summaryrefslogtreecommitdiffstats
path: root/Lib/encodings/cp424.py
diff options
context:
space:
mode:
authorMartin v. Löwis <martin@v.loewis.de>2006-06-04 19:36:28 (GMT)
committerMartin v. Löwis <martin@v.loewis.de>2006-06-04 19:36:28 (GMT)
commit3f767795f6784ca6bf797b055be67fce5bf2fa06 (patch)
tree851eea9180023026ef3ef2319fae871a50bb479c /Lib/encodings/cp424.py
parent67966bed72dc175938c4b971145c4746ac993f19 (diff)
downloadcpython-3f767795f6784ca6bf797b055be67fce5bf2fa06.zip
cpython-3f767795f6784ca6bf797b055be67fce5bf2fa06.tar.gz
cpython-3f767795f6784ca6bf797b055be67fce5bf2fa06.tar.bz2
Patch #1359618: Speed-up charmap encoder.
Diffstat (limited to 'Lib/encodings/cp424.py')
-rw-r--r--Lib/encodings/cp424.py227
1 files changed, 4 insertions, 223 deletions
diff --git a/Lib/encodings/cp424.py b/Lib/encodings/cp424.py
index 966aecb..b83787e 100644
--- a/Lib/encodings/cp424.py
+++ b/Lib/encodings/cp424.py
@@ -9,14 +9,14 @@ import codecs
class Codec(codecs.Codec):
def encode(self,input,errors='strict'):
- return codecs.charmap_encode(input,errors,encoding_map)
+ return codecs.charmap_encode(input,errors,encoding_table)
def decode(self,input,errors='strict'):
return codecs.charmap_decode(input,errors,decoding_table)
class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
- return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
@@ -303,225 +303,6 @@ decoding_table = (
u'\x9f' # 0xFF -> EIGHT ONES
)
-### Encoding Map
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
-encoding_map = {
- 0x0000: 0x00, # NULL
- 0x0001: 0x01, # START OF HEADING
- 0x0002: 0x02, # START OF TEXT
- 0x0003: 0x03, # END OF TEXT
- 0x0004: 0x37, # END OF TRANSMISSION
- 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
- 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
- 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
- 0x0020: 0x40, # SPACE
- 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
- 0x0060: 0x79, # GRAVE ACCENT
- 0x0061: 0x81, # LATIN SMALL LETTER A
- 0x0062: 0x82, # LATIN SMALL LETTER B
- 0x0063: 0x83, # LATIN SMALL LETTER C
- 0x0064: 0x84, # LATIN SMALL LETTER D
- 0x0065: 0x85, # LATIN SMALL LETTER E
- 0x0066: 0x86, # LATIN SMALL LETTER F
- 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
- 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
- 0x0080: 0x20, # DIGIT SELECT
- 0x0081: 0x21, # START OF SIGNIFICANCE
- 0x0082: 0x22, # FIELD SEPARATOR
- 0x0083: 0x23, # WORD UNDERSCORE
- 0x0084: 0x24, # BYPASS OR INHIBIT PRESENTATION
- 0x0085: 0x15, # NEW LINE
- 0x0086: 0x06, # REQUIRED NEW LINE
- 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
- 0x0090: 0x30, # <reserved>
- 0x0091: 0x31, # <reserved>
- 0x0092: 0x1A, # UNIT BACK SPACE
- 0x0093: 0x33, # INDEX RETURN
- 0x0094: 0x34, # PRESENTATION POSITION
- 0x0095: 0x35, # TRANSPARENT
- 0x0096: 0x36, # NUMERIC BACKSPACE
- 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, # <reserved>
- 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
-}