From e2020c47c14a8a03f44734a6c0adc48fb5129c2f Mon Sep 17 00:00:00 2001 From: Victor Wagner Date: Tue, 26 Apr 2016 10:53:16 +0300 Subject: [PATCH] Added new versions of charset files, fixes license issue, reporeted by Martin Ferrari --- charsets/8859-1.txt | 522 ++++++++++++++++++++---------------- charsets/8859-10.txt | 37 +-- charsets/8859-11.txt | 35 +-- charsets/8859-13.txt | 38 ++- charsets/8859-14.txt | 40 ++- charsets/8859-15.txt | 40 ++- charsets/8859-2.txt | 522 ++++++++++++++++++++---------------- charsets/8859-3.txt | 508 ++++++++++++++++++++--------------- charsets/8859-4.txt | 522 ++++++++++++++++++++---------------- charsets/8859-5.txt | 522 ++++++++++++++++++++---------------- charsets/8859-6.txt | 434 +++++++++++++++++------------- charsets/8859-7.txt | 523 ++++++++++++++++++++---------------- charsets/8859-8.txt | 121 +++++++-- charsets/8859-9.txt | 528 ++++++++++++++++++++---------------- charsets/cp1250.txt | 548 ++++++++++++++++++------------------- charsets/cp1251.txt | 20 +- charsets/cp1252.txt | 548 ++++++++++++++++++------------------- charsets/cp1253.txt | 548 ++++++++++++++++++------------------- charsets/cp1254.txt | 548 ++++++++++++++++++------------------- charsets/cp1255.txt | 548 ++++++++++++++++++------------------- charsets/cp1256.txt | 548 ++++++++++++++++++------------------- charsets/cp1257.txt | 548 ++++++++++++++++++------------------- charsets/cp1258.txt | 548 ++++++++++++++++++------------------- charsets/cp437.txt | 4 +- charsets/cp850.txt | 4 +- charsets/cp852.txt | 4 +- charsets/cp855.txt | 4 +- charsets/cp857.txt | 4 +- charsets/cp860.txt | 4 +- charsets/cp861.txt | 4 +- charsets/cp862.txt | 4 +- charsets/cp863.txt | 4 +- charsets/cp864.txt | 4 +- charsets/cp865.txt | 4 +- charsets/cp866.txt | 4 +- charsets/cp869.txt | 4 +- charsets/cp874.txt | 548 ++++++++++++++++++------------------- charsets/koi8-r.txt | 551 ++++++++++++++++++++------------------ charsets/koi8-u.txt | 525 ++++++++++++++++++++---------------- charsets/mac-cyrillic.txt | 129 ++++----- charsets/us-ascii.txt | 296 +++++++++++++------- 41 files changed, 5825 insertions(+), 5072 deletions(-) diff --git a/charsets/8859-1.txt b/charsets/8859-1.txt index e402254..3a55afe 100644 --- a/charsets/8859-1.txt +++ b/charsets/8859-1.txt @@ -1,230 +1,292 @@ -# -# Name: ISO 8859-1 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-1 (1987) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-1 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 8859-1 order -# -# Any comments or problems, contact -# -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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA1 0x00A1 # INVERTED EXCLAMATION MARK -0xA2 0x00A2 # CENT SIGN -0xA3 0x00A3 # POUND SIGN -0xA4 0x00A4 # CURRENCY SIGN -0xA5 0x00A5 # YEN SIGN -0xA6 0x00A6 # BROKEN BAR -0xA7 0x00A7 # SECTION SIGN -0xA8 0x00A8 # DIAERESIS -0xA9 0x00A9 # COPYRIGHT SIGN -0xAA 0x00AA # FEMININE ORDINAL INDICATOR -0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC # NOT SIGN -0xAD 0x00AD # SOFT HYPHEN -0xAE 0x00AE # REGISTERED SIGN -0xAF 0x00AF # MACRON -0xB0 0x00B0 # DEGREE SIGN -0xB1 0x00B1 # PLUS-MINUS SIGN -0xB2 0x00B2 # SUPERSCRIPT TWO -0xB3 0x00B3 # SUPERSCRIPT THREE -0xB4 0x00B4 # ACUTE ACCENT -0xB5 0x00B5 # MICRO SIGN -0xB6 0x00B6 # PILCROW SIGN -0xB7 0x00B7 # MIDDLE DOT -0xB8 0x00B8 # CEDILLA -0xB9 0x00B9 # SUPERSCRIPT ONE -0xBA 0x00BA # MASCULINE ORDINAL INDICATOR -0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC # VULGAR FRACTION ONE QUARTER -0xBD 0x00BD # VULGAR FRACTION ONE HALF -0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS -0xBF 0x00BF # INVERTED QUESTION MARK -0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE -0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE -0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE -0xC6 0x00C6 # LATIN CAPITAL LETTER AE -0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE -0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX -0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE -0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS -0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic) -0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE -0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE -0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE -0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 # MULTIPLICATION SIGN -0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE -0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE -0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE -0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic) -0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German) -0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE -0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE -0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE -0xE6 0x00E6 # LATIN SMALL LETTER AE -0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE -0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE -0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX -0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE -0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS -0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic) -0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE -0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE -0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE -0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 # DIVISION SIGN -0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE -0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE -0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE -0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX -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 +# 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: 2.0 +# Table format: Format A +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-1:1998 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-1 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 8859-1 order. +# +# Version history +# 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: +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x00A1 # INVERTED EXCLAMATION MARK +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00AA # FEMININE ORDINAL INDICATOR +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00BA # MASCULINE ORDINAL INDICATOR +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC # VULGAR FRACTION ONE QUARTER +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF # INVERTED QUESTION MARK +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic) +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic) +0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German) +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic) +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +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 diff --git a/charsets/8859-10.txt b/charsets/8859-10.txt index 374a42b..0ec67d7 100644 --- a/charsets/8859-10.txt +++ b/charsets/8859-10.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 -# -# 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 # # 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: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that 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 diff --git a/charsets/8859-11.txt b/charsets/8859-11.txt index 192bd9d..5334e3c 100644 --- a/charsets/8859-11.txt +++ b/charsets/8859-11.txt @@ -1,26 +1,14 @@ +# 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: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 2002 October 7 -# Authors: Ken Whistler -# -# Copyright (c) 2002 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: 2002 October 7 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -39,13 +27,14 @@ # # 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/ # -# For any comments or problems, please use the Unicode -# web contact form at: -# http://www.unicode.org/unicode/reporting.html +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/charsets/8859-13.txt b/charsets/8859-13.txt index cd11b53..b613dc0 100644 --- a/charsets/8859-13.txt +++ b/charsets/8859-13.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 -# -# 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 # # 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: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that 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 diff --git a/charsets/8859-14.txt b/charsets/8859-14.txt index 36038f4..0351d16 100644 --- a/charsets/8859-14.txt +++ b/charsets/8859-14.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 -# Ken Whistler -# -# 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 +# Ken Whistler # # 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: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that 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 diff --git a/charsets/8859-15.txt b/charsets/8859-15.txt index 1e31970..ada8fca 100644 --- a/charsets/8859-15.txt +++ b/charsets/8859-15.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 -# Ken Whistler -# -# 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 +# Ken Whistler # # 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: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that 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 diff --git a/charsets/8859-2.txt b/charsets/8859-2.txt index 0614739..20da9ba 100644 --- a/charsets/8859-2.txt +++ b/charsets/8859-2.txt @@ -1,230 +1,292 @@ -# -# Name: ISO 8859-2 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-2 (1987) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-2 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 8859-2 order -# -# Any comments or problems, contact -# -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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK -0xA2 0x02D8 # BREVE -0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE -0xA4 0x00A4 # CURRENCY SIGN -0xA5 0x013D # LATIN CAPITAL LETTER L WITH CARON -0xA6 0x015A # LATIN CAPITAL LETTER S WITH ACUTE -0xA7 0x00A7 # SECTION SIGN -0xA8 0x00A8 # DIAERESIS -0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON -0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA -0xAB 0x0164 # LATIN CAPITAL LETTER T WITH CARON -0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE -0xAD 0x00AD # SOFT HYPHEN -0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON -0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE -0xB0 0x00B0 # DEGREE SIGN -0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK -0xB2 0x02DB # OGONEK -0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE -0xB4 0x00B4 # ACUTE ACCENT -0xB5 0x013E # LATIN SMALL LETTER L WITH CARON -0xB6 0x015B # LATIN SMALL LETTER S WITH ACUTE -0xB7 0x02C7 # CARON -0xB8 0x00B8 # CEDILLA -0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON -0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA -0xBB 0x0165 # LATIN SMALL LETTER T WITH CARON -0xBC 0x017A # LATIN SMALL LETTER Z WITH ACUTE -0xBD 0x02DD # DOUBLE ACUTE ACCENT -0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON -0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE -0xC0 0x0154 # LATIN CAPITAL LETTER R WITH ACUTE -0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE -0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x0139 # LATIN CAPITAL LETTER L WITH ACUTE -0xC6 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE -0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON -0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK -0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x011A # LATIN CAPITAL LETTER E WITH CARON -0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x010E # LATIN CAPITAL LETTER D WITH CARON -0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE -0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE -0xD2 0x0147 # LATIN CAPITAL LETTER N WITH CARON -0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE -0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 # MULTIPLICATION SIGN -0xD8 0x0158 # LATIN CAPITAL LETTER R WITH CARON -0xD9 0x016E # LATIN CAPITAL LETTER U WITH RING ABOVE -0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE -0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE -0xDE 0x0162 # LATIN CAPITAL LETTER T WITH CEDILLA -0xDF 0x00DF # LATIN SMALL LETTER SHARP S -0xE0 0x0155 # LATIN SMALL LETTER R WITH ACUTE -0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x0103 # LATIN SMALL LETTER A WITH BREVE -0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x013A # LATIN SMALL LETTER L WITH ACUTE -0xE6 0x0107 # LATIN SMALL LETTER C WITH ACUTE -0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x010D # LATIN SMALL LETTER C WITH CARON -0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE -0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK -0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x011B # LATIN SMALL LETTER E WITH CARON -0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x010F # LATIN SMALL LETTER D WITH CARON -0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE -0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE -0xF2 0x0148 # LATIN SMALL LETTER N WITH CARON -0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE -0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 # DIVISION SIGN -0xF8 0x0159 # LATIN SMALL LETTER R WITH CARON -0xF9 0x016F # LATIN SMALL LETTER U WITH RING ABOVE -0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE -0xFB 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE -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 +# 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: 2.0 +# Table format: Format A +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-2:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-2 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 8859-2 order. +# +# Version history +# 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: +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x02D8 # BREVE +0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x013D # LATIN CAPITAL LETTER L WITH CARON +0xA6 0x015A # LATIN CAPITAL LETTER S WITH ACUTE +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON +0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x0164 # LATIN CAPITAL LETTER T WITH CARON +0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON +0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK +0xB2 0x02DB # OGONEK +0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x013E # LATIN SMALL LETTER L WITH CARON +0xB6 0x015B # LATIN SMALL LETTER S WITH ACUTE +0xB7 0x02C7 # CARON +0xB8 0x00B8 # CEDILLA +0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON +0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x0165 # LATIN SMALL LETTER T WITH CARON +0xBC 0x017A # LATIN SMALL LETTER Z WITH ACUTE +0xBD 0x02DD # DOUBLE ACUTE ACCENT +0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON +0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x0154 # LATIN CAPITAL LETTER R WITH ACUTE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x0139 # LATIN CAPITAL LETTER L WITH ACUTE +0xC6 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x011A # LATIN CAPITAL LETTER E WITH CARON +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x010E # LATIN CAPITAL LETTER D WITH CARON +0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0147 # LATIN CAPITAL LETTER N WITH CARON +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x0158 # LATIN CAPITAL LETTER R WITH CARON +0xD9 0x016E # LATIN CAPITAL LETTER U WITH RING ABOVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x0162 # LATIN CAPITAL LETTER T WITH CEDILLA +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x0155 # LATIN SMALL LETTER R WITH ACUTE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 # LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x013A # LATIN SMALL LETTER L WITH ACUTE +0xE6 0x0107 # LATIN SMALL LETTER C WITH ACUTE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x010D # LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x011B # LATIN SMALL LETTER E WITH CARON +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x010F # LATIN SMALL LETTER D WITH CARON +0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0148 # LATIN SMALL LETTER N WITH CARON +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x0159 # LATIN SMALL LETTER R WITH CARON +0xF9 0x016F # LATIN SMALL LETTER U WITH RING ABOVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE +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 diff --git a/charsets/8859-3.txt b/charsets/8859-3.txt index f9eeb86..5a6c5de 100644 --- a/charsets/8859-3.txt +++ b/charsets/8859-3.txt @@ -1,223 +1,285 @@ -# -# Name: ISO 8859-3 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-3 (1988) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-3 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 8859-3 order -# -# Any comments or problems, contact -# -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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE -0xA2 0x02D8 # BREVE -0xA3 0x00A3 # POUND SIGN -0xA4 0x00A4 # CURRENCY SIGN -0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX -0xA7 0x00A7 # SECTION SIGN -0xA8 0x00A8 # DIAERESIS -0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE -0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA -0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE -0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX -0xAD 0x00AD # SOFT HYPHEN -0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE -0xB0 0x00B0 # DEGREE SIGN -0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE -0xB2 0x00B2 # SUPERSCRIPT TWO -0xB3 0x00B3 # SUPERSCRIPT THREE -0xB4 0x00B4 # ACUTE ACCENT -0xB5 0x00B5 # MICRO SIGN -0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX -0xB7 0x00B7 # MIDDLE DOT -0xB8 0x00B8 # CEDILLA -0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I -0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA -0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE -0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX -0xBD 0x00BD # VULGAR FRACTION ONE HALF -0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE -0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE -0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE -0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX -0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE -0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX -0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE -0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS -0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE -0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE -0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE -0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 # MULTIPLICATION SIGN -0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX -0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE -0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x016C # LATIN CAPITAL LETTER U WITH BREVE -0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX -0xDF 0x00DF # LATIN SMALL LETTER SHARP S -0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE -0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE -0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX -0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE -0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE -0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX -0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE -0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS -0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE -0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE -0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE -0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 # DIVISION SIGN -0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX -0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE -0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE -0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX -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 +# 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: 2.0 +# Table format: Format A +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-3:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-3 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 8859-3 order. +# +# Version history +# 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: +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE +0xA2 0x02D8 # BREVE +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE +0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE +0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX +0xAD 0x00AD # SOFT HYPHEN +0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I +0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE +0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE +0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x016C # LATIN CAPITAL LETTER U WITH BREVE +0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE +0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +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 diff --git a/charsets/8859-4.txt b/charsets/8859-4.txt index 8b72ad8..e2f5e72 100644 --- a/charsets/8859-4.txt +++ b/charsets/8859-4.txt @@ -1,230 +1,292 @@ -# -# Name: ISO 8859-4 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-4 (1988) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-4 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 8859-4 order -# -# Any comments or problems, contact -# -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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK -0xA2 0x0138 # LATIN SMALL LETTER KRA -0xA3 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA -0xA4 0x00A4 # CURRENCY SIGN -0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE -0xA6 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA -0xA7 0x00A7 # SECTION SIGN -0xA8 0x00A8 # DIAERESIS -0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON -0xAA 0x0112 # LATIN CAPITAL LETTER E WITH MACRON -0xAB 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA -0xAC 0x0166 # LATIN CAPITAL LETTER T WITH STROKE -0xAD 0x00AD # SOFT HYPHEN -0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON -0xAF 0x00AF # MACRON -0xB0 0x00B0 # DEGREE SIGN -0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK -0xB2 0x02DB # OGONEK -0xB3 0x0157 # LATIN SMALL LETTER R WITH CEDILLA -0xB4 0x00B4 # ACUTE ACCENT -0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE -0xB6 0x013C # LATIN SMALL LETTER L WITH CEDILLA -0xB7 0x02C7 # CARON -0xB8 0x00B8 # CEDILLA -0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON -0xBA 0x0113 # LATIN SMALL LETTER E WITH MACRON -0xBB 0x0123 # LATIN SMALL LETTER G WITH CEDILLA -0xBC 0x0167 # LATIN SMALL LETTER T WITH STROKE -0xBD 0x014A # LATIN CAPITAL LETTER ENG -0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON -0xBF 0x014B # LATIN SMALL LETTER ENG -0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON -0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE -0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE -0xC6 0x00C6 # LATIN CAPITAL LETTER AE -0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK -0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON -0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK -0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE -0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x012A # LATIN CAPITAL LETTER I WITH MACRON -0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE -0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA -0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON -0xD3 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA -0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE -0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 # MULTIPLICATION SIGN -0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE -0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK -0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x0168 # LATIN CAPITAL LETTER U WITH TILDE -0xDE 0x016A # LATIN CAPITAL LETTER U WITH MACRON -0xDF 0x00DF # LATIN SMALL LETTER SHARP S -0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON -0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE -0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE -0xE6 0x00E6 # LATIN SMALL LETTER AE -0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK -0xE8 0x010D # LATIN SMALL LETTER C WITH CARON -0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE -0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK -0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE -0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x012B # LATIN SMALL LETTER I WITH MACRON -0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE -0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA -0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON -0xF3 0x0137 # LATIN SMALL LETTER K WITH CEDILLA -0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE -0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 # DIVISION SIGN -0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE -0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK -0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE -0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX -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 +# 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: 2.0 +# Table format: Format A +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-4:1998 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-4 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 8859-4 order. +# +# Version history +# 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: +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x0138 # LATIN SMALL LETTER KRA +0xA3 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE +0xA6 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON +0xAA 0x0112 # LATIN CAPITAL LETTER E WITH MACRON +0xAB 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA +0xAC 0x0166 # LATIN CAPITAL LETTER T WITH STROKE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK +0xB2 0x02DB # OGONEK +0xB3 0x0157 # LATIN SMALL LETTER R WITH CEDILLA +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE +0xB6 0x013C # LATIN SMALL LETTER L WITH CEDILLA +0xB7 0x02C7 # CARON +0xB8 0x00B8 # CEDILLA +0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON +0xBA 0x0113 # LATIN SMALL LETTER E WITH MACRON +0xBB 0x0123 # LATIN SMALL LETTER G WITH CEDILLA +0xBC 0x0167 # LATIN SMALL LETTER T WITH STROKE +0xBD 0x014A # LATIN CAPITAL LETTER ENG +0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON +0xBF 0x014B # LATIN SMALL LETTER ENG +0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK +0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x012A # LATIN CAPITAL LETTER I WITH MACRON +0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA +0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON +0xD3 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0168 # LATIN CAPITAL LETTER U WITH TILDE +0xDE 0x016A # LATIN CAPITAL LETTER U WITH MACRON +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK +0xE8 0x010D # LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x012B # LATIN SMALL LETTER I WITH MACRON +0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA +0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON +0xF3 0x0137 # LATIN SMALL LETTER K WITH CEDILLA +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +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 diff --git a/charsets/8859-5.txt b/charsets/8859-5.txt index 9783092..a574c3f 100644 --- a/charsets/8859-5.txt +++ b/charsets/8859-5.txt @@ -1,230 +1,292 @@ -# -# Name: ISO 8859-5 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-5 (1988) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-5 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 8859-5 order -# -# Any comments or problems, contact -# -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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA1 0x0401 # CYRILLIC CAPITAL LETTER IO -0xA2 0x0402 # CYRILLIC CAPITAL LETTER DJE -0xA3 0x0403 # CYRILLIC CAPITAL LETTER GJE -0xA4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE -0xA5 0x0405 # CYRILLIC CAPITAL LETTER DZE -0xA6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I -0xA7 0x0407 # CYRILLIC CAPITAL LETTER YI -0xA8 0x0408 # CYRILLIC CAPITAL LETTER JE -0xA9 0x0409 # CYRILLIC CAPITAL LETTER LJE -0xAA 0x040A # CYRILLIC CAPITAL LETTER NJE -0xAB 0x040B # CYRILLIC CAPITAL LETTER TSHE -0xAC 0x040C # CYRILLIC CAPITAL LETTER KJE -0xAD 0x00AD # SOFT HYPHEN -0xAE 0x040E # CYRILLIC CAPITAL LETTER SHORT U -0xAF 0x040F # CYRILLIC CAPITAL LETTER DZHE -0xB0 0x0410 # CYRILLIC CAPITAL LETTER A -0xB1 0x0411 # CYRILLIC CAPITAL LETTER BE -0xB2 0x0412 # CYRILLIC CAPITAL LETTER VE -0xB3 0x0413 # CYRILLIC CAPITAL LETTER GHE -0xB4 0x0414 # CYRILLIC CAPITAL LETTER DE -0xB5 0x0415 # CYRILLIC CAPITAL LETTER IE -0xB6 0x0416 # CYRILLIC CAPITAL LETTER ZHE -0xB7 0x0417 # CYRILLIC CAPITAL LETTER ZE -0xB8 0x0418 # CYRILLIC CAPITAL LETTER I -0xB9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I -0xBA 0x041A # CYRILLIC CAPITAL LETTER KA -0xBB 0x041B # CYRILLIC CAPITAL LETTER EL -0xBC 0x041C # CYRILLIC CAPITAL LETTER EM -0xBD 0x041D # CYRILLIC CAPITAL LETTER EN -0xBE 0x041E # CYRILLIC CAPITAL LETTER O -0xBF 0x041F # CYRILLIC CAPITAL LETTER PE -0xC0 0x0420 # CYRILLIC CAPITAL LETTER ER -0xC1 0x0421 # CYRILLIC CAPITAL LETTER ES -0xC2 0x0422 # CYRILLIC CAPITAL LETTER TE -0xC3 0x0423 # CYRILLIC CAPITAL LETTER U -0xC4 0x0424 # CYRILLIC CAPITAL LETTER EF -0xC5 0x0425 # CYRILLIC CAPITAL LETTER HA -0xC6 0x0426 # CYRILLIC CAPITAL LETTER TSE -0xC7 0x0427 # CYRILLIC CAPITAL LETTER CHE -0xC8 0x0428 # CYRILLIC CAPITAL LETTER SHA -0xC9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA -0xCA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN -0xCB 0x042B # CYRILLIC CAPITAL LETTER YERU -0xCC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN -0xCD 0x042D # CYRILLIC CAPITAL LETTER E -0xCE 0x042E # CYRILLIC CAPITAL LETTER YU -0xCF 0x042F # CYRILLIC CAPITAL LETTER YA -0xD0 0x0430 # CYRILLIC SMALL LETTER A -0xD1 0x0431 # CYRILLIC SMALL LETTER BE -0xD2 0x0432 # CYRILLIC SMALL LETTER VE -0xD3 0x0433 # CYRILLIC SMALL LETTER GHE -0xD4 0x0434 # CYRILLIC SMALL LETTER DE -0xD5 0x0435 # CYRILLIC SMALL LETTER IE -0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE -0xD7 0x0437 # CYRILLIC SMALL LETTER ZE -0xD8 0x0438 # CYRILLIC SMALL LETTER I -0xD9 0x0439 # CYRILLIC SMALL LETTER SHORT I -0xDA 0x043A # CYRILLIC SMALL LETTER KA -0xDB 0x043B # CYRILLIC SMALL LETTER EL -0xDC 0x043C # CYRILLIC SMALL LETTER EM -0xDD 0x043D # CYRILLIC SMALL LETTER EN -0xDE 0x043E # CYRILLIC SMALL LETTER O -0xDF 0x043F # CYRILLIC SMALL LETTER PE -0xE0 0x0440 # CYRILLIC SMALL LETTER ER -0xE1 0x0441 # CYRILLIC SMALL LETTER ES -0xE2 0x0442 # CYRILLIC SMALL LETTER TE -0xE3 0x0443 # CYRILLIC SMALL LETTER U -0xE4 0x0444 # CYRILLIC SMALL LETTER EF -0xE5 0x0445 # CYRILLIC SMALL LETTER HA -0xE6 0x0446 # CYRILLIC SMALL LETTER TSE -0xE7 0x0447 # CYRILLIC SMALL LETTER CHE -0xE8 0x0448 # CYRILLIC SMALL LETTER SHA -0xE9 0x0449 # CYRILLIC SMALL LETTER SHCHA -0xEA 0x044A # CYRILLIC SMALL LETTER HARD SIGN -0xEB 0x044B # CYRILLIC SMALL LETTER YERU -0xEC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN -0xED 0x044D # CYRILLIC SMALL LETTER E -0xEE 0x044E # CYRILLIC SMALL LETTER YU -0xEF 0x044F # CYRILLIC SMALL LETTER YA -0xF0 0x2116 # NUMERO SIGN -0xF1 0x0451 # CYRILLIC SMALL LETTER IO -0xF2 0x0452 # CYRILLIC SMALL LETTER DJE -0xF3 0x0453 # CYRILLIC SMALL LETTER GJE -0xF4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE -0xF5 0x0455 # CYRILLIC SMALL LETTER DZE -0xF6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I -0xF7 0x0457 # CYRILLIC SMALL LETTER YI -0xF8 0x0458 # CYRILLIC SMALL LETTER JE -0xF9 0x0459 # CYRILLIC SMALL LETTER LJE -0xFA 0x045A # CYRILLIC SMALL LETTER NJE -0xFB 0x045B # CYRILLIC SMALL LETTER TSHE -0xFC 0x045C # CYRILLIC SMALL LETTER KJE -0xFD 0x00A7 # SECTION SIGN -0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U -0xFF 0x045F # CYRILLIC SMALL LETTER DZHE +# 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: 2.0 +# Table format: Format A +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-5:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-5 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 8859-5 order. +# +# Version history +# 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: +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0401 # CYRILLIC CAPITAL LETTER IO +0xA2 0x0402 # CYRILLIC CAPITAL LETTER DJE +0xA3 0x0403 # CYRILLIC CAPITAL LETTER GJE +0xA4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xA5 0x0405 # CYRILLIC CAPITAL LETTER DZE +0xA6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xA7 0x0407 # CYRILLIC CAPITAL LETTER YI +0xA8 0x0408 # CYRILLIC CAPITAL LETTER JE +0xA9 0x0409 # CYRILLIC CAPITAL LETTER LJE +0xAA 0x040A # CYRILLIC CAPITAL LETTER NJE +0xAB 0x040B # CYRILLIC CAPITAL LETTER TSHE +0xAC 0x040C # CYRILLIC CAPITAL LETTER KJE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x040E # CYRILLIC CAPITAL LETTER SHORT U +0xAF 0x040F # CYRILLIC CAPITAL LETTER DZHE +0xB0 0x0410 # CYRILLIC CAPITAL LETTER A +0xB1 0x0411 # CYRILLIC CAPITAL LETTER BE +0xB2 0x0412 # CYRILLIC CAPITAL LETTER VE +0xB3 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xB4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xB5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xB6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xB7 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xB8 0x0418 # CYRILLIC CAPITAL LETTER I +0xB9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xBA 0x041A # CYRILLIC CAPITAL LETTER KA +0xBB 0x041B # CYRILLIC CAPITAL LETTER EL +0xBC 0x041C # CYRILLIC CAPITAL LETTER EM +0xBD 0x041D # CYRILLIC CAPITAL LETTER EN +0xBE 0x041E # CYRILLIC CAPITAL LETTER O +0xBF 0x041F # CYRILLIC CAPITAL LETTER PE +0xC0 0x0420 # CYRILLIC CAPITAL LETTER ER +0xC1 0x0421 # CYRILLIC CAPITAL LETTER ES +0xC2 0x0422 # CYRILLIC CAPITAL LETTER TE +0xC3 0x0423 # CYRILLIC CAPITAL LETTER U +0xC4 0x0424 # CYRILLIC CAPITAL LETTER EF +0xC5 0x0425 # CYRILLIC CAPITAL LETTER HA +0xC6 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xC7 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xC8 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xC9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xCA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN +0xCB 0x042B # CYRILLIC CAPITAL LETTER YERU +0xCC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xCD 0x042D # CYRILLIC CAPITAL LETTER E +0xCE 0x042E # CYRILLIC CAPITAL LETTER YU +0xCF 0x042F # CYRILLIC CAPITAL LETTER YA +0xD0 0x0430 # CYRILLIC SMALL LETTER A +0xD1 0x0431 # CYRILLIC SMALL LETTER BE +0xD2 0x0432 # CYRILLIC SMALL LETTER VE +0xD3 0x0433 # CYRILLIC SMALL LETTER GHE +0xD4 0x0434 # CYRILLIC SMALL LETTER DE +0xD5 0x0435 # CYRILLIC SMALL LETTER IE +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0437 # CYRILLIC SMALL LETTER ZE +0xD8 0x0438 # CYRILLIC SMALL LETTER I +0xD9 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xDA 0x043A # CYRILLIC SMALL LETTER KA +0xDB 0x043B # CYRILLIC SMALL LETTER EL +0xDC 0x043C # CYRILLIC SMALL LETTER EM +0xDD 0x043D # CYRILLIC SMALL LETTER EN +0xDE 0x043E # CYRILLIC SMALL LETTER O +0xDF 0x043F # CYRILLIC SMALL LETTER PE +0xE0 0x0440 # CYRILLIC SMALL LETTER ER +0xE1 0x0441 # CYRILLIC SMALL LETTER ES +0xE2 0x0442 # CYRILLIC SMALL LETTER TE +0xE3 0x0443 # CYRILLIC SMALL LETTER U +0xE4 0x0444 # CYRILLIC SMALL LETTER EF +0xE5 0x0445 # CYRILLIC SMALL LETTER HA +0xE6 0x0446 # CYRILLIC SMALL LETTER TSE +0xE7 0x0447 # CYRILLIC SMALL LETTER CHE +0xE8 0x0448 # CYRILLIC SMALL LETTER SHA +0xE9 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xEA 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xEB 0x044B # CYRILLIC SMALL LETTER YERU +0xEC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xED 0x044D # CYRILLIC SMALL LETTER E +0xEE 0x044E # CYRILLIC SMALL LETTER YU +0xEF 0x044F # CYRILLIC SMALL LETTER YA +0xF0 0x2116 # NUMERO SIGN +0xF1 0x0451 # CYRILLIC SMALL LETTER IO +0xF2 0x0452 # CYRILLIC SMALL LETTER DJE +0xF3 0x0453 # CYRILLIC SMALL LETTER GJE +0xF4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xF5 0x0455 # CYRILLIC SMALL LETTER DZE +0xF6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xF7 0x0457 # CYRILLIC SMALL LETTER YI +0xF8 0x0458 # CYRILLIC SMALL LETTER JE +0xF9 0x0459 # CYRILLIC SMALL LETTER LJE +0xFA 0x045A # CYRILLIC SMALL LETTER NJE +0xFB 0x045B # CYRILLIC SMALL LETTER TSHE +0xFC 0x045C # CYRILLIC SMALL LETTER KJE +0xFD 0x00A7 # SECTION SIGN +0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U +0xFF 0x045F # CYRILLIC SMALL LETTER DZHE diff --git a/charsets/8859-6.txt b/charsets/8859-6.txt index f15efdd..fed0af3 100644 --- a/charsets/8859-6.txt +++ b/charsets/8859-6.txt @@ -1,185 +1,249 @@ -# -# Name: ISO 8859-6 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-6 (1987) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-6 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 8859-6 order -# -# Any comments or problems, contact -# -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 0x0660 # ARABIC-INDIC DIGIT ZERO -0x31 0x0661 # ARABIC-INDIC DIGIT ONE -0x32 0x0662 # ARABIC-INDIC DIGIT TWO -0x33 0x0663 # ARABIC-INDIC DIGIT THREE -0x34 0x0664 # ARABIC-INDIC DIGIT FOUR -0x35 0x0665 # ARABIC-INDIC DIGIT FIVE -0x36 0x0666 # ARABIC-INDIC DIGIT SIX -0x37 0x0667 # ARABIC-INDIC DIGIT SEVEN -0x38 0x0668 # ARABIC-INDIC DIGIT EIGHT -0x39 0x0669 # ARABIC-INDIC 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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA4 0x00A4 # CURRENCY SIGN -0xAC 0x060C # ARABIC COMMA -0xAD 0x00AD # SOFT HYPHEN -0xBB 0x061B # ARABIC SEMICOLON -0xBF 0x061F # ARABIC QUESTION MARK -0xC1 0x0621 # ARABIC LETTER HAMZA -0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE -0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE -0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE -0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW -0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE -0xC7 0x0627 # ARABIC LETTER ALEF -0xC8 0x0628 # ARABIC LETTER BEH -0xC9 0x0629 # ARABIC LETTER TEH MARBUTA -0xCA 0x062A # ARABIC LETTER TEH -0xCB 0x062B # ARABIC LETTER THEH -0xCC 0x062C # ARABIC LETTER JEEM -0xCD 0x062D # ARABIC LETTER HAH -0xCE 0x062E # ARABIC LETTER KHAH -0xCF 0x062F # ARABIC LETTER DAL -0xD0 0x0630 # ARABIC LETTER THAL -0xD1 0x0631 # ARABIC LETTER REH -0xD2 0x0632 # ARABIC LETTER ZAIN -0xD3 0x0633 # ARABIC LETTER SEEN -0xD4 0x0634 # ARABIC LETTER SHEEN -0xD5 0x0635 # ARABIC LETTER SAD -0xD6 0x0636 # ARABIC LETTER DAD -0xD7 0x0637 # ARABIC LETTER TAH -0xD8 0x0638 # ARABIC LETTER ZAH -0xD9 0x0639 # ARABIC LETTER AIN -0xDA 0x063A # ARABIC LETTER GHAIN -0xE0 0x0640 # ARABIC TATWEEL -0xE1 0x0641 # ARABIC LETTER FEH -0xE2 0x0642 # ARABIC LETTER QAF -0xE3 0x0643 # ARABIC LETTER KAF -0xE4 0x0644 # ARABIC LETTER LAM -0xE5 0x0645 # ARABIC LETTER MEEM -0xE6 0x0646 # ARABIC LETTER NOON -0xE7 0x0647 # ARABIC LETTER HEH -0xE8 0x0648 # ARABIC LETTER WAW -0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA -0xEA 0x064A # ARABIC LETTER YEH -0xEB 0x064B # ARABIC FATHATAN -0xEC 0x064C # ARABIC DAMMATAN -0xED 0x064D # ARABIC KASRATAN -0xEE 0x064E # ARABIC FATHA -0xEF 0x064F # ARABIC DAMMA -0xF0 0x0650 # ARABIC KASRA -0xF1 0x0651 # ARABIC SHADDA -0xF2 0x0652 # ARABIC SUKUN +# 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: 2.0 +# Table format: Format A +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-6:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-6 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 8859-6 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). +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA4 0x00A4 # CURRENCY SIGN +0xAC 0x060C # ARABIC COMMA +0xAD 0x00AD # SOFT HYPHEN +0xBB 0x061B # ARABIC SEMICOLON +0xBF 0x061F # ARABIC QUESTION MARK +0xC1 0x0621 # ARABIC LETTER HAMZA +0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE +0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE +0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE +0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW +0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE +0xC7 0x0627 # ARABIC LETTER ALEF +0xC8 0x0628 # ARABIC LETTER BEH +0xC9 0x0629 # ARABIC LETTER TEH MARBUTA +0xCA 0x062A # ARABIC LETTER TEH +0xCB 0x062B # ARABIC LETTER THEH +0xCC 0x062C # ARABIC LETTER JEEM +0xCD 0x062D # ARABIC LETTER HAH +0xCE 0x062E # ARABIC LETTER KHAH +0xCF 0x062F # ARABIC LETTER DAL +0xD0 0x0630 # ARABIC LETTER THAL +0xD1 0x0631 # ARABIC LETTER REH +0xD2 0x0632 # ARABIC LETTER ZAIN +0xD3 0x0633 # ARABIC LETTER SEEN +0xD4 0x0634 # ARABIC LETTER SHEEN +0xD5 0x0635 # ARABIC LETTER SAD +0xD6 0x0636 # ARABIC LETTER DAD +0xD7 0x0637 # ARABIC LETTER TAH +0xD8 0x0638 # ARABIC LETTER ZAH +0xD9 0x0639 # ARABIC LETTER AIN +0xDA 0x063A # ARABIC LETTER GHAIN +0xE0 0x0640 # ARABIC TATWEEL +0xE1 0x0641 # ARABIC LETTER FEH +0xE2 0x0642 # ARABIC LETTER QAF +0xE3 0x0643 # ARABIC LETTER KAF +0xE4 0x0644 # ARABIC LETTER LAM +0xE5 0x0645 # ARABIC LETTER MEEM +0xE6 0x0646 # ARABIC LETTER NOON +0xE7 0x0647 # ARABIC LETTER HEH +0xE8 0x0648 # ARABIC LETTER WAW +0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA +0xEA 0x064A # ARABIC LETTER YEH +0xEB 0x064B # ARABIC FATHATAN +0xEC 0x064C # ARABIC DAMMATAN +0xED 0x064D # ARABIC KASRATAN +0xEE 0x064E # ARABIC FATHA +0xEF 0x064F # ARABIC DAMMA +0xF0 0x0650 # ARABIC KASRA +0xF1 0x0651 # ARABIC SHADDA +0xF2 0x0652 # ARABIC SUKUN diff --git a/charsets/8859-7.txt b/charsets/8859-7.txt index 499cd31..610c4b6 100644 --- a/charsets/8859-7.txt +++ b/charsets/8859-7.txt @@ -1,224 +1,299 @@ -# -# Name: ISO 8859-7 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-7 (1987) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-7 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 8859-7 order -# -# Any comments or problems, contact -# -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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA1 0x02BD # MODIFIER LETTER REVERSED COMMA -0xA2 0x02BC # MODIFIER LETTER APOSTROPHE -0xA3 0x00A3 # POUND SIGN -0xA6 0x00A6 # BROKEN BAR -0xA7 0x00A7 # SECTION SIGN -0xA8 0x00A8 # DIAERESIS -0xA9 0x00A9 # COPYRIGHT SIGN -0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC # NOT SIGN -0xAD 0x00AD # SOFT HYPHEN -0xAF 0x2015 # HORIZONTAL BAR -0xB0 0x00B0 # DEGREE SIGN -0xB1 0x00B1 # PLUS-MINUS SIGN -0xB2 0x00B2 # SUPERSCRIPT TWO -0xB3 0x00B3 # SUPERSCRIPT THREE -0xB4 0x0384 # GREEK TONOS -0xB5 0x0385 # GREEK DIALYTIKA TONOS -0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS -0xB7 0x00B7 # MIDDLE DOT -0xB8 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS -0xB9 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS -0xBA 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS -0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS -0xBD 0x00BD # VULGAR FRACTION ONE HALF -0xBE 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS -0xBF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS -0xC0 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS -0xC1 0x0391 # GREEK CAPITAL LETTER ALPHA -0xC2 0x0392 # GREEK CAPITAL LETTER BETA -0xC3 0x0393 # GREEK CAPITAL LETTER GAMMA -0xC4 0x0394 # GREEK CAPITAL LETTER DELTA -0xC5 0x0395 # GREEK CAPITAL LETTER EPSILON -0xC6 0x0396 # GREEK CAPITAL LETTER ZETA -0xC7 0x0397 # GREEK CAPITAL LETTER ETA -0xC8 0x0398 # GREEK CAPITAL LETTER THETA -0xC9 0x0399 # GREEK CAPITAL LETTER IOTA -0xCA 0x039A # GREEK CAPITAL LETTER KAPPA -0xCB 0x039B # GREEK CAPITAL LETTER LAMDA -0xCC 0x039C # GREEK CAPITAL LETTER MU -0xCD 0x039D # GREEK CAPITAL LETTER NU -0xCE 0x039E # GREEK CAPITAL LETTER XI -0xCF 0x039F # GREEK CAPITAL LETTER OMICRON -0xD0 0x03A0 # GREEK CAPITAL LETTER PI -0xD1 0x03A1 # GREEK CAPITAL LETTER RHO -0xD3 0x03A3 # GREEK CAPITAL LETTER SIGMA -0xD4 0x03A4 # GREEK CAPITAL LETTER TAU -0xD5 0x03A5 # GREEK CAPITAL LETTER UPSILON -0xD6 0x03A6 # GREEK CAPITAL LETTER PHI -0xD7 0x03A7 # GREEK CAPITAL LETTER CHI -0xD8 0x03A8 # GREEK CAPITAL LETTER PSI -0xD9 0x03A9 # GREEK CAPITAL LETTER OMEGA -0xDA 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA -0xDB 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA -0xDC 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS -0xDD 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS -0xDE 0x03AE # GREEK SMALL LETTER ETA WITH TONOS -0xDF 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS -0xE0 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS -0xE1 0x03B1 # GREEK SMALL LETTER ALPHA -0xE2 0x03B2 # GREEK SMALL LETTER BETA -0xE3 0x03B3 # GREEK SMALL LETTER GAMMA -0xE4 0x03B4 # GREEK SMALL LETTER DELTA -0xE5 0x03B5 # GREEK SMALL LETTER EPSILON -0xE6 0x03B6 # GREEK SMALL LETTER ZETA -0xE7 0x03B7 # GREEK SMALL LETTER ETA -0xE8 0x03B8 # GREEK SMALL LETTER THETA -0xE9 0x03B9 # GREEK SMALL LETTER IOTA -0xEA 0x03BA # GREEK SMALL LETTER KAPPA -0xEB 0x03BB # GREEK SMALL LETTER LAMDA -0xEC 0x03BC # GREEK SMALL LETTER MU -0xED 0x03BD # GREEK SMALL LETTER NU -0xEE 0x03BE # GREEK SMALL LETTER XI -0xEF 0x03BF # GREEK SMALL LETTER OMICRON -0xF0 0x03C0 # GREEK SMALL LETTER PI -0xF1 0x03C1 # GREEK SMALL LETTER RHO -0xF2 0x03C2 # GREEK SMALL LETTER FINAL SIGMA -0xF3 0x03C3 # GREEK SMALL LETTER SIGMA -0xF4 0x03C4 # GREEK SMALL LETTER TAU -0xF5 0x03C5 # GREEK SMALL LETTER UPSILON -0xF6 0x03C6 # GREEK SMALL LETTER PHI -0xF7 0x03C7 # GREEK SMALL LETTER CHI -0xF8 0x03C8 # GREEK SMALL LETTER PSI -0xF9 0x03C9 # GREEK SMALL LETTER OMEGA -0xFA 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA -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 +# 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 8859-7:2003 to Unicode +# Unicode version: 4.0 +# Table version: 3.0 +# Table format: Format A +# Date: 2003-Nov-12 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO 8859-7:2003 characters map into Unicode. +# +# ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928, +# 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) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO 8859-7 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# 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: +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +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 +0xAF 0x2015 # HORIZONTAL BAR +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x0384 # GREEK TONOS +0xB5 0x0385 # GREEK DIALYTIKA TONOS +0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS +0xB9 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS +0xBA 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS +0xBF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS +0xC0 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0xC1 0x0391 # GREEK CAPITAL LETTER ALPHA +0xC2 0x0392 # GREEK CAPITAL LETTER BETA +0xC3 0x0393 # GREEK CAPITAL LETTER GAMMA +0xC4 0x0394 # GREEK CAPITAL LETTER DELTA +0xC5 0x0395 # GREEK CAPITAL LETTER EPSILON +0xC6 0x0396 # GREEK CAPITAL LETTER ZETA +0xC7 0x0397 # GREEK CAPITAL LETTER ETA +0xC8 0x0398 # GREEK CAPITAL LETTER THETA +0xC9 0x0399 # GREEK CAPITAL LETTER IOTA +0xCA 0x039A # GREEK CAPITAL LETTER KAPPA +0xCB 0x039B # GREEK CAPITAL LETTER LAMDA +0xCC 0x039C # GREEK CAPITAL LETTER MU +0xCD 0x039D # GREEK CAPITAL LETTER NU +0xCE 0x039E # GREEK CAPITAL LETTER XI +0xCF 0x039F # GREEK CAPITAL LETTER OMICRON +0xD0 0x03A0 # GREEK CAPITAL LETTER PI +0xD1 0x03A1 # GREEK CAPITAL LETTER RHO +0xD3 0x03A3 # GREEK CAPITAL LETTER SIGMA +0xD4 0x03A4 # GREEK CAPITAL LETTER TAU +0xD5 0x03A5 # GREEK CAPITAL LETTER UPSILON +0xD6 0x03A6 # GREEK CAPITAL LETTER PHI +0xD7 0x03A7 # GREEK CAPITAL LETTER CHI +0xD8 0x03A8 # GREEK CAPITAL LETTER PSI +0xD9 0x03A9 # GREEK CAPITAL LETTER OMEGA +0xDA 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +0xDB 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +0xDC 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS +0xDD 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS +0xDE 0x03AE # GREEK SMALL LETTER ETA WITH TONOS +0xDF 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS +0xE0 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +0xE1 0x03B1 # GREEK SMALL LETTER ALPHA +0xE2 0x03B2 # GREEK SMALL LETTER BETA +0xE3 0x03B3 # GREEK SMALL LETTER GAMMA +0xE4 0x03B4 # GREEK SMALL LETTER DELTA +0xE5 0x03B5 # GREEK SMALL LETTER EPSILON +0xE6 0x03B6 # GREEK SMALL LETTER ZETA +0xE7 0x03B7 # GREEK SMALL LETTER ETA +0xE8 0x03B8 # GREEK SMALL LETTER THETA +0xE9 0x03B9 # GREEK SMALL LETTER IOTA +0xEA 0x03BA # GREEK SMALL LETTER KAPPA +0xEB 0x03BB # GREEK SMALL LETTER LAMDA +0xEC 0x03BC # GREEK SMALL LETTER MU +0xED 0x03BD # GREEK SMALL LETTER NU +0xEE 0x03BE # GREEK SMALL LETTER XI +0xEF 0x03BF # GREEK SMALL LETTER OMICRON +0xF0 0x03C0 # GREEK SMALL LETTER PI +0xF1 0x03C1 # GREEK SMALL LETTER RHO +0xF2 0x03C2 # GREEK SMALL LETTER FINAL SIGMA +0xF3 0x03C3 # GREEK SMALL LETTER SIGMA +0xF4 0x03C4 # GREEK SMALL LETTER TAU +0xF5 0x03C5 # GREEK SMALL LETTER UPSILON +0xF6 0x03C6 # GREEK SMALL LETTER PHI +0xF7 0x03C7 # GREEK SMALL LETTER CHI +0xF8 0x03C8 # GREEK SMALL LETTER PSI +0xF9 0x03C9 # GREEK SMALL LETTER OMEGA +0xFA 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA +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 diff --git a/charsets/8859-8.txt b/charsets/8859-8.txt index 347f567..2005b4c 100644 --- a/charsets/8859-8.txt +++ b/charsets/8859-8.txt @@ -1,42 +1,73 @@ +# 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 8859-8 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO/IEC 8859-8:1999 to Unicode +# Unicode version: 3.0 +# Table version: 2.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Date: 2000-Jan-03 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-8 (1988) characters map into Unicode. +# ISO/IEC 8859-8:1999 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-8 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-8 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 8859-8 order +# The entries are in ISO/IEC 8859-8 order. +# +# 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 +# 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: +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact +# 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 @@ -132,6 +163,39 @@ 0x7C 0x007C # VERTICAL LINE 0x7D 0x007D # RIGHT CURLY BRACKET 0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # 0xA0 0x00A0 # NO-BREAK SPACE 0xA2 0x00A2 # CENT SIGN 0xA3 0x00A3 # POUND SIGN @@ -146,7 +210,7 @@ 0xAC 0x00AC # NOT SIGN 0xAD 0x00AD # SOFT HYPHEN 0xAE 0x00AE # REGISTERED SIGN -0xAF 0x203E # OVERLINE +0xAF 0x00AF # MACRON 0xB0 0x00B0 # DEGREE SIGN 0xB1 0x00B1 # PLUS-MINUS SIGN 0xB2 0x00B2 # SUPERSCRIPT TWO @@ -190,3 +254,6 @@ 0xF8 0x05E8 # HEBREW LETTER RESH 0xF9 0x05E9 # HEBREW LETTER SHIN 0xFA 0x05EA # HEBREW LETTER TAV +0xFD 0x200E # LEFT-TO-RIGHT MARK +0xFE 0x200F # RIGHT-TO-LEFT MARK + diff --git a/charsets/8859-9.txt b/charsets/8859-9.txt index ef994d2..f18db22 100644 --- a/charsets/8859-9.txt +++ b/charsets/8859-9.txt @@ -1,232 +1,296 @@ -# -# Name: ISO 8859-9 (1989) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 -# Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood -# John H. Jenkins -# -# Copyright (c) 1991-1995 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. -# -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. -# -# General notes: -# -# This table contains the data the Unicode Consortium has on how -# ISO 8859-9 (1989) characters map into Unicode. -# -# Format: Three tab-separated columns -# Column #1 is the ISO 8859-9 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 8859-9 order -# -# Any comments or problems, contact -# -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 -0xA0 0x00A0 # NO-BREAK SPACE -0xA1 0x00A1 # INVERTED EXCLAMATION MARK -0xA2 0x00A2 # CENT SIGN -0xA3 0x00A3 # POUND SIGN -0xA4 0x00A4 # CURRENCY SIGN -0xA5 0x00A5 # YEN SIGN -0xA6 0x00A6 # BROKEN BAR -0xA7 0x00A7 # SECTION SIGN -0xA8 0x00A8 # DIAERESIS -0xA9 0x00A9 # COPYRIGHT SIGN -0xAA 0x00AA # FEMININE ORDINAL INDICATOR -0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC # NOT SIGN -0xAD 0x00AD # SOFT HYPHEN -0xAE 0x00AE # REGISTERED SIGN -0xAF 0x00AF # MACRON -0xB0 0x00B0 # DEGREE SIGN -0xB1 0x00B1 # PLUS-MINUS SIGN -0xB2 0x00B2 # SUPERSCRIPT TWO -0xB3 0x00B3 # SUPERSCRIPT THREE -0xB4 0x00B4 # ACUTE ACCENT -0xB5 0x00B5 # MICRO SIGN -0xB6 0x00B6 # PILCROW SIGN -0xB7 0x00B7 # MIDDLE DOT -0xB8 0x00B8 # CEDILLA -0xB9 0x00B9 # SUPERSCRIPT ONE -0xBA 0x00BA # MASCULINE ORDINAL INDICATOR -0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC # VULGAR FRACTION ONE QUARTER -0xBD 0x00BD # VULGAR FRACTION ONE HALF -0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS -0xBF 0x00BF # INVERTED QUESTION MARK -0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE -0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE -0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE -0xC6 0x00C6 # LATIN CAPITAL LETTER AE -0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE -0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX -0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE -0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS -0xD0 0x011E # LATIN CAPITAL LETTER G WITH BREVE -0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE -0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE -0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE -0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 # MULTIPLICATION SIGN -0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE -0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE -0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE -0xDE 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA -0xDF 0x00DF # LATIN SMALL LETTER SHARP S -0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE -0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE -0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE -0xE6 0x00E6 # LATIN SMALL LETTER AE -0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE -0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE -0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX -0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE -0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS -0xF0 0x011F # LATIN SMALL LETTER G WITH BREVE -0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE -0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE -0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE -0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 # DIVISION SIGN -0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE -0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE -0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE -0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX -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 - - +# 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: 2.0 +# Table format: Format A +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-9:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-9 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 8859-9 order. +# +# 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. +# 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x00A1 # INVERTED EXCLAMATION MARK +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00AA # FEMININE ORDINAL INDICATOR +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00BA # MASCULINE ORDINAL INDICATOR +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC # VULGAR FRACTION ONE QUARTER +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF # INVERTED QUESTION MARK +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x011E # LATIN CAPITAL LETTER G WITH BREVE +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE +0xDE 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x011F # LATIN SMALL LETTER G WITH BREVE +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +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 + + diff --git a/charsets/cp1250.txt b/charsets/cp1250.txt index 860ec3c..6bfab93 100644 --- a/charsets/cp1250.txt +++ b/charsets/cp1250.txt @@ -1,274 +1,274 @@ -# -# Name: cp1250 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1250 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1250 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 #UNDEFINED -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 #UNDEFINED -0x89 0x2030 #PER MILLE SIGN -0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE -0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON -0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON -0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 #UNDEFINED -0x99 0x2122 #TRADE MARK SIGN -0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE -0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON -0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON -0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 0x02C7 #CARON -0xA2 0x02D8 #BREVE -0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE -0xA4 0x00A4 #CURRENCY SIGN -0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00A8 #DIAERESIS -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x02DB #OGONEK -0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE -0xB4 0x00B4 #ACUTE ACCENT -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x00B8 #CEDILLA -0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK -0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON -0xBD 0x02DD #DOUBLE ACUTE ACCENT -0xBE 0x013E #LATIN SMALL LETTER L WITH CARON -0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE -0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE -0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE -0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE -0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE -0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON -0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK -0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON -0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON -0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE -0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE -0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON -0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE -0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 #MULTIPLICATION SIGN -0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON -0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE -0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE -0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE -0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA -0xDF 0x00DF #LATIN SMALL LETTER SHARP S -0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE -0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE -0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE -0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE -0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x010D #LATIN SMALL LETTER C WITH CARON -0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE -0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK -0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x011B #LATIN SMALL LETTER E WITH CARON -0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x010F #LATIN SMALL LETTER D WITH CARON -0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE -0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE -0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON -0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE -0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 #DIVISION SIGN -0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON -0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE -0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE -0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE -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 +# +# Name: cp1250 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1250 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1250 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 #UNDEFINED +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON +0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE +0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON +0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON +0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x02C7 #CARON +0xA2 0x02D8 #BREVE +0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x02DB #OGONEK +0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON +0xBD 0x02DD #DOUBLE ACUTE ACCENT +0xBE 0x013E #LATIN SMALL LETTER L WITH CARON +0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE +0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON +0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON +0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE +0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x011B #LATIN SMALL LETTER E WITH CARON +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x010F #LATIN SMALL LETTER D WITH CARON +0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON +0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE +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 diff --git a/charsets/cp1251.txt b/charsets/cp1251.txt index 5189b95..4d9b355 100644 --- a/charsets/cp1251.txt +++ b/charsets/cp1251.txt @@ -1,19 +1,20 @@ # -# Name: cp1251_WinCyrillic to Unicode table +# Name: cp1251 to Unicode table # Unicode version: 2.0 -# Table version: 2.00 +# Table version: 2.01 # Table format: Format A -# Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Date: 04/15/98 +# +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns -# Column #1 is the cp1251_WinCyrillic code (in hex) +# Column #1 is the cp1251 code (in hex) # Column #2 is the Unicode (in hex as 0xXXXX) # Column #3 is the Unicode name (follows a comment sign, '#') # -# The entries are in cp1251_WinCyrillic order +# The entries are in cp1251 order # 0x00 0x0000 #NULL 0x01 0x0001 #START OF HEADING @@ -151,7 +152,7 @@ 0x85 0x2026 #HORIZONTAL ELLIPSIS 0x86 0x2020 #DAGGER 0x87 0x2021 #DOUBLE DAGGER -0x88 #UNDEFINED +0x88 0x20AC #EURO SIGN 0x89 0x2030 #PER MILLE SIGN 0x8A 0x0409 #CYRILLIC CAPITAL LETTER LJE 0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK @@ -167,7 +168,7 @@ 0x95 0x2022 #BULLET 0x96 0x2013 #EN DASH 0x97 0x2014 #EM DASH -0x98 #UNDEFINED +0x98 #UNDEFINED 0x99 0x2122 #TRADE MARK SIGN 0x9A 0x0459 #CYRILLIC SMALL LETTER LJE 0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK @@ -271,4 +272,3 @@ 0xFD 0x044D #CYRILLIC SMALL LETTER E 0xFE 0x044E #CYRILLIC SMALL LETTER YU 0xFF 0x044F #CYRILLIC SMALL LETTER YA - diff --git a/charsets/cp1252.txt b/charsets/cp1252.txt index 066f3c5..8ff4b20 100644 --- a/charsets/cp1252.txt +++ b/charsets/cp1252.txt @@ -1,274 +1,274 @@ -# -# Name: cp1252 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1252 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1252 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT -0x89 0x2030 #PER MILLE SIGN -0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C 0x0152 #LATIN CAPITAL LIGATURE OE -0x8D #UNDEFINED -0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON -0x8F #UNDEFINED -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 0x02DC #SMALL TILDE -0x99 0x2122 #TRADE MARK SIGN -0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C 0x0153 #LATIN SMALL LIGATURE OE -0x9D #UNDEFINED -0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON -0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 0x00A1 #INVERTED EXCLAMATION MARK -0xA2 0x00A2 #CENT SIGN -0xA3 0x00A3 #POUND SIGN -0xA4 0x00A4 #CURRENCY SIGN -0xA5 0x00A5 #YEN SIGN -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00A8 #DIAERESIS -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA 0x00AA #FEMININE ORDINAL INDICATOR -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x00AF #MACRON -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x00B2 #SUPERSCRIPT TWO -0xB3 0x00B3 #SUPERSCRIPT THREE -0xB4 0x00B4 #ACUTE ACCENT -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x00B8 #CEDILLA -0xB9 0x00B9 #SUPERSCRIPT ONE -0xBA 0x00BA #MASCULINE ORDINAL INDICATOR -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC #VULGAR FRACTION ONE QUARTER -0xBD 0x00BD #VULGAR FRACTION ONE HALF -0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS -0xBF 0x00BF #INVERTED QUESTION MARK -0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE -0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE -0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE -0xC6 0x00C6 #LATIN CAPITAL LETTER AE -0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE -0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX -0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE -0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS -0xD0 0x00D0 #LATIN CAPITAL LETTER ETH -0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE -0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE -0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE -0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 #MULTIPLICATION SIGN -0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE -0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE -0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE -0xDE 0x00DE #LATIN CAPITAL LETTER THORN -0xDF 0x00DF #LATIN SMALL LETTER SHARP S -0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE -0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE -0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE -0xE6 0x00E6 #LATIN SMALL LETTER AE -0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE -0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE -0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX -0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE -0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS -0xF0 0x00F0 #LATIN SMALL LETTER ETH -0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE -0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE -0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE -0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 #DIVISION SIGN -0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE -0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE -0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE -0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX -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 +# +# Name: cp1252 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1252 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1252 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D #UNDEFINED +0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D #UNDEFINED +0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON +0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 #LATIN CAPITAL LETTER ETH +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE #LATIN CAPITAL LETTER THORN +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 #LATIN SMALL LETTER ETH +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +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 diff --git a/charsets/cp1253.txt b/charsets/cp1253.txt index 4d05935..20a55b0 100644 --- a/charsets/cp1253.txt +++ b/charsets/cp1253.txt @@ -1,274 +1,274 @@ -# -# Name: cp1253 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1253 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1253 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 #UNDEFINED -0x89 0x2030 #PER MILLE SIGN -0x8A #UNDEFINED -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C #UNDEFINED -0x8D #UNDEFINED -0x8E #UNDEFINED -0x8F #UNDEFINED -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 #UNDEFINED -0x99 0x2122 #TRADE MARK SIGN -0x9A #UNDEFINED -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C #UNDEFINED -0x9D #UNDEFINED -0x9E #UNDEFINED -0x9F #UNDEFINED -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 0x0385 #GREEK DIALYTIKA TONOS -0xA2 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS -0xA3 0x00A3 #POUND SIGN -0xA4 0x00A4 #CURRENCY SIGN -0xA5 0x00A5 #YEN SIGN -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00A8 #DIAERESIS -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA #UNDEFINED -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x2015 #HORIZONTAL BAR -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x00B2 #SUPERSCRIPT TWO -0xB3 0x00B3 #SUPERSCRIPT THREE -0xB4 0x0384 #GREEK TONOS -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS -0xB9 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS -0xBA 0x038A #GREEK CAPITAL LETTER IOTA WITH TONOS -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x038C #GREEK CAPITAL LETTER OMICRON WITH TONOS -0xBD 0x00BD #VULGAR FRACTION ONE HALF -0xBE 0x038E #GREEK CAPITAL LETTER UPSILON WITH TONOS -0xBF 0x038F #GREEK CAPITAL LETTER OMEGA WITH TONOS -0xC0 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS -0xC1 0x0391 #GREEK CAPITAL LETTER ALPHA -0xC2 0x0392 #GREEK CAPITAL LETTER BETA -0xC3 0x0393 #GREEK CAPITAL LETTER GAMMA -0xC4 0x0394 #GREEK CAPITAL LETTER DELTA -0xC5 0x0395 #GREEK CAPITAL LETTER EPSILON -0xC6 0x0396 #GREEK CAPITAL LETTER ZETA -0xC7 0x0397 #GREEK CAPITAL LETTER ETA -0xC8 0x0398 #GREEK CAPITAL LETTER THETA -0xC9 0x0399 #GREEK CAPITAL LETTER IOTA -0xCA 0x039A #GREEK CAPITAL LETTER KAPPA -0xCB 0x039B #GREEK CAPITAL LETTER LAMDA -0xCC 0x039C #GREEK CAPITAL LETTER MU -0xCD 0x039D #GREEK CAPITAL LETTER NU -0xCE 0x039E #GREEK CAPITAL LETTER XI -0xCF 0x039F #GREEK CAPITAL LETTER OMICRON -0xD0 0x03A0 #GREEK CAPITAL LETTER PI -0xD1 0x03A1 #GREEK CAPITAL LETTER RHO -0xD2 #UNDEFINED -0xD3 0x03A3 #GREEK CAPITAL LETTER SIGMA -0xD4 0x03A4 #GREEK CAPITAL LETTER TAU -0xD5 0x03A5 #GREEK CAPITAL LETTER UPSILON -0xD6 0x03A6 #GREEK CAPITAL LETTER PHI -0xD7 0x03A7 #GREEK CAPITAL LETTER CHI -0xD8 0x03A8 #GREEK CAPITAL LETTER PSI -0xD9 0x03A9 #GREEK CAPITAL LETTER OMEGA -0xDA 0x03AA #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA -0xDB 0x03AB #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA -0xDC 0x03AC #GREEK SMALL LETTER ALPHA WITH TONOS -0xDD 0x03AD #GREEK SMALL LETTER EPSILON WITH TONOS -0xDE 0x03AE #GREEK SMALL LETTER ETA WITH TONOS -0xDF 0x03AF #GREEK SMALL LETTER IOTA WITH TONOS -0xE0 0x03B0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS -0xE1 0x03B1 #GREEK SMALL LETTER ALPHA -0xE2 0x03B2 #GREEK SMALL LETTER BETA -0xE3 0x03B3 #GREEK SMALL LETTER GAMMA -0xE4 0x03B4 #GREEK SMALL LETTER DELTA -0xE5 0x03B5 #GREEK SMALL LETTER EPSILON -0xE6 0x03B6 #GREEK SMALL LETTER ZETA -0xE7 0x03B7 #GREEK SMALL LETTER ETA -0xE8 0x03B8 #GREEK SMALL LETTER THETA -0xE9 0x03B9 #GREEK SMALL LETTER IOTA -0xEA 0x03BA #GREEK SMALL LETTER KAPPA -0xEB 0x03BB #GREEK SMALL LETTER LAMDA -0xEC 0x03BC #GREEK SMALL LETTER MU -0xED 0x03BD #GREEK SMALL LETTER NU -0xEE 0x03BE #GREEK SMALL LETTER XI -0xEF 0x03BF #GREEK SMALL LETTER OMICRON -0xF0 0x03C0 #GREEK SMALL LETTER PI -0xF1 0x03C1 #GREEK SMALL LETTER RHO -0xF2 0x03C2 #GREEK SMALL LETTER FINAL SIGMA -0xF3 0x03C3 #GREEK SMALL LETTER SIGMA -0xF4 0x03C4 #GREEK SMALL LETTER TAU -0xF5 0x03C5 #GREEK SMALL LETTER UPSILON -0xF6 0x03C6 #GREEK SMALL LETTER PHI -0xF7 0x03C7 #GREEK SMALL LETTER CHI -0xF8 0x03C8 #GREEK SMALL LETTER PSI -0xF9 0x03C9 #GREEK SMALL LETTER OMEGA -0xFA 0x03CA #GREEK SMALL LETTER IOTA WITH DIALYTIKA -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 -0xFF #UNDEFINED +# +# Name: cp1253 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1253 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1253 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C #UNDEFINED +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C #UNDEFINED +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F #UNDEFINED +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x0385 #GREEK DIALYTIKA TONOS +0xA2 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA #UNDEFINED +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x2015 #HORIZONTAL BAR +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x0384 #GREEK TONOS +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS +0xB9 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS +0xBA 0x038A #GREEK CAPITAL LETTER IOTA WITH TONOS +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x038C #GREEK CAPITAL LETTER OMICRON WITH TONOS +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x038E #GREEK CAPITAL LETTER UPSILON WITH TONOS +0xBF 0x038F #GREEK CAPITAL LETTER OMEGA WITH TONOS +0xC0 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0xC1 0x0391 #GREEK CAPITAL LETTER ALPHA +0xC2 0x0392 #GREEK CAPITAL LETTER BETA +0xC3 0x0393 #GREEK CAPITAL LETTER GAMMA +0xC4 0x0394 #GREEK CAPITAL LETTER DELTA +0xC5 0x0395 #GREEK CAPITAL LETTER EPSILON +0xC6 0x0396 #GREEK CAPITAL LETTER ZETA +0xC7 0x0397 #GREEK CAPITAL LETTER ETA +0xC8 0x0398 #GREEK CAPITAL LETTER THETA +0xC9 0x0399 #GREEK CAPITAL LETTER IOTA +0xCA 0x039A #GREEK CAPITAL LETTER KAPPA +0xCB 0x039B #GREEK CAPITAL LETTER LAMDA +0xCC 0x039C #GREEK CAPITAL LETTER MU +0xCD 0x039D #GREEK CAPITAL LETTER NU +0xCE 0x039E #GREEK CAPITAL LETTER XI +0xCF 0x039F #GREEK CAPITAL LETTER OMICRON +0xD0 0x03A0 #GREEK CAPITAL LETTER PI +0xD1 0x03A1 #GREEK CAPITAL LETTER RHO +0xD2 #UNDEFINED +0xD3 0x03A3 #GREEK CAPITAL LETTER SIGMA +0xD4 0x03A4 #GREEK CAPITAL LETTER TAU +0xD5 0x03A5 #GREEK CAPITAL LETTER UPSILON +0xD6 0x03A6 #GREEK CAPITAL LETTER PHI +0xD7 0x03A7 #GREEK CAPITAL LETTER CHI +0xD8 0x03A8 #GREEK CAPITAL LETTER PSI +0xD9 0x03A9 #GREEK CAPITAL LETTER OMEGA +0xDA 0x03AA #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +0xDB 0x03AB #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +0xDC 0x03AC #GREEK SMALL LETTER ALPHA WITH TONOS +0xDD 0x03AD #GREEK SMALL LETTER EPSILON WITH TONOS +0xDE 0x03AE #GREEK SMALL LETTER ETA WITH TONOS +0xDF 0x03AF #GREEK SMALL LETTER IOTA WITH TONOS +0xE0 0x03B0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +0xE1 0x03B1 #GREEK SMALL LETTER ALPHA +0xE2 0x03B2 #GREEK SMALL LETTER BETA +0xE3 0x03B3 #GREEK SMALL LETTER GAMMA +0xE4 0x03B4 #GREEK SMALL LETTER DELTA +0xE5 0x03B5 #GREEK SMALL LETTER EPSILON +0xE6 0x03B6 #GREEK SMALL LETTER ZETA +0xE7 0x03B7 #GREEK SMALL LETTER ETA +0xE8 0x03B8 #GREEK SMALL LETTER THETA +0xE9 0x03B9 #GREEK SMALL LETTER IOTA +0xEA 0x03BA #GREEK SMALL LETTER KAPPA +0xEB 0x03BB #GREEK SMALL LETTER LAMDA +0xEC 0x03BC #GREEK SMALL LETTER MU +0xED 0x03BD #GREEK SMALL LETTER NU +0xEE 0x03BE #GREEK SMALL LETTER XI +0xEF 0x03BF #GREEK SMALL LETTER OMICRON +0xF0 0x03C0 #GREEK SMALL LETTER PI +0xF1 0x03C1 #GREEK SMALL LETTER RHO +0xF2 0x03C2 #GREEK SMALL LETTER FINAL SIGMA +0xF3 0x03C3 #GREEK SMALL LETTER SIGMA +0xF4 0x03C4 #GREEK SMALL LETTER TAU +0xF5 0x03C5 #GREEK SMALL LETTER UPSILON +0xF6 0x03C6 #GREEK SMALL LETTER PHI +0xF7 0x03C7 #GREEK SMALL LETTER CHI +0xF8 0x03C8 #GREEK SMALL LETTER PSI +0xF9 0x03C9 #GREEK SMALL LETTER OMEGA +0xFA 0x03CA #GREEK SMALL LETTER IOTA WITH DIALYTIKA +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 +0xFF #UNDEFINED diff --git a/charsets/cp1254.txt b/charsets/cp1254.txt index b20bfdf..987ed98 100644 --- a/charsets/cp1254.txt +++ b/charsets/cp1254.txt @@ -1,274 +1,274 @@ -# -# Name: cp1254 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1254 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1254 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT -0x89 0x2030 #PER MILLE SIGN -0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C 0x0152 #LATIN CAPITAL LIGATURE OE -0x8D #UNDEFINED -0x8E #UNDEFINED -0x8F #UNDEFINED -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 0x02DC #SMALL TILDE -0x99 0x2122 #TRADE MARK SIGN -0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C 0x0153 #LATIN SMALL LIGATURE OE -0x9D #UNDEFINED -0x9E #UNDEFINED -0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 0x00A1 #INVERTED EXCLAMATION MARK -0xA2 0x00A2 #CENT SIGN -0xA3 0x00A3 #POUND SIGN -0xA4 0x00A4 #CURRENCY SIGN -0xA5 0x00A5 #YEN SIGN -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00A8 #DIAERESIS -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA 0x00AA #FEMININE ORDINAL INDICATOR -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x00AF #MACRON -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x00B2 #SUPERSCRIPT TWO -0xB3 0x00B3 #SUPERSCRIPT THREE -0xB4 0x00B4 #ACUTE ACCENT -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x00B8 #CEDILLA -0xB9 0x00B9 #SUPERSCRIPT ONE -0xBA 0x00BA #MASCULINE ORDINAL INDICATOR -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC #VULGAR FRACTION ONE QUARTER -0xBD 0x00BD #VULGAR FRACTION ONE HALF -0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS -0xBF 0x00BF #INVERTED QUESTION MARK -0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE -0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE -0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE -0xC6 0x00C6 #LATIN CAPITAL LETTER AE -0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE -0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX -0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE -0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS -0xD0 0x011E #LATIN CAPITAL LETTER G WITH BREVE -0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE -0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE -0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE -0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 #MULTIPLICATION SIGN -0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE -0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE -0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE -0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA -0xDF 0x00DF #LATIN SMALL LETTER SHARP S -0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE -0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE -0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE -0xE6 0x00E6 #LATIN SMALL LETTER AE -0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE -0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE -0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX -0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE -0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS -0xF0 0x011F #LATIN SMALL LETTER G WITH BREVE -0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE -0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE -0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE -0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 #DIVISION SIGN -0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE -0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE -0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE -0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX -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 +# +# Name: cp1254 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1254 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1254 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x011E #LATIN CAPITAL LETTER G WITH BREVE +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE +0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x011F #LATIN SMALL LETTER G WITH BREVE +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +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 diff --git a/charsets/cp1255.txt b/charsets/cp1255.txt index 9feb4e7..585f993 100644 --- a/charsets/cp1255.txt +++ b/charsets/cp1255.txt @@ -1,274 +1,274 @@ -# -# Name: cp1255 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1255 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1255 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT -0x89 0x2030 #PER MILLE SIGN -0x8A #UNDEFINED -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C #UNDEFINED -0x8D #UNDEFINED -0x8E #UNDEFINED -0x8F #UNDEFINED -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 0x02DC #SMALL TILDE -0x99 0x2122 #TRADE MARK SIGN -0x9A #UNDEFINED -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C #UNDEFINED -0x9D #UNDEFINED -0x9E #UNDEFINED -0x9F #UNDEFINED -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 0x00A1 #INVERTED EXCLAMATION MARK -0xA2 0x00A2 #CENT SIGN -0xA3 0x00A3 #POUND SIGN -0xA4 0x20AA #NEW SHEQEL SIGN -0xA5 0x00A5 #YEN SIGN -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00A8 #DIAERESIS -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA 0x00D7 #MULTIPLICATION SIGN -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x00AF #MACRON -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x00B2 #SUPERSCRIPT TWO -0xB3 0x00B3 #SUPERSCRIPT THREE -0xB4 0x00B4 #ACUTE ACCENT -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x00B8 #CEDILLA -0xB9 0x00B9 #SUPERSCRIPT ONE -0xBA 0x00F7 #DIVISION SIGN -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC #VULGAR FRACTION ONE QUARTER -0xBD 0x00BD #VULGAR FRACTION ONE HALF -0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS -0xBF 0x00BF #INVERTED QUESTION MARK -0xC0 0x05B0 #HEBREW POINT SHEVA -0xC1 0x05B1 #HEBREW POINT HATAF SEGOL -0xC2 0x05B2 #HEBREW POINT HATAF PATAH -0xC3 0x05B3 #HEBREW POINT HATAF QAMATS -0xC4 0x05B4 #HEBREW POINT HIRIQ -0xC5 0x05B5 #HEBREW POINT TSERE -0xC6 0x05B6 #HEBREW POINT SEGOL -0xC7 0x05B7 #HEBREW POINT PATAH -0xC8 0x05B8 #HEBREW POINT QAMATS -0xC9 0x05B9 #HEBREW POINT HOLAM -0xCA #UNDEFINED -0xCB 0x05BB #HEBREW POINT QUBUTS -0xCC 0x05BC #HEBREW POINT DAGESH OR MAPIQ -0xCD 0x05BD #HEBREW POINT METEG -0xCE 0x05BE #HEBREW PUNCTUATION MAQAF -0xCF 0x05BF #HEBREW POINT RAFE -0xD0 0x05C0 #HEBREW PUNCTUATION PASEQ -0xD1 0x05C1 #HEBREW POINT SHIN DOT -0xD2 0x05C2 #HEBREW POINT SIN DOT -0xD3 0x05C3 #HEBREW PUNCTUATION SOF PASUQ -0xD4 0x05F0 #HEBREW LIGATURE YIDDISH DOUBLE VAV -0xD5 0x05F1 #HEBREW LIGATURE YIDDISH VAV YOD -0xD6 0x05F2 #HEBREW LIGATURE YIDDISH DOUBLE YOD -0xD7 0x05F3 #HEBREW PUNCTUATION GERESH -0xD8 0x05F4 #HEBREW PUNCTUATION GERSHAYIM -0xD9 #UNDEFINED -0xDA #UNDEFINED -0xDB #UNDEFINED -0xDC #UNDEFINED -0xDD #UNDEFINED -0xDE #UNDEFINED -0xDF #UNDEFINED -0xE0 0x05D0 #HEBREW LETTER ALEF -0xE1 0x05D1 #HEBREW LETTER BET -0xE2 0x05D2 #HEBREW LETTER GIMEL -0xE3 0x05D3 #HEBREW LETTER DALET -0xE4 0x05D4 #HEBREW LETTER HE -0xE5 0x05D5 #HEBREW LETTER VAV -0xE6 0x05D6 #HEBREW LETTER ZAYIN -0xE7 0x05D7 #HEBREW LETTER HET -0xE8 0x05D8 #HEBREW LETTER TET -0xE9 0x05D9 #HEBREW LETTER YOD -0xEA 0x05DA #HEBREW LETTER FINAL KAF -0xEB 0x05DB #HEBREW LETTER KAF -0xEC 0x05DC #HEBREW LETTER LAMED -0xED 0x05DD #HEBREW LETTER FINAL MEM -0xEE 0x05DE #HEBREW LETTER MEM -0xEF 0x05DF #HEBREW LETTER FINAL NUN -0xF0 0x05E0 #HEBREW LETTER NUN -0xF1 0x05E1 #HEBREW LETTER SAMEKH -0xF2 0x05E2 #HEBREW LETTER AYIN -0xF3 0x05E3 #HEBREW LETTER FINAL PE -0xF4 0x05E4 #HEBREW LETTER PE -0xF5 0x05E5 #HEBREW LETTER FINAL TSADI -0xF6 0x05E6 #HEBREW LETTER TSADI -0xF7 0x05E7 #HEBREW LETTER QOF -0xF8 0x05E8 #HEBREW LETTER RESH -0xF9 0x05E9 #HEBREW LETTER SHIN -0xFA 0x05EA #HEBREW LETTER TAV -0xFB #UNDEFINED -0xFC #UNDEFINED -0xFD 0x200E #LEFT-TO-RIGHT MARK -0xFE 0x200F #RIGHT-TO-LEFT MARK -0xFF #UNDEFINED +# +# Name: cp1255 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 1/7/2000 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1255 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1255 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C #UNDEFINED +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C #UNDEFINED +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F #UNDEFINED +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x20AA #NEW SHEQEL SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00D7 #MULTIPLICATION SIGN +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00F7 #DIVISION SIGN +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x05B0 #HEBREW POINT SHEVA +0xC1 0x05B1 #HEBREW POINT HATAF SEGOL +0xC2 0x05B2 #HEBREW POINT HATAF PATAH +0xC3 0x05B3 #HEBREW POINT HATAF QAMATS +0xC4 0x05B4 #HEBREW POINT HIRIQ +0xC5 0x05B5 #HEBREW POINT TSERE +0xC6 0x05B6 #HEBREW POINT SEGOL +0xC7 0x05B7 #HEBREW POINT PATAH +0xC8 0x05B8 #HEBREW POINT QAMATS +0xC9 0x05B9 #HEBREW POINT HOLAM +0xCA #UNDEFINED +0xCB 0x05BB #HEBREW POINT QUBUTS +0xCC 0x05BC #HEBREW POINT DAGESH OR MAPIQ +0xCD 0x05BD #HEBREW POINT METEG +0xCE 0x05BE #HEBREW PUNCTUATION MAQAF +0xCF 0x05BF #HEBREW POINT RAFE +0xD0 0x05C0 #HEBREW PUNCTUATION PASEQ +0xD1 0x05C1 #HEBREW POINT SHIN DOT +0xD2 0x05C2 #HEBREW POINT SIN DOT +0xD3 0x05C3 #HEBREW PUNCTUATION SOF PASUQ +0xD4 0x05F0 #HEBREW LIGATURE YIDDISH DOUBLE VAV +0xD5 0x05F1 #HEBREW LIGATURE YIDDISH VAV YOD +0xD6 0x05F2 #HEBREW LIGATURE YIDDISH DOUBLE YOD +0xD7 0x05F3 #HEBREW PUNCTUATION GERESH +0xD8 0x05F4 #HEBREW PUNCTUATION GERSHAYIM +0xD9 #UNDEFINED +0xDA #UNDEFINED +0xDB #UNDEFINED +0xDC #UNDEFINED +0xDD #UNDEFINED +0xDE #UNDEFINED +0xDF #UNDEFINED +0xE0 0x05D0 #HEBREW LETTER ALEF +0xE1 0x05D1 #HEBREW LETTER BET +0xE2 0x05D2 #HEBREW LETTER GIMEL +0xE3 0x05D3 #HEBREW LETTER DALET +0xE4 0x05D4 #HEBREW LETTER HE +0xE5 0x05D5 #HEBREW LETTER VAV +0xE6 0x05D6 #HEBREW LETTER ZAYIN +0xE7 0x05D7 #HEBREW LETTER HET +0xE8 0x05D8 #HEBREW LETTER TET +0xE9 0x05D9 #HEBREW LETTER YOD +0xEA 0x05DA #HEBREW LETTER FINAL KAF +0xEB 0x05DB #HEBREW LETTER KAF +0xEC 0x05DC #HEBREW LETTER LAMED +0xED 0x05DD #HEBREW LETTER FINAL MEM +0xEE 0x05DE #HEBREW LETTER MEM +0xEF 0x05DF #HEBREW LETTER FINAL NUN +0xF0 0x05E0 #HEBREW LETTER NUN +0xF1 0x05E1 #HEBREW LETTER SAMEKH +0xF2 0x05E2 #HEBREW LETTER AYIN +0xF3 0x05E3 #HEBREW LETTER FINAL PE +0xF4 0x05E4 #HEBREW LETTER PE +0xF5 0x05E5 #HEBREW LETTER FINAL TSADI +0xF6 0x05E6 #HEBREW LETTER TSADI +0xF7 0x05E7 #HEBREW LETTER QOF +0xF8 0x05E8 #HEBREW LETTER RESH +0xF9 0x05E9 #HEBREW LETTER SHIN +0xFA 0x05EA #HEBREW LETTER TAV +0xFB #UNDEFINED +0xFC #UNDEFINED +0xFD 0x200E #LEFT-TO-RIGHT MARK +0xFE 0x200F #RIGHT-TO-LEFT MARK +0xFF #UNDEFINED diff --git a/charsets/cp1256.txt b/charsets/cp1256.txt index 6301e4c..244dcce 100644 --- a/charsets/cp1256.txt +++ b/charsets/cp1256.txt @@ -1,274 +1,274 @@ -# -# Name: cp1256 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1256 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1256 order -# -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 0x20AC #EURO SIGN -0x81 0x067E #ARABIC LETTER PEH -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT -0x89 0x2030 #PER MILLE SIGN -0x8A #UNDEFINED -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C 0x0152 #LATIN CAPITAL LIGATURE OE -0x8D 0x0686 #ARABIC LETTER TCHEH -0x8E 0x0698 #ARABIC LETTER JEH -0x8F #UNDEFINED -0x90 0x06AF #ARABIC LETTER GAF -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 #UNDEFINED -0x99 0x2122 #TRADE MARK SIGN -0x9A #UNDEFINED -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C 0x0153 #LATIN SMALL LIGATURE OE -0x9D 0x200C #ZERO WIDTH NON-JOINER -0x9E 0x200D #ZERO WIDTH JOINER -0x9F #UNDEFINED -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 0x060C #ARABIC COMMA -0xA2 0x00A2 #CENT SIGN -0xA3 0x00A3 #POUND SIGN -0xA4 0x00A4 #CURRENCY SIGN -0xA5 0x00A5 #YEN SIGN -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00A8 #DIAERESIS -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA #UNDEFINED -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x00AF #MACRON -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x00B2 #SUPERSCRIPT TWO -0xB3 0x00B3 #SUPERSCRIPT THREE -0xB4 0x00B4 #ACUTE ACCENT -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x00B8 #CEDILLA -0xB9 0x00B9 #SUPERSCRIPT ONE -0xBA 0x061B #ARABIC SEMICOLON -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC #VULGAR FRACTION ONE QUARTER -0xBD 0x00BD #VULGAR FRACTION ONE HALF -0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS -0xBF 0x061F #ARABIC QUESTION MARK -0xC0 #UNDEFINED -0xC1 0x0621 #ARABIC LETTER HAMZA -0xC2 0x0622 #ARABIC LETTER ALEF WITH MADDA ABOVE -0xC3 0x0623 #ARABIC LETTER ALEF WITH HAMZA ABOVE -0xC4 0x0624 #ARABIC LETTER WAW WITH HAMZA ABOVE -0xC5 0x0625 #ARABIC LETTER ALEF WITH HAMZA BELOW -0xC6 0x0626 #ARABIC LETTER YEH WITH HAMZA ABOVE -0xC7 0x0627 #ARABIC LETTER ALEF -0xC8 0x0628 #ARABIC LETTER BEH -0xC9 0x0629 #ARABIC LETTER TEH MARBUTA -0xCA 0x062A #ARABIC LETTER TEH -0xCB 0x062B #ARABIC LETTER THEH -0xCC 0x062C #ARABIC LETTER JEEM -0xCD 0x062D #ARABIC LETTER HAH -0xCE 0x062E #ARABIC LETTER KHAH -0xCF 0x062F #ARABIC LETTER DAL -0xD0 0x0630 #ARABIC LETTER THAL -0xD1 0x0631 #ARABIC LETTER REH -0xD2 0x0632 #ARABIC LETTER ZAIN -0xD3 0x0633 #ARABIC LETTER SEEN -0xD4 0x0634 #ARABIC LETTER SHEEN -0xD5 0x0635 #ARABIC LETTER SAD -0xD6 0x0636 #ARABIC LETTER DAD -0xD7 0x00D7 #MULTIPLICATION SIGN -0xD8 0x0637 #ARABIC LETTER TAH -0xD9 0x0638 #ARABIC LETTER ZAH -0xDA 0x0639 #ARABIC LETTER AIN -0xDB 0x063A #ARABIC LETTER GHAIN -0xDC 0x0640 #ARABIC TATWEEL -0xDD 0x0641 #ARABIC LETTER FEH -0xDE 0x0642 #ARABIC LETTER QAF -0xDF 0x0643 #ARABIC LETTER KAF -0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE -0xE1 0x0644 #ARABIC LETTER LAM -0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x0645 #ARABIC LETTER MEEM -0xE4 0x0646 #ARABIC LETTER NOON -0xE5 0x0647 #ARABIC LETTER HEH -0xE6 0x0648 #ARABIC LETTER WAW -0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE -0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE -0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX -0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x0649 #ARABIC LETTER ALEF MAKSURA -0xED 0x064A #ARABIC LETTER YEH -0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS -0xF0 0x064B #ARABIC FATHATAN -0xF1 0x064C #ARABIC DAMMATAN -0xF2 0x064D #ARABIC KASRATAN -0xF3 0x064E #ARABIC FATHA -0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x064F #ARABIC DAMMA -0xF6 0x0650 #ARABIC KASRA -0xF7 0x00F7 #DIVISION SIGN -0xF8 0x0651 #ARABIC SHADDA -0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE -0xFA 0x0652 #ARABIC SUKUN -0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX -0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS -0xFD 0x200E #LEFT-TO-RIGHT MARK -0xFE 0x200F #RIGHT-TO-LEFT MARK -0xFF #UNDEFINED +# +# Name: cp1256 to Unicode table +# Unicode version: 2.1 +# Table version: 2.01 +# Table format: Format A +# Date: 01/5/99 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1256 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1256 order +# +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 0x20AC #EURO SIGN +0x81 0x067E #ARABIC LETTER PEH +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0679 #ARABIC LETTER TTEH +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D 0x0686 #ARABIC LETTER TCHEH +0x8E 0x0698 #ARABIC LETTER JEH +0x8F 0x0688 #ARABIC LETTER DDAL +0x90 0x06AF #ARABIC LETTER GAF +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x06A9 #ARABIC LETTER KEHEH +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0691 #ARABIC LETTER RREH +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D 0x200C #ZERO WIDTH NON-JOINER +0x9E 0x200D #ZERO WIDTH JOINER +0x9F 0x06BA #ARABIC LETTER NOON GHUNNA +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x060C #ARABIC COMMA +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x06BE #ARABIC LETTER HEH DOACHASHMEE +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x061B #ARABIC SEMICOLON +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x061F #ARABIC QUESTION MARK +0xC0 0x06C1 #ARABIC LETTER HEH GOAL +0xC1 0x0621 #ARABIC LETTER HAMZA +0xC2 0x0622 #ARABIC LETTER ALEF WITH MADDA ABOVE +0xC3 0x0623 #ARABIC LETTER ALEF WITH HAMZA ABOVE +0xC4 0x0624 #ARABIC LETTER WAW WITH HAMZA ABOVE +0xC5 0x0625 #ARABIC LETTER ALEF WITH HAMZA BELOW +0xC6 0x0626 #ARABIC LETTER YEH WITH HAMZA ABOVE +0xC7 0x0627 #ARABIC LETTER ALEF +0xC8 0x0628 #ARABIC LETTER BEH +0xC9 0x0629 #ARABIC LETTER TEH MARBUTA +0xCA 0x062A #ARABIC LETTER TEH +0xCB 0x062B #ARABIC LETTER THEH +0xCC 0x062C #ARABIC LETTER JEEM +0xCD 0x062D #ARABIC LETTER HAH +0xCE 0x062E #ARABIC LETTER KHAH +0xCF 0x062F #ARABIC LETTER DAL +0xD0 0x0630 #ARABIC LETTER THAL +0xD1 0x0631 #ARABIC LETTER REH +0xD2 0x0632 #ARABIC LETTER ZAIN +0xD3 0x0633 #ARABIC LETTER SEEN +0xD4 0x0634 #ARABIC LETTER SHEEN +0xD5 0x0635 #ARABIC LETTER SAD +0xD6 0x0636 #ARABIC LETTER DAD +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0637 #ARABIC LETTER TAH +0xD9 0x0638 #ARABIC LETTER ZAH +0xDA 0x0639 #ARABIC LETTER AIN +0xDB 0x063A #ARABIC LETTER GHAIN +0xDC 0x0640 #ARABIC TATWEEL +0xDD 0x0641 #ARABIC LETTER FEH +0xDE 0x0642 #ARABIC LETTER QAF +0xDF 0x0643 #ARABIC LETTER KAF +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x0644 #ARABIC LETTER LAM +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0645 #ARABIC LETTER MEEM +0xE4 0x0646 #ARABIC LETTER NOON +0xE5 0x0647 #ARABIC LETTER HEH +0xE6 0x0648 #ARABIC LETTER WAW +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0649 #ARABIC LETTER ALEF MAKSURA +0xED 0x064A #ARABIC LETTER YEH +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x064B #ARABIC FATHATAN +0xF1 0x064C #ARABIC DAMMATAN +0xF2 0x064D #ARABIC KASRATAN +0xF3 0x064E #ARABIC FATHA +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x064F #ARABIC DAMMA +0xF6 0x0650 #ARABIC KASRA +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0651 #ARABIC SHADDA +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x0652 #ARABIC SUKUN +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +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 diff --git a/charsets/cp1257.txt b/charsets/cp1257.txt index ca5f9a9..0dc475e 100644 --- a/charsets/cp1257.txt +++ b/charsets/cp1257.txt @@ -1,274 +1,274 @@ -# -# Name: cp1257 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1257 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1257 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 #UNDEFINED -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 #UNDEFINED -0x89 0x2030 #PER MILLE SIGN -0x8A #UNDEFINED -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C #UNDEFINED -0x8D 0x00A8 #DIAERESIS -0x8E 0x02C7 #CARON -0x8F 0x00B8 #CEDILLA -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 #UNDEFINED -0x99 0x2122 #TRADE MARK SIGN -0x9A #UNDEFINED -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C #UNDEFINED -0x9D 0x00AF #MACRON -0x9E 0x02DB #OGONEK -0x9F #UNDEFINED -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 #UNDEFINED -0xA2 0x00A2 #CENT SIGN -0xA3 0x00A3 #POUND SIGN -0xA4 0x00A4 #CURRENCY SIGN -0xA5 #UNDEFINED -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x00C6 #LATIN CAPITAL LETTER AE -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x00B2 #SUPERSCRIPT TWO -0xB3 0x00B3 #SUPERSCRIPT THREE -0xB4 0x00B4 #ACUTE ACCENT -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x00F8 #LATIN SMALL LETTER O WITH STROKE -0xB9 0x00B9 #SUPERSCRIPT ONE -0xBA 0x0157 #LATIN SMALL LETTER R WITH CEDILLA -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC #VULGAR FRACTION ONE QUARTER -0xBD 0x00BD #VULGAR FRACTION ONE HALF -0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS -0xBF 0x00E6 #LATIN SMALL LETTER AE -0xC0 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK -0xC1 0x012E #LATIN CAPITAL LETTER I WITH OGONEK -0xC2 0x0100 #LATIN CAPITAL LETTER A WITH MACRON -0xC3 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE -0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE -0xC6 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK -0xC7 0x0112 #LATIN CAPITAL LETTER E WITH MACRON -0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON -0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE -0xCB 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE -0xCC 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA -0xCD 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA -0xCE 0x012A #LATIN CAPITAL LETTER I WITH MACRON -0xCF 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA -0xD0 0x0160 #LATIN CAPITAL LETTER S WITH CARON -0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE -0xD2 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA -0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x014C #LATIN CAPITAL LETTER O WITH MACRON -0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE -0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 #MULTIPLICATION SIGN -0xD8 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK -0xD9 0x0141 #LATIN CAPITAL LETTER L WITH STROKE -0xDA 0x015A #LATIN CAPITAL LETTER S WITH ACUTE -0xDB 0x016A #LATIN CAPITAL LETTER U WITH MACRON -0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE -0xDE 0x017D #LATIN CAPITAL LETTER Z WITH CARON -0xDF 0x00DF #LATIN SMALL LETTER SHARP S -0xE0 0x0105 #LATIN SMALL LETTER A WITH OGONEK -0xE1 0x012F #LATIN SMALL LETTER I WITH OGONEK -0xE2 0x0101 #LATIN SMALL LETTER A WITH MACRON -0xE3 0x0107 #LATIN SMALL LETTER C WITH ACUTE -0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE -0xE6 0x0119 #LATIN SMALL LETTER E WITH OGONEK -0xE7 0x0113 #LATIN SMALL LETTER E WITH MACRON -0xE8 0x010D #LATIN SMALL LETTER C WITH CARON -0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE -0xEA 0x017A #LATIN SMALL LETTER Z WITH ACUTE -0xEB 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE -0xEC 0x0123 #LATIN SMALL LETTER G WITH CEDILLA -0xED 0x0137 #LATIN SMALL LETTER K WITH CEDILLA -0xEE 0x012B #LATIN SMALL LETTER I WITH MACRON -0xEF 0x013C #LATIN SMALL LETTER L WITH CEDILLA -0xF0 0x0161 #LATIN SMALL LETTER S WITH CARON -0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE -0xF2 0x0146 #LATIN SMALL LETTER N WITH CEDILLA -0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE -0xF4 0x014D #LATIN SMALL LETTER O WITH MACRON -0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE -0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 #DIVISION SIGN -0xF8 0x0173 #LATIN SMALL LETTER U WITH OGONEK -0xF9 0x0142 #LATIN SMALL LETTER L WITH STROKE -0xFA 0x015B #LATIN SMALL LETTER S WITH ACUTE -0xFB 0x016B #LATIN SMALL LETTER U WITH MACRON -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 +# +# Name: cp1257 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1257 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1257 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 #UNDEFINED +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C #UNDEFINED +0x8D 0x00A8 #DIAERESIS +0x8E 0x02C7 #CARON +0x8F 0x00B8 #CEDILLA +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C #UNDEFINED +0x9D 0x00AF #MACRON +0x9E 0x02DB #OGONEK +0x9F #UNDEFINED +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 #UNDEFINED +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 #UNDEFINED +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00C6 #LATIN CAPITAL LETTER AE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x0157 #LATIN SMALL LETTER R WITH CEDILLA +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00E6 #LATIN SMALL LETTER AE +0xC0 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xC1 0x012E #LATIN CAPITAL LETTER I WITH OGONEK +0xC2 0x0100 #LATIN CAPITAL LETTER A WITH MACRON +0xC3 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xC7 0x0112 #LATIN CAPITAL LETTER E WITH MACRON +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0xCB 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCC 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA +0xCD 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA +0xCE 0x012A #LATIN CAPITAL LETTER I WITH MACRON +0xCF 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA +0xD0 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x014C #LATIN CAPITAL LETTER O WITH MACRON +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK +0xD9 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xDA 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0xDB 0x016A #LATIN CAPITAL LETTER U WITH MACRON +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xDE 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xE1 0x012F #LATIN SMALL LETTER I WITH OGONEK +0xE2 0x0101 #LATIN SMALL LETTER A WITH MACRON +0xE3 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xE7 0x0113 #LATIN SMALL LETTER E WITH MACRON +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xEB 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE +0xEC 0x0123 #LATIN SMALL LETTER G WITH CEDILLA +0xED 0x0137 #LATIN SMALL LETTER K WITH CEDILLA +0xEE 0x012B #LATIN SMALL LETTER I WITH MACRON +0xEF 0x013C #LATIN SMALL LETTER L WITH CEDILLA +0xF0 0x0161 #LATIN SMALL LETTER S WITH CARON +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0146 #LATIN SMALL LETTER N WITH CEDILLA +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x014D #LATIN SMALL LETTER O WITH MACRON +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0173 #LATIN SMALL LETTER U WITH OGONEK +0xF9 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xFA 0x015B #LATIN SMALL LETTER S WITH ACUTE +0xFB 0x016B #LATIN SMALL LETTER U WITH MACRON +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 diff --git a/charsets/cp1258.txt b/charsets/cp1258.txt index 8841b64..f402b34 100644 --- a/charsets/cp1258.txt +++ b/charsets/cp1258.txt @@ -1,274 +1,274 @@ -# -# Name: cp1258 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp1258 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp1258 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 0x201A #SINGLE LOW-9 QUOTATION MARK -0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK -0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 0x2020 #DAGGER -0x87 0x2021 #DOUBLE DAGGER -0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT -0x89 0x2030 #PER MILLE SIGN -0x8A #UNDEFINED -0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0x8C 0x0152 #LATIN CAPITAL LIGATURE OE -0x8D #UNDEFINED -0x8E #UNDEFINED -0x8F #UNDEFINED -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 0x02DC #SMALL TILDE -0x99 0x2122 #TRADE MARK SIGN -0x9A #UNDEFINED -0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0x9C 0x0153 #LATIN SMALL LIGATURE OE -0x9D #UNDEFINED -0x9E #UNDEFINED -0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS -0xA0 0x00A0 #NO-BREAK SPACE -0xA1 0x00A1 #INVERTED EXCLAMATION MARK -0xA2 0x00A2 #CENT SIGN -0xA3 0x00A3 #POUND SIGN -0xA4 0x00A4 #CURRENCY SIGN -0xA5 0x00A5 #YEN SIGN -0xA6 0x00A6 #BROKEN BAR -0xA7 0x00A7 #SECTION SIGN -0xA8 0x00A8 #DIAERESIS -0xA9 0x00A9 #COPYRIGHT SIGN -0xAA 0x00AA #FEMININE ORDINAL INDICATOR -0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xAC 0x00AC #NOT SIGN -0xAD 0x00AD #SOFT HYPHEN -0xAE 0x00AE #REGISTERED SIGN -0xAF 0x00AF #MACRON -0xB0 0x00B0 #DEGREE SIGN -0xB1 0x00B1 #PLUS-MINUS SIGN -0xB2 0x00B2 #SUPERSCRIPT TWO -0xB3 0x00B3 #SUPERSCRIPT THREE -0xB4 0x00B4 #ACUTE ACCENT -0xB5 0x00B5 #MICRO SIGN -0xB6 0x00B6 #PILCROW SIGN -0xB7 0x00B7 #MIDDLE DOT -0xB8 0x00B8 #CEDILLA -0xB9 0x00B9 #SUPERSCRIPT ONE -0xBA 0x00BA #MASCULINE ORDINAL INDICATOR -0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xBC 0x00BC #VULGAR FRACTION ONE QUARTER -0xBD 0x00BD #VULGAR FRACTION ONE HALF -0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS -0xBF 0x00BF #INVERTED QUESTION MARK -0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE -0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE -0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE -0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS -0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE -0xC6 0x00C6 #LATIN CAPITAL LETTER AE -0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA -0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE -0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE -0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX -0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS -0xCC 0x0300 #COMBINING GRAVE ACCENT -0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE -0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS -0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE -0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE -0xD2 0x0309 #COMBINING HOOK ABOVE -0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE -0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xD5 0x01A0 #LATIN CAPITAL LETTER O WITH HORN -0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS -0xD7 0x00D7 #MULTIPLICATION SIGN -0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE -0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE -0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE -0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS -0xDD 0x01AF #LATIN CAPITAL LETTER U WITH HORN -0xDE 0x0303 #COMBINING TILDE -0xDF 0x00DF #LATIN SMALL LETTER SHARP S -0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE -0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE -0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX -0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE -0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS -0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE -0xE6 0x00E6 #LATIN SMALL LETTER AE -0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA -0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE -0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE -0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX -0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS -0xEC 0x0301 #COMBINING ACUTE ACCENT -0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE -0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX -0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS -0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE -0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE -0xF2 0x0323 #COMBINING DOT BELOW -0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE -0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX -0xF5 0x01A1 #LATIN SMALL LETTER O WITH HORN -0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS -0xF7 0x00F7 #DIVISION SIGN -0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE -0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE -0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE -0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX -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 +# +# Name: cp1258 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1258 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1258 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x0300 #COMBINING GRAVE ACCENT +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x0309 #COMBINING HOOK ABOVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x01A0 #LATIN CAPITAL LETTER O WITH HORN +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x01AF #LATIN CAPITAL LETTER U WITH HORN +0xDE 0x0303 #COMBINING TILDE +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0301 #COMBINING ACUTE ACCENT +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x0323 #COMBINING DOT BELOW +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x01A1 #LATIN SMALL LETTER O WITH HORN +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +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 diff --git a/charsets/cp437.txt b/charsets/cp437.txt index 479076f..8f74def 100644 --- a/charsets/cp437.txt +++ b/charsets/cp437.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp850.txt b/charsets/cp850.txt index 312e439..ef47b43 100644 --- a/charsets/cp850.txt +++ b/charsets/cp850.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp852.txt b/charsets/cp852.txt index bae9e7a..c5f3564 100644 --- a/charsets/cp852.txt +++ b/charsets/cp852.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp855.txt b/charsets/cp855.txt index af0168d..42063d8 100644 --- a/charsets/cp855.txt +++ b/charsets/cp855.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp857.txt b/charsets/cp857.txt index 7dde69f..5995085 100644 --- a/charsets/cp857.txt +++ b/charsets/cp857.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp860.txt b/charsets/cp860.txt index ce36f21..64e9378 100644 --- a/charsets/cp860.txt +++ b/charsets/cp860.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp861.txt b/charsets/cp861.txt index 5a50e4e..163b0b1 100644 --- a/charsets/cp861.txt +++ b/charsets/cp861.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp862.txt b/charsets/cp862.txt index 5a4f019..d33547a 100644 --- a/charsets/cp862.txt +++ b/charsets/cp862.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp863.txt b/charsets/cp863.txt index 115afbd..19f3e8b 100644 --- a/charsets/cp863.txt +++ b/charsets/cp863.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp864.txt b/charsets/cp864.txt index 4cf3394..d0079b0 100644 --- a/charsets/cp864.txt +++ b/charsets/cp864.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp865.txt b/charsets/cp865.txt index 38f5ce0..41d73da 100644 --- a/charsets/cp865.txt +++ b/charsets/cp865.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp866.txt b/charsets/cp866.txt index 25b831a..b0213a1 100644 --- a/charsets/cp866.txt +++ b/charsets/cp866.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp869.txt b/charsets/cp869.txt index 691ef97..3cd3f77 100644 --- a/charsets/cp869.txt +++ b/charsets/cp869.txt @@ -4,8 +4,8 @@ # Table version: 2.00 # Table format: Format A # Date: 04/24/96 -# Authors: Lori Brownell -# K.D. Chang +# Contact: Shawn.Steele@microsoft.com +# # General notes: none # # Format: Three tab-separated columns diff --git a/charsets/cp874.txt b/charsets/cp874.txt index 18eb2bc..0ab6504 100644 --- a/charsets/cp874.txt +++ b/charsets/cp874.txt @@ -1,274 +1,274 @@ -# -# Name: cp874 to Unicode table -# Unicode version: 2.0 -# Table version: 2.00 -# Table format: Format A -# Date: 04/15/98 -# -# Contact: cpxlate@microsoft.com -# -# General notes: none -# -# Format: Three tab-separated columns -# Column #1 is the cp874 code (in hex) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 is the Unicode name (follows a comment sign, '#') -# -# The entries are in cp874 order -# -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 0x20AC #EURO SIGN -0x81 #UNDEFINED -0x82 #UNDEFINED -0x83 #UNDEFINED -0x84 #UNDEFINED -0x85 0x2026 #HORIZONTAL ELLIPSIS -0x86 #UNDEFINED -0x87 #UNDEFINED -0x88 #UNDEFINED -0x89 #UNDEFINED -0x8A #UNDEFINED -0x8B #UNDEFINED -0x8C #UNDEFINED -0x8D #UNDEFINED -0x8E #UNDEFINED -0x8F #UNDEFINED -0x90 #UNDEFINED -0x91 0x2018 #LEFT SINGLE QUOTATION MARK -0x92 0x2019 #RIGHT SINGLE QUOTATION MARK -0x93 0x201C #LEFT DOUBLE QUOTATION MARK -0x94 0x201D #RIGHT DOUBLE QUOTATION MARK -0x95 0x2022 #BULLET -0x96 0x2013 #EN DASH -0x97 0x2014 #EM DASH -0x98 #UNDEFINED -0x99 #UNDEFINED -0x9A #UNDEFINED -0x9B #UNDEFINED -0x9C #UNDEFINED -0x9D #UNDEFINED -0x9E #UNDEFINED -0x9F #UNDEFINED -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 -0xDB #UNDEFINED -0xDC #UNDEFINED -0xDD #UNDEFINED -0xDE #UNDEFINED -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 -0xFC #UNDEFINED -0xFD #UNDEFINED -0xFE #UNDEFINED -0xFF #UNDEFINED +# +# Name: cp874 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 02/28/98 +# +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp874 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp874 order +# +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 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 #UNDEFINED +0x83 #UNDEFINED +0x84 #UNDEFINED +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 #UNDEFINED +0x87 #UNDEFINED +0x88 #UNDEFINED +0x89 #UNDEFINED +0x8A #UNDEFINED +0x8B #UNDEFINED +0x8C #UNDEFINED +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 #UNDEFINED +0x9A #UNDEFINED +0x9B #UNDEFINED +0x9C #UNDEFINED +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F #UNDEFINED +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 +0xDB #UNDEFINED +0xDC #UNDEFINED +0xDD #UNDEFINED +0xDE #UNDEFINED +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 +0xFC #UNDEFINED +0xFD #UNDEFINED +0xFE #UNDEFINED +0xFF #UNDEFINED diff --git a/charsets/koi8-r.txt b/charsets/koi8-r.txt index 94fffd8..2a1afb7 100644 --- a/charsets/koi8-r.txt +++ b/charsets/koi8-r.txt @@ -1,257 +1,294 @@ -# Koi8 to unicode translation (from rfc1489) -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 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL -0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL -0x82 0x250c # BOX DRAWINGS LIGHT DOWN AND RIGHT -0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT -0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT -0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT -0x86 0x251c # BOX DRAWINGS LIGHT VERTICAL AND RIGHT -0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT -0x88 0x252c # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL -0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL -0x8a 0x253c # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL -0x8b 0x2580 # UPPER HALF BLOCK -0x8c 0x2584 # LOWER HALF BLOCK -0x8d 0x2588 # FULL BLOCK -0x8e 0x258c # LEFT HALF BLOCK -0x8f 0x2590 # RIGHT HALF BLOCK -0x90 0x2591 # LIGHT SHADE -0x91 0x2592 # MEDIUM SHADE -0x92 0x2593 # DARK SHADE -0x93 0x2320 # UPPER HALF OF INTEGRAL -0x94 0x25a0 # BLACK SQUARE -0x95 0x2219 # BULLET OPERATOR -0x96 0x221a # SQUARE ROOT -0x97 0x2248 # ALMOST EQUAL TO -0x98 0x2264 # LESS-THAN OR EQUAL TO -0x99 0x2265 # GREATER-THAN OR EQUAL TO -0x9a 0x00a0 # NO-BREAK SPACE -0x9b 0x2321 # LOWER HALF OF INTEGRAL -0x9c 0x00b0 # DEGREE SIGN -0x9d 0x00b2 # SUPERSCRIPT TWO -0x9e 0x00b7 # MIDDLE DOT -0x9f 0x00f7 # DIVISION SIGN -0xa0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL -0xa1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL -0xa2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE -0xa3 0x0451 # CYRILLIC SMALL LETTER IO -0xa4 0x2553 # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE -0xa5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT -0xa6 0x2555 # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE -0xa7 0x2556 # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE -0xa8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT -0xa9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE -0xaa 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE -0xab 0x255a # BOX DRAWINGS DOUBLE UP AND RIGHT -0xac 0x255b # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE -0xad 0x255c # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE -0xae 0x255d # BOX DRAWINGS DOUBLE UP AND LEFT -0xaf 0x255e # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE -0xb0 0x255f # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE -0xb1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT -0xb2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE -0xb3 0x0401 # CYRILLIC CAPITAL LETTER IO -0xb4 0x2562 # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE -0xb5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT -0xb6 0x2564 # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE -0xb7 0x2565 # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE -0xb8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL -0xb9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE -0xba 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE -0xbb 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL -0xbc 0x256a # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE -0xbd 0x256b # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE -0xbe 0x256c # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL -0xbf 0x00a9 # COPYRIGHT SIGN -0xc0 0x044e # CYRILLIC SMALL LETTER YU -0xc1 0x0430 # CYRILLIC SMALL LETTER A -0xc2 0x0431 # CYRILLIC SMALL LETTER BE -0xc3 0x0446 # CYRILLIC SMALL LETTER TSE -0xc4 0x0434 # CYRILLIC SMALL LETTER DE -0xc5 0x0435 # CYRILLIC SMALL LETTER IE -0xc6 0x0444 # CYRILLIC SMALL LETTER EF -0xc7 0x0433 # CYRILLIC SMALL LETTER GHE -0xc8 0x0445 # CYRILLIC SMALL LETTER HA -0xc9 0x0438 # CYRILLIC SMALL LETTER I -0xca 0x0439 # CYRILLIC SMALL LETTER SHORT I -0xcb 0x043a # CYRILLIC SMALL LETTER KA -0xcc 0x043b # CYRILLIC SMALL LETTER EL -0xcd 0x043c # CYRILLIC SMALL LETTER EM -0xce 0x043d # CYRILLIC SMALL LETTER EN -0xcf 0x043e # CYRILLIC SMALL LETTER O -0xd0 0x043f # CYRILLIC SMALL LETTER PE -0xd1 0x044f # CYRILLIC SMALL LETTER YA -0xd2 0x0440 # CYRILLIC SMALL LETTER ER -0xd3 0x0441 # CYRILLIC SMALL LETTER ES -0xd4 0x0442 # CYRILLIC SMALL LETTER TE -0xd5 0x0443 # CYRILLIC SMALL LETTER U -0xd6 0x0436 # CYRILLIC SMALL LETTER ZHE -0xd7 0x0432 # CYRILLIC SMALL LETTER VE -0xd8 0x044c # CYRILLIC SMALL LETTER SOFT SIGN -0xd9 0x044b # CYRILLIC SMALL LETTER YERU -0xda 0x0437 # CYRILLIC SMALL LETTER ZE -0xdb 0x0448 # CYRILLIC SMALL LETTER SHA -0xdc 0x044d # CYRILLIC SMALL LETTER E -0xdd 0x0449 # CYRILLIC SMALL LETTER SHCHA -0xde 0x0447 # CYRILLIC SMALL LETTER CHE -0xdf 0x044a # CYRILLIC SMALL LETTER HARD SIGN -0xe0 0x042e # CYRILLIC CAPITAL LETTER YU -0xe1 0x0410 # CYRILLIC CAPITAL LETTER A -0xe2 0x0411 # CYRILLIC CAPITAL LETTER BE -0xe3 0x0426 # CYRILLIC CAPITAL LETTER TSE -0xe4 0x0414 # CYRILLIC CAPITAL LETTER DE -0xe5 0x0415 # CYRILLIC CAPITAL LETTER IE -0xe6 0x0424 # CYRILLIC CAPITAL LETTER EF -0xe7 0x0413 # CYRILLIC CAPITAL LETTER GHE -0xe8 0x0425 # CYRILLIC CAPITAL LETTER HA -0xe9 0x0418 # CYRILLIC CAPITAL LETTER I -0xea 0x0419 # CYRILLIC CAPITAL LETTER SHORT I -0xeb 0x041a # CYRILLIC CAPITAL LETTER KA -0xec 0x041b # CYRILLIC CAPITAL LETTER EL -0xed 0x041c # CYRILLIC CAPITAL LETTER EM -0xee 0x041d # CYRILLIC CAPITAL LETTER EN -0xef 0x041e # CYRILLIC CAPITAL LETTER O -0xf0 0x041f # CYRILLIC CAPITAL LETTER PE -0xf1 0x042f # CYRILLIC CAPITAL LETTER YA -0xf2 0x0420 # CYRILLIC CAPITAL LETTER ER -0xf3 0x0421 # CYRILLIC CAPITAL LETTER ES -0xf4 0x0422 # CYRILLIC CAPITAL LETTER TE -0xf5 0x0423 # CYRILLIC CAPITAL LETTER U -0xf6 0x0416 # CYRILLIC CAPITAL LETTER ZHE -0xf7 0x0412 # CYRILLIC CAPITAL LETTER VE -0xf8 0x042c # CYRILLIC CAPITAL LETTER SOFT SIGN -0xf9 0x042b # CYRILLIC CAPITAL LETTER YERU -0xfa 0x0417 # CYRILLIC CAPITAL LETTER ZE -0xfb 0x0428 # CYRILLIC CAPITAL LETTER SHA -0xfc 0x042d # CYRILLIC CAPITAL LETTER E -0xfd 0x0429 # CYRILLIC CAPITAL LETTER SHCHA -0xfe 0x0427 # CYRILLIC CAPITAL LETTER CHE -0xff 0x042a # CYRILLIC CAPITAL LETTER HARD SIGN +# KOI8-R.TXT +# Date: 2016-01-04 23:05:00 GMT [KW] +# © 2016 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Name: KOI8-R (RFC1489) to Unicode +# Unicode version: 3.0 +# Table version: 2.0 +# Table format: Format A +# Date: 18 August 1999 (header updated: 2016-January-04) +# Authors: Helmut Richter +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# KOI8-R characters map into Unicode. The underlying document is the +# mapping described in RFC 1489. No statements are made as to whether +# this mapping is the same as the mapping defined as "Code Page 878" +# with some vendors. +# +# Format: Three tab-separated columns +# Column #1 is the KOI8-R 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 KOI8-R 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: +# 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 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL +0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL +0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT +0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT +0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT +0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT +0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT +0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL +0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0x8B 0x2580 # UPPER HALF BLOCK +0x8C 0x2584 # LOWER HALF BLOCK +0x8D 0x2588 # FULL BLOCK +0x8E 0x258C # LEFT HALF BLOCK +0x8F 0x2590 # RIGHT HALF BLOCK +0x90 0x2591 # LIGHT SHADE +0x91 0x2592 # MEDIUM SHADE +0x92 0x2593 # DARK SHADE +0x93 0x2320 # TOP HALF INTEGRAL +0x94 0x25A0 # BLACK SQUARE +0x95 0x2219 # BULLET OPERATOR +0x96 0x221A # SQUARE ROOT +0x97 0x2248 # ALMOST EQUAL TO +0x98 0x2264 # LESS-THAN OR EQUAL TO +0x99 0x2265 # GREATER-THAN OR EQUAL TO +0x9A 0x00A0 # NO-BREAK SPACE +0x9B 0x2321 # BOTTOM HALF INTEGRAL +0x9C 0x00B0 # DEGREE SIGN +0x9D 0x00B2 # SUPERSCRIPT TWO +0x9E 0x00B7 # MIDDLE DOT +0x9F 0x00F7 # DIVISION SIGN +0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL +0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL +0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xA3 0x0451 # CYRILLIC SMALL LETTER IO +0xA4 0x2553 # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xA6 0x2555 # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xA7 0x2556 # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT +0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT +0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xAD 0x255C # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT +0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO +0xB4 0x2562 # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xB6 0x2564 # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xB7 0x2565 # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xBD 0x256B # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xBF 0x00A9 # COPYRIGHT SIGN +0xC0 0x044E # CYRILLIC SMALL LETTER YU +0xC1 0x0430 # CYRILLIC SMALL LETTER A +0xC2 0x0431 # CYRILLIC SMALL LETTER BE +0xC3 0x0446 # CYRILLIC SMALL LETTER TSE +0xC4 0x0434 # CYRILLIC SMALL LETTER DE +0xC5 0x0435 # CYRILLIC SMALL LETTER IE +0xC6 0x0444 # CYRILLIC SMALL LETTER EF +0xC7 0x0433 # CYRILLIC SMALL LETTER GHE +0xC8 0x0445 # CYRILLIC SMALL LETTER HA +0xC9 0x0438 # CYRILLIC SMALL LETTER I +0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xCB 0x043A # CYRILLIC SMALL LETTER KA +0xCC 0x043B # CYRILLIC SMALL LETTER EL +0xCD 0x043C # CYRILLIC SMALL LETTER EM +0xCE 0x043D # CYRILLIC SMALL LETTER EN +0xCF 0x043E # CYRILLIC SMALL LETTER O +0xD0 0x043F # CYRILLIC SMALL LETTER PE +0xD1 0x044F # CYRILLIC SMALL LETTER YA +0xD2 0x0440 # CYRILLIC SMALL LETTER ER +0xD3 0x0441 # CYRILLIC SMALL LETTER ES +0xD4 0x0442 # CYRILLIC SMALL LETTER TE +0xD5 0x0443 # CYRILLIC SMALL LETTER U +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0432 # CYRILLIC SMALL LETTER VE +0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xD9 0x044B # CYRILLIC SMALL LETTER YERU +0xDA 0x0437 # CYRILLIC SMALL LETTER ZE +0xDB 0x0448 # CYRILLIC SMALL LETTER SHA +0xDC 0x044D # CYRILLIC SMALL LETTER E +0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xDE 0x0447 # CYRILLIC SMALL LETTER CHE +0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xE0 0x042E # CYRILLIC CAPITAL LETTER YU +0xE1 0x0410 # CYRILLIC CAPITAL LETTER A +0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE +0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF +0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA +0xE9 0x0418 # CYRILLIC CAPITAL LETTER I +0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xEB 0x041A # CYRILLIC CAPITAL LETTER KA +0xEC 0x041B # CYRILLIC CAPITAL LETTER EL +0xED 0x041C # CYRILLIC CAPITAL LETTER EM +0xEE 0x041D # CYRILLIC CAPITAL LETTER EN +0xEF 0x041E # CYRILLIC CAPITAL LETTER O +0xF0 0x041F # CYRILLIC CAPITAL LETTER PE +0xF1 0x042F # CYRILLIC CAPITAL LETTER YA +0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER +0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES +0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE +0xF5 0x0423 # CYRILLIC CAPITAL LETTER U +0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE +0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU +0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xFC 0x042D # CYRILLIC CAPITAL LETTER E +0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN diff --git a/charsets/koi8-u.txt b/charsets/koi8-u.txt index 62f452b..c533b39 100644 --- a/charsets/koi8-u.txt +++ b/charsets/koi8-u.txt @@ -1,224 +1,301 @@ -# koi8-u to unicode translation from rfc 2319 -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 -0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL -0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL -0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT -0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT -0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT -0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT -0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT -0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT -0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL -0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL -0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL -0x8B 0x2580 # UPPER HALF BLOCK -0x8C 0x2584 # LOWER HALF BLOCK -0x8D 0x2588 # FULL BLOCK -0x8E 0x258C # LEFT HALF BLOCK -0x8F 0x2590 # RIGHT HALF BLOCK -0x90 0x2591 # LIGHT SHADE -0x91 0x2592 # MEDIUM SHADE -0x92 0x2593 # DARK SHADE -0x93 0x2320 # TOP HALF INTEGRAL -0x94 0x25A0 # BLACK SQUARE -0x95 0x2022 # BULLET -0x96 0x221A # SQUARE ROOT -0x97 0x2248 # ALMOST EQUAL TO -0x98 0x2264 # LESS-THAN OR EQUAL TO -0x99 0x2265 # GREATER-THAN OR EQUAL TO -0x9A 0x00A0 # NO-BREAK SPACE -0x9B 0x2321 # BOTTOM HALF INTEGRAL -0x9C 0x00B0 # DEGREE SIGN -0x9D 0x00B2 # SUPERSCRIPT TWO -0x9E 0x00B7 # MIDDLE DOT -0x9F 0x00F7 # DIVISION SIGN -0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL -0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL -0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE -0xA3 0x0451 # CYRILLIC SMALL LETTER IO -0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE -0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT -0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I -0xA7 0x0457 # CYRILLIC SMALL LETTER YI -0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT -0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE -0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE -0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT -0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE -0xAD 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN -0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT -0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE -0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE -0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT -0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE -0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO -0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE -0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT -0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I -0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI -0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL -0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE -0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE -0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL -0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE -0xBD 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN -0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL -0xBF 0x00A9 # COPYRIGHT SIGN -0xC0 0x044E # CYRILLIC SMALL LETTER YU -0xC1 0x0430 # CYRILLIC SMALL LETTER A -0xC2 0x0431 # CYRILLIC SMALL LETTER BE -0xC3 0x0446 # CYRILLIC SMALL LETTER TSE -0xC4 0x0434 # CYRILLIC SMALL LETTER DE -0xC5 0x0435 # CYRILLIC SMALL LETTER IE -0xC6 0x0444 # CYRILLIC SMALL LETTER EF -0xC7 0x0433 # CYRILLIC SMALL LETTER GHE -0xC8 0x0445 # CYRILLIC SMALL LETTER HA -0xC9 0x0438 # CYRILLIC SMALL LETTER I -0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I -0xCB 0x043A # CYRILLIC SMALL LETTER KA -0xCC 0x043B # CYRILLIC SMALL LETTER EL -0xCD 0x043C # CYRILLIC SMALL LETTER EM -0xCE 0x043D # CYRILLIC SMALL LETTER EN -0xCF 0x043E # CYRILLIC SMALL LETTER O -0xD0 0x043F # CYRILLIC SMALL LETTER PE -0xD1 0x044F # CYRILLIC SMALL LETTER YA -0xD2 0x0440 # CYRILLIC SMALL LETTER ER -0xD3 0x0441 # CYRILLIC SMALL LETTER ES -0xD4 0x0442 # CYRILLIC SMALL LETTER TE -0xD5 0x0443 # CYRILLIC SMALL LETTER U -0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE -0xD7 0x0432 # CYRILLIC SMALL LETTER VE -0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN -0xD9 0x044B # CYRILLIC SMALL LETTER YERU -0xDA 0x0437 # CYRILLIC SMALL LETTER ZE -0xDB 0x0448 # CYRILLIC SMALL LETTER SHA -0xDC 0x044D # CYRILLIC SMALL LETTER E -0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA -0xDE 0x0447 # CYRILLIC SMALL LETTER CHE -0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN -0xE0 0x042E # CYRILLIC CAPITAL LETTER YU -0xE1 0x0410 # CYRILLIC CAPITAL LETTER A -0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE -0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE -0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE -0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE -0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF -0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE -0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA -0xE9 0x0418 # CYRILLIC CAPITAL LETTER I -0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I -0xEB 0x041A # CYRILLIC CAPITAL LETTER KA -0xEC 0x041B # CYRILLIC CAPITAL LETTER EL -0xED 0x041C # CYRILLIC CAPITAL LETTER EM -0xEE 0x041D # CYRILLIC CAPITAL LETTER EN -0xEF 0x041E # CYRILLIC CAPITAL LETTER O -0xF0 0x041F # CYRILLIC CAPITAL LETTER PE -0xF1 0x042F # CYRILLIC CAPITAL LETTER YA -0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER -0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES -0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE -0xF5 0x0423 # CYRILLIC CAPITAL LETTER U -0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE -0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE -0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN -0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU -0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE -0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA -0xFC 0x042D # CYRILLIC CAPITAL LETTER E -0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA -0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE -0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN +# KOI8-U.TXT +# Date: 2016-01-04 23:09:00 GMT [KW] +# © 2016 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# +# Name: KOI8-U (RFC2319) to Unicode +# Unicode version: 5.1 +# Table version: 2.0 +# Table format: Format A +# Date: 13 October 2008 (header updated: 2016-January-04) +# Authors: Philippe Verdy , +# Helmut Richter +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# KOI8-U characters map into Unicode. The underlying document is the +# mapping described in RFC 2319. No statements are made as to whether +# this mapping is the same as the mapping defined as "Code Page 878" +# with some vendors. +# +# The KOI8-U (RFC2319) encoding is a variant based on KOI8-R (RFC1489), +# where the support for four additional Cyrillic letters was added (both small +# and capital letters), replacing 8 box-drawing characters. It is still widely +# used to encode texts in Ukrainian, Byelorussian and Bulgarian. +# +# Format: Three tab-separated columns +# Column #1 is the KOI8-U 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 KOI8-U 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: +# +# +# Any comments or problems, contact the Unicode Consortium at: +# +# +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 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL +0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL +0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT +0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT +0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT +0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT +0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT +0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL +0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0x8B 0x2580 # UPPER HALF BLOCK +0x8C 0x2584 # LOWER HALF BLOCK +0x8D 0x2588 # FULL BLOCK +0x8E 0x258C # LEFT HALF BLOCK +0x8F 0x2590 # RIGHT HALF BLOCK +0x90 0x2591 # LIGHT SHADE +0x91 0x2592 # MEDIUM SHADE +0x92 0x2593 # DARK SHADE +0x93 0x2320 # TOP HALF INTEGRAL +0x94 0x25A0 # BLACK SQUARE +0x95 0x2219 # BULLET OPERATOR +0x96 0x221A # SQUARE ROOT +0x97 0x2248 # ALMOST EQUAL TO +0x98 0x2264 # LESS-THAN OR EQUAL TO +0x99 0x2265 # GREATER-THAN OR EQUAL TO +0x9A 0x00A0 # NO-BREAK SPACE +0x9B 0x2321 # BOTTOM HALF INTEGRAL +0x9C 0x00B0 # DEGREE SIGN +0x9D 0x00B2 # SUPERSCRIPT TWO +0x9E 0x00B7 # MIDDLE DOT +0x9F 0x00F7 # DIVISION SIGN +0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL +0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL +0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xA3 0x0451 # CYRILLIC SMALL LETTER IO +0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xA7 0x0457 # CYRILLIC SMALL LETTER YI (UKRAINIAN) +0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT +0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT +0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xAD 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN +0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT +0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO +0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI (UKRAINIAN) +0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xBD 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xBF 0x00A9 # COPYRIGHT SIGN +0xC0 0x044E # CYRILLIC SMALL LETTER YU +0xC1 0x0430 # CYRILLIC SMALL LETTER A +0xC2 0x0431 # CYRILLIC SMALL LETTER BE +0xC3 0x0446 # CYRILLIC SMALL LETTER TSE +0xC4 0x0434 # CYRILLIC SMALL LETTER DE +0xC5 0x0435 # CYRILLIC SMALL LETTER IE +0xC6 0x0444 # CYRILLIC SMALL LETTER EF +0xC7 0x0433 # CYRILLIC SMALL LETTER GHE +0xC8 0x0445 # CYRILLIC SMALL LETTER HA +0xC9 0x0438 # CYRILLIC SMALL LETTER I +0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xCB 0x043A # CYRILLIC SMALL LETTER KA +0xCC 0x043B # CYRILLIC SMALL LETTER EL +0xCD 0x043C # CYRILLIC SMALL LETTER EM +0xCE 0x043D # CYRILLIC SMALL LETTER EN +0xCF 0x043E # CYRILLIC SMALL LETTER O +0xD0 0x043F # CYRILLIC SMALL LETTER PE +0xD1 0x044F # CYRILLIC SMALL LETTER YA +0xD2 0x0440 # CYRILLIC SMALL LETTER ER +0xD3 0x0441 # CYRILLIC SMALL LETTER ES +0xD4 0x0442 # CYRILLIC SMALL LETTER TE +0xD5 0x0443 # CYRILLIC SMALL LETTER U +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0432 # CYRILLIC SMALL LETTER VE +0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xD9 0x044B # CYRILLIC SMALL LETTER YERU +0xDA 0x0437 # CYRILLIC SMALL LETTER ZE +0xDB 0x0448 # CYRILLIC SMALL LETTER SHA +0xDC 0x044D # CYRILLIC SMALL LETTER E +0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xDE 0x0447 # CYRILLIC SMALL LETTER CHE +0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xE0 0x042E # CYRILLIC CAPITAL LETTER YU +0xE1 0x0410 # CYRILLIC CAPITAL LETTER A +0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE +0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF +0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA +0xE9 0x0418 # CYRILLIC CAPITAL LETTER I +0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xEB 0x041A # CYRILLIC CAPITAL LETTER KA +0xEC 0x041B # CYRILLIC CAPITAL LETTER EL +0xED 0x041C # CYRILLIC CAPITAL LETTER EM +0xEE 0x041D # CYRILLIC CAPITAL LETTER EN +0xEF 0x041E # CYRILLIC CAPITAL LETTER O +0xF0 0x041F # CYRILLIC CAPITAL LETTER PE +0xF1 0x042F # CYRILLIC CAPITAL LETTER YA +0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER +0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES +0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE +0xF5 0x0423 # CYRILLIC CAPITAL LETTER U +0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE +0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU +0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xFC 0x042D # CYRILLIC CAPITAL LETTER E +0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN diff --git a/charsets/mac-cyrillic.txt b/charsets/mac-cyrillic.txt index 22573a2..d569c2c 100644 --- a/charsets/mac-cyrillic.txt +++ b/charsets/mac-cyrillic.txt @@ -1,24 +1,32 @@ #======================================================================= -# FTP file name: CYRILLIC.TXT +# File name: CYRILLIC.TXT # -# Contents: Map (external version) from Mac OS Cyrillic -# character set to Unicode 2.0 +# Contents: Map (external version) from Mac OS Cyrillic +# character set to Unicode 2.1 and later. # -# Copyright: (c) 1995-1998 by Apple Computer, Inc., all rights -# reserved. +# Copyright: (c) 1995-2002, 2005 by Apple Computer, Inc., all rights +# reserved. # -# Contacts: Peter Edberg -# Julio Gonzalez -# John Jenkins +# Contact: charsets@apple.com # # Changes: # +# c03 2005-Apr-05 Update header comments. Matches internal xml +# and Text Encoding Converter 2.0. +# b3,c1 2002-Dec-19 Update URLs, notes. Matches internal +# utom. +# b02 1999-Sep-22 Encoding changed for Mac OS 9.0 to merge +# with Mac OS Ukrainian and support EURO SIGN; +# Change mappings for 0xA2, 0xB6, and 0xFF. +# Update contact e-mail address. Matches +# internal utom, ufrm, and Text +# Encoding Converter version 1.5. # n05 1998-Feb-05 Update header comments to new format; no -# mapping changes. Matches internal utom<3>, -# ufrm<13>, and Text Encoding Converter +# mapping changes. Matches internal utom, +# ufrm, and Text Encoding Converter # version 1.3. # n03 1995-Apr-15 First version (after fixing some typos). -# Matches internal ufrm<5>. +# Matches internal ufrm. # # Standard header: # ---------------- @@ -30,18 +38,17 @@ # Macintosh computers and "Unicode" can be used to refer to the # Unicode standard. # -# Apple makes no warranty or representation, either express or -# implied, with respect to these tables, their quality, accuracy, or -# fitness for a particular purpose. In no event will Apple be liable -# for direct, indirect, special, incidental, or consequential damages -# resulting from any defect or inaccuracy in this document or the -# accompanying tables. +# Apple Computer, Inc. ("Apple") makes no warranty or representation, +# either express or implied, with respect to this document and the +# included data, its quality, accuracy, or fitness for a particular +# purpose. In no event will Apple be liable for direct, indirect, +# special, incidental, or consequential damages resulting from any +# defect or inaccuracy in this document or the included data. # # These mapping tables and character lists are subject to change. # The latest tables should be available from the following: # -# -# +# # # For general information about Mac OS encodings and these mapping # tables, see the file "README.TXT". @@ -65,15 +72,35 @@ # Notes on Mac OS Cyrillic: # ------------------------- # -# The Mac Cyrillic encoding is used for most Cyrillic localized -# system software except Ukrainian. A variant of Mac OS Cyrillic -# is used for Ukrainian and for the Cyrillic Language Kit; it is -# covered by a separate table. +# This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa +# environments, it is only supported directly in programming +# interfaces for QuickDraw Text, the Script Manager, and related +# Text Utilities. For other purposes it is supported via transcoding +# to and from Unicode. # -# The Mac OS Cyrillic encoding has the same Cyrillic letter -# repertoire as ISO 8859-5 (although not at the same code points). -# This covers most of the Slavic languages written in Cyrillic -# script. +# This is the "Euro sign" version of Mac Cyrillic for Mac OS 9.0 and +# later. Before Mac OS 9.0, there were two separate Slavic Cyrillic +# encodings: +# +# 1. The Cyrillic currency sign variant (used for localized Russian +# and Bulgarian systems), which had the following: +# 0xA2 U+00A2 CENT SIGN +# 0xB6 U+2202 PARTIAL DIFFERENTIAL +# 0xFF U+00A4 CURRENCY SIGN +# +# 2. The Ukrainian currency sign variant (used for localized Ukrainian +# systems and the pre-9.0 Cyrillic Language Kit), which had the +# following: +# 0xA2 U+0490 CYRILLIC CAPITAL LETTER GHE WITH UPTURN +# 0xB6 U+0491 CYRILLIC SMALL LETTER GHE WITH UPTURN +# 0xFF U+00A4 CURRENCY SIGN +# +# This new Cyrillic Euro sign version is based on the old Ukrainian +# currency sign variant, with 0xFF changed to be EURO SIGN. +# +# The Mac OS Cyrillic encoding includes the Cyrillic letter repertoire +# of ISO 8859-5 (although not at the same code points). This covers +# most of the Slavic languages written in Cyrillic script. # # The Mac OS Cyrillic encoding also includes a number of characters # needed for the Mac OS user interface and localization (e.g. @@ -81,46 +108,24 @@ # Cyrillic that are also in the Mac OS Roman encoding are at the # same code point in both; this improves application compatibility. # +# Note: There is a common Ukrainian glyph variation in which the glyph +# for CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I may or may not +# have a dot above. +# # Unicode mapping issues and notes: # --------------------------------- # # Details of mapping changes in each version: # ------------------------------------------- # +# Changes from version n05 to version b02: +# +# - Encoding changed for Mac OS 9.0 to merge with Mac OS Ukrainian and +# support EURO SIGN. 0xA2 changed from U+00A2 to U+0490; 0xB6 changed +# from U+2202 to U+0491; 0xFF changed from U+00A4 to U+20AC. +# ################## -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 @@ -251,7 +256,7 @@ 0x9F 0x042F # CYRILLIC CAPITAL LETTER YA 0xA0 0x2020 # DAGGER 0xA1 0x00B0 # DEGREE SIGN -0xA2 0x00A2 # CENT SIGN +0xA2 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN 0xA3 0x00A3 # POUND SIGN 0xA4 0x00A7 # SECTION SIGN 0xA5 0x2022 # BULLET @@ -271,7 +276,7 @@ 0xB3 0x2265 # GREATER-THAN OR EQUAL TO 0xB4 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 0xB5 0x00B5 # MICRO SIGN -0xB6 0x2202 # PARTIAL DIFFERENTIAL +0xB6 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN 0xB7 0x0408 # CYRILLIC CAPITAL LETTER JE 0xB8 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE 0xB9 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE @@ -344,4 +349,4 @@ 0xFC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN 0xFD 0x044D # CYRILLIC SMALL LETTER E 0xFE 0x044E # CYRILLIC SMALL LETTER YU -0xFF 0x00A4 # CURRENCY SIGN +0xFF 0x20AC # EURO SIGN diff --git a/charsets/us-ascii.txt b/charsets/us-ascii.txt index cc28e9e..f021fa4 100644 --- a/charsets/us-ascii.txt +++ b/charsets/us-ascii.txt @@ -1,98 +1,198 @@ -# -# Name: US-ASCII\ to Unicode -# Unicode version: 1.1 -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 +# +# Name: ANSI X3.4-1968 (US-ASCII) with 0x60/0x27 as +# left/right single quotation mark to Unicode +# Unicode version: 3.2 +# Table version: 1.0 +# Table format: Format A +# Date: 2003 April 8 +# Authors: Markus Kuhn +# +# General notes: +# +# The coded character set commonly known as "American Standard +# Code for Information Interchange (ASCII)" originated in the +# early 1960s international standardization project that led to +# ECMA-6 (1965) and ISO 646 (1972). When the American National +# Standards Institute adopted this specification as national +# standard X3.4 in 1968, it added a national provision for +# overloading the code positions 0x60 and 0x27 with the +# typographic characters left and right single quotation mark. +# This usage was not reflected in the international standard and +# other national adoptions of it, but become widely used in some +# communities in the United States and is now found in numerous +# historic and still even some contemporary English-language +# 7-bit ASCII text files. The Unicode Standard followed +# explicitly the international standard, in which 0x27 encodes +# the directionally neutral (vertical) character that is used as +# both an opening and closing quotation mark as well as an +# apostrophe on traditional typewriters, and where 0x60 is a +# spacing grave accent that matches the spacing acute accent +# found in ISO 8859-1 on position 0xb4. +# +# To facilitate the correct display and conversion of such ASCII +# documents with directional quotation marks to Unicode, this +# encoding table defines a 7-bit coded character set mapping +# that differs from ISO 646-IRV in that the characters 0x60 and +# 0x27 are mapped to Unicode's typographic directional quotation +# marks on U+2018 and U+2019, respectively. +# +# Notes: +# +# - This historic ASCII interpretation is also used in the left +# half of the PostScript StandardEncoding and (erroneously) +# ISOLatin1Encoding encoding vectors. +# +# - Unicode features a SINGLE HIGH-REVERSED-9 QUOTATION MARK +# (U+201B), whose provided example glyph has a slightly +# closer ressemblance to the compromise glyphs found in many +# historic US-ASCII fonts that try to represent both a left +# quotation mark and a grave accent. However, since U+201B +# is not actually intended to encode correct English +# typographic quotation conventions, this table maps 0x60 to +# the the correct English opening quotation mark U+2018 +# instead (as did PostScript). +# +# References: +# +# - Markus Kuhn: ASCII and Unicode quotation marks. +# http://www.cl.cam.ac.uk/~mgk25/ucs/quotes.html +# +# - Jukka Korpela: Character histories: notes on some Ascii +# code positions. +# http://www.cs.tut.fi/~jkorpela/latin1/ascii-hist.html +# +# Format: Three tab-separated columns +# Column #1 is the ANSI X3.4 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 ANSI X3.4 order. +# +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 0x2019 # RIGHT SINGLE QUOTATION MARK +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 0x2018 # LEFT SINGLE QUOTATION MARK +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 -- 2.39.5