diff options
32 files changed, 558 insertions, 388 deletions
diff --git a/library/encoding/iso8859-11.enc b/library/encoding/iso8859-11.enc new file mode 100644 index 0000000..d683453 --- /dev/null +++ b/library/encoding/iso8859-11.enc @@ -0,0 +1,20 @@ +# Encoding file: iso8859-11, single-byte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diff --git a/library/encoding/iso8859-7.enc b/library/encoding/iso8859-7.enc index 0f93ac8..a46112f 100644 --- a/library/encoding/iso8859-7.enc +++ b/library/encoding/iso8859-7.enc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diff --git a/tests/encoding.test b/tests/encoding.test index 0e80c09..21610a7 100644 --- a/tests/encoding.test +++ b/tests/encoding.test @@ -762,7 +762,7 @@ test encoding-28.0 {all encodings load} -body { llength $name } return $count -} -result [expr {[info exists ::tcl_precision] ? 87 : 86}] +} -result [expr {[info exists ::tcl_precision] ? 88 : 87}] runtests diff --git a/tools/encoding/cp1250.txt b/tools/encoding/cp1250.txt index 081d776..ca94b25 100644 --- a/tools/encoding/cp1250.txt +++ b/tools/encoding/cp1250.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE 0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA -0xFF 0x02D9 #DOT ABOVE +0xFF 0x02D9 #DOT ABOVE
\ No newline at end of file diff --git a/tools/encoding/cp1251.txt b/tools/encoding/cp1251.txt index 37eadbd..c990b66 100644 --- a/tools/encoding/cp1251.txt +++ b/tools/encoding/cp1251.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x044C #CYRILLIC SMALL LETTER SOFT SIGN 0xFD 0x044D #CYRILLIC SMALL LETTER E 0xFE 0x044E #CYRILLIC SMALL LETTER YU -0xFF 0x044F #CYRILLIC SMALL LETTER YA +0xFF 0x044F #CYRILLIC SMALL LETTER YA
\ No newline at end of file diff --git a/tools/encoding/cp1252.txt b/tools/encoding/cp1252.txt index 2ca4486..7da1bc7 100644 --- a/tools/encoding/cp1252.txt +++ b/tools/encoding/cp1252.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE 0xFE 0x00FE #LATIN SMALL LETTER THORN -0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
\ No newline at end of file diff --git a/tools/encoding/cp1253.txt b/tools/encoding/cp1253.txt index 2ba51a0..5063b70 100644 --- a/tools/encoding/cp1253.txt +++ b/tools/encoding/cp1253.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x03CC #GREEK SMALL LETTER OMICRON WITH TONOS 0xFD 0x03CD #GREEK SMALL LETTER UPSILON WITH TONOS 0xFE 0x03CE #GREEK SMALL LETTER OMEGA WITH TONOS -0xFF #UNDEFINED +0xFF #UNDEFINED
\ No newline at end of file diff --git a/tools/encoding/cp1254.txt b/tools/encoding/cp1254.txt index ca1a1eb..5f82b8f 100644 --- a/tools/encoding/cp1254.txt +++ b/tools/encoding/cp1254.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x0131 #LATIN SMALL LETTER DOTLESS I 0xFE 0x015F #LATIN SMALL LETTER S WITH CEDILLA -0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
\ No newline at end of file diff --git a/tools/encoding/cp1255.txt b/tools/encoding/cp1255.txt index 341517f..2d05966 100644 --- a/tools/encoding/cp1255.txt +++ b/tools/encoding/cp1255.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 1/7/2000 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC #UNDEFINED 0xFD 0x200E #LEFT-TO-RIGHT MARK 0xFE 0x200F #RIGHT-TO-LEFT MARK -0xFF #UNDEFINED +0xFF #UNDEFINED
\ No newline at end of file diff --git a/tools/encoding/cp1256.txt b/tools/encoding/cp1256.txt index 0edd081..1f8cabb 100644 --- a/tools/encoding/cp1256.txt +++ b/tools/encoding/cp1256.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 01/5/99 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x200E #LEFT-TO-RIGHT MARK 0xFE 0x200F #RIGHT-TO-LEFT MARK -0xFF 0x06D2 #ARABIC LETTER YEH BARREE +0xFF 0x06D2 #ARABIC LETTER YEH BARREE
\ No newline at end of file diff --git a/tools/encoding/cp1257.txt b/tools/encoding/cp1257.txt index 97979d9..66ad8e6 100644 --- a/tools/encoding/cp1257.txt +++ b/tools/encoding/cp1257.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE 0xFE 0x017E #LATIN SMALL LETTER Z WITH CARON -0xFF 0x02D9 #DOT ABOVE +0xFF 0x02D9 #DOT ABOVE
\ No newline at end of file diff --git a/tools/encoding/cp1258.txt b/tools/encoding/cp1258.txt index 392310a..bd1b81c 100644 --- a/tools/encoding/cp1258.txt +++ b/tools/encoding/cp1258.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x01B0 #LATIN SMALL LETTER U WITH HORN 0xFE 0x20AB #DONG SIGN -0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
\ No newline at end of file diff --git a/tools/encoding/cp874.txt b/tools/encoding/cp874.txt index 1eb71df..210a566 100644 --- a/tools/encoding/cp874.txt +++ b/tools/encoding/cp874.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 02/28/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -271,4 +271,4 @@ 0xFC #UNDEFINED 0xFD #UNDEFINED 0xFE #UNDEFINED -0xFF #UNDEFINED +0xFF #UNDEFINED
\ No newline at end of file diff --git a/tools/encoding/cp932.txt b/tools/encoding/cp932.txt index 36bfdbf..aa9daf7 100644 --- a/tools/encoding/cp932.txt +++ b/tools/encoding/cp932.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 04/15/98 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -7995,4 +7995,4 @@ 0xFC48 0x9D6B #CJK UNIFIED IDEOGRAPH 0xFC49 0xFA2D #CJK COMPATIBILITY IDEOGRAPH 0xFC4A 0x9E19 #CJK UNIFIED IDEOGRAPH -0xFC4B 0x9ED1 #CJK UNIFIED IDEOGRAPH +0xFC4B 0x9ED1 #CJK UNIFIED IDEOGRAPH
\ No newline at end of file diff --git a/tools/encoding/cp936.txt b/tools/encoding/cp936.txt index 66a541b..13f714a 100644 --- a/tools/encoding/cp936.txt +++ b/tools/encoding/cp936.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 1/7/2000 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -22062,4 +22062,4 @@ 0xFE4C 0xFA24 #CJK COMPATIBILITY IDEOGRAPH 0xFE4D 0xFA27 #CJK COMPATIBILITY IDEOGRAPH 0xFE4E 0xFA28 #CJK COMPATIBILITY IDEOGRAPH -0xFE4F 0xFA29 #CJK COMPATIBILITY IDEOGRAPH +0xFE4F 0xFA29 #CJK COMPATIBILITY IDEOGRAPH
\ No newline at end of file diff --git a/tools/encoding/cp949.txt b/tools/encoding/cp949.txt index 6bbda39..08fe554 100644 --- a/tools/encoding/cp949.txt +++ b/tools/encoding/cp949.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 1/7/2000 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -17319,4 +17319,4 @@ 0xFDFB 0x79A7 #CJK UNIFIED IDEOGRAPH 0xFDFC 0x7A00 #CJK UNIFIED IDEOGRAPH 0xFDFD 0x7FB2 #CJK UNIFIED IDEOGRAPH -0xFDFE 0x8A70 #CJK UNIFIED IDEOGRAPH +0xFDFE 0x8A70 #CJK UNIFIED IDEOGRAPH
\ No newline at end of file diff --git a/tools/encoding/cp950.txt b/tools/encoding/cp950.txt index 7fadbbc..d67462e 100644 --- a/tools/encoding/cp950.txt +++ b/tools/encoding/cp950.txt @@ -5,7 +5,7 @@ # Table format: Format A # Date: 1/7/2000 # -# Contact: cpxlate@microsoft.com +# Contact: Shawn.Steele@microsoft.com # # General notes: none # @@ -13774,4 +13774,4 @@ 0xF9FB 0x256E #BOX DRAWINGS LIGHT ARC DOWN AND LEFT 0xF9FC 0x2570 #BOX DRAWINGS LIGHT ARC UP AND RIGHT 0xF9FD 0x256F #BOX DRAWINGS LIGHT ARC UP AND LEFT -0xF9FE 0x2593 #DARK SHADE +0xF9FE 0x2593 #DARK SHADE
\ No newline at end of file diff --git a/tools/encoding/iso8859-1.txt b/tools/encoding/iso8859-1.txt index 473ecab..5293ada 100644 --- a/tools/encoding/iso8859-1.txt +++ b/tools/encoding/iso8859-1.txt @@ -1,26 +1,14 @@ +# 8859-1.TXT +# Date: 2015-12-02 20:19:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-1:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-1 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -300,4 +289,4 @@ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE 0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic) -0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
\ No newline at end of file diff --git a/tools/encoding/iso8859-10.txt b/tools/encoding/iso8859-10.txt index 374a42b..7cf21f8 100644 --- a/tools/encoding/iso8859-10.txt +++ b/tools/encoding/iso8859-10.txt @@ -1,26 +1,14 @@ +# 8859-10.TXT +# Date: 2015-12-02 21:53:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-10:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.1 +# Table version: 2.0 # Table format: Format A -# Date: 1999 October 11 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 October 11 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -36,14 +24,15 @@ # # Version history # 1.0 version new. -# 1.1 corrected mistake in mapping of 0xA4 +# 1.1 corrected mistake in mapping of 0xA4 +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -300,4 +289,4 @@ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE 0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic) -0xFF 0x0138 # LATIN SMALL LETTER KRA +0xFF 0x0138 # LATIN SMALL LETTER KRA
\ No newline at end of file diff --git a/tools/encoding/iso8859-11.txt b/tools/encoding/iso8859-11.txt new file mode 100644 index 0000000..85d289f --- /dev/null +++ b/tools/encoding/iso8859-11.txt @@ -0,0 +1,286 @@ +# 8859-11.TXT +# Date: 2015-12-02 21:55:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Name: ISO/IEC 8859-11:2001 to Unicode +# Unicode version: 3.2 +# Table version: 2.0 +# Table format: Format A +# Date: 2002 October 7 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-11:2001 characters map into Unicode. +# +# ISO/IEC 8859-11:2001 is equivalent to TIS 620-2533 (1990) with +# the addition of 0xA0 NO-BREAK SPACE. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-11 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-11 order. +# +# Version history: +# 2002 October 7 Created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# +# Updated versions of this file may be found in: +# http://www.unicode.org/Public/MAPPINGS/ +# +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # <control> +0x81 0x0081 # <control> +0x82 0x0082 # <control> +0x83 0x0083 # <control> +0x84 0x0084 # <control> +0x85 0x0085 # <control> +0x86 0x0086 # <control> +0x87 0x0087 # <control> +0x88 0x0088 # <control> +0x89 0x0089 # <control> +0x8A 0x008A # <control> +0x8B 0x008B # <control> +0x8C 0x008C # <control> +0x8D 0x008D # <control> +0x8E 0x008E # <control> +0x8F 0x008F # <control> +0x90 0x0090 # <control> +0x91 0x0091 # <control> +0x92 0x0092 # <control> +0x93 0x0093 # <control> +0x94 0x0094 # <control> +0x95 0x0095 # <control> +0x96 0x0096 # <control> +0x97 0x0097 # <control> +0x98 0x0098 # <control> +0x99 0x0099 # <control> +0x9A 0x009A # <control> +0x9B 0x009B # <control> +0x9C 0x009C # <control> +0x9D 0x009D # <control> +0x9E 0x009E # <control> +0x9F 0x009F # <control> +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0E01 # THAI CHARACTER KO KAI +0xA2 0x0E02 # THAI CHARACTER KHO KHAI +0xA3 0x0E03 # THAI CHARACTER KHO KHUAT +0xA4 0x0E04 # THAI CHARACTER KHO KHWAI +0xA5 0x0E05 # THAI CHARACTER KHO KHON +0xA6 0x0E06 # THAI CHARACTER KHO RAKHANG +0xA7 0x0E07 # THAI CHARACTER NGO NGU +0xA8 0x0E08 # THAI CHARACTER CHO CHAN +0xA9 0x0E09 # THAI CHARACTER CHO CHING +0xAA 0x0E0A # THAI CHARACTER CHO CHANG +0xAB 0x0E0B # THAI CHARACTER SO SO +0xAC 0x0E0C # THAI CHARACTER CHO CHOE +0xAD 0x0E0D # THAI CHARACTER YO YING +0xAE 0x0E0E # THAI CHARACTER DO CHADA +0xAF 0x0E0F # THAI CHARACTER TO PATAK +0xB0 0x0E10 # THAI CHARACTER THO THAN +0xB1 0x0E11 # THAI CHARACTER THO NANGMONTHO +0xB2 0x0E12 # THAI CHARACTER THO PHUTHAO +0xB3 0x0E13 # THAI CHARACTER NO NEN +0xB4 0x0E14 # THAI CHARACTER DO DEK +0xB5 0x0E15 # THAI CHARACTER TO TAO +0xB6 0x0E16 # THAI CHARACTER THO THUNG +0xB7 0x0E17 # THAI CHARACTER THO THAHAN +0xB8 0x0E18 # THAI CHARACTER THO THONG +0xB9 0x0E19 # THAI CHARACTER NO NU +0xBA 0x0E1A # THAI CHARACTER BO BAIMAI +0xBB 0x0E1B # THAI CHARACTER PO PLA +0xBC 0x0E1C # THAI CHARACTER PHO PHUNG +0xBD 0x0E1D # THAI CHARACTER FO FA +0xBE 0x0E1E # THAI CHARACTER PHO PHAN +0xBF 0x0E1F # THAI CHARACTER FO FAN +0xC0 0x0E20 # THAI CHARACTER PHO SAMPHAO +0xC1 0x0E21 # THAI CHARACTER MO MA +0xC2 0x0E22 # THAI CHARACTER YO YAK +0xC3 0x0E23 # THAI CHARACTER RO RUA +0xC4 0x0E24 # THAI CHARACTER RU +0xC5 0x0E25 # THAI CHARACTER LO LING +0xC6 0x0E26 # THAI CHARACTER LU +0xC7 0x0E27 # THAI CHARACTER WO WAEN +0xC8 0x0E28 # THAI CHARACTER SO SALA +0xC9 0x0E29 # THAI CHARACTER SO RUSI +0xCA 0x0E2A # THAI CHARACTER SO SUA +0xCB 0x0E2B # THAI CHARACTER HO HIP +0xCC 0x0E2C # THAI CHARACTER LO CHULA +0xCD 0x0E2D # THAI CHARACTER O ANG +0xCE 0x0E2E # THAI CHARACTER HO NOKHUK +0xCF 0x0E2F # THAI CHARACTER PAIYANNOI +0xD0 0x0E30 # THAI CHARACTER SARA A +0xD1 0x0E31 # THAI CHARACTER MAI HAN-AKAT +0xD2 0x0E32 # THAI CHARACTER SARA AA +0xD3 0x0E33 # THAI CHARACTER SARA AM +0xD4 0x0E34 # THAI CHARACTER SARA I +0xD5 0x0E35 # THAI CHARACTER SARA II +0xD6 0x0E36 # THAI CHARACTER SARA UE +0xD7 0x0E37 # THAI CHARACTER SARA UEE +0xD8 0x0E38 # THAI CHARACTER SARA U +0xD9 0x0E39 # THAI CHARACTER SARA UU +0xDA 0x0E3A # THAI CHARACTER PHINTHU +0xDF 0x0E3F # THAI CURRENCY SYMBOL BAHT +0xE0 0x0E40 # THAI CHARACTER SARA E +0xE1 0x0E41 # THAI CHARACTER SARA AE +0xE2 0x0E42 # THAI CHARACTER SARA O +0xE3 0x0E43 # THAI CHARACTER SARA AI MAIMUAN +0xE4 0x0E44 # THAI CHARACTER SARA AI MAIMALAI +0xE5 0x0E45 # THAI CHARACTER LAKKHANGYAO +0xE6 0x0E46 # THAI CHARACTER MAIYAMOK +0xE7 0x0E47 # THAI CHARACTER MAITAIKHU +0xE8 0x0E48 # THAI CHARACTER MAI EK +0xE9 0x0E49 # THAI CHARACTER MAI THO +0xEA 0x0E4A # THAI CHARACTER MAI TRI +0xEB 0x0E4B # THAI CHARACTER MAI CHATTAWA +0xEC 0x0E4C # THAI CHARACTER THANTHAKHAT +0xED 0x0E4D # THAI CHARACTER NIKHAHIT +0xEE 0x0E4E # THAI CHARACTER YAMAKKAN +0xEF 0x0E4F # THAI CHARACTER FONGMAN +0xF0 0x0E50 # THAI DIGIT ZERO +0xF1 0x0E51 # THAI DIGIT ONE +0xF2 0x0E52 # THAI DIGIT TWO +0xF3 0x0E53 # THAI DIGIT THREE +0xF4 0x0E54 # THAI DIGIT FOUR +0xF5 0x0E55 # THAI DIGIT FIVE +0xF6 0x0E56 # THAI DIGIT SIX +0xF7 0x0E57 # THAI DIGIT SEVEN +0xF8 0x0E58 # THAI DIGIT EIGHT +0xF9 0x0E59 # THAI DIGIT NINE +0xFA 0x0E5A # THAI CHARACTER ANGKHANKHU +0xFB 0x0E5B # THAI CHARACTER KHOMUT
\ No newline at end of file diff --git a/tools/encoding/iso8859-13.txt b/tools/encoding/iso8859-13.txt index cd11b53..0dae9cb 100644 --- a/tools/encoding/iso8859-13.txt +++ b/tools/encoding/iso8859-13.txt @@ -1,26 +1,14 @@ +# 8859-13.TXT +# Date: 2015-12-02 22:03:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-13:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -34,12 +22,16 @@ # # The entries are in ISO/IEC 8859-13 order. # +# Version history +# 1.0 version: created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -296,4 +288,4 @@ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE 0xFE 0x017E # LATIN SMALL LETTER Z WITH CARON -0xFF 0x2019 # RIGHT SINGLE QUOTATION MARK +0xFF 0x2019 # RIGHT SINGLE QUOTATION MARK
\ No newline at end of file diff --git a/tools/encoding/iso8859-14.txt b/tools/encoding/iso8859-14.txt index 36038f4..3c3a024 100644 --- a/tools/encoding/iso8859-14.txt +++ b/tools/encoding/iso8859-14.txt @@ -1,27 +1,15 @@ +# 8859-14.TXT +# Date: 2015-12-02 22:05:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-14:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Markus Kuhn <mkuhn@acm.org> -# Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> +# Ken Whistler <ken@unicode.org> # # General notes: # @@ -35,12 +23,16 @@ # # The entries are in ISO/IEC 8859-14 order. # +# Version history +# 1.0 version: created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -298,4 +290,3 @@ 0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE 0xFE 0x0177 # LATIN SMALL LETTER Y WITH CIRCUMFLEX 0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS - diff --git a/tools/encoding/iso8859-15.txt b/tools/encoding/iso8859-15.txt index 1e31970..f21a763 100644 --- a/tools/encoding/iso8859-15.txt +++ b/tools/encoding/iso8859-15.txt @@ -1,27 +1,15 @@ +# 8859-15.TXT +# Date: 2015-12-02 22:06:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-15:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Markus Kuhn <mkuhn@acm.org> -# Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> +# Ken Whistler <ken@unicode.org> # # General notes: # @@ -37,12 +25,16 @@ # # Version history # +# Version history +# 1.0 version: created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -300,4 +292,3 @@ 0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE 0xFE 0x00FE # LATIN SMALL LETTER THORN 0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS - diff --git a/tools/encoding/iso8859-16.txt b/tools/encoding/iso8859-16.txt index 5353d74..e8f5a3e 100644 --- a/tools/encoding/iso8859-16.txt +++ b/tools/encoding/iso8859-16.txt @@ -1,27 +1,17 @@ +# 8859-16.TXT +# Date: 2015-12-02 22:08:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-16:2001 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 2001 July 26 -# Authors: Markus Kuhn <mkuhn@acm.org> +# Date: 2001 July 26 (header updated: 2015 December 02) +# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> # # Copyright (c) 1999-2001 Unicode, Inc. All Rights reserved. # -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. -# # General notes: # # This table contains the data the Unicode Consortium has on how @@ -34,12 +24,16 @@ # # The entries are in ISO/IEC 8859-16 order. # +# Version history +# 1.0 version: created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -296,4 +290,4 @@ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x0119 # LATIN SMALL LETTER E WITH OGONEK 0xFE 0x021B # LATIN SMALL LETTER T WITH COMMA BELOW -0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
\ No newline at end of file diff --git a/tools/encoding/iso8859-2.txt b/tools/encoding/iso8859-2.txt index e45df25..9236280 100644 --- a/tools/encoding/iso8859-2.txt +++ b/tools/encoding/iso8859-2.txt @@ -1,26 +1,14 @@ +# 8859-2.TXT +# Date: 2015-12-02 21:34:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO 8859-2:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-2 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -300,4 +289,4 @@ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE 0xFE 0x0163 # LATIN SMALL LETTER T WITH CEDILLA -0xFF 0x02D9 # DOT ABOVE +0xFF 0x02D9 # DOT ABOVE
\ No newline at end of file diff --git a/tools/encoding/iso8859-3.txt b/tools/encoding/iso8859-3.txt index 9b6ac69..11ea5ca 100644 --- a/tools/encoding/iso8859-3.txt +++ b/tools/encoding/iso8859-3.txt @@ -1,26 +1,14 @@ +# 8859-3.TXT +# Date: 2015-12-02 21:39:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-3:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-3 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -293,4 +282,4 @@ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x016D # LATIN SMALL LETTER U WITH BREVE 0xFE 0x015D # LATIN SMALL LETTER S WITH CIRCUMFLEX -0xFF 0x02D9 # DOT ABOVE +0xFF 0x02D9 # DOT ABOVE
\ No newline at end of file diff --git a/tools/encoding/iso8859-4.txt b/tools/encoding/iso8859-4.txt index 662e698..d5eed8e 100644 --- a/tools/encoding/iso8859-4.txt +++ b/tools/encoding/iso8859-4.txt @@ -1,26 +1,14 @@ +# 8859-4.TXT +# Date: 2015-12-02 21:41:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-4:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-4 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -300,4 +289,4 @@ 0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS 0xFD 0x0169 # LATIN SMALL LETTER U WITH TILDE 0xFE 0x016B # LATIN SMALL LETTER U WITH MACRON -0xFF 0x02D9 # DOT ABOVE +0xFF 0x02D9 # DOT ABOVE
\ No newline at end of file diff --git a/tools/encoding/iso8859-5.txt b/tools/encoding/iso8859-5.txt index a7ed1ce..5c01baf 100644 --- a/tools/encoding/iso8859-5.txt +++ b/tools/encoding/iso8859-5.txt @@ -1,26 +1,14 @@ +# 8859-5.TXT +# Date: 2015-12-02 21:43:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO 8859-5:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-5 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -300,4 +289,4 @@ 0xFC 0x045C # CYRILLIC SMALL LETTER KJE 0xFD 0x00A7 # SECTION SIGN 0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U -0xFF 0x045F # CYRILLIC SMALL LETTER DZHE +0xFF 0x045F # CYRILLIC SMALL LETTER DZHE
\ No newline at end of file diff --git a/tools/encoding/iso8859-6.txt b/tools/encoding/iso8859-6.txt index 69ac7f5..565b547 100644 --- a/tools/encoding/iso8859-6.txt +++ b/tools/encoding/iso8859-6.txt @@ -1,26 +1,14 @@ +# 8859-6.TXT +# Date: 2015-12-02 21:44:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO 8859-6:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -35,17 +23,18 @@ # The entries are in ISO/IEC 8859-6 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. -# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead -# of the Arabic digits (U+0660..U+0669). +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead +# of the Arabic digits (U+0660..U+0669). +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -257,4 +246,4 @@ 0xEF 0x064F # ARABIC DAMMA 0xF0 0x0650 # ARABIC KASRA 0xF1 0x0651 # ARABIC SHADDA -0xF2 0x0652 # ARABIC SUKUN +0xF2 0x0652 # ARABIC SUKUN
\ No newline at end of file diff --git a/tools/encoding/iso8859-7.txt b/tools/encoding/iso8859-7.txt index 52c42d0..245595d 100644 --- a/tools/encoding/iso8859-7.txt +++ b/tools/encoding/iso8859-7.txt @@ -1,34 +1,23 @@ +# 8859-7.TXT +# Date: 2015-12-02 21:47:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # -# Name: ISO 8859-7:1987 to Unicode -# Unicode version: 3.0 -# Table version: 1.0 +# Name: ISO 8859-7:2003 to Unicode +# Unicode version: 4.0 +# Table version: 3.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 2003-Nov-12 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-7:1987 characters map into Unicode. +# ISO 8859-7:2003 characters map into Unicode. # # ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928, -# and ECMA 118. +# and ECMA 118. ISO 8859-7:2003 adds two currency signs +# and one other character not in the earlier standard. # # Format: Three tab-separated columns # Column #1 is the ISO 8859-7 code (in hex as 0xXX) @@ -43,12 +32,17 @@ # Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7 # Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7 # +# 2.0 version updates 1.0 version by adding mappings for the +# three newly added characters 0xA4, 0xA5, 0xAA. +# +# 3.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -214,10 +208,13 @@ 0xA1 0x2018 # LEFT SINGLE QUOTATION MARK 0xA2 0x2019 # RIGHT SINGLE QUOTATION MARK 0xA3 0x00A3 # POUND SIGN +0xA4 0x20AC # EURO SIGN +0xA5 0x20AF # DRACHMA SIGN 0xA6 0x00A6 # BROKEN BAR 0xA7 0x00A7 # SECTION SIGN 0xA8 0x00A8 # DIAERESIS 0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x037A # GREEK YPOGEGRAMMENI 0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0xAC 0x00AC # NOT SIGN 0xAD 0x00AD # SOFT HYPHEN @@ -299,4 +296,4 @@ 0xFB 0x03CB # GREEK SMALL LETTER UPSILON WITH DIALYTIKA 0xFC 0x03CC # GREEK SMALL LETTER OMICRON WITH TONOS 0xFD 0x03CD # GREEK SMALL LETTER UPSILON WITH TONOS -0xFE 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS +0xFE 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS
\ No newline at end of file diff --git a/tools/encoding/iso8859-8.txt b/tools/encoding/iso8859-8.txt index bc8da4c..ff068f7 100644 --- a/tools/encoding/iso8859-8.txt +++ b/tools/encoding/iso8859-8.txt @@ -1,26 +1,14 @@ +# 8859-8.TXT +# Date: 2015-12-02 21:50:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-8:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.1 +# Table version: 2.0 # Table format: Format A -# Date: 2000-Jan-03 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 2000-Jan-03 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -37,15 +25,16 @@ # Version history # 1.0 version updates 0.1 version by adding mappings for all # control characters. -# 1.1 version updates to the published 8859-8:1999, correcting +# 1.1 version updates to the published 8859-8:1999, correcting # the mapping of 0xAF and adding mappings for LRM and RLM. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -267,4 +256,3 @@ 0xFA 0x05EA # HEBREW LETTER TAV 0xFD 0x200E # LEFT-TO-RIGHT MARK 0xFE 0x200F # RIGHT-TO-LEFT MARK - diff --git a/tools/encoding/iso8859-9.txt b/tools/encoding/iso8859-9.txt index 22901f1..c33d666 100644 --- a/tools/encoding/iso8859-9.txt +++ b/tools/encoding/iso8859-9.txt @@ -1,26 +1,14 @@ +# 8859-9.TXT +# Date: 2015-12-02 21:51:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-9:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler <kenw@sybase.com> -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler <ken@unicode.org> # # General notes: # @@ -37,15 +25,16 @@ # ISO/IEC 8859-9 is also equivalent to ISO-IR-148. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# <ftp://ftp.unicode.org/Public/MAPPINGS/> +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact <errata@unicode.org> -# Please note that <errata@unicode.org> is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -304,4 +293,3 @@ 0xFE 0x015F # LATIN SMALL LETTER S WITH CEDILLA 0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS - |