103' # 0xe3 -> LATIN SMALL LETTER A WITH BREVE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\u013a' # 0xe5 -> LATIN SMALL LETTER L WITH ACUTE - u'\u0107' # 0xe6 -> LATIN SMALL LETTER C WITH ACUTE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\u010d' # 0xe8 -> LATIN SMALL LETTER C WITH CARON - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\u0119' # 0xea -> LATIN SMALL LETTER E WITH OGONEK - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\u011b' # 0xec -> LATIN SMALL LETTER E WITH CARON - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\u010f' # 0xef -> LATIN SMALL LETTER D WITH CARON - u'\u0111' # 0xf0 -> LATIN SMALL LETTER D WITH STROKE - u'\u0144' # 0xf1 -> LATIN SMALL LETTER N WITH ACUTE - u'\u0148' # 0xf2 -> LATIN SMALL LETTER N WITH CARON - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\u0151' # 0xf5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\u0159' # 0xf8 -> LATIN SMALL LETTER R WITH CARON - u'\u016f' # 0xf9 -> LATIN SMALL LETTER U WITH RING ABOVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\u0171' # 0xfb -> LATIN SMALL LETTER U WITH DOUBLE ACUTE - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xfd' # 0xfd -> LATIN SMALL LETTER Y WITH ACUTE - u'\u0163' # 0xfe -> LATIN SMALL LETTER T WITH CEDILLA - u'\u02d9' # 0xff -> DOT ABOVE + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + u'\u02d8' # 0xA2 -> BREVE + u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\u013d' # 0xA5 -> LATIN CAPITAL LETTER L WITH CARON + u'\u015a' # 0xA6 -> LATIN CAPITAL LETTER S WITH ACUTE + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON + u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA + u'\u0164' # 0xAB -> LATIN CAPITAL LETTER T WITH CARON + u'\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE + u'\xad' # 0xAD -> SOFT HYPHEN + u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON + u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK + u'\u02db' # 0xB2 -> OGONEK + u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\u013e' # 0xB5 -> LATIN SMALL LETTER L WITH CARON + u'\u015b' # 0xB6 -> LATIN SMALL LETTER S WITH ACUTE + u'\u02c7' # 0xB7 -> CARON + u'\xb8' # 0xB8 -> CEDILLA + u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON + u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA + u'\u0165' # 0xBB -> LATIN SMALL LETTER T WITH CARON + u'\u017a' # 0xBC -> LATIN SMALL LETTER Z WITH ACUTE + u'\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT + u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON + u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + u'\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE + u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON + u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + u'\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON + u'\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE + u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON + u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + u'\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON + u'\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + u'\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA + u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00ad: 0xad, # SOFT HYPHEN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b8: 0xb8, # CEDILLA - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xdd, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xfd, # LATIN SMALL LETTER Y WITH ACUTE - 0x0102: 0xc3, # LATIN CAPITAL LETTER A WITH BREVE - 0x0103: 0xe3, # LATIN SMALL LETTER A WITH BREVE - 0x0104: 0xa1, # LATIN CAPITAL LETTER A WITH OGONEK - 0x0105: 0xb1, # LATIN SMALL LETTER A WITH OGONEK - 0x0106: 0xc6, # LATIN CAPITAL LETTER C WITH ACUTE - 0x0107: 0xe6, # LATIN SMALL LETTER C WITH ACUTE - 0x010c: 0xc8, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xe8, # LATIN SMALL LETTER C WITH CARON - 0x010e: 0xcf, # LATIN CAPITAL LETTER D WITH CARON - 0x010f: 0xef, # LATIN SMALL LETTER D WITH CARON - 0x0110: 0xd0, # LATIN CAPITAL LETTER D WITH STROKE - 0x0111: 0xf0, # LATIN SMALL LETTER D WITH STROKE - 0x0118: 0xca, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xea, # LATIN SMALL LETTER E WITH OGONEK - 0x011a: 0xcc, # LATIN CAPITAL LETTER E WITH CARON - 0x011b: 0xec, # LATIN SMALL LETTER E WITH CARON - 0x0139: 0xc5, # LATIN CAPITAL LETTER L WITH ACUTE - 0x013a: 0xe5, # LATIN SMALL LETTER L WITH ACUTE - 0x013d: 0xa5, # LATIN CAPITAL LETTER L WITH CARON - 0x013e: 0xb5, # LATIN SMALL LETTER L WITH CARON - 0x0141: 0xa3, # LATIN CAPITAL LETTER L WITH STROKE - 0x0142: 0xb3, # LATIN SMALL LETTER L WITH STROKE - 0x0143: 0xd1, # LATIN CAPITAL LETTER N WITH ACUTE - 0x0144: 0xf1, # LATIN SMALL LETTER N WITH ACUTE - 0x0147: 0xd2, # LATIN CAPITAL LETTER N WITH CARON - 0x0148: 0xf2, # LATIN SMALL LETTER N WITH CARON - 0x0150: 0xd5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - 0x0151: 0xf5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE - 0x0154: 0xc0, # LATIN CAPITAL LETTER R WITH ACUTE - 0x0155: 0xe0, # LATIN SMALL LETTER R WITH ACUTE - 0x0158: 0xd8, # LATIN CAPITAL LETTER R WITH CARON - 0x0159: 0xf8, # LATIN SMALL LETTER R WITH CARON - 0x015a: 0xa6, # LATIN CAPITAL LETTER S WITH ACUTE - 0x015b: 0xb6, # LATIN SMALL LETTER S WITH ACUTE - 0x015e: 0xaa, # LATIN CAPITAL LETTER S WITH CEDILLA - 0x015f: 0xba, # LATIN SMALL LETTER S WITH CEDILLA - 0x0160: 0xa9, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xb9, # LATIN SMALL LETTER S WITH CARON - 0x0162: 0xde, # LATIN CAPITAL LETTER T WITH CEDILLA - 0x0163: 0xfe, # LATIN SMALL LETTER T WITH CEDILLA - 0x0164: 0xab, # LATIN CAPITAL LETTER T WITH CARON - 0x0165: 0xbb, # LATIN SMALL LETTER T WITH CARON - 0x016e: 0xd9, # LATIN CAPITAL LETTER U WITH RING ABOVE - 0x016f: 0xf9, # LATIN SMALL LETTER U WITH RING ABOVE - 0x0170: 0xdb, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - 0x0171: 0xfb, # LATIN SMALL LETTER U WITH DOUBLE ACUTE - 0x0179: 0xac, # LATIN CAPITAL LETTER Z WITH ACUTE - 0x017a: 0xbc, # LATIN SMALL LETTER Z WITH ACUTE - 0x017b: 0xaf, # LATIN CAPITAL LETTER Z WITH DOT ABOVE - 0x017c: 0xbf, # LATIN SMALL LETTER Z WITH DOT ABOVE - 0x017d: 0xae, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xbe, # LATIN SMALL LETTER Z WITH CARON - 0x02c7: 0xb7, # CARON - 0x02d8: 0xa2, # BREVE - 0x02d9: 0xff, # DOT ABOVE - 0x02db: 0xb2, # OGONEK - 0x02dd: 0xbd, # DOUBLE ACUTE ACCENT -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B8: 0xB8, # CEDILLA + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xDD, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xFD, # LATIN SMALL LETTER Y WITH ACUTE + 0x0102: 0xC3, # LATIN CAPITAL LETTER A WITH BREVE + 0x0103: 0xE3, # LATIN SMALL LETTER A WITH BREVE + 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0xB1, # LATIN SMALL LETTER A WITH OGONEK + 0x0106: 0xC6, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0xE6, # LATIN SMALL LETTER C WITH ACUTE + 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON + 0x010E: 0xCF, # LATIN CAPITAL LETTER D WITH CARON + 0x010F: 0xEF, # LATIN SMALL LETTER D WITH CARON + 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE + 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK + 0x011A: 0xCC, # LATIN CAPITAL LETTER E WITH CARON + 0x011B: 0xEC, # LATIN SMALL LETTER E WITH CARON + 0x0139: 0xC5, # LATIN CAPITAL LETTER L WITH ACUTE + 0x013A: 0xE5, # LATIN SMALL LETTER L WITH ACUTE + 0x013D: 0xA5, # LATIN CAPITAL LETTER L WITH CARON + 0x013E: 0xB5, # LATIN SMALL LETTER L WITH CARON + 0x0141: 0xA3, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0xB3, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0xD1, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0xF1, # LATIN SMALL LETTER N WITH ACUTE + 0x0147: 0xD2, # LATIN CAPITAL LETTER N WITH CARON + 0x0148: 0xF2, # LATIN SMALL LETTER N WITH CARON + 0x0150: 0xD5, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + 0x0151: 0xF5, # LATIN SMALL LETTER O WITH DOUBLE ACUTE + 0x0154: 0xC0, # LATIN CAPITAL LETTER R WITH ACUTE + 0x0155: 0xE0, # LATIN SMALL LETTER R WITH ACUTE + 0x0158: 0xD8, # LATIN CAPITAL LETTER R WITH CARON + 0x0159: 0xF8, # LATIN SMALL LETTER R WITH CARON + 0x015A: 0xA6, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015B: 0xB6, # LATIN SMALL LETTER S WITH ACUTE + 0x015E: 0xAA, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015F: 0xBA, # LATIN SMALL LETTER S WITH CEDILLA + 0x0160: 0xA9, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xB9, # LATIN SMALL LETTER S WITH CARON + 0x0162: 0xDE, # LATIN CAPITAL LETTER T WITH CEDILLA + 0x0163: 0xFE, # LATIN SMALL LETTER T WITH CEDILLA + 0x0164: 0xAB, # LATIN CAPITAL LETTER T WITH CARON + 0x0165: 0xBB, # LATIN SMALL LETTER T WITH CARON + 0x016E: 0xD9, # LATIN CAPITAL LETTER U WITH RING ABOVE + 0x016F: 0xF9, # LATIN SMALL LETTER U WITH RING ABOVE + 0x0170: 0xDB, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + 0x0171: 0xFB, # LATIN SMALL LETTER U WITH DOUBLE ACUTE + 0x0179: 0xAC, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017A: 0xBC, # LATIN SMALL LETTER Z WITH ACUTE + 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017D: 0xAE, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xBE, # LATIN SMALL LETTER Z WITH CARON + 0x02C7: 0xB7, # CARON + 0x02D8: 0xA2, # BREVE + 0x02D9: 0xFF, # DOT ABOVE + 0x02DB: 0xB2, # OGONEK + 0x02DD: 0xBD, # DOUBLE ACUTE ACCENT +} + diff --git a/Lib/encodings/iso8859_3.py b/Lib/encodings/iso8859_3.py index 6897122..167b76a 100644 --- a/Lib/encodings/iso8859_3.py +++ b/Lib/encodings/iso8859_3.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0126' # 0xa1 -> LATIN CAPITAL LETTER H WITH STROKE - u'\u02d8' # 0xa2 -> BREVE - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0126' # 0xA1 -> LATIN CAPITAL LETTER H WITH STROKE + u'\u02d8' # 0xA2 -> BREVE + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN u'\ufffe' - u'\u0124' # 0xa6 -> LATIN CAPITAL LETTER H WITH CIRCUMFLEX - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\u0130' # 0xa9 -> LATIN CAPITAL LETTER I WITH DOT ABOVE - u'\u015e' # 0xaa -> LATIN CAPITAL LETTER S WITH CEDILLA - u'\u011e' # 0xab -> LATIN CAPITAL LETTER G WITH BREVE - u'\u0134' # 0xac -> LATIN CAPITAL LETTER J WITH CIRCUMFLEX - u'\xad' # 0xad -> SOFT HYPHEN + u'\u0124' # 0xA6 -> LATIN CAPITAL LETTER H WITH CIRCUMFLEX + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\u0130' # 0xA9 -> LATIN CAPITAL LETTER I WITH DOT ABOVE + u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA + u'\u011e' # 0xAB -> LATIN CAPITAL LETTER G WITH BREVE + u'\u0134' # 0xAC -> LATIN CAPITAL LETTER J WITH CIRCUMFLEX + u'\xad' # 0xAD -> SOFT HYPHEN u'\ufffe' - u'\u017b' # 0xaf -> LATIN CAPITAL LETTER Z WITH DOT ABOVE - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\u0127' # 0xb1 -> LATIN SMALL LETTER H WITH STROKE - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\u0125' # 0xb6 -> LATIN SMALL LETTER H WITH CIRCUMFLEX - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\u0131' # 0xb9 -> LATIN SMALL LETTER DOTLESS I - u'\u015f' # 0xba -> LATIN SMALL LETTER S WITH CEDILLA - u'\u011f' # 0xbb -> LATIN SMALL LETTER G WITH BREVE - u'\u0135' # 0xbc -> LATIN SMALL LETTER J WITH CIRCUMFLEX - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF + u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\u0127' # 0xB1 -> LATIN SMALL LETTER H WITH STROKE + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\u0125' # 0xB6 -> LATIN SMALL LETTER H WITH CIRCUMFLEX + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\u0131' # 0xB9 -> LATIN SMALL LETTER DOTLESS I + u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA + u'\u011f' # 0xBB -> LATIN SMALL LETTER G WITH BREVE + u'\u0135' # 0xBC -> LATIN SMALL LETTER J WITH CIRCUMFLEX + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\ufffe' - u'\u017c' # 0xbf -> LATIN SMALL LETTER Z WITH DOT ABOVE - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\ufffe' - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\u010a' # 0xc5 -> LATIN CAPITAL LETTER C WITH DOT ABOVE - u'\u0108' # 0xc6 -> LATIN CAPITAL LETTER C WITH CIRCUMFLEX - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\u010a' # 0xC5 -> LATIN CAPITAL LETTER C WITH DOT ABOVE + u'\u0108' # 0xC6 -> LATIN CAPITAL LETTER C WITH CIRCUMFLEX + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\ufffe' - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\u0120' # 0xd5 -> LATIN CAPITAL LETTER G WITH DOT ABOVE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\u011c' # 0xd8 -> LATIN CAPITAL LETTER G WITH CIRCUMFLEX - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u016c' # 0xdd -> LATIN CAPITAL LETTER U WITH BREVE - u'\u015c' # 0xde -> LATIN CAPITAL LETTER S WITH CIRCUMFLEX - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\u0120' # 0xD5 -> LATIN CAPITAL LETTER G WITH DOT ABOVE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\u011c' # 0xD8 -> LATIN CAPITAL LETTER G WITH CIRCUMFLEX + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u016c' # 0xDD -> LATIN CAPITAL LETTER U WITH BREVE + u'\u015c' # 0xDE -> LATIN CAPITAL LETTER S WITH CIRCUMFLEX + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\ufffe' - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\u010b' # 0xe5 -> LATIN SMALL LETTER C WITH DOT ABOVE - u'\u0109' # 0xe6 -> LATIN SMALL LETTER C WITH CIRCUMFLEX - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\u010b' # 0xE5 -> LATIN SMALL LETTER C WITH DOT ABOVE + u'\u0109' # 0xE6 -> LATIN SMALL LETTER C WITH CIRCUMFLEX + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\ufffe' - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\u0121' # 0xf5 -> LATIN SMALL LETTER G WITH DOT ABOVE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\u011d' # 0xf8 -> LATIN SMALL LETTER G WITH CIRCUMFLEX - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u016d' # 0xfd -> LATIN SMALL LETTER U WITH BREVE - u'\u015d' # 0xfe -> LATIN SMALL LETTER S WITH CIRCUMFLEX - u'\u02d9' # 0xff -> DOT ABOVE + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\u0121' # 0xF5 -> LATIN SMALL LETTER G WITH DOT ABOVE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\u011d' # 0xF8 -> LATIN SMALL LETTER G WITH CIRCUMFLEX + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u016d' # 0xFD -> LATIN SMALL LETTER U WITH BREVE + u'\u015d' # 0xFE -> LATIN SMALL LETTER S WITH CIRCUMFLEX + u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,99 +447,100 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00ad: 0xad, # SOFT HYPHEN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x0108: 0xc6, # LATIN CAPITAL LETTER C WITH CIRCUMFLEX - 0x0109: 0xe6, # LATIN SMALL LETTER C WITH CIRCUMFLEX - 0x010a: 0xc5, # LATIN CAPITAL LETTER C WITH DOT ABOVE - 0x010b: 0xe5, # LATIN SMALL LETTER C WITH DOT ABOVE - 0x011c: 0xd8, # LATIN CAPITAL LETTER G WITH CIRCUMFLEX - 0x011d: 0xf8, # LATIN SMALL LETTER G WITH CIRCUMFLEX - 0x011e: 0xab, # LATIN CAPITAL LETTER G WITH BREVE - 0x011f: 0xbb, # LATIN SMALL LETTER G WITH BREVE - 0x0120: 0xd5, # LATIN CAPITAL LETTER G WITH DOT ABOVE - 0x0121: 0xf5, # LATIN SMALL LETTER G WITH DOT ABOVE - 0x0124: 0xa6, # LATIN CAPITAL LETTER H WITH CIRCUMFLEX - 0x0125: 0xb6, # LATIN SMALL LETTER H WITH CIRCUMFLEX - 0x0126: 0xa1, # LATIN CAPITAL LETTER H WITH STROKE - 0x0127: 0xb1, # LATIN SMALL LETTER H WITH STROKE - 0x0130: 0xa9, # LATIN CAPITAL LETTER I WITH DOT ABOVE - 0x0131: 0xb9, # LATIN SMALL LETTER DOTLESS I - 0x0134: 0xac, # LATIN CAPITAL LETTER J WITH CIRCUMFLEX - 0x0135: 0xbc, # LATIN SMALL LETTER J WITH CIRCUMFLEX - 0x015c: 0xde, # LATIN CAPITAL LETTER S WITH CIRCUMFLEX - 0x015d: 0xfe, # LATIN SMALL LETTER S WITH CIRCUMFLEX - 0x015e: 0xaa, # LATIN CAPITAL LETTER S WITH CEDILLA - 0x015f: 0xba, # LATIN SMALL LETTER S WITH CEDILLA - 0x016c: 0xdd, # LATIN CAPITAL LETTER U WITH BREVE - 0x016d: 0xfd, # LATIN SMALL LETTER U WITH BREVE - 0x017b: 0xaf, # LATIN CAPITAL LETTER Z WITH DOT ABOVE - 0x017c: 0xbf, # LATIN SMALL LETTER Z WITH DOT ABOVE - 0x02d8: 0xa2, # BREVE - 0x02d9: 0xff, # DOT ABOVE -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0108: 0xC6, # LATIN CAPITAL LETTER C WITH CIRCUMFLEX + 0x0109: 0xE6, # LATIN SMALL LETTER C WITH CIRCUMFLEX + 0x010A: 0xC5, # LATIN CAPITAL LETTER C WITH DOT ABOVE + 0x010B: 0xE5, # LATIN SMALL LETTER C WITH DOT ABOVE + 0x011C: 0xD8, # LATIN CAPITAL LETTER G WITH CIRCUMFLEX + 0x011D: 0xF8, # LATIN SMALL LETTER G WITH CIRCUMFLEX + 0x011E: 0xAB, # LATIN CAPITAL LETTER G WITH BREVE + 0x011F: 0xBB, # LATIN SMALL LETTER G WITH BREVE + 0x0120: 0xD5, # LATIN CAPITAL LETTER G WITH DOT ABOVE + 0x0121: 0xF5, # LATIN SMALL LETTER G WITH DOT ABOVE + 0x0124: 0xA6, # LATIN CAPITAL LETTER H WITH CIRCUMFLEX + 0x0125: 0xB6, # LATIN SMALL LETTER H WITH CIRCUMFLEX + 0x0126: 0xA1, # LATIN CAPITAL LETTER H WITH STROKE + 0x0127: 0xB1, # LATIN SMALL LETTER H WITH STROKE + 0x0130: 0xA9, # LATIN CAPITAL LETTER I WITH DOT ABOVE + 0x0131: 0xB9, # LATIN SMALL LETTER DOTLESS I + 0x0134: 0xAC, # LATIN CAPITAL LETTER J WITH CIRCUMFLEX + 0x0135: 0xBC, # LATIN SMALL LETTER J WITH CIRCUMFLEX + 0x015C: 0xDE, # LATIN CAPITAL LETTER S WITH CIRCUMFLEX + 0x015D: 0xFE, # LATIN SMALL LETTER S WITH CIRCUMFLEX + 0x015E: 0xAA, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015F: 0xBA, # LATIN SMALL LETTER S WITH CEDILLA + 0x016C: 0xDD, # LATIN CAPITAL LETTER U WITH BREVE + 0x016D: 0xFD, # LATIN SMALL LETTER U WITH BREVE + 0x017B: 0xAF, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017C: 0xBF, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x02D8: 0xA2, # BREVE + 0x02D9: 0xFF, # DOT ABOVE +} + diff --git a/Lib/encodings/iso8859_4.py b/Lib/encodings/iso8859_4.py index 224d588..96b7d9c 100644 --- a/Lib/encodings/iso8859_4.py +++ b/Lib/encodings/iso8859_4.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0104' # 0xa1 -> LATIN CAPITAL LETTER A WITH OGONEK - u'\u0138' # 0xa2 -> LATIN SMALL LETTER KRA - u'\u0156' # 0xa3 -> LATIN CAPITAL LETTER R WITH CEDILLA - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\u0128' # 0xa5 -> LATIN CAPITAL LETTER I WITH TILDE - u'\u013b' # 0xa6 -> LATIN CAPITAL LETTER L WITH CEDILLA - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\u0160' # 0xa9 -> LATIN CAPITAL LETTER S WITH CARON - u'\u0112' # 0xaa -> LATIN CAPITAL LETTER E WITH MACRON - u'\u0122' # 0xab -> LATIN CAPITAL LETTER G WITH CEDILLA - u'\u0166' # 0xac -> LATIN CAPITAL LETTER T WITH STROKE - u'\xad' # 0xad -> SOFT HYPHEN - u'\u017d' # 0xae -> LATIN CAPITAL LETTER Z WITH CARON - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\u0105' # 0xb1 -> LATIN SMALL LETTER A WITH OGONEK - u'\u02db' # 0xb2 -> OGONEK - u'\u0157' # 0xb3 -> LATIN SMALL LETTER R WITH CEDILLA - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\u0129' # 0xb5 -> LATIN SMALL LETTER I WITH TILDE - u'\u013c' # 0xb6 -> LATIN SMALL LETTER L WITH CEDILLA - u'\u02c7' # 0xb7 -> CARON - u'\xb8' # 0xb8 -> CEDILLA - u'\u0161' # 0xb9 -> LATIN SMALL LETTER S WITH CARON - u'\u0113' # 0xba -> LATIN SMALL LETTER E WITH MACRON - u'\u0123' # 0xbb -> LATIN SMALL LETTER G WITH CEDILLA - u'\u0167' # 0xbc -> LATIN SMALL LETTER T WITH STROKE - u'\u014a' # 0xbd -> LATIN CAPITAL LETTER ENG - u'\u017e' # 0xbe -> LATIN SMALL LETTER Z WITH CARON - u'\u014b' # 0xbf -> LATIN SMALL LETTER ENG - u'\u0100' # 0xc0 -> LATIN CAPITAL LETTER A WITH MACRON - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\u012e' # 0xc7 -> LATIN CAPITAL LETTER I WITH OGONEK - u'\u010c' # 0xc8 -> LATIN CAPITAL LETTER C WITH CARON - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\u0118' # 0xca -> LATIN CAPITAL LETTER E WITH OGONEK - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\u0116' # 0xcc -> LATIN CAPITAL LETTER E WITH DOT ABOVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\u012a' # 0xcf -> LATIN CAPITAL LETTER I WITH MACRON - u'\u0110' # 0xd0 -> LATIN CAPITAL LETTER D WITH STROKE - u'\u0145' # 0xd1 -> LATIN CAPITAL LETTER N WITH CEDILLA - u'\u014c' # 0xd2 -> LATIN CAPITAL LETTER O WITH MACRON - u'\u0136' # 0xd3 -> LATIN CAPITAL LETTER K WITH CEDILLA - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\u0172' # 0xd9 -> LATIN CAPITAL LETTER U WITH OGONEK - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u0168' # 0xdd -> LATIN CAPITAL LETTER U WITH TILDE - u'\u016a' # 0xde -> LATIN CAPITAL LETTER U WITH MACRON - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\u0101' # 0xe0 -> LATIN SMALL LETTER A WITH MACRON - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\u012f' # 0xe7 -> LATIN SMALL LETTER I WITH OGONEK - u'\u010d' # 0xe8 -> LATIN SMALL LETTER C WITH CARON - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\u0119' # 0xea -> LATIN SMALL LETTER E WITH OGONEK - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\u0117' # 0xec -> LATIN SMALL LETTER E WITH DOT ABOVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\u012b' # 0xef -> LATIN SMALL LETTER I WITH MACRON - u'\u0111' # 0xf0 -> LATIN SMALL LETTER D WITH STROKE - u'\u0146' # 0xf1 -> LATIN SMALL LETTER N WITH CEDILLA - u'\u014d' # 0xf2 -> LATIN SMALL LETTER O WITH MACRON - u'\u0137' # 0xf3 -> LATIN SMALL LETTER K WITH CEDILLA - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\u0173' # 0xf9 -> LATIN SMALL LETTER U WITH OGONEK - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u0169' # 0xfd -> LATIN SMALL LETTER U WITH TILDE - u'\u016b' # 0xfe -> LATIN SMALL LETTER U WITH MACRON - u'\u02d9' # 0xff -> DOT ABOVE + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + u'\u0138' # 0xA2 -> LATIN SMALL LETTER KRA + u'\u0156' # 0xA3 -> LATIN CAPITAL LETTER R WITH CEDILLA + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE + u'\u013b' # 0xA6 -> LATIN CAPITAL LETTER L WITH CEDILLA + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON + u'\u0112' # 0xAA -> LATIN CAPITAL LETTER E WITH MACRON + u'\u0122' # 0xAB -> LATIN CAPITAL LETTER G WITH CEDILLA + u'\u0166' # 0xAC -> LATIN CAPITAL LETTER T WITH STROKE + u'\xad' # 0xAD -> SOFT HYPHEN + u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK + u'\u02db' # 0xB2 -> OGONEK + u'\u0157' # 0xB3 -> LATIN SMALL LETTER R WITH CEDILLA + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE + u'\u013c' # 0xB6 -> LATIN SMALL LETTER L WITH CEDILLA + u'\u02c7' # 0xB7 -> CARON + u'\xb8' # 0xB8 -> CEDILLA + u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON + u'\u0113' # 0xBA -> LATIN SMALL LETTER E WITH MACRON + u'\u0123' # 0xBB -> LATIN SMALL LETTER G WITH CEDILLA + u'\u0167' # 0xBC -> LATIN SMALL LETTER T WITH STROKE + u'\u014a' # 0xBD -> LATIN CAPITAL LETTER ENG + u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON + u'\u014b' # 0xBF -> LATIN SMALL LETTER ENG + u'\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK + u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\u012a' # 0xCF -> LATIN CAPITAL LETTER I WITH MACRON + u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + u'\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA + u'\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON + u'\u0136' # 0xD3 -> LATIN CAPITAL LETTER K WITH CEDILLA + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u0168' # 0xDD -> LATIN CAPITAL LETTER U WITH TILDE + u'\u016a' # 0xDE -> LATIN CAPITAL LETTER U WITH MACRON + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK + u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\u012b' # 0xEF -> LATIN SMALL LETTER I WITH MACRON + u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + u'\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA + u'\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON + u'\u0137' # 0xF3 -> LATIN SMALL LETTER K WITH CEDILLA + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u0169' # 0xFD -> LATIN SMALL LETTER U WITH TILDE + u'\u016b' # 0xFE -> LATIN SMALL LETTER U WITH MACRON + u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00ad: 0xad, # SOFT HYPHEN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b8: 0xb8, # CEDILLA - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x0100: 0xc0, # LATIN CAPITAL LETTER A WITH MACRON - 0x0101: 0xe0, # LATIN SMALL LETTER A WITH MACRON - 0x0104: 0xa1, # LATIN CAPITAL LETTER A WITH OGONEK - 0x0105: 0xb1, # LATIN SMALL LETTER A WITH OGONEK - 0x010c: 0xc8, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xe8, # LATIN SMALL LETTER C WITH CARON - 0x0110: 0xd0, # LATIN CAPITAL LETTER D WITH STROKE - 0x0111: 0xf0, # LATIN SMALL LETTER D WITH STROKE - 0x0112: 0xaa, # LATIN CAPITAL LETTER E WITH MACRON - 0x0113: 0xba, # LATIN SMALL LETTER E WITH MACRON - 0x0116: 0xcc, # LATIN CAPITAL LETTER E WITH DOT ABOVE - 0x0117: 0xec, # LATIN SMALL LETTER E WITH DOT ABOVE - 0x0118: 0xca, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xea, # LATIN SMALL LETTER E WITH OGONEK - 0x0122: 0xab, # LATIN CAPITAL LETTER G WITH CEDILLA - 0x0123: 0xbb, # LATIN SMALL LETTER G WITH CEDILLA - 0x0128: 0xa5, # LATIN CAPITAL LETTER I WITH TILDE - 0x0129: 0xb5, # LATIN SMALL LETTER I WITH TILDE - 0x012a: 0xcf, # LATIN CAPITAL LETTER I WITH MACRON - 0x012b: 0xef, # LATIN SMALL LETTER I WITH MACRON - 0x012e: 0xc7, # LATIN CAPITAL LETTER I WITH OGONEK - 0x012f: 0xe7, # LATIN SMALL LETTER I WITH OGONEK - 0x0136: 0xd3, # LATIN CAPITAL LETTER K WITH CEDILLA - 0x0137: 0xf3, # LATIN SMALL LETTER K WITH CEDILLA - 0x0138: 0xa2, # LATIN SMALL LETTER KRA - 0x013b: 0xa6, # LATIN CAPITAL LETTER L WITH CEDILLA - 0x013c: 0xb6, # LATIN SMALL LETTER L WITH CEDILLA - 0x0145: 0xd1, # LATIN CAPITAL LETTER N WITH CEDILLA - 0x0146: 0xf1, # LATIN SMALL LETTER N WITH CEDILLA - 0x014a: 0xbd, # LATIN CAPITAL LETTER ENG - 0x014b: 0xbf, # LATIN SMALL LETTER ENG - 0x014c: 0xd2, # LATIN CAPITAL LETTER O WITH MACRON - 0x014d: 0xf2, # LATIN SMALL LETTER O WITH MACRON - 0x0156: 0xa3, # LATIN CAPITAL LETTER R WITH CEDILLA - 0x0157: 0xb3, # LATIN SMALL LETTER R WITH CEDILLA - 0x0160: 0xa9, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xb9, # LATIN SMALL LETTER S WITH CARON - 0x0166: 0xac, # LATIN CAPITAL LETTER T WITH STROKE - 0x0167: 0xbc, # LATIN SMALL LETTER T WITH STROKE - 0x0168: 0xdd, # LATIN CAPITAL LETTER U WITH TILDE - 0x0169: 0xfd, # LATIN SMALL LETTER U WITH TILDE - 0x016a: 0xde, # LATIN CAPITAL LETTER U WITH MACRON - 0x016b: 0xfe, # LATIN SMALL LETTER U WITH MACRON - 0x0172: 0xd9, # LATIN CAPITAL LETTER U WITH OGONEK - 0x0173: 0xf9, # LATIN SMALL LETTER U WITH OGONEK - 0x017d: 0xae, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xbe, # LATIN SMALL LETTER Z WITH CARON - 0x02c7: 0xb7, # CARON - 0x02d9: 0xff, # DOT ABOVE - 0x02db: 0xb2, # OGONEK -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B8: 0xB8, # CEDILLA + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0100: 0xC0, # LATIN CAPITAL LETTER A WITH MACRON + 0x0101: 0xE0, # LATIN SMALL LETTER A WITH MACRON + 0x0104: 0xA1, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0xB1, # LATIN SMALL LETTER A WITH OGONEK + 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON + 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE + 0x0112: 0xAA, # LATIN CAPITAL LETTER E WITH MACRON + 0x0113: 0xBA, # LATIN SMALL LETTER E WITH MACRON + 0x0116: 0xCC, # LATIN CAPITAL LETTER E WITH DOT ABOVE + 0x0117: 0xEC, # LATIN SMALL LETTER E WITH DOT ABOVE + 0x0118: 0xCA, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xEA, # LATIN SMALL LETTER E WITH OGONEK + 0x0122: 0xAB, # LATIN CAPITAL LETTER G WITH CEDILLA + 0x0123: 0xBB, # LATIN SMALL LETTER G WITH CEDILLA + 0x0128: 0xA5, # LATIN CAPITAL LETTER I WITH TILDE + 0x0129: 0xB5, # LATIN SMALL LETTER I WITH TILDE + 0x012A: 0xCF, # LATIN CAPITAL LETTER I WITH MACRON + 0x012B: 0xEF, # LATIN SMALL LETTER I WITH MACRON + 0x012E: 0xC7, # LATIN CAPITAL LETTER I WITH OGONEK + 0x012F: 0xE7, # LATIN SMALL LETTER I WITH OGONEK + 0x0136: 0xD3, # LATIN CAPITAL LETTER K WITH CEDILLA + 0x0137: 0xF3, # LATIN SMALL LETTER K WITH CEDILLA + 0x0138: 0xA2, # LATIN SMALL LETTER KRA + 0x013B: 0xA6, # LATIN CAPITAL LETTER L WITH CEDILLA + 0x013C: 0xB6, # LATIN SMALL LETTER L WITH CEDILLA + 0x0145: 0xD1, # LATIN CAPITAL LETTER N WITH CEDILLA + 0x0146: 0xF1, # LATIN SMALL LETTER N WITH CEDILLA + 0x014A: 0xBD, # LATIN CAPITAL LETTER ENG + 0x014B: 0xBF, # LATIN SMALL LETTER ENG + 0x014C: 0xD2, # LATIN CAPITAL LETTER O WITH MACRON + 0x014D: 0xF2, # LATIN SMALL LETTER O WITH MACRON + 0x0156: 0xA3, # LATIN CAPITAL LETTER R WITH CEDILLA + 0x0157: 0xB3, # LATIN SMALL LETTER R WITH CEDILLA + 0x0160: 0xA9, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xB9, # LATIN SMALL LETTER S WITH CARON + 0x0166: 0xAC, # LATIN CAPITAL LETTER T WITH STROKE + 0x0167: 0xBC, # LATIN SMALL LETTER T WITH STROKE + 0x0168: 0xDD, # LATIN CAPITAL LETTER U WITH TILDE + 0x0169: 0xFD, # LATIN SMALL LETTER U WITH TILDE + 0x016A: 0xDE, # LATIN CAPITAL LETTER U WITH MACRON + 0x016B: 0xFE, # LATIN SMALL LETTER U WITH MACRON + 0x0172: 0xD9, # LATIN CAPITAL LETTER U WITH OGONEK + 0x0173: 0xF9, # LATIN SMALL LETTER U WITH OGONEK + 0x017D: 0xAE, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xBE, # LATIN SMALL LETTER Z WITH CARON + 0x02C7: 0xB7, # CARON + 0x02D9: 0xFF, # DOT ABOVE + 0x02DB: 0xB2, # OGONEK +} + diff --git a/Lib/encodings/iso8859_5.py b/Lib/encodings/iso8859_5.py index f881993..8db4314 100644 --- a/Lib/encodings/iso8859_5.py +++ b/Lib/encodings/iso8859_5.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u0401' # 0xa1 -> CYRILLIC CAPITAL LETTER IO - u'\u0402' # 0xa2 -> CYRILLIC CAPITAL LETTER DJE - u'\u0403' # 0xa3 -> CYRILLIC CAPITAL LETTER GJE - u'\u0404' # 0xa4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE - u'\u0405' # 0xa5 -> CYRILLIC CAPITAL LETTER DZE - u'\u0406' # 0xa6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - u'\u0407' # 0xa7 -> CYRILLIC CAPITAL LETTER YI - u'\u0408' # 0xa8 -> CYRILLIC CAPITAL LETTER JE - u'\u0409' # 0xa9 -> CYRILLIC CAPITAL LETTER LJE - u'\u040a' # 0xaa -> CYRILLIC CAPITAL LETTER NJE - u'\u040b' # 0xab -> CYRILLIC CAPITAL LETTER TSHE - u'\u040c' # 0xac -> CYRILLIC CAPITAL LETTER KJE - u'\xad' # 0xad -> SOFT HYPHEN - u'\u040e' # 0xae -> CYRILLIC CAPITAL LETTER SHORT U - u'\u040f' # 0xaf -> CYRILLIC CAPITAL LETTER DZHE - u'\u0410' # 0xb0 -> CYRILLIC CAPITAL LETTER A - u'\u0411' # 0xb1 -> CYRILLIC CAPITAL LETTER BE - u'\u0412' # 0xb2 -> CYRILLIC CAPITAL LETTER VE - u'\u0413' # 0xb3 -> CYRILLIC CAPITAL LETTER GHE - u'\u0414' # 0xb4 -> CYRILLIC CAPITAL LETTER DE - u'\u0415' # 0xb5 -> CYRILLIC CAPITAL LETTER IE - u'\u0416' # 0xb6 -> CYRILLIC CAPITAL LETTER ZHE - u'\u0417' # 0xb7 -> CYRILLIC CAPITAL LETTER ZE - u'\u0418' # 0xb8 -> CYRILLIC CAPITAL LETTER I - u'\u0419' # 0xb9 -> CYRILLIC CAPITAL LETTER SHORT I - u'\u041a' # 0xba -> CYRILLIC CAPITAL LETTER KA - u'\u041b' # 0xbb -> CYRILLIC CAPITAL LETTER EL - u'\u041c' # 0xbc -> CYRILLIC CAPITAL LETTER EM - u'\u041d' # 0xbd -> CYRILLIC CAPITAL LETTER EN - u'\u041e' # 0xbe -> CYRILLIC CAPITAL LETTER O - u'\u041f' # 0xbf -> CYRILLIC CAPITAL LETTER PE - u'\u0420' # 0xc0 -> CYRILLIC CAPITAL LETTER ER - u'\u0421' # 0xc1 -> CYRILLIC CAPITAL LETTER ES - u'\u0422' # 0xc2 -> CYRILLIC CAPITAL LETTER TE - u'\u0423' # 0xc3 -> CYRILLIC CAPITAL LETTER U - u'\u0424' # 0xc4 -> CYRILLIC CAPITAL LETTER EF - u'\u0425' # 0xc5 -> CYRILLIC CAPITAL LETTER HA - u'\u0426' # 0xc6 -> CYRILLIC CAPITAL LETTER TSE - u'\u0427' # 0xc7 -> CYRILLIC CAPITAL LETTER CHE - u'\u0428' # 0xc8 -> CYRILLIC CAPITAL LETTER SHA - u'\u0429' # 0xc9 -> CYRILLIC CAPITAL LETTER SHCHA - u'\u042a' # 0xca -> CYRILLIC CAPITAL LETTER HARD SIGN - u'\u042b' # 0xcb -> CYRILLIC CAPITAL LETTER YERU - u'\u042c' # 0xcc -> CYRILLIC CAPITAL LETTER SOFT SIGN - u'\u042d' # 0xcd -> CYRILLIC CAPITAL LETTER E - u'\u042e' # 0xce -> CYRILLIC CAPITAL LETTER YU - u'\u042f' # 0xcf -> CYRILLIC CAPITAL LETTER YA - u'\u0430' # 0xd0 -> CYRILLIC SMALL LETTER A - u'\u0431' # 0xd1 -> CYRILLIC SMALL LETTER BE - u'\u0432' # 0xd2 -> CYRILLIC SMALL LETTER VE - u'\u0433' # 0xd3 -> CYRILLIC SMALL LETTER GHE - u'\u0434' # 0xd4 -> CYRILLIC SMALL LETTER DE - u'\u0435' # 0xd5 -> CYRILLIC SMALL LETTER IE - u'\u0436' # 0xd6 -> CYRILLIC SMALL LETTER ZHE - u'\u0437' # 0xd7 -> CYRILLIC SMALL LETTER ZE - u'\u0438' # 0xd8 -> CYRILLIC SMALL LETTER I - u'\u0439' # 0xd9 -> CYRILLIC SMALL LETTER SHORT I - u'\u043a' # 0xda -> CYRILLIC SMALL LETTER KA - u'\u043b' # 0xdb -> CYRILLIC SMALL LETTER EL - u'\u043c' # 0xdc -> CYRILLIC SMALL LETTER EM - u'\u043d' # 0xdd -> CYRILLIC SMALL LETTER EN - u'\u043e' # 0xde -> CYRILLIC SMALL LETTER O - u'\u043f' # 0xdf -> CYRILLIC SMALL LETTER PE - u'\u0440' # 0xe0 -> CYRILLIC SMALL LETTER ER - u'\u0441' # 0xe1 -> CYRILLIC SMALL LETTER ES - u'\u0442' # 0xe2 -> CYRILLIC SMALL LETTER TE - u'\u0443' # 0xe3 -> CYRILLIC SMALL LETTER U - u'\u0444' # 0xe4 -> CYRILLIC SMALL LETTER EF - u'\u0445' # 0xe5 -> CYRILLIC SMALL LETTER HA - u'\u0446' # 0xe6 -> CYRILLIC SMALL LETTER TSE - u'\u0447' # 0xe7 -> CYRILLIC SMALL LETTER CHE - u'\u0448' # 0xe8 -> CYRILLIC SMALL LETTER SHA - u'\u0449' # 0xe9 -> CYRILLIC SMALL LETTER SHCHA - u'\u044a' # 0xea -> CYRILLIC SMALL LETTER HARD SIGN - u'\u044b' # 0xeb -> CYRILLIC SMALL LETTER YERU - u'\u044c' # 0xec -> CYRILLIC SMALL LETTER SOFT SIGN - u'\u044d' # 0xed -> CYRILLIC SMALL LETTER E - u'\u044e' # 0xee -> CYRILLIC SMALL LETTER YU - u'\u044f' # 0xef -> CYRILLIC SMALL LETTER YA - u'\u2116' # 0xf0 -> NUMERO SIGN - u'\u0451' # 0xf1 -> CYRILLIC SMALL LETTER IO - u'\u0452' # 0xf2 -> CYRILLIC SMALL LETTER DJE - u'\u0453' # 0xf3 -> CYRILLIC SMALL LETTER GJE - u'\u0454' # 0xf4 -> CYRILLIC SMALL LETTER UKRAINIAN IE - u'\u0455' # 0xf5 -> CYRILLIC SMALL LETTER DZE - u'\u0456' # 0xf6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - u'\u0457' # 0xf7 -> CYRILLIC SMALL LETTER YI - u'\u0458' # 0xf8 -> CYRILLIC SMALL LETTER JE - u'\u0459' # 0xf9 -> CYRILLIC SMALL LETTER LJE - u'\u045a' # 0xfa -> CYRILLIC SMALL LETTER NJE - u'\u045b' # 0xfb -> CYRILLIC SMALL LETTER TSHE - u'\u045c' # 0xfc -> CYRILLIC SMALL LETTER KJE - u'\xa7' # 0xfd -> SECTION SIGN - u'\u045e' # 0xfe -> CYRILLIC SMALL LETTER SHORT U - u'\u045f' # 0xff -> CYRILLIC SMALL LETTER DZHE + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u0401' # 0xA1 -> CYRILLIC CAPITAL LETTER IO + u'\u0402' # 0xA2 -> CYRILLIC CAPITAL LETTER DJE + u'\u0403' # 0xA3 -> CYRILLIC CAPITAL LETTER GJE + u'\u0404' # 0xA4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + u'\u0405' # 0xA5 -> CYRILLIC CAPITAL LETTER DZE + u'\u0406' # 0xA6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + u'\u0407' # 0xA7 -> CYRILLIC CAPITAL LETTER YI + u'\u0408' # 0xA8 -> CYRILLIC CAPITAL LETTER JE + u'\u0409' # 0xA9 -> CYRILLIC CAPITAL LETTER LJE + u'\u040a' # 0xAA -> CYRILLIC CAPITAL LETTER NJE + u'\u040b' # 0xAB -> CYRILLIC CAPITAL LETTER TSHE + u'\u040c' # 0xAC -> CYRILLIC CAPITAL LETTER KJE + u'\xad' # 0xAD -> SOFT HYPHEN + u'\u040e' # 0xAE -> CYRILLIC CAPITAL LETTER SHORT U + u'\u040f' # 0xAF -> CYRILLIC CAPITAL LETTER DZHE + u'\u0410' # 0xB0 -> CYRILLIC CAPITAL LETTER A + u'\u0411' # 0xB1 -> CYRILLIC CAPITAL LETTER BE + u'\u0412' # 0xB2 -> CYRILLIC CAPITAL LETTER VE + u'\u0413' # 0xB3 -> CYRILLIC CAPITAL LETTER GHE + u'\u0414' # 0xB4 -> CYRILLIC CAPITAL LETTER DE + u'\u0415' # 0xB5 -> CYRILLIC CAPITAL LETTER IE + u'\u0416' # 0xB6 -> CYRILLIC CAPITAL LETTER ZHE + u'\u0417' # 0xB7 -> CYRILLIC CAPITAL LETTER ZE + u'\u0418' # 0xB8 -> CYRILLIC CAPITAL LETTER I + u'\u0419' # 0xB9 -> CYRILLIC CAPITAL LETTER SHORT I + u'\u041a' # 0xBA -> CYRILLIC CAPITAL LETTER KA + u'\u041b' # 0xBB -> CYRILLIC CAPITAL LETTER EL + u'\u041c' # 0xBC -> CYRILLIC CAPITAL LETTER EM + u'\u041d' # 0xBD -> CYRILLIC CAPITAL LETTER EN + u'\u041e' # 0xBE -> CYRILLIC CAPITAL LETTER O + u'\u041f' # 0xBF -> CYRILLIC CAPITAL LETTER PE + u'\u0420' # 0xC0 -> CYRILLIC CAPITAL LETTER ER + u'\u0421' # 0xC1 -> CYRILLIC CAPITAL LETTER ES + u'\u0422' # 0xC2 -> CYRILLIC CAPITAL LETTER TE + u'\u0423' # 0xC3 -> CYRILLIC CAPITAL LETTER U + u'\u0424' # 0xC4 -> CYRILLIC CAPITAL LETTER EF + u'\u0425' # 0xC5 -> CYRILLIC CAPITAL LETTER HA + u'\u0426' # 0xC6 -> CYRILLIC CAPITAL LETTER TSE + u'\u0427' # 0xC7 -> CYRILLIC CAPITAL LETTER CHE + u'\u0428' # 0xC8 -> CYRILLIC CAPITAL LETTER SHA + u'\u0429' # 0xC9 -> CYRILLIC CAPITAL LETTER SHCHA + u'\u042a' # 0xCA -> CYRILLIC CAPITAL LETTER HARD SIGN + u'\u042b' # 0xCB -> CYRILLIC CAPITAL LETTER YERU + u'\u042c' # 0xCC -> CYRILLIC CAPITAL LETTER SOFT SIGN + u'\u042d' # 0xCD -> CYRILLIC CAPITAL LETTER E + u'\u042e' # 0xCE -> CYRILLIC CAPITAL LETTER YU + u'\u042f' # 0xCF -> CYRILLIC CAPITAL LETTER YA + u'\u0430' # 0xD0 -> CYRILLIC SMALL LETTER A + u'\u0431' # 0xD1 -> CYRILLIC SMALL LETTER BE + u'\u0432' # 0xD2 -> CYRILLIC SMALL LETTER VE + u'\u0433' # 0xD3 -> CYRILLIC SMALL LETTER GHE + u'\u0434' # 0xD4 -> CYRILLIC SMALL LETTER DE + u'\u0435' # 0xD5 -> CYRILLIC SMALL LETTER IE + u'\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE + u'\u0437' # 0xD7 -> CYRILLIC SMALL LETTER ZE + u'\u0438' # 0xD8 -> CYRILLIC SMALL LETTER I + u'\u0439' # 0xD9 -> CYRILLIC SMALL LETTER SHORT I + u'\u043a' # 0xDA -> CYRILLIC SMALL LETTER KA + u'\u043b' # 0xDB -> CYRILLIC SMALL LETTER EL + u'\u043c' # 0xDC -> CYRILLIC SMALL LETTER EM + u'\u043d' # 0xDD -> CYRILLIC SMALL LETTER EN + u'\u043e' # 0xDE -> CYRILLIC SMALL LETTER O + u'\u043f' # 0xDF -> CYRILLIC SMALL LETTER PE + u'\u0440' # 0xE0 -> CYRILLIC SMALL LETTER ER + u'\u0441' # 0xE1 -> CYRILLIC SMALL LETTER ES + u'\u0442' # 0xE2 -> CYRILLIC SMALL LETTER TE + u'\u0443' # 0xE3 -> CYRILLIC SMALL LETTER U + u'\u0444' # 0xE4 -> CYRILLIC SMALL LETTER EF + u'\u0445' # 0xE5 -> CYRILLIC SMALL LETTER HA + u'\u0446' # 0xE6 -> CYRILLIC SMALL LETTER TSE + u'\u0447' # 0xE7 -> CYRILLIC SMALL LETTER CHE + u'\u0448' # 0xE8 -> CYRILLIC SMALL LETTER SHA + u'\u0449' # 0xE9 -> CYRILLIC SMALL LETTER SHCHA + u'\u044a' # 0xEA -> CYRILLIC SMALL LETTER HARD SIGN + u'\u044b' # 0xEB -> CYRILLIC SMALL LETTER YERU + u'\u044c' # 0xEC -> CYRILLIC SMALL LETTER SOFT SIGN + u'\u044d' # 0xED -> CYRILLIC SMALL LETTER E + u'\u044e' # 0xEE -> CYRILLIC SMALL LETTER YU + u'\u044f' # 0xEF -> CYRILLIC SMALL LETTER YA + u'\u2116' # 0xF0 -> NUMERO SIGN + u'\u0451' # 0xF1 -> CYRILLIC SMALL LETTER IO + u'\u0452' # 0xF2 -> CYRILLIC SMALL LETTER DJE + u'\u0453' # 0xF3 -> CYRILLIC SMALL LETTER GJE + u'\u0454' # 0xF4 -> CYRILLIC SMALL LETTER UKRAINIAN IE + u'\u0455' # 0xF5 -> CYRILLIC SMALL LETTER DZE + u'\u0456' # 0xF6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + u'\u0457' # 0xF7 -> CYRILLIC SMALL LETTER YI + u'\u0458' # 0xF8 -> CYRILLIC SMALL LETTER JE + u'\u0459' # 0xF9 -> CYRILLIC SMALL LETTER LJE + u'\u045a' # 0xFA -> CYRILLIC SMALL LETTER NJE + u'\u045b' # 0xFB -> CYRILLIC SMALL LETTER TSHE + u'\u045c' # 0xFC -> CYRILLIC SMALL LETTER KJE + u'\xa7' # 0xFD -> SECTION SIGN + u'\u045e' # 0xFE -> CYRILLIC SMALL LETTER SHORT U + u'\u045f' # 0xFF -> CYRILLIC SMALL LETTER DZHE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a7: 0xfd, # SECTION SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x0401: 0xa1, # CYRILLIC CAPITAL LETTER IO - 0x0402: 0xa2, # CYRILLIC CAPITAL LETTER DJE - 0x0403: 0xa3, # CYRILLIC CAPITAL LETTER GJE - 0x0404: 0xa4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE - 0x0405: 0xa5, # CYRILLIC CAPITAL LETTER DZE - 0x0406: 0xa6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0407: 0xa7, # CYRILLIC CAPITAL LETTER YI - 0x0408: 0xa8, # CYRILLIC CAPITAL LETTER JE - 0x0409: 0xa9, # CYRILLIC CAPITAL LETTER LJE - 0x040a: 0xaa, # CYRILLIC CAPITAL LETTER NJE - 0x040b: 0xab, # CYRILLIC CAPITAL LETTER TSHE - 0x040c: 0xac, # CYRILLIC CAPITAL LETTER KJE - 0x040e: 0xae, # CYRILLIC CAPITAL LETTER SHORT U - 0x040f: 0xaf, # CYRILLIC CAPITAL LETTER DZHE - 0x0410: 0xb0, # CYRILLIC CAPITAL LETTER A - 0x0411: 0xb1, # CYRILLIC CAPITAL LETTER BE - 0x0412: 0xb2, # CYRILLIC CAPITAL LETTER VE - 0x0413: 0xb3, # CYRILLIC CAPITAL LETTER GHE - 0x0414: 0xb4, # CYRILLIC CAPITAL LETTER DE - 0x0415: 0xb5, # CYRILLIC CAPITAL LETTER IE - 0x0416: 0xb6, # CYRILLIC CAPITAL LETTER ZHE - 0x0417: 0xb7, # CYRILLIC CAPITAL LETTER ZE - 0x0418: 0xb8, # CYRILLIC CAPITAL LETTER I - 0x0419: 0xb9, # CYRILLIC CAPITAL LETTER SHORT I - 0x041a: 0xba, # CYRILLIC CAPITAL LETTER KA - 0x041b: 0xbb, # CYRILLIC CAPITAL LETTER EL - 0x041c: 0xbc, # CYRILLIC CAPITAL LETTER EM - 0x041d: 0xbd, # CYRILLIC CAPITAL LETTER EN - 0x041e: 0xbe, # CYRILLIC CAPITAL LETTER O - 0x041f: 0xbf, # CYRILLIC CAPITAL LETTER PE - 0x0420: 0xc0, # CYRILLIC CAPITAL LETTER ER - 0x0421: 0xc1, # CYRILLIC CAPITAL LETTER ES - 0x0422: 0xc2, # CYRILLIC CAPITAL LETTER TE - 0x0423: 0xc3, # CYRILLIC CAPITAL LETTER U - 0x0424: 0xc4, # CYRILLIC CAPITAL LETTER EF - 0x0425: 0xc5, # CYRILLIC CAPITAL LETTER HA - 0x0426: 0xc6, # CYRILLIC CAPITAL LETTER TSE - 0x0427: 0xc7, # CYRILLIC CAPITAL LETTER CHE - 0x0428: 0xc8, # CYRILLIC CAPITAL LETTER SHA - 0x0429: 0xc9, # CYRILLIC CAPITAL LETTER SHCHA - 0x042a: 0xca, # CYRILLIC CAPITAL LETTER HARD SIGN - 0x042b: 0xcb, # CYRILLIC CAPITAL LETTER YERU - 0x042c: 0xcc, # CYRILLIC CAPITAL LETTER SOFT SIGN - 0x042d: 0xcd, # CYRILLIC CAPITAL LETTER E - 0x042e: 0xce, # CYRILLIC CAPITAL LETTER YU - 0x042f: 0xcf, # CYRILLIC CAPITAL LETTER YA - 0x0430: 0xd0, # CYRILLIC SMALL LETTER A - 0x0431: 0xd1, # CYRILLIC SMALL LETTER BE - 0x0432: 0xd2, # CYRILLIC SMALL LETTER VE - 0x0433: 0xd3, # CYRILLIC SMALL LETTER GHE - 0x0434: 0xd4, # CYRILLIC SMALL LETTER DE - 0x0435: 0xd5, # CYRILLIC SMALL LETTER IE - 0x0436: 0xd6, # CYRILLIC SMALL LETTER ZHE - 0x0437: 0xd7, # CYRILLIC SMALL LETTER ZE - 0x0438: 0xd8, # CYRILLIC SMALL LETTER I - 0x0439: 0xd9, # CYRILLIC SMALL LETTER SHORT I - 0x043a: 0xda, # CYRILLIC SMALL LETTER KA - 0x043b: 0xdb, # CYRILLIC SMALL LETTER EL - 0x043c: 0xdc, # CYRILLIC SMALL LETTER EM - 0x043d: 0xdd, # CYRILLIC SMALL LETTER EN - 0x043e: 0xde, # CYRILLIC SMALL LETTER O - 0x043f: 0xdf, # CYRILLIC SMALL LETTER PE - 0x0440: 0xe0, # CYRILLIC SMALL LETTER ER - 0x0441: 0xe1, # CYRILLIC SMALL LETTER ES - 0x0442: 0xe2, # CYRILLIC SMALL LETTER TE - 0x0443: 0xe3, # CYRILLIC SMALL LETTER U - 0x0444: 0xe4, # CYRILLIC SMALL LETTER EF - 0x0445: 0xe5, # CYRILLIC SMALL LETTER HA - 0x0446: 0xe6, # CYRILLIC SMALL LETTER TSE - 0x0447: 0xe7, # CYRILLIC SMALL LETTER CHE - 0x0448: 0xe8, # CYRILLIC SMALL LETTER SHA - 0x0449: 0xe9, # CYRILLIC SMALL LETTER SHCHA - 0x044a: 0xea, # CYRILLIC SMALL LETTER HARD SIGN - 0x044b: 0xeb, # CYRILLIC SMALL LETTER YERU - 0x044c: 0xec, # CYRILLIC SMALL LETTER SOFT SIGN - 0x044d: 0xed, # CYRILLIC SMALL LETTER E - 0x044e: 0xee, # CYRILLIC SMALL LETTER YU - 0x044f: 0xef, # CYRILLIC SMALL LETTER YA - 0x0451: 0xf1, # CYRILLIC SMALL LETTER IO - 0x0452: 0xf2, # CYRILLIC SMALL LETTER DJE - 0x0453: 0xf3, # CYRILLIC SMALL LETTER GJE - 0x0454: 0xf4, # CYRILLIC SMALL LETTER UKRAINIAN IE - 0x0455: 0xf5, # CYRILLIC SMALL LETTER DZE - 0x0456: 0xf6, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0457: 0xf7, # CYRILLIC SMALL LETTER YI - 0x0458: 0xf8, # CYRILLIC SMALL LETTER JE - 0x0459: 0xf9, # CYRILLIC SMALL LETTER LJE - 0x045a: 0xfa, # CYRILLIC SMALL LETTER NJE - 0x045b: 0xfb, # CYRILLIC SMALL LETTER TSHE - 0x045c: 0xfc, # CYRILLIC SMALL LETTER KJE - 0x045e: 0xfe, # CYRILLIC SMALL LETTER SHORT U - 0x045f: 0xff, # CYRILLIC SMALL LETTER DZHE - 0x2116: 0xf0, # NUMERO SIGN -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A7: 0xFD, # SECTION SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x0401: 0xA1, # CYRILLIC CAPITAL LETTER IO + 0x0402: 0xA2, # CYRILLIC CAPITAL LETTER DJE + 0x0403: 0xA3, # CYRILLIC CAPITAL LETTER GJE + 0x0404: 0xA4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0405: 0xA5, # CYRILLIC CAPITAL LETTER DZE + 0x0406: 0xA6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0407: 0xA7, # CYRILLIC CAPITAL LETTER YI + 0x0408: 0xA8, # CYRILLIC CAPITAL LETTER JE + 0x0409: 0xA9, # CYRILLIC CAPITAL LETTER LJE + 0x040A: 0xAA, # CYRILLIC CAPITAL LETTER NJE + 0x040B: 0xAB, # CYRILLIC CAPITAL LETTER TSHE + 0x040C: 0xAC, # CYRILLIC CAPITAL LETTER KJE + 0x040E: 0xAE, # CYRILLIC CAPITAL LETTER SHORT U + 0x040F: 0xAF, # CYRILLIC CAPITAL LETTER DZHE + 0x0410: 0xB0, # CYRILLIC CAPITAL LETTER A + 0x0411: 0xB1, # CYRILLIC CAPITAL LETTER BE + 0x0412: 0xB2, # CYRILLIC CAPITAL LETTER VE + 0x0413: 0xB3, # CYRILLIC CAPITAL LETTER GHE + 0x0414: 0xB4, # CYRILLIC CAPITAL LETTER DE + 0x0415: 0xB5, # CYRILLIC CAPITAL LETTER IE + 0x0416: 0xB6, # CYRILLIC CAPITAL LETTER ZHE + 0x0417: 0xB7, # CYRILLIC CAPITAL LETTER ZE + 0x0418: 0xB8, # CYRILLIC CAPITAL LETTER I + 0x0419: 0xB9, # CYRILLIC CAPITAL LETTER SHORT I + 0x041A: 0xBA, # CYRILLIC CAPITAL LETTER KA + 0x041B: 0xBB, # CYRILLIC CAPITAL LETTER EL + 0x041C: 0xBC, # CYRILLIC CAPITAL LETTER EM + 0x041D: 0xBD, # CYRILLIC CAPITAL LETTER EN + 0x041E: 0xBE, # CYRILLIC CAPITAL LETTER O + 0x041F: 0xBF, # CYRILLIC CAPITAL LETTER PE + 0x0420: 0xC0, # CYRILLIC CAPITAL LETTER ER + 0x0421: 0xC1, # CYRILLIC CAPITAL LETTER ES + 0x0422: 0xC2, # CYRILLIC CAPITAL LETTER TE + 0x0423: 0xC3, # CYRILLIC CAPITAL LETTER U + 0x0424: 0xC4, # CYRILLIC CAPITAL LETTER EF + 0x0425: 0xC5, # CYRILLIC CAPITAL LETTER HA + 0x0426: 0xC6, # CYRILLIC CAPITAL LETTER TSE + 0x0427: 0xC7, # CYRILLIC CAPITAL LETTER CHE + 0x0428: 0xC8, # CYRILLIC CAPITAL LETTER SHA + 0x0429: 0xC9, # CYRILLIC CAPITAL LETTER SHCHA + 0x042A: 0xCA, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042B: 0xCB, # CYRILLIC CAPITAL LETTER YERU + 0x042C: 0xCC, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042D: 0xCD, # CYRILLIC CAPITAL LETTER E + 0x042E: 0xCE, # CYRILLIC CAPITAL LETTER YU + 0x042F: 0xCF, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0xD0, # CYRILLIC SMALL LETTER A + 0x0431: 0xD1, # CYRILLIC SMALL LETTER BE + 0x0432: 0xD2, # CYRILLIC SMALL LETTER VE + 0x0433: 0xD3, # CYRILLIC SMALL LETTER GHE + 0x0434: 0xD4, # CYRILLIC SMALL LETTER DE + 0x0435: 0xD5, # CYRILLIC SMALL LETTER IE + 0x0436: 0xD6, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0xD7, # CYRILLIC SMALL LETTER ZE + 0x0438: 0xD8, # CYRILLIC SMALL LETTER I + 0x0439: 0xD9, # CYRILLIC SMALL LETTER SHORT I + 0x043A: 0xDA, # CYRILLIC SMALL LETTER KA + 0x043B: 0xDB, # CYRILLIC SMALL LETTER EL + 0x043C: 0xDC, # CYRILLIC SMALL LETTER EM + 0x043D: 0xDD, # CYRILLIC SMALL LETTER EN + 0x043E: 0xDE, # CYRILLIC SMALL LETTER O + 0x043F: 0xDF, # CYRILLIC SMALL LETTER PE + 0x0440: 0xE0, # CYRILLIC SMALL LETTER ER + 0x0441: 0xE1, # CYRILLIC SMALL LETTER ES + 0x0442: 0xE2, # CYRILLIC SMALL LETTER TE + 0x0443: 0xE3, # CYRILLIC SMALL LETTER U + 0x0444: 0xE4, # CYRILLIC SMALL LETTER EF + 0x0445: 0xE5, # CYRILLIC SMALL LETTER HA + 0x0446: 0xE6, # CYRILLIC SMALL LETTER TSE + 0x0447: 0xE7, # CYRILLIC SMALL LETTER CHE + 0x0448: 0xE8, # CYRILLIC SMALL LETTER SHA + 0x0449: 0xE9, # CYRILLIC SMALL LETTER SHCHA + 0x044A: 0xEA, # CYRILLIC SMALL LETTER HARD SIGN + 0x044B: 0xEB, # CYRILLIC SMALL LETTER YERU + 0x044C: 0xEC, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044D: 0xED, # CYRILLIC SMALL LETTER E + 0x044E: 0xEE, # CYRILLIC SMALL LETTER YU + 0x044F: 0xEF, # CYRILLIC SMALL LETTER YA + 0x0451: 0xF1, # CYRILLIC SMALL LETTER IO + 0x0452: 0xF2, # CYRILLIC SMALL LETTER DJE + 0x0453: 0xF3, # CYRILLIC SMALL LETTER GJE + 0x0454: 0xF4, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0455: 0xF5, # CYRILLIC SMALL LETTER DZE + 0x0456: 0xF6, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0457: 0xF7, # CYRILLIC SMALL LETTER YI + 0x0458: 0xF8, # CYRILLIC SMALL LETTER JE + 0x0459: 0xF9, # CYRILLIC SMALL LETTER LJE + 0x045A: 0xFA, # CYRILLIC SMALL LETTER NJE + 0x045B: 0xFB, # CYRILLIC SMALL LETTER TSHE + 0x045C: 0xFC, # CYRILLIC SMALL LETTER KJE + 0x045E: 0xFE, # CYRILLIC SMALL LETTER SHORT U + 0x045F: 0xFF, # CYRILLIC SMALL LETTER DZHE + 0x2116: 0xF0, # NUMERO SIGN +} + diff --git a/Lib/encodings/iso8859_6.py b/Lib/encodings/iso8859_6.py index 1e99b1a..feb69c8 100644 --- a/Lib/encodings/iso8859_6.py +++ b/Lib/encodings/iso8859_6.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,17 +186,17 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\ufffe' u'\ufffe' u'\ufffe' - u'\xa4' # 0xa4 -> CURRENCY SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN u'\ufffe' u'\ufffe' u'\ufffe' @@ -204,8 +204,8 @@ decoding_table = ( u'\ufffe' u'\ufffe' u'\ufffe' - u'\u060c' # 0xac -> ARABIC COMMA - u'\xad' # 0xad -> SOFT HYPHEN + u'\u060c' # 0xAC -> ARABIC COMMA + u'\xad' # 0xAD -> SOFT HYPHEN u'\ufffe' u'\ufffe' u'\ufffe' @@ -219,62 +219,62 @@ decoding_table = ( u'\ufffe' u'\ufffe' u'\ufffe' - u'\u061b' # 0xbb -> ARABIC SEMICOLON + u'\u061b' # 0xBB -> ARABIC SEMICOLON u'\ufffe' u'\ufffe' u'\ufffe' - u'\u061f' # 0xbf -> ARABIC QUESTION MARK + u'\u061f' # 0xBF -> ARABIC QUESTION MARK u'\ufffe' - u'\u0621' # 0xc1 -> ARABIC LETTER HAMZA - u'\u0622' # 0xc2 -> ARABIC LETTER ALEF WITH MADDA ABOVE - u'\u0623' # 0xc3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE - u'\u0624' # 0xc4 -> ARABIC LETTER WAW WITH HAMZA ABOVE - u'\u0625' # 0xc5 -> ARABIC LETTER ALEF WITH HAMZA BELOW - u'\u0626' # 0xc6 -> ARABIC LETTER YEH WITH HAMZA ABOVE - u'\u0627' # 0xc7 -> ARABIC LETTER ALEF - u'\u0628' # 0xc8 -> ARABIC LETTER BEH - u'\u0629' # 0xc9 -> ARABIC LETTER TEH MARBUTA - u'\u062a' # 0xca -> ARABIC LETTER TEH - u'\u062b' # 0xcb -> ARABIC LETTER THEH - u'\u062c' # 0xcc -> ARABIC LETTER JEEM - u'\u062d' # 0xcd -> ARABIC LETTER HAH - u'\u062e' # 0xce -> ARABIC LETTER KHAH - u'\u062f' # 0xcf -> ARABIC LETTER DAL - u'\u0630' # 0xd0 -> ARABIC LETTER THAL - u'\u0631' # 0xd1 -> ARABIC LETTER REH - u'\u0632' # 0xd2 -> ARABIC LETTER ZAIN - u'\u0633' # 0xd3 -> ARABIC LETTER SEEN - u'\u0634' # 0xd4 -> ARABIC LETTER SHEEN - u'\u0635' # 0xd5 -> ARABIC LETTER SAD - u'\u0636' # 0xd6 -> ARABIC LETTER DAD - u'\u0637' # 0xd7 -> ARABIC LETTER TAH - u'\u0638' # 0xd8 -> ARABIC LETTER ZAH - u'\u0639' # 0xd9 -> ARABIC LETTER AIN - u'\u063a' # 0xda -> ARABIC LETTER GHAIN + u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA + u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE + u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE + u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE + u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW + u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE + u'\u0627' # 0xC7 -> ARABIC LETTER ALEF + u'\u0628' # 0xC8 -> ARABIC LETTER BEH + u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA + u'\u062a' # 0xCA -> ARABIC LETTER TEH + u'\u062b' # 0xCB -> ARABIC LETTER THEH + u'\u062c' # 0xCC -> ARABIC LETTER JEEM + u'\u062d' # 0xCD -> ARABIC LETTER HAH + u'\u062e' # 0xCE -> ARABIC LETTER KHAH + u'\u062f' # 0xCF -> ARABIC LETTER DAL + u'\u0630' # 0xD0 -> ARABIC LETTER THAL + u'\u0631' # 0xD1 -> ARABIC LETTER REH + u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN + u'\u0633' # 0xD3 -> ARABIC LETTER SEEN + u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN + u'\u0635' # 0xD5 -> ARABIC LETTER SAD + u'\u0636' # 0xD6 -> ARABIC LETTER DAD + u'\u0637' # 0xD7 -> ARABIC LETTER TAH + u'\u0638' # 0xD8 -> ARABIC LETTER ZAH + u'\u0639' # 0xD9 -> ARABIC LETTER AIN + u'\u063a' # 0xDA -> ARABIC LETTER GHAIN u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' - u'\u0640' # 0xe0 -> ARABIC TATWEEL - u'\u0641' # 0xe1 -> ARABIC LETTER FEH - u'\u0642' # 0xe2 -> ARABIC LETTER QAF - u'\u0643' # 0xe3 -> ARABIC LETTER KAF - u'\u0644' # 0xe4 -> ARABIC LETTER LAM - u'\u0645' # 0xe5 -> ARABIC LETTER MEEM - u'\u0646' # 0xe6 -> ARABIC LETTER NOON - u'\u0647' # 0xe7 -> ARABIC LETTER HEH - u'\u0648' # 0xe8 -> ARABIC LETTER WAW - u'\u0649' # 0xe9 -> ARABIC LETTER ALEF MAKSURA - u'\u064a' # 0xea -> ARABIC LETTER YEH - u'\u064b' # 0xeb -> ARABIC FATHATAN - u'\u064c' # 0xec -> ARABIC DAMMATAN - u'\u064d' # 0xed -> ARABIC KASRATAN - u'\u064e' # 0xee -> ARABIC FATHA - u'\u064f' # 0xef -> ARABIC DAMMA - u'\u0650' # 0xf0 -> ARABIC KASRA - u'\u0651' # 0xf1 -> ARABIC SHADDA - u'\u0652' # 0xf2 -> ARABIC SUKUN + u'\u0640' # 0xE0 -> ARABIC TATWEEL + u'\u0641' # 0xE1 -> ARABIC LETTER FEH + u'\u0642' # 0xE2 -> ARABIC LETTER QAF + u'\u0643' # 0xE3 -> ARABIC LETTER KAF + u'\u0644' # 0xE4 -> ARABIC LETTER LAM + u'\u0645' # 0xE5 -> ARABIC LETTER MEEM + u'\u0646' # 0xE6 -> ARABIC LETTER NOON + u'\u0647' # 0xE7 -> ARABIC LETTER HEH + u'\u0648' # 0xE8 -> ARABIC LETTER WAW + u'\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA + u'\u064a' # 0xEA -> ARABIC LETTER YEH + u'\u064b' # 0xEB -> ARABIC FATHATAN + u'\u064c' # 0xEC -> ARABIC DAMMATAN + u'\u064d' # 0xED -> ARABIC KASRATAN + u'\u064e' # 0xEE -> ARABIC FATHA + u'\u064f' # 0xEF -> ARABIC DAMMA + u'\u0650' # 0xF0 -> ARABIC KASRA + u'\u0651' # 0xF1 -> ARABIC SHADDA + u'\u0652' # 0xF2 -> ARABIC SUKUN u'\ufffe' u'\ufffe' u'\ufffe' @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,61 +447,62 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x060c: 0xac, # ARABIC COMMA - 0x061b: 0xbb, # ARABIC SEMICOLON - 0x061f: 0xbf, # ARABIC QUESTION MARK - 0x0621: 0xc1, # ARABIC LETTER HAMZA - 0x0622: 0xc2, # ARABIC LETTER ALEF WITH MADDA ABOVE - 0x0623: 0xc3, # ARABIC LETTER ALEF WITH HAMZA ABOVE - 0x0624: 0xc4, # ARABIC LETTER WAW WITH HAMZA ABOVE - 0x0625: 0xc5, # ARABIC LETTER ALEF WITH HAMZA BELOW - 0x0626: 0xc6, # ARABIC LETTER YEH WITH HAMZA ABOVE - 0x0627: 0xc7, # ARABIC LETTER ALEF - 0x0628: 0xc8, # ARABIC LETTER BEH - 0x0629: 0xc9, # ARABIC LETTER TEH MARBUTA - 0x062a: 0xca, # ARABIC LETTER TEH - 0x062b: 0xcb, # ARABIC LETTER THEH - 0x062c: 0xcc, # ARABIC LETTER JEEM - 0x062d: 0xcd, # ARABIC LETTER HAH - 0x062e: 0xce, # ARABIC LETTER KHAH - 0x062f: 0xcf, # ARABIC LETTER DAL - 0x0630: 0xd0, # ARABIC LETTER THAL - 0x0631: 0xd1, # ARABIC LETTER REH - 0x0632: 0xd2, # ARABIC LETTER ZAIN - 0x0633: 0xd3, # ARABIC LETTER SEEN - 0x0634: 0xd4, # ARABIC LETTER SHEEN - 0x0635: 0xd5, # ARABIC LETTER SAD - 0x0636: 0xd6, # ARABIC LETTER DAD - 0x0637: 0xd7, # ARABIC LETTER TAH - 0x0638: 0xd8, # ARABIC LETTER ZAH - 0x0639: 0xd9, # ARABIC LETTER AIN - 0x063a: 0xda, # ARABIC LETTER GHAIN - 0x0640: 0xe0, # ARABIC TATWEEL - 0x0641: 0xe1, # ARABIC LETTER FEH - 0x0642: 0xe2, # ARABIC LETTER QAF - 0x0643: 0xe3, # ARABIC LETTER KAF - 0x0644: 0xe4, # ARABIC LETTER LAM - 0x0645: 0xe5, # ARABIC LETTER MEEM - 0x0646: 0xe6, # ARABIC LETTER NOON - 0x0647: 0xe7, # ARABIC LETTER HEH - 0x0648: 0xe8, # ARABIC LETTER WAW - 0x0649: 0xe9, # ARABIC LETTER ALEF MAKSURA - 0x064a: 0xea, # ARABIC LETTER YEH - 0x064b: 0xeb, # ARABIC FATHATAN - 0x064c: 0xec, # ARABIC DAMMATAN - 0x064d: 0xed, # ARABIC KASRATAN - 0x064e: 0xee, # ARABIC FATHA - 0x064f: 0xef, # ARABIC DAMMA - 0x0650: 0xf0, # ARABIC KASRA - 0x0651: 0xf1, # ARABIC SHADDA - 0x0652: 0xf2, # ARABIC SUKUN -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x060C: 0xAC, # ARABIC COMMA + 0x061B: 0xBB, # ARABIC SEMICOLON + 0x061F: 0xBF, # ARABIC QUESTION MARK + 0x0621: 0xC1, # ARABIC LETTER HAMZA + 0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE + 0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE + 0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE + 0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW + 0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE + 0x0627: 0xC7, # ARABIC LETTER ALEF + 0x0628: 0xC8, # ARABIC LETTER BEH + 0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA + 0x062A: 0xCA, # ARABIC LETTER TEH + 0x062B: 0xCB, # ARABIC LETTER THEH + 0x062C: 0xCC, # ARABIC LETTER JEEM + 0x062D: 0xCD, # ARABIC LETTER HAH + 0x062E: 0xCE, # ARABIC LETTER KHAH + 0x062F: 0xCF, # ARABIC LETTER DAL + 0x0630: 0xD0, # ARABIC LETTER THAL + 0x0631: 0xD1, # ARABIC LETTER REH + 0x0632: 0xD2, # ARABIC LETTER ZAIN + 0x0633: 0xD3, # ARABIC LETTER SEEN + 0x0634: 0xD4, # ARABIC LETTER SHEEN + 0x0635: 0xD5, # ARABIC LETTER SAD + 0x0636: 0xD6, # ARABIC LETTER DAD + 0x0637: 0xD7, # ARABIC LETTER TAH + 0x0638: 0xD8, # ARABIC LETTER ZAH + 0x0639: 0xD9, # ARABIC LETTER AIN + 0x063A: 0xDA, # ARABIC LETTER GHAIN + 0x0640: 0xE0, # ARABIC TATWEEL + 0x0641: 0xE1, # ARABIC LETTER FEH + 0x0642: 0xE2, # ARABIC LETTER QAF + 0x0643: 0xE3, # ARABIC LETTER KAF + 0x0644: 0xE4, # ARABIC LETTER LAM + 0x0645: 0xE5, # ARABIC LETTER MEEM + 0x0646: 0xE6, # ARABIC LETTER NOON + 0x0647: 0xE7, # ARABIC LETTER HEH + 0x0648: 0xE8, # ARABIC LETTER WAW + 0x0649: 0xE9, # ARABIC LETTER ALEF MAKSURA + 0x064A: 0xEA, # ARABIC LETTER YEH + 0x064B: 0xEB, # ARABIC FATHATAN + 0x064C: 0xEC, # ARABIC DAMMATAN + 0x064D: 0xED, # ARABIC KASRATAN + 0x064E: 0xEE, # ARABIC FATHA + 0x064F: 0xEF, # ARABIC DAMMA + 0x0650: 0xF0, # ARABIC KASRA + 0x0651: 0xF1, # ARABIC SHADDA + 0x0652: 0xF2, # ARABIC SUKUN +} + diff --git a/Lib/encodings/iso8859_7.py b/Lib/encodings/iso8859_7.py index 5ef3ece..c43af8c 100644 --- a/Lib/encodings/iso8859_7.py +++ b/Lib/encodings/iso8859_7.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,107 +186,107 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\u2018' # 0xa1 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xa2 -> RIGHT SINGLE QUOTATION MARK - u'\xa3' # 0xa3 -> POUND SIGN - u'\u20ac' # 0xa4 -> EURO SIGN - u'\u20af' # 0xa5 -> DRACHMA SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u037a' # 0xaa -> GREEK YPOGEGRAMMENI - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\u2018' # 0xA1 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xA2 -> RIGHT SINGLE QUOTATION MARK + u'\xa3' # 0xA3 -> POUND SIGN + u'\u20ac' # 0xA4 -> EURO SIGN + u'\u20af' # 0xA5 -> DRACHMA SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u037a' # 0xAA -> GREEK YPOGEGRAMMENI + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN u'\ufffe' - u'\u2015' # 0xaf -> HORIZONTAL BAR - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\u0384' # 0xb4 -> GREEK TONOS - u'\u0385' # 0xb5 -> GREEK DIALYTIKA TONOS - u'\u0386' # 0xb6 -> GREEK CAPITAL LETTER ALPHA WITH TONOS - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\u0388' # 0xb8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS - u'\u0389' # 0xb9 -> GREEK CAPITAL LETTER ETA WITH TONOS - u'\u038a' # 0xba -> GREEK CAPITAL LETTER IOTA WITH TONOS - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u038c' # 0xbc -> GREEK CAPITAL LETTER OMICRON WITH TONOS - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\u038e' # 0xbe -> GREEK CAPITAL LETTER UPSILON WITH TONOS - u'\u038f' # 0xbf -> GREEK CAPITAL LETTER OMEGA WITH TONOS - u'\u0390' # 0xc0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS - u'\u0391' # 0xc1 -> GREEK CAPITAL LETTER ALPHA - u'\u0392' # 0xc2 -> GREEK CAPITAL LETTER BETA - u'\u0393' # 0xc3 -> GREEK CAPITAL LETTER GAMMA - u'\u0394' # 0xc4 -> GREEK CAPITAL LETTER DELTA - u'\u0395' # 0xc5 -> GREEK CAPITAL LETTER EPSILON - u'\u0396' # 0xc6 -> GREEK CAPITAL LETTER ZETA - u'\u0397' # 0xc7 -> GREEK CAPITAL LETTER ETA - u'\u0398' # 0xc8 -> GREEK CAPITAL LETTER THETA - u'\u0399' # 0xc9 -> GREEK CAPITAL LETTER IOTA - u'\u039a' # 0xca -> GREEK CAPITAL LETTER KAPPA - u'\u039b' # 0xcb -> GREEK CAPITAL LETTER LAMDA - u'\u039c' # 0xcc -> GREEK CAPITAL LETTER MU - u'\u039d' # 0xcd -> GREEK CAPITAL LETTER NU - u'\u039e' # 0xce -> GREEK CAPITAL LETTER XI - u'\u039f' # 0xcf -> GREEK CAPITAL LETTER OMICRON - u'\u03a0' # 0xd0 -> GREEK CAPITAL LETTER PI - u'\u03a1' # 0xd1 -> GREEK CAPITAL LETTER RHO + u'\u2015' # 0xAF -> HORIZONTAL BAR + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\u0384' # 0xB4 -> GREEK TONOS + u'\u0385' # 0xB5 -> GREEK DIALYTIKA TONOS + u'\u0386' # 0xB6 -> GREEK CAPITAL LETTER ALPHA WITH TONOS + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS + u'\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS + u'\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS + u'\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS + u'\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + u'\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA + u'\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA + u'\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA + u'\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA + u'\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON + u'\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA + u'\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA + u'\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA + u'\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA + u'\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA + u'\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA + u'\u039c' # 0xCC -> GREEK CAPITAL LETTER MU + u'\u039d' # 0xCD -> GREEK CAPITAL LETTER NU + u'\u039e' # 0xCE -> GREEK CAPITAL LETTER XI + u'\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON + u'\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI + u'\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO u'\ufffe' - u'\u03a3' # 0xd3 -> GREEK CAPITAL LETTER SIGMA - u'\u03a4' # 0xd4 -> GREEK CAPITAL LETTER TAU - u'\u03a5' # 0xd5 -> GREEK CAPITAL LETTER UPSILON - u'\u03a6' # 0xd6 -> GREEK CAPITAL LETTER PHI - u'\u03a7' # 0xd7 -> GREEK CAPITAL LETTER CHI - u'\u03a8' # 0xd8 -> GREEK CAPITAL LETTER PSI - u'\u03a9' # 0xd9 -> GREEK CAPITAL LETTER OMEGA - u'\u03aa' # 0xda -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - u'\u03ab' # 0xdb -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - u'\u03ac' # 0xdc -> GREEK SMALL LETTER ALPHA WITH TONOS - u'\u03ad' # 0xdd -> GREEK SMALL LETTER EPSILON WITH TONOS - u'\u03ae' # 0xde -> GREEK SMALL LETTER ETA WITH TONOS - u'\u03af' # 0xdf -> GREEK SMALL LETTER IOTA WITH TONOS - u'\u03b0' # 0xe0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - u'\u03b1' # 0xe1 -> GREEK SMALL LETTER ALPHA - u'\u03b2' # 0xe2 -> GREEK SMALL LETTER BETA - u'\u03b3' # 0xe3 -> GREEK SMALL LETTER GAMMA - u'\u03b4' # 0xe4 -> GREEK SMALL LETTER DELTA - u'\u03b5' # 0xe5 -> GREEK SMALL LETTER EPSILON - u'\u03b6' # 0xe6 -> GREEK SMALL LETTER ZETA - u'\u03b7' # 0xe7 -> GREEK SMALL LETTER ETA - u'\u03b8' # 0xe8 -> GREEK SMALL LETTER THETA - u'\u03b9' # 0xe9 -> GREEK SMALL LETTER IOTA - u'\u03ba' # 0xea -> GREEK SMALL LETTER KAPPA - u'\u03bb' # 0xeb -> GREEK SMALL LETTER LAMDA - u'\u03bc' # 0xec -> GREEK SMALL LETTER MU - u'\u03bd' # 0xed -> GREEK SMALL LETTER NU - u'\u03be' # 0xee -> GREEK SMALL LETTER XI - u'\u03bf' # 0xef -> GREEK SMALL LETTER OMICRON - u'\u03c0' # 0xf0 -> GREEK SMALL LETTER PI - u'\u03c1' # 0xf1 -> GREEK SMALL LETTER RHO - u'\u03c2' # 0xf2 -> GREEK SMALL LETTER FINAL SIGMA - u'\u03c3' # 0xf3 -> GREEK SMALL LETTER SIGMA - u'\u03c4' # 0xf4 -> GREEK SMALL LETTER TAU - u'\u03c5' # 0xf5 -> GREEK SMALL LETTER UPSILON - u'\u03c6' # 0xf6 -> GREEK SMALL LETTER PHI - u'\u03c7' # 0xf7 -> GREEK SMALL LETTER CHI - u'\u03c8' # 0xf8 -> GREEK SMALL LETTER PSI - u'\u03c9' # 0xf9 -> GREEK SMALL LETTER OMEGA - u'\u03ca' # 0xfa -> GREEK SMALL LETTER IOTA WITH DIALYTIKA - u'\u03cb' # 0xfb -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA - u'\u03cc' # 0xfc -> GREEK SMALL LETTER OMICRON WITH TONOS - u'\u03cd' # 0xfd -> GREEK SMALL LETTER UPSILON WITH TONOS - u'\u03ce' # 0xfe -> GREEK SMALL LETTER OMEGA WITH TONOS + u'\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA + u'\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU + u'\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON + u'\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI + u'\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI + u'\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI + u'\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA + u'\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + u'\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + u'\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS + u'\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS + u'\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS + u'\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS + u'\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA + u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA + u'\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA + u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA + u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON + u'\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA + u'\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA + u'\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA + u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA + u'\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA + u'\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA + u'\u03bc' # 0xEC -> GREEK SMALL LETTER MU + u'\u03bd' # 0xED -> GREEK SMALL LETTER NU + u'\u03be' # 0xEE -> GREEK SMALL LETTER XI + u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON + u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI + u'\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO + u'\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA + u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA + u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU + u'\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON + u'\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI + u'\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI + u'\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI + u'\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA + u'\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + u'\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + u'\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS + u'\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS + u'\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS u'\ufffe' ) @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,103 +447,104 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a3: 0xa3, # POUND SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b7: 0xb7, # MIDDLE DOT - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x037a: 0xaa, # GREEK YPOGEGRAMMENI - 0x0384: 0xb4, # GREEK TONOS - 0x0385: 0xb5, # GREEK DIALYTIKA TONOS - 0x0386: 0xb6, # GREEK CAPITAL LETTER ALPHA WITH TONOS - 0x0388: 0xb8, # GREEK CAPITAL LETTER EPSILON WITH TONOS - 0x0389: 0xb9, # GREEK CAPITAL LETTER ETA WITH TONOS - 0x038a: 0xba, # GREEK CAPITAL LETTER IOTA WITH TONOS - 0x038c: 0xbc, # GREEK CAPITAL LETTER OMICRON WITH TONOS - 0x038e: 0xbe, # GREEK CAPITAL LETTER UPSILON WITH TONOS - 0x038f: 0xbf, # GREEK CAPITAL LETTER OMEGA WITH TONOS - 0x0390: 0xc0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS - 0x0391: 0xc1, # GREEK CAPITAL LETTER ALPHA - 0x0392: 0xc2, # GREEK CAPITAL LETTER BETA - 0x0393: 0xc3, # GREEK CAPITAL LETTER GAMMA - 0x0394: 0xc4, # GREEK CAPITAL LETTER DELTA - 0x0395: 0xc5, # GREEK CAPITAL LETTER EPSILON - 0x0396: 0xc6, # GREEK CAPITAL LETTER ZETA - 0x0397: 0xc7, # GREEK CAPITAL LETTER ETA - 0x0398: 0xc8, # GREEK CAPITAL LETTER THETA - 0x0399: 0xc9, # GREEK CAPITAL LETTER IOTA - 0x039a: 0xca, # GREEK CAPITAL LETTER KAPPA - 0x039b: 0xcb, # GREEK CAPITAL LETTER LAMDA - 0x039c: 0xcc, # GREEK CAPITAL LETTER MU - 0x039d: 0xcd, # GREEK CAPITAL LETTER NU - 0x039e: 0xce, # GREEK CAPITAL LETTER XI - 0x039f: 0xcf, # GREEK CAPITAL LETTER OMICRON - 0x03a0: 0xd0, # GREEK CAPITAL LETTER PI - 0x03a1: 0xd1, # GREEK CAPITAL LETTER RHO - 0x03a3: 0xd3, # GREEK CAPITAL LETTER SIGMA - 0x03a4: 0xd4, # GREEK CAPITAL LETTER TAU - 0x03a5: 0xd5, # GREEK CAPITAL LETTER UPSILON - 0x03a6: 0xd6, # GREEK CAPITAL LETTER PHI - 0x03a7: 0xd7, # GREEK CAPITAL LETTER CHI - 0x03a8: 0xd8, # GREEK CAPITAL LETTER PSI - 0x03a9: 0xd9, # GREEK CAPITAL LETTER OMEGA - 0x03aa: 0xda, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - 0x03ab: 0xdb, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - 0x03ac: 0xdc, # GREEK SMALL LETTER ALPHA WITH TONOS - 0x03ad: 0xdd, # GREEK SMALL LETTER EPSILON WITH TONOS - 0x03ae: 0xde, # GREEK SMALL LETTER ETA WITH TONOS - 0x03af: 0xdf, # GREEK SMALL LETTER IOTA WITH TONOS - 0x03b0: 0xe0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - 0x03b1: 0xe1, # GREEK SMALL LETTER ALPHA - 0x03b2: 0xe2, # GREEK SMALL LETTER BETA - 0x03b3: 0xe3, # GREEK SMALL LETTER GAMMA - 0x03b4: 0xe4, # GREEK SMALL LETTER DELTA - 0x03b5: 0xe5, # GREEK SMALL LETTER EPSILON - 0x03b6: 0xe6, # GREEK SMALL LETTER ZETA - 0x03b7: 0xe7, # GREEK SMALL LETTER ETA - 0x03b8: 0xe8, # GREEK SMALL LETTER THETA - 0x03b9: 0xe9, # GREEK SMALL LETTER IOTA - 0x03ba: 0xea, # GREEK SMALL LETTER KAPPA - 0x03bb: 0xeb, # GREEK SMALL LETTER LAMDA - 0x03bc: 0xec, # GREEK SMALL LETTER MU - 0x03bd: 0xed, # GREEK SMALL LETTER NU - 0x03be: 0xee, # GREEK SMALL LETTER XI - 0x03bf: 0xef, # GREEK SMALL LETTER OMICRON - 0x03c0: 0xf0, # GREEK SMALL LETTER PI - 0x03c1: 0xf1, # GREEK SMALL LETTER RHO - 0x03c2: 0xf2, # GREEK SMALL LETTER FINAL SIGMA - 0x03c3: 0xf3, # GREEK SMALL LETTER SIGMA - 0x03c4: 0xf4, # GREEK SMALL LETTER TAU - 0x03c5: 0xf5, # GREEK SMALL LETTER UPSILON - 0x03c6: 0xf6, # GREEK SMALL LETTER PHI - 0x03c7: 0xf7, # GREEK SMALL LETTER CHI - 0x03c8: 0xf8, # GREEK SMALL LETTER PSI - 0x03c9: 0xf9, # GREEK SMALL LETTER OMEGA - 0x03ca: 0xfa, # GREEK SMALL LETTER IOTA WITH DIALYTIKA - 0x03cb: 0xfb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA - 0x03cc: 0xfc, # GREEK SMALL LETTER OMICRON WITH TONOS - 0x03cd: 0xfd, # GREEK SMALL LETTER UPSILON WITH TONOS - 0x03ce: 0xfe, # GREEK SMALL LETTER OMEGA WITH TONOS - 0x2015: 0xaf, # HORIZONTAL BAR - 0x2018: 0xa1, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xa2, # RIGHT SINGLE QUOTATION MARK - 0x20ac: 0xa4, # EURO SIGN - 0x20af: 0xa5, # DRACHMA SIGN -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A3: 0xA3, # POUND SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B7: 0xB7, # MIDDLE DOT + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x037A: 0xAA, # GREEK YPOGEGRAMMENI + 0x0384: 0xB4, # GREEK TONOS + 0x0385: 0xB5, # GREEK DIALYTIKA TONOS + 0x0386: 0xB6, # GREEK CAPITAL LETTER ALPHA WITH TONOS + 0x0388: 0xB8, # GREEK CAPITAL LETTER EPSILON WITH TONOS + 0x0389: 0xB9, # GREEK CAPITAL LETTER ETA WITH TONOS + 0x038A: 0xBA, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x038C: 0xBC, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x038E: 0xBE, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x038F: 0xBF, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x0390: 0xC0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + 0x0391: 0xC1, # GREEK CAPITAL LETTER ALPHA + 0x0392: 0xC2, # GREEK CAPITAL LETTER BETA + 0x0393: 0xC3, # GREEK CAPITAL LETTER GAMMA + 0x0394: 0xC4, # GREEK CAPITAL LETTER DELTA + 0x0395: 0xC5, # GREEK CAPITAL LETTER EPSILON + 0x0396: 0xC6, # GREEK CAPITAL LETTER ZETA + 0x0397: 0xC7, # GREEK CAPITAL LETTER ETA + 0x0398: 0xC8, # GREEK CAPITAL LETTER THETA + 0x0399: 0xC9, # GREEK CAPITAL LETTER IOTA + 0x039A: 0xCA, # GREEK CAPITAL LETTER KAPPA + 0x039B: 0xCB, # GREEK CAPITAL LETTER LAMDA + 0x039C: 0xCC, # GREEK CAPITAL LETTER MU + 0x039D: 0xCD, # GREEK CAPITAL LETTER NU + 0x039E: 0xCE, # GREEK CAPITAL LETTER XI + 0x039F: 0xCF, # GREEK CAPITAL LETTER OMICRON + 0x03A0: 0xD0, # GREEK CAPITAL LETTER PI + 0x03A1: 0xD1, # GREEK CAPITAL LETTER RHO + 0x03A3: 0xD3, # GREEK CAPITAL LETTER SIGMA + 0x03A4: 0xD4, # GREEK CAPITAL LETTER TAU + 0x03A5: 0xD5, # GREEK CAPITAL LETTER UPSILON + 0x03A6: 0xD6, # GREEK CAPITAL LETTER PHI + 0x03A7: 0xD7, # GREEK CAPITAL LETTER CHI + 0x03A8: 0xD8, # GREEK CAPITAL LETTER PSI + 0x03A9: 0xD9, # GREEK CAPITAL LETTER OMEGA + 0x03AA: 0xDA, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x03AB: 0xDB, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x03AC: 0xDC, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x03AD: 0xDD, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x03AE: 0xDE, # GREEK SMALL LETTER ETA WITH TONOS + 0x03AF: 0xDF, # GREEK SMALL LETTER IOTA WITH TONOS + 0x03B0: 0xE0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + 0x03B1: 0xE1, # GREEK SMALL LETTER ALPHA + 0x03B2: 0xE2, # GREEK SMALL LETTER BETA + 0x03B3: 0xE3, # GREEK SMALL LETTER GAMMA + 0x03B4: 0xE4, # GREEK SMALL LETTER DELTA + 0x03B5: 0xE5, # GREEK SMALL LETTER EPSILON + 0x03B6: 0xE6, # GREEK SMALL LETTER ZETA + 0x03B7: 0xE7, # GREEK SMALL LETTER ETA + 0x03B8: 0xE8, # GREEK SMALL LETTER THETA + 0x03B9: 0xE9, # GREEK SMALL LETTER IOTA + 0x03BA: 0xEA, # GREEK SMALL LETTER KAPPA + 0x03BB: 0xEB, # GREEK SMALL LETTER LAMDA + 0x03BC: 0xEC, # GREEK SMALL LETTER MU + 0x03BD: 0xED, # GREEK SMALL LETTER NU + 0x03BE: 0xEE, # GREEK SMALL LETTER XI + 0x03BF: 0xEF, # GREEK SMALL LETTER OMICRON + 0x03C0: 0xF0, # GREEK SMALL LETTER PI + 0x03C1: 0xF1, # GREEK SMALL LETTER RHO + 0x03C2: 0xF2, # GREEK SMALL LETTER FINAL SIGMA + 0x03C3: 0xF3, # GREEK SMALL LETTER SIGMA + 0x03C4: 0xF4, # GREEK SMALL LETTER TAU + 0x03C5: 0xF5, # GREEK SMALL LETTER UPSILON + 0x03C6: 0xF6, # GREEK SMALL LETTER PHI + 0x03C7: 0xF7, # GREEK SMALL LETTER CHI + 0x03C8: 0xF8, # GREEK SMALL LETTER PSI + 0x03C9: 0xF9, # GREEK SMALL LETTER OMEGA + 0x03CA: 0xFA, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x03CB: 0xFB, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x03CC: 0xFC, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x03CD: 0xFD, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x03CE: 0xFE, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x2015: 0xAF, # HORIZONTAL BAR + 0x2018: 0xA1, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xA2, # RIGHT SINGLE QUOTATION MARK + 0x20AC: 0xA4, # EURO SIGN + 0x20AF: 0xA5, # DRACHMA SIGN +} + diff --git a/Lib/encodings/iso8859_8.py b/Lib/encodings/iso8859_8.py index 118872c..259daea 100644 --- a/Lib/encodings/iso8859_8.py +++ b/Lib/encodings/iso8859_8.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,43 +186,43 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\ufffe' - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xd7' # 0xaa -> MULTIPLICATION SIGN - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xf7' # 0xba -> DIVISION SIGN - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xd7' # 0xAA -> MULTIPLICATION SIGN + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xf7' # 0xBA -> DIVISION SIGN + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\ufffe' u'\ufffe' u'\ufffe' @@ -255,38 +255,38 @@ decoding_table = ( u'\ufffe' u'\ufffe' u'\ufffe' - u'\u2017' # 0xdf -> DOUBLE LOW LINE - u'\u05d0' # 0xe0 -> HEBREW LETTER ALEF - u'\u05d1' # 0xe1 -> HEBREW LETTER BET - u'\u05d2' # 0xe2 -> HEBREW LETTER GIMEL - u'\u05d3' # 0xe3 -> HEBREW LETTER DALET - u'\u05d4' # 0xe4 -> HEBREW LETTER HE - u'\u05d5' # 0xe5 -> HEBREW LETTER VAV - u'\u05d6' # 0xe6 -> HEBREW LETTER ZAYIN - u'\u05d7' # 0xe7 -> HEBREW LETTER HET - u'\u05d8' # 0xe8 -> HEBREW LETTER TET - u'\u05d9' # 0xe9 -> HEBREW LETTER YOD - u'\u05da' # 0xea -> HEBREW LETTER FINAL KAF - u'\u05db' # 0xeb -> HEBREW LETTER KAF - u'\u05dc' # 0xec -> HEBREW LETTER LAMED - u'\u05dd' # 0xed -> HEBREW LETTER FINAL MEM - u'\u05de' # 0xee -> HEBREW LETTER MEM - u'\u05df' # 0xef -> HEBREW LETTER FINAL NUN - u'\u05e0' # 0xf0 -> HEBREW LETTER NUN - u'\u05e1' # 0xf1 -> HEBREW LETTER SAMEKH - u'\u05e2' # 0xf2 -> HEBREW LETTER AYIN - u'\u05e3' # 0xf3 -> HEBREW LETTER FINAL PE - u'\u05e4' # 0xf4 -> HEBREW LETTER PE - u'\u05e5' # 0xf5 -> HEBREW LETTER FINAL TSADI - u'\u05e6' # 0xf6 -> HEBREW LETTER TSADI - u'\u05e7' # 0xf7 -> HEBREW LETTER QOF - u'\u05e8' # 0xf8 -> HEBREW LETTER RESH - u'\u05e9' # 0xf9 -> HEBREW LETTER SHIN - u'\u05ea' # 0xfa -> HEBREW LETTER TAV + u'\u2017' # 0xDF -> DOUBLE LOW LINE + u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF + u'\u05d1' # 0xE1 -> HEBREW LETTER BET + u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL + u'\u05d3' # 0xE3 -> HEBREW LETTER DALET + u'\u05d4' # 0xE4 -> HEBREW LETTER HE + u'\u05d5' # 0xE5 -> HEBREW LETTER VAV + u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN + u'\u05d7' # 0xE7 -> HEBREW LETTER HET + u'\u05d8' # 0xE8 -> HEBREW LETTER TET + u'\u05d9' # 0xE9 -> HEBREW LETTER YOD + u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF + u'\u05db' # 0xEB -> HEBREW LETTER KAF + u'\u05dc' # 0xEC -> HEBREW LETTER LAMED + u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM + u'\u05de' # 0xEE -> HEBREW LETTER MEM + u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN + u'\u05e0' # 0xF0 -> HEBREW LETTER NUN + u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH + u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN + u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE + u'\u05e4' # 0xF4 -> HEBREW LETTER PE + u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI + u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI + u'\u05e7' # 0xF7 -> HEBREW LETTER QOF + u'\u05e8' # 0xF8 -> HEBREW LETTER RESH + u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN + u'\u05ea' # 0xFA -> HEBREW LETTER TAV u'\ufffe' u'\ufffe' - u'\u200e' # 0xfd -> LEFT-TO-RIGHT MARK - u'\u200f' # 0xfe -> RIGHT-TO-LEFT MARK + u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK + u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK u'\ufffe' ) @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,70 +447,71 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00d7: 0xaa, # MULTIPLICATION SIGN - 0x00f7: 0xba, # DIVISION SIGN - 0x05d0: 0xe0, # HEBREW LETTER ALEF - 0x05d1: 0xe1, # HEBREW LETTER BET - 0x05d2: 0xe2, # HEBREW LETTER GIMEL - 0x05d3: 0xe3, # HEBREW LETTER DALET - 0x05d4: 0xe4, # HEBREW LETTER HE - 0x05d5: 0xe5, # HEBREW LETTER VAV - 0x05d6: 0xe6, # HEBREW LETTER ZAYIN - 0x05d7: 0xe7, # HEBREW LETTER HET - 0x05d8: 0xe8, # HEBREW LETTER TET - 0x05d9: 0xe9, # HEBREW LETTER YOD - 0x05da: 0xea, # HEBREW LETTER FINAL KAF - 0x05db: 0xeb, # HEBREW LETTER KAF - 0x05dc: 0xec, # HEBREW LETTER LAMED - 0x05dd: 0xed, # HEBREW LETTER FINAL MEM - 0x05de: 0xee, # HEBREW LETTER MEM - 0x05df: 0xef, # HEBREW LETTER FINAL NUN - 0x05e0: 0xf0, # HEBREW LETTER NUN - 0x05e1: 0xf1, # HEBREW LETTER SAMEKH - 0x05e2: 0xf2, # HEBREW LETTER AYIN - 0x05e3: 0xf3, # HEBREW LETTER FINAL PE - 0x05e4: 0xf4, # HEBREW LETTER PE - 0x05e5: 0xf5, # HEBREW LETTER FINAL TSADI - 0x05e6: 0xf6, # HEBREW LETTER TSADI - 0x05e7: 0xf7, # HEBREW LETTER QOF - 0x05e8: 0xf8, # HEBREW LETTER RESH - 0x05e9: 0xf9, # HEBREW LETTER SHIN - 0x05ea: 0xfa, # HEBREW LETTER TAV - 0x200e: 0xfd, # LEFT-TO-RIGHT MARK - 0x200f: 0xfe, # RIGHT-TO-LEFT MARK - 0x2017: 0xdf, # DOUBLE LOW LINE -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00D7: 0xAA, # MULTIPLICATION SIGN + 0x00F7: 0xBA, # DIVISION SIGN + 0x05D0: 0xE0, # HEBREW LETTER ALEF + 0x05D1: 0xE1, # HEBREW LETTER BET + 0x05D2: 0xE2, # HEBREW LETTER GIMEL + 0x05D3: 0xE3, # HEBREW LETTER DALET + 0x05D4: 0xE4, # HEBREW LETTER HE + 0x05D5: 0xE5, # HEBREW LETTER VAV + 0x05D6: 0xE6, # HEBREW LETTER ZAYIN + 0x05D7: 0xE7, # HEBREW LETTER HET + 0x05D8: 0xE8, # HEBREW LETTER TET + 0x05D9: 0xE9, # HEBREW LETTER YOD + 0x05DA: 0xEA, # HEBREW LETTER FINAL KAF + 0x05DB: 0xEB, # HEBREW LETTER KAF + 0x05DC: 0xEC, # HEBREW LETTER LAMED + 0x05DD: 0xED, # HEBREW LETTER FINAL MEM + 0x05DE: 0xEE, # HEBREW LETTER MEM + 0x05DF: 0xEF, # HEBREW LETTER FINAL NUN + 0x05E0: 0xF0, # HEBREW LETTER NUN + 0x05E1: 0xF1, # HEBREW LETTER SAMEKH + 0x05E2: 0xF2, # HEBREW LETTER AYIN + 0x05E3: 0xF3, # HEBREW LETTER FINAL PE + 0x05E4: 0xF4, # HEBREW LETTER PE + 0x05E5: 0xF5, # HEBREW LETTER FINAL TSADI + 0x05E6: 0xF6, # HEBREW LETTER TSADI + 0x05E7: 0xF7, # HEBREW LETTER QOF + 0x05E8: 0xF8, # HEBREW LETTER RESH + 0x05E9: 0xF9, # HEBREW LETTER SHIN + 0x05EA: 0xFA, # HEBREW LETTER TAV + 0x200E: 0xFD, # LEFT-TO-RIGHT MARK + 0x200F: 0xFE, # RIGHT-TO-LEFT MARK + 0x2017: 0xDF, # DOUBLE LOW LINE +} + diff --git a/Lib/encodings/iso8859_9.py b/Lib/encodings/iso8859_9.py index b9152d1..0e32834 100644 --- a/Lib/encodings/iso8859_9.py +++ b/Lib/encodings/iso8859_9.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,108 +186,108 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> - u'\xa0' # 0xa0 -> NO-BREAK SPACE - u'\xa1' # 0xa1 -> INVERTED EXCLAMATION MARK - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa4' # 0xa4 -> CURRENCY SIGN - u'\xa5' # 0xa5 -> YEN SIGN - u'\xa6' # 0xa6 -> BROKEN BAR - u'\xa7' # 0xa7 -> SECTION SIGN - u'\xa8' # 0xa8 -> DIAERESIS - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\xaa' # 0xaa -> FEMININE ORDINAL INDICATOR - u'\xab' # 0xab -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xac' # 0xac -> NOT SIGN - u'\xad' # 0xad -> SOFT HYPHEN - u'\xae' # 0xae -> REGISTERED SIGN - u'\xaf' # 0xaf -> MACRON - u'\xb0' # 0xb0 -> DEGREE SIGN - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\xb2' # 0xb2 -> SUPERSCRIPT TWO - u'\xb3' # 0xb3 -> SUPERSCRIPT THREE - u'\xb4' # 0xb4 -> ACUTE ACCENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\xb6' # 0xb6 -> PILCROW SIGN - u'\xb7' # 0xb7 -> MIDDLE DOT - u'\xb8' # 0xb8 -> CEDILLA - u'\xb9' # 0xb9 -> SUPERSCRIPT ONE - u'\xba' # 0xba -> MASCULINE ORDINAL INDICATOR - u'\xbb' # 0xbb -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbc' # 0xbc -> VULGAR FRACTION ONE QUARTER - u'\xbd' # 0xbd -> VULGAR FRACTION ONE HALF - u'\xbe' # 0xbe -> VULGAR FRACTION THREE QUARTERS - u'\xbf' # 0xbf -> INVERTED QUESTION MARK - u'\xc0' # 0xc0 -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc1' # 0xc1 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xc2' # 0xc2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xc3' # 0xc3 -> LATIN CAPITAL LETTER A WITH TILDE - u'\xc4' # 0xc4 -> LATIN CAPITAL LETTER A WITH DIAERESIS - u'\xc5' # 0xc5 -> LATIN CAPITAL LETTER A WITH RING ABOVE - u'\xc6' # 0xc6 -> LATIN CAPITAL LETTER AE - u'\xc7' # 0xc7 -> LATIN CAPITAL LETTER C WITH CEDILLA - u'\xc8' # 0xc8 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xc9' # 0xc9 -> LATIN CAPITAL LETTER E WITH ACUTE - u'\xca' # 0xca -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xcb' # 0xcb -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xcc' # 0xcc -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xcd' # 0xcd -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xce -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xcf -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\u011e' # 0xd0 -> LATIN CAPITAL LETTER G WITH BREVE - u'\xd1' # 0xd1 -> LATIN CAPITAL LETTER N WITH TILDE - u'\xd2' # 0xd2 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xd3' # 0xd3 -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xd4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\xd5' # 0xd5 -> LATIN CAPITAL LETTER O WITH TILDE - u'\xd6' # 0xd6 -> LATIN CAPITAL LETTER O WITH DIAERESIS - u'\xd7' # 0xd7 -> MULTIPLICATION SIGN - u'\xd8' # 0xd8 -> LATIN CAPITAL LETTER O WITH STROKE - u'\xd9' # 0xd9 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\xda' # 0xda -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xdb -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xdc' # 0xdc -> LATIN CAPITAL LETTER U WITH DIAERESIS - u'\u0130' # 0xdd -> LATIN CAPITAL LETTER I WITH DOT ABOVE - u'\u015e' # 0xde -> LATIN CAPITAL LETTER S WITH CEDILLA - u'\xdf' # 0xdf -> LATIN SMALL LETTER SHARP S - u'\xe0' # 0xe0 -> LATIN SMALL LETTER A WITH GRAVE - u'\xe1' # 0xe1 -> LATIN SMALL LETTER A WITH ACUTE - u'\xe2' # 0xe2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe3' # 0xe3 -> LATIN SMALL LETTER A WITH TILDE - u'\xe4' # 0xe4 -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe5' # 0xe5 -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe6' # 0xe6 -> LATIN SMALL LETTER AE - u'\xe7' # 0xe7 -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe8' # 0xe8 -> LATIN SMALL LETTER E WITH GRAVE - u'\xe9' # 0xe9 -> LATIN SMALL LETTER E WITH ACUTE - u'\xea' # 0xea -> LATIN SMALL LETTER E WITH CIRCUMFLEX - u'\xeb' # 0xeb -> LATIN SMALL LETTER E WITH DIAERESIS - u'\xec' # 0xec -> LATIN SMALL LETTER I WITH GRAVE - u'\xed' # 0xed -> LATIN SMALL LETTER I WITH ACUTE - u'\xee' # 0xee -> LATIN SMALL LETTER I WITH CIRCUMFLEX - u'\xef' # 0xef -> LATIN SMALL LETTER I WITH DIAERESIS - u'\u011f' # 0xf0 -> LATIN SMALL LETTER G WITH BREVE - u'\xf1' # 0xf1 -> LATIN SMALL LETTER N WITH TILDE - u'\xf2' # 0xf2 -> LATIN SMALL LETTER O WITH GRAVE - u'\xf3' # 0xf3 -> LATIN SMALL LETTER O WITH ACUTE - u'\xf4' # 0xf4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf5' # 0xf5 -> LATIN SMALL LETTER O WITH TILDE - u'\xf6' # 0xf6 -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0xf7 -> DIVISION SIGN - u'\xf8' # 0xf8 -> LATIN SMALL LETTER O WITH STROKE - u'\xf9' # 0xf9 -> LATIN SMALL LETTER U WITH GRAVE - u'\xfa' # 0xfa -> LATIN SMALL LETTER U WITH ACUTE - u'\xfb' # 0xfb -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0xfc -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u0131' # 0xfd -> LATIN SMALL LETTER DOTLESS I - u'\u015f' # 0xfe -> LATIN SMALL LETTER S WITH CEDILLA - u'\xff' # 0xff -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> + u'\xa0' # 0xA0 -> NO-BREAK SPACE + u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa4' # 0xA4 -> CURRENCY SIGN + u'\xa5' # 0xA5 -> YEN SIGN + u'\xa6' # 0xA6 -> BROKEN BAR + u'\xa7' # 0xA7 -> SECTION SIGN + u'\xa8' # 0xA8 -> DIAERESIS + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xac' # 0xAC -> NOT SIGN + u'\xad' # 0xAD -> SOFT HYPHEN + u'\xae' # 0xAE -> REGISTERED SIGN + u'\xaf' # 0xAF -> MACRON + u'\xb0' # 0xB0 -> DEGREE SIGN + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\xb2' # 0xB2 -> SUPERSCRIPT TWO + u'\xb3' # 0xB3 -> SUPERSCRIPT THREE + u'\xb4' # 0xB4 -> ACUTE ACCENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\xb6' # 0xB6 -> PILCROW SIGN + u'\xb7' # 0xB7 -> MIDDLE DOT + u'\xb8' # 0xB8 -> CEDILLA + u'\xb9' # 0xB9 -> SUPERSCRIPT ONE + u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + u'\xbf' # 0xBF -> INVERTED QUESTION MARK + u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE + u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + u'\xd7' # 0xD7 -> MULTIPLICATION SIGN + u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + u'\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE + u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA + u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE + u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + u'\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE + u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0xF7 -> DIVISION SIGN + u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I + u'\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA + u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,106 +447,107 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x00a0: 0xa0, # NO-BREAK SPACE - 0x00a1: 0xa1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a4: 0xa4, # CURRENCY SIGN - 0x00a5: 0xa5, # YEN SIGN - 0x00a6: 0xa6, # BROKEN BAR - 0x00a7: 0xa7, # SECTION SIGN - 0x00a8: 0xa8, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xaa, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xac, # NOT SIGN - 0x00ad: 0xad, # SOFT HYPHEN - 0x00ae: 0xae, # REGISTERED SIGN - 0x00af: 0xaf, # MACRON - 0x00b0: 0xb0, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0xb2, # SUPERSCRIPT TWO - 0x00b3: 0xb3, # SUPERSCRIPT THREE - 0x00b4: 0xb4, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xb6, # PILCROW SIGN - 0x00b7: 0xb7, # MIDDLE DOT - 0x00b8: 0xb8, # CEDILLA - 0x00b9: 0xb9, # SUPERSCRIPT ONE - 0x00ba: 0xba, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xbb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bc: 0xbc, # VULGAR FRACTION ONE QUARTER - 0x00bd: 0xbd, # VULGAR FRACTION ONE HALF - 0x00be: 0xbe, # VULGAR FRACTION THREE QUARTERS - 0x00bf: 0xbf, # INVERTED QUESTION MARK - 0x00c0: 0xc0, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xc1, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xc2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xc3, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0xc4, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0xc5, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xc6, # LATIN CAPITAL LETTER AE - 0x00c7: 0xc7, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xc8, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0xc9, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xcb, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xcc, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xcd, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xcf, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0xd1, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xd2, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xd3, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xd4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xd5, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0xd6, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d7: 0xd7, # MULTIPLICATION SIGN - 0x00d8: 0xd8, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xd9, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xda, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xdb, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0xdc, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xdf, # LATIN SMALL LETTER SHARP S - 0x00e0: 0xe0, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0xe1, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0xe2, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0xe3, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0xe4, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0xe5, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xe6, # LATIN SMALL LETTER AE - 0x00e7: 0xe7, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0xe8, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0xe9, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0xea, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0xeb, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0xec, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0xed, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0xee, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0xef, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0xf1, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0xf2, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0xf3, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0xf4, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0xf5, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0xf6, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xf7, # DIVISION SIGN - 0x00f8: 0xf8, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0xf9, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0xfa, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0xfb, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0xfc, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xff, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x011e: 0xd0, # LATIN CAPITAL LETTER G WITH BREVE - 0x011f: 0xf0, # LATIN SMALL LETTER G WITH BREVE - 0x0130: 0xdd, # LATIN CAPITAL LETTER I WITH DOT ABOVE - 0x0131: 0xfd, # LATIN SMALL LETTER DOTLESS I - 0x015e: 0xde, # LATIN CAPITAL LETTER S WITH CEDILLA - 0x015f: 0xfe, # LATIN SMALL LETTER S WITH CEDILLA -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x00A0: 0xA0, # NO-BREAK SPACE + 0x00A1: 0xA1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A4: 0xA4, # CURRENCY SIGN + 0x00A5: 0xA5, # YEN SIGN + 0x00A6: 0xA6, # BROKEN BAR + 0x00A7: 0xA7, # SECTION SIGN + 0x00A8: 0xA8, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xAA, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xAB, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xAC, # NOT SIGN + 0x00AD: 0xAD, # SOFT HYPHEN + 0x00AE: 0xAE, # REGISTERED SIGN + 0x00AF: 0xAF, # MACRON + 0x00B0: 0xB0, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0xB2, # SUPERSCRIPT TWO + 0x00B3: 0xB3, # SUPERSCRIPT THREE + 0x00B4: 0xB4, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xB6, # PILCROW SIGN + 0x00B7: 0xB7, # MIDDLE DOT + 0x00B8: 0xB8, # CEDILLA + 0x00B9: 0xB9, # SUPERSCRIPT ONE + 0x00BA: 0xBA, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xBB, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BC: 0xBC, # VULGAR FRACTION ONE QUARTER + 0x00BD: 0xBD, # VULGAR FRACTION ONE HALF + 0x00BE: 0xBE, # VULGAR FRACTION THREE QUARTERS + 0x00BF: 0xBF, # INVERTED QUESTION MARK + 0x00C0: 0xC0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xC1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xC2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xC3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0xC4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0xC5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xC6, # LATIN CAPITAL LETTER AE + 0x00C7: 0xC7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xC8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0xC9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xCA, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xCB, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xCC, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xCD, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xCE, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xCF, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0xD1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xD2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xD3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xD4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xD5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0xD6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D7: 0xD7, # MULTIPLICATION SIGN + 0x00D8: 0xD8, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xD9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xDA, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xDB, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0xDC, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xDF, # LATIN SMALL LETTER SHARP S + 0x00E0: 0xE0, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0xE1, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0xE2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0xE3, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0xE4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0xE5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xE6, # LATIN SMALL LETTER AE + 0x00E7: 0xE7, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0xE8, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0xE9, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0xEA, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0xEB, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0xEC, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0xED, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0xEE, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0xEF, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0xF1, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0xF2, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0xF3, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0xF4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0xF5, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0xF6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xF7, # DIVISION SIGN + 0x00F8: 0xF8, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0xF9, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0xFA, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0xFB, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0xFC, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xFF, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x011E: 0xD0, # LATIN CAPITAL LETTER G WITH BREVE + 0x011F: 0xF0, # LATIN SMALL LETTER G WITH BREVE + 0x0130: 0xDD, # LATIN CAPITAL LETTER I WITH DOT ABOVE + 0x0131: 0xFD, # LATIN SMALL LETTER DOTLESS I + 0x015E: 0xDE, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015F: 0xFE, # LATIN SMALL LETTER S WITH CEDILLA +} + diff --git a/Lib/encodings/koi8_r.py b/Lib/encodings/koi8_r.py index fffc471..34341c6 100644 --- a/Lib/encodings/koi8_r.py +++ b/Lib/encodings/koi8_r.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u2500' # 0x80 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u2502' # 0x81 -> BOX DRAWINGS LIGHT VERTICAL u'\u250c' # 0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT @@ -170,12 +170,12 @@ decoding_table = ( u'\u2524' # 0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u252c' # 0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u2534' # 0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL - u'\u253c' # 0x8a -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL - u'\u2580' # 0x8b -> UPPER HALF BLOCK - u'\u2584' # 0x8c -> LOWER HALF BLOCK - u'\u2588' # 0x8d -> FULL BLOCK - u'\u258c' # 0x8e -> LEFT HALF BLOCK - u'\u2590' # 0x8f -> RIGHT HALF BLOCK + u'\u253c' # 0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + u'\u2580' # 0x8B -> UPPER HALF BLOCK + u'\u2584' # 0x8C -> LOWER HALF BLOCK + u'\u2588' # 0x8D -> FULL BLOCK + u'\u258c' # 0x8E -> LEFT HALF BLOCK + u'\u2590' # 0x8F -> RIGHT HALF BLOCK u'\u2591' # 0x90 -> LIGHT SHADE u'\u2592' # 0x91 -> MEDIUM SHADE u'\u2593' # 0x92 -> DARK SHADE @@ -186,108 +186,108 @@ decoding_table = ( u'\u2248' # 0x97 -> ALMOST EQUAL TO u'\u2264' # 0x98 -> LESS-THAN OR EQUAL TO u'\u2265' # 0x99 -> GREATER-THAN OR EQUAL TO - u'\xa0' # 0x9a -> NO-BREAK SPACE - u'\u2321' # 0x9b -> BOTTOM HALF INTEGRAL - u'\xb0' # 0x9c -> DEGREE SIGN - u'\xb2' # 0x9d -> SUPERSCRIPT TWO - u'\xb7' # 0x9e -> MIDDLE DOT - u'\xf7' # 0x9f -> DIVISION SIGN - u'\u2550' # 0xa0 -> BOX DRAWINGS DOUBLE HORIZONTAL - u'\u2551' # 0xa1 -> BOX DRAWINGS DOUBLE VERTICAL - u'\u2552' # 0xa2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE - u'\u0451' # 0xa3 -> CYRILLIC SMALL LETTER IO - u'\u2553' # 0xa4 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE - u'\u2554' # 0xa5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT - u'\u2555' # 0xa6 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE - u'\u2556' # 0xa7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE - u'\u2557' # 0xa8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT - u'\u2558' # 0xa9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE - u'\u2559' # 0xaa -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE - u'\u255a' # 0xab -> BOX DRAWINGS DOUBLE UP AND RIGHT - u'\u255b' # 0xac -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE - u'\u255c' # 0xad -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE - u'\u255d' # 0xae -> BOX DRAWINGS DOUBLE UP AND LEFT - u'\u255e' # 0xaf -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE - u'\u255f' # 0xb0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE - u'\u2560' # 0xb1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT - u'\u2561' # 0xb2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE - u'\u0401' # 0xb3 -> CYRILLIC CAPITAL LETTER IO - u'\u2562' # 0xb4 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE - u'\u2563' # 0xb5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT - u'\u2564' # 0xb6 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE - u'\u2565' # 0xb7 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE - u'\u2566' # 0xb8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL - u'\u2567' # 0xb9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE - u'\u2568' # 0xba -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE - u'\u2569' # 0xbb -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL - u'\u256a' # 0xbc -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE - u'\u256b' # 0xbd -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE - u'\u256c' # 0xbe -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL - u'\xa9' # 0xbf -> COPYRIGHT SIGN - u'\u044e' # 0xc0 -> CYRILLIC SMALL LETTER YU - u'\u0430' # 0xc1 -> CYRILLIC SMALL LETTER A - u'\u0431' # 0xc2 -> CYRILLIC SMALL LETTER BE - u'\u0446' # 0xc3 -> CYRILLIC SMALL LETTER TSE - u'\u0434' # 0xc4 -> CYRILLIC SMALL LETTER DE - u'\u0435' # 0xc5 -> CYRILLIC SMALL LETTER IE - u'\u0444' # 0xc6 -> CYRILLIC SMALL LETTER EF - u'\u0433' # 0xc7 -> CYRILLIC SMALL LETTER GHE - u'\u0445' # 0xc8 -> CYRILLIC SMALL LETTER HA - u'\u0438' # 0xc9 -> CYRILLIC SMALL LETTER I - u'\u0439' # 0xca -> CYRILLIC SMALL LETTER SHORT I - u'\u043a' # 0xcb -> CYRILLIC SMALL LETTER KA - u'\u043b' # 0xcc -> CYRILLIC SMALL LETTER EL - u'\u043c' # 0xcd -> CYRILLIC SMALL LETTER EM - u'\u043d' # 0xce -> CYRILLIC SMALL LETTER EN - u'\u043e' # 0xcf -> CYRILLIC SMALL LETTER O - u'\u043f' # 0xd0 -> CYRILLIC SMALL LETTER PE - u'\u044f' # 0xd1 -> CYRILLIC SMALL LETTER YA - u'\u0440' # 0xd2 -> CYRILLIC SMALL LETTER ER - u'\u0441' # 0xd3 -> CYRILLIC SMALL LETTER ES - u'\u0442' # 0xd4 -> CYRILLIC SMALL LETTER TE - u'\u0443' # 0xd5 -> CYRILLIC SMALL LETTER U - u'\u0436' # 0xd6 -> CYRILLIC SMALL LETTER ZHE - u'\u0432' # 0xd7 -> CYRILLIC SMALL LETTER VE - u'\u044c' # 0xd8 -> CYRILLIC SMALL LETTER SOFT SIGN - u'\u044b' # 0xd9 -> CYRILLIC SMALL LETTER YERU - u'\u0437' # 0xda -> CYRILLIC SMALL LETTER ZE - u'\u0448' # 0xdb -> CYRILLIC SMALL LETTER SHA - u'\u044d' # 0xdc -> CYRILLIC SMALL LETTER E - u'\u0449' # 0xdd -> CYRILLIC SMALL LETTER SHCHA - u'\u0447' # 0xde -> CYRILLIC SMALL LETTER CHE - u'\u044a' # 0xdf -> CYRILLIC SMALL LETTER HARD SIGN - u'\u042e' # 0xe0 -> CYRILLIC CAPITAL LETTER YU - u'\u0410' # 0xe1 -> CYRILLIC CAPITAL LETTER A - u'\u0411' # 0xe2 -> CYRILLIC CAPITAL LETTER BE - u'\u0426' # 0xe3 -> CYRILLIC CAPITAL LETTER TSE - u'\u0414' # 0xe4 -> CYRILLIC CAPITAL LETTER DE - u'\u0415' # 0xe5 -> CYRILLIC CAPITAL LETTER IE - u'\u0424' # 0xe6 -> CYRILLIC CAPITAL LETTER EF - u'\u0413' # 0xe7 -> CYRILLIC CAPITAL LETTER GHE - u'\u0425' # 0xe8 -> CYRILLIC CAPITAL LETTER HA - u'\u0418' # 0xe9 -> CYRILLIC CAPITAL LETTER I - u'\u0419' # 0xea -> CYRILLIC CAPITAL LETTER SHORT I - u'\u041a' # 0xeb -> CYRILLIC CAPITAL LETTER KA - u'\u041b' # 0xec -> CYRILLIC CAPITAL LETTER EL - u'\u041c' # 0xed -> CYRILLIC CAPITAL LETTER EM - u'\u041d' # 0xee -> CYRILLIC CAPITAL LETTER EN - u'\u041e' # 0xef -> CYRILLIC CAPITAL LETTER O - u'\u041f' # 0xf0 -> CYRILLIC CAPITAL LETTER PE - u'\u042f' # 0xf1 -> CYRILLIC CAPITAL LETTER YA - u'\u0420' # 0xf2 -> CYRILLIC CAPITAL LETTER ER - u'\u0421' # 0xf3 -> CYRILLIC CAPITAL LETTER ES - u'\u0422' # 0xf4 -> CYRILLIC CAPITAL LETTER TE - u'\u0423' # 0xf5 -> CYRILLIC CAPITAL LETTER U - u'\u0416' # 0xf6 -> CYRILLIC CAPITAL LETTER ZHE - u'\u0412' # 0xf7 -> CYRILLIC CAPITAL LETTER VE - u'\u042c' # 0xf8 -> CYRILLIC CAPITAL LETTER SOFT SIGN - u'\u042b' # 0xf9 -> CYRILLIC CAPITAL LETTER YERU - u'\u0417' # 0xfa -> CYRILLIC CAPITAL LETTER ZE - u'\u0428' # 0xfb -> CYRILLIC CAPITAL LETTER SHA - u'\u042d' # 0xfc -> CYRILLIC CAPITAL LETTER E - u'\u0429' # 0xfd -> CYRILLIC CAPITAL LETTER SHCHA - u'\u0427' # 0xfe -> CYRILLIC CAPITAL LETTER CHE - u'\u042a' # 0xff -> CYRILLIC CAPITAL LETTER HARD SIGN + u'\xa0' # 0x9A -> NO-BREAK SPACE + u'\u2321' # 0x9B -> BOTTOM HALF INTEGRAL + u'\xb0' # 0x9C -> DEGREE SIGN + u'\xb2' # 0x9D -> SUPERSCRIPT TWO + u'\xb7' # 0x9E -> MIDDLE DOT + u'\xf7' # 0x9F -> DIVISION SIGN + u'\u2550' # 0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL + u'\u2551' # 0xA1 -> BOX DRAWINGS DOUBLE VERTICAL + u'\u2552' # 0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + u'\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO + u'\u2553' # 0xA4 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + u'\u2554' # 0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + u'\u2555' # 0xA6 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + u'\u2556' # 0xA7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + u'\u2557' # 0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT + u'\u2558' # 0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + u'\u2559' # 0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + u'\u255a' # 0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT + u'\u255b' # 0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + u'\u255c' # 0xAD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + u'\u255d' # 0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT + u'\u255e' # 0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + u'\u255f' # 0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + u'\u2560' # 0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + u'\u2561' # 0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + u'\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO + u'\u2562' # 0xB4 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + u'\u2563' # 0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + u'\u2564' # 0xB6 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + u'\u2565' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + u'\u2566' # 0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + u'\u2567' # 0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + u'\u2568' # 0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + u'\u2569' # 0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + u'\u256a' # 0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + u'\u256b' # 0xBD -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + u'\u256c' # 0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + u'\xa9' # 0xBF -> COPYRIGHT SIGN + u'\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU + u'\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A + u'\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE + u'\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE + u'\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE + u'\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE + u'\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF + u'\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE + u'\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA + u'\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I + u'\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I + u'\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA + u'\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL + u'\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM + u'\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN + u'\u043e' # 0xCF -> CYRILLIC SMALL LETTER O + u'\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE + u'\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA + u'\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER + u'\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES + u'\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE + u'\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U + u'\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE + u'\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE + u'\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN + u'\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU + u'\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE + u'\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA + u'\u044d' # 0xDC -> CYRILLIC SMALL LETTER E + u'\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA + u'\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE + u'\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN + u'\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU + u'\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A + u'\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE + u'\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE + u'\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE + u'\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE + u'\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF + u'\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE + u'\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA + u'\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I + u'\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I + u'\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA + u'\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL + u'\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM + u'\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN + u'\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O + u'\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE + u'\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA + u'\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER + u'\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES + u'\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE + u'\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U + u'\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE + u'\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE + u'\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN + u'\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU + u'\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE + u'\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA + u'\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E + u'\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA + u'\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE + u'\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0x9a, # NO-BREAK SPACE - 0x00a9: 0xbf, # COPYRIGHT SIGN - 0x00b0: 0x9c, # DEGREE SIGN - 0x00b2: 0x9d, # SUPERSCRIPT TWO - 0x00b7: 0x9e, # MIDDLE DOT - 0x00f7: 0x9f, # DIVISION SIGN - 0x0401: 0xb3, # CYRILLIC CAPITAL LETTER IO - 0x0410: 0xe1, # CYRILLIC CAPITAL LETTER A - 0x0411: 0xe2, # CYRILLIC CAPITAL LETTER BE - 0x0412: 0xf7, # CYRILLIC CAPITAL LETTER VE - 0x0413: 0xe7, # CYRILLIC CAPITAL LETTER GHE - 0x0414: 0xe4, # CYRILLIC CAPITAL LETTER DE - 0x0415: 0xe5, # CYRILLIC CAPITAL LETTER IE - 0x0416: 0xf6, # CYRILLIC CAPITAL LETTER ZHE - 0x0417: 0xfa, # CYRILLIC CAPITAL LETTER ZE - 0x0418: 0xe9, # CYRILLIC CAPITAL LETTER I - 0x0419: 0xea, # CYRILLIC CAPITAL LETTER SHORT I - 0x041a: 0xeb, # CYRILLIC CAPITAL LETTER KA - 0x041b: 0xec, # CYRILLIC CAPITAL LETTER EL - 0x041c: 0xed, # CYRILLIC CAPITAL LETTER EM - 0x041d: 0xee, # CYRILLIC CAPITAL LETTER EN - 0x041e: 0xef, # CYRILLIC CAPITAL LETTER O - 0x041f: 0xf0, # CYRILLIC CAPITAL LETTER PE - 0x0420: 0xf2, # CYRILLIC CAPITAL LETTER ER - 0x0421: 0xf3, # CYRILLIC CAPITAL LETTER ES - 0x0422: 0xf4, # CYRILLIC CAPITAL LETTER TE - 0x0423: 0xf5, # CYRILLIC CAPITAL LETTER U - 0x0424: 0xe6, # CYRILLIC CAPITAL LETTER EF - 0x0425: 0xe8, # CYRILLIC CAPITAL LETTER HA - 0x0426: 0xe3, # CYRILLIC CAPITAL LETTER TSE - 0x0427: 0xfe, # CYRILLIC CAPITAL LETTER CHE - 0x0428: 0xfb, # CYRILLIC CAPITAL LETTER SHA - 0x0429: 0xfd, # CYRILLIC CAPITAL LETTER SHCHA - 0x042a: 0xff, # CYRILLIC CAPITAL LETTER HARD SIGN - 0x042b: 0xf9, # CYRILLIC CAPITAL LETTER YERU - 0x042c: 0xf8, # CYRILLIC CAPITAL LETTER SOFT SIGN - 0x042d: 0xfc, # CYRILLIC CAPITAL LETTER E - 0x042e: 0xe0, # CYRILLIC CAPITAL LETTER YU - 0x042f: 0xf1, # CYRILLIC CAPITAL LETTER YA - 0x0430: 0xc1, # CYRILLIC SMALL LETTER A - 0x0431: 0xc2, # CYRILLIC SMALL LETTER BE - 0x0432: 0xd7, # CYRILLIC SMALL LETTER VE - 0x0433: 0xc7, # CYRILLIC SMALL LETTER GHE - 0x0434: 0xc4, # CYRILLIC SMALL LETTER DE - 0x0435: 0xc5, # CYRILLIC SMALL LETTER IE - 0x0436: 0xd6, # CYRILLIC SMALL LETTER ZHE - 0x0437: 0xda, # CYRILLIC SMALL LETTER ZE - 0x0438: 0xc9, # CYRILLIC SMALL LETTER I - 0x0439: 0xca, # CYRILLIC SMALL LETTER SHORT I - 0x043a: 0xcb, # CYRILLIC SMALL LETTER KA - 0x043b: 0xcc, # CYRILLIC SMALL LETTER EL - 0x043c: 0xcd, # CYRILLIC SMALL LETTER EM - 0x043d: 0xce, # CYRILLIC SMALL LETTER EN - 0x043e: 0xcf, # CYRILLIC SMALL LETTER O - 0x043f: 0xd0, # CYRILLIC SMALL LETTER PE - 0x0440: 0xd2, # CYRILLIC SMALL LETTER ER - 0x0441: 0xd3, # CYRILLIC SMALL LETTER ES - 0x0442: 0xd4, # CYRILLIC SMALL LETTER TE - 0x0443: 0xd5, # CYRILLIC SMALL LETTER U - 0x0444: 0xc6, # CYRILLIC SMALL LETTER EF - 0x0445: 0xc8, # CYRILLIC SMALL LETTER HA - 0x0446: 0xc3, # CYRILLIC SMALL LETTER TSE - 0x0447: 0xde, # CYRILLIC SMALL LETTER CHE - 0x0448: 0xdb, # CYRILLIC SMALL LETTER SHA - 0x0449: 0xdd, # CYRILLIC SMALL LETTER SHCHA - 0x044a: 0xdf, # CYRILLIC SMALL LETTER HARD SIGN - 0x044b: 0xd9, # CYRILLIC SMALL LETTER YERU - 0x044c: 0xd8, # CYRILLIC SMALL LETTER SOFT SIGN - 0x044d: 0xdc, # CYRILLIC SMALL LETTER E - 0x044e: 0xc0, # CYRILLIC SMALL LETTER YU - 0x044f: 0xd1, # CYRILLIC SMALL LETTER YA - 0x0451: 0xa3, # CYRILLIC SMALL LETTER IO + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0x9A, # NO-BREAK SPACE + 0x00A9: 0xBF, # COPYRIGHT SIGN + 0x00B0: 0x9C, # DEGREE SIGN + 0x00B2: 0x9D, # SUPERSCRIPT TWO + 0x00B7: 0x9E, # MIDDLE DOT + 0x00F7: 0x9F, # DIVISION SIGN + 0x0401: 0xB3, # CYRILLIC CAPITAL LETTER IO + 0x0410: 0xE1, # CYRILLIC CAPITAL LETTER A + 0x0411: 0xE2, # CYRILLIC CAPITAL LETTER BE + 0x0412: 0xF7, # CYRILLIC CAPITAL LETTER VE + 0x0413: 0xE7, # CYRILLIC CAPITAL LETTER GHE + 0x0414: 0xE4, # CYRILLIC CAPITAL LETTER DE + 0x0415: 0xE5, # CYRILLIC CAPITAL LETTER IE + 0x0416: 0xF6, # CYRILLIC CAPITAL LETTER ZHE + 0x0417: 0xFA, # CYRILLIC CAPITAL LETTER ZE + 0x0418: 0xE9, # CYRILLIC CAPITAL LETTER I + 0x0419: 0xEA, # CYRILLIC CAPITAL LETTER SHORT I + 0x041A: 0xEB, # CYRILLIC CAPITAL LETTER KA + 0x041B: 0xEC, # CYRILLIC CAPITAL LETTER EL + 0x041C: 0xED, # CYRILLIC CAPITAL LETTER EM + 0x041D: 0xEE, # CYRILLIC CAPITAL LETTER EN + 0x041E: 0xEF, # CYRILLIC CAPITAL LETTER O + 0x041F: 0xF0, # CYRILLIC CAPITAL LETTER PE + 0x0420: 0xF2, # CYRILLIC CAPITAL LETTER ER + 0x0421: 0xF3, # CYRILLIC CAPITAL LETTER ES + 0x0422: 0xF4, # CYRILLIC CAPITAL LETTER TE + 0x0423: 0xF5, # CYRILLIC CAPITAL LETTER U + 0x0424: 0xE6, # CYRILLIC CAPITAL LETTER EF + 0x0425: 0xE8, # CYRILLIC CAPITAL LETTER HA + 0x0426: 0xE3, # CYRILLIC CAPITAL LETTER TSE + 0x0427: 0xFE, # CYRILLIC CAPITAL LETTER CHE + 0x0428: 0xFB, # CYRILLIC CAPITAL LETTER SHA + 0x0429: 0xFD, # CYRILLIC CAPITAL LETTER SHCHA + 0x042A: 0xFF, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042B: 0xF9, # CYRILLIC CAPITAL LETTER YERU + 0x042C: 0xF8, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042D: 0xFC, # CYRILLIC CAPITAL LETTER E + 0x042E: 0xE0, # CYRILLIC CAPITAL LETTER YU + 0x042F: 0xF1, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0xC1, # CYRILLIC SMALL LETTER A + 0x0431: 0xC2, # CYRILLIC SMALL LETTER BE + 0x0432: 0xD7, # CYRILLIC SMALL LETTER VE + 0x0433: 0xC7, # CYRILLIC SMALL LETTER GHE + 0x0434: 0xC4, # CYRILLIC SMALL LETTER DE + 0x0435: 0xC5, # CYRILLIC SMALL LETTER IE + 0x0436: 0xD6, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0xDA, # CYRILLIC SMALL LETTER ZE + 0x0438: 0xC9, # CYRILLIC SMALL LETTER I + 0x0439: 0xCA, # CYRILLIC SMALL LETTER SHORT I + 0x043A: 0xCB, # CYRILLIC SMALL LETTER KA + 0x043B: 0xCC, # CYRILLIC SMALL LETTER EL + 0x043C: 0xCD, # CYRILLIC SMALL LETTER EM + 0x043D: 0xCE, # CYRILLIC SMALL LETTER EN + 0x043E: 0xCF, # CYRILLIC SMALL LETTER O + 0x043F: 0xD0, # CYRILLIC SMALL LETTER PE + 0x0440: 0xD2, # CYRILLIC SMALL LETTER ER + 0x0441: 0xD3, # CYRILLIC SMALL LETTER ES + 0x0442: 0xD4, # CYRILLIC SMALL LETTER TE + 0x0443: 0xD5, # CYRILLIC SMALL LETTER U + 0x0444: 0xC6, # CYRILLIC SMALL LETTER EF + 0x0445: 0xC8, # CYRILLIC SMALL LETTER HA + 0x0446: 0xC3, # CYRILLIC SMALL LETTER TSE + 0x0447: 0xDE, # CYRILLIC SMALL LETTER CHE + 0x0448: 0xDB, # CYRILLIC SMALL LETTER SHA + 0x0449: 0xDD, # CYRILLIC SMALL LETTER SHCHA + 0x044A: 0xDF, # CYRILLIC SMALL LETTER HARD SIGN + 0x044B: 0xD9, # CYRILLIC SMALL LETTER YERU + 0x044C: 0xD8, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044D: 0xDC, # CYRILLIC SMALL LETTER E + 0x044E: 0xC0, # CYRILLIC SMALL LETTER YU + 0x044F: 0xD1, # CYRILLIC SMALL LETTER YA + 0x0451: 0xA3, # CYRILLIC SMALL LETTER IO 0x2219: 0x95, # BULLET OPERATOR - 0x221a: 0x96, # SQUARE ROOT + 0x221A: 0x96, # SQUARE ROOT 0x2248: 0x97, # ALMOST EQUAL TO 0x2264: 0x98, # LESS-THAN OR EQUAL TO 0x2265: 0x99, # GREATER-THAN OR EQUAL TO 0x2320: 0x93, # TOP HALF INTEGRAL - 0x2321: 0x9b, # BOTTOM HALF INTEGRAL + 0x2321: 0x9B, # BOTTOM HALF INTEGRAL 0x2500: 0x80, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x81, # BOX DRAWINGS LIGHT VERTICAL - 0x250c: 0x82, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x250C: 0x82, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x83, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x84, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x85, # BOX DRAWINGS LIGHT UP AND LEFT - 0x251c: 0x86, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x251C: 0x86, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x87, # BOX DRAWINGS LIGHT VERTICAL AND LEFT - 0x252c: 0x88, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x252C: 0x88, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x89, # BOX DRAWINGS LIGHT UP AND HORIZONTAL - 0x253c: 0x8a, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL - 0x2550: 0xa0, # BOX DRAWINGS DOUBLE HORIZONTAL - 0x2551: 0xa1, # BOX DRAWINGS DOUBLE VERTICAL - 0x2552: 0xa2, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE - 0x2553: 0xa4, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE - 0x2554: 0xa5, # BOX DRAWINGS DOUBLE DOWN AND RIGHT - 0x2555: 0xa6, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE - 0x2556: 0xa7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE - 0x2557: 0xa8, # BOX DRAWINGS DOUBLE DOWN AND LEFT - 0x2558: 0xa9, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE - 0x2559: 0xaa, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE - 0x255a: 0xab, # BOX DRAWINGS DOUBLE UP AND RIGHT - 0x255b: 0xac, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE - 0x255c: 0xad, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE - 0x255d: 0xae, # BOX DRAWINGS DOUBLE UP AND LEFT - 0x255e: 0xaf, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE - 0x255f: 0xb0, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE - 0x2560: 0xb1, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT - 0x2561: 0xb2, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE - 0x2562: 0xb4, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE - 0x2563: 0xb5, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT - 0x2564: 0xb6, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE - 0x2565: 0xb7, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE - 0x2566: 0xb8, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL - 0x2567: 0xb9, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE - 0x2568: 0xba, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE - 0x2569: 0xbb, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL - 0x256a: 0xbc, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE - 0x256b: 0xbd, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE - 0x256c: 0xbe, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL - 0x2580: 0x8b, # UPPER HALF BLOCK - 0x2584: 0x8c, # LOWER HALF BLOCK - 0x2588: 0x8d, # FULL BLOCK - 0x258c: 0x8e, # LEFT HALF BLOCK - 0x2590: 0x8f, # RIGHT HALF BLOCK + 0x253C: 0x8A, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0xA0, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0xA1, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0xA2, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0xA4, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0xA5, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0xA6, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0xA7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0xA8, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0xA9, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0xAA, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255A: 0xAB, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255B: 0xAC, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255C: 0xAD, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255D: 0xAE, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255E: 0xAF, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255F: 0xB0, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0xB1, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0xB2, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0xB4, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0xB5, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0xB6, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0xB7, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0xB8, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0xB9, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0xBA, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0xBB, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256A: 0xBC, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256B: 0xBD, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256C: 0xBE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x8B, # UPPER HALF BLOCK + 0x2584: 0x8C, # LOWER HALF BLOCK + 0x2588: 0x8D, # FULL BLOCK + 0x258C: 0x8E, # LEFT HALF BLOCK + 0x2590: 0x8F, # RIGHT HALF BLOCK 0x2591: 0x90, # LIGHT SHADE 0x2592: 0x91, # MEDIUM SHADE 0x2593: 0x92, # DARK SHADE - 0x25a0: 0x94, # BLACK SQUARE -} \ No newline at end of file + 0x25A0: 0x94, # BLACK SQUARE +} + diff --git a/Lib/encodings/koi8_u.py b/Lib/encodings/koi8_u.py index c5180d0..a9a64f6 100644 --- a/Lib/encodings/koi8_u.py +++ b/Lib/encodings/koi8_u.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\u2500' # 0x80 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u2502' # 0x81 -> BOX DRAWINGS LIGHT VERTICAL u'\u250c' # 0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT @@ -170,12 +170,12 @@ decoding_table = ( u'\u2524' # 0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u252c' # 0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u2534' # 0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL - u'\u253c' # 0x8a -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL - u'\u2580' # 0x8b -> UPPER HALF BLOCK - u'\u2584' # 0x8c -> LOWER HALF BLOCK - u'\u2588' # 0x8d -> FULL BLOCK - u'\u258c' # 0x8e -> LEFT HALF BLOCK - u'\u2590' # 0x8f -> RIGHT HALF BLOCK + u'\u253c' # 0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + u'\u2580' # 0x8B -> UPPER HALF BLOCK + u'\u2584' # 0x8C -> LOWER HALF BLOCK + u'\u2588' # 0x8D -> FULL BLOCK + u'\u258c' # 0x8E -> LEFT HALF BLOCK + u'\u2590' # 0x8F -> RIGHT HALF BLOCK u'\u2591' # 0x90 -> LIGHT SHADE u'\u2592' # 0x91 -> MEDIUM SHADE u'\u2593' # 0x92 -> DARK SHADE @@ -186,108 +186,108 @@ decoding_table = ( u'\u2248' # 0x97 -> ALMOST EQUAL TO u'\u2264' # 0x98 -> LESS-THAN OR EQUAL TO u'\u2265' # 0x99 -> GREATER-THAN OR EQUAL TO - u'\xa0' # 0x9a -> NO-BREAK SPACE - u'\u2321' # 0x9b -> BOTTOM HALF INTEGRAL - u'\xb0' # 0x9c -> DEGREE SIGN - u'\xb2' # 0x9d -> SUPERSCRIPT TWO - u'\xb7' # 0x9e -> MIDDLE DOT - u'\xf7' # 0x9f -> DIVISION SIGN - u'\u2550' # 0xa0 -> BOX DRAWINGS DOUBLE HORIZONTAL - u'\u2551' # 0xa1 -> BOX DRAWINGS DOUBLE VERTICAL - u'\u2552' # 0xa2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE - u'\u0451' # 0xa3 -> CYRILLIC SMALL LETTER IO - u'\u0454' # 0xa4 -> CYRILLIC SMALL LETTER UKRAINIAN IE - u'\u2554' # 0xa5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT - u'\u0456' # 0xa6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - u'\u0457' # 0xa7 -> CYRILLIC SMALL LETTER YI (UKRAINIAN) - u'\u2557' # 0xa8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT - u'\u2558' # 0xa9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE - u'\u2559' # 0xaa -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE - u'\u255a' # 0xab -> BOX DRAWINGS DOUBLE UP AND RIGHT - u'\u255b' # 0xac -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE - u'\u0491' # 0xad -> CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN - u'\u255d' # 0xae -> BOX DRAWINGS DOUBLE UP AND LEFT - u'\u255e' # 0xaf -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE - u'\u255f' # 0xb0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE - u'\u2560' # 0xb1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT - u'\u2561' # 0xb2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE - u'\u0401' # 0xb3 -> CYRILLIC CAPITAL LETTER IO - u'\u0404' # 0xb4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE - u'\u2563' # 0xb5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT - u'\u0406' # 0xb6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - u'\u0407' # 0xb7 -> CYRILLIC CAPITAL LETTER YI (UKRAINIAN) - u'\u2566' # 0xb8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL - u'\u2567' # 0xb9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE - u'\u2568' # 0xba -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE - u'\u2569' # 0xbb -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL - u'\u256a' # 0xbc -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE - u'\u0490' # 0xbd -> CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN - u'\u256c' # 0xbe -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL - u'\xa9' # 0xbf -> COPYRIGHT SIGN - u'\u044e' # 0xc0 -> CYRILLIC SMALL LETTER YU - u'\u0430' # 0xc1 -> CYRILLIC SMALL LETTER A - u'\u0431' # 0xc2 -> CYRILLIC SMALL LETTER BE - u'\u0446' # 0xc3 -> CYRILLIC SMALL LETTER TSE - u'\u0434' # 0xc4 -> CYRILLIC SMALL LETTER DE - u'\u0435' # 0xc5 -> CYRILLIC SMALL LETTER IE - u'\u0444' # 0xc6 -> CYRILLIC SMALL LETTER EF - u'\u0433' # 0xc7 -> CYRILLIC SMALL LETTER GHE - u'\u0445' # 0xc8 -> CYRILLIC SMALL LETTER HA - u'\u0438' # 0xc9 -> CYRILLIC SMALL LETTER I - u'\u0439' # 0xca -> CYRILLIC SMALL LETTER SHORT I - u'\u043a' # 0xcb -> CYRILLIC SMALL LETTER KA - u'\u043b' # 0xcc -> CYRILLIC SMALL LETTER EL - u'\u043c' # 0xcd -> CYRILLIC SMALL LETTER EM - u'\u043d' # 0xce -> CYRILLIC SMALL LETTER EN - u'\u043e' # 0xcf -> CYRILLIC SMALL LETTER O - u'\u043f' # 0xd0 -> CYRILLIC SMALL LETTER PE - u'\u044f' # 0xd1 -> CYRILLIC SMALL LETTER YA - u'\u0440' # 0xd2 -> CYRILLIC SMALL LETTER ER - u'\u0441' # 0xd3 -> CYRILLIC SMALL LETTER ES - u'\u0442' # 0xd4 -> CYRILLIC SMALL LETTER TE - u'\u0443' # 0xd5 -> CYRILLIC SMALL LETTER U - u'\u0436' # 0xd6 -> CYRILLIC SMALL LETTER ZHE - u'\u0432' # 0xd7 -> CYRILLIC SMALL LETTER VE - u'\u044c' # 0xd8 -> CYRILLIC SMALL LETTER SOFT SIGN - u'\u044b' # 0xd9 -> CYRILLIC SMALL LETTER YERU - u'\u0437' # 0xda -> CYRILLIC SMALL LETTER ZE - u'\u0448' # 0xdb -> CYRILLIC SMALL LETTER SHA - u'\u044d' # 0xdc -> CYRILLIC SMALL LETTER E - u'\u0449' # 0xdd -> CYRILLIC SMALL LETTER SHCHA - u'\u0447' # 0xde -> CYRILLIC SMALL LETTER CHE - u'\u044a' # 0xdf -> CYRILLIC SMALL LETTER HARD SIGN - u'\u042e' # 0xe0 -> CYRILLIC CAPITAL LETTER YU - u'\u0410' # 0xe1 -> CYRILLIC CAPITAL LETTER A - u'\u0411' # 0xe2 -> CYRILLIC CAPITAL LETTER BE - u'\u0426' # 0xe3 -> CYRILLIC CAPITAL LETTER TSE - u'\u0414' # 0xe4 -> CYRILLIC CAPITAL LETTER DE - u'\u0415' # 0xe5 -> CYRILLIC CAPITAL LETTER IE - u'\u0424' # 0xe6 -> CYRILLIC CAPITAL LETTER EF - u'\u0413' # 0xe7 -> CYRILLIC CAPITAL LETTER GHE - u'\u0425' # 0xe8 -> CYRILLIC CAPITAL LETTER HA - u'\u0418' # 0xe9 -> CYRILLIC CAPITAL LETTER I - u'\u0419' # 0xea -> CYRILLIC CAPITAL LETTER SHORT I - u'\u041a' # 0xeb -> CYRILLIC CAPITAL LETTER KA - u'\u041b' # 0xec -> CYRILLIC CAPITAL LETTER EL - u'\u041c' # 0xed -> CYRILLIC CAPITAL LETTER EM - u'\u041d' # 0xee -> CYRILLIC CAPITAL LETTER EN - u'\u041e' # 0xef -> CYRILLIC CAPITAL LETTER O - u'\u041f' # 0xf0 -> CYRILLIC CAPITAL LETTER PE - u'\u042f' # 0xf1 -> CYRILLIC CAPITAL LETTER YA - u'\u0420' # 0xf2 -> CYRILLIC CAPITAL LETTER ER - u'\u0421' # 0xf3 -> CYRILLIC CAPITAL LETTER ES - u'\u0422' # 0xf4 -> CYRILLIC CAPITAL LETTER TE - u'\u0423' # 0xf5 -> CYRILLIC CAPITAL LETTER U - u'\u0416' # 0xf6 -> CYRILLIC CAPITAL LETTER ZHE - u'\u0412' # 0xf7 -> CYRILLIC CAPITAL LETTER VE - u'\u042c' # 0xf8 -> CYRILLIC CAPITAL LETTER SOFT SIGN - u'\u042b' # 0xf9 -> CYRILLIC CAPITAL LETTER YERU - u'\u0417' # 0xfa -> CYRILLIC CAPITAL LETTER ZE - u'\u0428' # 0xfb -> CYRILLIC CAPITAL LETTER SHA - u'\u042d' # 0xfc -> CYRILLIC CAPITAL LETTER E - u'\u0429' # 0xfd -> CYRILLIC CAPITAL LETTER SHCHA - u'\u0427' # 0xfe -> CYRILLIC CAPITAL LETTER CHE - u'\u042a' # 0xff -> CYRILLIC CAPITAL LETTER HARD SIGN + u'\xa0' # 0x9A -> NO-BREAK SPACE + u'\u2321' # 0x9B -> BOTTOM HALF INTEGRAL + u'\xb0' # 0x9C -> DEGREE SIGN + u'\xb2' # 0x9D -> SUPERSCRIPT TWO + u'\xb7' # 0x9E -> MIDDLE DOT + u'\xf7' # 0x9F -> DIVISION SIGN + u'\u2550' # 0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL + u'\u2551' # 0xA1 -> BOX DRAWINGS DOUBLE VERTICAL + u'\u2552' # 0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + u'\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO + u'\u0454' # 0xA4 -> CYRILLIC SMALL LETTER UKRAINIAN IE + u'\u2554' # 0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + u'\u0456' # 0xA6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + u'\u0457' # 0xA7 -> CYRILLIC SMALL LETTER YI (UKRAINIAN) + u'\u2557' # 0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT + u'\u2558' # 0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + u'\u2559' # 0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + u'\u255a' # 0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT + u'\u255b' # 0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + u'\u0491' # 0xAD -> CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN + u'\u255d' # 0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT + u'\u255e' # 0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + u'\u255f' # 0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + u'\u2560' # 0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + u'\u2561' # 0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + u'\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO + u'\u0404' # 0xB4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + u'\u2563' # 0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + u'\u0406' # 0xB6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + u'\u0407' # 0xB7 -> CYRILLIC CAPITAL LETTER YI (UKRAINIAN) + u'\u2566' # 0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + u'\u2567' # 0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + u'\u2568' # 0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + u'\u2569' # 0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + u'\u256a' # 0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + u'\u0490' # 0xBD -> CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN + u'\u256c' # 0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + u'\xa9' # 0xBF -> COPYRIGHT SIGN + u'\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU + u'\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A + u'\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE + u'\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE + u'\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE + u'\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE + u'\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF + u'\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE + u'\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA + u'\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I + u'\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I + u'\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA + u'\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL + u'\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM + u'\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN + u'\u043e' # 0xCF -> CYRILLIC SMALL LETTER O + u'\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE + u'\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA + u'\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER + u'\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES + u'\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE + u'\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U + u'\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE + u'\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE + u'\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN + u'\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU + u'\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE + u'\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA + u'\u044d' # 0xDC -> CYRILLIC SMALL LETTER E + u'\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA + u'\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE + u'\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN + u'\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU + u'\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A + u'\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE + u'\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE + u'\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE + u'\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE + u'\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF + u'\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE + u'\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA + u'\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I + u'\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I + u'\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA + u'\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL + u'\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM + u'\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN + u'\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O + u'\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE + u'\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA + u'\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER + u'\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES + u'\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE + u'\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U + u'\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE + u'\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE + u'\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN + u'\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU + u'\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE + u'\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA + u'\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E + u'\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA + u'\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE + u'\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE - 0x00a0: 0x9a, # NO-BREAK SPACE - 0x00a9: 0xbf, # COPYRIGHT SIGN - 0x00b0: 0x9c, # DEGREE SIGN - 0x00b2: 0x9d, # SUPERSCRIPT TWO - 0x00b7: 0x9e, # MIDDLE DOT - 0x00f7: 0x9f, # DIVISION SIGN - 0x0401: 0xb3, # CYRILLIC CAPITAL LETTER IO - 0x0404: 0xb4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE - 0x0406: 0xb6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0407: 0xb7, # CYRILLIC CAPITAL LETTER YI (UKRAINIAN) - 0x0410: 0xe1, # CYRILLIC CAPITAL LETTER A - 0x0411: 0xe2, # CYRILLIC CAPITAL LETTER BE - 0x0412: 0xf7, # CYRILLIC CAPITAL LETTER VE - 0x0413: 0xe7, # CYRILLIC CAPITAL LETTER GHE - 0x0414: 0xe4, # CYRILLIC CAPITAL LETTER DE - 0x0415: 0xe5, # CYRILLIC CAPITAL LETTER IE - 0x0416: 0xf6, # CYRILLIC CAPITAL LETTER ZHE - 0x0417: 0xfa, # CYRILLIC CAPITAL LETTER ZE - 0x0418: 0xe9, # CYRILLIC CAPITAL LETTER I - 0x0419: 0xea, # CYRILLIC CAPITAL LETTER SHORT I - 0x041a: 0xeb, # CYRILLIC CAPITAL LETTER KA - 0x041b: 0xec, # CYRILLIC CAPITAL LETTER EL - 0x041c: 0xed, # CYRILLIC CAPITAL LETTER EM - 0x041d: 0xee, # CYRILLIC CAPITAL LETTER EN - 0x041e: 0xef, # CYRILLIC CAPITAL LETTER O - 0x041f: 0xf0, # CYRILLIC CAPITAL LETTER PE - 0x0420: 0xf2, # CYRILLIC CAPITAL LETTER ER - 0x0421: 0xf3, # CYRILLIC CAPITAL LETTER ES - 0x0422: 0xf4, # CYRILLIC CAPITAL LETTER TE - 0x0423: 0xf5, # CYRILLIC CAPITAL LETTER U - 0x0424: 0xe6, # CYRILLIC CAPITAL LETTER EF - 0x0425: 0xe8, # CYRILLIC CAPITAL LETTER HA - 0x0426: 0xe3, # CYRILLIC CAPITAL LETTER TSE - 0x0427: 0xfe, # CYRILLIC CAPITAL LETTER CHE - 0x0428: 0xfb, # CYRILLIC CAPITAL LETTER SHA - 0x0429: 0xfd, # CYRILLIC CAPITAL LETTER SHCHA - 0x042a: 0xff, # CYRILLIC CAPITAL LETTER HARD SIGN - 0x042b: 0xf9, # CYRILLIC CAPITAL LETTER YERU - 0x042c: 0xf8, # CYRILLIC CAPITAL LETTER SOFT SIGN - 0x042d: 0xfc, # CYRILLIC CAPITAL LETTER E - 0x042e: 0xe0, # CYRILLIC CAPITAL LETTER YU - 0x042f: 0xf1, # CYRILLIC CAPITAL LETTER YA - 0x0430: 0xc1, # CYRILLIC SMALL LETTER A - 0x0431: 0xc2, # CYRILLIC SMALL LETTER BE - 0x0432: 0xd7, # CYRILLIC SMALL LETTER VE - 0x0433: 0xc7, # CYRILLIC SMALL LETTER GHE - 0x0434: 0xc4, # CYRILLIC SMALL LETTER DE - 0x0435: 0xc5, # CYRILLIC SMALL LETTER IE - 0x0436: 0xd6, # CYRILLIC SMALL LETTER ZHE - 0x0437: 0xda, # CYRILLIC SMALL LETTER ZE - 0x0438: 0xc9, # CYRILLIC SMALL LETTER I - 0x0439: 0xca, # CYRILLIC SMALL LETTER SHORT I - 0x043a: 0xcb, # CYRILLIC SMALL LETTER KA - 0x043b: 0xcc, # CYRILLIC SMALL LETTER EL - 0x043c: 0xcd, # CYRILLIC SMALL LETTER EM - 0x043d: 0xce, # CYRILLIC SMALL LETTER EN - 0x043e: 0xcf, # CYRILLIC SMALL LETTER O - 0x043f: 0xd0, # CYRILLIC SMALL LETTER PE - 0x0440: 0xd2, # CYRILLIC SMALL LETTER ER - 0x0441: 0xd3, # CYRILLIC SMALL LETTER ES - 0x0442: 0xd4, # CYRILLIC SMALL LETTER TE - 0x0443: 0xd5, # CYRILLIC SMALL LETTER U - 0x0444: 0xc6, # CYRILLIC SMALL LETTER EF - 0x0445: 0xc8, # CYRILLIC SMALL LETTER HA - 0x0446: 0xc3, # CYRILLIC SMALL LETTER TSE - 0x0447: 0xde, # CYRILLIC SMALL LETTER CHE - 0x0448: 0xdb, # CYRILLIC SMALL LETTER SHA - 0x0449: 0xdd, # CYRILLIC SMALL LETTER SHCHA - 0x044a: 0xdf, # CYRILLIC SMALL LETTER HARD SIGN - 0x044b: 0xd9, # CYRILLIC SMALL LETTER YERU - 0x044c: 0xd8, # CYRILLIC SMALL LETTER SOFT SIGN - 0x044d: 0xdc, # CYRILLIC SMALL LETTER E - 0x044e: 0xc0, # CYRILLIC SMALL LETTER YU - 0x044f: 0xd1, # CYRILLIC SMALL LETTER YA - 0x0451: 0xa3, # CYRILLIC SMALL LETTER IO - 0x0454: 0xa4, # CYRILLIC SMALL LETTER UKRAINIAN IE - 0x0456: 0xa6, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0457: 0xa7, # CYRILLIC SMALL LETTER YI (UKRAINIAN) - 0x0490: 0xbd, # CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN - 0x0491: 0xad, # CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE + 0x00A0: 0x9A, # NO-BREAK SPACE + 0x00A9: 0xBF, # COPYRIGHT SIGN + 0x00B0: 0x9C, # DEGREE SIGN + 0x00B2: 0x9D, # SUPERSCRIPT TWO + 0x00B7: 0x9E, # MIDDLE DOT + 0x00F7: 0x9F, # DIVISION SIGN + 0x0401: 0xB3, # CYRILLIC CAPITAL LETTER IO + 0x0404: 0xB4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0406: 0xB6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0407: 0xB7, # CYRILLIC CAPITAL LETTER YI (UKRAINIAN) + 0x0410: 0xE1, # CYRILLIC CAPITAL LETTER A + 0x0411: 0xE2, # CYRILLIC CAPITAL LETTER BE + 0x0412: 0xF7, # CYRILLIC CAPITAL LETTER VE + 0x0413: 0xE7, # CYRILLIC CAPITAL LETTER GHE + 0x0414: 0xE4, # CYRILLIC CAPITAL LETTER DE + 0x0415: 0xE5, # CYRILLIC CAPITAL LETTER IE + 0x0416: 0xF6, # CYRILLIC CAPITAL LETTER ZHE + 0x0417: 0xFA, # CYRILLIC CAPITAL LETTER ZE + 0x0418: 0xE9, # CYRILLIC CAPITAL LETTER I + 0x0419: 0xEA, # CYRILLIC CAPITAL LETTER SHORT I + 0x041A: 0xEB, # CYRILLIC CAPITAL LETTER KA + 0x041B: 0xEC, # CYRILLIC CAPITAL LETTER EL + 0x041C: 0xED, # CYRILLIC CAPITAL LETTER EM + 0x041D: 0xEE, # CYRILLIC CAPITAL LETTER EN + 0x041E: 0xEF, # CYRILLIC CAPITAL LETTER O + 0x041F: 0xF0, # CYRILLIC CAPITAL LETTER PE + 0x0420: 0xF2, # CYRILLIC CAPITAL LETTER ER + 0x0421: 0xF3, # CYRILLIC CAPITAL LETTER ES + 0x0422: 0xF4, # CYRILLIC CAPITAL LETTER TE + 0x0423: 0xF5, # CYRILLIC CAPITAL LETTER U + 0x0424: 0xE6, # CYRILLIC CAPITAL LETTER EF + 0x0425: 0xE8, # CYRILLIC CAPITAL LETTER HA + 0x0426: 0xE3, # CYRILLIC CAPITAL LETTER TSE + 0x0427: 0xFE, # CYRILLIC CAPITAL LETTER CHE + 0x0428: 0xFB, # CYRILLIC CAPITAL LETTER SHA + 0x0429: 0xFD, # CYRILLIC CAPITAL LETTER SHCHA + 0x042A: 0xFF, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042B: 0xF9, # CYRILLIC CAPITAL LETTER YERU + 0x042C: 0xF8, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042D: 0xFC, # CYRILLIC CAPITAL LETTER E + 0x042E: 0xE0, # CYRILLIC CAPITAL LETTER YU + 0x042F: 0xF1, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0xC1, # CYRILLIC SMALL LETTER A + 0x0431: 0xC2, # CYRILLIC SMALL LETTER BE + 0x0432: 0xD7, # CYRILLIC SMALL LETTER VE + 0x0433: 0xC7, # CYRILLIC SMALL LETTER GHE + 0x0434: 0xC4, # CYRILLIC SMALL LETTER DE + 0x0435: 0xC5, # CYRILLIC SMALL LETTER IE + 0x0436: 0xD6, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0xDA, # CYRILLIC SMALL LETTER ZE + 0x0438: 0xC9, # CYRILLIC SMALL LETTER I + 0x0439: 0xCA, # CYRILLIC SMALL LETTER SHORT I + 0x043A: 0xCB, # CYRILLIC SMALL LETTER KA + 0x043B: 0xCC, # CYRILLIC SMALL LETTER EL + 0x043C: 0xCD, # CYRILLIC SMALL LETTER EM + 0x043D: 0xCE, # CYRILLIC SMALL LETTER EN + 0x043E: 0xCF, # CYRILLIC SMALL LETTER O + 0x043F: 0xD0, # CYRILLIC SMALL LETTER PE + 0x0440: 0xD2, # CYRILLIC SMALL LETTER ER + 0x0441: 0xD3, # CYRILLIC SMALL LETTER ES + 0x0442: 0xD4, # CYRILLIC SMALL LETTER TE + 0x0443: 0xD5, # CYRILLIC SMALL LETTER U + 0x0444: 0xC6, # CYRILLIC SMALL LETTER EF + 0x0445: 0xC8, # CYRILLIC SMALL LETTER HA + 0x0446: 0xC3, # CYRILLIC SMALL LETTER TSE + 0x0447: 0xDE, # CYRILLIC SMALL LETTER CHE + 0x0448: 0xDB, # CYRILLIC SMALL LETTER SHA + 0x0449: 0xDD, # CYRILLIC SMALL LETTER SHCHA + 0x044A: 0xDF, # CYRILLIC SMALL LETTER HARD SIGN + 0x044B: 0xD9, # CYRILLIC SMALL LETTER YERU + 0x044C: 0xD8, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044D: 0xDC, # CYRILLIC SMALL LETTER E + 0x044E: 0xC0, # CYRILLIC SMALL LETTER YU + 0x044F: 0xD1, # CYRILLIC SMALL LETTER YA + 0x0451: 0xA3, # CYRILLIC SMALL LETTER IO + 0x0454: 0xA4, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0456: 0xA6, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0457: 0xA7, # CYRILLIC SMALL LETTER YI (UKRAINIAN) + 0x0490: 0xBD, # CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN + 0x0491: 0xAD, # CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN 0x2219: 0x95, # BULLET OPERATOR - 0x221a: 0x96, # SQUARE ROOT + 0x221A: 0x96, # SQUARE ROOT 0x2248: 0x97, # ALMOST EQUAL TO 0x2264: 0x98, # LESS-THAN OR EQUAL TO 0x2265: 0x99, # GREATER-THAN OR EQUAL TO 0x2320: 0x93, # TOP HALF INTEGRAL - 0x2321: 0x9b, # BOTTOM HALF INTEGRAL + 0x2321: 0x9B, # BOTTOM HALF INTEGRAL 0x2500: 0x80, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x81, # BOX DRAWINGS LIGHT VERTICAL - 0x250c: 0x82, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x250C: 0x82, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x83, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x84, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x85, # BOX DRAWINGS LIGHT UP AND LEFT - 0x251c: 0x86, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x251C: 0x86, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x87, # BOX DRAWINGS LIGHT VERTICAL AND LEFT - 0x252c: 0x88, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x252C: 0x88, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x89, # BOX DRAWINGS LIGHT UP AND HORIZONTAL - 0x253c: 0x8a, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL - 0x2550: 0xa0, # BOX DRAWINGS DOUBLE HORIZONTAL - 0x2551: 0xa1, # BOX DRAWINGS DOUBLE VERTICAL - 0x2552: 0xa2, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE - 0x2554: 0xa5, # BOX DRAWINGS DOUBLE DOWN AND RIGHT - 0x2557: 0xa8, # BOX DRAWINGS DOUBLE DOWN AND LEFT - 0x2558: 0xa9, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE - 0x2559: 0xaa, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE - 0x255a: 0xab, # BOX DRAWINGS DOUBLE UP AND RIGHT - 0x255b: 0xac, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE - 0x255d: 0xae, # BOX DRAWINGS DOUBLE UP AND LEFT - 0x255e: 0xaf, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE - 0x255f: 0xb0, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE - 0x2560: 0xb1, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT - 0x2561: 0xb2, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE - 0x2563: 0xb5, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT - 0x2566: 0xb8, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL - 0x2567: 0xb9, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE - 0x2568: 0xba, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE - 0x2569: 0xbb, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL - 0x256a: 0xbc, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE - 0x256c: 0xbe, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL - 0x2580: 0x8b, # UPPER HALF BLOCK - 0x2584: 0x8c, # LOWER HALF BLOCK - 0x2588: 0x8d, # FULL BLOCK - 0x258c: 0x8e, # LEFT HALF BLOCK - 0x2590: 0x8f, # RIGHT HALF BLOCK + 0x253C: 0x8A, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0xA0, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0xA1, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0xA2, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2554: 0xA5, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0xA8, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0xA9, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0xAA, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255A: 0xAB, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255B: 0xAC, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255D: 0xAE, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255E: 0xAF, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255F: 0xB0, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0xB1, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0xB2, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2563: 0xB5, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0xB8, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0xB9, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0xBA, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0xBB, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256A: 0xBC, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256C: 0xBE, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x8B, # UPPER HALF BLOCK + 0x2584: 0x8C, # LOWER HALF BLOCK + 0x2588: 0x8D, # FULL BLOCK + 0x258C: 0x8E, # LEFT HALF BLOCK + 0x2590: 0x8F, # RIGHT HALF BLOCK 0x2591: 0x90, # LIGHT SHADE 0x2592: 0x91, # MEDIUM SHADE 0x2593: 0x92, # DARK SHADE - 0x25a0: 0x94, # BLACK SQUARE -} \ No newline at end of file + 0x25A0: 0x94, # BLACK SQUARE +} + diff --git a/Lib/encodings/mac_centeuro.py b/Lib/encodings/mac_centeuro.py index 08a21af..dffc025 100644 --- a/Lib/encodings/mac_centeuro.py +++ b/Lib/encodings/mac_centeuro.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\u0100' # 0x81 -> LATIN CAPITAL LETTER A WITH MACRON u'\u0101' # 0x82 -> LATIN SMALL LETTER A WITH MACRON @@ -170,12 +170,12 @@ decoding_table = ( u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\u0105' # 0x88 -> LATIN SMALL LETTER A WITH OGONEK u'\u010c' # 0x89 -> LATIN CAPITAL LETTER C WITH CARON - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\u010d' # 0x8b -> LATIN SMALL LETTER C WITH CARON - u'\u0106' # 0x8c -> LATIN CAPITAL LETTER C WITH ACUTE - u'\u0107' # 0x8d -> LATIN SMALL LETTER C WITH ACUTE - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\u0179' # 0x8f -> LATIN CAPITAL LETTER Z WITH ACUTE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\u010d' # 0x8B -> LATIN SMALL LETTER C WITH CARON + u'\u0106' # 0x8C -> LATIN CAPITAL LETTER C WITH ACUTE + u'\u0107' # 0x8D -> LATIN SMALL LETTER C WITH ACUTE + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE u'\u017a' # 0x90 -> LATIN SMALL LETTER Z WITH ACUTE u'\u010e' # 0x91 -> LATIN CAPITAL LETTER D WITH CARON u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE @@ -186,108 +186,108 @@ decoding_table = ( u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\u0117' # 0x98 -> LATIN SMALL LETTER E WITH DOT ABOVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf5' # 0x9b -> LATIN SMALL LETTER O WITH TILDE - u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE - u'\u011a' # 0x9d -> LATIN CAPITAL LETTER E WITH CARON - u'\u011b' # 0x9e -> LATIN SMALL LETTER E WITH CARON - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u2020' # 0xa0 -> DAGGER - u'\xb0' # 0xa1 -> DEGREE SIGN - u'\u0118' # 0xa2 -> LATIN CAPITAL LETTER E WITH OGONEK - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa7' # 0xa4 -> SECTION SIGN - u'\u2022' # 0xa5 -> BULLET - u'\xb6' # 0xa6 -> PILCROW SIGN - u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u2122' # 0xaa -> TRADE MARK SIGN - u'\u0119' # 0xab -> LATIN SMALL LETTER E WITH OGONEK - u'\xa8' # 0xac -> DIAERESIS - u'\u2260' # 0xad -> NOT EQUAL TO - u'\u0123' # 0xae -> LATIN SMALL LETTER G WITH CEDILLA - u'\u012e' # 0xaf -> LATIN CAPITAL LETTER I WITH OGONEK - u'\u012f' # 0xb0 -> LATIN SMALL LETTER I WITH OGONEK - u'\u012a' # 0xb1 -> LATIN CAPITAL LETTER I WITH MACRON - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\u012b' # 0xb4 -> LATIN SMALL LETTER I WITH MACRON - u'\u0136' # 0xb5 -> LATIN CAPITAL LETTER K WITH CEDILLA - u'\u2202' # 0xb6 -> PARTIAL DIFFERENTIAL - u'\u2211' # 0xb7 -> N-ARY SUMMATION - u'\u0142' # 0xb8 -> LATIN SMALL LETTER L WITH STROKE - u'\u013b' # 0xb9 -> LATIN CAPITAL LETTER L WITH CEDILLA - u'\u013c' # 0xba -> LATIN SMALL LETTER L WITH CEDILLA - u'\u013d' # 0xbb -> LATIN CAPITAL LETTER L WITH CARON - u'\u013e' # 0xbc -> LATIN SMALL LETTER L WITH CARON - u'\u0139' # 0xbd -> LATIN CAPITAL LETTER L WITH ACUTE - u'\u013a' # 0xbe -> LATIN SMALL LETTER L WITH ACUTE - u'\u0145' # 0xbf -> LATIN CAPITAL LETTER N WITH CEDILLA - u'\u0146' # 0xc0 -> LATIN SMALL LETTER N WITH CEDILLA - u'\u0143' # 0xc1 -> LATIN CAPITAL LETTER N WITH ACUTE - u'\xac' # 0xc2 -> NOT SIGN - u'\u221a' # 0xc3 -> SQUARE ROOT - u'\u0144' # 0xc4 -> LATIN SMALL LETTER N WITH ACUTE - u'\u0147' # 0xc5 -> LATIN CAPITAL LETTER N WITH CARON - u'\u2206' # 0xc6 -> INCREMENT - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\u0148' # 0xcb -> LATIN SMALL LETTER N WITH CARON - u'\u0150' # 0xcc -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - u'\xd5' # 0xcd -> LATIN CAPITAL LETTER O WITH TILDE - u'\u0151' # 0xce -> LATIN SMALL LETTER O WITH DOUBLE ACUTE - u'\u014c' # 0xcf -> LATIN CAPITAL LETTER O WITH MACRON - u'\u2013' # 0xd0 -> EN DASH - u'\u2014' # 0xd1 -> EM DASH - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u25ca' # 0xd7 -> LOZENGE - u'\u014d' # 0xd8 -> LATIN SMALL LETTER O WITH MACRON - u'\u0154' # 0xd9 -> LATIN CAPITAL LETTER R WITH ACUTE - u'\u0155' # 0xda -> LATIN SMALL LETTER R WITH ACUTE - u'\u0158' # 0xdb -> LATIN CAPITAL LETTER R WITH CARON - u'\u2039' # 0xdc -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u203a' # 0xdd -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u0159' # 0xde -> LATIN SMALL LETTER R WITH CARON - u'\u0156' # 0xdf -> LATIN CAPITAL LETTER R WITH CEDILLA - u'\u0157' # 0xe0 -> LATIN SMALL LETTER R WITH CEDILLA - u'\u0160' # 0xe1 -> LATIN CAPITAL LETTER S WITH CARON - u'\u201a' # 0xe2 -> SINGLE LOW-9 QUOTATION MARK - u'\u201e' # 0xe3 -> DOUBLE LOW-9 QUOTATION MARK - u'\u0161' # 0xe4 -> LATIN SMALL LETTER S WITH CARON - u'\u015a' # 0xe5 -> LATIN CAPITAL LETTER S WITH ACUTE - u'\u015b' # 0xe6 -> LATIN SMALL LETTER S WITH ACUTE - u'\xc1' # 0xe7 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\u0164' # 0xe8 -> LATIN CAPITAL LETTER T WITH CARON - u'\u0165' # 0xe9 -> LATIN SMALL LETTER T WITH CARON - u'\xcd' # 0xea -> LATIN CAPITAL LETTER I WITH ACUTE - u'\u017d' # 0xeb -> LATIN CAPITAL LETTER Z WITH CARON - u'\u017e' # 0xec -> LATIN SMALL LETTER Z WITH CARON - u'\u016a' # 0xed -> LATIN CAPITAL LETTER U WITH MACRON - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\u016b' # 0xf0 -> LATIN SMALL LETTER U WITH MACRON - u'\u016e' # 0xf1 -> LATIN CAPITAL LETTER U WITH RING ABOVE - u'\xda' # 0xf2 -> LATIN CAPITAL LETTER U WITH ACUTE - u'\u016f' # 0xf3 -> LATIN SMALL LETTER U WITH RING ABOVE - u'\u0170' # 0xf4 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - u'\u0171' # 0xf5 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE - u'\u0172' # 0xf6 -> LATIN CAPITAL LETTER U WITH OGONEK - u'\u0173' # 0xf7 -> LATIN SMALL LETTER U WITH OGONEK - u'\xdd' # 0xf8 -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xfd' # 0xf9 -> LATIN SMALL LETTER Y WITH ACUTE - u'\u0137' # 0xfa -> LATIN SMALL LETTER K WITH CEDILLA - u'\u017b' # 0xfb -> LATIN CAPITAL LETTER Z WITH DOT ABOVE - u'\u0141' # 0xfc -> LATIN CAPITAL LETTER L WITH STROKE - u'\u017c' # 0xfd -> LATIN SMALL LETTER Z WITH DOT ABOVE - u'\u0122' # 0xfe -> LATIN CAPITAL LETTER G WITH CEDILLA - u'\u02c7' # 0xff -> CARON + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + u'\u011a' # 0x9D -> LATIN CAPITAL LETTER E WITH CARON + u'\u011b' # 0x9E -> LATIN SMALL LETTER E WITH CARON + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u2020' # 0xA0 -> DAGGER + u'\xb0' # 0xA1 -> DEGREE SIGN + u'\u0118' # 0xA2 -> LATIN CAPITAL LETTER E WITH OGONEK + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa7' # 0xA4 -> SECTION SIGN + u'\u2022' # 0xA5 -> BULLET + u'\xb6' # 0xA6 -> PILCROW SIGN + u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u2122' # 0xAA -> TRADE MARK SIGN + u'\u0119' # 0xAB -> LATIN SMALL LETTER E WITH OGONEK + u'\xa8' # 0xAC -> DIAERESIS + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\u0123' # 0xAE -> LATIN SMALL LETTER G WITH CEDILLA + u'\u012e' # 0xAF -> LATIN CAPITAL LETTER I WITH OGONEK + u'\u012f' # 0xB0 -> LATIN SMALL LETTER I WITH OGONEK + u'\u012a' # 0xB1 -> LATIN CAPITAL LETTER I WITH MACRON + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON + u'\u0136' # 0xB5 -> LATIN CAPITAL LETTER K WITH CEDILLA + u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + u'\u2211' # 0xB7 -> N-ARY SUMMATION + u'\u0142' # 0xB8 -> LATIN SMALL LETTER L WITH STROKE + u'\u013b' # 0xB9 -> LATIN CAPITAL LETTER L WITH CEDILLA + u'\u013c' # 0xBA -> LATIN SMALL LETTER L WITH CEDILLA + u'\u013d' # 0xBB -> LATIN CAPITAL LETTER L WITH CARON + u'\u013e' # 0xBC -> LATIN SMALL LETTER L WITH CARON + u'\u0139' # 0xBD -> LATIN CAPITAL LETTER L WITH ACUTE + u'\u013a' # 0xBE -> LATIN SMALL LETTER L WITH ACUTE + u'\u0145' # 0xBF -> LATIN CAPITAL LETTER N WITH CEDILLA + u'\u0146' # 0xC0 -> LATIN SMALL LETTER N WITH CEDILLA + u'\u0143' # 0xC1 -> LATIN CAPITAL LETTER N WITH ACUTE + u'\xac' # 0xC2 -> NOT SIGN + u'\u221a' # 0xC3 -> SQUARE ROOT + u'\u0144' # 0xC4 -> LATIN SMALL LETTER N WITH ACUTE + u'\u0147' # 0xC5 -> LATIN CAPITAL LETTER N WITH CARON + u'\u2206' # 0xC6 -> INCREMENT + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\u0148' # 0xCB -> LATIN SMALL LETTER N WITH CARON + u'\u0150' # 0xCC -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + u'\u0151' # 0xCE -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + u'\u014c' # 0xCF -> LATIN CAPITAL LETTER O WITH MACRON + u'\u2013' # 0xD0 -> EN DASH + u'\u2014' # 0xD1 -> EM DASH + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u25ca' # 0xD7 -> LOZENGE + u'\u014d' # 0xD8 -> LATIN SMALL LETTER O WITH MACRON + u'\u0154' # 0xD9 -> LATIN CAPITAL LETTER R WITH ACUTE + u'\u0155' # 0xDA -> LATIN SMALL LETTER R WITH ACUTE + u'\u0158' # 0xDB -> LATIN CAPITAL LETTER R WITH CARON + u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u0159' # 0xDE -> LATIN SMALL LETTER R WITH CARON + u'\u0156' # 0xDF -> LATIN CAPITAL LETTER R WITH CEDILLA + u'\u0157' # 0xE0 -> LATIN SMALL LETTER R WITH CEDILLA + u'\u0160' # 0xE1 -> LATIN CAPITAL LETTER S WITH CARON + u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + u'\u0161' # 0xE4 -> LATIN SMALL LETTER S WITH CARON + u'\u015a' # 0xE5 -> LATIN CAPITAL LETTER S WITH ACUTE + u'\u015b' # 0xE6 -> LATIN SMALL LETTER S WITH ACUTE + u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\u0164' # 0xE8 -> LATIN CAPITAL LETTER T WITH CARON + u'\u0165' # 0xE9 -> LATIN SMALL LETTER T WITH CARON + u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + u'\u017d' # 0xEB -> LATIN CAPITAL LETTER Z WITH CARON + u'\u017e' # 0xEC -> LATIN SMALL LETTER Z WITH CARON + u'\u016a' # 0xED -> LATIN CAPITAL LETTER U WITH MACRON + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\u016b' # 0xF0 -> LATIN SMALL LETTER U WITH MACRON + u'\u016e' # 0xF1 -> LATIN CAPITAL LETTER U WITH RING ABOVE + u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + u'\u016f' # 0xF3 -> LATIN SMALL LETTER U WITH RING ABOVE + u'\u0170' # 0xF4 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + u'\u0171' # 0xF5 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + u'\u0172' # 0xF6 -> LATIN CAPITAL LETTER U WITH OGONEK + u'\u0173' # 0xF7 -> LATIN SMALL LETTER U WITH OGONEK + u'\xdd' # 0xF8 -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xfd' # 0xF9 -> LATIN SMALL LETTER Y WITH ACUTE + u'\u0137' # 0xFA -> LATIN SMALL LETTER K WITH CEDILLA + u'\u017b' # 0xFB -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + u'\u0141' # 0xFC -> LATIN CAPITAL LETTER L WITH STROKE + u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE + u'\u0122' # 0xFE -> LATIN CAPITAL LETTER G WITH CEDILLA + u'\u02c7' # 0xFF -> CARON ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a3: 0xa3, # POUND SIGN - 0x00a7: 0xa4, # SECTION SIGN - 0x00a8: 0xac, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00b0: 0xa1, # DEGREE SIGN - 0x00b6: 0xa6, # PILCROW SIGN - 0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00c1: 0xe7, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00cd: 0xea, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xcd, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00da: 0xf2, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xf8, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00df: 0xa7, # LATIN SMALL LETTER SHARP S - 0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE - 0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0x9b, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xd6, # DIVISION SIGN - 0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xf9, # LATIN SMALL LETTER Y WITH ACUTE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A3: 0xA3, # POUND SIGN + 0x00A7: 0xA4, # SECTION SIGN + 0x00A8: 0xAC, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00B0: 0xA1, # DEGREE SIGN + 0x00B6: 0xA6, # PILCROW SIGN + 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xF8, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S + 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE + 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xD6, # DIVISION SIGN + 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xF9, # LATIN SMALL LETTER Y WITH ACUTE 0x0100: 0x81, # LATIN CAPITAL LETTER A WITH MACRON 0x0101: 0x82, # LATIN SMALL LETTER A WITH MACRON 0x0104: 0x84, # LATIN CAPITAL LETTER A WITH OGONEK 0x0105: 0x88, # LATIN SMALL LETTER A WITH OGONEK - 0x0106: 0x8c, # LATIN CAPITAL LETTER C WITH ACUTE - 0x0107: 0x8d, # LATIN SMALL LETTER C WITH ACUTE - 0x010c: 0x89, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0x8b, # LATIN SMALL LETTER C WITH CARON - 0x010e: 0x91, # LATIN CAPITAL LETTER D WITH CARON - 0x010f: 0x93, # LATIN SMALL LETTER D WITH CARON + 0x0106: 0x8C, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0x8D, # LATIN SMALL LETTER C WITH ACUTE + 0x010C: 0x89, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0x8B, # LATIN SMALL LETTER C WITH CARON + 0x010E: 0x91, # LATIN CAPITAL LETTER D WITH CARON + 0x010F: 0x93, # LATIN SMALL LETTER D WITH CARON 0x0112: 0x94, # LATIN CAPITAL LETTER E WITH MACRON 0x0113: 0x95, # LATIN SMALL LETTER E WITH MACRON 0x0116: 0x96, # LATIN CAPITAL LETTER E WITH DOT ABOVE 0x0117: 0x98, # LATIN SMALL LETTER E WITH DOT ABOVE - 0x0118: 0xa2, # LATIN CAPITAL LETTER E WITH OGONEK - 0x0119: 0xab, # LATIN SMALL LETTER E WITH OGONEK - 0x011a: 0x9d, # LATIN CAPITAL LETTER E WITH CARON - 0x011b: 0x9e, # LATIN SMALL LETTER E WITH CARON - 0x0122: 0xfe, # LATIN CAPITAL LETTER G WITH CEDILLA - 0x0123: 0xae, # LATIN SMALL LETTER G WITH CEDILLA - 0x012a: 0xb1, # LATIN CAPITAL LETTER I WITH MACRON - 0x012b: 0xb4, # LATIN SMALL LETTER I WITH MACRON - 0x012e: 0xaf, # LATIN CAPITAL LETTER I WITH OGONEK - 0x012f: 0xb0, # LATIN SMALL LETTER I WITH OGONEK - 0x0136: 0xb5, # LATIN CAPITAL LETTER K WITH CEDILLA - 0x0137: 0xfa, # LATIN SMALL LETTER K WITH CEDILLA - 0x0139: 0xbd, # LATIN CAPITAL LETTER L WITH ACUTE - 0x013a: 0xbe, # LATIN SMALL LETTER L WITH ACUTE - 0x013b: 0xb9, # LATIN CAPITAL LETTER L WITH CEDILLA - 0x013c: 0xba, # LATIN SMALL LETTER L WITH CEDILLA - 0x013d: 0xbb, # LATIN CAPITAL LETTER L WITH CARON - 0x013e: 0xbc, # LATIN SMALL LETTER L WITH CARON - 0x0141: 0xfc, # LATIN CAPITAL LETTER L WITH STROKE - 0x0142: 0xb8, # LATIN SMALL LETTER L WITH STROKE - 0x0143: 0xc1, # LATIN CAPITAL LETTER N WITH ACUTE - 0x0144: 0xc4, # LATIN SMALL LETTER N WITH ACUTE - 0x0145: 0xbf, # LATIN CAPITAL LETTER N WITH CEDILLA - 0x0146: 0xc0, # LATIN SMALL LETTER N WITH CEDILLA - 0x0147: 0xc5, # LATIN CAPITAL LETTER N WITH CARON - 0x0148: 0xcb, # LATIN SMALL LETTER N WITH CARON - 0x014c: 0xcf, # LATIN CAPITAL LETTER O WITH MACRON - 0x014d: 0xd8, # LATIN SMALL LETTER O WITH MACRON - 0x0150: 0xcc, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - 0x0151: 0xce, # LATIN SMALL LETTER O WITH DOUBLE ACUTE - 0x0154: 0xd9, # LATIN CAPITAL LETTER R WITH ACUTE - 0x0155: 0xda, # LATIN SMALL LETTER R WITH ACUTE - 0x0156: 0xdf, # LATIN CAPITAL LETTER R WITH CEDILLA - 0x0157: 0xe0, # LATIN SMALL LETTER R WITH CEDILLA - 0x0158: 0xdb, # LATIN CAPITAL LETTER R WITH CARON - 0x0159: 0xde, # LATIN SMALL LETTER R WITH CARON - 0x015a: 0xe5, # LATIN CAPITAL LETTER S WITH ACUTE - 0x015b: 0xe6, # LATIN SMALL LETTER S WITH ACUTE - 0x0160: 0xe1, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xe4, # LATIN SMALL LETTER S WITH CARON - 0x0164: 0xe8, # LATIN CAPITAL LETTER T WITH CARON - 0x0165: 0xe9, # LATIN SMALL LETTER T WITH CARON - 0x016a: 0xed, # LATIN CAPITAL LETTER U WITH MACRON - 0x016b: 0xf0, # LATIN SMALL LETTER U WITH MACRON - 0x016e: 0xf1, # LATIN CAPITAL LETTER U WITH RING ABOVE - 0x016f: 0xf3, # LATIN SMALL LETTER U WITH RING ABOVE - 0x0170: 0xf4, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - 0x0171: 0xf5, # LATIN SMALL LETTER U WITH DOUBLE ACUTE - 0x0172: 0xf6, # LATIN CAPITAL LETTER U WITH OGONEK - 0x0173: 0xf7, # LATIN SMALL LETTER U WITH OGONEK - 0x0179: 0x8f, # LATIN CAPITAL LETTER Z WITH ACUTE - 0x017a: 0x90, # LATIN SMALL LETTER Z WITH ACUTE - 0x017b: 0xfb, # LATIN CAPITAL LETTER Z WITH DOT ABOVE - 0x017c: 0xfd, # LATIN SMALL LETTER Z WITH DOT ABOVE - 0x017d: 0xeb, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xec, # LATIN SMALL LETTER Z WITH CARON - 0x02c7: 0xff, # CARON - 0x2013: 0xd0, # EN DASH - 0x2014: 0xd1, # EM DASH - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0xe2, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xe3, # DOUBLE LOW-9 QUOTATION MARK - 0x2020: 0xa0, # DAGGER - 0x2022: 0xa5, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS - 0x2039: 0xdc, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0xdd, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x2122: 0xaa, # TRADE MARK SIGN - 0x2202: 0xb6, # PARTIAL DIFFERENTIAL - 0x2206: 0xc6, # INCREMENT - 0x2211: 0xb7, # N-ARY SUMMATION - 0x221a: 0xc3, # SQUARE ROOT - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO - 0x25ca: 0xd7, # LOZENGE -} \ No newline at end of file + 0x0118: 0xA2, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0xAB, # LATIN SMALL LETTER E WITH OGONEK + 0x011A: 0x9D, # LATIN CAPITAL LETTER E WITH CARON + 0x011B: 0x9E, # LATIN SMALL LETTER E WITH CARON + 0x0122: 0xFE, # LATIN CAPITAL LETTER G WITH CEDILLA + 0x0123: 0xAE, # LATIN SMALL LETTER G WITH CEDILLA + 0x012A: 0xB1, # LATIN CAPITAL LETTER I WITH MACRON + 0x012B: 0xB4, # LATIN SMALL LETTER I WITH MACRON + 0x012E: 0xAF, # LATIN CAPITAL LETTER I WITH OGONEK + 0x012F: 0xB0, # LATIN SMALL LETTER I WITH OGONEK + 0x0136: 0xB5, # LATIN CAPITAL LETTER K WITH CEDILLA + 0x0137: 0xFA, # LATIN SMALL LETTER K WITH CEDILLA + 0x0139: 0xBD, # LATIN CAPITAL LETTER L WITH ACUTE + 0x013A: 0xBE, # LATIN SMALL LETTER L WITH ACUTE + 0x013B: 0xB9, # LATIN CAPITAL LETTER L WITH CEDILLA + 0x013C: 0xBA, # LATIN SMALL LETTER L WITH CEDILLA + 0x013D: 0xBB, # LATIN CAPITAL LETTER L WITH CARON + 0x013E: 0xBC, # LATIN SMALL LETTER L WITH CARON + 0x0141: 0xFC, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0xB8, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0xC1, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0xC4, # LATIN SMALL LETTER N WITH ACUTE + 0x0145: 0xBF, # LATIN CAPITAL LETTER N WITH CEDILLA + 0x0146: 0xC0, # LATIN SMALL LETTER N WITH CEDILLA + 0x0147: 0xC5, # LATIN CAPITAL LETTER N WITH CARON + 0x0148: 0xCB, # LATIN SMALL LETTER N WITH CARON + 0x014C: 0xCF, # LATIN CAPITAL LETTER O WITH MACRON + 0x014D: 0xD8, # LATIN SMALL LETTER O WITH MACRON + 0x0150: 0xCC, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + 0x0151: 0xCE, # LATIN SMALL LETTER O WITH DOUBLE ACUTE + 0x0154: 0xD9, # LATIN CAPITAL LETTER R WITH ACUTE + 0x0155: 0xDA, # LATIN SMALL LETTER R WITH ACUTE + 0x0156: 0xDF, # LATIN CAPITAL LETTER R WITH CEDILLA + 0x0157: 0xE0, # LATIN SMALL LETTER R WITH CEDILLA + 0x0158: 0xDB, # LATIN CAPITAL LETTER R WITH CARON + 0x0159: 0xDE, # LATIN SMALL LETTER R WITH CARON + 0x015A: 0xE5, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015B: 0xE6, # LATIN SMALL LETTER S WITH ACUTE + 0x0160: 0xE1, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xE4, # LATIN SMALL LETTER S WITH CARON + 0x0164: 0xE8, # LATIN CAPITAL LETTER T WITH CARON + 0x0165: 0xE9, # LATIN SMALL LETTER T WITH CARON + 0x016A: 0xED, # LATIN CAPITAL LETTER U WITH MACRON + 0x016B: 0xF0, # LATIN SMALL LETTER U WITH MACRON + 0x016E: 0xF1, # LATIN CAPITAL LETTER U WITH RING ABOVE + 0x016F: 0xF3, # LATIN SMALL LETTER U WITH RING ABOVE + 0x0170: 0xF4, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + 0x0171: 0xF5, # LATIN SMALL LETTER U WITH DOUBLE ACUTE + 0x0172: 0xF6, # LATIN CAPITAL LETTER U WITH OGONEK + 0x0173: 0xF7, # LATIN SMALL LETTER U WITH OGONEK + 0x0179: 0x8F, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017A: 0x90, # LATIN SMALL LETTER Z WITH ACUTE + 0x017B: 0xFB, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017C: 0xFD, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017D: 0xEB, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xEC, # LATIN SMALL LETTER Z WITH CARON + 0x02C7: 0xFF, # CARON + 0x2013: 0xD0, # EN DASH + 0x2014: 0xD1, # EM DASH + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK + 0x2020: 0xA0, # DAGGER + 0x2022: 0xA5, # BULLET + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS + 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x2122: 0xAA, # TRADE MARK SIGN + 0x2202: 0xB6, # PARTIAL DIFFERENTIAL + 0x2206: 0xC6, # INCREMENT + 0x2211: 0xB7, # N-ARY SUMMATION + 0x221A: 0xC3, # SQUARE ROOT + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO + 0x25CA: 0xD7, # LOZENGE +} + diff --git a/Lib/encodings/mac_croatian.py b/Lib/encodings/mac_croatian.py index 32a4e37..8cdf8d1 100644 --- a/Lib/encodings/mac_croatian.py +++ b/Lib/encodings/mac_croatian.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA @@ -170,12 +170,12 @@ decoding_table = ( u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe3' # 0x8b -> LATIN SMALL LETTER A WITH TILDE - u'\xe5' # 0x8c -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe7' # 0x8d -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\xe8' # 0x8f -> LATIN SMALL LETTER E WITH GRAVE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE @@ -186,108 +186,108 @@ decoding_table = ( u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf5' # 0x9b -> LATIN SMALL LETTER O WITH TILDE - u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE - u'\xf9' # 0x9d -> LATIN SMALL LETTER U WITH GRAVE - u'\xfb' # 0x9e -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u2020' # 0xa0 -> DAGGER - u'\xb0' # 0xa1 -> DEGREE SIGN - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa7' # 0xa4 -> SECTION SIGN - u'\u2022' # 0xa5 -> BULLET - u'\xb6' # 0xa6 -> PILCROW SIGN - u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\u0160' # 0xa9 -> LATIN CAPITAL LETTER S WITH CARON - u'\u2122' # 0xaa -> TRADE MARK SIGN - u'\xb4' # 0xab -> ACUTE ACCENT - u'\xa8' # 0xac -> DIAERESIS - u'\u2260' # 0xad -> NOT EQUAL TO - u'\u017d' # 0xae -> LATIN CAPITAL LETTER Z WITH CARON - u'\xd8' # 0xaf -> LATIN CAPITAL LETTER O WITH STROKE - u'\u221e' # 0xb0 -> INFINITY - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\u2206' # 0xb4 -> INCREMENT - u'\xb5' # 0xb5 -> MICRO SIGN - u'\u2202' # 0xb6 -> PARTIAL DIFFERENTIAL - u'\u2211' # 0xb7 -> N-ARY SUMMATION - u'\u220f' # 0xb8 -> N-ARY PRODUCT - u'\u0161' # 0xb9 -> LATIN SMALL LETTER S WITH CARON - u'\u222b' # 0xba -> INTEGRAL - u'\xaa' # 0xbb -> FEMININE ORDINAL INDICATOR - u'\xba' # 0xbc -> MASCULINE ORDINAL INDICATOR - u'\u03a9' # 0xbd -> GREEK CAPITAL LETTER OMEGA - u'\u017e' # 0xbe -> LATIN SMALL LETTER Z WITH CARON - u'\xf8' # 0xbf -> LATIN SMALL LETTER O WITH STROKE - u'\xbf' # 0xc0 -> INVERTED QUESTION MARK - u'\xa1' # 0xc1 -> INVERTED EXCLAMATION MARK - u'\xac' # 0xc2 -> NOT SIGN - u'\u221a' # 0xc3 -> SQUARE ROOT - u'\u0192' # 0xc4 -> LATIN SMALL LETTER F WITH HOOK - u'\u2248' # 0xc5 -> ALMOST EQUAL TO - u'\u0106' # 0xc6 -> LATIN CAPITAL LETTER C WITH ACUTE - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u010c' # 0xc8 -> LATIN CAPITAL LETTER C WITH CARON - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\xc0' # 0xcb -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc3' # 0xcc -> LATIN CAPITAL LETTER A WITH TILDE - u'\xd5' # 0xcd -> LATIN CAPITAL LETTER O WITH TILDE - u'\u0152' # 0xce -> LATIN CAPITAL LIGATURE OE - u'\u0153' # 0xcf -> LATIN SMALL LIGATURE OE - u'\u0110' # 0xd0 -> LATIN CAPITAL LETTER D WITH STROKE - u'\u2014' # 0xd1 -> EM DASH - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u25ca' # 0xd7 -> LOZENGE - u'\uf8ff' # 0xd8 -> Apple logo - u'\xa9' # 0xd9 -> COPYRIGHT SIGN - u'\u2044' # 0xda -> FRACTION SLASH - u'\u20ac' # 0xdb -> EURO SIGN - u'\u2039' # 0xdc -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u203a' # 0xdd -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\xc6' # 0xde -> LATIN CAPITAL LETTER AE - u'\xbb' # 0xdf -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2013' # 0xe0 -> EN DASH - u'\xb7' # 0xe1 -> MIDDLE DOT - u'\u201a' # 0xe2 -> SINGLE LOW-9 QUOTATION MARK - u'\u201e' # 0xe3 -> DOUBLE LOW-9 QUOTATION MARK - u'\u2030' # 0xe4 -> PER MILLE SIGN - u'\xc2' # 0xe5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\u0107' # 0xe6 -> LATIN SMALL LETTER C WITH ACUTE - u'\xc1' # 0xe7 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\u010d' # 0xe8 -> LATIN SMALL LETTER C WITH CARON - u'\xc8' # 0xe9 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xcd' # 0xea -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xeb -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xec -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xcc' # 0xed -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\u0111' # 0xf0 -> LATIN SMALL LETTER D WITH STROKE - u'\xd2' # 0xf1 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xda' # 0xf2 -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xf3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xd9' # 0xf4 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\u0131' # 0xf5 -> LATIN SMALL LETTER DOTLESS I - u'\u02c6' # 0xf6 -> MODIFIER LETTER CIRCUMFLEX ACCENT - u'\u02dc' # 0xf7 -> SMALL TILDE - u'\xaf' # 0xf8 -> MACRON - u'\u03c0' # 0xf9 -> GREEK SMALL LETTER PI - u'\xcb' # 0xfa -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\u02da' # 0xfb -> RING ABOVE - u'\xb8' # 0xfc -> CEDILLA - u'\xca' # 0xfd -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xe6' # 0xfe -> LATIN SMALL LETTER AE - u'\u02c7' # 0xff -> CARON + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u2020' # 0xA0 -> DAGGER + u'\xb0' # 0xA1 -> DEGREE SIGN + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa7' # 0xA4 -> SECTION SIGN + u'\u2022' # 0xA5 -> BULLET + u'\xb6' # 0xA6 -> PILCROW SIGN + u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON + u'\u2122' # 0xAA -> TRADE MARK SIGN + u'\xb4' # 0xAB -> ACUTE ACCENT + u'\xa8' # 0xAC -> DIAERESIS + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON + u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + u'\u221e' # 0xB0 -> INFINITY + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\u2206' # 0xB4 -> INCREMENT + u'\xb5' # 0xB5 -> MICRO SIGN + u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + u'\u2211' # 0xB7 -> N-ARY SUMMATION + u'\u220f' # 0xB8 -> N-ARY PRODUCT + u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON + u'\u222b' # 0xBA -> INTEGRAL + u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON + u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + u'\xbf' # 0xC0 -> INVERTED QUESTION MARK + u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + u'\xac' # 0xC2 -> NOT SIGN + u'\u221a' # 0xC3 -> SQUARE ROOT + u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + u'\u2248' # 0xC5 -> ALMOST EQUAL TO + u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + u'\u2014' # 0xD1 -> EM DASH + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u25ca' # 0xD7 -> LOZENGE + u'\uf8ff' # 0xD8 -> Apple logo + u'\xa9' # 0xD9 -> COPYRIGHT SIGN + u'\u2044' # 0xDA -> FRACTION SLASH + u'\u20ac' # 0xDB -> EURO SIGN + u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\xc6' # 0xDE -> LATIN CAPITAL LETTER AE + u'\xbb' # 0xDF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2013' # 0xE0 -> EN DASH + u'\xb7' # 0xE1 -> MIDDLE DOT + u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + u'\u2030' # 0xE4 -> PER MILLE SIGN + u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE + u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + u'\u02dc' # 0xF7 -> SMALL TILDE + u'\xaf' # 0xF8 -> MACRON + u'\u03c0' # 0xF9 -> GREEK SMALL LETTER PI + u'\xcb' # 0xFA -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\u02da' # 0xFB -> RING ABOVE + u'\xb8' # 0xFC -> CEDILLA + u'\xca' # 0xFD -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xe6' # 0xFE -> LATIN SMALL LETTER AE + u'\u02c7' # 0xFF -> CARON ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a1: 0xc1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a7: 0xa4, # SECTION SIGN - 0x00a8: 0xac, # DIAERESIS - 0x00a9: 0xd9, # COPYRIGHT SIGN - 0x00aa: 0xbb, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00af: 0xf8, # MACRON - 0x00b0: 0xa1, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b4: 0xab, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xa6, # PILCROW SIGN - 0x00b7: 0xe1, # MIDDLE DOT - 0x00b8: 0xfc, # CEDILLA - 0x00ba: 0xbc, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xdf, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bf: 0xc0, # INVERTED QUESTION MARK - 0x00c0: 0xcb, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xe7, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xe5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xcc, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xde, # LATIN CAPITAL LETTER AE - 0x00c7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xe9, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xfd, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xfa, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xed, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xea, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xeb, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xec, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xf1, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xcd, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d8: 0xaf, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xf4, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xf2, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xf3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xa7, # LATIN SMALL LETTER SHARP S - 0x00e0: 0x88, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x8b, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x8c, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xfe, # LATIN SMALL LETTER AE - 0x00e7: 0x8d, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x8f, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x93, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0x96, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0x98, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0x9b, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xd6, # DIVISION SIGN - 0x00f8: 0xbf, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0x9d, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0x9e, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x0106: 0xc6, # LATIN CAPITAL LETTER C WITH ACUTE - 0x0107: 0xe6, # LATIN SMALL LETTER C WITH ACUTE - 0x010c: 0xc8, # LATIN CAPITAL LETTER C WITH CARON - 0x010d: 0xe8, # LATIN SMALL LETTER C WITH CARON - 0x0110: 0xd0, # LATIN CAPITAL LETTER D WITH STROKE - 0x0111: 0xf0, # LATIN SMALL LETTER D WITH STROKE - 0x0131: 0xf5, # LATIN SMALL LETTER DOTLESS I - 0x0152: 0xce, # LATIN CAPITAL LIGATURE OE - 0x0153: 0xcf, # LATIN SMALL LIGATURE OE - 0x0160: 0xa9, # LATIN CAPITAL LETTER S WITH CARON - 0x0161: 0xb9, # LATIN SMALL LETTER S WITH CARON - 0x017d: 0xae, # LATIN CAPITAL LETTER Z WITH CARON - 0x017e: 0xbe, # LATIN SMALL LETTER Z WITH CARON - 0x0192: 0xc4, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0xf6, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02c7: 0xff, # CARON - 0x02da: 0xfb, # RING ABOVE - 0x02dc: 0xf7, # SMALL TILDE - 0x03a9: 0xbd, # GREEK CAPITAL LETTER OMEGA - 0x03c0: 0xf9, # GREEK SMALL LETTER PI - 0x2013: 0xe0, # EN DASH - 0x2014: 0xd1, # EM DASH - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0xe2, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xe3, # DOUBLE LOW-9 QUOTATION MARK - 0x2020: 0xa0, # DAGGER - 0x2022: 0xa5, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS - 0x2030: 0xe4, # PER MILLE SIGN - 0x2039: 0xdc, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0xdd, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x2044: 0xda, # FRACTION SLASH - 0x20ac: 0xdb, # EURO SIGN - 0x2122: 0xaa, # TRADE MARK SIGN - 0x2202: 0xb6, # PARTIAL DIFFERENTIAL - 0x2206: 0xb4, # INCREMENT - 0x220f: 0xb8, # N-ARY PRODUCT - 0x2211: 0xb7, # N-ARY SUMMATION - 0x221a: 0xc3, # SQUARE ROOT - 0x221e: 0xb0, # INFINITY - 0x222b: 0xba, # INTEGRAL - 0x2248: 0xc5, # ALMOST EQUAL TO - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO - 0x25ca: 0xd7, # LOZENGE - 0xf8ff: 0xd8, # Apple logo -} \ No newline at end of file + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A7: 0xA4, # SECTION SIGN + 0x00A8: 0xAC, # DIAERESIS + 0x00A9: 0xD9, # COPYRIGHT SIGN + 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00AF: 0xF8, # MACRON + 0x00B0: 0xA1, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B4: 0xAB, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xA6, # PILCROW SIGN + 0x00B7: 0xE1, # MIDDLE DOT + 0x00B8: 0xFC, # CEDILLA + 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xDF, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BF: 0xC0, # INVERTED QUESTION MARK + 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xDE, # LATIN CAPITAL LETTER AE + 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xFD, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xFA, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S + 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xFE, # LATIN SMALL LETTER AE + 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xD6, # DIVISION SIGN + 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0106: 0xC6, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0xE6, # LATIN SMALL LETTER C WITH ACUTE + 0x010C: 0xC8, # LATIN CAPITAL LETTER C WITH CARON + 0x010D: 0xE8, # LATIN SMALL LETTER C WITH CARON + 0x0110: 0xD0, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0xF0, # LATIN SMALL LETTER D WITH STROKE + 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I + 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE + 0x0153: 0xCF, # LATIN SMALL LIGATURE OE + 0x0160: 0xA9, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0xB9, # LATIN SMALL LETTER S WITH CARON + 0x017D: 0xAE, # LATIN CAPITAL LETTER Z WITH CARON + 0x017E: 0xBE, # LATIN SMALL LETTER Z WITH CARON + 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK + 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02C7: 0xFF, # CARON + 0x02DA: 0xFB, # RING ABOVE + 0x02DC: 0xF7, # SMALL TILDE + 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA + 0x03C0: 0xF9, # GREEK SMALL LETTER PI + 0x2013: 0xE0, # EN DASH + 0x2014: 0xD1, # EM DASH + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK + 0x2020: 0xA0, # DAGGER + 0x2022: 0xA5, # BULLET + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS + 0x2030: 0xE4, # PER MILLE SIGN + 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x2044: 0xDA, # FRACTION SLASH + 0x20AC: 0xDB, # EURO SIGN + 0x2122: 0xAA, # TRADE MARK SIGN + 0x2202: 0xB6, # PARTIAL DIFFERENTIAL + 0x2206: 0xB4, # INCREMENT + 0x220F: 0xB8, # N-ARY PRODUCT + 0x2211: 0xB7, # N-ARY SUMMATION + 0x221A: 0xC3, # SQUARE ROOT + 0x221E: 0xB0, # INFINITY + 0x222B: 0xBA, # INTEGRAL + 0x2248: 0xC5, # ALMOST EQUAL TO + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO + 0x25CA: 0xD7, # LOZENGE + 0xF8FF: 0xD8, # Apple logo +} + diff --git a/Lib/encodings/mac_cyrillic.py b/Lib/encodings/mac_cyrillic.py index e3e5cf2..22624ca 100644 --- a/Lib/encodings/mac_cyrillic.py +++ b/Lib/encodings/mac_cyrillic.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\u0410' # 0x80 -> CYRILLIC CAPITAL LETTER A u'\u0411' # 0x81 -> CYRILLIC CAPITAL LETTER BE u'\u0412' # 0x82 -> CYRILLIC CAPITAL LETTER VE @@ -170,12 +170,12 @@ decoding_table = ( u'\u0417' # 0x87 -> CYRILLIC CAPITAL LETTER ZE u'\u0418' # 0x88 -> CYRILLIC CAPITAL LETTER I u'\u0419' # 0x89 -> CYRILLIC CAPITAL LETTER SHORT I - u'\u041a' # 0x8a -> CYRILLIC CAPITAL LETTER KA - u'\u041b' # 0x8b -> CYRILLIC CAPITAL LETTER EL - u'\u041c' # 0x8c -> CYRILLIC CAPITAL LETTER EM - u'\u041d' # 0x8d -> CYRILLIC CAPITAL LETTER EN - u'\u041e' # 0x8e -> CYRILLIC CAPITAL LETTER O - u'\u041f' # 0x8f -> CYRILLIC CAPITAL LETTER PE + u'\u041a' # 0x8A -> CYRILLIC CAPITAL LETTER KA + u'\u041b' # 0x8B -> CYRILLIC CAPITAL LETTER EL + u'\u041c' # 0x8C -> CYRILLIC CAPITAL LETTER EM + u'\u041d' # 0x8D -> CYRILLIC CAPITAL LETTER EN + u'\u041e' # 0x8E -> CYRILLIC CAPITAL LETTER O + u'\u041f' # 0x8F -> CYRILLIC CAPITAL LETTER PE u'\u0420' # 0x90 -> CYRILLIC CAPITAL LETTER ER u'\u0421' # 0x91 -> CYRILLIC CAPITAL LETTER ES u'\u0422' # 0x92 -> CYRILLIC CAPITAL LETTER TE @@ -186,108 +186,108 @@ decoding_table = ( u'\u0427' # 0x97 -> CYRILLIC CAPITAL LETTER CHE u'\u0428' # 0x98 -> CYRILLIC CAPITAL LETTER SHA u'\u0429' # 0x99 -> CYRILLIC CAPITAL LETTER SHCHA - u'\u042a' # 0x9a -> CYRILLIC CAPITAL LETTER HARD SIGN - u'\u042b' # 0x9b -> CYRILLIC CAPITAL LETTER YERU - u'\u042c' # 0x9c -> CYRILLIC CAPITAL LETTER SOFT SIGN - u'\u042d' # 0x9d -> CYRILLIC CAPITAL LETTER E - u'\u042e' # 0x9e -> CYRILLIC CAPITAL LETTER YU - u'\u042f' # 0x9f -> CYRILLIC CAPITAL LETTER YA - u'\u2020' # 0xa0 -> DAGGER - u'\xb0' # 0xa1 -> DEGREE SIGN - u'\u0490' # 0xa2 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa7' # 0xa4 -> SECTION SIGN - u'\u2022' # 0xa5 -> BULLET - u'\xb6' # 0xa6 -> PILCROW SIGN - u'\u0406' # 0xa7 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u2122' # 0xaa -> TRADE MARK SIGN - u'\u0402' # 0xab -> CYRILLIC CAPITAL LETTER DJE - u'\u0452' # 0xac -> CYRILLIC SMALL LETTER DJE - u'\u2260' # 0xad -> NOT EQUAL TO - u'\u0403' # 0xae -> CYRILLIC CAPITAL LETTER GJE - u'\u0453' # 0xaf -> CYRILLIC SMALL LETTER GJE - u'\u221e' # 0xb0 -> INFINITY - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\u0456' # 0xb4 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - u'\xb5' # 0xb5 -> MICRO SIGN - u'\u0491' # 0xb6 -> CYRILLIC SMALL LETTER GHE WITH UPTURN - u'\u0408' # 0xb7 -> CYRILLIC CAPITAL LETTER JE - u'\u0404' # 0xb8 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE - u'\u0454' # 0xb9 -> CYRILLIC SMALL LETTER UKRAINIAN IE - u'\u0407' # 0xba -> CYRILLIC CAPITAL LETTER YI - u'\u0457' # 0xbb -> CYRILLIC SMALL LETTER YI - u'\u0409' # 0xbc -> CYRILLIC CAPITAL LETTER LJE - u'\u0459' # 0xbd -> CYRILLIC SMALL LETTER LJE - u'\u040a' # 0xbe -> CYRILLIC CAPITAL LETTER NJE - u'\u045a' # 0xbf -> CYRILLIC SMALL LETTER NJE - u'\u0458' # 0xc0 -> CYRILLIC SMALL LETTER JE - u'\u0405' # 0xc1 -> CYRILLIC CAPITAL LETTER DZE - u'\xac' # 0xc2 -> NOT SIGN - u'\u221a' # 0xc3 -> SQUARE ROOT - u'\u0192' # 0xc4 -> LATIN SMALL LETTER F WITH HOOK - u'\u2248' # 0xc5 -> ALMOST EQUAL TO - u'\u2206' # 0xc6 -> INCREMENT - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\u040b' # 0xcb -> CYRILLIC CAPITAL LETTER TSHE - u'\u045b' # 0xcc -> CYRILLIC SMALL LETTER TSHE - u'\u040c' # 0xcd -> CYRILLIC CAPITAL LETTER KJE - u'\u045c' # 0xce -> CYRILLIC SMALL LETTER KJE - u'\u0455' # 0xcf -> CYRILLIC SMALL LETTER DZE - u'\u2013' # 0xd0 -> EN DASH - u'\u2014' # 0xd1 -> EM DASH - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u201e' # 0xd7 -> DOUBLE LOW-9 QUOTATION MARK - u'\u040e' # 0xd8 -> CYRILLIC CAPITAL LETTER SHORT U - u'\u045e' # 0xd9 -> CYRILLIC SMALL LETTER SHORT U - u'\u040f' # 0xda -> CYRILLIC CAPITAL LETTER DZHE - u'\u045f' # 0xdb -> CYRILLIC SMALL LETTER DZHE - u'\u2116' # 0xdc -> NUMERO SIGN - u'\u0401' # 0xdd -> CYRILLIC CAPITAL LETTER IO - u'\u0451' # 0xde -> CYRILLIC SMALL LETTER IO - u'\u044f' # 0xdf -> CYRILLIC SMALL LETTER YA - u'\u0430' # 0xe0 -> CYRILLIC SMALL LETTER A - u'\u0431' # 0xe1 -> CYRILLIC SMALL LETTER BE - u'\u0432' # 0xe2 -> CYRILLIC SMALL LETTER VE - u'\u0433' # 0xe3 -> CYRILLIC SMALL LETTER GHE - u'\u0434' # 0xe4 -> CYRILLIC SMALL LETTER DE - u'\u0435' # 0xe5 -> CYRILLIC SMALL LETTER IE - u'\u0436' # 0xe6 -> CYRILLIC SMALL LETTER ZHE - u'\u0437' # 0xe7 -> CYRILLIC SMALL LETTER ZE - u'\u0438' # 0xe8 -> CYRILLIC SMALL LETTER I - u'\u0439' # 0xe9 -> CYRILLIC SMALL LETTER SHORT I - u'\u043a' # 0xea -> CYRILLIC SMALL LETTER KA - u'\u043b' # 0xeb -> CYRILLIC SMALL LETTER EL - u'\u043c' # 0xec -> CYRILLIC SMALL LETTER EM - u'\u043d' # 0xed -> CYRILLIC SMALL LETTER EN - u'\u043e' # 0xee -> CYRILLIC SMALL LETTER O - u'\u043f' # 0xef -> CYRILLIC SMALL LETTER PE - u'\u0440' # 0xf0 -> CYRILLIC SMALL LETTER ER - u'\u0441' # 0xf1 -> CYRILLIC SMALL LETTER ES - u'\u0442' # 0xf2 -> CYRILLIC SMALL LETTER TE - u'\u0443' # 0xf3 -> CYRILLIC SMALL LETTER U - u'\u0444' # 0xf4 -> CYRILLIC SMALL LETTER EF - u'\u0445' # 0xf5 -> CYRILLIC SMALL LETTER HA - u'\u0446' # 0xf6 -> CYRILLIC SMALL LETTER TSE - u'\u0447' # 0xf7 -> CYRILLIC SMALL LETTER CHE - u'\u0448' # 0xf8 -> CYRILLIC SMALL LETTER SHA - u'\u0449' # 0xf9 -> CYRILLIC SMALL LETTER SHCHA - u'\u044a' # 0xfa -> CYRILLIC SMALL LETTER HARD SIGN - u'\u044b' # 0xfb -> CYRILLIC SMALL LETTER YERU - u'\u044c' # 0xfc -> CYRILLIC SMALL LETTER SOFT SIGN - u'\u044d' # 0xfd -> CYRILLIC SMALL LETTER E - u'\u044e' # 0xfe -> CYRILLIC SMALL LETTER YU - u'\u20ac' # 0xff -> EURO SIGN + u'\u042a' # 0x9A -> CYRILLIC CAPITAL LETTER HARD SIGN + u'\u042b' # 0x9B -> CYRILLIC CAPITAL LETTER YERU + u'\u042c' # 0x9C -> CYRILLIC CAPITAL LETTER SOFT SIGN + u'\u042d' # 0x9D -> CYRILLIC CAPITAL LETTER E + u'\u042e' # 0x9E -> CYRILLIC CAPITAL LETTER YU + u'\u042f' # 0x9F -> CYRILLIC CAPITAL LETTER YA + u'\u2020' # 0xA0 -> DAGGER + u'\xb0' # 0xA1 -> DEGREE SIGN + u'\u0490' # 0xA2 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa7' # 0xA4 -> SECTION SIGN + u'\u2022' # 0xA5 -> BULLET + u'\xb6' # 0xA6 -> PILCROW SIGN + u'\u0406' # 0xA7 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u2122' # 0xAA -> TRADE MARK SIGN + u'\u0402' # 0xAB -> CYRILLIC CAPITAL LETTER DJE + u'\u0452' # 0xAC -> CYRILLIC SMALL LETTER DJE + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\u0403' # 0xAE -> CYRILLIC CAPITAL LETTER GJE + u'\u0453' # 0xAF -> CYRILLIC SMALL LETTER GJE + u'\u221e' # 0xB0 -> INFINITY + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\u0456' # 0xB4 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + u'\xb5' # 0xB5 -> MICRO SIGN + u'\u0491' # 0xB6 -> CYRILLIC SMALL LETTER GHE WITH UPTURN + u'\u0408' # 0xB7 -> CYRILLIC CAPITAL LETTER JE + u'\u0404' # 0xB8 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + u'\u0454' # 0xB9 -> CYRILLIC SMALL LETTER UKRAINIAN IE + u'\u0407' # 0xBA -> CYRILLIC CAPITAL LETTER YI + u'\u0457' # 0xBB -> CYRILLIC SMALL LETTER YI + u'\u0409' # 0xBC -> CYRILLIC CAPITAL LETTER LJE + u'\u0459' # 0xBD -> CYRILLIC SMALL LETTER LJE + u'\u040a' # 0xBE -> CYRILLIC CAPITAL LETTER NJE + u'\u045a' # 0xBF -> CYRILLIC SMALL LETTER NJE + u'\u0458' # 0xC0 -> CYRILLIC SMALL LETTER JE + u'\u0405' # 0xC1 -> CYRILLIC CAPITAL LETTER DZE + u'\xac' # 0xC2 -> NOT SIGN + u'\u221a' # 0xC3 -> SQUARE ROOT + u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + u'\u2248' # 0xC5 -> ALMOST EQUAL TO + u'\u2206' # 0xC6 -> INCREMENT + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\u040b' # 0xCB -> CYRILLIC CAPITAL LETTER TSHE + u'\u045b' # 0xCC -> CYRILLIC SMALL LETTER TSHE + u'\u040c' # 0xCD -> CYRILLIC CAPITAL LETTER KJE + u'\u045c' # 0xCE -> CYRILLIC SMALL LETTER KJE + u'\u0455' # 0xCF -> CYRILLIC SMALL LETTER DZE + u'\u2013' # 0xD0 -> EN DASH + u'\u2014' # 0xD1 -> EM DASH + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u201e' # 0xD7 -> DOUBLE LOW-9 QUOTATION MARK + u'\u040e' # 0xD8 -> CYRILLIC CAPITAL LETTER SHORT U + u'\u045e' # 0xD9 -> CYRILLIC SMALL LETTER SHORT U + u'\u040f' # 0xDA -> CYRILLIC CAPITAL LETTER DZHE + u'\u045f' # 0xDB -> CYRILLIC SMALL LETTER DZHE + u'\u2116' # 0xDC -> NUMERO SIGN + u'\u0401' # 0xDD -> CYRILLIC CAPITAL LETTER IO + u'\u0451' # 0xDE -> CYRILLIC SMALL LETTER IO + u'\u044f' # 0xDF -> CYRILLIC SMALL LETTER YA + u'\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A + u'\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE + u'\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE + u'\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE + u'\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE + u'\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE + u'\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE + u'\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE + u'\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I + u'\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I + u'\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA + u'\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL + u'\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM + u'\u043d' # 0xED -> CYRILLIC SMALL LETTER EN + u'\u043e' # 0xEE -> CYRILLIC SMALL LETTER O + u'\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE + u'\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER + u'\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES + u'\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE + u'\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U + u'\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF + u'\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA + u'\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE + u'\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE + u'\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA + u'\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA + u'\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN + u'\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU + u'\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN + u'\u044d' # 0xFD -> CYRILLIC SMALL LETTER E + u'\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU + u'\u20ac' # 0xFF -> EURO SIGN ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,40 +415,40 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a3: 0xa3, # POUND SIGN - 0x00a7: 0xa4, # SECTION SIGN - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00b0: 0xa1, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xa6, # PILCROW SIGN - 0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00f7: 0xd6, # DIVISION SIGN - 0x0192: 0xc4, # LATIN SMALL LETTER F WITH HOOK - 0x0401: 0xdd, # CYRILLIC CAPITAL LETTER IO - 0x0402: 0xab, # CYRILLIC CAPITAL LETTER DJE - 0x0403: 0xae, # CYRILLIC CAPITAL LETTER GJE - 0x0404: 0xb8, # CYRILLIC CAPITAL LETTER UKRAINIAN IE - 0x0405: 0xc1, # CYRILLIC CAPITAL LETTER DZE - 0x0406: 0xa7, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0407: 0xba, # CYRILLIC CAPITAL LETTER YI - 0x0408: 0xb7, # CYRILLIC CAPITAL LETTER JE - 0x0409: 0xbc, # CYRILLIC CAPITAL LETTER LJE - 0x040a: 0xbe, # CYRILLIC CAPITAL LETTER NJE - 0x040b: 0xcb, # CYRILLIC CAPITAL LETTER TSHE - 0x040c: 0xcd, # CYRILLIC CAPITAL LETTER KJE - 0x040e: 0xd8, # CYRILLIC CAPITAL LETTER SHORT U - 0x040f: 0xda, # CYRILLIC CAPITAL LETTER DZHE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A3: 0xA3, # POUND SIGN + 0x00A7: 0xA4, # SECTION SIGN + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00B0: 0xA1, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xA6, # PILCROW SIGN + 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00F7: 0xD6, # DIVISION SIGN + 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK + 0x0401: 0xDD, # CYRILLIC CAPITAL LETTER IO + 0x0402: 0xAB, # CYRILLIC CAPITAL LETTER DJE + 0x0403: 0xAE, # CYRILLIC CAPITAL LETTER GJE + 0x0404: 0xB8, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0405: 0xC1, # CYRILLIC CAPITAL LETTER DZE + 0x0406: 0xA7, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0407: 0xBA, # CYRILLIC CAPITAL LETTER YI + 0x0408: 0xB7, # CYRILLIC CAPITAL LETTER JE + 0x0409: 0xBC, # CYRILLIC CAPITAL LETTER LJE + 0x040A: 0xBE, # CYRILLIC CAPITAL LETTER NJE + 0x040B: 0xCB, # CYRILLIC CAPITAL LETTER TSHE + 0x040C: 0xCD, # CYRILLIC CAPITAL LETTER KJE + 0x040E: 0xD8, # CYRILLIC CAPITAL LETTER SHORT U + 0x040F: 0xDA, # CYRILLIC CAPITAL LETTER DZHE 0x0410: 0x80, # CYRILLIC CAPITAL LETTER A 0x0411: 0x81, # CYRILLIC CAPITAL LETTER BE 0x0412: 0x82, # CYRILLIC CAPITAL LETTER VE @@ -459,12 +459,12 @@ encoding_map = { 0x0417: 0x87, # CYRILLIC CAPITAL LETTER ZE 0x0418: 0x88, # CYRILLIC CAPITAL LETTER I 0x0419: 0x89, # CYRILLIC CAPITAL LETTER SHORT I - 0x041a: 0x8a, # CYRILLIC CAPITAL LETTER KA - 0x041b: 0x8b, # CYRILLIC CAPITAL LETTER EL - 0x041c: 0x8c, # CYRILLIC CAPITAL LETTER EM - 0x041d: 0x8d, # CYRILLIC CAPITAL LETTER EN - 0x041e: 0x8e, # CYRILLIC CAPITAL LETTER O - 0x041f: 0x8f, # CYRILLIC CAPITAL LETTER PE + 0x041A: 0x8A, # CYRILLIC CAPITAL LETTER KA + 0x041B: 0x8B, # CYRILLIC CAPITAL LETTER EL + 0x041C: 0x8C, # CYRILLIC CAPITAL LETTER EM + 0x041D: 0x8D, # CYRILLIC CAPITAL LETTER EN + 0x041E: 0x8E, # CYRILLIC CAPITAL LETTER O + 0x041F: 0x8F, # CYRILLIC CAPITAL LETTER PE 0x0420: 0x90, # CYRILLIC CAPITAL LETTER ER 0x0421: 0x91, # CYRILLIC CAPITAL LETTER ES 0x0422: 0x92, # CYRILLIC CAPITAL LETTER TE @@ -475,78 +475,79 @@ encoding_map = { 0x0427: 0x97, # CYRILLIC CAPITAL LETTER CHE 0x0428: 0x98, # CYRILLIC CAPITAL LETTER SHA 0x0429: 0x99, # CYRILLIC CAPITAL LETTER SHCHA - 0x042a: 0x9a, # CYRILLIC CAPITAL LETTER HARD SIGN - 0x042b: 0x9b, # CYRILLIC CAPITAL LETTER YERU - 0x042c: 0x9c, # CYRILLIC CAPITAL LETTER SOFT SIGN - 0x042d: 0x9d, # CYRILLIC CAPITAL LETTER E - 0x042e: 0x9e, # CYRILLIC CAPITAL LETTER YU - 0x042f: 0x9f, # CYRILLIC CAPITAL LETTER YA - 0x0430: 0xe0, # CYRILLIC SMALL LETTER A - 0x0431: 0xe1, # CYRILLIC SMALL LETTER BE - 0x0432: 0xe2, # CYRILLIC SMALL LETTER VE - 0x0433: 0xe3, # CYRILLIC SMALL LETTER GHE - 0x0434: 0xe4, # CYRILLIC SMALL LETTER DE - 0x0435: 0xe5, # CYRILLIC SMALL LETTER IE - 0x0436: 0xe6, # CYRILLIC SMALL LETTER ZHE - 0x0437: 0xe7, # CYRILLIC SMALL LETTER ZE - 0x0438: 0xe8, # CYRILLIC SMALL LETTER I - 0x0439: 0xe9, # CYRILLIC SMALL LETTER SHORT I - 0x043a: 0xea, # CYRILLIC SMALL LETTER KA - 0x043b: 0xeb, # CYRILLIC SMALL LETTER EL - 0x043c: 0xec, # CYRILLIC SMALL LETTER EM - 0x043d: 0xed, # CYRILLIC SMALL LETTER EN - 0x043e: 0xee, # CYRILLIC SMALL LETTER O - 0x043f: 0xef, # CYRILLIC SMALL LETTER PE - 0x0440: 0xf0, # CYRILLIC SMALL LETTER ER - 0x0441: 0xf1, # CYRILLIC SMALL LETTER ES - 0x0442: 0xf2, # CYRILLIC SMALL LETTER TE - 0x0443: 0xf3, # CYRILLIC SMALL LETTER U - 0x0444: 0xf4, # CYRILLIC SMALL LETTER EF - 0x0445: 0xf5, # CYRILLIC SMALL LETTER HA - 0x0446: 0xf6, # CYRILLIC SMALL LETTER TSE - 0x0447: 0xf7, # CYRILLIC SMALL LETTER CHE - 0x0448: 0xf8, # CYRILLIC SMALL LETTER SHA - 0x0449: 0xf9, # CYRILLIC SMALL LETTER SHCHA - 0x044a: 0xfa, # CYRILLIC SMALL LETTER HARD SIGN - 0x044b: 0xfb, # CYRILLIC SMALL LETTER YERU - 0x044c: 0xfc, # CYRILLIC SMALL LETTER SOFT SIGN - 0x044d: 0xfd, # CYRILLIC SMALL LETTER E - 0x044e: 0xfe, # CYRILLIC SMALL LETTER YU - 0x044f: 0xdf, # CYRILLIC SMALL LETTER YA - 0x0451: 0xde, # CYRILLIC SMALL LETTER IO - 0x0452: 0xac, # CYRILLIC SMALL LETTER DJE - 0x0453: 0xaf, # CYRILLIC SMALL LETTER GJE - 0x0454: 0xb9, # CYRILLIC SMALL LETTER UKRAINIAN IE - 0x0455: 0xcf, # CYRILLIC SMALL LETTER DZE - 0x0456: 0xb4, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - 0x0457: 0xbb, # CYRILLIC SMALL LETTER YI - 0x0458: 0xc0, # CYRILLIC SMALL LETTER JE - 0x0459: 0xbd, # CYRILLIC SMALL LETTER LJE - 0x045a: 0xbf, # CYRILLIC SMALL LETTER NJE - 0x045b: 0xcc, # CYRILLIC SMALL LETTER TSHE - 0x045c: 0xce, # CYRILLIC SMALL LETTER KJE - 0x045e: 0xd9, # CYRILLIC SMALL LETTER SHORT U - 0x045f: 0xdb, # CYRILLIC SMALL LETTER DZHE - 0x0490: 0xa2, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN - 0x0491: 0xb6, # CYRILLIC SMALL LETTER GHE WITH UPTURN - 0x2013: 0xd0, # EN DASH - 0x2014: 0xd1, # EM DASH - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xd7, # DOUBLE LOW-9 QUOTATION MARK - 0x2020: 0xa0, # DAGGER - 0x2022: 0xa5, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS - 0x20ac: 0xff, # EURO SIGN - 0x2116: 0xdc, # NUMERO SIGN - 0x2122: 0xaa, # TRADE MARK SIGN - 0x2206: 0xc6, # INCREMENT - 0x221a: 0xc3, # SQUARE ROOT - 0x221e: 0xb0, # INFINITY - 0x2248: 0xc5, # ALMOST EQUAL TO - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO -} \ No newline at end of file + 0x042A: 0x9A, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042B: 0x9B, # CYRILLIC CAPITAL LETTER YERU + 0x042C: 0x9C, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042D: 0x9D, # CYRILLIC CAPITAL LETTER E + 0x042E: 0x9E, # CYRILLIC CAPITAL LETTER YU + 0x042F: 0x9F, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0xE0, # CYRILLIC SMALL LETTER A + 0x0431: 0xE1, # CYRILLIC SMALL LETTER BE + 0x0432: 0xE2, # CYRILLIC SMALL LETTER VE + 0x0433: 0xE3, # CYRILLIC SMALL LETTER GHE + 0x0434: 0xE4, # CYRILLIC SMALL LETTER DE + 0x0435: 0xE5, # CYRILLIC SMALL LETTER IE + 0x0436: 0xE6, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0xE7, # CYRILLIC SMALL LETTER ZE + 0x0438: 0xE8, # CYRILLIC SMALL LETTER I + 0x0439: 0xE9, # CYRILLIC SMALL LETTER SHORT I + 0x043A: 0xEA, # CYRILLIC SMALL LETTER KA + 0x043B: 0xEB, # CYRILLIC SMALL LETTER EL + 0x043C: 0xEC, # CYRILLIC SMALL LETTER EM + 0x043D: 0xED, # CYRILLIC SMALL LETTER EN + 0x043E: 0xEE, # CYRILLIC SMALL LETTER O + 0x043F: 0xEF, # CYRILLIC SMALL LETTER PE + 0x0440: 0xF0, # CYRILLIC SMALL LETTER ER + 0x0441: 0xF1, # CYRILLIC SMALL LETTER ES + 0x0442: 0xF2, # CYRILLIC SMALL LETTER TE + 0x0443: 0xF3, # CYRILLIC SMALL LETTER U + 0x0444: 0xF4, # CYRILLIC SMALL LETTER EF + 0x0445: 0xF5, # CYRILLIC SMALL LETTER HA + 0x0446: 0xF6, # CYRILLIC SMALL LETTER TSE + 0x0447: 0xF7, # CYRILLIC SMALL LETTER CHE + 0x0448: 0xF8, # CYRILLIC SMALL LETTER SHA + 0x0449: 0xF9, # CYRILLIC SMALL LETTER SHCHA + 0x044A: 0xFA, # CYRILLIC SMALL LETTER HARD SIGN + 0x044B: 0xFB, # CYRILLIC SMALL LETTER YERU + 0x044C: 0xFC, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044D: 0xFD, # CYRILLIC SMALL LETTER E + 0x044E: 0xFE, # CYRILLIC SMALL LETTER YU + 0x044F: 0xDF, # CYRILLIC SMALL LETTER YA + 0x0451: 0xDE, # CYRILLIC SMALL LETTER IO + 0x0452: 0xAC, # CYRILLIC SMALL LETTER DJE + 0x0453: 0xAF, # CYRILLIC SMALL LETTER GJE + 0x0454: 0xB9, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0455: 0xCF, # CYRILLIC SMALL LETTER DZE + 0x0456: 0xB4, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0457: 0xBB, # CYRILLIC SMALL LETTER YI + 0x0458: 0xC0, # CYRILLIC SMALL LETTER JE + 0x0459: 0xBD, # CYRILLIC SMALL LETTER LJE + 0x045A: 0xBF, # CYRILLIC SMALL LETTER NJE + 0x045B: 0xCC, # CYRILLIC SMALL LETTER TSHE + 0x045C: 0xCE, # CYRILLIC SMALL LETTER KJE + 0x045E: 0xD9, # CYRILLIC SMALL LETTER SHORT U + 0x045F: 0xDB, # CYRILLIC SMALL LETTER DZHE + 0x0490: 0xA2, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN + 0x0491: 0xB6, # CYRILLIC SMALL LETTER GHE WITH UPTURN + 0x2013: 0xD0, # EN DASH + 0x2014: 0xD1, # EM DASH + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xD7, # DOUBLE LOW-9 QUOTATION MARK + 0x2020: 0xA0, # DAGGER + 0x2022: 0xA5, # BULLET + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS + 0x20AC: 0xFF, # EURO SIGN + 0x2116: 0xDC, # NUMERO SIGN + 0x2122: 0xAA, # TRADE MARK SIGN + 0x2206: 0xC6, # INCREMENT + 0x221A: 0xC3, # SQUARE ROOT + 0x221E: 0xB0, # INFINITY + 0x2248: 0xC5, # ALMOST EQUAL TO + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO +} + diff --git a/Lib/encodings/mac_farsi.py b/Lib/encodings/mac_farsi.py index 8a09f8e..f5ecc4c 100644 --- a/Lib/encodings/mac_farsi.py +++ b/Lib/encodings/mac_farsi.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE, left-right u'!' # 0x21 -> EXCLAMATION MARK, left-right u'"' # 0x22 -> QUOTATION MARK, left-right @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE, left-right u'(' # 0x28 -> LEFT PARENTHESIS, left-right u')' # 0x29 -> RIGHT PARENTHESIS, left-right - u'*' # 0x2a -> ASTERISK, left-right - u'+' # 0x2b -> PLUS SIGN, left-right - u',' # 0x2c -> COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR - u'-' # 0x2d -> HYPHEN-MINUS, left-right - u'.' # 0x2e -> FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR - u'/' # 0x2f -> SOLIDUS, left-right + u'*' # 0x2A -> ASTERISK, left-right + u'+' # 0x2B -> PLUS SIGN, left-right + u',' # 0x2C -> COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR + u'-' # 0x2D -> HYPHEN-MINUS, left-right + u'.' # 0x2E -> FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR + u'/' # 0x2F -> SOLIDUS, left-right u'0' # 0x30 -> DIGIT ZERO; in Arabic-script context, displayed as 0x06F0 EXTENDED ARABIC-INDIC DIGIT ZERO u'1' # 0x31 -> DIGIT ONE; in Arabic-script context, displayed as 0x06F1 EXTENDED ARABIC-INDIC DIGIT ONE u'2' # 0x32 -> DIGIT TWO; in Arabic-script context, displayed as 0x06F2 EXTENDED ARABIC-INDIC DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN; in Arabic-script context, displayed as 0x06F7 EXTENDED ARABIC-INDIC DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT; in Arabic-script context, displayed as 0x06F8 EXTENDED ARABIC-INDIC DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE; in Arabic-script context, displayed as 0x06F9 EXTENDED ARABIC-INDIC DIGIT NINE - u':' # 0x3a -> COLON, left-right - u';' # 0x3b -> SEMICOLON, left-right - u'<' # 0x3c -> LESS-THAN SIGN, left-right - u'=' # 0x3d -> EQUALS SIGN, left-right - u'>' # 0x3e -> GREATER-THAN SIGN, left-right - u'?' # 0x3f -> QUESTION MARK, left-right + u':' # 0x3A -> COLON, left-right + u';' # 0x3B -> SEMICOLON, left-right + u'<' # 0x3C -> LESS-THAN SIGN, left-right + u'=' # 0x3D -> EQUALS SIGN, left-right + u'>' # 0x3E -> GREATER-THAN SIGN, left-right + u'?' # 0x3F -> QUESTION MARK, left-right u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET, left-right - u'\\' # 0x5c -> REVERSE SOLIDUS, left-right - u']' # 0x5d -> RIGHT SQUARE BRACKET, left-right - u'^' # 0x5e -> CIRCUMFLEX ACCENT, left-right - u'_' # 0x5f -> LOW LINE, left-right + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET, left-right + u'\\' # 0x5C -> REVERSE SOLIDUS, left-right + u']' # 0x5D -> RIGHT SQUARE BRACKET, left-right + u'^' # 0x5E -> CIRCUMFLEX ACCENT, left-right + u'_' # 0x5F -> LOW LINE, left-right u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET, left-right - u'|' # 0x7c -> VERTICAL LINE, left-right - u'}' # 0x7d -> RIGHT CURLY BRACKET, left-right - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET, left-right + u'|' # 0x7C -> VERTICAL LINE, left-right + u'}' # 0x7D -> RIGHT CURLY BRACKET, left-right + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xa0' # 0x81 -> NO-BREAK SPACE, right-left u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA @@ -170,12 +170,12 @@ decoding_table = ( u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\u06ba' # 0x8b -> ARABIC LETTER NOON GHUNNA - u'\xab' # 0x8c -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left - u'\xe7' # 0x8d -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\xe8' # 0x8f -> LATIN SMALL LETTER E WITH GRAVE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\u06ba' # 0x8B -> ARABIC LETTER NOON GHUNNA + u'\xab' # 0x8C -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE @@ -186,108 +186,108 @@ decoding_table = ( u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xbb' # 0x98 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf7' # 0x9b -> DIVISION SIGN, right-left - u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE - u'\xf9' # 0x9d -> LATIN SMALL LETTER U WITH GRAVE - u'\xfb' # 0x9e -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u' ' # 0xa0 -> SPACE, right-left - u'!' # 0xa1 -> EXCLAMATION MARK, right-left - u'"' # 0xa2 -> QUOTATION MARK, right-left - u'#' # 0xa3 -> NUMBER SIGN, right-left - u'$' # 0xa4 -> DOLLAR SIGN, right-left - u'\u066a' # 0xa5 -> ARABIC PERCENT SIGN - u'&' # 0xa6 -> AMPERSAND, right-left - u"'" # 0xa7 -> APOSTROPHE, right-left - u'(' # 0xa8 -> LEFT PARENTHESIS, right-left - u')' # 0xa9 -> RIGHT PARENTHESIS, right-left - u'*' # 0xaa -> ASTERISK, right-left - u'+' # 0xab -> PLUS SIGN, right-left - u'\u060c' # 0xac -> ARABIC COMMA - u'-' # 0xad -> HYPHEN-MINUS, right-left - u'.' # 0xae -> FULL STOP, right-left - u'/' # 0xaf -> SOLIDUS, right-left - u'\u06f0' # 0xb0 -> EXTENDED ARABIC-INDIC DIGIT ZERO, right-left (need override) - u'\u06f1' # 0xb1 -> EXTENDED ARABIC-INDIC DIGIT ONE, right-left (need override) - u'\u06f2' # 0xb2 -> EXTENDED ARABIC-INDIC DIGIT TWO, right-left (need override) - u'\u06f3' # 0xb3 -> EXTENDED ARABIC-INDIC DIGIT THREE, right-left (need override) - u'\u06f4' # 0xb4 -> EXTENDED ARABIC-INDIC DIGIT FOUR, right-left (need override) - u'\u06f5' # 0xb5 -> EXTENDED ARABIC-INDIC DIGIT FIVE, right-left (need override) - u'\u06f6' # 0xb6 -> EXTENDED ARABIC-INDIC DIGIT SIX, right-left (need override) - u'\u06f7' # 0xb7 -> EXTENDED ARABIC-INDIC DIGIT SEVEN, right-left (need override) - u'\u06f8' # 0xb8 -> EXTENDED ARABIC-INDIC DIGIT EIGHT, right-left (need override) - u'\u06f9' # 0xb9 -> EXTENDED ARABIC-INDIC DIGIT NINE, right-left (need override) - u':' # 0xba -> COLON, right-left - u'\u061b' # 0xbb -> ARABIC SEMICOLON - u'<' # 0xbc -> LESS-THAN SIGN, right-left - u'=' # 0xbd -> EQUALS SIGN, right-left - u'>' # 0xbe -> GREATER-THAN SIGN, right-left - u'\u061f' # 0xbf -> ARABIC QUESTION MARK - u'\u274a' # 0xc0 -> EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left - u'\u0621' # 0xc1 -> ARABIC LETTER HAMZA - u'\u0622' # 0xc2 -> ARABIC LETTER ALEF WITH MADDA ABOVE - u'\u0623' # 0xc3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE - u'\u0624' # 0xc4 -> ARABIC LETTER WAW WITH HAMZA ABOVE - u'\u0625' # 0xc5 -> ARABIC LETTER ALEF WITH HAMZA BELOW - u'\u0626' # 0xc6 -> ARABIC LETTER YEH WITH HAMZA ABOVE - u'\u0627' # 0xc7 -> ARABIC LETTER ALEF - u'\u0628' # 0xc8 -> ARABIC LETTER BEH - u'\u0629' # 0xc9 -> ARABIC LETTER TEH MARBUTA - u'\u062a' # 0xca -> ARABIC LETTER TEH - u'\u062b' # 0xcb -> ARABIC LETTER THEH - u'\u062c' # 0xcc -> ARABIC LETTER JEEM - u'\u062d' # 0xcd -> ARABIC LETTER HAH - u'\u062e' # 0xce -> ARABIC LETTER KHAH - u'\u062f' # 0xcf -> ARABIC LETTER DAL - u'\u0630' # 0xd0 -> ARABIC LETTER THAL - u'\u0631' # 0xd1 -> ARABIC LETTER REH - u'\u0632' # 0xd2 -> ARABIC LETTER ZAIN - u'\u0633' # 0xd3 -> ARABIC LETTER SEEN - u'\u0634' # 0xd4 -> ARABIC LETTER SHEEN - u'\u0635' # 0xd5 -> ARABIC LETTER SAD - u'\u0636' # 0xd6 -> ARABIC LETTER DAD - u'\u0637' # 0xd7 -> ARABIC LETTER TAH - u'\u0638' # 0xd8 -> ARABIC LETTER ZAH - u'\u0639' # 0xd9 -> ARABIC LETTER AIN - u'\u063a' # 0xda -> ARABIC LETTER GHAIN - u'[' # 0xdb -> LEFT SQUARE BRACKET, right-left - u'\\' # 0xdc -> REVERSE SOLIDUS, right-left - u']' # 0xdd -> RIGHT SQUARE BRACKET, right-left - u'^' # 0xde -> CIRCUMFLEX ACCENT, right-left - u'_' # 0xdf -> LOW LINE, right-left - u'\u0640' # 0xe0 -> ARABIC TATWEEL - u'\u0641' # 0xe1 -> ARABIC LETTER FEH - u'\u0642' # 0xe2 -> ARABIC LETTER QAF - u'\u0643' # 0xe3 -> ARABIC LETTER KAF - u'\u0644' # 0xe4 -> ARABIC LETTER LAM - u'\u0645' # 0xe5 -> ARABIC LETTER MEEM - u'\u0646' # 0xe6 -> ARABIC LETTER NOON - u'\u0647' # 0xe7 -> ARABIC LETTER HEH - u'\u0648' # 0xe8 -> ARABIC LETTER WAW - u'\u0649' # 0xe9 -> ARABIC LETTER ALEF MAKSURA - u'\u064a' # 0xea -> ARABIC LETTER YEH - u'\u064b' # 0xeb -> ARABIC FATHATAN - u'\u064c' # 0xec -> ARABIC DAMMATAN - u'\u064d' # 0xed -> ARABIC KASRATAN - u'\u064e' # 0xee -> ARABIC FATHA - u'\u064f' # 0xef -> ARABIC DAMMA - u'\u0650' # 0xf0 -> ARABIC KASRA - u'\u0651' # 0xf1 -> ARABIC SHADDA - u'\u0652' # 0xf2 -> ARABIC SUKUN - u'\u067e' # 0xf3 -> ARABIC LETTER PEH - u'\u0679' # 0xf4 -> ARABIC LETTER TTEH - u'\u0686' # 0xf5 -> ARABIC LETTER TCHEH - u'\u06d5' # 0xf6 -> ARABIC LETTER AE - u'\u06a4' # 0xf7 -> ARABIC LETTER VEH - u'\u06af' # 0xf8 -> ARABIC LETTER GAF - u'\u0688' # 0xf9 -> ARABIC LETTER DDAL - u'\u0691' # 0xfa -> ARABIC LETTER RREH - u'{' # 0xfb -> LEFT CURLY BRACKET, right-left - u'|' # 0xfc -> VERTICAL LINE, right-left - u'}' # 0xfd -> RIGHT CURLY BRACKET, right-left - u'\u0698' # 0xfe -> ARABIC LETTER JEH - u'\u06d2' # 0xff -> ARABIC LETTER YEH BARREE + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf7' # 0x9B -> DIVISION SIGN, right-left + u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u' ' # 0xA0 -> SPACE, right-left + u'!' # 0xA1 -> EXCLAMATION MARK, right-left + u'"' # 0xA2 -> QUOTATION MARK, right-left + u'#' # 0xA3 -> NUMBER SIGN, right-left + u'$' # 0xA4 -> DOLLAR SIGN, right-left + u'\u066a' # 0xA5 -> ARABIC PERCENT SIGN + u'&' # 0xA6 -> AMPERSAND, right-left + u"'" # 0xA7 -> APOSTROPHE, right-left + u'(' # 0xA8 -> LEFT PARENTHESIS, right-left + u')' # 0xA9 -> RIGHT PARENTHESIS, right-left + u'*' # 0xAA -> ASTERISK, right-left + u'+' # 0xAB -> PLUS SIGN, right-left + u'\u060c' # 0xAC -> ARABIC COMMA + u'-' # 0xAD -> HYPHEN-MINUS, right-left + u'.' # 0xAE -> FULL STOP, right-left + u'/' # 0xAF -> SOLIDUS, right-left + u'\u06f0' # 0xB0 -> EXTENDED ARABIC-INDIC DIGIT ZERO, right-left (need override) + u'\u06f1' # 0xB1 -> EXTENDED ARABIC-INDIC DIGIT ONE, right-left (need override) + u'\u06f2' # 0xB2 -> EXTENDED ARABIC-INDIC DIGIT TWO, right-left (need override) + u'\u06f3' # 0xB3 -> EXTENDED ARABIC-INDIC DIGIT THREE, right-left (need override) + u'\u06f4' # 0xB4 -> EXTENDED ARABIC-INDIC DIGIT FOUR, right-left (need override) + u'\u06f5' # 0xB5 -> EXTENDED ARABIC-INDIC DIGIT FIVE, right-left (need override) + u'\u06f6' # 0xB6 -> EXTENDED ARABIC-INDIC DIGIT SIX, right-left (need override) + u'\u06f7' # 0xB7 -> EXTENDED ARABIC-INDIC DIGIT SEVEN, right-left (need override) + u'\u06f8' # 0xB8 -> EXTENDED ARABIC-INDIC DIGIT EIGHT, right-left (need override) + u'\u06f9' # 0xB9 -> EXTENDED ARABIC-INDIC DIGIT NINE, right-left (need override) + u':' # 0xBA -> COLON, right-left + u'\u061b' # 0xBB -> ARABIC SEMICOLON + u'<' # 0xBC -> LESS-THAN SIGN, right-left + u'=' # 0xBD -> EQUALS SIGN, right-left + u'>' # 0xBE -> GREATER-THAN SIGN, right-left + u'\u061f' # 0xBF -> ARABIC QUESTION MARK + u'\u274a' # 0xC0 -> EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left + u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA + u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE + u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE + u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE + u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW + u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE + u'\u0627' # 0xC7 -> ARABIC LETTER ALEF + u'\u0628' # 0xC8 -> ARABIC LETTER BEH + u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA + u'\u062a' # 0xCA -> ARABIC LETTER TEH + u'\u062b' # 0xCB -> ARABIC LETTER THEH + u'\u062c' # 0xCC -> ARABIC LETTER JEEM + u'\u062d' # 0xCD -> ARABIC LETTER HAH + u'\u062e' # 0xCE -> ARABIC LETTER KHAH + u'\u062f' # 0xCF -> ARABIC LETTER DAL + u'\u0630' # 0xD0 -> ARABIC LETTER THAL + u'\u0631' # 0xD1 -> ARABIC LETTER REH + u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN + u'\u0633' # 0xD3 -> ARABIC LETTER SEEN + u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN + u'\u0635' # 0xD5 -> ARABIC LETTER SAD + u'\u0636' # 0xD6 -> ARABIC LETTER DAD + u'\u0637' # 0xD7 -> ARABIC LETTER TAH + u'\u0638' # 0xD8 -> ARABIC LETTER ZAH + u'\u0639' # 0xD9 -> ARABIC LETTER AIN + u'\u063a' # 0xDA -> ARABIC LETTER GHAIN + u'[' # 0xDB -> LEFT SQUARE BRACKET, right-left + u'\\' # 0xDC -> REVERSE SOLIDUS, right-left + u']' # 0xDD -> RIGHT SQUARE BRACKET, right-left + u'^' # 0xDE -> CIRCUMFLEX ACCENT, right-left + u'_' # 0xDF -> LOW LINE, right-left + u'\u0640' # 0xE0 -> ARABIC TATWEEL + u'\u0641' # 0xE1 -> ARABIC LETTER FEH + u'\u0642' # 0xE2 -> ARABIC LETTER QAF + u'\u0643' # 0xE3 -> ARABIC LETTER KAF + u'\u0644' # 0xE4 -> ARABIC LETTER LAM + u'\u0645' # 0xE5 -> ARABIC LETTER MEEM + u'\u0646' # 0xE6 -> ARABIC LETTER NOON + u'\u0647' # 0xE7 -> ARABIC LETTER HEH + u'\u0648' # 0xE8 -> ARABIC LETTER WAW + u'\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA + u'\u064a' # 0xEA -> ARABIC LETTER YEH + u'\u064b' # 0xEB -> ARABIC FATHATAN + u'\u064c' # 0xEC -> ARABIC DAMMATAN + u'\u064d' # 0xED -> ARABIC KASRATAN + u'\u064e' # 0xEE -> ARABIC FATHA + u'\u064f' # 0xEF -> ARABIC DAMMA + u'\u0650' # 0xF0 -> ARABIC KASRA + u'\u0651' # 0xF1 -> ARABIC SHADDA + u'\u0652' # 0xF2 -> ARABIC SUKUN + u'\u067e' # 0xF3 -> ARABIC LETTER PEH + u'\u0679' # 0xF4 -> ARABIC LETTER TTEH + u'\u0686' # 0xF5 -> ARABIC LETTER TCHEH + u'\u06d5' # 0xF6 -> ARABIC LETTER AE + u'\u06a4' # 0xF7 -> ARABIC LETTER VEH + u'\u06af' # 0xF8 -> ARABIC LETTER GAF + u'\u0688' # 0xF9 -> ARABIC LETTER DDAL + u'\u0691' # 0xFA -> ARABIC LETTER RREH + u'{' # 0xFB -> LEFT CURLY BRACKET, right-left + u'|' # 0xFC -> VERTICAL LINE, right-left + u'}' # 0xFD -> RIGHT CURLY BRACKET, right-left + u'\u0698' # 0xFE -> ARABIC LETTER JEH + u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,42 +319,42 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE, left-right - 0x0020: 0xa0, # SPACE, right-left + 0x0020: 0xA0, # SPACE, right-left 0x0021: 0x21, # EXCLAMATION MARK, left-right - 0x0021: 0xa1, # EXCLAMATION MARK, right-left + 0x0021: 0xA1, # EXCLAMATION MARK, right-left 0x0022: 0x22, # QUOTATION MARK, left-right - 0x0022: 0xa2, # QUOTATION MARK, right-left + 0x0022: 0xA2, # QUOTATION MARK, right-left 0x0023: 0x23, # NUMBER SIGN, left-right - 0x0023: 0xa3, # NUMBER SIGN, right-left + 0x0023: 0xA3, # NUMBER SIGN, right-left 0x0024: 0x24, # DOLLAR SIGN, left-right - 0x0024: 0xa4, # DOLLAR SIGN, right-left + 0x0024: 0xA4, # DOLLAR SIGN, right-left 0x0025: 0x25, # PERCENT SIGN, left-right 0x0026: 0x26, # AMPERSAND, left-right - 0x0026: 0xa6, # AMPERSAND, right-left + 0x0026: 0xA6, # AMPERSAND, right-left 0x0027: 0x27, # APOSTROPHE, left-right - 0x0027: 0xa7, # APOSTROPHE, right-left + 0x0027: 0xA7, # APOSTROPHE, right-left 0x0028: 0x28, # LEFT PARENTHESIS, left-right - 0x0028: 0xa8, # LEFT PARENTHESIS, right-left + 0x0028: 0xA8, # LEFT PARENTHESIS, right-left 0x0029: 0x29, # RIGHT PARENTHESIS, left-right - 0x0029: 0xa9, # RIGHT PARENTHESIS, right-left - 0x002a: 0x2a, # ASTERISK, left-right - 0x002a: 0xaa, # ASTERISK, right-left - 0x002b: 0x2b, # PLUS SIGN, left-right - 0x002b: 0xab, # PLUS SIGN, right-left - 0x002c: 0x2c, # COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR - 0x002d: 0x2d, # HYPHEN-MINUS, left-right - 0x002d: 0xad, # HYPHEN-MINUS, right-left - 0x002e: 0x2e, # FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR - 0x002e: 0xae, # FULL STOP, right-left - 0x002f: 0x2f, # SOLIDUS, left-right - 0x002f: 0xaf, # SOLIDUS, right-left + 0x0029: 0xA9, # RIGHT PARENTHESIS, right-left + 0x002A: 0x2A, # ASTERISK, left-right + 0x002A: 0xAA, # ASTERISK, right-left + 0x002B: 0x2B, # PLUS SIGN, left-right + 0x002B: 0xAB, # PLUS SIGN, right-left + 0x002C: 0x2C, # COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR + 0x002D: 0x2D, # HYPHEN-MINUS, left-right + 0x002D: 0xAD, # HYPHEN-MINUS, right-left + 0x002E: 0x2E, # FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR + 0x002E: 0xAE, # FULL STOP, right-left + 0x002F: 0x2F, # SOLIDUS, left-right + 0x002F: 0xAF, # SOLIDUS, right-left 0x0030: 0x30, # DIGIT ZERO; in Arabic-script context, displayed as 0x06F0 EXTENDED ARABIC-INDIC DIGIT ZERO 0x0031: 0x31, # DIGIT ONE; in Arabic-script context, displayed as 0x06F1 EXTENDED ARABIC-INDIC DIGIT ONE 0x0032: 0x32, # DIGIT TWO; in Arabic-script context, displayed as 0x06F2 EXTENDED ARABIC-INDIC DIGIT TWO @@ -365,16 +365,16 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN; in Arabic-script context, displayed as 0x06F7 EXTENDED ARABIC-INDIC DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT; in Arabic-script context, displayed as 0x06F8 EXTENDED ARABIC-INDIC DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE; in Arabic-script context, displayed as 0x06F9 EXTENDED ARABIC-INDIC DIGIT NINE - 0x003a: 0x3a, # COLON, left-right - 0x003a: 0xba, # COLON, right-left - 0x003b: 0x3b, # SEMICOLON, left-right - 0x003c: 0x3c, # LESS-THAN SIGN, left-right - 0x003c: 0xbc, # LESS-THAN SIGN, right-left - 0x003d: 0x3d, # EQUALS SIGN, left-right - 0x003d: 0xbd, # EQUALS SIGN, right-left - 0x003e: 0x3e, # GREATER-THAN SIGN, left-right - 0x003e: 0xbe, # GREATER-THAN SIGN, right-left - 0x003f: 0x3f, # QUESTION MARK, left-right + 0x003A: 0x3A, # COLON, left-right + 0x003A: 0xBA, # COLON, right-left + 0x003B: 0x3B, # SEMICOLON, left-right + 0x003C: 0x3C, # LESS-THAN SIGN, left-right + 0x003C: 0xBC, # LESS-THAN SIGN, right-left + 0x003D: 0x3D, # EQUALS SIGN, left-right + 0x003D: 0xBD, # EQUALS SIGN, right-left + 0x003E: 0x3E, # GREATER-THAN SIGN, left-right + 0x003E: 0xBE, # GREATER-THAN SIGN, right-left + 0x003F: 0x3F, # QUESTION MARK, left-right 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -385,12 +385,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -401,17 +401,17 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET, left-right - 0x005b: 0xdb, # LEFT SQUARE BRACKET, right-left - 0x005c: 0x5c, # REVERSE SOLIDUS, left-right - 0x005c: 0xdc, # REVERSE SOLIDUS, right-left - 0x005d: 0x5d, # RIGHT SQUARE BRACKET, left-right - 0x005d: 0xdd, # RIGHT SQUARE BRACKET, right-left - 0x005e: 0x5e, # CIRCUMFLEX ACCENT, left-right - 0x005e: 0xde, # CIRCUMFLEX ACCENT, right-left - 0x005f: 0x5f, # LOW LINE, left-right - 0x005f: 0xdf, # LOW LINE, right-left + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET, left-right + 0x005B: 0xDB, # LEFT SQUARE BRACKET, right-left + 0x005C: 0x5C, # REVERSE SOLIDUS, left-right + 0x005C: 0xDC, # REVERSE SOLIDUS, right-left + 0x005D: 0x5D, # RIGHT SQUARE BRACKET, left-right + 0x005D: 0xDD, # RIGHT SQUARE BRACKET, right-left + 0x005E: 0x5E, # CIRCUMFLEX ACCENT, left-right + 0x005E: 0xDE, # CIRCUMFLEX ACCENT, right-left + 0x005F: 0x5F, # LOW LINE, left-right + 0x005F: 0xDF, # LOW LINE, right-left 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -422,12 +422,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -438,115 +438,116 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET, left-right - 0x007b: 0xfb, # LEFT CURLY BRACKET, right-left - 0x007c: 0x7c, # VERTICAL LINE, left-right - 0x007c: 0xfc, # VERTICAL LINE, right-left - 0x007d: 0x7d, # RIGHT CURLY BRACKET, left-right - 0x007d: 0xfd, # RIGHT CURLY BRACKET, right-left - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0x81, # NO-BREAK SPACE, right-left - 0x00ab: 0x8c, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left - 0x00bb: 0x98, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00d1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00e0: 0x88, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e7: 0x8d, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x8f, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0x96, # LATIN SMALL LETTER N WITH TILDE - 0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0x9b, # DIVISION SIGN, right-left - 0x00f9: 0x9d, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0x9e, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x060c: 0xac, # ARABIC COMMA - 0x061b: 0xbb, # ARABIC SEMICOLON - 0x061f: 0xbf, # ARABIC QUESTION MARK - 0x0621: 0xc1, # ARABIC LETTER HAMZA - 0x0622: 0xc2, # ARABIC LETTER ALEF WITH MADDA ABOVE - 0x0623: 0xc3, # ARABIC LETTER ALEF WITH HAMZA ABOVE - 0x0624: 0xc4, # ARABIC LETTER WAW WITH HAMZA ABOVE - 0x0625: 0xc5, # ARABIC LETTER ALEF WITH HAMZA BELOW - 0x0626: 0xc6, # ARABIC LETTER YEH WITH HAMZA ABOVE - 0x0627: 0xc7, # ARABIC LETTER ALEF - 0x0628: 0xc8, # ARABIC LETTER BEH - 0x0629: 0xc9, # ARABIC LETTER TEH MARBUTA - 0x062a: 0xca, # ARABIC LETTER TEH - 0x062b: 0xcb, # ARABIC LETTER THEH - 0x062c: 0xcc, # ARABIC LETTER JEEM - 0x062d: 0xcd, # ARABIC LETTER HAH - 0x062e: 0xce, # ARABIC LETTER KHAH - 0x062f: 0xcf, # ARABIC LETTER DAL - 0x0630: 0xd0, # ARABIC LETTER THAL - 0x0631: 0xd1, # ARABIC LETTER REH - 0x0632: 0xd2, # ARABIC LETTER ZAIN - 0x0633: 0xd3, # ARABIC LETTER SEEN - 0x0634: 0xd4, # ARABIC LETTER SHEEN - 0x0635: 0xd5, # ARABIC LETTER SAD - 0x0636: 0xd6, # ARABIC LETTER DAD - 0x0637: 0xd7, # ARABIC LETTER TAH - 0x0638: 0xd8, # ARABIC LETTER ZAH - 0x0639: 0xd9, # ARABIC LETTER AIN - 0x063a: 0xda, # ARABIC LETTER GHAIN - 0x0640: 0xe0, # ARABIC TATWEEL - 0x0641: 0xe1, # ARABIC LETTER FEH - 0x0642: 0xe2, # ARABIC LETTER QAF - 0x0643: 0xe3, # ARABIC LETTER KAF - 0x0644: 0xe4, # ARABIC LETTER LAM - 0x0645: 0xe5, # ARABIC LETTER MEEM - 0x0646: 0xe6, # ARABIC LETTER NOON - 0x0647: 0xe7, # ARABIC LETTER HEH - 0x0648: 0xe8, # ARABIC LETTER WAW - 0x0649: 0xe9, # ARABIC LETTER ALEF MAKSURA - 0x064a: 0xea, # ARABIC LETTER YEH - 0x064b: 0xeb, # ARABIC FATHATAN - 0x064c: 0xec, # ARABIC DAMMATAN - 0x064d: 0xed, # ARABIC KASRATAN - 0x064e: 0xee, # ARABIC FATHA - 0x064f: 0xef, # ARABIC DAMMA - 0x0650: 0xf0, # ARABIC KASRA - 0x0651: 0xf1, # ARABIC SHADDA - 0x0652: 0xf2, # ARABIC SUKUN - 0x066a: 0xa5, # ARABIC PERCENT SIGN - 0x0679: 0xf4, # ARABIC LETTER TTEH - 0x067e: 0xf3, # ARABIC LETTER PEH - 0x0686: 0xf5, # ARABIC LETTER TCHEH - 0x0688: 0xf9, # ARABIC LETTER DDAL - 0x0691: 0xfa, # ARABIC LETTER RREH - 0x0698: 0xfe, # ARABIC LETTER JEH - 0x06a4: 0xf7, # ARABIC LETTER VEH - 0x06af: 0xf8, # ARABIC LETTER GAF - 0x06ba: 0x8b, # ARABIC LETTER NOON GHUNNA - 0x06d2: 0xff, # ARABIC LETTER YEH BARREE - 0x06d5: 0xf6, # ARABIC LETTER AE - 0x06f0: 0xb0, # EXTENDED ARABIC-INDIC DIGIT ZERO, right-left (need override) - 0x06f1: 0xb1, # EXTENDED ARABIC-INDIC DIGIT ONE, right-left (need override) - 0x06f2: 0xb2, # EXTENDED ARABIC-INDIC DIGIT TWO, right-left (need override) - 0x06f3: 0xb3, # EXTENDED ARABIC-INDIC DIGIT THREE, right-left (need override) - 0x06f4: 0xb4, # EXTENDED ARABIC-INDIC DIGIT FOUR, right-left (need override) - 0x06f5: 0xb5, # EXTENDED ARABIC-INDIC DIGIT FIVE, right-left (need override) - 0x06f6: 0xb6, # EXTENDED ARABIC-INDIC DIGIT SIX, right-left (need override) - 0x06f7: 0xb7, # EXTENDED ARABIC-INDIC DIGIT SEVEN, right-left (need override) - 0x06f8: 0xb8, # EXTENDED ARABIC-INDIC DIGIT EIGHT, right-left (need override) - 0x06f9: 0xb9, # EXTENDED ARABIC-INDIC DIGIT NINE, right-left (need override) + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET, left-right + 0x007B: 0xFB, # LEFT CURLY BRACKET, right-left + 0x007C: 0x7C, # VERTICAL LINE, left-right + 0x007C: 0xFC, # VERTICAL LINE, right-left + 0x007D: 0x7D, # RIGHT CURLY BRACKET, left-right + 0x007D: 0xFD, # RIGHT CURLY BRACKET, right-left + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0x81, # NO-BREAK SPACE, right-left + 0x00AB: 0x8C, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + 0x00BB: 0x98, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE + 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0x9B, # DIVISION SIGN, right-left + 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x060C: 0xAC, # ARABIC COMMA + 0x061B: 0xBB, # ARABIC SEMICOLON + 0x061F: 0xBF, # ARABIC QUESTION MARK + 0x0621: 0xC1, # ARABIC LETTER HAMZA + 0x0622: 0xC2, # ARABIC LETTER ALEF WITH MADDA ABOVE + 0x0623: 0xC3, # ARABIC LETTER ALEF WITH HAMZA ABOVE + 0x0624: 0xC4, # ARABIC LETTER WAW WITH HAMZA ABOVE + 0x0625: 0xC5, # ARABIC LETTER ALEF WITH HAMZA BELOW + 0x0626: 0xC6, # ARABIC LETTER YEH WITH HAMZA ABOVE + 0x0627: 0xC7, # ARABIC LETTER ALEF + 0x0628: 0xC8, # ARABIC LETTER BEH + 0x0629: 0xC9, # ARABIC LETTER TEH MARBUTA + 0x062A: 0xCA, # ARABIC LETTER TEH + 0x062B: 0xCB, # ARABIC LETTER THEH + 0x062C: 0xCC, # ARABIC LETTER JEEM + 0x062D: 0xCD, # ARABIC LETTER HAH + 0x062E: 0xCE, # ARABIC LETTER KHAH + 0x062F: 0xCF, # ARABIC LETTER DAL + 0x0630: 0xD0, # ARABIC LETTER THAL + 0x0631: 0xD1, # ARABIC LETTER REH + 0x0632: 0xD2, # ARABIC LETTER ZAIN + 0x0633: 0xD3, # ARABIC LETTER SEEN + 0x0634: 0xD4, # ARABIC LETTER SHEEN + 0x0635: 0xD5, # ARABIC LETTER SAD + 0x0636: 0xD6, # ARABIC LETTER DAD + 0x0637: 0xD7, # ARABIC LETTER TAH + 0x0638: 0xD8, # ARABIC LETTER ZAH + 0x0639: 0xD9, # ARABIC LETTER AIN + 0x063A: 0xDA, # ARABIC LETTER GHAIN + 0x0640: 0xE0, # ARABIC TATWEEL + 0x0641: 0xE1, # ARABIC LETTER FEH + 0x0642: 0xE2, # ARABIC LETTER QAF + 0x0643: 0xE3, # ARABIC LETTER KAF + 0x0644: 0xE4, # ARABIC LETTER LAM + 0x0645: 0xE5, # ARABIC LETTER MEEM + 0x0646: 0xE6, # ARABIC LETTER NOON + 0x0647: 0xE7, # ARABIC LETTER HEH + 0x0648: 0xE8, # ARABIC LETTER WAW + 0x0649: 0xE9, # ARABIC LETTER ALEF MAKSURA + 0x064A: 0xEA, # ARABIC LETTER YEH + 0x064B: 0xEB, # ARABIC FATHATAN + 0x064C: 0xEC, # ARABIC DAMMATAN + 0x064D: 0xED, # ARABIC KASRATAN + 0x064E: 0xEE, # ARABIC FATHA + 0x064F: 0xEF, # ARABIC DAMMA + 0x0650: 0xF0, # ARABIC KASRA + 0x0651: 0xF1, # ARABIC SHADDA + 0x0652: 0xF2, # ARABIC SUKUN + 0x066A: 0xA5, # ARABIC PERCENT SIGN + 0x0679: 0xF4, # ARABIC LETTER TTEH + 0x067E: 0xF3, # ARABIC LETTER PEH + 0x0686: 0xF5, # ARABIC LETTER TCHEH + 0x0688: 0xF9, # ARABIC LETTER DDAL + 0x0691: 0xFA, # ARABIC LETTER RREH + 0x0698: 0xFE, # ARABIC LETTER JEH + 0x06A4: 0xF7, # ARABIC LETTER VEH + 0x06AF: 0xF8, # ARABIC LETTER GAF + 0x06BA: 0x8B, # ARABIC LETTER NOON GHUNNA + 0x06D2: 0xFF, # ARABIC LETTER YEH BARREE + 0x06D5: 0xF6, # ARABIC LETTER AE + 0x06F0: 0xB0, # EXTENDED ARABIC-INDIC DIGIT ZERO, right-left (need override) + 0x06F1: 0xB1, # EXTENDED ARABIC-INDIC DIGIT ONE, right-left (need override) + 0x06F2: 0xB2, # EXTENDED ARABIC-INDIC DIGIT TWO, right-left (need override) + 0x06F3: 0xB3, # EXTENDED ARABIC-INDIC DIGIT THREE, right-left (need override) + 0x06F4: 0xB4, # EXTENDED ARABIC-INDIC DIGIT FOUR, right-left (need override) + 0x06F5: 0xB5, # EXTENDED ARABIC-INDIC DIGIT FIVE, right-left (need override) + 0x06F6: 0xB6, # EXTENDED ARABIC-INDIC DIGIT SIX, right-left (need override) + 0x06F7: 0xB7, # EXTENDED ARABIC-INDIC DIGIT SEVEN, right-left (need override) + 0x06F8: 0xB8, # EXTENDED ARABIC-INDIC DIGIT EIGHT, right-left (need override) + 0x06F9: 0xB9, # EXTENDED ARABIC-INDIC DIGIT NINE, right-left (need override) 0x2026: 0x93, # HORIZONTAL ELLIPSIS, right-left - 0x274a: 0xc0, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left -} \ No newline at end of file + 0x274A: 0xC0, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left +} + diff --git a/Lib/encodings/mac_greek.py b/Lib/encodings/mac_greek.py index d0757c1..872e92d 100644 --- a/Lib/encodings/mac_greek.py +++ b/Lib/encodings/mac_greek.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xb9' # 0x81 -> SUPERSCRIPT ONE u'\xb2' # 0x82 -> SUPERSCRIPT TWO @@ -170,12 +170,12 @@ decoding_table = ( u'\u0385' # 0x87 -> GREEK DIALYTIKA TONOS u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\u0384' # 0x8b -> GREEK TONOS - u'\xa8' # 0x8c -> DIAERESIS - u'\xe7' # 0x8d -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\xe8' # 0x8f -> LATIN SMALL LETTER E WITH GRAVE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\u0384' # 0x8B -> GREEK TONOS + u'\xa8' # 0x8C -> DIAERESIS + u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xa3' # 0x92 -> POUND SIGN @@ -186,108 +186,108 @@ decoding_table = ( u'\xbd' # 0x97 -> VULGAR FRACTION ONE HALF u'\u2030' # 0x98 -> PER MILLE SIGN u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xa6' # 0x9b -> BROKEN BAR - u'\u20ac' # 0x9c -> EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN - u'\xf9' # 0x9d -> LATIN SMALL LETTER U WITH GRAVE - u'\xfb' # 0x9e -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u2020' # 0xa0 -> DAGGER - u'\u0393' # 0xa1 -> GREEK CAPITAL LETTER GAMMA - u'\u0394' # 0xa2 -> GREEK CAPITAL LETTER DELTA - u'\u0398' # 0xa3 -> GREEK CAPITAL LETTER THETA - u'\u039b' # 0xa4 -> GREEK CAPITAL LETTER LAMDA - u'\u039e' # 0xa5 -> GREEK CAPITAL LETTER XI - u'\u03a0' # 0xa6 -> GREEK CAPITAL LETTER PI - u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u03a3' # 0xaa -> GREEK CAPITAL LETTER SIGMA - u'\u03aa' # 0xab -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - u'\xa7' # 0xac -> SECTION SIGN - u'\u2260' # 0xad -> NOT EQUAL TO - u'\xb0' # 0xae -> DEGREE SIGN - u'\xb7' # 0xaf -> MIDDLE DOT - u'\u0391' # 0xb0 -> GREEK CAPITAL LETTER ALPHA - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\xa5' # 0xb4 -> YEN SIGN - u'\u0392' # 0xb5 -> GREEK CAPITAL LETTER BETA - u'\u0395' # 0xb6 -> GREEK CAPITAL LETTER EPSILON - u'\u0396' # 0xb7 -> GREEK CAPITAL LETTER ZETA - u'\u0397' # 0xb8 -> GREEK CAPITAL LETTER ETA - u'\u0399' # 0xb9 -> GREEK CAPITAL LETTER IOTA - u'\u039a' # 0xba -> GREEK CAPITAL LETTER KAPPA - u'\u039c' # 0xbb -> GREEK CAPITAL LETTER MU - u'\u03a6' # 0xbc -> GREEK CAPITAL LETTER PHI - u'\u03ab' # 0xbd -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - u'\u03a8' # 0xbe -> GREEK CAPITAL LETTER PSI - u'\u03a9' # 0xbf -> GREEK CAPITAL LETTER OMEGA - u'\u03ac' # 0xc0 -> GREEK SMALL LETTER ALPHA WITH TONOS - u'\u039d' # 0xc1 -> GREEK CAPITAL LETTER NU - u'\xac' # 0xc2 -> NOT SIGN - u'\u039f' # 0xc3 -> GREEK CAPITAL LETTER OMICRON - u'\u03a1' # 0xc4 -> GREEK CAPITAL LETTER RHO - u'\u2248' # 0xc5 -> ALMOST EQUAL TO - u'\u03a4' # 0xc6 -> GREEK CAPITAL LETTER TAU - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\u03a5' # 0xcb -> GREEK CAPITAL LETTER UPSILON - u'\u03a7' # 0xcc -> GREEK CAPITAL LETTER CHI - u'\u0386' # 0xcd -> GREEK CAPITAL LETTER ALPHA WITH TONOS - u'\u0388' # 0xce -> GREEK CAPITAL LETTER EPSILON WITH TONOS - u'\u0153' # 0xcf -> LATIN SMALL LIGATURE OE - u'\u2013' # 0xd0 -> EN DASH - u'\u2015' # 0xd1 -> HORIZONTAL BAR - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u0389' # 0xd7 -> GREEK CAPITAL LETTER ETA WITH TONOS - u'\u038a' # 0xd8 -> GREEK CAPITAL LETTER IOTA WITH TONOS - u'\u038c' # 0xd9 -> GREEK CAPITAL LETTER OMICRON WITH TONOS - u'\u038e' # 0xda -> GREEK CAPITAL LETTER UPSILON WITH TONOS - u'\u03ad' # 0xdb -> GREEK SMALL LETTER EPSILON WITH TONOS - u'\u03ae' # 0xdc -> GREEK SMALL LETTER ETA WITH TONOS - u'\u03af' # 0xdd -> GREEK SMALL LETTER IOTA WITH TONOS - u'\u03cc' # 0xde -> GREEK SMALL LETTER OMICRON WITH TONOS - u'\u038f' # 0xdf -> GREEK CAPITAL LETTER OMEGA WITH TONOS - u'\u03cd' # 0xe0 -> GREEK SMALL LETTER UPSILON WITH TONOS - u'\u03b1' # 0xe1 -> GREEK SMALL LETTER ALPHA - u'\u03b2' # 0xe2 -> GREEK SMALL LETTER BETA - u'\u03c8' # 0xe3 -> GREEK SMALL LETTER PSI - u'\u03b4' # 0xe4 -> GREEK SMALL LETTER DELTA - u'\u03b5' # 0xe5 -> GREEK SMALL LETTER EPSILON - u'\u03c6' # 0xe6 -> GREEK SMALL LETTER PHI - u'\u03b3' # 0xe7 -> GREEK SMALL LETTER GAMMA - u'\u03b7' # 0xe8 -> GREEK SMALL LETTER ETA - u'\u03b9' # 0xe9 -> GREEK SMALL LETTER IOTA - u'\u03be' # 0xea -> GREEK SMALL LETTER XI - u'\u03ba' # 0xeb -> GREEK SMALL LETTER KAPPA - u'\u03bb' # 0xec -> GREEK SMALL LETTER LAMDA - u'\u03bc' # 0xed -> GREEK SMALL LETTER MU - u'\u03bd' # 0xee -> GREEK SMALL LETTER NU - u'\u03bf' # 0xef -> GREEK SMALL LETTER OMICRON - u'\u03c0' # 0xf0 -> GREEK SMALL LETTER PI - u'\u03ce' # 0xf1 -> GREEK SMALL LETTER OMEGA WITH TONOS - u'\u03c1' # 0xf2 -> GREEK SMALL LETTER RHO - u'\u03c3' # 0xf3 -> GREEK SMALL LETTER SIGMA - u'\u03c4' # 0xf4 -> GREEK SMALL LETTER TAU - u'\u03b8' # 0xf5 -> GREEK SMALL LETTER THETA - u'\u03c9' # 0xf6 -> GREEK SMALL LETTER OMEGA - u'\u03c2' # 0xf7 -> GREEK SMALL LETTER FINAL SIGMA - u'\u03c7' # 0xf8 -> GREEK SMALL LETTER CHI - u'\u03c5' # 0xf9 -> GREEK SMALL LETTER UPSILON - u'\u03b6' # 0xfa -> GREEK SMALL LETTER ZETA - u'\u03ca' # 0xfb -> GREEK SMALL LETTER IOTA WITH DIALYTIKA - u'\u03cb' # 0xfc -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA - u'\u0390' # 0xfd -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS - u'\u03b0' # 0xfe -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - u'\xad' # 0xff -> SOFT HYPHEN # before Mac OS 9.2.2, was undefined + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xa6' # 0x9B -> BROKEN BAR + u'\u20ac' # 0x9C -> EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN + u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u2020' # 0xA0 -> DAGGER + u'\u0393' # 0xA1 -> GREEK CAPITAL LETTER GAMMA + u'\u0394' # 0xA2 -> GREEK CAPITAL LETTER DELTA + u'\u0398' # 0xA3 -> GREEK CAPITAL LETTER THETA + u'\u039b' # 0xA4 -> GREEK CAPITAL LETTER LAMDA + u'\u039e' # 0xA5 -> GREEK CAPITAL LETTER XI + u'\u03a0' # 0xA6 -> GREEK CAPITAL LETTER PI + u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u03a3' # 0xAA -> GREEK CAPITAL LETTER SIGMA + u'\u03aa' # 0xAB -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + u'\xa7' # 0xAC -> SECTION SIGN + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\xb0' # 0xAE -> DEGREE SIGN + u'\xb7' # 0xAF -> MIDDLE DOT + u'\u0391' # 0xB0 -> GREEK CAPITAL LETTER ALPHA + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\xa5' # 0xB4 -> YEN SIGN + u'\u0392' # 0xB5 -> GREEK CAPITAL LETTER BETA + u'\u0395' # 0xB6 -> GREEK CAPITAL LETTER EPSILON + u'\u0396' # 0xB7 -> GREEK CAPITAL LETTER ZETA + u'\u0397' # 0xB8 -> GREEK CAPITAL LETTER ETA + u'\u0399' # 0xB9 -> GREEK CAPITAL LETTER IOTA + u'\u039a' # 0xBA -> GREEK CAPITAL LETTER KAPPA + u'\u039c' # 0xBB -> GREEK CAPITAL LETTER MU + u'\u03a6' # 0xBC -> GREEK CAPITAL LETTER PHI + u'\u03ab' # 0xBD -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + u'\u03a8' # 0xBE -> GREEK CAPITAL LETTER PSI + u'\u03a9' # 0xBF -> GREEK CAPITAL LETTER OMEGA + u'\u03ac' # 0xC0 -> GREEK SMALL LETTER ALPHA WITH TONOS + u'\u039d' # 0xC1 -> GREEK CAPITAL LETTER NU + u'\xac' # 0xC2 -> NOT SIGN + u'\u039f' # 0xC3 -> GREEK CAPITAL LETTER OMICRON + u'\u03a1' # 0xC4 -> GREEK CAPITAL LETTER RHO + u'\u2248' # 0xC5 -> ALMOST EQUAL TO + u'\u03a4' # 0xC6 -> GREEK CAPITAL LETTER TAU + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\u03a5' # 0xCB -> GREEK CAPITAL LETTER UPSILON + u'\u03a7' # 0xCC -> GREEK CAPITAL LETTER CHI + u'\u0386' # 0xCD -> GREEK CAPITAL LETTER ALPHA WITH TONOS + u'\u0388' # 0xCE -> GREEK CAPITAL LETTER EPSILON WITH TONOS + u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + u'\u2013' # 0xD0 -> EN DASH + u'\u2015' # 0xD1 -> HORIZONTAL BAR + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u0389' # 0xD7 -> GREEK CAPITAL LETTER ETA WITH TONOS + u'\u038a' # 0xD8 -> GREEK CAPITAL LETTER IOTA WITH TONOS + u'\u038c' # 0xD9 -> GREEK CAPITAL LETTER OMICRON WITH TONOS + u'\u038e' # 0xDA -> GREEK CAPITAL LETTER UPSILON WITH TONOS + u'\u03ad' # 0xDB -> GREEK SMALL LETTER EPSILON WITH TONOS + u'\u03ae' # 0xDC -> GREEK SMALL LETTER ETA WITH TONOS + u'\u03af' # 0xDD -> GREEK SMALL LETTER IOTA WITH TONOS + u'\u03cc' # 0xDE -> GREEK SMALL LETTER OMICRON WITH TONOS + u'\u038f' # 0xDF -> GREEK CAPITAL LETTER OMEGA WITH TONOS + u'\u03cd' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH TONOS + u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA + u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA + u'\u03c8' # 0xE3 -> GREEK SMALL LETTER PSI + u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA + u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON + u'\u03c6' # 0xE6 -> GREEK SMALL LETTER PHI + u'\u03b3' # 0xE7 -> GREEK SMALL LETTER GAMMA + u'\u03b7' # 0xE8 -> GREEK SMALL LETTER ETA + u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA + u'\u03be' # 0xEA -> GREEK SMALL LETTER XI + u'\u03ba' # 0xEB -> GREEK SMALL LETTER KAPPA + u'\u03bb' # 0xEC -> GREEK SMALL LETTER LAMDA + u'\u03bc' # 0xED -> GREEK SMALL LETTER MU + u'\u03bd' # 0xEE -> GREEK SMALL LETTER NU + u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON + u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI + u'\u03ce' # 0xF1 -> GREEK SMALL LETTER OMEGA WITH TONOS + u'\u03c1' # 0xF2 -> GREEK SMALL LETTER RHO + u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA + u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU + u'\u03b8' # 0xF5 -> GREEK SMALL LETTER THETA + u'\u03c9' # 0xF6 -> GREEK SMALL LETTER OMEGA + u'\u03c2' # 0xF7 -> GREEK SMALL LETTER FINAL SIGMA + u'\u03c7' # 0xF8 -> GREEK SMALL LETTER CHI + u'\u03c5' # 0xF9 -> GREEK SMALL LETTER UPSILON + u'\u03b6' # 0xFA -> GREEK SMALL LETTER ZETA + u'\u03ca' # 0xFB -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + u'\u03cb' # 0xFC -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + u'\u0390' # 0xFD -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + u'\u03b0' # 0xFE -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + u'\xad' # 0xFF -> SOFT HYPHEN # before Mac OS 9.2.2, was undefined ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a3: 0x92, # POUND SIGN - 0x00a5: 0xb4, # YEN SIGN - 0x00a6: 0x9b, # BROKEN BAR - 0x00a7: 0xac, # SECTION SIGN - 0x00a8: 0x8c, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ad: 0xff, # SOFT HYPHEN # before Mac OS 9.2.2, was undefined - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00b0: 0xae, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b2: 0x82, # SUPERSCRIPT TWO - 0x00b3: 0x84, # SUPERSCRIPT THREE - 0x00b7: 0xaf, # MIDDLE DOT - 0x00b9: 0x81, # SUPERSCRIPT ONE - 0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bd: 0x97, # VULGAR FRACTION ONE HALF - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xa7, # LATIN SMALL LETTER SHARP S - 0x00e0: 0x88, # LATIN SMALL LETTER A WITH GRAVE - 0x00e2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e7: 0x8d, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x8f, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ee: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xd6, # DIVISION SIGN - 0x00f9: 0x9d, # LATIN SMALL LETTER U WITH GRAVE - 0x00fb: 0x9e, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x0153: 0xcf, # LATIN SMALL LIGATURE OE - 0x0384: 0x8b, # GREEK TONOS + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A3: 0x92, # POUND SIGN + 0x00A5: 0xB4, # YEN SIGN + 0x00A6: 0x9B, # BROKEN BAR + 0x00A7: 0xAC, # SECTION SIGN + 0x00A8: 0x8C, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AD: 0xFF, # SOFT HYPHEN # before Mac OS 9.2.2, was undefined + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00B0: 0xAE, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B2: 0x82, # SUPERSCRIPT TWO + 0x00B3: 0x84, # SUPERSCRIPT THREE + 0x00B7: 0xAF, # MIDDLE DOT + 0x00B9: 0x81, # SUPERSCRIPT ONE + 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BD: 0x97, # VULGAR FRACTION ONE HALF + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S + 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE + 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xD6, # DIVISION SIGN + 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE + 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0153: 0xCF, # LATIN SMALL LIGATURE OE + 0x0384: 0x8B, # GREEK TONOS 0x0385: 0x87, # GREEK DIALYTIKA TONOS - 0x0386: 0xcd, # GREEK CAPITAL LETTER ALPHA WITH TONOS - 0x0388: 0xce, # GREEK CAPITAL LETTER EPSILON WITH TONOS - 0x0389: 0xd7, # GREEK CAPITAL LETTER ETA WITH TONOS - 0x038a: 0xd8, # GREEK CAPITAL LETTER IOTA WITH TONOS - 0x038c: 0xd9, # GREEK CAPITAL LETTER OMICRON WITH TONOS - 0x038e: 0xda, # GREEK CAPITAL LETTER UPSILON WITH TONOS - 0x038f: 0xdf, # GREEK CAPITAL LETTER OMEGA WITH TONOS - 0x0390: 0xfd, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS - 0x0391: 0xb0, # GREEK CAPITAL LETTER ALPHA - 0x0392: 0xb5, # GREEK CAPITAL LETTER BETA - 0x0393: 0xa1, # GREEK CAPITAL LETTER GAMMA - 0x0394: 0xa2, # GREEK CAPITAL LETTER DELTA - 0x0395: 0xb6, # GREEK CAPITAL LETTER EPSILON - 0x0396: 0xb7, # GREEK CAPITAL LETTER ZETA - 0x0397: 0xb8, # GREEK CAPITAL LETTER ETA - 0x0398: 0xa3, # GREEK CAPITAL LETTER THETA - 0x0399: 0xb9, # GREEK CAPITAL LETTER IOTA - 0x039a: 0xba, # GREEK CAPITAL LETTER KAPPA - 0x039b: 0xa4, # GREEK CAPITAL LETTER LAMDA - 0x039c: 0xbb, # GREEK CAPITAL LETTER MU - 0x039d: 0xc1, # GREEK CAPITAL LETTER NU - 0x039e: 0xa5, # GREEK CAPITAL LETTER XI - 0x039f: 0xc3, # GREEK CAPITAL LETTER OMICRON - 0x03a0: 0xa6, # GREEK CAPITAL LETTER PI - 0x03a1: 0xc4, # GREEK CAPITAL LETTER RHO - 0x03a3: 0xaa, # GREEK CAPITAL LETTER SIGMA - 0x03a4: 0xc6, # GREEK CAPITAL LETTER TAU - 0x03a5: 0xcb, # GREEK CAPITAL LETTER UPSILON - 0x03a6: 0xbc, # GREEK CAPITAL LETTER PHI - 0x03a7: 0xcc, # GREEK CAPITAL LETTER CHI - 0x03a8: 0xbe, # GREEK CAPITAL LETTER PSI - 0x03a9: 0xbf, # GREEK CAPITAL LETTER OMEGA - 0x03aa: 0xab, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - 0x03ab: 0xbd, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - 0x03ac: 0xc0, # GREEK SMALL LETTER ALPHA WITH TONOS - 0x03ad: 0xdb, # GREEK SMALL LETTER EPSILON WITH TONOS - 0x03ae: 0xdc, # GREEK SMALL LETTER ETA WITH TONOS - 0x03af: 0xdd, # GREEK SMALL LETTER IOTA WITH TONOS - 0x03b0: 0xfe, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - 0x03b1: 0xe1, # GREEK SMALL LETTER ALPHA - 0x03b2: 0xe2, # GREEK SMALL LETTER BETA - 0x03b3: 0xe7, # GREEK SMALL LETTER GAMMA - 0x03b4: 0xe4, # GREEK SMALL LETTER DELTA - 0x03b5: 0xe5, # GREEK SMALL LETTER EPSILON - 0x03b6: 0xfa, # GREEK SMALL LETTER ZETA - 0x03b7: 0xe8, # GREEK SMALL LETTER ETA - 0x03b8: 0xf5, # GREEK SMALL LETTER THETA - 0x03b9: 0xe9, # GREEK SMALL LETTER IOTA - 0x03ba: 0xeb, # GREEK SMALL LETTER KAPPA - 0x03bb: 0xec, # GREEK SMALL LETTER LAMDA - 0x03bc: 0xed, # GREEK SMALL LETTER MU - 0x03bd: 0xee, # GREEK SMALL LETTER NU - 0x03be: 0xea, # GREEK SMALL LETTER XI - 0x03bf: 0xef, # GREEK SMALL LETTER OMICRON - 0x03c0: 0xf0, # GREEK SMALL LETTER PI - 0x03c1: 0xf2, # GREEK SMALL LETTER RHO - 0x03c2: 0xf7, # GREEK SMALL LETTER FINAL SIGMA - 0x03c3: 0xf3, # GREEK SMALL LETTER SIGMA - 0x03c4: 0xf4, # GREEK SMALL LETTER TAU - 0x03c5: 0xf9, # GREEK SMALL LETTER UPSILON - 0x03c6: 0xe6, # GREEK SMALL LETTER PHI - 0x03c7: 0xf8, # GREEK SMALL LETTER CHI - 0x03c8: 0xe3, # GREEK SMALL LETTER PSI - 0x03c9: 0xf6, # GREEK SMALL LETTER OMEGA - 0x03ca: 0xfb, # GREEK SMALL LETTER IOTA WITH DIALYTIKA - 0x03cb: 0xfc, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA - 0x03cc: 0xde, # GREEK SMALL LETTER OMICRON WITH TONOS - 0x03cd: 0xe0, # GREEK SMALL LETTER UPSILON WITH TONOS - 0x03ce: 0xf1, # GREEK SMALL LETTER OMEGA WITH TONOS - 0x2013: 0xd0, # EN DASH - 0x2015: 0xd1, # HORIZONTAL BAR - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x2020: 0xa0, # DAGGER + 0x0386: 0xCD, # GREEK CAPITAL LETTER ALPHA WITH TONOS + 0x0388: 0xCE, # GREEK CAPITAL LETTER EPSILON WITH TONOS + 0x0389: 0xD7, # GREEK CAPITAL LETTER ETA WITH TONOS + 0x038A: 0xD8, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x038C: 0xD9, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x038E: 0xDA, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x038F: 0xDF, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x0390: 0xFD, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + 0x0391: 0xB0, # GREEK CAPITAL LETTER ALPHA + 0x0392: 0xB5, # GREEK CAPITAL LETTER BETA + 0x0393: 0xA1, # GREEK CAPITAL LETTER GAMMA + 0x0394: 0xA2, # GREEK CAPITAL LETTER DELTA + 0x0395: 0xB6, # GREEK CAPITAL LETTER EPSILON + 0x0396: 0xB7, # GREEK CAPITAL LETTER ZETA + 0x0397: 0xB8, # GREEK CAPITAL LETTER ETA + 0x0398: 0xA3, # GREEK CAPITAL LETTER THETA + 0x0399: 0xB9, # GREEK CAPITAL LETTER IOTA + 0x039A: 0xBA, # GREEK CAPITAL LETTER KAPPA + 0x039B: 0xA4, # GREEK CAPITAL LETTER LAMDA + 0x039C: 0xBB, # GREEK CAPITAL LETTER MU + 0x039D: 0xC1, # GREEK CAPITAL LETTER NU + 0x039E: 0xA5, # GREEK CAPITAL LETTER XI + 0x039F: 0xC3, # GREEK CAPITAL LETTER OMICRON + 0x03A0: 0xA6, # GREEK CAPITAL LETTER PI + 0x03A1: 0xC4, # GREEK CAPITAL LETTER RHO + 0x03A3: 0xAA, # GREEK CAPITAL LETTER SIGMA + 0x03A4: 0xC6, # GREEK CAPITAL LETTER TAU + 0x03A5: 0xCB, # GREEK CAPITAL LETTER UPSILON + 0x03A6: 0xBC, # GREEK CAPITAL LETTER PHI + 0x03A7: 0xCC, # GREEK CAPITAL LETTER CHI + 0x03A8: 0xBE, # GREEK CAPITAL LETTER PSI + 0x03A9: 0xBF, # GREEK CAPITAL LETTER OMEGA + 0x03AA: 0xAB, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x03AB: 0xBD, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x03AC: 0xC0, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x03AD: 0xDB, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x03AE: 0xDC, # GREEK SMALL LETTER ETA WITH TONOS + 0x03AF: 0xDD, # GREEK SMALL LETTER IOTA WITH TONOS + 0x03B0: 0xFE, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + 0x03B1: 0xE1, # GREEK SMALL LETTER ALPHA + 0x03B2: 0xE2, # GREEK SMALL LETTER BETA + 0x03B3: 0xE7, # GREEK SMALL LETTER GAMMA + 0x03B4: 0xE4, # GREEK SMALL LETTER DELTA + 0x03B5: 0xE5, # GREEK SMALL LETTER EPSILON + 0x03B6: 0xFA, # GREEK SMALL LETTER ZETA + 0x03B7: 0xE8, # GREEK SMALL LETTER ETA + 0x03B8: 0xF5, # GREEK SMALL LETTER THETA + 0x03B9: 0xE9, # GREEK SMALL LETTER IOTA + 0x03BA: 0xEB, # GREEK SMALL LETTER KAPPA + 0x03BB: 0xEC, # GREEK SMALL LETTER LAMDA + 0x03BC: 0xED, # GREEK SMALL LETTER MU + 0x03BD: 0xEE, # GREEK SMALL LETTER NU + 0x03BE: 0xEA, # GREEK SMALL LETTER XI + 0x03BF: 0xEF, # GREEK SMALL LETTER OMICRON + 0x03C0: 0xF0, # GREEK SMALL LETTER PI + 0x03C1: 0xF2, # GREEK SMALL LETTER RHO + 0x03C2: 0xF7, # GREEK SMALL LETTER FINAL SIGMA + 0x03C3: 0xF3, # GREEK SMALL LETTER SIGMA + 0x03C4: 0xF4, # GREEK SMALL LETTER TAU + 0x03C5: 0xF9, # GREEK SMALL LETTER UPSILON + 0x03C6: 0xE6, # GREEK SMALL LETTER PHI + 0x03C7: 0xF8, # GREEK SMALL LETTER CHI + 0x03C8: 0xE3, # GREEK SMALL LETTER PSI + 0x03C9: 0xF6, # GREEK SMALL LETTER OMEGA + 0x03CA: 0xFB, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x03CB: 0xFC, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x03CC: 0xDE, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x03CD: 0xE0, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x03CE: 0xF1, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x2013: 0xD0, # EN DASH + 0x2015: 0xD1, # HORIZONTAL BAR + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x2020: 0xA0, # DAGGER 0x2022: 0x96, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS 0x2030: 0x98, # PER MILLE SIGN - 0x20ac: 0x9c, # EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN + 0x20AC: 0x9C, # EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN 0x2122: 0x93, # TRADE MARK SIGN - 0x2248: 0xc5, # ALMOST EQUAL TO - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO -} \ No newline at end of file + 0x2248: 0xC5, # ALMOST EQUAL TO + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO +} + diff --git a/Lib/encodings/mac_iceland.py b/Lib/encodings/mac_iceland.py index 6a30ba2..5a2aabc 100644 --- a/Lib/encodings/mac_iceland.py +++ b/Lib/encodings/mac_iceland.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA @@ -170,12 +170,12 @@ decoding_table = ( u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe3' # 0x8b -> LATIN SMALL LETTER A WITH TILDE - u'\xe5' # 0x8c -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe7' # 0x8d -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\xe8' # 0x8f -> LATIN SMALL LETTER E WITH GRAVE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE @@ -186,108 +186,108 @@ decoding_table = ( u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf5' # 0x9b -> LATIN SMALL LETTER O WITH TILDE - u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE - u'\xf9' # 0x9d -> LATIN SMALL LETTER U WITH GRAVE - u'\xfb' # 0x9e -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u'\xdd' # 0xa0 -> LATIN CAPITAL LETTER Y WITH ACUTE - u'\xb0' # 0xa1 -> DEGREE SIGN - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa7' # 0xa4 -> SECTION SIGN - u'\u2022' # 0xa5 -> BULLET - u'\xb6' # 0xa6 -> PILCROW SIGN - u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u2122' # 0xaa -> TRADE MARK SIGN - u'\xb4' # 0xab -> ACUTE ACCENT - u'\xa8' # 0xac -> DIAERESIS - u'\u2260' # 0xad -> NOT EQUAL TO - u'\xc6' # 0xae -> LATIN CAPITAL LETTER AE - u'\xd8' # 0xaf -> LATIN CAPITAL LETTER O WITH STROKE - u'\u221e' # 0xb0 -> INFINITY - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\xa5' # 0xb4 -> YEN SIGN - u'\xb5' # 0xb5 -> MICRO SIGN - u'\u2202' # 0xb6 -> PARTIAL DIFFERENTIAL - u'\u2211' # 0xb7 -> N-ARY SUMMATION - u'\u220f' # 0xb8 -> N-ARY PRODUCT - u'\u03c0' # 0xb9 -> GREEK SMALL LETTER PI - u'\u222b' # 0xba -> INTEGRAL - u'\xaa' # 0xbb -> FEMININE ORDINAL INDICATOR - u'\xba' # 0xbc -> MASCULINE ORDINAL INDICATOR - u'\u03a9' # 0xbd -> GREEK CAPITAL LETTER OMEGA - u'\xe6' # 0xbe -> LATIN SMALL LETTER AE - u'\xf8' # 0xbf -> LATIN SMALL LETTER O WITH STROKE - u'\xbf' # 0xc0 -> INVERTED QUESTION MARK - u'\xa1' # 0xc1 -> INVERTED EXCLAMATION MARK - u'\xac' # 0xc2 -> NOT SIGN - u'\u221a' # 0xc3 -> SQUARE ROOT - u'\u0192' # 0xc4 -> LATIN SMALL LETTER F WITH HOOK - u'\u2248' # 0xc5 -> ALMOST EQUAL TO - u'\u2206' # 0xc6 -> INCREMENT - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\xc0' # 0xcb -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc3' # 0xcc -> LATIN CAPITAL LETTER A WITH TILDE - u'\xd5' # 0xcd -> LATIN CAPITAL LETTER O WITH TILDE - u'\u0152' # 0xce -> LATIN CAPITAL LIGATURE OE - u'\u0153' # 0xcf -> LATIN SMALL LIGATURE OE - u'\u2013' # 0xd0 -> EN DASH - u'\u2014' # 0xd1 -> EM DASH - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u25ca' # 0xd7 -> LOZENGE - u'\xff' # 0xd8 -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\u0178' # 0xd9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\u2044' # 0xda -> FRACTION SLASH - u'\u20ac' # 0xdb -> EURO SIGN - u'\xd0' # 0xdc -> LATIN CAPITAL LETTER ETH - u'\xf0' # 0xdd -> LATIN SMALL LETTER ETH - u'\xde' # 0xde -> LATIN CAPITAL LETTER THORN - u'\xfe' # 0xdf -> LATIN SMALL LETTER THORN - u'\xfd' # 0xe0 -> LATIN SMALL LETTER Y WITH ACUTE - u'\xb7' # 0xe1 -> MIDDLE DOT - u'\u201a' # 0xe2 -> SINGLE LOW-9 QUOTATION MARK - u'\u201e' # 0xe3 -> DOUBLE LOW-9 QUOTATION MARK - u'\u2030' # 0xe4 -> PER MILLE SIGN - u'\xc2' # 0xe5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xca' # 0xe6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xc1' # 0xe7 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xcb' # 0xe8 -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xc8' # 0xe9 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xcd' # 0xea -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xeb -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xec -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xcc' # 0xed -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\uf8ff' # 0xf0 -> Apple logo - u'\xd2' # 0xf1 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xda' # 0xf2 -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xf3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xd9' # 0xf4 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\u0131' # 0xf5 -> LATIN SMALL LETTER DOTLESS I - u'\u02c6' # 0xf6 -> MODIFIER LETTER CIRCUMFLEX ACCENT - u'\u02dc' # 0xf7 -> SMALL TILDE - u'\xaf' # 0xf8 -> MACRON - u'\u02d8' # 0xf9 -> BREVE - u'\u02d9' # 0xfa -> DOT ABOVE - u'\u02da' # 0xfb -> RING ABOVE - u'\xb8' # 0xfc -> CEDILLA - u'\u02dd' # 0xfd -> DOUBLE ACUTE ACCENT - u'\u02db' # 0xfe -> OGONEK - u'\u02c7' # 0xff -> CARON + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u'\xdd' # 0xA0 -> LATIN CAPITAL LETTER Y WITH ACUTE + u'\xb0' # 0xA1 -> DEGREE SIGN + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa7' # 0xA4 -> SECTION SIGN + u'\u2022' # 0xA5 -> BULLET + u'\xb6' # 0xA6 -> PILCROW SIGN + u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u2122' # 0xAA -> TRADE MARK SIGN + u'\xb4' # 0xAB -> ACUTE ACCENT + u'\xa8' # 0xAC -> DIAERESIS + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\xc6' # 0xAE -> LATIN CAPITAL LETTER AE + u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + u'\u221e' # 0xB0 -> INFINITY + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\xa5' # 0xB4 -> YEN SIGN + u'\xb5' # 0xB5 -> MICRO SIGN + u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + u'\u2211' # 0xB7 -> N-ARY SUMMATION + u'\u220f' # 0xB8 -> N-ARY PRODUCT + u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + u'\u222b' # 0xBA -> INTEGRAL + u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + u'\xe6' # 0xBE -> LATIN SMALL LETTER AE + u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + u'\xbf' # 0xC0 -> INVERTED QUESTION MARK + u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + u'\xac' # 0xC2 -> NOT SIGN + u'\u221a' # 0xC3 -> SQUARE ROOT + u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + u'\u2248' # 0xC5 -> ALMOST EQUAL TO + u'\u2206' # 0xC6 -> INCREMENT + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + u'\u2013' # 0xD0 -> EN DASH + u'\u2014' # 0xD1 -> EM DASH + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u25ca' # 0xD7 -> LOZENGE + u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\u2044' # 0xDA -> FRACTION SLASH + u'\u20ac' # 0xDB -> EURO SIGN + u'\xd0' # 0xDC -> LATIN CAPITAL LETTER ETH + u'\xf0' # 0xDD -> LATIN SMALL LETTER ETH + u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN + u'\xfe' # 0xDF -> LATIN SMALL LETTER THORN + u'\xfd' # 0xE0 -> LATIN SMALL LETTER Y WITH ACUTE + u'\xb7' # 0xE1 -> MIDDLE DOT + u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + u'\u2030' # 0xE4 -> PER MILLE SIGN + u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\uf8ff' # 0xF0 -> Apple logo + u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + u'\u02dc' # 0xF7 -> SMALL TILDE + u'\xaf' # 0xF8 -> MACRON + u'\u02d8' # 0xF9 -> BREVE + u'\u02d9' # 0xFA -> DOT ABOVE + u'\u02da' # 0xFB -> RING ABOVE + u'\xb8' # 0xFC -> CEDILLA + u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + u'\u02db' # 0xFE -> OGONEK + u'\u02c7' # 0xFF -> CARON ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a1: 0xc1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a5: 0xb4, # YEN SIGN - 0x00a7: 0xa4, # SECTION SIGN - 0x00a8: 0xac, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xbb, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00af: 0xf8, # MACRON - 0x00b0: 0xa1, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b4: 0xab, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xa6, # PILCROW SIGN - 0x00b7: 0xe1, # MIDDLE DOT - 0x00b8: 0xfc, # CEDILLA - 0x00ba: 0xbc, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bf: 0xc0, # INVERTED QUESTION MARK - 0x00c0: 0xcb, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xe7, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xe5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xcc, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xae, # LATIN CAPITAL LETTER AE - 0x00c7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xe9, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xe6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xe8, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xed, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xea, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xeb, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xec, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d0: 0xdc, # LATIN CAPITAL LETTER ETH - 0x00d1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xf1, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xcd, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d8: 0xaf, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xf4, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xf2, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xf3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00dd: 0xa0, # LATIN CAPITAL LETTER Y WITH ACUTE - 0x00de: 0xde, # LATIN CAPITAL LETTER THORN - 0x00df: 0xa7, # LATIN SMALL LETTER SHARP S - 0x00e0: 0x88, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x8b, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x8c, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xbe, # LATIN SMALL LETTER AE - 0x00e7: 0x8d, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x8f, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x93, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f0: 0xdd, # LATIN SMALL LETTER ETH - 0x00f1: 0x96, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0x98, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0x9b, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xd6, # DIVISION SIGN - 0x00f8: 0xbf, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0x9d, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0x9e, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00fd: 0xe0, # LATIN SMALL LETTER Y WITH ACUTE - 0x00fe: 0xdf, # LATIN SMALL LETTER THORN - 0x00ff: 0xd8, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x0131: 0xf5, # LATIN SMALL LETTER DOTLESS I - 0x0152: 0xce, # LATIN CAPITAL LIGATURE OE - 0x0153: 0xcf, # LATIN SMALL LIGATURE OE - 0x0178: 0xd9, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x0192: 0xc4, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0xf6, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02c7: 0xff, # CARON - 0x02d8: 0xf9, # BREVE - 0x02d9: 0xfa, # DOT ABOVE - 0x02da: 0xfb, # RING ABOVE - 0x02db: 0xfe, # OGONEK - 0x02dc: 0xf7, # SMALL TILDE - 0x02dd: 0xfd, # DOUBLE ACUTE ACCENT - 0x03a9: 0xbd, # GREEK CAPITAL LETTER OMEGA - 0x03c0: 0xb9, # GREEK SMALL LETTER PI - 0x2013: 0xd0, # EN DASH - 0x2014: 0xd1, # EM DASH - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0xe2, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xe3, # DOUBLE LOW-9 QUOTATION MARK - 0x2022: 0xa5, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS - 0x2030: 0xe4, # PER MILLE SIGN - 0x2044: 0xda, # FRACTION SLASH - 0x20ac: 0xdb, # EURO SIGN - 0x2122: 0xaa, # TRADE MARK SIGN - 0x2202: 0xb6, # PARTIAL DIFFERENTIAL - 0x2206: 0xc6, # INCREMENT - 0x220f: 0xb8, # N-ARY PRODUCT - 0x2211: 0xb7, # N-ARY SUMMATION - 0x221a: 0xc3, # SQUARE ROOT - 0x221e: 0xb0, # INFINITY - 0x222b: 0xba, # INTEGRAL - 0x2248: 0xc5, # ALMOST EQUAL TO - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO - 0x25ca: 0xd7, # LOZENGE - 0xf8ff: 0xf0, # Apple logo -} \ No newline at end of file + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A5: 0xB4, # YEN SIGN + 0x00A7: 0xA4, # SECTION SIGN + 0x00A8: 0xAC, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00AF: 0xF8, # MACRON + 0x00B0: 0xA1, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B4: 0xAB, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xA6, # PILCROW SIGN + 0x00B7: 0xE1, # MIDDLE DOT + 0x00B8: 0xFC, # CEDILLA + 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BF: 0xC0, # INVERTED QUESTION MARK + 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xAE, # LATIN CAPITAL LETTER AE + 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D0: 0xDC, # LATIN CAPITAL LETTER ETH + 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DD: 0xA0, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00DE: 0xDE, # LATIN CAPITAL LETTER THORN + 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S + 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xBE, # LATIN SMALL LETTER AE + 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F0: 0xDD, # LATIN SMALL LETTER ETH + 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xD6, # DIVISION SIGN + 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FD: 0xE0, # LATIN SMALL LETTER Y WITH ACUTE + 0x00FE: 0xDF, # LATIN SMALL LETTER THORN + 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I + 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE + 0x0153: 0xCF, # LATIN SMALL LIGATURE OE + 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK + 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02C7: 0xFF, # CARON + 0x02D8: 0xF9, # BREVE + 0x02D9: 0xFA, # DOT ABOVE + 0x02DA: 0xFB, # RING ABOVE + 0x02DB: 0xFE, # OGONEK + 0x02DC: 0xF7, # SMALL TILDE + 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT + 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA + 0x03C0: 0xB9, # GREEK SMALL LETTER PI + 0x2013: 0xD0, # EN DASH + 0x2014: 0xD1, # EM DASH + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK + 0x2022: 0xA5, # BULLET + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS + 0x2030: 0xE4, # PER MILLE SIGN + 0x2044: 0xDA, # FRACTION SLASH + 0x20AC: 0xDB, # EURO SIGN + 0x2122: 0xAA, # TRADE MARK SIGN + 0x2202: 0xB6, # PARTIAL DIFFERENTIAL + 0x2206: 0xC6, # INCREMENT + 0x220F: 0xB8, # N-ARY PRODUCT + 0x2211: 0xB7, # N-ARY SUMMATION + 0x221A: 0xC3, # SQUARE ROOT + 0x221E: 0xB0, # INFINITY + 0x222B: 0xBA, # INTEGRAL + 0x2248: 0xC5, # ALMOST EQUAL TO + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO + 0x25CA: 0xD7, # LOZENGE + 0xF8FF: 0xF0, # Apple logo +} + diff --git a/Lib/encodings/mac_roman.py b/Lib/encodings/mac_roman.py index 77c2dec..a4f476f 100644 --- a/Lib/encodings/mac_roman.py +++ b/Lib/encodings/mac_roman.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA @@ -170,12 +170,12 @@ decoding_table = ( u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe3' # 0x8b -> LATIN SMALL LETTER A WITH TILDE - u'\xe5' # 0x8c -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe7' # 0x8d -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\xe8' # 0x8f -> LATIN SMALL LETTER E WITH GRAVE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE @@ -186,108 +186,108 @@ decoding_table = ( u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf5' # 0x9b -> LATIN SMALL LETTER O WITH TILDE - u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE - u'\xf9' # 0x9d -> LATIN SMALL LETTER U WITH GRAVE - u'\xfb' # 0x9e -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u2020' # 0xa0 -> DAGGER - u'\xb0' # 0xa1 -> DEGREE SIGN - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa7' # 0xa4 -> SECTION SIGN - u'\u2022' # 0xa5 -> BULLET - u'\xb6' # 0xa6 -> PILCROW SIGN - u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u2122' # 0xaa -> TRADE MARK SIGN - u'\xb4' # 0xab -> ACUTE ACCENT - u'\xa8' # 0xac -> DIAERESIS - u'\u2260' # 0xad -> NOT EQUAL TO - u'\xc6' # 0xae -> LATIN CAPITAL LETTER AE - u'\xd8' # 0xaf -> LATIN CAPITAL LETTER O WITH STROKE - u'\u221e' # 0xb0 -> INFINITY - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\xa5' # 0xb4 -> YEN SIGN - u'\xb5' # 0xb5 -> MICRO SIGN - u'\u2202' # 0xb6 -> PARTIAL DIFFERENTIAL - u'\u2211' # 0xb7 -> N-ARY SUMMATION - u'\u220f' # 0xb8 -> N-ARY PRODUCT - u'\u03c0' # 0xb9 -> GREEK SMALL LETTER PI - u'\u222b' # 0xba -> INTEGRAL - u'\xaa' # 0xbb -> FEMININE ORDINAL INDICATOR - u'\xba' # 0xbc -> MASCULINE ORDINAL INDICATOR - u'\u03a9' # 0xbd -> GREEK CAPITAL LETTER OMEGA - u'\xe6' # 0xbe -> LATIN SMALL LETTER AE - u'\xf8' # 0xbf -> LATIN SMALL LETTER O WITH STROKE - u'\xbf' # 0xc0 -> INVERTED QUESTION MARK - u'\xa1' # 0xc1 -> INVERTED EXCLAMATION MARK - u'\xac' # 0xc2 -> NOT SIGN - u'\u221a' # 0xc3 -> SQUARE ROOT - u'\u0192' # 0xc4 -> LATIN SMALL LETTER F WITH HOOK - u'\u2248' # 0xc5 -> ALMOST EQUAL TO - u'\u2206' # 0xc6 -> INCREMENT - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\xc0' # 0xcb -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc3' # 0xcc -> LATIN CAPITAL LETTER A WITH TILDE - u'\xd5' # 0xcd -> LATIN CAPITAL LETTER O WITH TILDE - u'\u0152' # 0xce -> LATIN CAPITAL LIGATURE OE - u'\u0153' # 0xcf -> LATIN SMALL LIGATURE OE - u'\u2013' # 0xd0 -> EN DASH - u'\u2014' # 0xd1 -> EM DASH - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u25ca' # 0xd7 -> LOZENGE - u'\xff' # 0xd8 -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\u0178' # 0xd9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\u2044' # 0xda -> FRACTION SLASH - u'\u20ac' # 0xdb -> EURO SIGN - u'\u2039' # 0xdc -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u203a' # 0xdd -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\ufb01' # 0xde -> LATIN SMALL LIGATURE FI - u'\ufb02' # 0xdf -> LATIN SMALL LIGATURE FL - u'\u2021' # 0xe0 -> DOUBLE DAGGER - u'\xb7' # 0xe1 -> MIDDLE DOT - u'\u201a' # 0xe2 -> SINGLE LOW-9 QUOTATION MARK - u'\u201e' # 0xe3 -> DOUBLE LOW-9 QUOTATION MARK - u'\u2030' # 0xe4 -> PER MILLE SIGN - u'\xc2' # 0xe5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xca' # 0xe6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xc1' # 0xe7 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xcb' # 0xe8 -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xc8' # 0xe9 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xcd' # 0xea -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xeb -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xec -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xcc' # 0xed -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\uf8ff' # 0xf0 -> Apple logo - u'\xd2' # 0xf1 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xda' # 0xf2 -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xf3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xd9' # 0xf4 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\u0131' # 0xf5 -> LATIN SMALL LETTER DOTLESS I - u'\u02c6' # 0xf6 -> MODIFIER LETTER CIRCUMFLEX ACCENT - u'\u02dc' # 0xf7 -> SMALL TILDE - u'\xaf' # 0xf8 -> MACRON - u'\u02d8' # 0xf9 -> BREVE - u'\u02d9' # 0xfa -> DOT ABOVE - u'\u02da' # 0xfb -> RING ABOVE - u'\xb8' # 0xfc -> CEDILLA - u'\u02dd' # 0xfd -> DOUBLE ACUTE ACCENT - u'\u02db' # 0xfe -> OGONEK - u'\u02c7' # 0xff -> CARON + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u2020' # 0xA0 -> DAGGER + u'\xb0' # 0xA1 -> DEGREE SIGN + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa7' # 0xA4 -> SECTION SIGN + u'\u2022' # 0xA5 -> BULLET + u'\xb6' # 0xA6 -> PILCROW SIGN + u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u2122' # 0xAA -> TRADE MARK SIGN + u'\xb4' # 0xAB -> ACUTE ACCENT + u'\xa8' # 0xAC -> DIAERESIS + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\xc6' # 0xAE -> LATIN CAPITAL LETTER AE + u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + u'\u221e' # 0xB0 -> INFINITY + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\xa5' # 0xB4 -> YEN SIGN + u'\xb5' # 0xB5 -> MICRO SIGN + u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + u'\u2211' # 0xB7 -> N-ARY SUMMATION + u'\u220f' # 0xB8 -> N-ARY PRODUCT + u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + u'\u222b' # 0xBA -> INTEGRAL + u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + u'\xe6' # 0xBE -> LATIN SMALL LETTER AE + u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + u'\xbf' # 0xC0 -> INVERTED QUESTION MARK + u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + u'\xac' # 0xC2 -> NOT SIGN + u'\u221a' # 0xC3 -> SQUARE ROOT + u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + u'\u2248' # 0xC5 -> ALMOST EQUAL TO + u'\u2206' # 0xC6 -> INCREMENT + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + u'\u2013' # 0xD0 -> EN DASH + u'\u2014' # 0xD1 -> EM DASH + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u25ca' # 0xD7 -> LOZENGE + u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\u2044' # 0xDA -> FRACTION SLASH + u'\u20ac' # 0xDB -> EURO SIGN + u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\ufb01' # 0xDE -> LATIN SMALL LIGATURE FI + u'\ufb02' # 0xDF -> LATIN SMALL LIGATURE FL + u'\u2021' # 0xE0 -> DOUBLE DAGGER + u'\xb7' # 0xE1 -> MIDDLE DOT + u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + u'\u2030' # 0xE4 -> PER MILLE SIGN + u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\uf8ff' # 0xF0 -> Apple logo + u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + u'\u02dc' # 0xF7 -> SMALL TILDE + u'\xaf' # 0xF8 -> MACRON + u'\u02d8' # 0xF9 -> BREVE + u'\u02d9' # 0xFA -> DOT ABOVE + u'\u02da' # 0xFB -> RING ABOVE + u'\xb8' # 0xFC -> CEDILLA + u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + u'\u02db' # 0xFE -> OGONEK + u'\u02c7' # 0xFF -> CARON ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a1: 0xc1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a5: 0xb4, # YEN SIGN - 0x00a7: 0xa4, # SECTION SIGN - 0x00a8: 0xac, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xbb, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00af: 0xf8, # MACRON - 0x00b0: 0xa1, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b4: 0xab, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xa6, # PILCROW SIGN - 0x00b7: 0xe1, # MIDDLE DOT - 0x00b8: 0xfc, # CEDILLA - 0x00ba: 0xbc, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bf: 0xc0, # INVERTED QUESTION MARK - 0x00c0: 0xcb, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xe7, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xe5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xcc, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xae, # LATIN CAPITAL LETTER AE - 0x00c7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xe9, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xe6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xe8, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xed, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xea, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xeb, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xec, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xf1, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xcd, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d8: 0xaf, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xf4, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xf2, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xf3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xa7, # LATIN SMALL LETTER SHARP S - 0x00e0: 0x88, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x8b, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x8c, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xbe, # LATIN SMALL LETTER AE - 0x00e7: 0x8d, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x8f, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x93, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0x96, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0x98, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0x9b, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xd6, # DIVISION SIGN - 0x00f8: 0xbf, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0x9d, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0x9e, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xd8, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x0131: 0xf5, # LATIN SMALL LETTER DOTLESS I - 0x0152: 0xce, # LATIN CAPITAL LIGATURE OE - 0x0153: 0xcf, # LATIN SMALL LIGATURE OE - 0x0178: 0xd9, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x0192: 0xc4, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0xf6, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02c7: 0xff, # CARON - 0x02d8: 0xf9, # BREVE - 0x02d9: 0xfa, # DOT ABOVE - 0x02da: 0xfb, # RING ABOVE - 0x02db: 0xfe, # OGONEK - 0x02dc: 0xf7, # SMALL TILDE - 0x02dd: 0xfd, # DOUBLE ACUTE ACCENT - 0x03a9: 0xbd, # GREEK CAPITAL LETTER OMEGA - 0x03c0: 0xb9, # GREEK SMALL LETTER PI - 0x2013: 0xd0, # EN DASH - 0x2014: 0xd1, # EM DASH - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0xe2, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xe3, # DOUBLE LOW-9 QUOTATION MARK - 0x2020: 0xa0, # DAGGER - 0x2021: 0xe0, # DOUBLE DAGGER - 0x2022: 0xa5, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS - 0x2030: 0xe4, # PER MILLE SIGN - 0x2039: 0xdc, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0xdd, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x2044: 0xda, # FRACTION SLASH - 0x20ac: 0xdb, # EURO SIGN - 0x2122: 0xaa, # TRADE MARK SIGN - 0x2202: 0xb6, # PARTIAL DIFFERENTIAL - 0x2206: 0xc6, # INCREMENT - 0x220f: 0xb8, # N-ARY PRODUCT - 0x2211: 0xb7, # N-ARY SUMMATION - 0x221a: 0xc3, # SQUARE ROOT - 0x221e: 0xb0, # INFINITY - 0x222b: 0xba, # INTEGRAL - 0x2248: 0xc5, # ALMOST EQUAL TO - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO - 0x25ca: 0xd7, # LOZENGE - 0xf8ff: 0xf0, # Apple logo - 0xfb01: 0xde, # LATIN SMALL LIGATURE FI - 0xfb02: 0xdf, # LATIN SMALL LIGATURE FL -} \ No newline at end of file + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A5: 0xB4, # YEN SIGN + 0x00A7: 0xA4, # SECTION SIGN + 0x00A8: 0xAC, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00AF: 0xF8, # MACRON + 0x00B0: 0xA1, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B4: 0xAB, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xA6, # PILCROW SIGN + 0x00B7: 0xE1, # MIDDLE DOT + 0x00B8: 0xFC, # CEDILLA + 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BF: 0xC0, # INVERTED QUESTION MARK + 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xAE, # LATIN CAPITAL LETTER AE + 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S + 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xBE, # LATIN SMALL LETTER AE + 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xD6, # DIVISION SIGN + 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I + 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE + 0x0153: 0xCF, # LATIN SMALL LIGATURE OE + 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK + 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02C7: 0xFF, # CARON + 0x02D8: 0xF9, # BREVE + 0x02D9: 0xFA, # DOT ABOVE + 0x02DA: 0xFB, # RING ABOVE + 0x02DB: 0xFE, # OGONEK + 0x02DC: 0xF7, # SMALL TILDE + 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT + 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA + 0x03C0: 0xB9, # GREEK SMALL LETTER PI + 0x2013: 0xD0, # EN DASH + 0x2014: 0xD1, # EM DASH + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK + 0x2020: 0xA0, # DAGGER + 0x2021: 0xE0, # DOUBLE DAGGER + 0x2022: 0xA5, # BULLET + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS + 0x2030: 0xE4, # PER MILLE SIGN + 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x2044: 0xDA, # FRACTION SLASH + 0x20AC: 0xDB, # EURO SIGN + 0x2122: 0xAA, # TRADE MARK SIGN + 0x2202: 0xB6, # PARTIAL DIFFERENTIAL + 0x2206: 0xC6, # INCREMENT + 0x220F: 0xB8, # N-ARY PRODUCT + 0x2211: 0xB7, # N-ARY SUMMATION + 0x221A: 0xC3, # SQUARE ROOT + 0x221E: 0xB0, # INFINITY + 0x222B: 0xBA, # INTEGRAL + 0x2248: 0xC5, # ALMOST EQUAL TO + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO + 0x25CA: 0xD7, # LOZENGE + 0xF8FF: 0xF0, # Apple logo + 0xFB01: 0xDE, # LATIN SMALL LIGATURE FI + 0xFB02: 0xDF, # LATIN SMALL LIGATURE FL +} + diff --git a/Lib/encodings/mac_romanian.py b/Lib/encodings/mac_romanian.py index aa1d713..ba6c173 100644 --- a/Lib/encodings/mac_romanian.py +++ b/Lib/encodings/mac_romanian.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA @@ -170,12 +170,12 @@ decoding_table = ( u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe3' # 0x8b -> LATIN SMALL LETTER A WITH TILDE - u'\xe5' # 0x8c -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe7' # 0x8d -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\xe8' # 0x8f -> LATIN SMALL LETTER E WITH GRAVE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE @@ -186,108 +186,108 @@ decoding_table = ( u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf5' # 0x9b -> LATIN SMALL LETTER O WITH TILDE - u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE - u'\xf9' # 0x9d -> LATIN SMALL LETTER U WITH GRAVE - u'\xfb' # 0x9e -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u2020' # 0xa0 -> DAGGER - u'\xb0' # 0xa1 -> DEGREE SIGN - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa7' # 0xa4 -> SECTION SIGN - u'\u2022' # 0xa5 -> BULLET - u'\xb6' # 0xa6 -> PILCROW SIGN - u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u2122' # 0xaa -> TRADE MARK SIGN - u'\xb4' # 0xab -> ACUTE ACCENT - u'\xa8' # 0xac -> DIAERESIS - u'\u2260' # 0xad -> NOT EQUAL TO - u'\u0102' # 0xae -> LATIN CAPITAL LETTER A WITH BREVE - u'\u0218' # 0xaf -> LATIN CAPITAL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later - u'\u221e' # 0xb0 -> INFINITY - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\xa5' # 0xb4 -> YEN SIGN - u'\xb5' # 0xb5 -> MICRO SIGN - u'\u2202' # 0xb6 -> PARTIAL DIFFERENTIAL - u'\u2211' # 0xb7 -> N-ARY SUMMATION - u'\u220f' # 0xb8 -> N-ARY PRODUCT - u'\u03c0' # 0xb9 -> GREEK SMALL LETTER PI - u'\u222b' # 0xba -> INTEGRAL - u'\xaa' # 0xbb -> FEMININE ORDINAL INDICATOR - u'\xba' # 0xbc -> MASCULINE ORDINAL INDICATOR - u'\u03a9' # 0xbd -> GREEK CAPITAL LETTER OMEGA - u'\u0103' # 0xbe -> LATIN SMALL LETTER A WITH BREVE - u'\u0219' # 0xbf -> LATIN SMALL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later - u'\xbf' # 0xc0 -> INVERTED QUESTION MARK - u'\xa1' # 0xc1 -> INVERTED EXCLAMATION MARK - u'\xac' # 0xc2 -> NOT SIGN - u'\u221a' # 0xc3 -> SQUARE ROOT - u'\u0192' # 0xc4 -> LATIN SMALL LETTER F WITH HOOK - u'\u2248' # 0xc5 -> ALMOST EQUAL TO - u'\u2206' # 0xc6 -> INCREMENT - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\xc0' # 0xcb -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc3' # 0xcc -> LATIN CAPITAL LETTER A WITH TILDE - u'\xd5' # 0xcd -> LATIN CAPITAL LETTER O WITH TILDE - u'\u0152' # 0xce -> LATIN CAPITAL LIGATURE OE - u'\u0153' # 0xcf -> LATIN SMALL LIGATURE OE - u'\u2013' # 0xd0 -> EN DASH - u'\u2014' # 0xd1 -> EM DASH - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u25ca' # 0xd7 -> LOZENGE - u'\xff' # 0xd8 -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\u0178' # 0xd9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\u2044' # 0xda -> FRACTION SLASH - u'\u20ac' # 0xdb -> EURO SIGN - u'\u2039' # 0xdc -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK - u'\u203a' # 0xdd -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - u'\u021a' # 0xde -> LATIN CAPITAL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later - u'\u021b' # 0xdf -> LATIN SMALL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later - u'\u2021' # 0xe0 -> DOUBLE DAGGER - u'\xb7' # 0xe1 -> MIDDLE DOT - u'\u201a' # 0xe2 -> SINGLE LOW-9 QUOTATION MARK - u'\u201e' # 0xe3 -> DOUBLE LOW-9 QUOTATION MARK - u'\u2030' # 0xe4 -> PER MILLE SIGN - u'\xc2' # 0xe5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xca' # 0xe6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xc1' # 0xe7 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xcb' # 0xe8 -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xc8' # 0xe9 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xcd' # 0xea -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xeb -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xec -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xcc' # 0xed -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\uf8ff' # 0xf0 -> Apple logo - u'\xd2' # 0xf1 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xda' # 0xf2 -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xf3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xd9' # 0xf4 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\u0131' # 0xf5 -> LATIN SMALL LETTER DOTLESS I - u'\u02c6' # 0xf6 -> MODIFIER LETTER CIRCUMFLEX ACCENT - u'\u02dc' # 0xf7 -> SMALL TILDE - u'\xaf' # 0xf8 -> MACRON - u'\u02d8' # 0xf9 -> BREVE - u'\u02d9' # 0xfa -> DOT ABOVE - u'\u02da' # 0xfb -> RING ABOVE - u'\xb8' # 0xfc -> CEDILLA - u'\u02dd' # 0xfd -> DOUBLE ACUTE ACCENT - u'\u02db' # 0xfe -> OGONEK - u'\u02c7' # 0xff -> CARON + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u2020' # 0xA0 -> DAGGER + u'\xb0' # 0xA1 -> DEGREE SIGN + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa7' # 0xA4 -> SECTION SIGN + u'\u2022' # 0xA5 -> BULLET + u'\xb6' # 0xA6 -> PILCROW SIGN + u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u2122' # 0xAA -> TRADE MARK SIGN + u'\xb4' # 0xAB -> ACUTE ACCENT + u'\xa8' # 0xAC -> DIAERESIS + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\u0102' # 0xAE -> LATIN CAPITAL LETTER A WITH BREVE + u'\u0218' # 0xAF -> LATIN CAPITAL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later + u'\u221e' # 0xB0 -> INFINITY + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\xa5' # 0xB4 -> YEN SIGN + u'\xb5' # 0xB5 -> MICRO SIGN + u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + u'\u2211' # 0xB7 -> N-ARY SUMMATION + u'\u220f' # 0xB8 -> N-ARY PRODUCT + u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + u'\u222b' # 0xBA -> INTEGRAL + u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + u'\u0103' # 0xBE -> LATIN SMALL LETTER A WITH BREVE + u'\u0219' # 0xBF -> LATIN SMALL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later + u'\xbf' # 0xC0 -> INVERTED QUESTION MARK + u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + u'\xac' # 0xC2 -> NOT SIGN + u'\u221a' # 0xC3 -> SQUARE ROOT + u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + u'\u2248' # 0xC5 -> ALMOST EQUAL TO + u'\u2206' # 0xC6 -> INCREMENT + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + u'\u2013' # 0xD0 -> EN DASH + u'\u2014' # 0xD1 -> EM DASH + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u25ca' # 0xD7 -> LOZENGE + u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\u2044' # 0xDA -> FRACTION SLASH + u'\u20ac' # 0xDB -> EURO SIGN + u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + u'\u021a' # 0xDE -> LATIN CAPITAL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later + u'\u021b' # 0xDF -> LATIN SMALL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later + u'\u2021' # 0xE0 -> DOUBLE DAGGER + u'\xb7' # 0xE1 -> MIDDLE DOT + u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + u'\u2030' # 0xE4 -> PER MILLE SIGN + u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\uf8ff' # 0xF0 -> Apple logo + u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + u'\u02dc' # 0xF7 -> SMALL TILDE + u'\xaf' # 0xF8 -> MACRON + u'\u02d8' # 0xF9 -> BREVE + u'\u02d9' # 0xFA -> DOT ABOVE + u'\u02da' # 0xFB -> RING ABOVE + u'\xb8' # 0xFC -> CEDILLA + u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + u'\u02db' # 0xFE -> OGONEK + u'\u02c7' # 0xFF -> CARON ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a1: 0xc1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a5: 0xb4, # YEN SIGN - 0x00a7: 0xa4, # SECTION SIGN - 0x00a8: 0xac, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xbb, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00af: 0xf8, # MACRON - 0x00b0: 0xa1, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b4: 0xab, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xa6, # PILCROW SIGN - 0x00b7: 0xe1, # MIDDLE DOT - 0x00b8: 0xfc, # CEDILLA - 0x00ba: 0xbc, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bf: 0xc0, # INVERTED QUESTION MARK - 0x00c0: 0xcb, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xe7, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xe5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xcc, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xe9, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xe6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xe8, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xed, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xea, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xeb, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xec, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xf1, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xcd, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d9: 0xf4, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xf2, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xf3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xa7, # LATIN SMALL LETTER SHARP S - 0x00e0: 0x88, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x8b, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x8c, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e7: 0x8d, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x8f, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x93, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0x96, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0x98, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0x9b, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xd6, # DIVISION SIGN - 0x00f9: 0x9d, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0x9e, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xd8, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x0102: 0xae, # LATIN CAPITAL LETTER A WITH BREVE - 0x0103: 0xbe, # LATIN SMALL LETTER A WITH BREVE - 0x0131: 0xf5, # LATIN SMALL LETTER DOTLESS I - 0x0152: 0xce, # LATIN CAPITAL LIGATURE OE - 0x0153: 0xcf, # LATIN SMALL LIGATURE OE - 0x0178: 0xd9, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x0192: 0xc4, # LATIN SMALL LETTER F WITH HOOK - 0x0218: 0xaf, # LATIN CAPITAL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later - 0x0219: 0xbf, # LATIN SMALL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later - 0x021a: 0xde, # LATIN CAPITAL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later - 0x021b: 0xdf, # LATIN SMALL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later - 0x02c6: 0xf6, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02c7: 0xff, # CARON - 0x02d8: 0xf9, # BREVE - 0x02d9: 0xfa, # DOT ABOVE - 0x02da: 0xfb, # RING ABOVE - 0x02db: 0xfe, # OGONEK - 0x02dc: 0xf7, # SMALL TILDE - 0x02dd: 0xfd, # DOUBLE ACUTE ACCENT - 0x03a9: 0xbd, # GREEK CAPITAL LETTER OMEGA - 0x03c0: 0xb9, # GREEK SMALL LETTER PI - 0x2013: 0xd0, # EN DASH - 0x2014: 0xd1, # EM DASH - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0xe2, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xe3, # DOUBLE LOW-9 QUOTATION MARK - 0x2020: 0xa0, # DAGGER - 0x2021: 0xe0, # DOUBLE DAGGER - 0x2022: 0xa5, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS - 0x2030: 0xe4, # PER MILLE SIGN - 0x2039: 0xdc, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK - 0x203a: 0xdd, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK - 0x2044: 0xda, # FRACTION SLASH - 0x20ac: 0xdb, # EURO SIGN - 0x2122: 0xaa, # TRADE MARK SIGN - 0x2202: 0xb6, # PARTIAL DIFFERENTIAL - 0x2206: 0xc6, # INCREMENT - 0x220f: 0xb8, # N-ARY PRODUCT - 0x2211: 0xb7, # N-ARY SUMMATION - 0x221a: 0xc3, # SQUARE ROOT - 0x221e: 0xb0, # INFINITY - 0x222b: 0xba, # INTEGRAL - 0x2248: 0xc5, # ALMOST EQUAL TO - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO - 0x25ca: 0xd7, # LOZENGE - 0xf8ff: 0xf0, # Apple logo -} \ No newline at end of file + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A5: 0xB4, # YEN SIGN + 0x00A7: 0xA4, # SECTION SIGN + 0x00A8: 0xAC, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00AF: 0xF8, # MACRON + 0x00B0: 0xA1, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B4: 0xAB, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xA6, # PILCROW SIGN + 0x00B7: 0xE1, # MIDDLE DOT + 0x00B8: 0xFC, # CEDILLA + 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BF: 0xC0, # INVERTED QUESTION MARK + 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S + 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xD6, # DIVISION SIGN + 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0102: 0xAE, # LATIN CAPITAL LETTER A WITH BREVE + 0x0103: 0xBE, # LATIN SMALL LETTER A WITH BREVE + 0x0131: 0xF5, # LATIN SMALL LETTER DOTLESS I + 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE + 0x0153: 0xCF, # LATIN SMALL LIGATURE OE + 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK + 0x0218: 0xAF, # LATIN CAPITAL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later + 0x0219: 0xBF, # LATIN SMALL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later + 0x021A: 0xDE, # LATIN CAPITAL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later + 0x021B: 0xDF, # LATIN SMALL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later + 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02C7: 0xFF, # CARON + 0x02D8: 0xF9, # BREVE + 0x02D9: 0xFA, # DOT ABOVE + 0x02DA: 0xFB, # RING ABOVE + 0x02DB: 0xFE, # OGONEK + 0x02DC: 0xF7, # SMALL TILDE + 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT + 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA + 0x03C0: 0xB9, # GREEK SMALL LETTER PI + 0x2013: 0xD0, # EN DASH + 0x2014: 0xD1, # EM DASH + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK + 0x2020: 0xA0, # DAGGER + 0x2021: 0xE0, # DOUBLE DAGGER + 0x2022: 0xA5, # BULLET + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS + 0x2030: 0xE4, # PER MILLE SIGN + 0x2039: 0xDC, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 0x203A: 0xDD, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 0x2044: 0xDA, # FRACTION SLASH + 0x20AC: 0xDB, # EURO SIGN + 0x2122: 0xAA, # TRADE MARK SIGN + 0x2202: 0xB6, # PARTIAL DIFFERENTIAL + 0x2206: 0xC6, # INCREMENT + 0x220F: 0xB8, # N-ARY PRODUCT + 0x2211: 0xB7, # N-ARY SUMMATION + 0x221A: 0xC3, # SQUARE ROOT + 0x221E: 0xB0, # INFINITY + 0x222B: 0xBA, # INTEGRAL + 0x2248: 0xC5, # ALMOST EQUAL TO + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO + 0x25CA: 0xD7, # LOZENGE + 0xF8FF: 0xF0, # Apple logo +} + diff --git a/Lib/encodings/mac_turkish.py b/Lib/encodings/mac_turkish.py index e3899b6..8a3efb7 100644 --- a/Lib/encodings/mac_turkish.py +++ b/Lib/encodings/mac_turkish.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER - u'\n' # 0x0a -> CONTROL CHARACTER - u'\x0b' # 0x0b -> CONTROL CHARACTER - u'\x0c' # 0x0c -> CONTROL CHARACTER - u'\r' # 0x0d -> CONTROL CHARACTER - u'\x0e' # 0x0e -> CONTROL CHARACTER - u'\x0f' # 0x0f -> CONTROL CHARACTER + u'\n' # 0x0A -> CONTROL CHARACTER + u'\x0b' # 0x0B -> CONTROL CHARACTER + u'\x0c' # 0x0C -> CONTROL CHARACTER + u'\r' # 0x0D -> CONTROL CHARACTER + u'\x0e' # 0x0E -> CONTROL CHARACTER + u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER - u'\x1a' # 0x1a -> CONTROL CHARACTER - u'\x1b' # 0x1b -> CONTROL CHARACTER - u'\x1c' # 0x1c -> CONTROL CHARACTER - u'\x1d' # 0x1d -> CONTROL CHARACTER - u'\x1e' # 0x1e -> CONTROL CHARACTER - u'\x1f' # 0x1f -> CONTROL CHARACTER + u'\x1a' # 0x1A -> CONTROL CHARACTER + u'\x1b' # 0x1B -> CONTROL CHARACTER + u'\x1c' # 0x1C -> CONTROL CHARACTER + u'\x1d' # 0x1D -> CONTROL CHARACTER + u'\x1e' # 0x1E -> CONTROL CHARACTER + u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> CONTROL CHARACTER + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA @@ -170,12 +170,12 @@ decoding_table = ( u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX - u'\xe4' # 0x8a -> LATIN SMALL LETTER A WITH DIAERESIS - u'\xe3' # 0x8b -> LATIN SMALL LETTER A WITH TILDE - u'\xe5' # 0x8c -> LATIN SMALL LETTER A WITH RING ABOVE - u'\xe7' # 0x8d -> LATIN SMALL LETTER C WITH CEDILLA - u'\xe9' # 0x8e -> LATIN SMALL LETTER E WITH ACUTE - u'\xe8' # 0x8f -> LATIN SMALL LETTER E WITH GRAVE + u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE @@ -186,108 +186,108 @@ decoding_table = ( u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX - u'\xf6' # 0x9a -> LATIN SMALL LETTER O WITH DIAERESIS - u'\xf5' # 0x9b -> LATIN SMALL LETTER O WITH TILDE - u'\xfa' # 0x9c -> LATIN SMALL LETTER U WITH ACUTE - u'\xf9' # 0x9d -> LATIN SMALL LETTER U WITH GRAVE - u'\xfb' # 0x9e -> LATIN SMALL LETTER U WITH CIRCUMFLEX - u'\xfc' # 0x9f -> LATIN SMALL LETTER U WITH DIAERESIS - u'\u2020' # 0xa0 -> DAGGER - u'\xb0' # 0xa1 -> DEGREE SIGN - u'\xa2' # 0xa2 -> CENT SIGN - u'\xa3' # 0xa3 -> POUND SIGN - u'\xa7' # 0xa4 -> SECTION SIGN - u'\u2022' # 0xa5 -> BULLET - u'\xb6' # 0xa6 -> PILCROW SIGN - u'\xdf' # 0xa7 -> LATIN SMALL LETTER SHARP S - u'\xae' # 0xa8 -> REGISTERED SIGN - u'\xa9' # 0xa9 -> COPYRIGHT SIGN - u'\u2122' # 0xaa -> TRADE MARK SIGN - u'\xb4' # 0xab -> ACUTE ACCENT - u'\xa8' # 0xac -> DIAERESIS - u'\u2260' # 0xad -> NOT EQUAL TO - u'\xc6' # 0xae -> LATIN CAPITAL LETTER AE - u'\xd8' # 0xaf -> LATIN CAPITAL LETTER O WITH STROKE - u'\u221e' # 0xb0 -> INFINITY - u'\xb1' # 0xb1 -> PLUS-MINUS SIGN - u'\u2264' # 0xb2 -> LESS-THAN OR EQUAL TO - u'\u2265' # 0xb3 -> GREATER-THAN OR EQUAL TO - u'\xa5' # 0xb4 -> YEN SIGN - u'\xb5' # 0xb5 -> MICRO SIGN - u'\u2202' # 0xb6 -> PARTIAL DIFFERENTIAL - u'\u2211' # 0xb7 -> N-ARY SUMMATION - u'\u220f' # 0xb8 -> N-ARY PRODUCT - u'\u03c0' # 0xb9 -> GREEK SMALL LETTER PI - u'\u222b' # 0xba -> INTEGRAL - u'\xaa' # 0xbb -> FEMININE ORDINAL INDICATOR - u'\xba' # 0xbc -> MASCULINE ORDINAL INDICATOR - u'\u03a9' # 0xbd -> GREEK CAPITAL LETTER OMEGA - u'\xe6' # 0xbe -> LATIN SMALL LETTER AE - u'\xf8' # 0xbf -> LATIN SMALL LETTER O WITH STROKE - u'\xbf' # 0xc0 -> INVERTED QUESTION MARK - u'\xa1' # 0xc1 -> INVERTED EXCLAMATION MARK - u'\xac' # 0xc2 -> NOT SIGN - u'\u221a' # 0xc3 -> SQUARE ROOT - u'\u0192' # 0xc4 -> LATIN SMALL LETTER F WITH HOOK - u'\u2248' # 0xc5 -> ALMOST EQUAL TO - u'\u2206' # 0xc6 -> INCREMENT - u'\xab' # 0xc7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\xbb' # 0xc8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - u'\u2026' # 0xc9 -> HORIZONTAL ELLIPSIS - u'\xa0' # 0xca -> NO-BREAK SPACE - u'\xc0' # 0xcb -> LATIN CAPITAL LETTER A WITH GRAVE - u'\xc3' # 0xcc -> LATIN CAPITAL LETTER A WITH TILDE - u'\xd5' # 0xcd -> LATIN CAPITAL LETTER O WITH TILDE - u'\u0152' # 0xce -> LATIN CAPITAL LIGATURE OE - u'\u0153' # 0xcf -> LATIN SMALL LIGATURE OE - u'\u2013' # 0xd0 -> EN DASH - u'\u2014' # 0xd1 -> EM DASH - u'\u201c' # 0xd2 -> LEFT DOUBLE QUOTATION MARK - u'\u201d' # 0xd3 -> RIGHT DOUBLE QUOTATION MARK - u'\u2018' # 0xd4 -> LEFT SINGLE QUOTATION MARK - u'\u2019' # 0xd5 -> RIGHT SINGLE QUOTATION MARK - u'\xf7' # 0xd6 -> DIVISION SIGN - u'\u25ca' # 0xd7 -> LOZENGE - u'\xff' # 0xd8 -> LATIN SMALL LETTER Y WITH DIAERESIS - u'\u0178' # 0xd9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS - u'\u011e' # 0xda -> LATIN CAPITAL LETTER G WITH BREVE - u'\u011f' # 0xdb -> LATIN SMALL LETTER G WITH BREVE - u'\u0130' # 0xdc -> LATIN CAPITAL LETTER I WITH DOT ABOVE - u'\u0131' # 0xdd -> LATIN SMALL LETTER DOTLESS I - u'\u015e' # 0xde -> LATIN CAPITAL LETTER S WITH CEDILLA - u'\u015f' # 0xdf -> LATIN SMALL LETTER S WITH CEDILLA - u'\u2021' # 0xe0 -> DOUBLE DAGGER - u'\xb7' # 0xe1 -> MIDDLE DOT - u'\u201a' # 0xe2 -> SINGLE LOW-9 QUOTATION MARK - u'\u201e' # 0xe3 -> DOUBLE LOW-9 QUOTATION MARK - u'\u2030' # 0xe4 -> PER MILLE SIGN - u'\xc2' # 0xe5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - u'\xca' # 0xe6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - u'\xc1' # 0xe7 -> LATIN CAPITAL LETTER A WITH ACUTE - u'\xcb' # 0xe8 -> LATIN CAPITAL LETTER E WITH DIAERESIS - u'\xc8' # 0xe9 -> LATIN CAPITAL LETTER E WITH GRAVE - u'\xcd' # 0xea -> LATIN CAPITAL LETTER I WITH ACUTE - u'\xce' # 0xeb -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - u'\xcf' # 0xec -> LATIN CAPITAL LETTER I WITH DIAERESIS - u'\xcc' # 0xed -> LATIN CAPITAL LETTER I WITH GRAVE - u'\xd3' # 0xee -> LATIN CAPITAL LETTER O WITH ACUTE - u'\xd4' # 0xef -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - u'\uf8ff' # 0xf0 -> Apple logo - u'\xd2' # 0xf1 -> LATIN CAPITAL LETTER O WITH GRAVE - u'\xda' # 0xf2 -> LATIN CAPITAL LETTER U WITH ACUTE - u'\xdb' # 0xf3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - u'\xd9' # 0xf4 -> LATIN CAPITAL LETTER U WITH GRAVE - u'\uf8a0' # 0xf5 -> undefined1 - u'\u02c6' # 0xf6 -> MODIFIER LETTER CIRCUMFLEX ACCENT - u'\u02dc' # 0xf7 -> SMALL TILDE - u'\xaf' # 0xf8 -> MACRON - u'\u02d8' # 0xf9 -> BREVE - u'\u02d9' # 0xfa -> DOT ABOVE - u'\u02da' # 0xfb -> RING ABOVE - u'\xb8' # 0xfc -> CEDILLA - u'\u02dd' # 0xfd -> DOUBLE ACUTE ACCENT - u'\u02db' # 0xfe -> OGONEK - u'\u02c7' # 0xff -> CARON + u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + u'\u2020' # 0xA0 -> DAGGER + u'\xb0' # 0xA1 -> DEGREE SIGN + u'\xa2' # 0xA2 -> CENT SIGN + u'\xa3' # 0xA3 -> POUND SIGN + u'\xa7' # 0xA4 -> SECTION SIGN + u'\u2022' # 0xA5 -> BULLET + u'\xb6' # 0xA6 -> PILCROW SIGN + u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + u'\xae' # 0xA8 -> REGISTERED SIGN + u'\xa9' # 0xA9 -> COPYRIGHT SIGN + u'\u2122' # 0xAA -> TRADE MARK SIGN + u'\xb4' # 0xAB -> ACUTE ACCENT + u'\xa8' # 0xAC -> DIAERESIS + u'\u2260' # 0xAD -> NOT EQUAL TO + u'\xc6' # 0xAE -> LATIN CAPITAL LETTER AE + u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + u'\u221e' # 0xB0 -> INFINITY + u'\xb1' # 0xB1 -> PLUS-MINUS SIGN + u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + u'\xa5' # 0xB4 -> YEN SIGN + u'\xb5' # 0xB5 -> MICRO SIGN + u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + u'\u2211' # 0xB7 -> N-ARY SUMMATION + u'\u220f' # 0xB8 -> N-ARY PRODUCT + u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + u'\u222b' # 0xBA -> INTEGRAL + u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + u'\xe6' # 0xBE -> LATIN SMALL LETTER AE + u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + u'\xbf' # 0xC0 -> INVERTED QUESTION MARK + u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + u'\xac' # 0xC2 -> NOT SIGN + u'\u221a' # 0xC3 -> SQUARE ROOT + u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + u'\u2248' # 0xC5 -> ALMOST EQUAL TO + u'\u2206' # 0xC6 -> INCREMENT + u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + u'\xa0' # 0xCA -> NO-BREAK SPACE + u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + u'\u2013' # 0xD0 -> EN DASH + u'\u2014' # 0xD1 -> EM DASH + u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + u'\xf7' # 0xD6 -> DIVISION SIGN + u'\u25ca' # 0xD7 -> LOZENGE + u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + u'\u011e' # 0xDA -> LATIN CAPITAL LETTER G WITH BREVE + u'\u011f' # 0xDB -> LATIN SMALL LETTER G WITH BREVE + u'\u0130' # 0xDC -> LATIN CAPITAL LETTER I WITH DOT ABOVE + u'\u0131' # 0xDD -> LATIN SMALL LETTER DOTLESS I + u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA + u'\u015f' # 0xDF -> LATIN SMALL LETTER S WITH CEDILLA + u'\u2021' # 0xE0 -> DOUBLE DAGGER + u'\xb7' # 0xE1 -> MIDDLE DOT + u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + u'\u2030' # 0xE4 -> PER MILLE SIGN + u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + u'\uf8ff' # 0xF0 -> Apple logo + u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + u'\uf8a0' # 0xF5 -> undefined1 + u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + u'\u02dc' # 0xF7 -> SMALL TILDE + u'\xaf' # 0xF8 -> MACRON + u'\u02d8' # 0xF9 -> BREVE + u'\u02d9' # 0xFA -> DOT ABOVE + u'\u02da' # 0xFB -> RING ABOVE + u'\xb8' # 0xFC -> CEDILLA + u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + u'\u02db' # 0xFE -> OGONEK + u'\u02c7' # 0xFF -> CARON ) ### Encoding Map @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # CONTROL CHARACTER 0x0008: 0x08, # CONTROL CHARACTER 0x0009: 0x09, # CONTROL CHARACTER - 0x000a: 0x0a, # CONTROL CHARACTER - 0x000b: 0x0b, # CONTROL CHARACTER - 0x000c: 0x0c, # CONTROL CHARACTER - 0x000d: 0x0d, # CONTROL CHARACTER - 0x000e: 0x0e, # CONTROL CHARACTER - 0x000f: 0x0f, # CONTROL CHARACTER + 0x000A: 0x0A, # CONTROL CHARACTER + 0x000B: 0x0B, # CONTROL CHARACTER + 0x000C: 0x0C, # CONTROL CHARACTER + 0x000D: 0x0D, # CONTROL CHARACTER + 0x000E: 0x0E, # CONTROL CHARACTER + 0x000F: 0x0F, # CONTROL CHARACTER 0x0010: 0x10, # CONTROL CHARACTER 0x0011: 0x11, # CONTROL CHARACTER 0x0012: 0x12, # CONTROL CHARACTER @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # CONTROL CHARACTER 0x0018: 0x18, # CONTROL CHARACTER 0x0019: 0x19, # CONTROL CHARACTER - 0x001a: 0x1a, # CONTROL CHARACTER - 0x001b: 0x1b, # CONTROL CHARACTER - 0x001c: 0x1c, # CONTROL CHARACTER - 0x001d: 0x1d, # CONTROL CHARACTER - 0x001e: 0x1e, # CONTROL CHARACTER - 0x001f: 0x1f, # CONTROL CHARACTER + 0x001A: 0x1A, # CONTROL CHARACTER + 0x001B: 0x1B, # CONTROL CHARACTER + 0x001C: 0x1C, # CONTROL CHARACTER + 0x001D: 0x1D, # CONTROL CHARACTER + 0x001E: 0x1E, # CONTROL CHARACTER + 0x001F: 0x1F, # CONTROL CHARACTER 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,138 +415,139 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # CONTROL CHARACTER - 0x00a0: 0xca, # NO-BREAK SPACE - 0x00a1: 0xc1, # INVERTED EXCLAMATION MARK - 0x00a2: 0xa2, # CENT SIGN - 0x00a3: 0xa3, # POUND SIGN - 0x00a5: 0xb4, # YEN SIGN - 0x00a7: 0xa4, # SECTION SIGN - 0x00a8: 0xac, # DIAERESIS - 0x00a9: 0xa9, # COPYRIGHT SIGN - 0x00aa: 0xbb, # FEMININE ORDINAL INDICATOR - 0x00ab: 0xc7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00ac: 0xc2, # NOT SIGN - 0x00ae: 0xa8, # REGISTERED SIGN - 0x00af: 0xf8, # MACRON - 0x00b0: 0xa1, # DEGREE SIGN - 0x00b1: 0xb1, # PLUS-MINUS SIGN - 0x00b4: 0xab, # ACUTE ACCENT - 0x00b5: 0xb5, # MICRO SIGN - 0x00b6: 0xa6, # PILCROW SIGN - 0x00b7: 0xe1, # MIDDLE DOT - 0x00b8: 0xfc, # CEDILLA - 0x00ba: 0xbc, # MASCULINE ORDINAL INDICATOR - 0x00bb: 0xc8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK - 0x00bf: 0xc0, # INVERTED QUESTION MARK - 0x00c0: 0xcb, # LATIN CAPITAL LETTER A WITH GRAVE - 0x00c1: 0xe7, # LATIN CAPITAL LETTER A WITH ACUTE - 0x00c2: 0xe5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX - 0x00c3: 0xcc, # LATIN CAPITAL LETTER A WITH TILDE - 0x00c4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS - 0x00c5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE - 0x00c6: 0xae, # LATIN CAPITAL LETTER AE - 0x00c7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA - 0x00c8: 0xe9, # LATIN CAPITAL LETTER E WITH GRAVE - 0x00c9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE - 0x00ca: 0xe6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX - 0x00cb: 0xe8, # LATIN CAPITAL LETTER E WITH DIAERESIS - 0x00cc: 0xed, # LATIN CAPITAL LETTER I WITH GRAVE - 0x00cd: 0xea, # LATIN CAPITAL LETTER I WITH ACUTE - 0x00ce: 0xeb, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX - 0x00cf: 0xec, # LATIN CAPITAL LETTER I WITH DIAERESIS - 0x00d1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE - 0x00d2: 0xf1, # LATIN CAPITAL LETTER O WITH GRAVE - 0x00d3: 0xee, # LATIN CAPITAL LETTER O WITH ACUTE - 0x00d4: 0xef, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX - 0x00d5: 0xcd, # LATIN CAPITAL LETTER O WITH TILDE - 0x00d6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS - 0x00d8: 0xaf, # LATIN CAPITAL LETTER O WITH STROKE - 0x00d9: 0xf4, # LATIN CAPITAL LETTER U WITH GRAVE - 0x00da: 0xf2, # LATIN CAPITAL LETTER U WITH ACUTE - 0x00db: 0xf3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX - 0x00dc: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS - 0x00df: 0xa7, # LATIN SMALL LETTER SHARP S - 0x00e0: 0x88, # LATIN SMALL LETTER A WITH GRAVE - 0x00e1: 0x87, # LATIN SMALL LETTER A WITH ACUTE - 0x00e2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX - 0x00e3: 0x8b, # LATIN SMALL LETTER A WITH TILDE - 0x00e4: 0x8a, # LATIN SMALL LETTER A WITH DIAERESIS - 0x00e5: 0x8c, # LATIN SMALL LETTER A WITH RING ABOVE - 0x00e6: 0xbe, # LATIN SMALL LETTER AE - 0x00e7: 0x8d, # LATIN SMALL LETTER C WITH CEDILLA - 0x00e8: 0x8f, # LATIN SMALL LETTER E WITH GRAVE - 0x00e9: 0x8e, # LATIN SMALL LETTER E WITH ACUTE - 0x00ea: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX - 0x00eb: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS - 0x00ec: 0x93, # LATIN SMALL LETTER I WITH GRAVE - 0x00ed: 0x92, # LATIN SMALL LETTER I WITH ACUTE - 0x00ee: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX - 0x00ef: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS - 0x00f1: 0x96, # LATIN SMALL LETTER N WITH TILDE - 0x00f2: 0x98, # LATIN SMALL LETTER O WITH GRAVE - 0x00f3: 0x97, # LATIN SMALL LETTER O WITH ACUTE - 0x00f4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX - 0x00f5: 0x9b, # LATIN SMALL LETTER O WITH TILDE - 0x00f6: 0x9a, # LATIN SMALL LETTER O WITH DIAERESIS - 0x00f7: 0xd6, # DIVISION SIGN - 0x00f8: 0xbf, # LATIN SMALL LETTER O WITH STROKE - 0x00f9: 0x9d, # LATIN SMALL LETTER U WITH GRAVE - 0x00fa: 0x9c, # LATIN SMALL LETTER U WITH ACUTE - 0x00fb: 0x9e, # LATIN SMALL LETTER U WITH CIRCUMFLEX - 0x00fc: 0x9f, # LATIN SMALL LETTER U WITH DIAERESIS - 0x00ff: 0xd8, # LATIN SMALL LETTER Y WITH DIAERESIS - 0x011e: 0xda, # LATIN CAPITAL LETTER G WITH BREVE - 0x011f: 0xdb, # LATIN SMALL LETTER G WITH BREVE - 0x0130: 0xdc, # LATIN CAPITAL LETTER I WITH DOT ABOVE - 0x0131: 0xdd, # LATIN SMALL LETTER DOTLESS I - 0x0152: 0xce, # LATIN CAPITAL LIGATURE OE - 0x0153: 0xcf, # LATIN SMALL LIGATURE OE - 0x015e: 0xde, # LATIN CAPITAL LETTER S WITH CEDILLA - 0x015f: 0xdf, # LATIN SMALL LETTER S WITH CEDILLA - 0x0178: 0xd9, # LATIN CAPITAL LETTER Y WITH DIAERESIS - 0x0192: 0xc4, # LATIN SMALL LETTER F WITH HOOK - 0x02c6: 0xf6, # MODIFIER LETTER CIRCUMFLEX ACCENT - 0x02c7: 0xff, # CARON - 0x02d8: 0xf9, # BREVE - 0x02d9: 0xfa, # DOT ABOVE - 0x02da: 0xfb, # RING ABOVE - 0x02db: 0xfe, # OGONEK - 0x02dc: 0xf7, # SMALL TILDE - 0x02dd: 0xfd, # DOUBLE ACUTE ACCENT - 0x03a9: 0xbd, # GREEK CAPITAL LETTER OMEGA - 0x03c0: 0xb9, # GREEK SMALL LETTER PI - 0x2013: 0xd0, # EN DASH - 0x2014: 0xd1, # EM DASH - 0x2018: 0xd4, # LEFT SINGLE QUOTATION MARK - 0x2019: 0xd5, # RIGHT SINGLE QUOTATION MARK - 0x201a: 0xe2, # SINGLE LOW-9 QUOTATION MARK - 0x201c: 0xd2, # LEFT DOUBLE QUOTATION MARK - 0x201d: 0xd3, # RIGHT DOUBLE QUOTATION MARK - 0x201e: 0xe3, # DOUBLE LOW-9 QUOTATION MARK - 0x2020: 0xa0, # DAGGER - 0x2021: 0xe0, # DOUBLE DAGGER - 0x2022: 0xa5, # BULLET - 0x2026: 0xc9, # HORIZONTAL ELLIPSIS - 0x2030: 0xe4, # PER MILLE SIGN - 0x2122: 0xaa, # TRADE MARK SIGN - 0x2202: 0xb6, # PARTIAL DIFFERENTIAL - 0x2206: 0xc6, # INCREMENT - 0x220f: 0xb8, # N-ARY PRODUCT - 0x2211: 0xb7, # N-ARY SUMMATION - 0x221a: 0xc3, # SQUARE ROOT - 0x221e: 0xb0, # INFINITY - 0x222b: 0xba, # INTEGRAL - 0x2248: 0xc5, # ALMOST EQUAL TO - 0x2260: 0xad, # NOT EQUAL TO - 0x2264: 0xb2, # LESS-THAN OR EQUAL TO - 0x2265: 0xb3, # GREATER-THAN OR EQUAL TO - 0x25ca: 0xd7, # LOZENGE - 0xf8a0: 0xf5, # undefined1 - 0xf8ff: 0xf0, # Apple logo -} \ No newline at end of file + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # CONTROL CHARACTER + 0x00A0: 0xCA, # NO-BREAK SPACE + 0x00A1: 0xC1, # INVERTED EXCLAMATION MARK + 0x00A2: 0xA2, # CENT SIGN + 0x00A3: 0xA3, # POUND SIGN + 0x00A5: 0xB4, # YEN SIGN + 0x00A7: 0xA4, # SECTION SIGN + 0x00A8: 0xAC, # DIAERESIS + 0x00A9: 0xA9, # COPYRIGHT SIGN + 0x00AA: 0xBB, # FEMININE ORDINAL INDICATOR + 0x00AB: 0xC7, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00AC: 0xC2, # NOT SIGN + 0x00AE: 0xA8, # REGISTERED SIGN + 0x00AF: 0xF8, # MACRON + 0x00B0: 0xA1, # DEGREE SIGN + 0x00B1: 0xB1, # PLUS-MINUS SIGN + 0x00B4: 0xAB, # ACUTE ACCENT + 0x00B5: 0xB5, # MICRO SIGN + 0x00B6: 0xA6, # PILCROW SIGN + 0x00B7: 0xE1, # MIDDLE DOT + 0x00B8: 0xFC, # CEDILLA + 0x00BA: 0xBC, # MASCULINE ORDINAL INDICATOR + 0x00BB: 0xC8, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00BF: 0xC0, # INVERTED QUESTION MARK + 0x00C0: 0xCB, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00C1: 0xE7, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00C2: 0xE5, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00C3: 0xCC, # LATIN CAPITAL LETTER A WITH TILDE + 0x00C4: 0x80, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00C5: 0x81, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00C6: 0xAE, # LATIN CAPITAL LETTER AE + 0x00C7: 0x82, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00C8: 0xE9, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00C9: 0x83, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00CA: 0xE6, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00CB: 0xE8, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00CC: 0xED, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00CD: 0xEA, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00CE: 0xEB, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00CF: 0xEC, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00D1: 0x84, # LATIN CAPITAL LETTER N WITH TILDE + 0x00D2: 0xF1, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00D3: 0xEE, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00D4: 0xEF, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00D5: 0xCD, # LATIN CAPITAL LETTER O WITH TILDE + 0x00D6: 0x85, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00D8: 0xAF, # LATIN CAPITAL LETTER O WITH STROKE + 0x00D9: 0xF4, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00DA: 0xF2, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00DB: 0xF3, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00DC: 0x86, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00DF: 0xA7, # LATIN SMALL LETTER SHARP S + 0x00E0: 0x88, # LATIN SMALL LETTER A WITH GRAVE + 0x00E1: 0x87, # LATIN SMALL LETTER A WITH ACUTE + 0x00E2: 0x89, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00E3: 0x8B, # LATIN SMALL LETTER A WITH TILDE + 0x00E4: 0x8A, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00E5: 0x8C, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00E6: 0xBE, # LATIN SMALL LETTER AE + 0x00E7: 0x8D, # LATIN SMALL LETTER C WITH CEDILLA + 0x00E8: 0x8F, # LATIN SMALL LETTER E WITH GRAVE + 0x00E9: 0x8E, # LATIN SMALL LETTER E WITH ACUTE + 0x00EA: 0x90, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00EB: 0x91, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00EC: 0x93, # LATIN SMALL LETTER I WITH GRAVE + 0x00ED: 0x92, # LATIN SMALL LETTER I WITH ACUTE + 0x00EE: 0x94, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00EF: 0x95, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00F1: 0x96, # LATIN SMALL LETTER N WITH TILDE + 0x00F2: 0x98, # LATIN SMALL LETTER O WITH GRAVE + 0x00F3: 0x97, # LATIN SMALL LETTER O WITH ACUTE + 0x00F4: 0x99, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00F5: 0x9B, # LATIN SMALL LETTER O WITH TILDE + 0x00F6: 0x9A, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00F7: 0xD6, # DIVISION SIGN + 0x00F8: 0xBF, # LATIN SMALL LETTER O WITH STROKE + 0x00F9: 0x9D, # LATIN SMALL LETTER U WITH GRAVE + 0x00FA: 0x9C, # LATIN SMALL LETTER U WITH ACUTE + 0x00FB: 0x9E, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00FC: 0x9F, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00FF: 0xD8, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x011E: 0xDA, # LATIN CAPITAL LETTER G WITH BREVE + 0x011F: 0xDB, # LATIN SMALL LETTER G WITH BREVE + 0x0130: 0xDC, # LATIN CAPITAL LETTER I WITH DOT ABOVE + 0x0131: 0xDD, # LATIN SMALL LETTER DOTLESS I + 0x0152: 0xCE, # LATIN CAPITAL LIGATURE OE + 0x0153: 0xCF, # LATIN SMALL LIGATURE OE + 0x015E: 0xDE, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015F: 0xDF, # LATIN SMALL LETTER S WITH CEDILLA + 0x0178: 0xD9, # LATIN CAPITAL LETTER Y WITH DIAERESIS + 0x0192: 0xC4, # LATIN SMALL LETTER F WITH HOOK + 0x02C6: 0xF6, # MODIFIER LETTER CIRCUMFLEX ACCENT + 0x02C7: 0xFF, # CARON + 0x02D8: 0xF9, # BREVE + 0x02D9: 0xFA, # DOT ABOVE + 0x02DA: 0xFB, # RING ABOVE + 0x02DB: 0xFE, # OGONEK + 0x02DC: 0xF7, # SMALL TILDE + 0x02DD: 0xFD, # DOUBLE ACUTE ACCENT + 0x03A9: 0xBD, # GREEK CAPITAL LETTER OMEGA + 0x03C0: 0xB9, # GREEK SMALL LETTER PI + 0x2013: 0xD0, # EN DASH + 0x2014: 0xD1, # EM DASH + 0x2018: 0xD4, # LEFT SINGLE QUOTATION MARK + 0x2019: 0xD5, # RIGHT SINGLE QUOTATION MARK + 0x201A: 0xE2, # SINGLE LOW-9 QUOTATION MARK + 0x201C: 0xD2, # LEFT DOUBLE QUOTATION MARK + 0x201D: 0xD3, # RIGHT DOUBLE QUOTATION MARK + 0x201E: 0xE3, # DOUBLE LOW-9 QUOTATION MARK + 0x2020: 0xA0, # DAGGER + 0x2021: 0xE0, # DOUBLE DAGGER + 0x2022: 0xA5, # BULLET + 0x2026: 0xC9, # HORIZONTAL ELLIPSIS + 0x2030: 0xE4, # PER MILLE SIGN + 0x2122: 0xAA, # TRADE MARK SIGN + 0x2202: 0xB6, # PARTIAL DIFFERENTIAL + 0x2206: 0xC6, # INCREMENT + 0x220F: 0xB8, # N-ARY PRODUCT + 0x2211: 0xB7, # N-ARY SUMMATION + 0x221A: 0xC3, # SQUARE ROOT + 0x221E: 0xB0, # INFINITY + 0x222B: 0xBA, # INTEGRAL + 0x2248: 0xC5, # ALMOST EQUAL TO + 0x2260: 0xAD, # NOT EQUAL TO + 0x2264: 0xB2, # LESS-THAN OR EQUAL TO + 0x2265: 0xB3, # GREATER-THAN OR EQUAL TO + 0x25CA: 0xD7, # LOZENGE + 0xF8A0: 0xF5, # undefined1 + 0xF8FF: 0xF0, # Apple logo +} + diff --git a/Lib/encodings/tis_620.py b/Lib/encodings/tis_620.py index f7c3f01..cf5ddae 100644 --- a/Lib/encodings/tis_620.py +++ b/Lib/encodings/tis_620.py @@ -42,12 +42,12 @@ decoding_table = ( u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION - u'\n' # 0x0a -> LINE FEED - u'\x0b' # 0x0b -> VERTICAL TABULATION - u'\x0c' # 0x0c -> FORM FEED - u'\r' # 0x0d -> CARRIAGE RETURN - u'\x0e' # 0x0e -> SHIFT OUT - u'\x0f' # 0x0f -> SHIFT IN + u'\n' # 0x0A -> LINE FEED + u'\x0b' # 0x0B -> VERTICAL TABULATION + u'\x0c' # 0x0C -> FORM FEED + u'\r' # 0x0D -> CARRIAGE RETURN + u'\x0e' # 0x0E -> SHIFT OUT + u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO @@ -58,12 +58,12 @@ decoding_table = ( u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM - u'\x1a' # 0x1a -> SUBSTITUTE - u'\x1b' # 0x1b -> ESCAPE - u'\x1c' # 0x1c -> FILE SEPARATOR - u'\x1d' # 0x1d -> GROUP SEPARATOR - u'\x1e' # 0x1e -> RECORD SEPARATOR - u'\x1f' # 0x1f -> UNIT SEPARATOR + u'\x1a' # 0x1A -> SUBSTITUTE + u'\x1b' # 0x1B -> ESCAPE + u'\x1c' # 0x1C -> FILE SEPARATOR + u'\x1d' # 0x1D -> GROUP SEPARATOR + u'\x1e' # 0x1E -> RECORD SEPARATOR + u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK @@ -74,12 +74,12 @@ decoding_table = ( u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS - u'*' # 0x2a -> ASTERISK - u'+' # 0x2b -> PLUS SIGN - u',' # 0x2c -> COMMA - u'-' # 0x2d -> HYPHEN-MINUS - u'.' # 0x2e -> FULL STOP - u'/' # 0x2f -> SOLIDUS + u'*' # 0x2A -> ASTERISK + u'+' # 0x2B -> PLUS SIGN + u',' # 0x2C -> COMMA + u'-' # 0x2D -> HYPHEN-MINUS + u'.' # 0x2E -> FULL STOP + u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO @@ -90,12 +90,12 @@ decoding_table = ( u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE - u':' # 0x3a -> COLON - u';' # 0x3b -> SEMICOLON - u'<' # 0x3c -> LESS-THAN SIGN - u'=' # 0x3d -> EQUALS SIGN - u'>' # 0x3e -> GREATER-THAN SIGN - u'?' # 0x3f -> QUESTION MARK + u':' # 0x3A -> COLON + u';' # 0x3B -> SEMICOLON + u'<' # 0x3C -> LESS-THAN SIGN + u'=' # 0x3D -> EQUALS SIGN + u'>' # 0x3E -> GREATER-THAN SIGN + u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B @@ -106,12 +106,12 @@ decoding_table = ( u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I - u'J' # 0x4a -> LATIN CAPITAL LETTER J - u'K' # 0x4b -> LATIN CAPITAL LETTER K - u'L' # 0x4c -> LATIN CAPITAL LETTER L - u'M' # 0x4d -> LATIN CAPITAL LETTER M - u'N' # 0x4e -> LATIN CAPITAL LETTER N - u'O' # 0x4f -> LATIN CAPITAL LETTER O + u'J' # 0x4A -> LATIN CAPITAL LETTER J + u'K' # 0x4B -> LATIN CAPITAL LETTER K + u'L' # 0x4C -> LATIN CAPITAL LETTER L + u'M' # 0x4D -> LATIN CAPITAL LETTER M + u'N' # 0x4E -> LATIN CAPITAL LETTER N + u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R @@ -122,12 +122,12 @@ decoding_table = ( u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y - u'Z' # 0x5a -> LATIN CAPITAL LETTER Z - u'[' # 0x5b -> LEFT SQUARE BRACKET - u'\\' # 0x5c -> REVERSE SOLIDUS - u']' # 0x5d -> RIGHT SQUARE BRACKET - u'^' # 0x5e -> CIRCUMFLEX ACCENT - u'_' # 0x5f -> LOW LINE + u'Z' # 0x5A -> LATIN CAPITAL LETTER Z + u'[' # 0x5B -> LEFT SQUARE BRACKET + u'\\' # 0x5C -> REVERSE SOLIDUS + u']' # 0x5D -> RIGHT SQUARE BRACKET + u'^' # 0x5E -> CIRCUMFLEX ACCENT + u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B @@ -138,12 +138,12 @@ decoding_table = ( u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I - u'j' # 0x6a -> LATIN SMALL LETTER J - u'k' # 0x6b -> LATIN SMALL LETTER K - u'l' # 0x6c -> LATIN SMALL LETTER L - u'm' # 0x6d -> LATIN SMALL LETTER M - u'n' # 0x6e -> LATIN SMALL LETTER N - u'o' # 0x6f -> LATIN SMALL LETTER O + u'j' # 0x6A -> LATIN SMALL LETTER J + u'k' # 0x6B -> LATIN SMALL LETTER K + u'l' # 0x6C -> LATIN SMALL LETTER L + u'm' # 0x6D -> LATIN SMALL LETTER M + u'n' # 0x6E -> LATIN SMALL LETTER N + u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R @@ -154,12 +154,12 @@ decoding_table = ( u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y - u'z' # 0x7a -> LATIN SMALL LETTER Z - u'{' # 0x7b -> LEFT CURLY BRACKET - u'|' # 0x7c -> VERTICAL LINE - u'}' # 0x7d -> RIGHT CURLY BRACKET - u'~' # 0x7e -> TILDE - u'\x7f' # 0x7f -> DELETE + u'z' # 0x7A -> LATIN SMALL LETTER Z + u'{' # 0x7B -> LEFT CURLY BRACKET + u'|' # 0x7C -> VERTICAL LINE + u'}' # 0x7D -> RIGHT CURLY BRACKET + u'~' # 0x7E -> TILDE + u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> @@ -170,12 +170,12 @@ decoding_table = ( u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> - u'\x8a' # 0x8a -> - u'\x8b' # 0x8b -> - u'\x8c' # 0x8c -> - u'\x8d' # 0x8d -> - u'\x8e' # 0x8e -> - u'\x8f' # 0x8f -> + u'\x8a' # 0x8A -> + u'\x8b' # 0x8B -> + u'\x8c' # 0x8C -> + u'\x8d' # 0x8D -> + u'\x8e' # 0x8E -> + u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> @@ -186,104 +186,104 @@ decoding_table = ( u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> - u'\x9a' # 0x9a -> - u'\x9b' # 0x9b -> - u'\x9c' # 0x9c -> - u'\x9d' # 0x9d -> - u'\x9e' # 0x9e -> - u'\x9f' # 0x9f -> + u'\x9a' # 0x9A -> + u'\x9b' # 0x9B -> + u'\x9c' # 0x9C -> + u'\x9d' # 0x9D -> + u'\x9e' # 0x9E -> + u'\x9f' # 0x9F -> u'\ufffe' - u'\u0e01' # 0xa1 -> THAI CHARACTER KO KAI - u'\u0e02' # 0xa2 -> THAI CHARACTER KHO KHAI - u'\u0e03' # 0xa3 -> THAI CHARACTER KHO KHUAT - u'\u0e04' # 0xa4 -> THAI CHARACTER KHO KHWAI - u'\u0e05' # 0xa5 -> THAI CHARACTER KHO KHON - u'\u0e06' # 0xa6 -> THAI CHARACTER KHO RAKHANG - u'\u0e07' # 0xa7 -> THAI CHARACTER NGO NGU - u'\u0e08' # 0xa8 -> THAI CHARACTER CHO CHAN - u'\u0e09' # 0xa9 -> THAI CHARACTER CHO CHING - u'\u0e0a' # 0xaa -> THAI CHARACTER CHO CHANG - u'\u0e0b' # 0xab -> THAI CHARACTER SO SO - u'\u0e0c' # 0xac -> THAI CHARACTER CHO CHOE - u'\u0e0d' # 0xad -> THAI CHARACTER YO YING - u'\u0e0e' # 0xae -> THAI CHARACTER DO CHADA - u'\u0e0f' # 0xaf -> THAI CHARACTER TO PATAK - u'\u0e10' # 0xb0 -> THAI CHARACTER THO THAN - u'\u0e11' # 0xb1 -> THAI CHARACTER THO NANGMONTHO - u'\u0e12' # 0xb2 -> THAI CHARACTER THO PHUTHAO - u'\u0e13' # 0xb3 -> THAI CHARACTER NO NEN - u'\u0e14' # 0xb4 -> THAI CHARACTER DO DEK - u'\u0e15' # 0xb5 -> THAI CHARACTER TO TAO - u'\u0e16' # 0xb6 -> THAI CHARACTER THO THUNG - u'\u0e17' # 0xb7 -> THAI CHARACTER THO THAHAN - u'\u0e18' # 0xb8 -> THAI CHARACTER THO THONG - u'\u0e19' # 0xb9 -> THAI CHARACTER NO NU - u'\u0e1a' # 0xba -> THAI CHARACTER BO BAIMAI - u'\u0e1b' # 0xbb -> THAI CHARACTER PO PLA - u'\u0e1c' # 0xbc -> THAI CHARACTER PHO PHUNG - u'\u0e1d' # 0xbd -> THAI CHARACTER FO FA - u'\u0e1e' # 0xbe -> THAI CHARACTER PHO PHAN - u'\u0e1f' # 0xbf -> THAI CHARACTER FO FAN - u'\u0e20' # 0xc0 -> THAI CHARACTER PHO SAMPHAO - u'\u0e21' # 0xc1 -> THAI CHARACTER MO MA - u'\u0e22' # 0xc2 -> THAI CHARACTER YO YAK - u'\u0e23' # 0xc3 -> THAI CHARACTER RO RUA - u'\u0e24' # 0xc4 -> THAI CHARACTER RU - u'\u0e25' # 0xc5 -> THAI CHARACTER LO LING - u'\u0e26' # 0xc6 -> THAI CHARACTER LU - u'\u0e27' # 0xc7 -> THAI CHARACTER WO WAEN - u'\u0e28' # 0xc8 -> THAI CHARACTER SO SALA - u'\u0e29' # 0xc9 -> THAI CHARACTER SO RUSI - u'\u0e2a' # 0xca -> THAI CHARACTER SO SUA - u'\u0e2b' # 0xcb -> THAI CHARACTER HO HIP - u'\u0e2c' # 0xcc -> THAI CHARACTER LO CHULA - u'\u0e2d' # 0xcd -> THAI CHARACTER O ANG - u'\u0e2e' # 0xce -> THAI CHARACTER HO NOKHUK - u'\u0e2f' # 0xcf -> THAI CHARACTER PAIYANNOI - u'\u0e30' # 0xd0 -> THAI CHARACTER SARA A - u'\u0e31' # 0xd1 -> THAI CHARACTER MAI HAN-AKAT - u'\u0e32' # 0xd2 -> THAI CHARACTER SARA AA - u'\u0e33' # 0xd3 -> THAI CHARACTER SARA AM - u'\u0e34' # 0xd4 -> THAI CHARACTER SARA I - u'\u0e35' # 0xd5 -> THAI CHARACTER SARA II - u'\u0e36' # 0xd6 -> THAI CHARACTER SARA UE - u'\u0e37' # 0xd7 -> THAI CHARACTER SARA UEE - u'\u0e38' # 0xd8 -> THAI CHARACTER SARA U - u'\u0e39' # 0xd9 -> THAI CHARACTER SARA UU - u'\u0e3a' # 0xda -> THAI CHARACTER PHINTHU + u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI + u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI + u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT + u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI + u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON + u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG + u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU + u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN + u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING + u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG + u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO + u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE + u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING + u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA + u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK + u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN + u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO + u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO + u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN + u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK + u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO + u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG + u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN + u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG + u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU + u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI + u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA + u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG + u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA + u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN + u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN + u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO + u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA + u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK + u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA + u'\u0e24' # 0xC4 -> THAI CHARACTER RU + u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING + u'\u0e26' # 0xC6 -> THAI CHARACTER LU + u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN + u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA + u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI + u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA + u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP + u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA + u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG + u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK + u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI + u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A + u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT + u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA + u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM + u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I + u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II + u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE + u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE + u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U + u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU + u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' - u'\u0e3f' # 0xdf -> THAI CURRENCY SYMBOL BAHT - u'\u0e40' # 0xe0 -> THAI CHARACTER SARA E - u'\u0e41' # 0xe1 -> THAI CHARACTER SARA AE - u'\u0e42' # 0xe2 -> THAI CHARACTER SARA O - u'\u0e43' # 0xe3 -> THAI CHARACTER SARA AI MAIMUAN - u'\u0e44' # 0xe4 -> THAI CHARACTER SARA AI MAIMALAI - u'\u0e45' # 0xe5 -> THAI CHARACTER LAKKHANGYAO - u'\u0e46' # 0xe6 -> THAI CHARACTER MAIYAMOK - u'\u0e47' # 0xe7 -> THAI CHARACTER MAITAIKHU - u'\u0e48' # 0xe8 -> THAI CHARACTER MAI EK - u'\u0e49' # 0xe9 -> THAI CHARACTER MAI THO - u'\u0e4a' # 0xea -> THAI CHARACTER MAI TRI - u'\u0e4b' # 0xeb -> THAI CHARACTER MAI CHATTAWA - u'\u0e4c' # 0xec -> THAI CHARACTER THANTHAKHAT - u'\u0e4d' # 0xed -> THAI CHARACTER NIKHAHIT - u'\u0e4e' # 0xee -> THAI CHARACTER YAMAKKAN - u'\u0e4f' # 0xef -> THAI CHARACTER FONGMAN - u'\u0e50' # 0xf0 -> THAI DIGIT ZERO - u'\u0e51' # 0xf1 -> THAI DIGIT ONE - u'\u0e52' # 0xf2 -> THAI DIGIT TWO - u'\u0e53' # 0xf3 -> THAI DIGIT THREE - u'\u0e54' # 0xf4 -> THAI DIGIT FOUR - u'\u0e55' # 0xf5 -> THAI DIGIT FIVE - u'\u0e56' # 0xf6 -> THAI DIGIT SIX - u'\u0e57' # 0xf7 -> THAI DIGIT SEVEN - u'\u0e58' # 0xf8 -> THAI DIGIT EIGHT - u'\u0e59' # 0xf9 -> THAI DIGIT NINE - u'\u0e5a' # 0xfa -> THAI CHARACTER ANGKHANKHU - u'\u0e5b' # 0xfb -> THAI CHARACTER KHOMUT + u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT + u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E + u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE + u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O + u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN + u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI + u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO + u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK + u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU + u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK + u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO + u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI + u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA + u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT + u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT + u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN + u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN + u'\u0e50' # 0xF0 -> THAI DIGIT ZERO + u'\u0e51' # 0xF1 -> THAI DIGIT ONE + u'\u0e52' # 0xF2 -> THAI DIGIT TWO + u'\u0e53' # 0xF3 -> THAI DIGIT THREE + u'\u0e54' # 0xF4 -> THAI DIGIT FOUR + u'\u0e55' # 0xF5 -> THAI DIGIT FIVE + u'\u0e56' # 0xF6 -> THAI DIGIT SIX + u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN + u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT + u'\u0e59' # 0xF9 -> THAI DIGIT NINE + u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU + u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT u'\ufffe' u'\ufffe' u'\ufffe' @@ -303,12 +303,12 @@ encoding_map = { 0x0007: 0x07, # BELL 0x0008: 0x08, # BACKSPACE 0x0009: 0x09, # HORIZONTAL TABULATION - 0x000a: 0x0a, # LINE FEED - 0x000b: 0x0b, # VERTICAL TABULATION - 0x000c: 0x0c, # FORM FEED - 0x000d: 0x0d, # CARRIAGE RETURN - 0x000e: 0x0e, # SHIFT OUT - 0x000f: 0x0f, # SHIFT IN + 0x000A: 0x0A, # LINE FEED + 0x000B: 0x0B, # VERTICAL TABULATION + 0x000C: 0x0C, # FORM FEED + 0x000D: 0x0D, # CARRIAGE RETURN + 0x000E: 0x0E, # SHIFT OUT + 0x000F: 0x0F, # SHIFT IN 0x0010: 0x10, # DATA LINK ESCAPE 0x0011: 0x11, # DEVICE CONTROL ONE 0x0012: 0x12, # DEVICE CONTROL TWO @@ -319,12 +319,12 @@ encoding_map = { 0x0017: 0x17, # END OF TRANSMISSION BLOCK 0x0018: 0x18, # CANCEL 0x0019: 0x19, # END OF MEDIUM - 0x001a: 0x1a, # SUBSTITUTE - 0x001b: 0x1b, # ESCAPE - 0x001c: 0x1c, # FILE SEPARATOR - 0x001d: 0x1d, # GROUP SEPARATOR - 0x001e: 0x1e, # RECORD SEPARATOR - 0x001f: 0x1f, # UNIT SEPARATOR + 0x001A: 0x1A, # SUBSTITUTE + 0x001B: 0x1B, # ESCAPE + 0x001C: 0x1C, # FILE SEPARATOR + 0x001D: 0x1D, # GROUP SEPARATOR + 0x001E: 0x1E, # RECORD SEPARATOR + 0x001F: 0x1F, # UNIT SEPARATOR 0x0020: 0x20, # SPACE 0x0021: 0x21, # EXCLAMATION MARK 0x0022: 0x22, # QUOTATION MARK @@ -335,12 +335,12 @@ encoding_map = { 0x0027: 0x27, # APOSTROPHE 0x0028: 0x28, # LEFT PARENTHESIS 0x0029: 0x29, # RIGHT PARENTHESIS - 0x002a: 0x2a, # ASTERISK - 0x002b: 0x2b, # PLUS SIGN - 0x002c: 0x2c, # COMMA - 0x002d: 0x2d, # HYPHEN-MINUS - 0x002e: 0x2e, # FULL STOP - 0x002f: 0x2f, # SOLIDUS + 0x002A: 0x2A, # ASTERISK + 0x002B: 0x2B, # PLUS SIGN + 0x002C: 0x2C, # COMMA + 0x002D: 0x2D, # HYPHEN-MINUS + 0x002E: 0x2E, # FULL STOP + 0x002F: 0x2F, # SOLIDUS 0x0030: 0x30, # DIGIT ZERO 0x0031: 0x31, # DIGIT ONE 0x0032: 0x32, # DIGIT TWO @@ -351,12 +351,12 @@ encoding_map = { 0x0037: 0x37, # DIGIT SEVEN 0x0038: 0x38, # DIGIT EIGHT 0x0039: 0x39, # DIGIT NINE - 0x003a: 0x3a, # COLON - 0x003b: 0x3b, # SEMICOLON - 0x003c: 0x3c, # LESS-THAN SIGN - 0x003d: 0x3d, # EQUALS SIGN - 0x003e: 0x3e, # GREATER-THAN SIGN - 0x003f: 0x3f, # QUESTION MARK + 0x003A: 0x3A, # COLON + 0x003B: 0x3B, # SEMICOLON + 0x003C: 0x3C, # LESS-THAN SIGN + 0x003D: 0x3D, # EQUALS SIGN + 0x003E: 0x3E, # GREATER-THAN SIGN + 0x003F: 0x3F, # QUESTION MARK 0x0040: 0x40, # COMMERCIAL AT 0x0041: 0x41, # LATIN CAPITAL LETTER A 0x0042: 0x42, # LATIN CAPITAL LETTER B @@ -367,12 +367,12 @@ encoding_map = { 0x0047: 0x47, # LATIN CAPITAL LETTER G 0x0048: 0x48, # LATIN CAPITAL LETTER H 0x0049: 0x49, # LATIN CAPITAL LETTER I - 0x004a: 0x4a, # LATIN CAPITAL LETTER J - 0x004b: 0x4b, # LATIN CAPITAL LETTER K - 0x004c: 0x4c, # LATIN CAPITAL LETTER L - 0x004d: 0x4d, # LATIN CAPITAL LETTER M - 0x004e: 0x4e, # LATIN CAPITAL LETTER N - 0x004f: 0x4f, # LATIN CAPITAL LETTER O + 0x004A: 0x4A, # LATIN CAPITAL LETTER J + 0x004B: 0x4B, # LATIN CAPITAL LETTER K + 0x004C: 0x4C, # LATIN CAPITAL LETTER L + 0x004D: 0x4D, # LATIN CAPITAL LETTER M + 0x004E: 0x4E, # LATIN CAPITAL LETTER N + 0x004F: 0x4F, # LATIN CAPITAL LETTER O 0x0050: 0x50, # LATIN CAPITAL LETTER P 0x0051: 0x51, # LATIN CAPITAL LETTER Q 0x0052: 0x52, # LATIN CAPITAL LETTER R @@ -383,12 +383,12 @@ encoding_map = { 0x0057: 0x57, # LATIN CAPITAL LETTER W 0x0058: 0x58, # LATIN CAPITAL LETTER X 0x0059: 0x59, # LATIN CAPITAL LETTER Y - 0x005a: 0x5a, # LATIN CAPITAL LETTER Z - 0x005b: 0x5b, # LEFT SQUARE BRACKET - 0x005c: 0x5c, # REVERSE SOLIDUS - 0x005d: 0x5d, # RIGHT SQUARE BRACKET - 0x005e: 0x5e, # CIRCUMFLEX ACCENT - 0x005f: 0x5f, # LOW LINE + 0x005A: 0x5A, # LATIN CAPITAL LETTER Z + 0x005B: 0x5B, # LEFT SQUARE BRACKET + 0x005C: 0x5C, # REVERSE SOLIDUS + 0x005D: 0x5D, # RIGHT SQUARE BRACKET + 0x005E: 0x5E, # CIRCUMFLEX ACCENT + 0x005F: 0x5F, # LOW LINE 0x0060: 0x60, # GRAVE ACCENT 0x0061: 0x61, # LATIN SMALL LETTER A 0x0062: 0x62, # LATIN SMALL LETTER B @@ -399,12 +399,12 @@ encoding_map = { 0x0067: 0x67, # LATIN SMALL LETTER G 0x0068: 0x68, # LATIN SMALL LETTER H 0x0069: 0x69, # LATIN SMALL LETTER I - 0x006a: 0x6a, # LATIN SMALL LETTER J - 0x006b: 0x6b, # LATIN SMALL LETTER K - 0x006c: 0x6c, # LATIN SMALL LETTER L - 0x006d: 0x6d, # LATIN SMALL LETTER M - 0x006e: 0x6e, # LATIN SMALL LETTER N - 0x006f: 0x6f, # LATIN SMALL LETTER O + 0x006A: 0x6A, # LATIN SMALL LETTER J + 0x006B: 0x6B, # LATIN SMALL LETTER K + 0x006C: 0x6C, # LATIN SMALL LETTER L + 0x006D: 0x6D, # LATIN SMALL LETTER M + 0x006E: 0x6E, # LATIN SMALL LETTER N + 0x006F: 0x6F, # LATIN SMALL LETTER O 0x0070: 0x70, # LATIN SMALL LETTER P 0x0071: 0x71, # LATIN SMALL LETTER Q 0x0072: 0x72, # LATIN SMALL LETTER R @@ -415,12 +415,12 @@ encoding_map = { 0x0077: 0x77, # LATIN SMALL LETTER W 0x0078: 0x78, # LATIN SMALL LETTER X 0x0079: 0x79, # LATIN SMALL LETTER Y - 0x007a: 0x7a, # LATIN SMALL LETTER Z - 0x007b: 0x7b, # LEFT CURLY BRACKET - 0x007c: 0x7c, # VERTICAL LINE - 0x007d: 0x7d, # RIGHT CURLY BRACKET - 0x007e: 0x7e, # TILDE - 0x007f: 0x7f, # DELETE + 0x007A: 0x7A, # LATIN SMALL LETTER Z + 0x007B: 0x7B, # LEFT CURLY BRACKET + 0x007C: 0x7C, # VERTICAL LINE + 0x007D: 0x7D, # RIGHT CURLY BRACKET + 0x007E: 0x7E, # TILDE + 0x007F: 0x7F, # DELETE 0x0080: 0x80, # 0x0081: 0x81, # 0x0082: 0x82, # @@ -431,12 +431,12 @@ encoding_map = { 0x0087: 0x87, # 0x0088: 0x88, # 0x0089: 0x89, # - 0x008a: 0x8a, # - 0x008b: 0x8b, # - 0x008c: 0x8c, # - 0x008d: 0x8d, # - 0x008e: 0x8e, # - 0x008f: 0x8f, # + 0x008A: 0x8A, # + 0x008B: 0x8B, # + 0x008C: 0x8C, # + 0x008D: 0x8D, # + 0x008E: 0x8E, # + 0x008F: 0x8F, # 0x0090: 0x90, # 0x0091: 0x91, # 0x0092: 0x92, # @@ -447,97 +447,98 @@ encoding_map = { 0x0097: 0x97, # 0x0098: 0x98, # 0x0099: 0x99, # - 0x009a: 0x9a, # - 0x009b: 0x9b, # - 0x009c: 0x9c, # - 0x009d: 0x9d, # - 0x009e: 0x9e, # - 0x009f: 0x9f, # - 0x0e01: 0xa1, # THAI CHARACTER KO KAI - 0x0e02: 0xa2, # THAI CHARACTER KHO KHAI - 0x0e03: 0xa3, # THAI CHARACTER KHO KHUAT - 0x0e04: 0xa4, # THAI CHARACTER KHO KHWAI - 0x0e05: 0xa5, # THAI CHARACTER KHO KHON - 0x0e06: 0xa6, # THAI CHARACTER KHO RAKHANG - 0x0e07: 0xa7, # THAI CHARACTER NGO NGU - 0x0e08: 0xa8, # THAI CHARACTER CHO CHAN - 0x0e09: 0xa9, # THAI CHARACTER CHO CHING - 0x0e0a: 0xaa, # THAI CHARACTER CHO CHANG - 0x0e0b: 0xab, # THAI CHARACTER SO SO - 0x0e0c: 0xac, # THAI CHARACTER CHO CHOE - 0x0e0d: 0xad, # THAI CHARACTER YO YING - 0x0e0e: 0xae, # THAI CHARACTER DO CHADA - 0x0e0f: 0xaf, # THAI CHARACTER TO PATAK - 0x0e10: 0xb0, # THAI CHARACTER THO THAN - 0x0e11: 0xb1, # THAI CHARACTER THO NANGMONTHO - 0x0e12: 0xb2, # THAI CHARACTER THO PHUTHAO - 0x0e13: 0xb3, # THAI CHARACTER NO NEN - 0x0e14: 0xb4, # THAI CHARACTER DO DEK - 0x0e15: 0xb5, # THAI CHARACTER TO TAO - 0x0e16: 0xb6, # THAI CHARACTER THO THUNG - 0x0e17: 0xb7, # THAI CHARACTER THO THAHAN - 0x0e18: 0xb8, # THAI CHARACTER THO THONG - 0x0e19: 0xb9, # THAI CHARACTER NO NU - 0x0e1a: 0xba, # THAI CHARACTER BO BAIMAI - 0x0e1b: 0xbb, # THAI CHARACTER PO PLA - 0x0e1c: 0xbc, # THAI CHARACTER PHO PHUNG - 0x0e1d: 0xbd, # THAI CHARACTER FO FA - 0x0e1e: 0xbe, # THAI CHARACTER PHO PHAN - 0x0e1f: 0xbf, # THAI CHARACTER FO FAN - 0x0e20: 0xc0, # THAI CHARACTER PHO SAMPHAO - 0x0e21: 0xc1, # THAI CHARACTER MO MA - 0x0e22: 0xc2, # THAI CHARACTER YO YAK - 0x0e23: 0xc3, # THAI CHARACTER RO RUA - 0x0e24: 0xc4, # THAI CHARACTER RU - 0x0e25: 0xc5, # THAI CHARACTER LO LING - 0x0e26: 0xc6, # THAI CHARACTER LU - 0x0e27: 0xc7, # THAI CHARACTER WO WAEN - 0x0e28: 0xc8, # THAI CHARACTER SO SALA - 0x0e29: 0xc9, # THAI CHARACTER SO RUSI - 0x0e2a: 0xca, # THAI CHARACTER SO SUA - 0x0e2b: 0xcb, # THAI CHARACTER HO HIP - 0x0e2c: 0xcc, # THAI CHARACTER LO CHULA - 0x0e2d: 0xcd, # THAI CHARACTER O ANG - 0x0e2e: 0xce, # THAI CHARACTER HO NOKHUK - 0x0e2f: 0xcf, # THAI CHARACTER PAIYANNOI - 0x0e30: 0xd0, # THAI CHARACTER SARA A - 0x0e31: 0xd1, # THAI CHARACTER MAI HAN-AKAT - 0x0e32: 0xd2, # THAI CHARACTER SARA AA - 0x0e33: 0xd3, # THAI CHARACTER SARA AM - 0x0e34: 0xd4, # THAI CHARACTER SARA I - 0x0e35: 0xd5, # THAI CHARACTER SARA II - 0x0e36: 0xd6, # THAI CHARACTER SARA UE - 0x0e37: 0xd7, # THAI CHARACTER SARA UEE - 0x0e38: 0xd8, # THAI CHARACTER SARA U - 0x0e39: 0xd9, # THAI CHARACTER SARA UU - 0x0e3a: 0xda, # THAI CHARACTER PHINTHU - 0x0e3f: 0xdf, # THAI CURRENCY SYMBOL BAHT - 0x0e40: 0xe0, # THAI CHARACTER SARA E - 0x0e41: 0xe1, # THAI CHARACTER SARA AE - 0x0e42: 0xe2, # THAI CHARACTER SARA O - 0x0e43: 0xe3, # THAI CHARACTER SARA AI MAIMUAN - 0x0e44: 0xe4, # THAI CHARACTER SARA AI MAIMALAI - 0x0e45: 0xe5, # THAI CHARACTER LAKKHANGYAO - 0x0e46: 0xe6, # THAI CHARACTER MAIYAMOK - 0x0e47: 0xe7, # THAI CHARACTER MAITAIKHU - 0x0e48: 0xe8, # THAI CHARACTER MAI EK - 0x0e49: 0xe9, # THAI CHARACTER MAI THO - 0x0e4a: 0xea, # THAI CHARACTER MAI TRI - 0x0e4b: 0xeb, # THAI CHARACTER MAI CHATTAWA - 0x0e4c: 0xec, # THAI CHARACTER THANTHAKHAT - 0x0e4d: 0xed, # THAI CHARACTER NIKHAHIT - 0x0e4e: 0xee, # THAI CHARACTER YAMAKKAN - 0x0e4f: 0xef, # THAI CHARACTER FONGMAN - 0x0e50: 0xf0, # THAI DIGIT ZERO - 0x0e51: 0xf1, # THAI DIGIT ONE - 0x0e52: 0xf2, # THAI DIGIT TWO - 0x0e53: 0xf3, # THAI DIGIT THREE - 0x0e54: 0xf4, # THAI DIGIT FOUR - 0x0e55: 0xf5, # THAI DIGIT FIVE - 0x0e56: 0xf6, # THAI DIGIT SIX - 0x0e57: 0xf7, # THAI DIGIT SEVEN - 0x0e58: 0xf8, # THAI DIGIT EIGHT - 0x0e59: 0xf9, # THAI DIGIT NINE - 0x0e5a: 0xfa, # THAI CHARACTER ANGKHANKHU - 0x0e5b: 0xfb, # THAI CHARACTER KHOMUT -} \ No newline at end of file + 0x009A: 0x9A, # + 0x009B: 0x9B, # + 0x009C: 0x9C, # + 0x009D: 0x9D, # + 0x009E: 0x9E, # + 0x009F: 0x9F, # + 0x0E01: 0xA1, # THAI CHARACTER KO KAI + 0x0E02: 0xA2, # THAI CHARACTER KHO KHAI + 0x0E03: 0xA3, # THAI CHARACTER KHO KHUAT + 0x0E04: 0xA4, # THAI CHARACTER KHO KHWAI + 0x0E05: 0xA5, # THAI CHARACTER KHO KHON + 0x0E06: 0xA6, # THAI CHARACTER KHO RAKHANG + 0x0E07: 0xA7, # THAI CHARACTER NGO NGU + 0x0E08: 0xA8, # THAI CHARACTER CHO CHAN + 0x0E09: 0xA9, # THAI CHARACTER CHO CHING + 0x0E0A: 0xAA, # THAI CHARACTER CHO CHANG + 0x0E0B: 0xAB, # THAI CHARACTER SO SO + 0x0E0C: 0xAC, # THAI CHARACTER CHO CHOE + 0x0E0D: 0xAD, # THAI CHARACTER YO YING + 0x0E0E: 0xAE, # THAI CHARACTER DO CHADA + 0x0E0F: 0xAF, # THAI CHARACTER TO PATAK + 0x0E10: 0xB0, # THAI CHARACTER THO THAN + 0x0E11: 0xB1, # THAI CHARACTER THO NANGMONTHO + 0x0E12: 0xB2, # THAI CHARACTER THO PHUTHAO + 0x0E13: 0xB3, # THAI CHARACTER NO NEN + 0x0E14: 0xB4, # THAI CHARACTER DO DEK + 0x0E15: 0xB5, # THAI CHARACTER TO TAO + 0x0E16: 0xB6, # THAI CHARACTER THO THUNG + 0x0E17: 0xB7, # THAI CHARACTER THO THAHAN + 0x0E18: 0xB8, # THAI CHARACTER THO THONG + 0x0E19: 0xB9, # THAI CHARACTER NO NU + 0x0E1A: 0xBA, # THAI CHARACTER BO BAIMAI + 0x0E1B: 0xBB, # THAI CHARACTER PO PLA + 0x0E1C: 0xBC, # THAI CHARACTER PHO PHUNG + 0x0E1D: 0xBD, # THAI CHARACTER FO FA + 0x0E1E: 0xBE, # THAI CHARACTER PHO PHAN + 0x0E1F: 0xBF, # THAI CHARACTER FO FAN + 0x0E20: 0xC0, # THAI CHARACTER PHO SAMPHAO + 0x0E21: 0xC1, # THAI CHARACTER MO MA + 0x0E22: 0xC2, # THAI CHARACTER YO YAK + 0x0E23: 0xC3, # THAI CHARACTER RO RUA + 0x0E24: 0xC4, # THAI CHARACTER RU + 0x0E25: 0xC5, # THAI CHARACTER LO LING + 0x0E26: 0xC6, # THAI CHARACTER LU + 0x0E27: 0xC7, # THAI CHARACTER WO WAEN + 0x0E28: 0xC8, # THAI CHARACTER SO SALA + 0x0E29: 0xC9, # THAI CHARACTER SO RUSI + 0x0E2A: 0xCA, # THAI CHARACTER SO SUA + 0x0E2B: 0xCB, # THAI CHARACTER HO HIP + 0x0E2C: 0xCC, # THAI CHARACTER LO CHULA + 0x0E2D: 0xCD, # THAI CHARACTER O ANG + 0x0E2E: 0xCE, # THAI CHARACTER HO NOKHUK + 0x0E2F: 0xCF, # THAI CHARACTER PAIYANNOI + 0x0E30: 0xD0, # THAI CHARACTER SARA A + 0x0E31: 0xD1, # THAI CHARACTER MAI HAN-AKAT + 0x0E32: 0xD2, # THAI CHARACTER SARA AA + 0x0E33: 0xD3, # THAI CHARACTER SARA AM + 0x0E34: 0xD4, # THAI CHARACTER SARA I + 0x0E35: 0xD5, # THAI CHARACTER SARA II + 0x0E36: 0xD6, # THAI CHARACTER SARA UE + 0x0E37: 0xD7, # THAI CHARACTER SARA UEE + 0x0E38: 0xD8, # THAI CHARACTER SARA U + 0x0E39: 0xD9, # THAI CHARACTER SARA UU + 0x0E3A: 0xDA, # THAI CHARACTER PHINTHU + 0x0E3F: 0xDF, # THAI CURRENCY SYMBOL BAHT + 0x0E40: 0xE0, # THAI CHARACTER SARA E + 0x0E41: 0xE1, # THAI CHARACTER SARA AE + 0x0E42: 0xE2, # THAI CHARACTER SARA O + 0x0E43: 0xE3, # THAI CHARACTER SARA AI MAIMUAN + 0x0E44: 0xE4, # THAI CHARACTER SARA AI MAIMALAI + 0x0E45: 0xE5, # THAI CHARACTER LAKKHANGYAO + 0x0E46: 0xE6, # THAI CHARACTER MAIYAMOK + 0x0E47: 0xE7, # THAI CHARACTER MAITAIKHU + 0x0E48: 0xE8, # THAI CHARACTER MAI EK + 0x0E49: 0xE9, # THAI CHARACTER MAI THO + 0x0E4A: 0xEA, # THAI CHARACTER MAI TRI + 0x0E4B: 0xEB, # THAI CHARACTER MAI CHATTAWA + 0x0E4C: 0xEC, # THAI CHARACTER THANTHAKHAT + 0x0E4D: 0xED, # THAI CHARACTER NIKHAHIT + 0x0E4E: 0xEE, # THAI CHARACTER YAMAKKAN + 0x0E4F: 0xEF, # THAI CHARACTER FONGMAN + 0x0E50: 0xF0, # THAI DIGIT ZERO + 0x0E51: 0xF1, # THAI DIGIT ONE + 0x0E52: 0xF2, # THAI DIGIT TWO + 0x0E53: 0xF3, # THAI DIGIT THREE + 0x0E54: 0xF4, # THAI DIGIT FOUR + 0x0E55: 0xF5, # THAI DIGIT FIVE + 0x0E56: 0xF6, # THAI DIGIT SIX + 0x0E57: 0xF7, # THAI DIGIT SEVEN + 0x0E58: 0xF8, # THAI DIGIT EIGHT + 0x0E59: 0xF9, # THAI DIGIT NINE + 0x0E5A: 0xFA, # THAI CHARACTER ANGKHANKHU + 0x0E5B: 0xFB, # THAI CHARACTER KHOMUT +} + -- cgit v0.12