Initial commit of Typo3 charset libraries and Moodle's textlib.class code.

Merged from MOODLE_15_STABLE
This commit is contained in:
stronk7 2005-10-17 15:48:46 +00:00
parent acf879d685
commit 779dc9aca1
38 changed files with 86007 additions and 0 deletions

168
lib/textlib.class.php Normal file
View file

@ -0,0 +1,168 @@
<?php // $Id$
///////////////////////////////////////////////////////////////////////////
// //
// NOTICE OF COPYRIGHT //
// //
// Moodle - Modular Object-Oriented Dynamic Learning Environment //
// http://moodle.com //
// //
// Copyright (C) 2001-3001 Martin Dougiamas http://dougiamas.com //
// (C) 2001-3001 Eloy Lafuente (stronk7) http://contiento.com //
// //
// This program is free software; you can redistribute it and/or modify //
// it under the terms of the GNU General Public License as published by //
// the Free Software Foundation; either version 2 of the License, or //
// (at your option) any later version. //
// //
// This program is distributed in the hope that it will be useful, //
// but WITHOUT ANY WARRANTY; without even the implied warranty of //
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the //
// GNU General Public License for more details: //
// //
// http://www.gnu.org/copyleft/gpl.html //
// //
///////////////////////////////////////////////////////////////////////////
/// Required files
require_once('typo3/class.t3lib_cs.php');
require_once('typo3/class.t3lib_div.php');
/// If ICONV is available, lets Typo3 library use it for convert
if (extension_loaded('iconv')) {
$GLOBALS['TYPO3_CONF_VARS']['SYS']['t3lib_cs_convMethod'] = 'iconv';
/// Else if mbstring is available, lets Typo3 library use it
} else if (extension_loaded('mbstring')) {
$GLOBALS['TYPO3_CONF_VARS']['SYS']['t3lib_cs_convMethod'] = 'mbstring';
} else {
$GLOBALS['TYPO3_CONF_VARS']['SYS']['t3lib_cs_convMethod'] = '';
}
/// If mbstring is available, lets Typo3 library use it for functions
if (extension_loaded('mbstring')) {
$GLOBALS['TYPO3_CONF_VARS']['SYS']['t3lib_cs_utils'] = 'mbstring';
} else {
$GLOBALS['TYPO3_CONF_VARS']['SYS']['t3lib_cs_utils'] = '';
/// And this directoy must exist to allow Typo to cache conversion
/// tables when using internal functions
make_upload_directory('temp/typo3temp/cs');
}
/// Default mask for Typo
$GLOBALS['TYPO3_CONF_VARS']['BE']['fileCreateMask'] = $CFG->directorypermissions;
/// This full path constants must be defined too, transforming backslashes
/// to forward slashed beacuse Typo3 requires it.
define ('PATH_t3lib', str_replace('\\','/',$CFG->dirroot.'/testutf/typo3/'));
define ('PATH_typo3', str_replace('\\','/',$CFG->dirroot.'/testutf/typo3/'));
define ('PATH_site', str_replace('\\','/',$CFG->dataroot.'/temp/'));
define ('TYPO3_OS', stristr(PHP_OS,'win')&&!stristr(PHP_OS,'darwin')?'WIN':'');
/// As we implement the singleton pattern to use this class (only one instance
/// is shared globally), we need this helper function
function textlib_get_instance () {
static $instance;
if (!is_object($instance)) {
$instance = new textlib();
}
return $instance;
}
/**
* This class is used to manipulate strings under Moodle 1.6 an later. As
* utf-8 text become mandatory a pool of safe functions under this encoding
* become necessary. All of them are static methods that will be called from
* Moodle code with the :: syntax. The name of the methods is exactly the
* same than their PHP originals.
*
* A big part of this class acts as a wrapper over the Typo3 charset library,
* really a cool group of utilities to handle texts and encoding conversion.
*
* Take a look to its own copyright and license details.
*/
class textlib {
var $typo3cs;
/* Standard constructor of the class. All it does is to instantiate
* a new t3lib_cs object to have all their functions ready.
*
* Instead of istantiating a lot of objects of this class everytime
* some of their functions is going to be used, you can invoke the:
* textlib_get_instance() function, avoiding the creation of them
* (following the singleton pattern)
*/
function textlib() {
/// Instantiate a conversor object some of the methods in typo3
/// reference to $this and cannot be executed in a static context
$this->typo3cs = new t3lib_cs();
}
/* Converts the text between different encodings. It will use iconv, mbstring
* or internal (typo3) methods to try such conversion. Returns false if fails.
*/
function convert($text, $fromCS, $toCS='utf-8') {
/// Avoid some notices from Typo3 code
$oldlevel = error_reporting(E_PARSE);
/// Call Typo3 conv() function. It will do all the work
$result = $this->typo3cs->conv($text, $fromCS, $toCS);
/// Restore original debug level
error_reporting($oldlevel);
return $result;
}
/* Multibyte safe substr() function, uses mbstring if available. */
function substr($text, $start, $len=null, $charset='utf-8') {
/// Call Typo3 substr() function. It will do all the work
return $this->typo3cs->substr($charset,$text,$start,$len);
}
/* Multibyte safe strlen() function, uses mbstring if available. */
function strlen($text, $charset='utf-8') {
/// Avoid some notices from Typo3 code
$oldlevel = error_reporting(E_PARSE);
/// Call Typo3 strlen() function. It will do all the work
$result = $this->typo3cs->strlen($charset,$text);
/// Restore original debug level
error_reporting($oldlevel);
return $result;
}
/* Multibyte safe strtolower() function, uses mbstring if available. */
function strtolower($text, $charset='utf-8') {
/// Avoid some notices from Typo3 code
$oldlevel = error_reporting(E_PARSE);
/// Call Typo3 conv_case() function. It will do all the work
$result = $this->typo3cs->conv_case($charset,$text,'toLower');
/// Restore original debug level
error_reporting($oldlevel);
return $result;
}
/* Multibyte safe strtoupper() function, uses mbstring if available. */
function strtoupper($text, $charset='utf-8') {
/// Avoid some notices from Typo3 code
$oldlevel = error_reporting(E_PARSE);
/// Call Typo3 conv_case() function. It will do all the work
$result = $this->typo3cs->conv_case($charset,$text,'toUpper');
/// Restore original debug level
error_reporting($oldlevel);
return $result;
}
/* UTF-8 ONLY safe strpos() function, uses mbstring if available. */
function strpos($haystack,$needle,$offset=0) {
/// Call Typo3 utf8_strpos() function. It will do all the work
return $this->typo3cs->utf8_strpos($haystack,$needle,$offset);
}
/* UTF-8 ONLY safe strrpos() function, uses mbstring if available. */
function strrpos($haystack,$needle) {
/// Call Typo3 utf8_strrpos() function. It will do all the work
return $this->typo3cs->utf8_strrpos($haystack,$needle);
}
}
?>

2053
lib/typo3/class.t3lib_cs.php Normal file

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

13778
lib/typo3/csconvtbl/big5.tbl Normal file

File diff suppressed because it is too large Load diff

17048
lib/typo3/csconvtbl/euc-kr.tbl Normal file

File diff suppressed because it is too large Load diff

21792
lib/typo3/csconvtbl/gb2312.tbl Normal file

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,96 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+00A1 : INVERTED EXCLAMATION MARK
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00AA : FEMININE ORDINAL INDICATOR
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00BA : MASCULINE ORDINAL INDICATOR
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+00BF : INVERTED QUESTION MARK
C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+00C3 : LATIN CAPITAL LETTER A WITH TILDE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+00C6 : LATIN CAPITAL LETTER AE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+00CC : LATIN CAPITAL LETTER I WITH GRAVE
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
D0 = U+00D0 : LATIN CAPITAL LETTER ETH
D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
D2 = U+00D2 : LATIN CAPITAL LETTER O WITH GRAVE
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+00DD : LATIN CAPITAL LETTER Y WITH ACUTE
DE = U+00DE : LATIN CAPITAL LETTER THORN
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+00E3 : LATIN SMALL LETTER A WITH TILDE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+00E6 : LATIN SMALL LETTER AE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+00EC : LATIN SMALL LETTER I WITH GRAVE
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F0 = U+00F0 : LATIN SMALL LETTER ETH
F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
F2 = U+00F2 : LATIN SMALL LETTER O WITH GRAVE
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+00FD : LATIN SMALL LETTER Y WITH ACUTE
FE = U+00FE : LATIN SMALL LETTER THORN
FF = U+00FF : LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,303 @@
#
# Name: ISO/IEC 8859-10:1998 to Unicode
# Unicode version: 3.0
# Table version: 1.1
# Table format: Format A
# Date: 1999 October 11
# Authors: Ken Whistler <kenw@sybase.com>
#
# Copyright (c) 1999 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on optical media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Unicode, Inc. hereby grants the right to freely use the information
# supplied in this file in the creation of products supporting the
# Unicode Standard, and to make copies of this file in any form for
# internal or external distribution as long as this notice remains
# attached.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO/IEC 8859-10:1998 characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO/IEC 8859-10 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 8859-10 order.
#
# Version history
# 1.0 version new.
# 1.1 corrected mistake in mapping of 0xA4
#
# Updated versions of this file may be found in:
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
#
# Any comments or problems, contact <errata@unicode.org>
# Please note that <errata@unicode.org> is an archival address;
# notices will be checked, but do not expect an immediate response.
#
0x00 0x0000 # NULL
0x01 0x0001 # START OF HEADING
0x02 0x0002 # START OF TEXT
0x03 0x0003 # END OF TEXT
0x04 0x0004 # END OF TRANSMISSION
0x05 0x0005 # ENQUIRY
0x06 0x0006 # ACKNOWLEDGE
0x07 0x0007 # BELL
0x08 0x0008 # BACKSPACE
0x09 0x0009 # HORIZONTAL TABULATION
0x0A 0x000A # LINE FEED
0x0B 0x000B # VERTICAL TABULATION
0x0C 0x000C # FORM FEED
0x0D 0x000D # CARRIAGE RETURN
0x0E 0x000E # SHIFT OUT
0x0F 0x000F # SHIFT IN
0x10 0x0010 # DATA LINK ESCAPE
0x11 0x0011 # DEVICE CONTROL ONE
0x12 0x0012 # DEVICE CONTROL TWO
0x13 0x0013 # DEVICE CONTROL THREE
0x14 0x0014 # DEVICE CONTROL FOUR
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
0x16 0x0016 # SYNCHRONOUS IDLE
0x17 0x0017 # END OF TRANSMISSION BLOCK
0x18 0x0018 # CANCEL
0x19 0x0019 # END OF MEDIUM
0x1A 0x001A # SUBSTITUTE
0x1B 0x001B # ESCAPE
0x1C 0x001C # FILE SEPARATOR
0x1D 0x001D # GROUP SEPARATOR
0x1E 0x001E # RECORD SEPARATOR
0x1F 0x001F # UNIT SEPARATOR
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0x7F 0x007F # DELETE
0x80 0x0080 # <control>
0x81 0x0081 # <control>
0x82 0x0082 # <control>
0x83 0x0083 # <control>
0x84 0x0084 # <control>
0x85 0x0085 # <control>
0x86 0x0086 # <control>
0x87 0x0087 # <control>
0x88 0x0088 # <control>
0x89 0x0089 # <control>
0x8A 0x008A # <control>
0x8B 0x008B # <control>
0x8C 0x008C # <control>
0x8D 0x008D # <control>
0x8E 0x008E # <control>
0x8F 0x008F # <control>
0x90 0x0090 # <control>
0x91 0x0091 # <control>
0x92 0x0092 # <control>
0x93 0x0093 # <control>
0x94 0x0094 # <control>
0x95 0x0095 # <control>
0x96 0x0096 # <control>
0x97 0x0097 # <control>
0x98 0x0098 # <control>
0x99 0x0099 # <control>
0x9A 0x009A # <control>
0x9B 0x009B # <control>
0x9C 0x009C # <control>
0x9D 0x009D # <control>
0x9E 0x009E # <control>
0x9F 0x009F # <control>
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
0xA2 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
0xA3 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
0xA4 0x012A # LATIN CAPITAL LETTER I WITH MACRON
0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE
0xA6 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
0xA7 0x00A7 # SECTION SIGN
0xA8 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
0xA9 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
0xAA 0x0160 # LATIN CAPITAL LETTER S WITH CARON
0xAB 0x0166 # LATIN CAPITAL LETTER T WITH STROKE
0xAC 0x017D # LATIN CAPITAL LETTER Z WITH CARON
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x016A # LATIN CAPITAL LETTER U WITH MACRON
0xAF 0x014A # LATIN CAPITAL LETTER ENG
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
0xB2 0x0113 # LATIN SMALL LETTER E WITH MACRON
0xB3 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
0xB4 0x012B # LATIN SMALL LETTER I WITH MACRON
0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE
0xB6 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
0xB7 0x00B7 # MIDDLE DOT
0xB8 0x013C # LATIN SMALL LETTER L WITH CEDILLA
0xB9 0x0111 # LATIN SMALL LETTER D WITH STROKE
0xBA 0x0161 # LATIN SMALL LETTER S WITH CARON
0xBB 0x0167 # LATIN SMALL LETTER T WITH STROKE
0xBC 0x017E # LATIN SMALL LETTER Z WITH CARON
0xBD 0x2015 # HORIZONTAL BAR
0xBE 0x016B # LATIN SMALL LETTER U WITH MACRON
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 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic)
0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON
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 0x0168 # LATIN CAPITAL LETTER U WITH TILDE
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 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic)
0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
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 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic)
0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON
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 0x0169 # LATIN SMALL LETTER U WITH TILDE
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 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic)
0xFF 0x0138 # LATIN SMALL LETTER KRA

View file

@ -0,0 +1,87 @@
A1 = U+0E01 : THAI CHARACTER KO KAI
A2 = U+0E02 : THAI CHARACTER KHO KHAI
A3 = U+0E03 : THAI CHARACTER KHO KHUAT
A4 = U+0E04 : THAI CHARACTER KHO KHWAI
A5 = U+0E05 : THAI CHARACTER KHO KHON
A6 = U+0E06 : THAI CHARACTER KHO RAKHANG
A7 = U+0E07 : THAI CHARACTER NGO NGU
A8 = U+0E08 : THAI CHARACTER CHO CHAN
A9 = U+0E09 : THAI CHARACTER CHO CHING
AA = U+0E0A : THAI CHARACTER CHO CHANG
AB = U+0E0B : THAI CHARACTER SO SO
AC = U+0E0C : THAI CHARACTER CHO CHOE
AD = U+0E0D : THAI CHARACTER YO YING
AE = U+0E0E : THAI CHARACTER DO CHADA
AF = U+0E0F : THAI CHARACTER TO PATAK
B0 = U+0E10 : THAI CHARACTER THO THAN
B1 = U+0E11 : THAI CHARACTER THO NANGMONTHO
B2 = U+0E12 : THAI CHARACTER THO PHUTHAO
B3 = U+0E13 : THAI CHARACTER NO NEN
B4 = U+0E14 : THAI CHARACTER DO DEK
B5 = U+0E15 : THAI CHARACTER TO TAO
B6 = U+0E16 : THAI CHARACTER THO THUNG
B7 = U+0E17 : THAI CHARACTER THO THAHAN
B8 = U+0E18 : THAI CHARACTER THO THONG
B9 = U+0E19 : THAI CHARACTER NO NU
BA = U+0E1A : THAI CHARACTER BO BAIMAI
BB = U+0E1B : THAI CHARACTER PO PLA
BC = U+0E1C : THAI CHARACTER PHO PHUNG
BD = U+0E1D : THAI CHARACTER FO FA
BE = U+0E1E : THAI CHARACTER PHO PHAN
BF = U+0E1F : THAI CHARACTER FO FAN
C0 = U+0E20 : THAI CHARACTER PHO SAMPHAO
C1 = U+0E21 : THAI CHARACTER MO MA
C2 = U+0E22 : THAI CHARACTER YO YAK
C3 = U+0E23 : THAI CHARACTER RO RUA
C4 = U+0E24 : THAI CHARACTER RU
C5 = U+0E25 : THAI CHARACTER LO LING
C6 = U+0E26 : THAI CHARACTER LU
C7 = U+0E27 : THAI CHARACTER WO WAEN
C8 = U+0E28 : THAI CHARACTER SO SALA
C9 = U+0E29 : THAI CHARACTER SO RUSI
CA = U+0E2A : THAI CHARACTER SO SUA
CB = U+0E2B : THAI CHARACTER HO HIP
CC = U+0E2C : THAI CHARACTER LO CHULA
CD = U+0E2D : THAI CHARACTER O ANG
CE = U+0E2E : THAI CHARACTER HO NOKHUK
CF = U+0E2F : THAI CHARACTER PAIYANNOI
D0 = U+0E30 : THAI CHARACTER SARA A
D1 = U+0E31 : THAI CHARACTER MAI HAN-AKAT
D2 = U+0E32 : THAI CHARACTER SARA AA
D3 = U+0E33 : THAI CHARACTER SARA AM
D4 = U+0E34 : THAI CHARACTER SARA I
D5 = U+0E35 : THAI CHARACTER SARA II
D6 = U+0E36 : THAI CHARACTER SARA UE
D7 = U+0E37 : THAI CHARACTER SARA UEE
D8 = U+0E38 : THAI CHARACTER SARA U
D9 = U+0E39 : THAI CHARACTER SARA UU
DA = U+0E3A : THAI CHARACTER PHINTHU
DF = U+0E3F : THAI CURRENCY SYMBOL BAHT
E0 = U+0E40 : THAI CHARACTER SARA E
E1 = U+0E41 : THAI CHARACTER SARA AE
E2 = U+0E42 : THAI CHARACTER SARA O
E3 = U+0E43 : THAI CHARACTER SARA AI MAIMUAN
E4 = U+0E44 : THAI CHARACTER SARA AI MAIMALAI
E5 = U+0E45 : THAI CHARACTER LAKKHANGYAO
E6 = U+0E46 : THAI CHARACTER MAIYAMOK
E7 = U+0E47 : THAI CHARACTER MAITAIKHU
E8 = U+0E48 : THAI CHARACTER MAI EK
E9 = U+0E49 : THAI CHARACTER MAI THO
EA = U+0E4A : THAI CHARACTER MAI TRI
EB = U+0E4B : THAI CHARACTER MAI CHATTAWA
EC = U+0E4C : THAI CHARACTER THANTHAKHAT
ED = U+0E4D : THAI CHARACTER NIKHAHIT
EE = U+0E4E : THAI CHARACTER YAMAKKAN
EF = U+0E4F : THAI CHARACTER FONGMAN
F0 = U+0E50 : THAI DIGIT ZERO
F1 = U+0E51 : THAI DIGIT ONE
F2 = U+0E52 : THAI DIGIT TWO
F3 = U+0E53 : THAI DIGIT THREE
F4 = U+0E54 : THAI DIGIT FOUR
F5 = U+0E55 : THAI DIGIT FIVE
F6 = U+0E56 : THAI DIGIT SIX
F7 = U+0E57 : THAI DIGIT SEVEN
F8 = U+0E58 : THAI DIGIT EIGHT
F9 = U+0E59 : THAI DIGIT NINE
FA = U+0E5A : THAI CHARACTER ANGKHANKHU
FB = U+0E5B : THAI CHARACTER KHOMUT

View file

@ -0,0 +1,299 @@
#
# Name: ISO/IEC 8859-13:1998 to Unicode
# Unicode version: 3.0
# Table version: 1.0
# Table format: Format A
# Date: 1999 July 27
# Authors: Ken Whistler <kenw@sybase.com>
#
# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on optical media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Unicode, Inc. hereby grants the right to freely use the information
# supplied in this file in the creation of products supporting the
# Unicode Standard, and to make copies of this file in any form for
# internal or external distribution as long as this notice remains
# attached.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO/IEC 8859-13:1998 characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO/IEC 8859-13 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 8859-13 order.
#
# Updated versions of this file may be found in:
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
#
# Any comments or problems, contact <errata@unicode.org>
# Please note that <errata@unicode.org> is an archival address;
# notices will be checked, but do not expect an immediate response.
#
0x00 0x0000 # NULL
0x01 0x0001 # START OF HEADING
0x02 0x0002 # START OF TEXT
0x03 0x0003 # END OF TEXT
0x04 0x0004 # END OF TRANSMISSION
0x05 0x0005 # ENQUIRY
0x06 0x0006 # ACKNOWLEDGE
0x07 0x0007 # BELL
0x08 0x0008 # BACKSPACE
0x09 0x0009 # HORIZONTAL TABULATION
0x0A 0x000A # LINE FEED
0x0B 0x000B # VERTICAL TABULATION
0x0C 0x000C # FORM FEED
0x0D 0x000D # CARRIAGE RETURN
0x0E 0x000E # SHIFT OUT
0x0F 0x000F # SHIFT IN
0x10 0x0010 # DATA LINK ESCAPE
0x11 0x0011 # DEVICE CONTROL ONE
0x12 0x0012 # DEVICE CONTROL TWO
0x13 0x0013 # DEVICE CONTROL THREE
0x14 0x0014 # DEVICE CONTROL FOUR
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
0x16 0x0016 # SYNCHRONOUS IDLE
0x17 0x0017 # END OF TRANSMISSION BLOCK
0x18 0x0018 # CANCEL
0x19 0x0019 # END OF MEDIUM
0x1A 0x001A # SUBSTITUTE
0x1B 0x001B # ESCAPE
0x1C 0x001C # FILE SEPARATOR
0x1D 0x001D # GROUP SEPARATOR
0x1E 0x001E # RECORD SEPARATOR
0x1F 0x001F # UNIT SEPARATOR
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0x7F 0x007F # DELETE
0x80 0x0080 # <control>
0x81 0x0081 # <control>
0x82 0x0082 # <control>
0x83 0x0083 # <control>
0x84 0x0084 # <control>
0x85 0x0085 # <control>
0x86 0x0086 # <control>
0x87 0x0087 # <control>
0x88 0x0088 # <control>
0x89 0x0089 # <control>
0x8A 0x008A # <control>
0x8B 0x008B # <control>
0x8C 0x008C # <control>
0x8D 0x008D # <control>
0x8E 0x008E # <control>
0x8F 0x008F # <control>
0x90 0x0090 # <control>
0x91 0x0091 # <control>
0x92 0x0092 # <control>
0x93 0x0093 # <control>
0x94 0x0094 # <control>
0x95 0x0095 # <control>
0x96 0x0096 # <control>
0x97 0x0097 # <control>
0x98 0x0098 # <control>
0x99 0x0099 # <control>
0x9A 0x009A # <control>
0x9B 0x009B # <control>
0x9C 0x009C # <control>
0x9D 0x009D # <control>
0x9E 0x009E # <control>
0x9F 0x009F # <control>
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x201D # RIGHT DOUBLE QUOTATION MARK
0xA2 0x00A2 # CENT SIGN
0xA3 0x00A3 # POUND SIGN
0xA4 0x00A4 # CURRENCY SIGN
0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK
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 0x201C # LEFT DOUBLE QUOTATION MARK
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 (German)
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 0x2019 # RIGHT SINGLE QUOTATION MARK

View file

@ -0,0 +1,301 @@
#
# Name: ISO/IEC 8859-14:1998 to Unicode
# Unicode version: 3.0
# Table version: 1.0
# Table format: Format A
# Date: 1999 July 27
# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
# Ken Whistler <kenw@sybase.com>
#
# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on optical media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Unicode, Inc. hereby grants the right to freely use the information
# supplied in this file in the creation of products supporting the
# Unicode Standard, and to make copies of this file in any form for
# internal or external distribution as long as this notice remains
# attached.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO/IEC 8859-14:1998 characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO/IEC 8859-14 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 8859-14 order.
#
# Updated versions of this file may be found in:
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
#
# Any comments or problems, contact <errata@unicode.org>
# Please note that <errata@unicode.org> is an archival address;
# notices will be checked, but do not expect an immediate response.
#
0x00 0x0000 # NULL
0x01 0x0001 # START OF HEADING
0x02 0x0002 # START OF TEXT
0x03 0x0003 # END OF TEXT
0x04 0x0004 # END OF TRANSMISSION
0x05 0x0005 # ENQUIRY
0x06 0x0006 # ACKNOWLEDGE
0x07 0x0007 # BELL
0x08 0x0008 # BACKSPACE
0x09 0x0009 # HORIZONTAL TABULATION
0x0A 0x000A # LINE FEED
0x0B 0x000B # VERTICAL TABULATION
0x0C 0x000C # FORM FEED
0x0D 0x000D # CARRIAGE RETURN
0x0E 0x000E # SHIFT OUT
0x0F 0x000F # SHIFT IN
0x10 0x0010 # DATA LINK ESCAPE
0x11 0x0011 # DEVICE CONTROL ONE
0x12 0x0012 # DEVICE CONTROL TWO
0x13 0x0013 # DEVICE CONTROL THREE
0x14 0x0014 # DEVICE CONTROL FOUR
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
0x16 0x0016 # SYNCHRONOUS IDLE
0x17 0x0017 # END OF TRANSMISSION BLOCK
0x18 0x0018 # CANCEL
0x19 0x0019 # END OF MEDIUM
0x1A 0x001A # SUBSTITUTE
0x1B 0x001B # ESCAPE
0x1C 0x001C # FILE SEPARATOR
0x1D 0x001D # GROUP SEPARATOR
0x1E 0x001E # RECORD SEPARATOR
0x1F 0x001F # UNIT SEPARATOR
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0x7F 0x007F # DELETE
0x80 0x0080 # <control>
0x81 0x0081 # <control>
0x82 0x0082 # <control>
0x83 0x0083 # <control>
0x84 0x0084 # <control>
0x85 0x0085 # <control>
0x86 0x0086 # <control>
0x87 0x0087 # <control>
0x88 0x0088 # <control>
0x89 0x0089 # <control>
0x8A 0x008A # <control>
0x8B 0x008B # <control>
0x8C 0x008C # <control>
0x8D 0x008D # <control>
0x8E 0x008E # <control>
0x8F 0x008F # <control>
0x90 0x0090 # <control>
0x91 0x0091 # <control>
0x92 0x0092 # <control>
0x93 0x0093 # <control>
0x94 0x0094 # <control>
0x95 0x0095 # <control>
0x96 0x0096 # <control>
0x97 0x0097 # <control>
0x98 0x0098 # <control>
0x99 0x0099 # <control>
0x9A 0x009A # <control>
0x9B 0x009B # <control>
0x9C 0x009C # <control>
0x9D 0x009D # <control>
0x9E 0x009E # <control>
0x9F 0x009F # <control>
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x1E02 # LATIN CAPITAL LETTER B WITH DOT ABOVE
0xA2 0x1E03 # LATIN SMALL LETTER B WITH DOT ABOVE
0xA3 0x00A3 # POUND SIGN
0xA4 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE
0xA5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE
0xA6 0x1E0A # LATIN CAPITAL LETTER D WITH DOT ABOVE
0xA7 0x00A7 # SECTION SIGN
0xA8 0x1E80 # LATIN CAPITAL LETTER W WITH GRAVE
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x1E82 # LATIN CAPITAL LETTER W WITH ACUTE
0xAB 0x1E0B # LATIN SMALL LETTER D WITH DOT ABOVE
0xAC 0x1EF2 # LATIN CAPITAL LETTER Y WITH GRAVE
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x00AE # REGISTERED SIGN
0xAF 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
0xB0 0x1E1E # LATIN CAPITAL LETTER F WITH DOT ABOVE
0xB1 0x1E1F # LATIN SMALL LETTER F WITH DOT ABOVE
0xB2 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE
0xB3 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE
0xB4 0x1E40 # LATIN CAPITAL LETTER M WITH DOT ABOVE
0xB5 0x1E41 # LATIN SMALL LETTER M WITH DOT ABOVE
0xB6 0x00B6 # PILCROW SIGN
0xB7 0x1E56 # LATIN CAPITAL LETTER P WITH DOT ABOVE
0xB8 0x1E81 # LATIN SMALL LETTER W WITH GRAVE
0xB9 0x1E57 # LATIN SMALL LETTER P WITH DOT ABOVE
0xBA 0x1E83 # LATIN SMALL LETTER W WITH ACUTE
0xBB 0x1E60 # LATIN CAPITAL LETTER S WITH DOT ABOVE
0xBC 0x1EF3 # LATIN SMALL LETTER Y WITH GRAVE
0xBD 0x1E84 # LATIN CAPITAL LETTER W WITH DIAERESIS
0xBE 0x1E85 # LATIN SMALL LETTER W WITH DIAERESIS
0xBF 0x1E61 # LATIN SMALL LETTER S 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
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 0x0174 # LATIN CAPITAL LETTER W WITH CIRCUMFLEX
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 0x1E6A # LATIN CAPITAL LETTER T WITH DOT ABOVE
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 0x0176 # LATIN CAPITAL LETTER Y 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
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 0x0175 # LATIN SMALL LETTER W WITH CIRCUMFLEX
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 0x1E6B # LATIN SMALL LETTER T WITH DOT ABOVE
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 0x0177 # LATIN SMALL LETTER Y WITH CIRCUMFLEX
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,96 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+00A1 : INVERTED EXCLAMATION MARK
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+20AC : EURO SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+0160 : LATIN CAPITAL LETTER S WITH CARON
A7 = U+00A7 : SECTION SIGN
A8 = U+0161 : LATIN SMALL LETTER S WITH CARON
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00AA : FEMININE ORDINAL INDICATOR
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+017D : LATIN CAPITAL LETTER Z WITH CARON
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+017E : LATIN SMALL LETTER Z WITH CARON
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00BA : MASCULINE ORDINAL INDICATOR
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+0152 : LATIN CAPITAL LIGATURE OE
BD = U+0153 : LATIN SMALL LIGATURE OE
BE = U+0178 : LATIN CAPITAL LETTER Y WITH DIAERESIS
BF = U+00BF : INVERTED QUESTION MARK
C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+00C3 : LATIN CAPITAL LETTER A WITH TILDE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+00C6 : LATIN CAPITAL LETTER AE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+00CC : LATIN CAPITAL LETTER I WITH GRAVE
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
D0 = U+00D0 : LATIN CAPITAL LETTER ETH
D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
D2 = U+00D2 : LATIN CAPITAL LETTER O WITH GRAVE
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+00DD : LATIN CAPITAL LETTER Y WITH ACUTE
DE = U+00DE : LATIN CAPITAL LETTER THORN
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+00E3 : LATIN SMALL LETTER A WITH TILDE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+00E6 : LATIN SMALL LETTER AE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+00EC : LATIN SMALL LETTER I WITH GRAVE
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F0 = U+00F0 : LATIN SMALL LETTER ETH
F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
F2 = U+00F2 : LATIN SMALL LETTER O WITH GRAVE
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+00FD : LATIN SMALL LETTER Y WITH ACUTE
FE = U+00FE : LATIN SMALL LETTER THORN
FF = U+00FF : LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,299 @@
#
# Name: ISO/IEC 8859-16:2001 to Unicode
# Unicode version: 3.0
# Table version: 1.0
# Table format: Format A
# Date: 2001 July 26
# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
#
# Copyright (c) 1999-2001 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on optical media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Unicode, Inc. hereby grants the right to freely use the information
# supplied in this file in the creation of products supporting the
# Unicode Standard, and to make copies of this file in any form for
# internal or external distribution as long as this notice remains
# attached.
#
# General notes:
#
# This table contains the data the Unicode Consortium has on how
# ISO/IEC 8859-16:2001 characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the ISO/IEC 8859-16 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 8859-16 order.
#
# Updated versions of this file may be found in:
# <ftp://ftp.unicode.org/Public/MAPPINGS/>
#
# Any comments or problems, contact <errata@unicode.org>
# Please note that <errata@unicode.org> is an archival address;
# notices will be checked, but do not expect an immediate response.
#
0x00 0x0000 # NULL
0x01 0x0001 # START OF HEADING
0x02 0x0002 # START OF TEXT
0x03 0x0003 # END OF TEXT
0x04 0x0004 # END OF TRANSMISSION
0x05 0x0005 # ENQUIRY
0x06 0x0006 # ACKNOWLEDGE
0x07 0x0007 # BELL
0x08 0x0008 # BACKSPACE
0x09 0x0009 # HORIZONTAL TABULATION
0x0A 0x000A # LINE FEED
0x0B 0x000B # VERTICAL TABULATION
0x0C 0x000C # FORM FEED
0x0D 0x000D # CARRIAGE RETURN
0x0E 0x000E # SHIFT OUT
0x0F 0x000F # SHIFT IN
0x10 0x0010 # DATA LINK ESCAPE
0x11 0x0011 # DEVICE CONTROL ONE
0x12 0x0012 # DEVICE CONTROL TWO
0x13 0x0013 # DEVICE CONTROL THREE
0x14 0x0014 # DEVICE CONTROL FOUR
0x15 0x0015 # NEGATIVE ACKNOWLEDGE
0x16 0x0016 # SYNCHRONOUS IDLE
0x17 0x0017 # END OF TRANSMISSION BLOCK
0x18 0x0018 # CANCEL
0x19 0x0019 # END OF MEDIUM
0x1A 0x001A # SUBSTITUTE
0x1B 0x001B # ESCAPE
0x1C 0x001C # FILE SEPARATOR
0x1D 0x001D # GROUP SEPARATOR
0x1E 0x001E # RECORD SEPARATOR
0x1F 0x001F # UNIT SEPARATOR
0x20 0x0020 # SPACE
0x21 0x0021 # EXCLAMATION MARK
0x22 0x0022 # QUOTATION MARK
0x23 0x0023 # NUMBER SIGN
0x24 0x0024 # DOLLAR SIGN
0x25 0x0025 # PERCENT SIGN
0x26 0x0026 # AMPERSAND
0x27 0x0027 # APOSTROPHE
0x28 0x0028 # LEFT PARENTHESIS
0x29 0x0029 # RIGHT PARENTHESIS
0x2A 0x002A # ASTERISK
0x2B 0x002B # PLUS SIGN
0x2C 0x002C # COMMA
0x2D 0x002D # HYPHEN-MINUS
0x2E 0x002E # FULL STOP
0x2F 0x002F # SOLIDUS
0x30 0x0030 # DIGIT ZERO
0x31 0x0031 # DIGIT ONE
0x32 0x0032 # DIGIT TWO
0x33 0x0033 # DIGIT THREE
0x34 0x0034 # DIGIT FOUR
0x35 0x0035 # DIGIT FIVE
0x36 0x0036 # DIGIT SIX
0x37 0x0037 # DIGIT SEVEN
0x38 0x0038 # DIGIT EIGHT
0x39 0x0039 # DIGIT NINE
0x3A 0x003A # COLON
0x3B 0x003B # SEMICOLON
0x3C 0x003C # LESS-THAN SIGN
0x3D 0x003D # EQUALS SIGN
0x3E 0x003E # GREATER-THAN SIGN
0x3F 0x003F # QUESTION MARK
0x40 0x0040 # COMMERCIAL AT
0x41 0x0041 # LATIN CAPITAL LETTER A
0x42 0x0042 # LATIN CAPITAL LETTER B
0x43 0x0043 # LATIN CAPITAL LETTER C
0x44 0x0044 # LATIN CAPITAL LETTER D
0x45 0x0045 # LATIN CAPITAL LETTER E
0x46 0x0046 # LATIN CAPITAL LETTER F
0x47 0x0047 # LATIN CAPITAL LETTER G
0x48 0x0048 # LATIN CAPITAL LETTER H
0x49 0x0049 # LATIN CAPITAL LETTER I
0x4A 0x004A # LATIN CAPITAL LETTER J
0x4B 0x004B # LATIN CAPITAL LETTER K
0x4C 0x004C # LATIN CAPITAL LETTER L
0x4D 0x004D # LATIN CAPITAL LETTER M
0x4E 0x004E # LATIN CAPITAL LETTER N
0x4F 0x004F # LATIN CAPITAL LETTER O
0x50 0x0050 # LATIN CAPITAL LETTER P
0x51 0x0051 # LATIN CAPITAL LETTER Q
0x52 0x0052 # LATIN CAPITAL LETTER R
0x53 0x0053 # LATIN CAPITAL LETTER S
0x54 0x0054 # LATIN CAPITAL LETTER T
0x55 0x0055 # LATIN CAPITAL LETTER U
0x56 0x0056 # LATIN CAPITAL LETTER V
0x57 0x0057 # LATIN CAPITAL LETTER W
0x58 0x0058 # LATIN CAPITAL LETTER X
0x59 0x0059 # LATIN CAPITAL LETTER Y
0x5A 0x005A # LATIN CAPITAL LETTER Z
0x5B 0x005B # LEFT SQUARE BRACKET
0x5C 0x005C # REVERSE SOLIDUS
0x5D 0x005D # RIGHT SQUARE BRACKET
0x5E 0x005E # CIRCUMFLEX ACCENT
0x5F 0x005F # LOW LINE
0x60 0x0060 # GRAVE ACCENT
0x61 0x0061 # LATIN SMALL LETTER A
0x62 0x0062 # LATIN SMALL LETTER B
0x63 0x0063 # LATIN SMALL LETTER C
0x64 0x0064 # LATIN SMALL LETTER D
0x65 0x0065 # LATIN SMALL LETTER E
0x66 0x0066 # LATIN SMALL LETTER F
0x67 0x0067 # LATIN SMALL LETTER G
0x68 0x0068 # LATIN SMALL LETTER H
0x69 0x0069 # LATIN SMALL LETTER I
0x6A 0x006A # LATIN SMALL LETTER J
0x6B 0x006B # LATIN SMALL LETTER K
0x6C 0x006C # LATIN SMALL LETTER L
0x6D 0x006D # LATIN SMALL LETTER M
0x6E 0x006E # LATIN SMALL LETTER N
0x6F 0x006F # LATIN SMALL LETTER O
0x70 0x0070 # LATIN SMALL LETTER P
0x71 0x0071 # LATIN SMALL LETTER Q
0x72 0x0072 # LATIN SMALL LETTER R
0x73 0x0073 # LATIN SMALL LETTER S
0x74 0x0074 # LATIN SMALL LETTER T
0x75 0x0075 # LATIN SMALL LETTER U
0x76 0x0076 # LATIN SMALL LETTER V
0x77 0x0077 # LATIN SMALL LETTER W
0x78 0x0078 # LATIN SMALL LETTER X
0x79 0x0079 # LATIN SMALL LETTER Y
0x7A 0x007A # LATIN SMALL LETTER Z
0x7B 0x007B # LEFT CURLY BRACKET
0x7C 0x007C # VERTICAL LINE
0x7D 0x007D # RIGHT CURLY BRACKET
0x7E 0x007E # TILDE
0x7F 0x007F # DELETE
0x80 0x0080 # <control>
0x81 0x0081 # <control>
0x82 0x0082 # <control>
0x83 0x0083 # <control>
0x84 0x0084 # <control>
0x85 0x0085 # <control>
0x86 0x0086 # <control>
0x87 0x0087 # <control>
0x88 0x0088 # <control>
0x89 0x0089 # <control>
0x8A 0x008A # <control>
0x8B 0x008B # <control>
0x8C 0x008C # <control>
0x8D 0x008D # <control>
0x8E 0x008E # <control>
0x8F 0x008F # <control>
0x90 0x0090 # <control>
0x91 0x0091 # <control>
0x92 0x0092 # <control>
0x93 0x0093 # <control>
0x94 0x0094 # <control>
0x95 0x0095 # <control>
0x96 0x0096 # <control>
0x97 0x0097 # <control>
0x98 0x0098 # <control>
0x99 0x0099 # <control>
0x9A 0x009A # <control>
0x9B 0x009B # <control>
0x9C 0x009C # <control>
0x9D 0x009D # <control>
0x9E 0x009E # <control>
0x9F 0x009F # <control>
0xA0 0x00A0 # NO-BREAK SPACE
0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
0xA2 0x0105 # LATIN SMALL LETTER A WITH OGONEK
0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
0xA4 0x20AC # EURO SIGN
0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK
0xA6 0x0160 # LATIN CAPITAL LETTER S WITH CARON
0xA7 0x00A7 # SECTION SIGN
0xA8 0x0161 # LATIN SMALL LETTER S WITH CARON
0xA9 0x00A9 # COPYRIGHT SIGN
0xAA 0x0218 # LATIN CAPITAL LETTER S WITH COMMA BELOW
0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
0xAD 0x00AD # SOFT HYPHEN
0xAE 0x017A # LATIN SMALL LETTER Z WITH ACUTE
0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
0xB0 0x00B0 # DEGREE SIGN
0xB1 0x00B1 # PLUS-MINUS SIGN
0xB2 0x010C # LATIN CAPITAL LETTER C WITH CARON
0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE
0xB4 0x017D # LATIN CAPITAL LETTER Z WITH CARON
0xB5 0x201D # RIGHT DOUBLE QUOTATION MARK
0xB6 0x00B6 # PILCROW SIGN
0xB7 0x00B7 # MIDDLE DOT
0xB8 0x017E # LATIN SMALL LETTER Z WITH CARON
0xB9 0x010D # LATIN SMALL LETTER C WITH CARON
0xBA 0x0219 # LATIN SMALL LETTER S WITH COMMA BELOW
0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
0xBC 0x0152 # LATIN CAPITAL LIGATURE OE
0xBD 0x0153 # LATIN SMALL LIGATURE OE
0xBE 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
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
0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE
0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
0xC5 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
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 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
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 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
0xD7 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
0xD8 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
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 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
0xDE 0x021A # LATIN CAPITAL LETTER T WITH COMMA BELOW
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 0x0107 # LATIN SMALL LETTER C WITH ACUTE
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 0x0111 # LATIN SMALL LETTER D WITH STROKE
0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
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 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE
0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
0xF7 0x015B # LATIN SMALL LETTER S WITH ACUTE
0xF8 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE
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 0x0119 # LATIN SMALL LETTER E WITH OGONEK
0xFE 0x021B # LATIN SMALL LETTER T WITH COMMA BELOW
0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,96 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+0104 : LATIN CAPITAL LETTER A WITH OGONEK
A2 = U+02D8 : BREVE
A3 = U+0141 : LATIN CAPITAL LETTER L WITH STROKE
A4 = U+00A4 : CURRENCY SIGN
A5 = U+013D : LATIN CAPITAL LETTER L WITH CARON
A6 = U+015A : LATIN CAPITAL LETTER S WITH ACUTE
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+0160 : LATIN CAPITAL LETTER S WITH CARON
AA = U+015E : LATIN CAPITAL LETTER S WITH CEDILLA
AB = U+0164 : LATIN CAPITAL LETTER T WITH CARON
AC = U+0179 : LATIN CAPITAL LETTER Z WITH ACUTE
AD = U+00AD : SOFT HYPHEN
AE = U+017D : LATIN CAPITAL LETTER Z WITH CARON
AF = U+017B : LATIN CAPITAL LETTER Z WITH DOT ABOVE
B0 = U+00B0 : DEGREE SIGN
B1 = U+0105 : LATIN SMALL LETTER A WITH OGONEK
B2 = U+02DB : OGONEK
B3 = U+0142 : LATIN SMALL LETTER L WITH STROKE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+013E : LATIN SMALL LETTER L WITH CARON
B6 = U+015B : LATIN SMALL LETTER S WITH ACUTE
B7 = U+02C7 : CARON
B8 = U+00B8 : CEDILLA
B9 = U+0161 : LATIN SMALL LETTER S WITH CARON
BA = U+015F : LATIN SMALL LETTER S WITH CEDILLA
BB = U+0165 : LATIN SMALL LETTER T WITH CARON
BC = U+017A : LATIN SMALL LETTER Z WITH ACUTE
BD = U+02DD : DOUBLE ACUTE ACCENT
BE = U+017E : LATIN SMALL LETTER Z WITH CARON
BF = U+017C : LATIN SMALL LETTER Z WITH DOT ABOVE
C0 = U+0154 : LATIN CAPITAL LETTER R WITH ACUTE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+0102 : LATIN CAPITAL LETTER A WITH BREVE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+0139 : LATIN CAPITAL LETTER L WITH ACUTE
C6 = U+0106 : LATIN CAPITAL LETTER C WITH ACUTE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+010C : LATIN CAPITAL LETTER C WITH CARON
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+0118 : LATIN CAPITAL LETTER E WITH OGONEK
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+011A : LATIN CAPITAL LETTER E WITH CARON
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+010E : LATIN CAPITAL LETTER D WITH CARON
D0 = U+0110 : LATIN CAPITAL LETTER D WITH STROKE
D1 = U+0143 : LATIN CAPITAL LETTER N WITH ACUTE
D2 = U+0147 : LATIN CAPITAL LETTER N WITH CARON
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+0150 : LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+0158 : LATIN CAPITAL LETTER R WITH CARON
D9 = U+016E : LATIN CAPITAL LETTER U WITH RING ABOVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+0170 : LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+00DD : LATIN CAPITAL LETTER Y WITH ACUTE
DE = U+0162 : LATIN CAPITAL LETTER T WITH CEDILLA
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+0155 : LATIN SMALL LETTER R WITH ACUTE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+0103 : LATIN SMALL LETTER A WITH BREVE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+013A : LATIN SMALL LETTER L WITH ACUTE
E6 = U+0107 : LATIN SMALL LETTER C WITH ACUTE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+010D : LATIN SMALL LETTER C WITH CARON
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+0119 : LATIN SMALL LETTER E WITH OGONEK
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+011B : LATIN SMALL LETTER E WITH CARON
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+010F : LATIN SMALL LETTER D WITH CARON
F0 = U+0111 : LATIN SMALL LETTER D WITH STROKE
F1 = U+0144 : LATIN SMALL LETTER N WITH ACUTE
F2 = U+0148 : LATIN SMALL LETTER N WITH CARON
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+0151 : LATIN SMALL LETTER O WITH DOUBLE ACUTE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+0159 : LATIN SMALL LETTER R WITH CARON
F9 = U+016F : LATIN SMALL LETTER U WITH RING ABOVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+0171 : LATIN SMALL LETTER U WITH DOUBLE ACUTE
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+00FD : LATIN SMALL LETTER Y WITH ACUTE
FE = U+0163 : LATIN SMALL LETTER T WITH CEDILLA
FF = U+02D9 : DOT ABOVE

View file

@ -0,0 +1,89 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+0126 : LATIN CAPITAL LETTER H WITH STROKE
A2 = U+02D8 : BREVE
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A6 = U+0124 : LATIN CAPITAL LETTER H WITH CIRCUMFLEX
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+0130 : LATIN CAPITAL LETTER I WITH DOT ABOVE
AA = U+015E : LATIN CAPITAL LETTER S WITH CEDILLA
AB = U+011E : LATIN CAPITAL LETTER G WITH BREVE
AC = U+0134 : LATIN CAPITAL LETTER J WITH CIRCUMFLEX
AD = U+00AD : SOFT HYPHEN
AF = U+017B : LATIN CAPITAL LETTER Z WITH DOT ABOVE
B0 = U+00B0 : DEGREE SIGN
B1 = U+0127 : LATIN SMALL LETTER H WITH STROKE
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+0125 : LATIN SMALL LETTER H WITH CIRCUMFLEX
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+0131 : LATIN SMALL LETTER DOTLESS I
BA = U+015F : LATIN SMALL LETTER S WITH CEDILLA
BB = U+011F : LATIN SMALL LETTER G WITH BREVE
BC = U+0135 : LATIN SMALL LETTER J WITH CIRCUMFLEX
BD = U+00BD : VULGAR FRACTION ONE HALF
BF = U+017C : LATIN SMALL LETTER Z WITH DOT ABOVE
C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+010A : LATIN CAPITAL LETTER C WITH DOT ABOVE
C6 = U+0108 : LATIN CAPITAL LETTER C WITH CIRCUMFLEX
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+00CC : LATIN CAPITAL LETTER I WITH GRAVE
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
D2 = U+00D2 : LATIN CAPITAL LETTER O WITH GRAVE
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+0120 : LATIN CAPITAL LETTER G WITH DOT ABOVE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+011C : LATIN CAPITAL LETTER G WITH CIRCUMFLEX
D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+016C : LATIN CAPITAL LETTER U WITH BREVE
DE = U+015C : LATIN CAPITAL LETTER S WITH CIRCUMFLEX
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+010B : LATIN SMALL LETTER C WITH DOT ABOVE
E6 = U+0109 : LATIN SMALL LETTER C WITH CIRCUMFLEX
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+00EC : LATIN SMALL LETTER I WITH GRAVE
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
F2 = U+00F2 : LATIN SMALL LETTER O WITH GRAVE
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+0121 : LATIN SMALL LETTER G WITH DOT ABOVE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+011D : LATIN SMALL LETTER G WITH CIRCUMFLEX
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+016D : LATIN SMALL LETTER U WITH BREVE
FE = U+015D : LATIN SMALL LETTER S WITH CIRCUMFLEX
FF = U+02D9 : DOT ABOVE

View file

@ -0,0 +1,96 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+0104 : LATIN CAPITAL LETTER A WITH OGONEK
A2 = U+0138 : LATIN SMALL LETTER KRA
A3 = U+0156 : LATIN CAPITAL LETTER R WITH CEDILLA
A4 = U+00A4 : CURRENCY SIGN
A5 = U+0128 : LATIN CAPITAL LETTER I WITH TILDE
A6 = U+013B : LATIN CAPITAL LETTER L WITH CEDILLA
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+0160 : LATIN CAPITAL LETTER S WITH CARON
AA = U+0112 : LATIN CAPITAL LETTER E WITH MACRON
AB = U+0122 : LATIN CAPITAL LETTER G WITH CEDILLA
AC = U+0166 : LATIN CAPITAL LETTER T WITH STROKE
AD = U+00AD : SOFT HYPHEN
AE = U+017D : LATIN CAPITAL LETTER Z WITH CARON
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+0105 : LATIN SMALL LETTER A WITH OGONEK
B2 = U+02DB : OGONEK
B3 = U+0157 : LATIN SMALL LETTER R WITH CEDILLA
B4 = U+00B4 : ACUTE ACCENT
B5 = U+0129 : LATIN SMALL LETTER I WITH TILDE
B6 = U+013C : LATIN SMALL LETTER L WITH CEDILLA
B7 = U+02C7 : CARON
B8 = U+00B8 : CEDILLA
B9 = U+0161 : LATIN SMALL LETTER S WITH CARON
BA = U+0113 : LATIN SMALL LETTER E WITH MACRON
BB = U+0123 : LATIN SMALL LETTER G WITH CEDILLA
BC = U+0167 : LATIN SMALL LETTER T WITH STROKE
BD = U+014A : LATIN CAPITAL LETTER ENG
BE = U+017E : LATIN SMALL LETTER Z WITH CARON
BF = U+014B : LATIN SMALL LETTER ENG
C0 = U+0100 : LATIN CAPITAL LETTER A WITH MACRON
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+00C3 : LATIN CAPITAL LETTER A WITH TILDE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+00C6 : LATIN CAPITAL LETTER AE
C7 = U+012E : LATIN CAPITAL LETTER I WITH OGONEK
C8 = U+010C : LATIN CAPITAL LETTER C WITH CARON
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+0118 : LATIN CAPITAL LETTER E WITH OGONEK
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+0116 : LATIN CAPITAL LETTER E WITH DOT ABOVE
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+012A : LATIN CAPITAL LETTER I WITH MACRON
D0 = U+0110 : LATIN CAPITAL LETTER D WITH STROKE
D1 = U+0145 : LATIN CAPITAL LETTER N WITH CEDILLA
D2 = U+014C : LATIN CAPITAL LETTER O WITH MACRON
D3 = U+0136 : LATIN CAPITAL LETTER K WITH CEDILLA
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
D9 = U+0172 : LATIN CAPITAL LETTER U WITH OGONEK
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+0168 : LATIN CAPITAL LETTER U WITH TILDE
DE = U+016A : LATIN CAPITAL LETTER U WITH MACRON
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+0101 : LATIN SMALL LETTER A WITH MACRON
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+00E3 : LATIN SMALL LETTER A WITH TILDE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+00E6 : LATIN SMALL LETTER AE
E7 = U+012F : LATIN SMALL LETTER I WITH OGONEK
E8 = U+010D : LATIN SMALL LETTER C WITH CARON
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+0119 : LATIN SMALL LETTER E WITH OGONEK
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+0117 : LATIN SMALL LETTER E WITH DOT ABOVE
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+012B : LATIN SMALL LETTER I WITH MACRON
F0 = U+0111 : LATIN SMALL LETTER D WITH STROKE
F1 = U+0146 : LATIN SMALL LETTER N WITH CEDILLA
F2 = U+014D : LATIN SMALL LETTER O WITH MACRON
F3 = U+0137 : LATIN SMALL LETTER K WITH CEDILLA
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
F9 = U+0173 : LATIN SMALL LETTER U WITH OGONEK
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+0169 : LATIN SMALL LETTER U WITH TILDE
FE = U+016B : LATIN SMALL LETTER U WITH MACRON
FF = U+02D9 : DOT ABOVE

View file

@ -0,0 +1,96 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+0401 : CYRILLIC CAPITAL LETTER IO
A2 = U+0402 : CYRILLIC CAPITAL LETTER DJE
A3 = U+0403 : CYRILLIC CAPITAL LETTER GJE
A4 = U+0404 : CYRILLIC CAPITAL LETTER UKRAINIAN IE
A5 = U+0405 : CYRILLIC CAPITAL LETTER DZE
A6 = U+0406 : CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
A7 = U+0407 : CYRILLIC CAPITAL LETTER YI
A8 = U+0408 : CYRILLIC CAPITAL LETTER JE
A9 = U+0409 : CYRILLIC CAPITAL LETTER LJE
AA = U+040A : CYRILLIC CAPITAL LETTER NJE
AB = U+040B : CYRILLIC CAPITAL LETTER TSHE
AC = U+040C : CYRILLIC CAPITAL LETTER KJE
AD = U+00AD : SOFT HYPHEN
AE = U+040E : CYRILLIC CAPITAL LETTER SHORT U
AF = U+040F : CYRILLIC CAPITAL LETTER DZHE
B0 = U+0410 : CYRILLIC CAPITAL LETTER A
B1 = U+0411 : CYRILLIC CAPITAL LETTER BE
B2 = U+0412 : CYRILLIC CAPITAL LETTER VE
B3 = U+0413 : CYRILLIC CAPITAL LETTER GHE
B4 = U+0414 : CYRILLIC CAPITAL LETTER DE
B5 = U+0415 : CYRILLIC CAPITAL LETTER IE
B6 = U+0416 : CYRILLIC CAPITAL LETTER ZHE
B7 = U+0417 : CYRILLIC CAPITAL LETTER ZE
B8 = U+0418 : CYRILLIC CAPITAL LETTER I
B9 = U+0419 : CYRILLIC CAPITAL LETTER SHORT I
BA = U+041A : CYRILLIC CAPITAL LETTER KA
BB = U+041B : CYRILLIC CAPITAL LETTER EL
BC = U+041C : CYRILLIC CAPITAL LETTER EM
BD = U+041D : CYRILLIC CAPITAL LETTER EN
BE = U+041E : CYRILLIC CAPITAL LETTER O
BF = U+041F : CYRILLIC CAPITAL LETTER PE
C0 = U+0420 : CYRILLIC CAPITAL LETTER ER
C1 = U+0421 : CYRILLIC CAPITAL LETTER ES
C2 = U+0422 : CYRILLIC CAPITAL LETTER TE
C3 = U+0423 : CYRILLIC CAPITAL LETTER U
C4 = U+0424 : CYRILLIC CAPITAL LETTER EF
C5 = U+0425 : CYRILLIC CAPITAL LETTER HA
C6 = U+0426 : CYRILLIC CAPITAL LETTER TSE
C7 = U+0427 : CYRILLIC CAPITAL LETTER CHE
C8 = U+0428 : CYRILLIC CAPITAL LETTER SHA
C9 = U+0429 : CYRILLIC CAPITAL LETTER SHCHA
CA = U+042A : CYRILLIC CAPITAL LETTER HARD SIGN
CB = U+042B : CYRILLIC CAPITAL LETTER YERU
CC = U+042C : CYRILLIC CAPITAL LETTER SOFT SIGN
CD = U+042D : CYRILLIC CAPITAL LETTER E
CE = U+042E : CYRILLIC CAPITAL LETTER YU
CF = U+042F : CYRILLIC CAPITAL LETTER YA
D0 = U+0430 : CYRILLIC SMALL LETTER A
D1 = U+0431 : CYRILLIC SMALL LETTER BE
D2 = U+0432 : CYRILLIC SMALL LETTER VE
D3 = U+0433 : CYRILLIC SMALL LETTER GHE
D4 = U+0434 : CYRILLIC SMALL LETTER DE
D5 = U+0435 : CYRILLIC SMALL LETTER IE
D6 = U+0436 : CYRILLIC SMALL LETTER ZHE
D7 = U+0437 : CYRILLIC SMALL LETTER ZE
D8 = U+0438 : CYRILLIC SMALL LETTER I
D9 = U+0439 : CYRILLIC SMALL LETTER SHORT I
DA = U+043A : CYRILLIC SMALL LETTER KA
DB = U+043B : CYRILLIC SMALL LETTER EL
DC = U+043C : CYRILLIC SMALL LETTER EM
DD = U+043D : CYRILLIC SMALL LETTER EN
DE = U+043E : CYRILLIC SMALL LETTER O
DF = U+043F : CYRILLIC SMALL LETTER PE
E0 = U+0440 : CYRILLIC SMALL LETTER ER
E1 = U+0441 : CYRILLIC SMALL LETTER ES
E2 = U+0442 : CYRILLIC SMALL LETTER TE
E3 = U+0443 : CYRILLIC SMALL LETTER U
E4 = U+0444 : CYRILLIC SMALL LETTER EF
E5 = U+0445 : CYRILLIC SMALL LETTER HA
E6 = U+0446 : CYRILLIC SMALL LETTER TSE
E7 = U+0447 : CYRILLIC SMALL LETTER CHE
E8 = U+0448 : CYRILLIC SMALL LETTER SHA
E9 = U+0449 : CYRILLIC SMALL LETTER SHCHA
EA = U+044A : CYRILLIC SMALL LETTER HARD SIGN
EB = U+044B : CYRILLIC SMALL LETTER YERU
EC = U+044C : CYRILLIC SMALL LETTER SOFT SIGN
ED = U+044D : CYRILLIC SMALL LETTER E
EE = U+044E : CYRILLIC SMALL LETTER YU
EF = U+044F : CYRILLIC SMALL LETTER YA
F0 = U+2116 : NUMERO SIGN
F1 = U+0451 : CYRILLIC SMALL LETTER IO
F2 = U+0452 : CYRILLIC SMALL LETTER DJE
F3 = U+0453 : CYRILLIC SMALL LETTER GJE
F4 = U+0454 : CYRILLIC SMALL LETTER UKRAINIAN IE
F5 = U+0455 : CYRILLIC SMALL LETTER DZE
F6 = U+0456 : CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
F7 = U+0457 : CYRILLIC SMALL LETTER YI
F8 = U+0458 : CYRILLIC SMALL LETTER JE
F9 = U+0459 : CYRILLIC SMALL LETTER LJE
FA = U+045A : CYRILLIC SMALL LETTER NJE
FB = U+045B : CYRILLIC SMALL LETTER TSHE
FC = U+045C : CYRILLIC SMALL LETTER KJE
FD = U+00A7 : SECTION SIGN
FE = U+045E : CYRILLIC SMALL LETTER SHORT U
FF = U+045F : CYRILLIC SMALL LETTER DZHE

View file

@ -0,0 +1,51 @@
A0 = U+00A0 : NO-BREAK SPACE
A4 = U+00A4 : CURRENCY SIGN
AC = U+060C : ARABIC COMMA
AD = U+00AD : SOFT HYPHEN
BB = U+061B : ARABIC SEMICOLON
BF = U+061F : ARABIC QUESTION MARK
C1 = U+0621 : ARABIC LETTER HAMZA
C2 = U+0622 : ARABIC LETTER ALEF WITH MADDA ABOVE
C3 = U+0623 : ARABIC LETTER ALEF WITH HAMZA ABOVE
C4 = U+0624 : ARABIC LETTER WAW WITH HAMZA ABOVE
C5 = U+0625 : ARABIC LETTER ALEF WITH HAMZA BELOW
C6 = U+0626 : ARABIC LETTER YEH WITH HAMZA ABOVE
C7 = U+0627 : ARABIC LETTER ALEF
C8 = U+0628 : ARABIC LETTER BEH
C9 = U+0629 : ARABIC LETTER TEH MARBUTA
CA = U+062A : ARABIC LETTER TEH
CB = U+062B : ARABIC LETTER THEH
CC = U+062C : ARABIC LETTER JEEM
CD = U+062D : ARABIC LETTER HAH
CE = U+062E : ARABIC LETTER KHAH
CF = U+062F : ARABIC LETTER DAL
D0 = U+0630 : ARABIC LETTER THAL
D1 = U+0631 : ARABIC LETTER REH
D2 = U+0632 : ARABIC LETTER ZAIN
D3 = U+0633 : ARABIC LETTER SEEN
D4 = U+0634 : ARABIC LETTER SHEEN
D5 = U+0635 : ARABIC LETTER SAD
D6 = U+0636 : ARABIC LETTER DAD
D7 = U+0637 : ARABIC LETTER TAH
D8 = U+0638 : ARABIC LETTER ZAH
D9 = U+0639 : ARABIC LETTER AIN
DA = U+063A : ARABIC LETTER GHAIN
E0 = U+0640 : ARABIC TATWEEL
E1 = U+0641 : ARABIC LETTER FEH
E2 = U+0642 : ARABIC LETTER QAF
E3 = U+0643 : ARABIC LETTER KAF
E4 = U+0644 : ARABIC LETTER LAM
E5 = U+0645 : ARABIC LETTER MEEM
E6 = U+0646 : ARABIC LETTER NOON
E7 = U+0647 : ARABIC LETTER HEH
E8 = U+0648 : ARABIC LETTER WAW
E9 = U+0649 : ARABIC LETTER ALEF MAKSURA
EA = U+064A : ARABIC LETTER YEH
EB = U+064B : ARABIC FATHATAN
EC = U+064C : ARABIC DAMMATAN
ED = U+064D : ARABIC KASRATAN
EE = U+064E : ARABIC FATHA
EF = U+064F : ARABIC DAMMA
F0 = U+0650 : ARABIC KASRA
F1 = U+0651 : ARABIC SHADDA
F2 = U+0652 : ARABIC SUKUN

View file

@ -0,0 +1,90 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+02BD : MODIFIER LETTER REVERSED COMMA
A2 = U+02BC : MODIFIER LETTER APOSTROPHE
A3 = U+00A3 : POUND SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AF = U+2015 : HORIZONTAL BAR
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+0384 : GREEK TONOS
B5 = U+0385 : GREEK DIALYTIKA TONOS
B6 = U+0386 : GREEK CAPITAL LETTER ALPHA WITH TONOS
B7 = U+00B7 : MIDDLE DOT
B8 = U+0388 : GREEK CAPITAL LETTER EPSILON WITH TONOS
B9 = U+0389 : GREEK CAPITAL LETTER ETA WITH TONOS
BA = U+038A : GREEK CAPITAL LETTER IOTA WITH TONOS
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+038C : GREEK CAPITAL LETTER OMICRON WITH TONOS
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+038E : GREEK CAPITAL LETTER UPSILON WITH TONOS
BF = U+038F : GREEK CAPITAL LETTER OMEGA WITH TONOS
C0 = U+0390 : GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
C1 = U+0391 : GREEK CAPITAL LETTER ALPHA
C2 = U+0392 : GREEK CAPITAL LETTER BETA
C3 = U+0393 : GREEK CAPITAL LETTER GAMMA
C4 = U+0394 : GREEK CAPITAL LETTER DELTA
C5 = U+0395 : GREEK CAPITAL LETTER EPSILON
C6 = U+0396 : GREEK CAPITAL LETTER ZETA
C7 = U+0397 : GREEK CAPITAL LETTER ETA
C8 = U+0398 : GREEK CAPITAL LETTER THETA
C9 = U+0399 : GREEK CAPITAL LETTER IOTA
CA = U+039A : GREEK CAPITAL LETTER KAPPA
CB = U+039B : GREEK CAPITAL LETTER LAMDA
CC = U+039C : GREEK CAPITAL LETTER MU
CD = U+039D : GREEK CAPITAL LETTER NU
CE = U+039E : GREEK CAPITAL LETTER XI
CF = U+039F : GREEK CAPITAL LETTER OMICRON
D0 = U+03A0 : GREEK CAPITAL LETTER PI
D1 = U+03A1 : GREEK CAPITAL LETTER RHO
D3 = U+03A3 : GREEK CAPITAL LETTER SIGMA
D4 = U+03A4 : GREEK CAPITAL LETTER TAU
D5 = U+03A5 : GREEK CAPITAL LETTER UPSILON
D6 = U+03A6 : GREEK CAPITAL LETTER PHI
D7 = U+03A7 : GREEK CAPITAL LETTER CHI
D8 = U+03A8 : GREEK CAPITAL LETTER PSI
D9 = U+03A9 : GREEK CAPITAL LETTER OMEGA
DA = U+03AA : GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
DB = U+03AB : GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
DC = U+03AC : GREEK SMALL LETTER ALPHA WITH TONOS
DD = U+03AD : GREEK SMALL LETTER EPSILON WITH TONOS
DE = U+03AE : GREEK SMALL LETTER ETA WITH TONOS
DF = U+03AF : GREEK SMALL LETTER IOTA WITH TONOS
E0 = U+03B0 : GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
E1 = U+03B1 : GREEK SMALL LETTER ALPHA
E2 = U+03B2 : GREEK SMALL LETTER BETA
E3 = U+03B3 : GREEK SMALL LETTER GAMMA
E4 = U+03B4 : GREEK SMALL LETTER DELTA
E5 = U+03B5 : GREEK SMALL LETTER EPSILON
E6 = U+03B6 : GREEK SMALL LETTER ZETA
E7 = U+03B7 : GREEK SMALL LETTER ETA
E8 = U+03B8 : GREEK SMALL LETTER THETA
E9 = U+03B9 : GREEK SMALL LETTER IOTA
EA = U+03BA : GREEK SMALL LETTER KAPPA
EB = U+03BB : GREEK SMALL LETTER LAMDA
EC = U+03BC : GREEK SMALL LETTER MU
ED = U+03BD : GREEK SMALL LETTER NU
EE = U+03BE : GREEK SMALL LETTER XI
EF = U+03BF : GREEK SMALL LETTER OMICRON
F0 = U+03C0 : GREEK SMALL LETTER PI
F1 = U+03C1 : GREEK SMALL LETTER RHO
F2 = U+03C2 : GREEK SMALL LETTER FINAL SIGMA
F3 = U+03C3 : GREEK SMALL LETTER SIGMA
F4 = U+03C4 : GREEK SMALL LETTER TAU
F5 = U+03C5 : GREEK SMALL LETTER UPSILON
F6 = U+03C6 : GREEK SMALL LETTER PHI
F7 = U+03C7 : GREEK SMALL LETTER CHI
F8 = U+03C8 : GREEK SMALL LETTER PSI
F9 = U+03C9 : GREEK SMALL LETTER OMEGA
FA = U+03CA : GREEK SMALL LETTER IOTA WITH DIALYTIKA
FB = U+03CB : GREEK SMALL LETTER UPSILON WITH DIALYTIKA
FC = U+03CC : GREEK SMALL LETTER OMICRON WITH TONOS
FD = U+03CD : GREEK SMALL LETTER UPSILON WITH TONOS
FE = U+03CE : GREEK SMALL LETTER OMEGA WITH TONOS

View file

@ -0,0 +1,58 @@
A0 = U+00A0 : NO-BREAK SPACE
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00D7 : MULTIPLICATION SIGN
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+203E : OVERLINE
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00F7 : DIVISION SIGN
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
DF = U+2017 : DOUBLE LOW LINE
E0 = U+05D0 : HEBREW LETTER ALEF
E1 = U+05D1 : HEBREW LETTER BET
E2 = U+05D2 : HEBREW LETTER GIMEL
E3 = U+05D3 : HEBREW LETTER DALET
E4 = U+05D4 : HEBREW LETTER HE
E5 = U+05D5 : HEBREW LETTER VAV
E6 = U+05D6 : HEBREW LETTER ZAYIN
E7 = U+05D7 : HEBREW LETTER HET
E8 = U+05D8 : HEBREW LETTER TET
E9 = U+05D9 : HEBREW LETTER YOD
EA = U+05DA : HEBREW LETTER FINAL KAF
EB = U+05DB : HEBREW LETTER KAF
EC = U+05DC : HEBREW LETTER LAMED
ED = U+05DD : HEBREW LETTER FINAL MEM
EE = U+05DE : HEBREW LETTER MEM
EF = U+05DF : HEBREW LETTER FINAL NUN
F0 = U+05E0 : HEBREW LETTER NUN
F1 = U+05E1 : HEBREW LETTER SAMEKH
F2 = U+05E2 : HEBREW LETTER AYIN
F3 = U+05E3 : HEBREW LETTER FINAL PE
F4 = U+05E4 : HEBREW LETTER PE
F5 = U+05E5 : HEBREW LETTER FINAL TSADI
F6 = U+05E6 : HEBREW LETTER TSADI
F7 = U+05E7 : HEBREW LETTER QOF
F8 = U+05E8 : HEBREW LETTER RESH
F9 = U+05E9 : HEBREW LETTER SHIN
FA = U+05EA : HEBREW LETTER TAV

View file

@ -0,0 +1,96 @@
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+00A1 : INVERTED EXCLAMATION MARK
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00AA : FEMININE ORDINAL INDICATOR
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00BA : MASCULINE ORDINAL INDICATOR
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+00BF : INVERTED QUESTION MARK
C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+00C3 : LATIN CAPITAL LETTER A WITH TILDE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+00C6 : LATIN CAPITAL LETTER AE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+00CC : LATIN CAPITAL LETTER I WITH GRAVE
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
D0 = U+011E : LATIN CAPITAL LETTER G WITH BREVE
D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
D2 = U+00D2 : LATIN CAPITAL LETTER O WITH GRAVE
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+0130 : LATIN CAPITAL LETTER I WITH DOT ABOVE
DE = U+015E : LATIN CAPITAL LETTER S WITH CEDILLA
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+00E3 : LATIN SMALL LETTER A WITH TILDE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+00E6 : LATIN SMALL LETTER AE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+00EC : LATIN SMALL LETTER I WITH GRAVE
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F0 = U+011F : LATIN SMALL LETTER G WITH BREVE
F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
F2 = U+00F2 : LATIN SMALL LETTER O WITH GRAVE
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+0131 : LATIN SMALL LETTER DOTLESS I
FE = U+015F : LATIN SMALL LETTER S WITH CEDILLA
FF = U+00FF : LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,302 @@
#
# Name: KOI8-R (RFC1489) to Unicode
# Unicode version: 3.0
# Table version: 1.0
# Table format: Format A
# Date: 18 August 1999
# Authors: Helmut Richter <richter@lrz.de>
#
# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on optical media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Unicode, Inc. hereby grants the right to freely use the information
# supplied in this file in the creation of products supporting the
# Unicode Standard, and to make copies of this file in any form for
# internal or external distribution as long as this notice remains
# attached.
#
# 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.
#
# Any comments or problems, contact <errata@unicode.org>
# Please note that <errata@unicode.org> is an archival address;
# notices will be checked, but do not expect an immediate response.
#
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

View file

@ -0,0 +1,187 @@
Charset Conversion Tables
The files in this directory contains conversion tables from a number of charsets (corresponding to the filenames) to UNICODE.
This is used by the TYPO3 class "t3lib_cs" which uses these tables when asked to convert a string from one charset to another.
Conversion tables are reproduced from http://www.microsoft.com/globaldev/reference/cphome.mspx
Found overview on this page: http://www.i18nguy.com/unicode/codepages.html
A mirror of Czyborra's pages: http://aspell.net/charsets/
Further a lot of mapping tables are found here as well:
http://www.unicode.org/Public/MAPPINGS/
PARSING:
The conversion table files are parsed linie by linie, extracting by either of these formulars:
Syntax 1:
[Local charset value, hex] = U+[UNICODE hex number] : [descriptive text, ignored]
Example:
A0 = U+00A0 : NO-BREAK SPACE
(eg. iso-8859-1.tbl)
Syntax 2:
0x[Local charset value, hex] 0x[UNICODE hex number] [descriptive text, ignored]
Example:
0xA0 0x00A0 NO-BREAK SPACE
(eg. big5.tbl)
Lines beginning with "#" or empty lines are ignored.
The syntax is auto-detected based on the first line found in the file.
Syntax 2 is directly from http://www.unicode.org/Public/MAPPINGS/ and you can probably take any charmap there and just copy into th csconvtbl/ folder and it will be ready for use.
INDEX:
iso-8859-1.tbl
ISO Character Set 8859-1 (Latin 1)
http://www.microsoft.com/globaldev/reference/iso/28591.htm
iso-8859-2.tbl
ISO Character Set 8859-2 (Latin 2)
http://www.microsoft.com/globaldev/reference/iso/28592.htm
iso-8859-3.tbl
ISO Character Set 8859-3 (Latin 3)
http://www.microsoft.com/globaldev/reference/iso/28593.htm
iso-8859-4.tbl
ISO Character Set 8859-4 (Baltic)
http://www.microsoft.com/globaldev/reference/iso/28594.htm
iso-8859-5.tbl
ISO Character Set 8859-5 (Cyrillic)
http://www.microsoft.com/globaldev/reference/iso/28595.htm
iso-8859-6.tbl
ISO Character Set 8859-6 (Arabic)
http://www.microsoft.com/globaldev/reference/iso/28596.htm
iso-8859-7.tbl
ISO Character Set 8859-7 (Greek)
http://www.microsoft.com/globaldev/reference/iso/28597.htm
iso-8859-8.tbl
ISO Character Set 8859-8 (Hebrew)
http://www.microsoft.com/globaldev/reference/iso/28598.htm
iso-8859-9.tbl
ISO Character Set 8859-9 (Turkish)
http://www.microsoft.com/globaldev/reference/iso/28599.htm
iso-8859-10.tbl
ISO Character Set 8859-10
http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-10.TXT
iso-8859-11.tbl
ISO Character Set 8859-11 (Thai)
http://czyborra.com/charsets/iso8859.html
http://aspell.net/charsets/iso8859.html
http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT
iso-8859-13.tbl
ISO Character Set 8859-13 (Lithuanian)
http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-13.TXT
iso-8859-14.tbl
ISO Character Set 8859-14 (Celtic)
http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-10.TXT
iso-8859-15.tbl
ISO Character Set 8859-15 (Latin 9)
http://www.microsoft.com/globaldev/reference/iso/28605.htm
iso-8859-16.tbl
ISO Character Set 8859-16 (Romanian)
http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT
windows-1250.tbl
Microsoft Windows Codepage : 1250 (Central Europe)
http://www.microsoft.com/globaldev/reference/sbcs/1250.htm
windows-1251.tbl
Microsoft Windows Codepage : 1251 (Cyrillic)
http://www.microsoft.com/globaldev/reference/sbcs/1251.htm
windows-1252.tbl
Microsoft Windows Codepage : 1252 (Latin I)
http://www.microsoft.com/globaldev/reference/sbcs/1252.htm
windows-1253.tbl
Microsoft Windows Code Page : 1253 (Greek)
http://www.microsoft.com/globaldev/reference/sbcs/1253.htm
windows-1254.tbl
Microsoft Windows Codepage : 1254 (Turkish)
http://www.microsoft.com/globaldev/reference/sbcs/1254.htm
windows-1255.tbl
Microsoft Windows Codepage : 1255 (Hebrew)
http://www.microsoft.com/globaldev/reference/sbcs/1255.htm
windows-1256.tbl
Microsoft Windows Codepage : 1256 (Arabic)
http://www.microsoft.com/globaldev/reference/sbcs/1256.htm
windows-1257.tbl
Microsoft Windows Codepage : 1257 (Baltic)
http://www.microsoft.com/globaldev/reference/sbcs/1257.htm
windows-1258.tbl
Microsoft Windows Codepage : 1258 (Viet Nam)
http://www.microsoft.com/globaldev/reference/sbcs/1258.htm
windows-874.tbl
Microsoft Windows Codepage : 874 (Thai)
http://www.microsoft.com/globaldev/reference/sbcs/874.htm
shift_jis.tbl
Microsoft Windows Codepage : 932 (Japanese Shift-JIS)
http://www.microsoft.com/globaldev/reference/dbcs/932.htm
(Multibyte)
gb2312.tbl
Microsoft Windows Codepage : 936 (Simplified Chinese GBK)
gb2312 936 Chinese Simplified (GB2312)
gb_2312-80 936 Chinese Simplified (GB2312)
http://www.microsoft.com/globaldev/reference/dbcs/936.htm
(Multibyte)
Note: this is a MS-specific superset of the real GB2312
euc-kr.tbl
Microsoft Windows Codepage : 949 (Korean EUC-KR)
http://www.microsoft.com/globaldev/reference/dbcs/932.htm
(Multibyte)
Note: this is a MS-specific superset of the real EUC-KR
big5.tbl
Microsoft Windows Codepage : 950 (Traditional Chinese Big5)
http://www.microsoft.com/globaldev/reference/dbcs/950.htm
(Multibyte)
Note: this is a MS-specific superset of the real Big5
koi8-r.tbl
Cyrillic (Russian)
http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,123 @@
80 = U+20AC : EURO SIGN
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
89 = U+2030 : PER MILLE SIGN
8A = U+0160 : LATIN CAPITAL LETTER S WITH CARON
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
8C = U+015A : LATIN CAPITAL LETTER S WITH ACUTE
8D = U+0164 : LATIN CAPITAL LETTER T WITH CARON
8E = U+017D : LATIN CAPITAL LETTER Z WITH CARON
8F = U+0179 : LATIN CAPITAL LETTER Z WITH ACUTE
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
99 = U+2122 : TRADE MARK SIGN
9A = U+0161 : LATIN SMALL LETTER S WITH CARON
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
9C = U+015B : LATIN SMALL LETTER S WITH ACUTE
9D = U+0165 : LATIN SMALL LETTER T WITH CARON
9E = U+017E : LATIN SMALL LETTER Z WITH CARON
9F = U+017A : LATIN SMALL LETTER Z WITH ACUTE
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+02C7 : CARON
A2 = U+02D8 : BREVE
A3 = U+0141 : LATIN CAPITAL LETTER L WITH STROKE
A4 = U+00A4 : CURRENCY SIGN
A5 = U+0104 : LATIN CAPITAL LETTER A WITH OGONEK
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+015E : LATIN CAPITAL LETTER S WITH CEDILLA
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+017B : LATIN CAPITAL LETTER Z WITH DOT ABOVE
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+02DB : OGONEK
B3 = U+0142 : LATIN SMALL LETTER L WITH STROKE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+0105 : LATIN SMALL LETTER A WITH OGONEK
BA = U+015F : LATIN SMALL LETTER S WITH CEDILLA
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+013D : LATIN CAPITAL LETTER L WITH CARON
BD = U+02DD : DOUBLE ACUTE ACCENT
BE = U+013E : LATIN SMALL LETTER L WITH CARON
BF = U+017C : LATIN SMALL LETTER Z WITH DOT ABOVE
C0 = U+0154 : LATIN CAPITAL LETTER R WITH ACUTE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+0102 : LATIN CAPITAL LETTER A WITH BREVE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+0139 : LATIN CAPITAL LETTER L WITH ACUTE
C6 = U+0106 : LATIN CAPITAL LETTER C WITH ACUTE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+010C : LATIN CAPITAL LETTER C WITH CARON
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+0118 : LATIN CAPITAL LETTER E WITH OGONEK
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+011A : LATIN CAPITAL LETTER E WITH CARON
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+010E : LATIN CAPITAL LETTER D WITH CARON
D0 = U+0110 : LATIN CAPITAL LETTER D WITH STROKE
D1 = U+0143 : LATIN CAPITAL LETTER N WITH ACUTE
D2 = U+0147 : LATIN CAPITAL LETTER N WITH CARON
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+0150 : LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+0158 : LATIN CAPITAL LETTER R WITH CARON
D9 = U+016E : LATIN CAPITAL LETTER U WITH RING ABOVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+0170 : LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+00DD : LATIN CAPITAL LETTER Y WITH ACUTE
DE = U+0162 : LATIN CAPITAL LETTER T WITH CEDILLA
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+0155 : LATIN SMALL LETTER R WITH ACUTE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+0103 : LATIN SMALL LETTER A WITH BREVE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+013A : LATIN SMALL LETTER L WITH ACUTE
E6 = U+0107 : LATIN SMALL LETTER C WITH ACUTE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+010D : LATIN SMALL LETTER C WITH CARON
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+0119 : LATIN SMALL LETTER E WITH OGONEK
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+011B : LATIN SMALL LETTER E WITH CARON
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+010F : LATIN SMALL LETTER D WITH CARON
F0 = U+0111 : LATIN SMALL LETTER D WITH STROKE
F1 = U+0144 : LATIN SMALL LETTER N WITH ACUTE
F2 = U+0148 : LATIN SMALL LETTER N WITH CARON
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+0151 : LATIN SMALL LETTER O WITH DOUBLE ACUTE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+0159 : LATIN SMALL LETTER R WITH CARON
F9 = U+016F : LATIN SMALL LETTER U WITH RING ABOVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+0171 : LATIN SMALL LETTER U WITH DOUBLE ACUTE
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+00FD : LATIN SMALL LETTER Y WITH ACUTE
FE = U+0163 : LATIN SMALL LETTER T WITH CEDILLA
FF = U+02D9 : DOT ABOVE

View file

@ -0,0 +1,127 @@
80 = U+0402 : CYRILLIC CAPITAL LETTER DJE
81 = U+0403 : CYRILLIC CAPITAL LETTER GJE
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
83 = U+0453 : CYRILLIC SMALL LETTER GJE
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
88 = U+20AC : EURO SIGN
89 = U+2030 : PER MILLE SIGN
8A = U+0409 : CYRILLIC CAPITAL LETTER LJE
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
8C = U+040A : CYRILLIC CAPITAL LETTER NJE
8D = U+040C : CYRILLIC CAPITAL LETTER KJE
8E = U+040B : CYRILLIC CAPITAL LETTER TSHE
8F = U+040F : CYRILLIC CAPITAL LETTER DZHE
90 = U+0452 : CYRILLIC SMALL LETTER DJE
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
99 = U+2122 : TRADE MARK SIGN
9A = U+0459 : CYRILLIC SMALL LETTER LJE
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
9C = U+045A : CYRILLIC SMALL LETTER NJE
9D = U+045C : CYRILLIC SMALL LETTER KJE
9E = U+045B : CYRILLIC SMALL LETTER TSHE
9F = U+045F : CYRILLIC SMALL LETTER DZHE
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+040E : CYRILLIC CAPITAL LETTER SHORT U
A2 = U+045E : CYRILLIC SMALL LETTER SHORT U
A3 = U+0408 : CYRILLIC CAPITAL LETTER JE
A4 = U+00A4 : CURRENCY SIGN
A5 = U+0490 : CYRILLIC CAPITAL LETTER GHE WITH UPTURN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+0401 : CYRILLIC CAPITAL LETTER IO
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+0404 : CYRILLIC CAPITAL LETTER UKRAINIAN IE
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+0407 : CYRILLIC CAPITAL LETTER YI
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+0406 : CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
B3 = U+0456 : CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
B4 = U+0491 : CYRILLIC SMALL LETTER GHE WITH UPTURN
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+0451 : CYRILLIC SMALL LETTER IO
B9 = U+2116 : NUMERO SIGN
BA = U+0454 : CYRILLIC SMALL LETTER UKRAINIAN IE
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+0458 : CYRILLIC SMALL LETTER JE
BD = U+0405 : CYRILLIC CAPITAL LETTER DZE
BE = U+0455 : CYRILLIC SMALL LETTER DZE
BF = U+0457 : CYRILLIC SMALL LETTER YI
C0 = U+0410 : CYRILLIC CAPITAL LETTER A
C1 = U+0411 : CYRILLIC CAPITAL LETTER BE
C2 = U+0412 : CYRILLIC CAPITAL LETTER VE
C3 = U+0413 : CYRILLIC CAPITAL LETTER GHE
C4 = U+0414 : CYRILLIC CAPITAL LETTER DE
C5 = U+0415 : CYRILLIC CAPITAL LETTER IE
C6 = U+0416 : CYRILLIC CAPITAL LETTER ZHE
C7 = U+0417 : CYRILLIC CAPITAL LETTER ZE
C8 = U+0418 : CYRILLIC CAPITAL LETTER I
C9 = U+0419 : CYRILLIC CAPITAL LETTER SHORT I
CA = U+041A : CYRILLIC CAPITAL LETTER KA
CB = U+041B : CYRILLIC CAPITAL LETTER EL
CC = U+041C : CYRILLIC CAPITAL LETTER EM
CD = U+041D : CYRILLIC CAPITAL LETTER EN
CE = U+041E : CYRILLIC CAPITAL LETTER O
CF = U+041F : CYRILLIC CAPITAL LETTER PE
D0 = U+0420 : CYRILLIC CAPITAL LETTER ER
D1 = U+0421 : CYRILLIC CAPITAL LETTER ES
D2 = U+0422 : CYRILLIC CAPITAL LETTER TE
D3 = U+0423 : CYRILLIC CAPITAL LETTER U
D4 = U+0424 : CYRILLIC CAPITAL LETTER EF
D5 = U+0425 : CYRILLIC CAPITAL LETTER HA
D6 = U+0426 : CYRILLIC CAPITAL LETTER TSE
D7 = U+0427 : CYRILLIC CAPITAL LETTER CHE
D8 = U+0428 : CYRILLIC CAPITAL LETTER SHA
D9 = U+0429 : CYRILLIC CAPITAL LETTER SHCHA
DA = U+042A : CYRILLIC CAPITAL LETTER HARD SIGN
DB = U+042B : CYRILLIC CAPITAL LETTER YERU
DC = U+042C : CYRILLIC CAPITAL LETTER SOFT SIGN
DD = U+042D : CYRILLIC CAPITAL LETTER E
DE = U+042E : CYRILLIC CAPITAL LETTER YU
DF = U+042F : CYRILLIC CAPITAL LETTER YA
E0 = U+0430 : CYRILLIC SMALL LETTER A
E1 = U+0431 : CYRILLIC SMALL LETTER BE
E2 = U+0432 : CYRILLIC SMALL LETTER VE
E3 = U+0433 : CYRILLIC SMALL LETTER GHE
E4 = U+0434 : CYRILLIC SMALL LETTER DE
E5 = U+0435 : CYRILLIC SMALL LETTER IE
E6 = U+0436 : CYRILLIC SMALL LETTER ZHE
E7 = U+0437 : CYRILLIC SMALL LETTER ZE
E8 = U+0438 : CYRILLIC SMALL LETTER I
E9 = U+0439 : CYRILLIC SMALL LETTER SHORT I
EA = U+043A : CYRILLIC SMALL LETTER KA
EB = U+043B : CYRILLIC SMALL LETTER EL
EC = U+043C : CYRILLIC SMALL LETTER EM
ED = U+043D : CYRILLIC SMALL LETTER EN
EE = U+043E : CYRILLIC SMALL LETTER O
EF = U+043F : CYRILLIC SMALL LETTER PE
F0 = U+0440 : CYRILLIC SMALL LETTER ER
F1 = U+0441 : CYRILLIC SMALL LETTER ES
F2 = U+0442 : CYRILLIC SMALL LETTER TE
F3 = U+0443 : CYRILLIC SMALL LETTER U
F4 = U+0444 : CYRILLIC SMALL LETTER EF
F5 = U+0445 : CYRILLIC SMALL LETTER HA
F6 = U+0446 : CYRILLIC SMALL LETTER TSE
F7 = U+0447 : CYRILLIC SMALL LETTER CHE
F8 = U+0448 : CYRILLIC SMALL LETTER SHA
F9 = U+0449 : CYRILLIC SMALL LETTER SHCHA
FA = U+044A : CYRILLIC SMALL LETTER HARD SIGN
FB = U+044B : CYRILLIC SMALL LETTER YERU
FC = U+044C : CYRILLIC SMALL LETTER SOFT SIGN
FD = U+044D : CYRILLIC SMALL LETTER E
FE = U+044E : CYRILLIC SMALL LETTER YU
FF = U+044F : CYRILLIC SMALL LETTER YA

View file

@ -0,0 +1,123 @@
80 = U+20AC : EURO SIGN
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
83 = U+0192 : LATIN SMALL LETTER F WITH HOOK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
88 = U+02C6 : MODIFIER LETTER CIRCUMFLEX ACCENT
89 = U+2030 : PER MILLE SIGN
8A = U+0160 : LATIN CAPITAL LETTER S WITH CARON
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
8C = U+0152 : LATIN CAPITAL LIGATURE OE
8E = U+017D : LATIN CAPITAL LETTER Z WITH CARON
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
98 = U+02DC : SMALL TILDE
99 = U+2122 : TRADE MARK SIGN
9A = U+0161 : LATIN SMALL LETTER S WITH CARON
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
9C = U+0153 : LATIN SMALL LIGATURE OE
9E = U+017E : LATIN SMALL LETTER Z WITH CARON
9F = U+0178 : LATIN CAPITAL LETTER Y WITH DIAERESIS
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+00A1 : INVERTED EXCLAMATION MARK
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00AA : FEMININE ORDINAL INDICATOR
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00BA : MASCULINE ORDINAL INDICATOR
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+00BF : INVERTED QUESTION MARK
C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+00C3 : LATIN CAPITAL LETTER A WITH TILDE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+00C6 : LATIN CAPITAL LETTER AE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+00CC : LATIN CAPITAL LETTER I WITH GRAVE
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
D0 = U+00D0 : LATIN CAPITAL LETTER ETH
D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
D2 = U+00D2 : LATIN CAPITAL LETTER O WITH GRAVE
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+00DD : LATIN CAPITAL LETTER Y WITH ACUTE
DE = U+00DE : LATIN CAPITAL LETTER THORN
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+00E3 : LATIN SMALL LETTER A WITH TILDE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+00E6 : LATIN SMALL LETTER AE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+00EC : LATIN SMALL LETTER I WITH GRAVE
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F0 = U+00F0 : LATIN SMALL LETTER ETH
F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
F2 = U+00F2 : LATIN SMALL LETTER O WITH GRAVE
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+00FD : LATIN SMALL LETTER Y WITH ACUTE
FE = U+00FE : LATIN SMALL LETTER THORN
FF = U+00FF : LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,111 @@
80 = U+20AC : EURO SIGN
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
83 = U+0192 : LATIN SMALL LETTER F WITH HOOK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
89 = U+2030 : PER MILLE SIGN
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
99 = U+2122 : TRADE MARK SIGN
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+0385 : GREEK DIALYTIKA TONOS
A2 = U+0386 : GREEK CAPITAL LETTER ALPHA WITH TONOS
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+2015 : HORIZONTAL BAR
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+0384 : GREEK TONOS
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+0388 : GREEK CAPITAL LETTER EPSILON WITH TONOS
B9 = U+0389 : GREEK CAPITAL LETTER ETA WITH TONOS
BA = U+038A : GREEK CAPITAL LETTER IOTA WITH TONOS
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+038C : GREEK CAPITAL LETTER OMICRON WITH TONOS
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+038E : GREEK CAPITAL LETTER UPSILON WITH TONOS
BF = U+038F : GREEK CAPITAL LETTER OMEGA WITH TONOS
C0 = U+0390 : GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
C1 = U+0391 : GREEK CAPITAL LETTER ALPHA
C2 = U+0392 : GREEK CAPITAL LETTER BETA
C3 = U+0393 : GREEK CAPITAL LETTER GAMMA
C4 = U+0394 : GREEK CAPITAL LETTER DELTA
C5 = U+0395 : GREEK CAPITAL LETTER EPSILON
C6 = U+0396 : GREEK CAPITAL LETTER ZETA
C7 = U+0397 : GREEK CAPITAL LETTER ETA
C8 = U+0398 : GREEK CAPITAL LETTER THETA
C9 = U+0399 : GREEK CAPITAL LETTER IOTA
CA = U+039A : GREEK CAPITAL LETTER KAPPA
CB = U+039B : GREEK CAPITAL LETTER LAMDA
CC = U+039C : GREEK CAPITAL LETTER MU
CD = U+039D : GREEK CAPITAL LETTER NU
CE = U+039E : GREEK CAPITAL LETTER XI
CF = U+039F : GREEK CAPITAL LETTER OMICRON
D0 = U+03A0 : GREEK CAPITAL LETTER PI
D1 = U+03A1 : GREEK CAPITAL LETTER RHO
D3 = U+03A3 : GREEK CAPITAL LETTER SIGMA
D4 = U+03A4 : GREEK CAPITAL LETTER TAU
D5 = U+03A5 : GREEK CAPITAL LETTER UPSILON
D6 = U+03A6 : GREEK CAPITAL LETTER PHI
D7 = U+03A7 : GREEK CAPITAL LETTER CHI
D8 = U+03A8 : GREEK CAPITAL LETTER PSI
D9 = U+03A9 : GREEK CAPITAL LETTER OMEGA
DA = U+03AA : GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
DB = U+03AB : GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
DC = U+03AC : GREEK SMALL LETTER ALPHA WITH TONOS
DD = U+03AD : GREEK SMALL LETTER EPSILON WITH TONOS
DE = U+03AE : GREEK SMALL LETTER ETA WITH TONOS
DF = U+03AF : GREEK SMALL LETTER IOTA WITH TONOS
E0 = U+03B0 : GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
E1 = U+03B1 : GREEK SMALL LETTER ALPHA
E2 = U+03B2 : GREEK SMALL LETTER BETA
E3 = U+03B3 : GREEK SMALL LETTER GAMMA
E4 = U+03B4 : GREEK SMALL LETTER DELTA
E5 = U+03B5 : GREEK SMALL LETTER EPSILON
E6 = U+03B6 : GREEK SMALL LETTER ZETA
E7 = U+03B7 : GREEK SMALL LETTER ETA
E8 = U+03B8 : GREEK SMALL LETTER THETA
E9 = U+03B9 : GREEK SMALL LETTER IOTA
EA = U+03BA : GREEK SMALL LETTER KAPPA
EB = U+03BB : GREEK SMALL LETTER LAMDA
EC = U+03BC : GREEK SMALL LETTER MU
ED = U+03BD : GREEK SMALL LETTER NU
EE = U+03BE : GREEK SMALL LETTER XI
EF = U+03BF : GREEK SMALL LETTER OMICRON
F0 = U+03C0 : GREEK SMALL LETTER PI
F1 = U+03C1 : GREEK SMALL LETTER RHO
F2 = U+03C2 : GREEK SMALL LETTER FINAL SIGMA
F3 = U+03C3 : GREEK SMALL LETTER SIGMA
F4 = U+03C4 : GREEK SMALL LETTER TAU
F5 = U+03C5 : GREEK SMALL LETTER UPSILON
F6 = U+03C6 : GREEK SMALL LETTER PHI
F7 = U+03C7 : GREEK SMALL LETTER CHI
F8 = U+03C8 : GREEK SMALL LETTER PSI
F9 = U+03C9 : GREEK SMALL LETTER OMEGA
FA = U+03CA : GREEK SMALL LETTER IOTA WITH DIALYTIKA
FB = U+03CB : GREEK SMALL LETTER UPSILON WITH DIALYTIKA
FC = U+03CC : GREEK SMALL LETTER OMICRON WITH TONOS
FD = U+03CD : GREEK SMALL LETTER UPSILON WITH TONOS
FE = U+03CE : GREEK SMALL LETTER OMEGA WITH TONOS

View file

@ -0,0 +1,121 @@
80 = U+20AC : EURO SIGN
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
83 = U+0192 : LATIN SMALL LETTER F WITH HOOK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
88 = U+02C6 : MODIFIER LETTER CIRCUMFLEX ACCENT
89 = U+2030 : PER MILLE SIGN
8A = U+0160 : LATIN CAPITAL LETTER S WITH CARON
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
8C = U+0152 : LATIN CAPITAL LIGATURE OE
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
98 = U+02DC : SMALL TILDE
99 = U+2122 : TRADE MARK SIGN
9A = U+0161 : LATIN SMALL LETTER S WITH CARON
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
9C = U+0153 : LATIN SMALL LIGATURE OE
9F = U+0178 : LATIN CAPITAL LETTER Y WITH DIAERESIS
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+00A1 : INVERTED EXCLAMATION MARK
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00AA : FEMININE ORDINAL INDICATOR
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00BA : MASCULINE ORDINAL INDICATOR
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+00BF : INVERTED QUESTION MARK
C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+00C3 : LATIN CAPITAL LETTER A WITH TILDE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+00C6 : LATIN CAPITAL LETTER AE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+00CC : LATIN CAPITAL LETTER I WITH GRAVE
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
D0 = U+011E : LATIN CAPITAL LETTER G WITH BREVE
D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
D2 = U+00D2 : LATIN CAPITAL LETTER O WITH GRAVE
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+0130 : LATIN CAPITAL LETTER I WITH DOT ABOVE
DE = U+015E : LATIN CAPITAL LETTER S WITH CEDILLA
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+00E3 : LATIN SMALL LETTER A WITH TILDE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+00E6 : LATIN SMALL LETTER AE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+00EC : LATIN SMALL LETTER I WITH GRAVE
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F0 = U+011F : LATIN SMALL LETTER G WITH BREVE
F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
F2 = U+00F2 : LATIN SMALL LETTER O WITH GRAVE
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+0131 : LATIN SMALL LETTER DOTLESS I
FE = U+015F : LATIN SMALL LETTER S WITH CEDILLA
FF = U+00FF : LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,105 @@
80 = U+20AC : EURO SIGN
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
83 = U+0192 : LATIN SMALL LETTER F WITH HOOK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
88 = U+02C6 : MODIFIER LETTER CIRCUMFLEX ACCENT
89 = U+2030 : PER MILLE SIGN
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
98 = U+02DC : SMALL TILDE
99 = U+2122 : TRADE MARK SIGN
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+00A1 : INVERTED EXCLAMATION MARK
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+20AA : NEW SHEQEL SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00D7 : MULTIPLICATION SIGN
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00F7 : DIVISION SIGN
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+00BF : INVERTED QUESTION MARK
C0 = U+05B0 : HEBREW POINT SHEVA
C1 = U+05B1 : HEBREW POINT HATAF SEGOL
C2 = U+05B2 : HEBREW POINT HATAF PATAH
C3 = U+05B3 : HEBREW POINT HATAF QAMATS
C4 = U+05B4 : HEBREW POINT HIRIQ
C5 = U+05B5 : HEBREW POINT TSERE
C6 = U+05B6 : HEBREW POINT SEGOL
C7 = U+05B7 : HEBREW POINT PATAH
C8 = U+05B8 : HEBREW POINT QAMATS
C9 = U+05B9 : HEBREW POINT HOLAM
CB = U+05BB : HEBREW POINT QUBUTS
CC = U+05BC : HEBREW POINT DAGESH OR MAPIQ
CD = U+05BD : HEBREW POINT METEG
CE = U+05BE : HEBREW PUNCTUATION MAQAF
CF = U+05BF : HEBREW POINT RAFE
D0 = U+05C0 : HEBREW PUNCTUATION PASEQ
D1 = U+05C1 : HEBREW POINT SHIN DOT
D2 = U+05C2 : HEBREW POINT SIN DOT
D3 = U+05C3 : HEBREW PUNCTUATION SOF PASUQ
D4 = U+05F0 : HEBREW LIGATURE YIDDISH DOUBLE VAV
D5 = U+05F1 : HEBREW LIGATURE YIDDISH VAV YOD
D6 = U+05F2 : HEBREW LIGATURE YIDDISH DOUBLE YOD
D7 = U+05F3 : HEBREW PUNCTUATION GERESH
D8 = U+05F4 : HEBREW PUNCTUATION GERSHAYIM
E0 = U+05D0 : HEBREW LETTER ALEF
E1 = U+05D1 : HEBREW LETTER BET
E2 = U+05D2 : HEBREW LETTER GIMEL
E3 = U+05D3 : HEBREW LETTER DALET
E4 = U+05D4 : HEBREW LETTER HE
E5 = U+05D5 : HEBREW LETTER VAV
E6 = U+05D6 : HEBREW LETTER ZAYIN
E7 = U+05D7 : HEBREW LETTER HET
E8 = U+05D8 : HEBREW LETTER TET
E9 = U+05D9 : HEBREW LETTER YOD
EA = U+05DA : HEBREW LETTER FINAL KAF
EB = U+05DB : HEBREW LETTER KAF
EC = U+05DC : HEBREW LETTER LAMED
ED = U+05DD : HEBREW LETTER FINAL MEM
EE = U+05DE : HEBREW LETTER MEM
EF = U+05DF : HEBREW LETTER FINAL NUN
F0 = U+05E0 : HEBREW LETTER NUN
F1 = U+05E1 : HEBREW LETTER SAMEKH
F2 = U+05E2 : HEBREW LETTER AYIN
F3 = U+05E3 : HEBREW LETTER FINAL PE
F4 = U+05E4 : HEBREW LETTER PE
F5 = U+05E5 : HEBREW LETTER FINAL TSADI
F6 = U+05E6 : HEBREW LETTER TSADI
F7 = U+05E7 : HEBREW LETTER QOF
F8 = U+05E8 : HEBREW LETTER RESH
F9 = U+05E9 : HEBREW LETTER SHIN
FA = U+05EA : HEBREW LETTER TAV
FD = U+200E : LEFT-TO-RIGHT MARK
FE = U+200F : RIGHT-TO-LEFT MARK

View file

@ -0,0 +1,128 @@
80 = U+20AC : EURO SIGN
81 = U+067E : ARABIC LETTER PEH
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
83 = U+0192 : LATIN SMALL LETTER F WITH HOOK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
88 = U+02C6 : MODIFIER LETTER CIRCUMFLEX ACCENT
89 = U+2030 : PER MILLE SIGN
8A = U+0679 : ARABIC LETTER TTEH
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
8C = U+0152 : LATIN CAPITAL LIGATURE OE
8D = U+0686 : ARABIC LETTER TCHEH
8E = U+0698 : ARABIC LETTER JEH
8F = U+0688 : ARABIC LETTER DDAL
90 = U+06AF : ARABIC LETTER GAF
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
98 = U+06A9 : ARABIC LETTER KEHEH
99 = U+2122 : TRADE MARK SIGN
9A = U+0691 : ARABIC LETTER RREH
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
9C = U+0153 : LATIN SMALL LIGATURE OE
9D = U+200C : ZERO WIDTH NON-JOINER
9E = U+200D : ZERO WIDTH JOINER
9F = U+06BA : ARABIC LETTER NOON GHUNNA
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+060C : ARABIC COMMA
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+06BE : ARABIC LETTER HEH DOACHASHMEE
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+061B : ARABIC SEMICOLON
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+061F : ARABIC QUESTION MARK
C0 = U+06C1 : ARABIC LETTER HEH GOAL
C1 = U+0621 : ARABIC LETTER HAMZA
C2 = U+0622 : ARABIC LETTER ALEF WITH MADDA ABOVE
C3 = U+0623 : ARABIC LETTER ALEF WITH HAMZA ABOVE
C4 = U+0624 : ARABIC LETTER WAW WITH HAMZA ABOVE
C5 = U+0625 : ARABIC LETTER ALEF WITH HAMZA BELOW
C6 = U+0626 : ARABIC LETTER YEH WITH HAMZA ABOVE
C7 = U+0627 : ARABIC LETTER ALEF
C8 = U+0628 : ARABIC LETTER BEH
C9 = U+0629 : ARABIC LETTER TEH MARBUTA
CA = U+062A : ARABIC LETTER TEH
CB = U+062B : ARABIC LETTER THEH
CC = U+062C : ARABIC LETTER JEEM
CD = U+062D : ARABIC LETTER HAH
CE = U+062E : ARABIC LETTER KHAH
CF = U+062F : ARABIC LETTER DAL
D0 = U+0630 : ARABIC LETTER THAL
D1 = U+0631 : ARABIC LETTER REH
D2 = U+0632 : ARABIC LETTER ZAIN
D3 = U+0633 : ARABIC LETTER SEEN
D4 = U+0634 : ARABIC LETTER SHEEN
D5 = U+0635 : ARABIC LETTER SAD
D6 = U+0636 : ARABIC LETTER DAD
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+0637 : ARABIC LETTER TAH
D9 = U+0638 : ARABIC LETTER ZAH
DA = U+0639 : ARABIC LETTER AIN
DB = U+063A : ARABIC LETTER GHAIN
DC = U+0640 : ARABIC TATWEEL
DD = U+0641 : ARABIC LETTER FEH
DE = U+0642 : ARABIC LETTER QAF
DF = U+0643 : ARABIC LETTER KAF
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+0644 : ARABIC LETTER LAM
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+0645 : ARABIC LETTER MEEM
E4 = U+0646 : ARABIC LETTER NOON
E5 = U+0647 : ARABIC LETTER HEH
E6 = U+0648 : ARABIC LETTER WAW
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+0649 : ARABIC LETTER ALEF MAKSURA
ED = U+064A : ARABIC LETTER YEH
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F0 = U+064B : ARABIC FATHATAN
F1 = U+064C : ARABIC DAMMATAN
F2 = U+064D : ARABIC KASRATAN
F3 = U+064E : ARABIC FATHA
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+064F : ARABIC DAMMA
F6 = U+0650 : ARABIC KASRA
F7 = U+00F7 : DIVISION SIGN
F8 = U+0651 : ARABIC SHADDA
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+0652 : ARABIC SUKUN
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+200E : LEFT-TO-RIGHT MARK
FE = U+200F : RIGHT-TO-LEFT MARK
FF = U+06D2 : ARABIC LETTER YEH BARREE

View file

@ -0,0 +1,116 @@
80 = U+20AC : EURO SIGN
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
89 = U+2030 : PER MILLE SIGN
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
8D = U+00A8 : DIAERESIS
8E = U+02C7 : CARON
8F = U+00B8 : CEDILLA
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
99 = U+2122 : TRADE MARK SIGN
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
9D = U+00AF : MACRON
9E = U+02DB : OGONEK
A0 = U+00A0 : NO-BREAK SPACE
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+0156 : LATIN CAPITAL LETTER R WITH CEDILLA
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00C6 : LATIN CAPITAL LETTER AE
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+0157 : LATIN SMALL LETTER R WITH CEDILLA
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+00E6 : LATIN SMALL LETTER AE
C0 = U+0104 : LATIN CAPITAL LETTER A WITH OGONEK
C1 = U+012E : LATIN CAPITAL LETTER I WITH OGONEK
C2 = U+0100 : LATIN CAPITAL LETTER A WITH MACRON
C3 = U+0106 : LATIN CAPITAL LETTER C WITH ACUTE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+0118 : LATIN CAPITAL LETTER E WITH OGONEK
C7 = U+0112 : LATIN CAPITAL LETTER E WITH MACRON
C8 = U+010C : LATIN CAPITAL LETTER C WITH CARON
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+0179 : LATIN CAPITAL LETTER Z WITH ACUTE
CB = U+0116 : LATIN CAPITAL LETTER E WITH DOT ABOVE
CC = U+0122 : LATIN CAPITAL LETTER G WITH CEDILLA
CD = U+0136 : LATIN CAPITAL LETTER K WITH CEDILLA
CE = U+012A : LATIN CAPITAL LETTER I WITH MACRON
CF = U+013B : LATIN CAPITAL LETTER L WITH CEDILLA
D0 = U+0160 : LATIN CAPITAL LETTER S WITH CARON
D1 = U+0143 : LATIN CAPITAL LETTER N WITH ACUTE
D2 = U+0145 : LATIN CAPITAL LETTER N WITH CEDILLA
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+014C : LATIN CAPITAL LETTER O WITH MACRON
D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+0172 : LATIN CAPITAL LETTER U WITH OGONEK
D9 = U+0141 : LATIN CAPITAL LETTER L WITH STROKE
DA = U+015A : LATIN CAPITAL LETTER S WITH ACUTE
DB = U+016A : LATIN CAPITAL LETTER U WITH MACRON
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+017B : LATIN CAPITAL LETTER Z WITH DOT ABOVE
DE = U+017D : LATIN CAPITAL LETTER Z WITH CARON
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+0105 : LATIN SMALL LETTER A WITH OGONEK
E1 = U+012F : LATIN SMALL LETTER I WITH OGONEK
E2 = U+0101 : LATIN SMALL LETTER A WITH MACRON
E3 = U+0107 : LATIN SMALL LETTER C WITH ACUTE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+0119 : LATIN SMALL LETTER E WITH OGONEK
E7 = U+0113 : LATIN SMALL LETTER E WITH MACRON
E8 = U+010D : LATIN SMALL LETTER C WITH CARON
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+017A : LATIN SMALL LETTER Z WITH ACUTE
EB = U+0117 : LATIN SMALL LETTER E WITH DOT ABOVE
EC = U+0123 : LATIN SMALL LETTER G WITH CEDILLA
ED = U+0137 : LATIN SMALL LETTER K WITH CEDILLA
EE = U+012B : LATIN SMALL LETTER I WITH MACRON
EF = U+013C : LATIN SMALL LETTER L WITH CEDILLA
F0 = U+0161 : LATIN SMALL LETTER S WITH CARON
F1 = U+0144 : LATIN SMALL LETTER N WITH ACUTE
F2 = U+0146 : LATIN SMALL LETTER N WITH CEDILLA
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+014D : LATIN SMALL LETTER O WITH MACRON
F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+0173 : LATIN SMALL LETTER U WITH OGONEK
F9 = U+0142 : LATIN SMALL LETTER L WITH STROKE
FA = U+015B : LATIN SMALL LETTER S WITH ACUTE
FB = U+016B : LATIN SMALL LETTER U WITH MACRON
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+017C : LATIN SMALL LETTER Z WITH DOT ABOVE
FE = U+017E : LATIN SMALL LETTER Z WITH CARON
FF = U+02D9 : DOT ABOVE

View file

@ -0,0 +1,119 @@
80 = U+20AC : EURO SIGN
82 = U+201A : SINGLE LOW-9 QUOTATION MARK
83 = U+0192 : LATIN SMALL LETTER F WITH HOOK
84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
85 = U+2026 : HORIZONTAL ELLIPSIS
86 = U+2020 : DAGGER
87 = U+2021 : DOUBLE DAGGER
88 = U+02C6 : MODIFIER LETTER CIRCUMFLEX ACCENT
89 = U+2030 : PER MILLE SIGN
8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
8C = U+0152 : LATIN CAPITAL LIGATURE OE
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
98 = U+02DC : SMALL TILDE
99 = U+2122 : TRADE MARK SIGN
9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
9C = U+0153 : LATIN SMALL LIGATURE OE
9F = U+0178 : LATIN CAPITAL LETTER Y WITH DIAERESIS
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+00A1 : INVERTED EXCLAMATION MARK
A2 = U+00A2 : CENT SIGN
A3 = U+00A3 : POUND SIGN
A4 = U+00A4 : CURRENCY SIGN
A5 = U+00A5 : YEN SIGN
A6 = U+00A6 : BROKEN BAR
A7 = U+00A7 : SECTION SIGN
A8 = U+00A8 : DIAERESIS
A9 = U+00A9 : COPYRIGHT SIGN
AA = U+00AA : FEMININE ORDINAL INDICATOR
AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
AC = U+00AC : NOT SIGN
AD = U+00AD : SOFT HYPHEN
AE = U+00AE : REGISTERED SIGN
AF = U+00AF : MACRON
B0 = U+00B0 : DEGREE SIGN
B1 = U+00B1 : PLUS-MINUS SIGN
B2 = U+00B2 : SUPERSCRIPT TWO
B3 = U+00B3 : SUPERSCRIPT THREE
B4 = U+00B4 : ACUTE ACCENT
B5 = U+00B5 : MICRO SIGN
B6 = U+00B6 : PILCROW SIGN
B7 = U+00B7 : MIDDLE DOT
B8 = U+00B8 : CEDILLA
B9 = U+00B9 : SUPERSCRIPT ONE
BA = U+00BA : MASCULINE ORDINAL INDICATOR
BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
BC = U+00BC : VULGAR FRACTION ONE QUARTER
BD = U+00BD : VULGAR FRACTION ONE HALF
BE = U+00BE : VULGAR FRACTION THREE QUARTERS
BF = U+00BF : INVERTED QUESTION MARK
C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
C3 = U+0102 : LATIN CAPITAL LETTER A WITH BREVE
C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
C6 = U+00C6 : LATIN CAPITAL LETTER AE
C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
CC = U+0300 : COMBINING GRAVE ACCENT
CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
D0 = U+0110 : LATIN CAPITAL LETTER D WITH STROKE
D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
D2 = U+0309 : COMBINING HOOK ABOVE
D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
D5 = U+01A0 : LATIN CAPITAL LETTER O WITH HORN
D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
D7 = U+00D7 : MULTIPLICATION SIGN
D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
DD = U+01AF : LATIN CAPITAL LETTER U WITH HORN
DE = U+0303 : COMBINING TILDE
DF = U+00DF : LATIN SMALL LETTER SHARP S
E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
E3 = U+0103 : LATIN SMALL LETTER A WITH BREVE
E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
E6 = U+00E6 : LATIN SMALL LETTER AE
E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
EC = U+0301 : COMBINING ACUTE ACCENT
ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
F0 = U+0111 : LATIN SMALL LETTER D WITH STROKE
F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
F2 = U+0323 : COMBINING DOT BELOW
F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
F5 = U+01A1 : LATIN SMALL LETTER O WITH HORN
F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
F7 = U+00F7 : DIVISION SIGN
F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
FD = U+01B0 : LATIN SMALL LETTER U WITH HORN
FE = U+20AB : DONG SIGN
FF = U+00FF : LATIN SMALL LETTER Y WITH DIAERESIS

View file

@ -0,0 +1,97 @@
80 = U+20AC : EURO SIGN
85 = U+2026 : HORIZONTAL ELLIPSIS
91 = U+2018 : LEFT SINGLE QUOTATION MARK
92 = U+2019 : RIGHT SINGLE QUOTATION MARK
93 = U+201C : LEFT DOUBLE QUOTATION MARK
94 = U+201D : RIGHT DOUBLE QUOTATION MARK
95 = U+2022 : BULLET
96 = U+2013 : EN DASH
97 = U+2014 : EM DASH
A0 = U+00A0 : NO-BREAK SPACE
A1 = U+0E01 : THAI CHARACTER KO KAI
A2 = U+0E02 : THAI CHARACTER KHO KHAI
A3 = U+0E03 : THAI CHARACTER KHO KHUAT
A4 = U+0E04 : THAI CHARACTER KHO KHWAI
A5 = U+0E05 : THAI CHARACTER KHO KHON
A6 = U+0E06 : THAI CHARACTER KHO RAKHANG
A7 = U+0E07 : THAI CHARACTER NGO NGU
A8 = U+0E08 : THAI CHARACTER CHO CHAN
A9 = U+0E09 : THAI CHARACTER CHO CHING
AA = U+0E0A : THAI CHARACTER CHO CHANG
AB = U+0E0B : THAI CHARACTER SO SO
AC = U+0E0C : THAI CHARACTER CHO CHOE
AD = U+0E0D : THAI CHARACTER YO YING
AE = U+0E0E : THAI CHARACTER DO CHADA
AF = U+0E0F : THAI CHARACTER TO PATAK
B0 = U+0E10 : THAI CHARACTER THO THAN
B1 = U+0E11 : THAI CHARACTER THO NANGMONTHO
B2 = U+0E12 : THAI CHARACTER THO PHUTHAO
B3 = U+0E13 : THAI CHARACTER NO NEN
B4 = U+0E14 : THAI CHARACTER DO DEK
B5 = U+0E15 : THAI CHARACTER TO TAO
B6 = U+0E16 : THAI CHARACTER THO THUNG
B7 = U+0E17 : THAI CHARACTER THO THAHAN
B8 = U+0E18 : THAI CHARACTER THO THONG
B9 = U+0E19 : THAI CHARACTER NO NU
BA = U+0E1A : THAI CHARACTER BO BAIMAI
BB = U+0E1B : THAI CHARACTER PO PLA
BC = U+0E1C : THAI CHARACTER PHO PHUNG
BD = U+0E1D : THAI CHARACTER FO FA
BE = U+0E1E : THAI CHARACTER PHO PHAN
BF = U+0E1F : THAI CHARACTER FO FAN
C0 = U+0E20 : THAI CHARACTER PHO SAMPHAO
C1 = U+0E21 : THAI CHARACTER MO MA
C2 = U+0E22 : THAI CHARACTER YO YAK
C3 = U+0E23 : THAI CHARACTER RO RUA
C4 = U+0E24 : THAI CHARACTER RU
C5 = U+0E25 : THAI CHARACTER LO LING
C6 = U+0E26 : THAI CHARACTER LU
C7 = U+0E27 : THAI CHARACTER WO WAEN
C8 = U+0E28 : THAI CHARACTER SO SALA
C9 = U+0E29 : THAI CHARACTER SO RUSI
CA = U+0E2A : THAI CHARACTER SO SUA
CB = U+0E2B : THAI CHARACTER HO HIP
CC = U+0E2C : THAI CHARACTER LO CHULA
CD = U+0E2D : THAI CHARACTER O ANG
CE = U+0E2E : THAI CHARACTER HO NOKHUK
CF = U+0E2F : THAI CHARACTER PAIYANNOI
D0 = U+0E30 : THAI CHARACTER SARA A
D1 = U+0E31 : THAI CHARACTER MAI HAN-AKAT
D2 = U+0E32 : THAI CHARACTER SARA AA
D3 = U+0E33 : THAI CHARACTER SARA AM
D4 = U+0E34 : THAI CHARACTER SARA I
D5 = U+0E35 : THAI CHARACTER SARA II
D6 = U+0E36 : THAI CHARACTER SARA UE
D7 = U+0E37 : THAI CHARACTER SARA UEE
D8 = U+0E38 : THAI CHARACTER SARA U
D9 = U+0E39 : THAI CHARACTER SARA UU
DA = U+0E3A : THAI CHARACTER PHINTHU
DF = U+0E3F : THAI CURRENCY SYMBOL BAHT
E0 = U+0E40 : THAI CHARACTER SARA E
E1 = U+0E41 : THAI CHARACTER SARA AE
E2 = U+0E42 : THAI CHARACTER SARA O
E3 = U+0E43 : THAI CHARACTER SARA AI MAIMUAN
E4 = U+0E44 : THAI CHARACTER SARA AI MAIMALAI
E5 = U+0E45 : THAI CHARACTER LAKKHANGYAO
E6 = U+0E46 : THAI CHARACTER MAIYAMOK
E7 = U+0E47 : THAI CHARACTER MAITAIKHU
E8 = U+0E48 : THAI CHARACTER MAI EK
E9 = U+0E49 : THAI CHARACTER MAI THO
EA = U+0E4A : THAI CHARACTER MAI TRI
EB = U+0E4B : THAI CHARACTER MAI CHATTAWA
EC = U+0E4C : THAI CHARACTER THANTHAKHAT
ED = U+0E4D : THAI CHARACTER NIKHAHIT
EE = U+0E4E : THAI CHARACTER YAMAKKAN
EF = U+0E4F : THAI CHARACTER FONGMAN
F0 = U+0E50 : THAI DIGIT ZERO
F1 = U+0E51 : THAI DIGIT ONE
F2 = U+0E52 : THAI DIGIT TWO
F3 = U+0E53 : THAI DIGIT THREE
F4 = U+0E54 : THAI DIGIT FOUR
F5 = U+0E55 : THAI DIGIT FIVE
F6 = U+0E56 : THAI DIGIT SIX
F7 = U+0E57 : THAI DIGIT SEVEN
F8 = U+0E58 : THAI DIGIT EIGHT
F9 = U+0E59 : THAI DIGIT NINE
FA = U+0E5A : THAI CHARACTER ANGKHANKHU
FB = U+0E5B : THAI CHARACTER KHOMUT

View file

@ -0,0 +1,256 @@
# SpecialCasing-4.0.1.txt
# Date: 2003-10-06, 17:30:00 PST [KW]
#
# Special Casing Properties
#
# This file is a supplement to the UnicodeData file.
# It contains additional information about the casing of Unicode characters.
# (For compatibility, the UnicodeData.txt file only contains case mappings for
# characters where they are 1-1, and does not have locale-specific mappings.)
# For more information, see the discussion of Case Mappings in the Unicode Standard.
#
# All code points not listed in this file that do not have a simple case mappings
# in UnicodeData.txt map to themselves.
# ================================================================================
# Format
# ================================================================================
# The entries in this file are in the following machine-readable format:
#
# <code>; <lower> ; <title> ; <upper> ; (<condition_list> ;)? # <comment>
#
# <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more than
# one character, they are separated by spaces. Other than as used to separate elements,
# spaces are to be ignored.
#
# The <condition_list> is optional. Where present, it consists of one or more locales or contexts,
# separated by spaces. In these conditions:
# - A condition list overrides the normal behavior if all of the listed conditions are true.
# - The context is always the context of the characters in the original string,
# NOT in the resulting string.
# - Case distinctions in the condition list are not significant.
# - Conditions preceded by "Not_" represent the negation of the condition.
#
# A locale is defined as:
# <locale> := <ISO_639_code> ( "_" <ISO_3166_code> ( "_" <variant> )? )?
# <ISO_3166_code> := 2-letter ISO country code,
# <ISO_639_code> := 2-letter ISO language code
#
# A context is one of the following, as defined in the Unicode Standard:
# Final_Sigma, After_Soft_Dotted, More_Above, Before_Dot, Not_Before_Dot, After_I
#
# Parsers of this file must be prepared to deal with future additions to this format:
# * Additional contexts
# * Additional fields
# ================================================================================
# ================================================================================
# Unconditional mappings
# ================================================================================
# The German es-zed is special--the normal mapping is to SS.
# Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
# Preserve canonical equivalence for I with dot. Turkic is handled below.
0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
# Ligatures
FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
# No corresponding uppercase precomposed character
0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
# IMPORTANT-when capitalizing iota-subscript (0345)
# It MUST be in normalized form--moved to the end of any sequence of combining marks.
# This is because logically it represents a following base character!
# E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript>
# It should never be the first character in a word, so in titlecasing it can be left as is.
# The following cases are already in the UnicodeData file, so are only commented here.
# 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
# have special uppercases.
# Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
# ================================================================================
# Conditional mappings
# ================================================================================
# Special case for final form of sigma
03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
# Note: the following cases for non-final are already in the UnicodeData file.
# 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
# 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
# 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
# Note: the following cases are not included, since they would case-fold in lowercasing
# 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
# 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
# ================================================================================
# Locale-sensitive mappings
# ================================================================================
# Lithuanian
# Lithuanian retains the dot in a lowercase i when followed by accents.
# Remove DOT ABOVE after "i" with upper or titlecase
0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
# Introduce an explicit dot above when lowercasing capital I's and J's
# whenever there are more accents above.
# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
# ================================================================================
# Turkish and Azeri
# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
# The following rules handle those cases.
0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
# This matches the behavior of the canonically equivalent I-dot_above
0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
# When uppercasing, i turns into a dotted capital I
0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
# Note: the following case is already in the UnicodeData file.
# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I

View file

@ -0,0 +1,215 @@
# Latin (iso-8859-1)
00A5; 0079 0065 006E; YEN SIGN => yen
00A6; 007C; BROKEN BAR => |
00AB; 003C 003C; LEFT-POINTING DOUBLE ANGLE QUOTATION MARK => <<
00A9; 0028 0063 0029; COPYRIGHT SIGN => (c)
00AE; 0028 0052 0029; REGISTERED SIGN => (R)
00B1; 002B 002F 002D; PLUS-MINUS SIGN => +/-
00B5; 0075; MICRO SIGN => u (American style)
00B7; 002A; MIDDLE DOT => *
00BB; 003E 003E; RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK => <<
00C4; 0041 0045; LATIN CAPITAL LETTER A WITH DIAERESIS => AE (German)
00C5; 0041 0041; LATIN CAPITAL LETTER A WITH RING ABOVE => AA (Danish)
00C6; 0041 0045; LATIN CAPITAL LETTER AE => AE (Danish)
00D6; 004F 0045; LATIN CAPITAL LETTER O WITH DIAERESIS => OE (German)
00D7; 0078; MULTIPLICATION SIGN => x
00D8; 004F 0045; LATIN CAPITAL LETTER O WITH STROKE => OE (Danish)
00DC; 0055 0045; LATIN CAPITAL LETTER U WITH DIAERESIS => UE (German)
00E4; 0061 0065; LATIN SMALL LETTER A WITH DIAERESIS => ae (German)
00E5; 0061 0061; LATIN SMALL LETTER A WITH RING ABOVE => aa (Danish)
00DF; 0073 0073; LATIN SMALL LETTER SHARP S => ss (German)
00E6; 0061 0065; LATIN SMALL LETTER AE => ae (Danish)
00F6; 006F 0065; LATIN SMALL LETTER O WITH DIAERESIS => oe (German)
00F7; 002F; DIVISION SIGN => /
00F8; 006F 0065; LATIN SMALL LETTER O WITH STROKE => oe (Danish)
00FC; 0075 0065; LATIN SMALL LETTER U WITH DIAERESIS => ue (German)
# more Latin (windows-1252, windows-1254, windows-1257)
0100; 0041 0041; LATIN CAPITAL LETTER A WITH MACRON => AA (Latvian)
0101; 0061 0061; LATIN SMALL LETTER A WITH MACRON => aa (Latvian)
0112; 0045 0045; LATIN CAPITAL LETTER E WITH MACRON => EE (Latvian)
0113; 0065 0065; LATIN SMALL LETTER E WITH MACRON => ee (Latvian)
012A; 0049 0049; LATIN CAPITAL LETTER I WITH MACRON => II (Latvian)
012B; 0060 0069; LATIN SMALL LETTER I WITH MACRON => ii(Latvian)
014C; 004F 004F; LATIN CAPITAL LETTER O WITH MACRON => OO
014D; 006F 006F; LATIN SMALL LETTER O WITH MACRON => oo
016A; 0055 0055; LATIN CAPITAL LETTER U WITH MACRON => UU (Latvian)
016B; 0075 0075; LATIN SMALL LETTER U WITH MACRON => uu (Latvian)
0131; 0069; LATIN SMALL LETTER DOTLESS I => i (Turkish)
0152; 004F 0045; LATIN CAPITAL LETTER OE => OE
0153; 006F 0065; LATIN SMALL LETTER OE => oe
0192; 0066; LATIN SMALL LETTER F WITH HOOK => f
02BC; 0027; MODIFIER LETTER APOSTROPHE => '
02CA; 0027; MODIFIER LETTER ACUTE ACCENT => '
2010; 002D; HYPHEN => -
2013; 002D; EN DASH => -
2014; 002D; EM DASH => -
2018; 0060; LEFT SINGLE QUOTATION MARK => `
2019; 0027; RIGHT SINGLE QUOTATION MARK >= '
201C; 0022; LEFT DOUBLE QUOTATION MARK => "
201D; 0022; RIGHT DOUBLE QUOTATION MARK => "
201E; 0022; DOUBLE LOW-9 QUOTATION MARK => "
2022; 002A; BULLET => *
2039; 003C; SINGLE LEFT-POINTING ANGLE QUOTATION MARK => <
203A; 003E; SINGLE RIGHT-POINTING ANGLE QUOTATION MARK => >
2044; 002F; FRACTION SLASH => /
20A0; 0045 0055 0052; EURO-CURRENCY SIGN => EUR
20AC; 0045 0055 0052; EURO-CURRENCY SIGN => EUR
# Cyrillic (Russian transliteration: modified GOST)
0401; 004A 004F; CYRILLIC CAPITAL LETTER IO => JO
#0402; ; CYRILLIC CAPITAL LETTER DJE
#0403; ; CYRILLIC CAPITAL LETTER GJE
0404; 004A 0045; CYRILLIC CAPITAL LETTER UKRAINIAN IE => JE
#0405; ; CYRILLIC CAPITAL LETTER DZE
0406; 0049; CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I => I
0407; 0049; CYRILLIC CAPITAL LETTER YI => I
#0408; ; CYRILLIC CAPITAL LETTER JE ?? J
#0409; ; CYRILLIC CAPITAL LETTER LJE ?? LJ
#040A; ; CYRILLIC CAPITAL LETTER NJE ?? NJ
#040B; ; CYRILLIC CAPITAL LETTER TSHE ?? TSH
#040C; ; CYRILLIC CAPITAL LETTER KJE ?? KJ KY
040E; 0055; CYRILLIC CAPITAL LETTER SHORT U => U (Belorussian)
#040F; ; CYRILLIC CAPITAL LETTER DZHE ?? DZH
0410; 0041; CYRILLIC CAPITAL LETTER A => A
0411; 0042; CYRILLIC CAPITAL LETTER BE => B
0412; 0056; CYRILLIC CAPITAL LETTER VE => V
0413; 0047; CYRILLIC CAPITAL LETTER GHE => G
0414; 0044; CYRILLIC CAPITAL LETTER DE => D
0415; 0045; CYRILLIC CAPITAL LETTER IE => E
0416; 005A 0048; CYRILLIC CAPITAL LETTER ZHE => ZH
0417; 005A; CYRILLIC CAPITAL LETTER ZE => Z
0418; 0049; CYRILLIC CAPITAL LETTER I=> I
0419; 0049; CYRILLIC CAPITAL LETTER SHORT I => I (GOST has I)
041A; 004B; CYRILLIC CAPITAL LETTER KA => K
041B; 004C; CYRILLIC CAPITAL LETTER EL => L
041C; 004D; CYRILLIC CAPITAL LETTER EM => M
041D; 004E; CYRILLIC CAPITAL LETTER EN => N
041E; 004F; CYRILLIC CAPITAL LETTER O => O
041F; 0050; CYRILLIC CAPITAL LETTER PE => P
0420; 0052; CYRILLIC CAPITAL LETTER ER => R
0421; 0053; CYRILLIC CAPITAL LETTER ES => S
0422; 0054; CYRILLIC CAPITAL LETTER TE => T
0423; 0055; CYRILLIC CAPITAL LETTER U => U
0424; 0046; CYRILLIC CAPITAL LETTER EF => F
0425; 004B 0048; CYRILLIC CAPITAL LETTER HA => KH
0426; 0043; CYRILLIC CAPITAL LETTER TSE => C
0427; 0043 0048; CYRILLIC CAPITAL LETTER CHE => CH
0428; 0053 0048; CYRILLIC CAPITAL LETTER SHA => SH
0429; 0053 0048 0043 0048; CYRILLIC CAPITAL LETTER SHCHA => SHCH (GOST has SHH)
042A; ; CYRILLIC CAPITAL LETTER HARD SIGN => omit (GOST has ")
042B; 0059; CYRILLIC CAPITAL LETTER YERU => Y
042C; ; CYRILLIC CAPITAL LETTER SOFT SIGN => omit (GOST has ')
042D; 0045 0048; CYRILLIC CAPITAL LETTER E => EH
042E; 004A 0055; CYRILLIC CAPITAL LETTER YU => JU
042F; 004A 0041; CYRILLIC CAPITAL LETTER YA => JA
0430; 0061; CYRILLIC SMALL LETTER A => a
0431; 0062; CYRILLIC SMALL LETTER BE => b
0432; 0076; CYRILLIC SMALL LETTER VE => v
0433; 0067; CYRILLIC SMALL LETTER GHE => g
0434; 0064; CYRILLIC SMALL LETTER DE => d
0435; 0065; CYRILLIC SMALL LETTER IE => e
0436; 007A 0068; CYRILLIC SMALL LETTER ZHE => zh
0437; 007A; CYRILLIC SMALL LETTER ZE => z
0438; 0069; CYRILLIC SMALL LETTER I => i
0439; 0069; CYRILLIC SMALL LETTER SHORT I => i (GOST has j)
043A; 006B; CYRILLIC SMALL LETTER KA => k
043B; 006C; CYRILLIC SMALL LETTER EL => l
043C; 006D; CYRILLIC SMALL LETTER EM => m
043D; 006E; CYRILLIC SMALL LETTER EN => n
043E; 006F; CYRILLIC SMALL LETTER O => o
043F; 0070; CYRILLIC SMALL LETTER PE => p
0440; 0072; CYRILLIC SMALL LETTER ER => r
0441; 0073; CYRILLIC SMALL LETTER ES => s
0442; 0074; CYRILLIC SMALL LETTER TE => t
0443; 0075; CYRILLIC SMALL LETTER U => u
0444; 0066; CYRILLIC SMALL LETTER EF => f
0445; 006B 0068; CYRILLIC SMALL LETTER HA => kh
0446; 0063; CYRILLIC SMALL LETTER TSE => c
0447; 0063 0068; CYRILLIC SMALL LETTER CHE => ch
0448; 0073 0068; CYRILLIC SMALL LETTER SHA => sh
0449; 0073 0068 0063 0068; CYRILLIC SMALL LETTER SHCHA => shch (GOST has shh)
044A; ; CYRILLIC SMALL LETTER HARD SIGN => omit (GOST has ")
044B; 0079; CYRILLIC SMALL LETTER YERU => y
044C; ; CYRILLIC SMALL LETTER SOFT SIGN => omit (GOST has ')
044D; 0065 0068; CYRILLIC SMALL LETTER E => eh
044E; 006A 0075; CYRILLIC SMALL LETTER YU => ju
044F; 006A 0061; CYRILLIC SMALL LETTER YA => ja
0451; 006A 006F; CYRILLIC SMALL LETTER IO => jo
#0452; ; CYRILLIC SMALL LETTER DJE => dj dy ??
#0453; ; CYRILLIC SMALL LETTER GJE => gj gy ??
0454; 006A 0065; CYRILLIC SMALL LETTER UKRAINIAN IE => je
#0455; ; CYRILLIC SMALL LETTER DZE => dz ??
0456; 0069; CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I => i
0457; 006A 0069; CYRILLIC SMALL LETTER YI => ji
#0458; ; CYRILLIC SMALL LETTER JE ?? j y
#0459; ; CYRILLIC SMALL LETTER LJE ?? lj ly
#045A; ; CYRILLIC SMALL LETTER NJE ?? nj ny
#045B; ; CYRILLIC SMALL LETTER TSHE => ??? tsh ch (Serbocroatian)
#045C; ; CYRILLIC SMALL LETTER KJE
045E; 0075; CYRILLIC SMALL LETTER SHORT U => U (Belorussian)
#045F; ; CYRILLIC SMALL LETTER DZHE ???
0490; 0047 0047; CYRILLIC CAPITAL LETTER GHE WITH UPTURN => GG (Belorussian, Ukrainian)
0491; 0067 0076; CYRILLIC SMALL LETTER GHE WITH UPTURN => gg (Belorussian, Ukrainian)
# Hebrew
#05B0; ; HEBREW POINT SHEVA ??? win1255
#05B1; ; HEBREW POINT HATAF SEGOL ??? win1255
#05B2; ; HEBREW POINT HATAF PATAH ??? win1255
#05B3; ; HEBREW POINT HATAF QAMATS ??? win1255
#05B4; ; HEBREW POINT HIRIQ ??? win1255
#05B5; ; HEBREW POINT TSERE ??? win1255
#05B6; ; HEBREW POINT SEGOL ??? win1255
#05B7; ; HEBREW POINT PATAH ??? win1255
#05B8; ; HEBREW POINT QAMATS ??? win1255
#05B9; ; HEBREW POINT HOLAM ??? win1255
#05BB; ; HEBREW POINT QUBUTS ??? win1255
#05BC; ; HEBREW POINT DAGESH OR MAPIQ ??? win1255
#05BD; ; HEBREW POINT METEG ??? win1255
#05BE; ; HEBREW PUNCTUATION MAQAF ??? win1255
#05BF; ; HEBREW POINT RAFE ??? win1255
#05C0; ; HEBREW PUNCTUATION PASEQ ??? win1255
#05C1; ; HEBREW POINT SHIN DOT ??? win1255
#05C2; ; HEBREW POINT SIN DOT ??? win1255
05D0; 0041; HEBREW LETTER ALEF => A
05D1; 0042; HEBREW LETTER BET => B
05D2; 0047; HEBREW LETTER GIMEL => G
05D3; 0044; HEBREW LETTER DALET => D
05D4; 0048 0061; HEBREW LETTER HE => Ha
05D5; 004F; HEBREW LETTER VAV => O
05D6; 005A; HEBREW LETTER ZAYIN => Z
05D7; 0048; HEBREW LETTER HET => H
05D8; 0054; HEBREW LETTER TET => T
05D9; 0049; HEBREW LETTER YOD => I
05DA; 004B 0068; HEBREW LETTER FINAL KAF => Kh
05DB; 004B 0068; HEBREW LETTER KAF => Kh
05DC; 004C; HEBREW LETTER LAMED => L
05DD; 004D; HEBREW LETTER FINAL MEM => M
05DE; 004D; HEBREW LETTER MEM => M
05DF; 004E; HEBREW LETTER FINAL NUN => N
05E0; 004E; HEBREW LETTER NUN => N
05E1; 0053; HEBREW LETTER SAMEKH => S
05E2; 0041; HEBREW LETTER AYIN => A
05E3; 0050 0066; HEBREW LETTER FINAL PE => Pf
05E4; 0050 0066; HEBREW LETTER PE => Pf
05E5; 0054 0073; HEBREW LETTER FINAL TSADI => Ts
05E6; 0054 0073; HEBREW LETTER TSADI => Ts
05E7; 004B; HEBREW LETTER QOF => K
05E8; 0052; HEBREW LETTER RESH => R
05E9; 0053 0068; HEBREW LETTER SHIN => Sh
05EA; 0054; HEBREW LETTER TAV => T
05F0; 0056; HEBREW LIGATURE YIDDISH DOUBLE VAV => V
#05F1; ; HEBREW LIGATURE YIDDISH VAV YOD ??? win1255
#05F2; ; HEBREW LIGATURE YIDDISH DOUBLE YOD ??? win1255
#05F3; ; HEBREW PUNCTUATION GERESH ??? win1255
#05F4; ; HEBREW PUNCTUATION GERSHAYIM ??? win1255
#20AA; ; NEW SHEQEL SIGN ??? win1255

File diff suppressed because it is too large Load diff