From 83dbb7a8a5595addead6c50fb5ba411a6d3dfe7b Mon Sep 17 00:00:00 2001 From: thomascube Date: Fri, 20 Jan 2006 00:01:53 +0000 Subject: Use iconv and utf8 class for charset conversion --- program/include/main.inc | 48 +++--- program/lib/encoding/CP1250.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1251.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1252.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1253.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1254.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1255.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1256.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1257.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/CP1258.map | 274 ++++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-1.map | 303 +++++++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-2.map | 303 +++++++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-3.map | 296 ++++++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-4.map | 303 +++++++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-5.map | 303 +++++++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-6.map | 260 ++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-7.map | 308 ++++++++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-8.map | 270 +++++++++++++++++++++++++++++++ program/lib/encoding/ISO-8859-9.map | 307 +++++++++++++++++++++++++++++++++++ program/lib/utf8.class.php | 173 ++++++++++++++++++++ program/lib/utf8.inc | 104 ------------ 21 files changed, 5320 insertions(+), 124 deletions(-) create mode 100644 program/lib/encoding/CP1250.map create mode 100644 program/lib/encoding/CP1251.map create mode 100644 program/lib/encoding/CP1252.map create mode 100644 program/lib/encoding/CP1253.map create mode 100644 program/lib/encoding/CP1254.map create mode 100644 program/lib/encoding/CP1255.map create mode 100644 program/lib/encoding/CP1256.map create mode 100644 program/lib/encoding/CP1257.map create mode 100644 program/lib/encoding/CP1258.map create mode 100644 program/lib/encoding/ISO-8859-1.map create mode 100644 program/lib/encoding/ISO-8859-2.map create mode 100644 program/lib/encoding/ISO-8859-3.map create mode 100644 program/lib/encoding/ISO-8859-4.map create mode 100644 program/lib/encoding/ISO-8859-5.map create mode 100644 program/lib/encoding/ISO-8859-6.map create mode 100644 program/lib/encoding/ISO-8859-7.map create mode 100644 program/lib/encoding/ISO-8859-8.map create mode 100644 program/lib/encoding/ISO-8859-9.map create mode 100644 program/lib/utf8.class.php delete mode 100644 program/lib/utf8.inc diff --git a/program/include/main.inc b/program/include/main.inc index 307a880fb..99eaa9128 100644 --- a/program/include/main.inc +++ b/program/include/main.inc @@ -21,6 +21,7 @@ require_once('lib/des.inc'); require_once('lib/utf7.inc'); +require_once('lib/utf8.class.php'); // register session and connect to server @@ -701,33 +702,40 @@ function rcmail_clear_session_temp($sess_id) // this function is not complete and not tested well function rcube_charset_convert($str, $from, $to=NULL) { - $from = strtolower($from); - $to = $to==NULL ? strtolower($GLOBALS['CHARSET']) : strtolower($to); + $from = strtoupper($from); + $to = $to==NULL ? strtoupper($GLOBALS['CHARSET']) : strtoupper($to); if ($from==$to) return $str; - - // decode characters - if ($from=='utf-7') - $str = UTF7DecodeString($str); - else if ($from=='utf-8' && function_exists('utf8_decode')) - $str = utf8_decode($str); - else if ($from=="koi8-r") - $str = convert_cyr_string($str, 'k', 'i'); - else if ($from=="windows-1251" || $from=="win-1251") - $str = convert_cyr_string($str, 'w', 'i'); - else if ($from=="x-cp866") - $str = convert_cyr_string($str, 'a', 'i'); - else if ($from=="x-mac-cyrillic") - $str = convert_cyr_string($str, 'm', 'i'); + + // convert charset using iconv module + if (function_exists('iconv') && $from!='UTF-7' && $to!='UTF-7') { + return iconv($from, $to, $str); + } + + // convert string to UTF-8 + if ($from=='UTF-7') + $str = rcube_charset_convert(UTF7DecodeString($str), 'ISO-8859-1'); + else if ($from=='ISO-8859-1' && function_exists('utf8_encode')) + $str = utf8_encode($str); + else if ($from!='UTF-8') + { + $conv = new utf8($from); + $str = $conv->strToUtf8($str); + } // encode string for output - if ($to=='utf-8' && function_exists('utf8_encode')) - return utf8_encode($str); - else if ($to=='utf-7') + if ($to=='UTF-7') return UTF7EncodeString($str); + else if ($to=='ISO-8859-1' && function_exists('utf8_decode')) + return utf8_decode($str); + else if ($to!='UTF-8') + { + $conv = new utf8($to); + return $conv->utf8ToStr($str); + } - // return raw string + // return UTF-8 string return $str; } diff --git a/program/lib/encoding/CP1250.map b/program/lib/encoding/CP1250.map new file mode 100644 index 000000000..081d7763b --- /dev/null +++ b/program/lib/encoding/CP1250.map @@ -0,0 +1,274 @@ +# +# Name: cp1250 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1250 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1250 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 #UNDEFINED +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0x8D 0x0164 #LATIN CAPITAL LETTER T WITH CARON +0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0x8F 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x015B #LATIN SMALL LETTER S WITH ACUTE +0x9D 0x0165 #LATIN SMALL LETTER T WITH CARON +0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON +0x9F 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x02C7 #CARON +0xA2 0x02D8 #BREVE +0xA3 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x02DB #OGONEK +0xB3 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xBA 0x015F #LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x013D #LATIN CAPITAL LETTER L WITH CARON +0xBD 0x02DD #DOUBLE ACUTE ACCENT +0xBE 0x013E #LATIN SMALL LETTER L WITH CARON +0xBF 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x0154 #LATIN CAPITAL LETTER R WITH ACUTE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x0139 #LATIN CAPITAL LETTER L WITH ACUTE +0xC6 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x011A #LATIN CAPITAL LETTER E WITH CARON +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x010E #LATIN CAPITAL LETTER D WITH CARON +0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0147 #LATIN CAPITAL LETTER N WITH CARON +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0150 #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0158 #LATIN CAPITAL LETTER R WITH CARON +0xD9 0x016E #LATIN CAPITAL LETTER U WITH RING ABOVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x0170 #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x0162 #LATIN CAPITAL LETTER T WITH CEDILLA +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0155 #LATIN SMALL LETTER R WITH ACUTE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x013A #LATIN SMALL LETTER L WITH ACUTE +0xE6 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x011B #LATIN SMALL LETTER E WITH CARON +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x010F #LATIN SMALL LETTER D WITH CARON +0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0148 #LATIN SMALL LETTER N WITH CARON +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0151 #LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0159 #LATIN SMALL LETTER R WITH CARON +0xF9 0x016F #LATIN SMALL LETTER U WITH RING ABOVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x0171 #LATIN SMALL LETTER U WITH DOUBLE ACUTE +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x0163 #LATIN SMALL LETTER T WITH CEDILLA +0xFF 0x02D9 #DOT ABOVE diff --git a/program/lib/encoding/CP1251.map b/program/lib/encoding/CP1251.map new file mode 100644 index 000000000..e7d4f2c5b --- /dev/null +++ b/program/lib/encoding/CP1251.map @@ -0,0 +1,274 @@ +# +# Name: cp1251 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1251 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1251 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x0402 #CYRILLIC CAPITAL LETTER DJE +0x81 0x0403 #CYRILLIC CAPITAL LETTER GJE +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0453 #CYRILLIC SMALL LETTER GJE +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x20AC #EURO SIGN +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0409 #CYRILLIC CAPITAL LETTER LJE +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x040A #CYRILLIC CAPITAL LETTER NJE +0x8D 0x040C #CYRILLIC CAPITAL LETTER KJE +0x8E 0x040B #CYRILLIC CAPITAL LETTER TSHE +0x8F 0x040F #CYRILLIC CAPITAL LETTER DZHE +0x90 0x0452 #CYRILLIC SMALL LETTER DJE +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0459 #CYRILLIC SMALL LETTER LJE +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x045A #CYRILLIC SMALL LETTER NJE +0x9D 0x045C #CYRILLIC SMALL LETTER KJE +0x9E 0x045B #CYRILLIC SMALL LETTER TSHE +0x9F 0x045F #CYRILLIC SMALL LETTER DZHE +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x040E #CYRILLIC CAPITAL LETTER SHORT U +0xA2 0x045E #CYRILLIC SMALL LETTER SHORT U +0xA3 0x0408 #CYRILLIC CAPITAL LETTER JE +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x0490 #CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x0401 #CYRILLIC CAPITAL LETTER IO +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x0407 #CYRILLIC CAPITAL LETTER YI +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xB3 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xB4 0x0491 #CYRILLIC SMALL LETTER GHE WITH UPTURN +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x0451 #CYRILLIC SMALL LETTER IO +0xB9 0x2116 #NUMERO SIGN +0xBA 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x0458 #CYRILLIC SMALL LETTER JE +0xBD 0x0405 #CYRILLIC CAPITAL LETTER DZE +0xBE 0x0455 #CYRILLIC SMALL LETTER DZE +0xBF 0x0457 #CYRILLIC SMALL LETTER YI +0xC0 0x0410 #CYRILLIC CAPITAL LETTER A +0xC1 0x0411 #CYRILLIC CAPITAL LETTER BE +0xC2 0x0412 #CYRILLIC CAPITAL LETTER VE +0xC3 0x0413 #CYRILLIC CAPITAL LETTER GHE +0xC4 0x0414 #CYRILLIC CAPITAL LETTER DE +0xC5 0x0415 #CYRILLIC CAPITAL LETTER IE +0xC6 0x0416 #CYRILLIC CAPITAL LETTER ZHE +0xC7 0x0417 #CYRILLIC CAPITAL LETTER ZE +0xC8 0x0418 #CYRILLIC CAPITAL LETTER I +0xC9 0x0419 #CYRILLIC CAPITAL LETTER SHORT I +0xCA 0x041A #CYRILLIC CAPITAL LETTER KA +0xCB 0x041B #CYRILLIC CAPITAL LETTER EL +0xCC 0x041C #CYRILLIC CAPITAL LETTER EM +0xCD 0x041D #CYRILLIC CAPITAL LETTER EN +0xCE 0x041E #CYRILLIC CAPITAL LETTER O +0xCF 0x041F #CYRILLIC CAPITAL LETTER PE +0xD0 0x0420 #CYRILLIC CAPITAL LETTER ER +0xD1 0x0421 #CYRILLIC CAPITAL LETTER ES +0xD2 0x0422 #CYRILLIC CAPITAL LETTER TE +0xD3 0x0423 #CYRILLIC CAPITAL LETTER U +0xD4 0x0424 #CYRILLIC CAPITAL LETTER EF +0xD5 0x0425 #CYRILLIC CAPITAL LETTER HA +0xD6 0x0426 #CYRILLIC CAPITAL LETTER TSE +0xD7 0x0427 #CYRILLIC CAPITAL LETTER CHE +0xD8 0x0428 #CYRILLIC CAPITAL LETTER SHA +0xD9 0x0429 #CYRILLIC CAPITAL LETTER SHCHA +0xDA 0x042A #CYRILLIC CAPITAL LETTER HARD SIGN +0xDB 0x042B #CYRILLIC CAPITAL LETTER YERU +0xDC 0x042C #CYRILLIC CAPITAL LETTER SOFT SIGN +0xDD 0x042D #CYRILLIC CAPITAL LETTER E +0xDE 0x042E #CYRILLIC CAPITAL LETTER YU +0xDF 0x042F #CYRILLIC CAPITAL LETTER YA +0xE0 0x0430 #CYRILLIC SMALL LETTER A +0xE1 0x0431 #CYRILLIC SMALL LETTER BE +0xE2 0x0432 #CYRILLIC SMALL LETTER VE +0xE3 0x0433 #CYRILLIC SMALL LETTER GHE +0xE4 0x0434 #CYRILLIC SMALL LETTER DE +0xE5 0x0435 #CYRILLIC SMALL LETTER IE +0xE6 0x0436 #CYRILLIC SMALL LETTER ZHE +0xE7 0x0437 #CYRILLIC SMALL LETTER ZE +0xE8 0x0438 #CYRILLIC SMALL LETTER I +0xE9 0x0439 #CYRILLIC SMALL LETTER SHORT I +0xEA 0x043A #CYRILLIC SMALL LETTER KA +0xEB 0x043B #CYRILLIC SMALL LETTER EL +0xEC 0x043C #CYRILLIC SMALL LETTER EM +0xED 0x043D #CYRILLIC SMALL LETTER EN +0xEE 0x043E #CYRILLIC SMALL LETTER O +0xEF 0x043F #CYRILLIC SMALL LETTER PE +0xF0 0x0440 #CYRILLIC SMALL LETTER ER +0xF1 0x0441 #CYRILLIC SMALL LETTER ES +0xF2 0x0442 #CYRILLIC SMALL LETTER TE +0xF3 0x0443 #CYRILLIC SMALL LETTER U +0xF4 0x0444 #CYRILLIC SMALL LETTER EF +0xF5 0x0445 #CYRILLIC SMALL LETTER HA +0xF6 0x0446 #CYRILLIC SMALL LETTER TSE +0xF7 0x0447 #CYRILLIC SMALL LETTER CHE +0xF8 0x0448 #CYRILLIC SMALL LETTER SHA +0xF9 0x0449 #CYRILLIC SMALL LETTER SHCHA +0xFA 0x044A #CYRILLIC SMALL LETTER HARD SIGN +0xFB 0x044B #CYRILLIC SMALL LETTER YERU +0xFC 0x044C #CYRILLIC SMALL LETTER SOFT SIGN +0xFD 0x044D #CYRILLIC SMALL LETTER E +0xFE 0x044E #CYRILLIC SMALL LETTER YU +0xFF 0x044F #CYRILLIC SMALL LETTER YA diff --git a/program/lib/encoding/CP1252.map b/program/lib/encoding/CP1252.map new file mode 100644 index 000000000..2ca4486eb --- /dev/null +++ b/program/lib/encoding/CP1252.map @@ -0,0 +1,274 @@ +# +# Name: cp1252 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1252 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1252 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D #UNDEFINED +0x8E 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D #UNDEFINED +0x9E 0x017E #LATIN SMALL LETTER Z WITH CARON +0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 #LATIN CAPITAL LETTER ETH +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE #LATIN CAPITAL LETTER THORN +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 #LATIN SMALL LETTER ETH +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD #LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x00FE #LATIN SMALL LETTER THORN +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS diff --git a/program/lib/encoding/CP1253.map b/program/lib/encoding/CP1253.map new file mode 100644 index 000000000..2ba51a0c8 --- /dev/null +++ b/program/lib/encoding/CP1253.map @@ -0,0 +1,274 @@ +# +# Name: cp1253 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1253 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1253 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C #UNDEFINED +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C #UNDEFINED +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F #UNDEFINED +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x0385 #GREEK DIALYTIKA TONOS +0xA2 0x0386 #GREEK CAPITAL LETTER ALPHA WITH TONOS +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA #UNDEFINED +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x2015 #HORIZONTAL BAR +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x0384 #GREEK TONOS +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x0388 #GREEK CAPITAL LETTER EPSILON WITH TONOS +0xB9 0x0389 #GREEK CAPITAL LETTER ETA WITH TONOS +0xBA 0x038A #GREEK CAPITAL LETTER IOTA WITH TONOS +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x038C #GREEK CAPITAL LETTER OMICRON WITH TONOS +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x038E #GREEK CAPITAL LETTER UPSILON WITH TONOS +0xBF 0x038F #GREEK CAPITAL LETTER OMEGA WITH TONOS +0xC0 0x0390 #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0xC1 0x0391 #GREEK CAPITAL LETTER ALPHA +0xC2 0x0392 #GREEK CAPITAL LETTER BETA +0xC3 0x0393 #GREEK CAPITAL LETTER GAMMA +0xC4 0x0394 #GREEK CAPITAL LETTER DELTA +0xC5 0x0395 #GREEK CAPITAL LETTER EPSILON +0xC6 0x0396 #GREEK CAPITAL LETTER ZETA +0xC7 0x0397 #GREEK CAPITAL LETTER ETA +0xC8 0x0398 #GREEK CAPITAL LETTER THETA +0xC9 0x0399 #GREEK CAPITAL LETTER IOTA +0xCA 0x039A #GREEK CAPITAL LETTER KAPPA +0xCB 0x039B #GREEK CAPITAL LETTER LAMDA +0xCC 0x039C #GREEK CAPITAL LETTER MU +0xCD 0x039D #GREEK CAPITAL LETTER NU +0xCE 0x039E #GREEK CAPITAL LETTER XI +0xCF 0x039F #GREEK CAPITAL LETTER OMICRON +0xD0 0x03A0 #GREEK CAPITAL LETTER PI +0xD1 0x03A1 #GREEK CAPITAL LETTER RHO +0xD2 #UNDEFINED +0xD3 0x03A3 #GREEK CAPITAL LETTER SIGMA +0xD4 0x03A4 #GREEK CAPITAL LETTER TAU +0xD5 0x03A5 #GREEK CAPITAL LETTER UPSILON +0xD6 0x03A6 #GREEK CAPITAL LETTER PHI +0xD7 0x03A7 #GREEK CAPITAL LETTER CHI +0xD8 0x03A8 #GREEK CAPITAL LETTER PSI +0xD9 0x03A9 #GREEK CAPITAL LETTER OMEGA +0xDA 0x03AA #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +0xDB 0x03AB #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +0xDC 0x03AC #GREEK SMALL LETTER ALPHA WITH TONOS +0xDD 0x03AD #GREEK SMALL LETTER EPSILON WITH TONOS +0xDE 0x03AE #GREEK SMALL LETTER ETA WITH TONOS +0xDF 0x03AF #GREEK SMALL LETTER IOTA WITH TONOS +0xE0 0x03B0 #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +0xE1 0x03B1 #GREEK SMALL LETTER ALPHA +0xE2 0x03B2 #GREEK SMALL LETTER BETA +0xE3 0x03B3 #GREEK SMALL LETTER GAMMA +0xE4 0x03B4 #GREEK SMALL LETTER DELTA +0xE5 0x03B5 #GREEK SMALL LETTER EPSILON +0xE6 0x03B6 #GREEK SMALL LETTER ZETA +0xE7 0x03B7 #GREEK SMALL LETTER ETA +0xE8 0x03B8 #GREEK SMALL LETTER THETA +0xE9 0x03B9 #GREEK SMALL LETTER IOTA +0xEA 0x03BA #GREEK SMALL LETTER KAPPA +0xEB 0x03BB #GREEK SMALL LETTER LAMDA +0xEC 0x03BC #GREEK SMALL LETTER MU +0xED 0x03BD #GREEK SMALL LETTER NU +0xEE 0x03BE #GREEK SMALL LETTER XI +0xEF 0x03BF #GREEK SMALL LETTER OMICRON +0xF0 0x03C0 #GREEK SMALL LETTER PI +0xF1 0x03C1 #GREEK SMALL LETTER RHO +0xF2 0x03C2 #GREEK SMALL LETTER FINAL SIGMA +0xF3 0x03C3 #GREEK SMALL LETTER SIGMA +0xF4 0x03C4 #GREEK SMALL LETTER TAU +0xF5 0x03C5 #GREEK SMALL LETTER UPSILON +0xF6 0x03C6 #GREEK SMALL LETTER PHI +0xF7 0x03C7 #GREEK SMALL LETTER CHI +0xF8 0x03C8 #GREEK SMALL LETTER PSI +0xF9 0x03C9 #GREEK SMALL LETTER OMEGA +0xFA 0x03CA #GREEK SMALL LETTER IOTA WITH DIALYTIKA +0xFB 0x03CB #GREEK SMALL LETTER UPSILON WITH DIALYTIKA +0xFC 0x03CC #GREEK SMALL LETTER OMICRON WITH TONOS +0xFD 0x03CD #GREEK SMALL LETTER UPSILON WITH TONOS +0xFE 0x03CE #GREEK SMALL LETTER OMEGA WITH TONOS +0xFF #UNDEFINED diff --git a/program/lib/encoding/CP1254.map b/program/lib/encoding/CP1254.map new file mode 100644 index 000000000..ca1a1ebdb --- /dev/null +++ b/program/lib/encoding/CP1254.map @@ -0,0 +1,274 @@ +# +# Name: cp1254 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1254 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1254 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x011E #LATIN CAPITAL LETTER G WITH BREVE +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE +0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x011F #LATIN SMALL LETTER G WITH BREVE +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x0131 #LATIN SMALL LETTER DOTLESS I +0xFE 0x015F #LATIN SMALL LETTER S WITH CEDILLA +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS diff --git a/program/lib/encoding/CP1255.map b/program/lib/encoding/CP1255.map new file mode 100644 index 000000000..341517f11 --- /dev/null +++ b/program/lib/encoding/CP1255.map @@ -0,0 +1,274 @@ +# +# Name: cp1255 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 1/7/2000 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1255 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1255 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C #UNDEFINED +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C #UNDEFINED +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F #UNDEFINED +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x20AA #NEW SHEQEL SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00D7 #MULTIPLICATION SIGN +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00F7 #DIVISION SIGN +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x05B0 #HEBREW POINT SHEVA +0xC1 0x05B1 #HEBREW POINT HATAF SEGOL +0xC2 0x05B2 #HEBREW POINT HATAF PATAH +0xC3 0x05B3 #HEBREW POINT HATAF QAMATS +0xC4 0x05B4 #HEBREW POINT HIRIQ +0xC5 0x05B5 #HEBREW POINT TSERE +0xC6 0x05B6 #HEBREW POINT SEGOL +0xC7 0x05B7 #HEBREW POINT PATAH +0xC8 0x05B8 #HEBREW POINT QAMATS +0xC9 0x05B9 #HEBREW POINT HOLAM +0xCA #UNDEFINED +0xCB 0x05BB #HEBREW POINT QUBUTS +0xCC 0x05BC #HEBREW POINT DAGESH OR MAPIQ +0xCD 0x05BD #HEBREW POINT METEG +0xCE 0x05BE #HEBREW PUNCTUATION MAQAF +0xCF 0x05BF #HEBREW POINT RAFE +0xD0 0x05C0 #HEBREW PUNCTUATION PASEQ +0xD1 0x05C1 #HEBREW POINT SHIN DOT +0xD2 0x05C2 #HEBREW POINT SIN DOT +0xD3 0x05C3 #HEBREW PUNCTUATION SOF PASUQ +0xD4 0x05F0 #HEBREW LIGATURE YIDDISH DOUBLE VAV +0xD5 0x05F1 #HEBREW LIGATURE YIDDISH VAV YOD +0xD6 0x05F2 #HEBREW LIGATURE YIDDISH DOUBLE YOD +0xD7 0x05F3 #HEBREW PUNCTUATION GERESH +0xD8 0x05F4 #HEBREW PUNCTUATION GERSHAYIM +0xD9 #UNDEFINED +0xDA #UNDEFINED +0xDB #UNDEFINED +0xDC #UNDEFINED +0xDD #UNDEFINED +0xDE #UNDEFINED +0xDF #UNDEFINED +0xE0 0x05D0 #HEBREW LETTER ALEF +0xE1 0x05D1 #HEBREW LETTER BET +0xE2 0x05D2 #HEBREW LETTER GIMEL +0xE3 0x05D3 #HEBREW LETTER DALET +0xE4 0x05D4 #HEBREW LETTER HE +0xE5 0x05D5 #HEBREW LETTER VAV +0xE6 0x05D6 #HEBREW LETTER ZAYIN +0xE7 0x05D7 #HEBREW LETTER HET +0xE8 0x05D8 #HEBREW LETTER TET +0xE9 0x05D9 #HEBREW LETTER YOD +0xEA 0x05DA #HEBREW LETTER FINAL KAF +0xEB 0x05DB #HEBREW LETTER KAF +0xEC 0x05DC #HEBREW LETTER LAMED +0xED 0x05DD #HEBREW LETTER FINAL MEM +0xEE 0x05DE #HEBREW LETTER MEM +0xEF 0x05DF #HEBREW LETTER FINAL NUN +0xF0 0x05E0 #HEBREW LETTER NUN +0xF1 0x05E1 #HEBREW LETTER SAMEKH +0xF2 0x05E2 #HEBREW LETTER AYIN +0xF3 0x05E3 #HEBREW LETTER FINAL PE +0xF4 0x05E4 #HEBREW LETTER PE +0xF5 0x05E5 #HEBREW LETTER FINAL TSADI +0xF6 0x05E6 #HEBREW LETTER TSADI +0xF7 0x05E7 #HEBREW LETTER QOF +0xF8 0x05E8 #HEBREW LETTER RESH +0xF9 0x05E9 #HEBREW LETTER SHIN +0xFA 0x05EA #HEBREW LETTER TAV +0xFB #UNDEFINED +0xFC #UNDEFINED +0xFD 0x200E #LEFT-TO-RIGHT MARK +0xFE 0x200F #RIGHT-TO-LEFT MARK +0xFF #UNDEFINED diff --git a/program/lib/encoding/CP1256.map b/program/lib/encoding/CP1256.map new file mode 100644 index 000000000..0edd081b9 --- /dev/null +++ b/program/lib/encoding/CP1256.map @@ -0,0 +1,274 @@ +# +# Name: cp1256 to Unicode table +# Unicode version: 2.1 +# Table version: 2.01 +# Table format: Format A +# Date: 01/5/99 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1256 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1256 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 0x067E #ARABIC LETTER PEH +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A 0x0679 #ARABIC LETTER TTEH +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D 0x0686 #ARABIC LETTER TCHEH +0x8E 0x0698 #ARABIC LETTER JEH +0x8F 0x0688 #ARABIC LETTER DDAL +0x90 0x06AF #ARABIC LETTER GAF +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x06A9 #ARABIC LETTER KEHEH +0x99 0x2122 #TRADE MARK SIGN +0x9A 0x0691 #ARABIC LETTER RREH +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D 0x200C #ZERO WIDTH NON-JOINER +0x9E 0x200D #ZERO WIDTH JOINER +0x9F 0x06BA #ARABIC LETTER NOON GHUNNA +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x060C #ARABIC COMMA +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x06BE #ARABIC LETTER HEH DOACHASHMEE +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x061B #ARABIC SEMICOLON +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x061F #ARABIC QUESTION MARK +0xC0 0x06C1 #ARABIC LETTER HEH GOAL +0xC1 0x0621 #ARABIC LETTER HAMZA +0xC2 0x0622 #ARABIC LETTER ALEF WITH MADDA ABOVE +0xC3 0x0623 #ARABIC LETTER ALEF WITH HAMZA ABOVE +0xC4 0x0624 #ARABIC LETTER WAW WITH HAMZA ABOVE +0xC5 0x0625 #ARABIC LETTER ALEF WITH HAMZA BELOW +0xC6 0x0626 #ARABIC LETTER YEH WITH HAMZA ABOVE +0xC7 0x0627 #ARABIC LETTER ALEF +0xC8 0x0628 #ARABIC LETTER BEH +0xC9 0x0629 #ARABIC LETTER TEH MARBUTA +0xCA 0x062A #ARABIC LETTER TEH +0xCB 0x062B #ARABIC LETTER THEH +0xCC 0x062C #ARABIC LETTER JEEM +0xCD 0x062D #ARABIC LETTER HAH +0xCE 0x062E #ARABIC LETTER KHAH +0xCF 0x062F #ARABIC LETTER DAL +0xD0 0x0630 #ARABIC LETTER THAL +0xD1 0x0631 #ARABIC LETTER REH +0xD2 0x0632 #ARABIC LETTER ZAIN +0xD3 0x0633 #ARABIC LETTER SEEN +0xD4 0x0634 #ARABIC LETTER SHEEN +0xD5 0x0635 #ARABIC LETTER SAD +0xD6 0x0636 #ARABIC LETTER DAD +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0637 #ARABIC LETTER TAH +0xD9 0x0638 #ARABIC LETTER ZAH +0xDA 0x0639 #ARABIC LETTER AIN +0xDB 0x063A #ARABIC LETTER GHAIN +0xDC 0x0640 #ARABIC TATWEEL +0xDD 0x0641 #ARABIC LETTER FEH +0xDE 0x0642 #ARABIC LETTER QAF +0xDF 0x0643 #ARABIC LETTER KAF +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x0644 #ARABIC LETTER LAM +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0645 #ARABIC LETTER MEEM +0xE4 0x0646 #ARABIC LETTER NOON +0xE5 0x0647 #ARABIC LETTER HEH +0xE6 0x0648 #ARABIC LETTER WAW +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0649 #ARABIC LETTER ALEF MAKSURA +0xED 0x064A #ARABIC LETTER YEH +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x064B #ARABIC FATHATAN +0xF1 0x064C #ARABIC DAMMATAN +0xF2 0x064D #ARABIC KASRATAN +0xF3 0x064E #ARABIC FATHA +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x064F #ARABIC DAMMA +0xF6 0x0650 #ARABIC KASRA +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0651 #ARABIC SHADDA +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x0652 #ARABIC SUKUN +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x200E #LEFT-TO-RIGHT MARK +0xFE 0x200F #RIGHT-TO-LEFT MARK +0xFF 0x06D2 #ARABIC LETTER YEH BARREE diff --git a/program/lib/encoding/CP1257.map b/program/lib/encoding/CP1257.map new file mode 100644 index 000000000..97979d931 --- /dev/null +++ b/program/lib/encoding/CP1257.map @@ -0,0 +1,274 @@ +# +# Name: cp1257 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1257 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1257 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 #UNDEFINED +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 #UNDEFINED +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C #UNDEFINED +0x8D 0x00A8 #DIAERESIS +0x8E 0x02C7 #CARON +0x8F 0x00B8 #CEDILLA +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 #UNDEFINED +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C #UNDEFINED +0x9D 0x00AF #MACRON +0x9E 0x02DB #OGONEK +0x9F #UNDEFINED +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 #UNDEFINED +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 #UNDEFINED +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00C6 #LATIN CAPITAL LETTER AE +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x0157 #LATIN SMALL LETTER R WITH CEDILLA +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00E6 #LATIN SMALL LETTER AE +0xC0 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK +0xC1 0x012E #LATIN CAPITAL LETTER I WITH OGONEK +0xC2 0x0100 #LATIN CAPITAL LETTER A WITH MACRON +0xC3 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK +0xC7 0x0112 #LATIN CAPITAL LETTER E WITH MACRON +0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE +0xCB 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCC 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA +0xCD 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA +0xCE 0x012A #LATIN CAPITAL LETTER I WITH MACRON +0xCF 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA +0xD0 0x0160 #LATIN CAPITAL LETTER S WITH CARON +0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x014C #LATIN CAPITAL LETTER O WITH MACRON +0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK +0xD9 0x0141 #LATIN CAPITAL LETTER L WITH STROKE +0xDA 0x015A #LATIN CAPITAL LETTER S WITH ACUTE +0xDB 0x016A #LATIN CAPITAL LETTER U WITH MACRON +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xDE 0x017D #LATIN CAPITAL LETTER Z WITH CARON +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x0105 #LATIN SMALL LETTER A WITH OGONEK +0xE1 0x012F #LATIN SMALL LETTER I WITH OGONEK +0xE2 0x0101 #LATIN SMALL LETTER A WITH MACRON +0xE3 0x0107 #LATIN SMALL LETTER C WITH ACUTE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x0119 #LATIN SMALL LETTER E WITH OGONEK +0xE7 0x0113 #LATIN SMALL LETTER E WITH MACRON +0xE8 0x010D #LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x017A #LATIN SMALL LETTER Z WITH ACUTE +0xEB 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE +0xEC 0x0123 #LATIN SMALL LETTER G WITH CEDILLA +0xED 0x0137 #LATIN SMALL LETTER K WITH CEDILLA +0xEE 0x012B #LATIN SMALL LETTER I WITH MACRON +0xEF 0x013C #LATIN SMALL LETTER L WITH CEDILLA +0xF0 0x0161 #LATIN SMALL LETTER S WITH CARON +0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0146 #LATIN SMALL LETTER N WITH CEDILLA +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x014D #LATIN SMALL LETTER O WITH MACRON +0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x0173 #LATIN SMALL LETTER U WITH OGONEK +0xF9 0x0142 #LATIN SMALL LETTER L WITH STROKE +0xFA 0x015B #LATIN SMALL LETTER S WITH ACUTE +0xFB 0x016B #LATIN SMALL LETTER U WITH MACRON +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE +0xFE 0x017E #LATIN SMALL LETTER Z WITH CARON +0xFF 0x02D9 #DOT ABOVE diff --git a/program/lib/encoding/CP1258.map b/program/lib/encoding/CP1258.map new file mode 100644 index 000000000..392310a8c --- /dev/null +++ b/program/lib/encoding/CP1258.map @@ -0,0 +1,274 @@ +# +# Name: cp1258 to Unicode table +# Unicode version: 2.0 +# Table version: 2.01 +# Table format: Format A +# Date: 04/15/98 +# +# Contact: cpxlate@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp1258 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp1258 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0A 0x000A #LINE FEED +0x0B 0x000B #VERTICAL TABULATION +0x0C 0x000C #FORM FEED +0x0D 0x000D #CARRIAGE RETURN +0x0E 0x000E #SHIFT OUT +0x0F 0x000F #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1A 0x001A #SUBSTITUTE +0x1B 0x001B #ESCAPE +0x1C 0x001C #FILE SEPARATOR +0x1D 0x001D #GROUP SEPARATOR +0x1E 0x001E #RECORD SEPARATOR +0x1F 0x001F #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2A 0x002A #ASTERISK +0x2B 0x002B #PLUS SIGN +0x2C 0x002C #COMMA +0x2D 0x002D #HYPHEN-MINUS +0x2E 0x002E #FULL STOP +0x2F 0x002F #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3A 0x003A #COLON +0x3B 0x003B #SEMICOLON +0x3C 0x003C #LESS-THAN SIGN +0x3D 0x003D #EQUALS SIGN +0x3E 0x003E #GREATER-THAN SIGN +0x3F 0x003F #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4A 0x004A #LATIN CAPITAL LETTER J +0x4B 0x004B #LATIN CAPITAL LETTER K +0x4C 0x004C #LATIN CAPITAL LETTER L +0x4D 0x004D #LATIN CAPITAL LETTER M +0x4E 0x004E #LATIN CAPITAL LETTER N +0x4F 0x004F #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5A 0x005A #LATIN CAPITAL LETTER Z +0x5B 0x005B #LEFT SQUARE BRACKET +0x5C 0x005C #REVERSE SOLIDUS +0x5D 0x005D #RIGHT SQUARE BRACKET +0x5E 0x005E #CIRCUMFLEX ACCENT +0x5F 0x005F #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6A 0x006A #LATIN SMALL LETTER J +0x6B 0x006B #LATIN SMALL LETTER K +0x6C 0x006C #LATIN SMALL LETTER L +0x6D 0x006D #LATIN SMALL LETTER M +0x6E 0x006E #LATIN SMALL LETTER N +0x6F 0x006F #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7A 0x007A #LATIN SMALL LETTER Z +0x7B 0x007B #LEFT CURLY BRACKET +0x7C 0x007C #VERTICAL LINE +0x7D 0x007D #RIGHT CURLY BRACKET +0x7E 0x007E #TILDE +0x7F 0x007F #DELETE +0x80 0x20AC #EURO SIGN +0x81 #UNDEFINED +0x82 0x201A #SINGLE LOW-9 QUOTATION MARK +0x83 0x0192 #LATIN SMALL LETTER F WITH HOOK +0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK +0x85 0x2026 #HORIZONTAL ELLIPSIS +0x86 0x2020 #DAGGER +0x87 0x2021 #DOUBLE DAGGER +0x88 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT +0x89 0x2030 #PER MILLE SIGN +0x8A #UNDEFINED +0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0x8C 0x0152 #LATIN CAPITAL LIGATURE OE +0x8D #UNDEFINED +0x8E #UNDEFINED +0x8F #UNDEFINED +0x90 #UNDEFINED +0x91 0x2018 #LEFT SINGLE QUOTATION MARK +0x92 0x2019 #RIGHT SINGLE QUOTATION MARK +0x93 0x201C #LEFT DOUBLE QUOTATION MARK +0x94 0x201D #RIGHT DOUBLE QUOTATION MARK +0x95 0x2022 #BULLET +0x96 0x2013 #EN DASH +0x97 0x2014 #EM DASH +0x98 0x02DC #SMALL TILDE +0x99 0x2122 #TRADE MARK SIGN +0x9A #UNDEFINED +0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0x9C 0x0153 #LATIN SMALL LIGATURE OE +0x9D #UNDEFINED +0x9E #UNDEFINED +0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS +0xA0 0x00A0 #NO-BREAK SPACE +0xA1 0x00A1 #INVERTED EXCLAMATION MARK +0xA2 0x00A2 #CENT SIGN +0xA3 0x00A3 #POUND SIGN +0xA4 0x00A4 #CURRENCY SIGN +0xA5 0x00A5 #YEN SIGN +0xA6 0x00A6 #BROKEN BAR +0xA7 0x00A7 #SECTION SIGN +0xA8 0x00A8 #DIAERESIS +0xA9 0x00A9 #COPYRIGHT SIGN +0xAA 0x00AA #FEMININE ORDINAL INDICATOR +0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC #NOT SIGN +0xAD 0x00AD #SOFT HYPHEN +0xAE 0x00AE #REGISTERED SIGN +0xAF 0x00AF #MACRON +0xB0 0x00B0 #DEGREE SIGN +0xB1 0x00B1 #PLUS-MINUS SIGN +0xB2 0x00B2 #SUPERSCRIPT TWO +0xB3 0x00B3 #SUPERSCRIPT THREE +0xB4 0x00B4 #ACUTE ACCENT +0xB5 0x00B5 #MICRO SIGN +0xB6 0x00B6 #PILCROW SIGN +0xB7 0x00B7 #MIDDLE DOT +0xB8 0x00B8 #CEDILLA +0xB9 0x00B9 #SUPERSCRIPT ONE +0xBA 0x00BA #MASCULINE ORDINAL INDICATOR +0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC #VULGAR FRACTION ONE QUARTER +0xBD 0x00BD #VULGAR FRACTION ONE HALF +0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF #INVERTED QUESTION MARK +0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 #LATIN CAPITAL LETTER AE +0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x0300 #COMBINING GRAVE ACCENT +0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x0309 #COMBINING HOOK ABOVE +0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x01A0 #LATIN CAPITAL LETTER O WITH HORN +0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 #MULTIPLICATION SIGN +0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x01AF #LATIN CAPITAL LETTER U WITH HORN +0xDE 0x0303 #COMBINING TILDE +0xDF 0x00DF #LATIN SMALL LETTER SHARP S +0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 #LATIN SMALL LETTER AE +0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0301 #COMBINING ACUTE ACCENT +0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE +0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE +0xF2 0x0323 #COMBINING DOT BELOW +0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x01A1 #LATIN SMALL LETTER O WITH HORN +0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 #DIVISION SIGN +0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x01B0 #LATIN SMALL LETTER U WITH HORN +0xFE 0x20AB #DONG SIGN +0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS diff --git a/program/lib/encoding/ISO-8859-1.map b/program/lib/encoding/ISO-8859-1.map new file mode 100644 index 000000000..473ecabc1 --- /dev/null +++ b/program/lib/encoding/ISO-8859-1.map @@ -0,0 +1,303 @@ +# +# Name: ISO/IEC 8859-1:1998 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler +# +# 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 +# ISO/IEC 8859-1:1998 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-1 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-1 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x00A1 # INVERTED EXCLAMATION MARK +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00AA # FEMININE ORDINAL INDICATOR +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00BA # MASCULINE ORDINAL INDICATOR +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC # VULGAR FRACTION ONE QUARTER +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF # INVERTED QUESTION MARK +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic) +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic) +0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German) +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x00F0 # LATIN SMALL LETTER ETH (Icelandic) +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic) +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS diff --git a/program/lib/encoding/ISO-8859-2.map b/program/lib/encoding/ISO-8859-2.map new file mode 100644 index 000000000..e45df25eb --- /dev/null +++ b/program/lib/encoding/ISO-8859-2.map @@ -0,0 +1,303 @@ +# +# Name: ISO 8859-2:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler +# +# 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 +# ISO/IEC 8859-2:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-2 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-2 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x02D8 # BREVE +0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x013D # LATIN CAPITAL LETTER L WITH CARON +0xA6 0x015A # LATIN CAPITAL LETTER S WITH ACUTE +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON +0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x0164 # LATIN CAPITAL LETTER T WITH CARON +0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON +0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK +0xB2 0x02DB # OGONEK +0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x013E # LATIN SMALL LETTER L WITH CARON +0xB6 0x015B # LATIN SMALL LETTER S WITH ACUTE +0xB7 0x02C7 # CARON +0xB8 0x00B8 # CEDILLA +0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON +0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x0165 # LATIN SMALL LETTER T WITH CARON +0xBC 0x017A # LATIN SMALL LETTER Z WITH ACUTE +0xBD 0x02DD # DOUBLE ACUTE ACCENT +0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON +0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x0154 # LATIN CAPITAL LETTER R WITH ACUTE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x0102 # LATIN CAPITAL LETTER A WITH BREVE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x0139 # LATIN CAPITAL LETTER L WITH ACUTE +0xC6 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x011A # LATIN CAPITAL LETTER E WITH CARON +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x010E # LATIN CAPITAL LETTER D WITH CARON +0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE +0xD2 0x0147 # LATIN CAPITAL LETTER N WITH CARON +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x0158 # LATIN CAPITAL LETTER R WITH CARON +0xD9 0x016E # LATIN CAPITAL LETTER U WITH RING ABOVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE +0xDE 0x0162 # LATIN CAPITAL LETTER T WITH CEDILLA +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x0155 # LATIN SMALL LETTER R WITH ACUTE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x0103 # LATIN SMALL LETTER A WITH BREVE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x013A # LATIN SMALL LETTER L WITH ACUTE +0xE6 0x0107 # LATIN SMALL LETTER C WITH ACUTE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x010D # LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x011B # LATIN SMALL LETTER E WITH CARON +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x010F # LATIN SMALL LETTER D WITH CARON +0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE +0xF2 0x0148 # LATIN SMALL LETTER N WITH CARON +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x0159 # LATIN SMALL LETTER R WITH CARON +0xF9 0x016F # LATIN SMALL LETTER U WITH RING ABOVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE +0xFE 0x0163 # LATIN SMALL LETTER T WITH CEDILLA +0xFF 0x02D9 # DOT ABOVE diff --git a/program/lib/encoding/ISO-8859-3.map b/program/lib/encoding/ISO-8859-3.map new file mode 100644 index 000000000..9b6ac69dd --- /dev/null +++ b/program/lib/encoding/ISO-8859-3.map @@ -0,0 +1,296 @@ +# +# Name: ISO/IEC 8859-3:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler +# +# 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 +# ISO/IEC 8859-3:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-3 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-3 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE +0xA2 0x02D8 # BREVE +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE +0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE +0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX +0xAD 0x00AD # SOFT HYPHEN +0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I +0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA +0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE +0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE +0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x016C # LATIN CAPITAL LETTER U WITH BREVE +0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE +0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x016D # LATIN SMALL LETTER U WITH BREVE +0xFE 0x015D # LATIN SMALL LETTER S WITH CIRCUMFLEX +0xFF 0x02D9 # DOT ABOVE diff --git a/program/lib/encoding/ISO-8859-4.map b/program/lib/encoding/ISO-8859-4.map new file mode 100644 index 000000000..662e698ab --- /dev/null +++ b/program/lib/encoding/ISO-8859-4.map @@ -0,0 +1,303 @@ +# +# Name: ISO/IEC 8859-4:1998 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler +# +# 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 +# ISO/IEC 8859-4:1998 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-4 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-4 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK +0xA2 0x0138 # LATIN SMALL LETTER KRA +0xA3 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE +0xA6 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON +0xAA 0x0112 # LATIN CAPITAL LETTER E WITH MACRON +0xAB 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA +0xAC 0x0166 # LATIN CAPITAL LETTER T WITH STROKE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK +0xB2 0x02DB # OGONEK +0xB3 0x0157 # LATIN SMALL LETTER R WITH CEDILLA +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE +0xB6 0x013C # LATIN SMALL LETTER L WITH CEDILLA +0xB7 0x02C7 # CARON +0xB8 0x00B8 # CEDILLA +0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON +0xBA 0x0113 # LATIN SMALL LETTER E WITH MACRON +0xBB 0x0123 # LATIN SMALL LETTER G WITH CEDILLA +0xBC 0x0167 # LATIN SMALL LETTER T WITH STROKE +0xBD 0x014A # LATIN CAPITAL LETTER ENG +0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON +0xBF 0x014B # LATIN SMALL LETTER ENG +0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x012E # LATIN CAPITAL LETTER I WITH OGONEK +0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x012A # LATIN CAPITAL LETTER I WITH MACRON +0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE +0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA +0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON +0xD3 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0168 # LATIN CAPITAL LETTER U WITH TILDE +0xDE 0x016A # LATIN CAPITAL LETTER U WITH MACRON +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x012F # LATIN SMALL LETTER I WITH OGONEK +0xE8 0x010D # LATIN SMALL LETTER C WITH CARON +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x012B # LATIN SMALL LETTER I WITH MACRON +0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE +0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA +0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON +0xF3 0x0137 # LATIN SMALL LETTER K WITH CEDILLA +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x0169 # LATIN SMALL LETTER U WITH TILDE +0xFE 0x016B # LATIN SMALL LETTER U WITH MACRON +0xFF 0x02D9 # DOT ABOVE diff --git a/program/lib/encoding/ISO-8859-5.map b/program/lib/encoding/ISO-8859-5.map new file mode 100644 index 000000000..a7ed1ce2a --- /dev/null +++ b/program/lib/encoding/ISO-8859-5.map @@ -0,0 +1,303 @@ +# +# Name: ISO 8859-5:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler +# +# 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 +# ISO/IEC 8859-5:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-5 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-5 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x0401 # CYRILLIC CAPITAL LETTER IO +0xA2 0x0402 # CYRILLIC CAPITAL LETTER DJE +0xA3 0x0403 # CYRILLIC CAPITAL LETTER GJE +0xA4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xA5 0x0405 # CYRILLIC CAPITAL LETTER DZE +0xA6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xA7 0x0407 # CYRILLIC CAPITAL LETTER YI +0xA8 0x0408 # CYRILLIC CAPITAL LETTER JE +0xA9 0x0409 # CYRILLIC CAPITAL LETTER LJE +0xAA 0x040A # CYRILLIC CAPITAL LETTER NJE +0xAB 0x040B # CYRILLIC CAPITAL LETTER TSHE +0xAC 0x040C # CYRILLIC CAPITAL LETTER KJE +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x040E # CYRILLIC CAPITAL LETTER SHORT U +0xAF 0x040F # CYRILLIC CAPITAL LETTER DZHE +0xB0 0x0410 # CYRILLIC CAPITAL LETTER A +0xB1 0x0411 # CYRILLIC CAPITAL LETTER BE +0xB2 0x0412 # CYRILLIC CAPITAL LETTER VE +0xB3 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xB4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xB5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xB6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xB7 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xB8 0x0418 # CYRILLIC CAPITAL LETTER I +0xB9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xBA 0x041A # CYRILLIC CAPITAL LETTER KA +0xBB 0x041B # CYRILLIC CAPITAL LETTER EL +0xBC 0x041C # CYRILLIC CAPITAL LETTER EM +0xBD 0x041D # CYRILLIC CAPITAL LETTER EN +0xBE 0x041E # CYRILLIC CAPITAL LETTER O +0xBF 0x041F # CYRILLIC CAPITAL LETTER PE +0xC0 0x0420 # CYRILLIC CAPITAL LETTER ER +0xC1 0x0421 # CYRILLIC CAPITAL LETTER ES +0xC2 0x0422 # CYRILLIC CAPITAL LETTER TE +0xC3 0x0423 # CYRILLIC CAPITAL LETTER U +0xC4 0x0424 # CYRILLIC CAPITAL LETTER EF +0xC5 0x0425 # CYRILLIC CAPITAL LETTER HA +0xC6 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xC7 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xC8 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xC9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xCA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN +0xCB 0x042B # CYRILLIC CAPITAL LETTER YERU +0xCC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xCD 0x042D # CYRILLIC CAPITAL LETTER E +0xCE 0x042E # CYRILLIC CAPITAL LETTER YU +0xCF 0x042F # CYRILLIC CAPITAL LETTER YA +0xD0 0x0430 # CYRILLIC SMALL LETTER A +0xD1 0x0431 # CYRILLIC SMALL LETTER BE +0xD2 0x0432 # CYRILLIC SMALL LETTER VE +0xD3 0x0433 # CYRILLIC SMALL LETTER GHE +0xD4 0x0434 # CYRILLIC SMALL LETTER DE +0xD5 0x0435 # CYRILLIC SMALL LETTER IE +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0437 # CYRILLIC SMALL LETTER ZE +0xD8 0x0438 # CYRILLIC SMALL LETTER I +0xD9 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xDA 0x043A # CYRILLIC SMALL LETTER KA +0xDB 0x043B # CYRILLIC SMALL LETTER EL +0xDC 0x043C # CYRILLIC SMALL LETTER EM +0xDD 0x043D # CYRILLIC SMALL LETTER EN +0xDE 0x043E # CYRILLIC SMALL LETTER O +0xDF 0x043F # CYRILLIC SMALL LETTER PE +0xE0 0x0440 # CYRILLIC SMALL LETTER ER +0xE1 0x0441 # CYRILLIC SMALL LETTER ES +0xE2 0x0442 # CYRILLIC SMALL LETTER TE +0xE3 0x0443 # CYRILLIC SMALL LETTER U +0xE4 0x0444 # CYRILLIC SMALL LETTER EF +0xE5 0x0445 # CYRILLIC SMALL LETTER HA +0xE6 0x0446 # CYRILLIC SMALL LETTER TSE +0xE7 0x0447 # CYRILLIC SMALL LETTER CHE +0xE8 0x0448 # CYRILLIC SMALL LETTER SHA +0xE9 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xEA 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xEB 0x044B # CYRILLIC SMALL LETTER YERU +0xEC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xED 0x044D # CYRILLIC SMALL LETTER E +0xEE 0x044E # CYRILLIC SMALL LETTER YU +0xEF 0x044F # CYRILLIC SMALL LETTER YA +0xF0 0x2116 # NUMERO SIGN +0xF1 0x0451 # CYRILLIC SMALL LETTER IO +0xF2 0x0452 # CYRILLIC SMALL LETTER DJE +0xF3 0x0453 # CYRILLIC SMALL LETTER GJE +0xF4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xF5 0x0455 # CYRILLIC SMALL LETTER DZE +0xF6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xF7 0x0457 # CYRILLIC SMALL LETTER YI +0xF8 0x0458 # CYRILLIC SMALL LETTER JE +0xF9 0x0459 # CYRILLIC SMALL LETTER LJE +0xFA 0x045A # CYRILLIC SMALL LETTER NJE +0xFB 0x045B # CYRILLIC SMALL LETTER TSHE +0xFC 0x045C # CYRILLIC SMALL LETTER KJE +0xFD 0x00A7 # SECTION SIGN +0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U +0xFF 0x045F # CYRILLIC SMALL LETTER DZHE diff --git a/program/lib/encoding/ISO-8859-6.map b/program/lib/encoding/ISO-8859-6.map new file mode 100644 index 000000000..69ac7f589 --- /dev/null +++ b/program/lib/encoding/ISO-8859-6.map @@ -0,0 +1,260 @@ +# +# Name: ISO 8859-6:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler +# +# 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 +# ISO/IEC 8859-6:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-6 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-6 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead +# of the Arabic digits (U+0660..U+0669). +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA4 0x00A4 # CURRENCY SIGN +0xAC 0x060C # ARABIC COMMA +0xAD 0x00AD # SOFT HYPHEN +0xBB 0x061B # ARABIC SEMICOLON +0xBF 0x061F # ARABIC QUESTION MARK +0xC1 0x0621 # ARABIC LETTER HAMZA +0xC2 0x0622 # ARABIC LETTER ALEF WITH MADDA ABOVE +0xC3 0x0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE +0xC4 0x0624 # ARABIC LETTER WAW WITH HAMZA ABOVE +0xC5 0x0625 # ARABIC LETTER ALEF WITH HAMZA BELOW +0xC6 0x0626 # ARABIC LETTER YEH WITH HAMZA ABOVE +0xC7 0x0627 # ARABIC LETTER ALEF +0xC8 0x0628 # ARABIC LETTER BEH +0xC9 0x0629 # ARABIC LETTER TEH MARBUTA +0xCA 0x062A # ARABIC LETTER TEH +0xCB 0x062B # ARABIC LETTER THEH +0xCC 0x062C # ARABIC LETTER JEEM +0xCD 0x062D # ARABIC LETTER HAH +0xCE 0x062E # ARABIC LETTER KHAH +0xCF 0x062F # ARABIC LETTER DAL +0xD0 0x0630 # ARABIC LETTER THAL +0xD1 0x0631 # ARABIC LETTER REH +0xD2 0x0632 # ARABIC LETTER ZAIN +0xD3 0x0633 # ARABIC LETTER SEEN +0xD4 0x0634 # ARABIC LETTER SHEEN +0xD5 0x0635 # ARABIC LETTER SAD +0xD6 0x0636 # ARABIC LETTER DAD +0xD7 0x0637 # ARABIC LETTER TAH +0xD8 0x0638 # ARABIC LETTER ZAH +0xD9 0x0639 # ARABIC LETTER AIN +0xDA 0x063A # ARABIC LETTER GHAIN +0xE0 0x0640 # ARABIC TATWEEL +0xE1 0x0641 # ARABIC LETTER FEH +0xE2 0x0642 # ARABIC LETTER QAF +0xE3 0x0643 # ARABIC LETTER KAF +0xE4 0x0644 # ARABIC LETTER LAM +0xE5 0x0645 # ARABIC LETTER MEEM +0xE6 0x0646 # ARABIC LETTER NOON +0xE7 0x0647 # ARABIC LETTER HEH +0xE8 0x0648 # ARABIC LETTER WAW +0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA +0xEA 0x064A # ARABIC LETTER YEH +0xEB 0x064B # ARABIC FATHATAN +0xEC 0x064C # ARABIC DAMMATAN +0xED 0x064D # ARABIC KASRATAN +0xEE 0x064E # ARABIC FATHA +0xEF 0x064F # ARABIC DAMMA +0xF0 0x0650 # ARABIC KASRA +0xF1 0x0651 # ARABIC SHADDA +0xF2 0x0652 # ARABIC SUKUN diff --git a/program/lib/encoding/ISO-8859-7.map b/program/lib/encoding/ISO-8859-7.map new file mode 100644 index 000000000..bc46b7471 --- /dev/null +++ b/program/lib/encoding/ISO-8859-7.map @@ -0,0 +1,308 @@ +# +# Name: ISO 8859-7:2003 to Unicode +# Unicode version: 4.0 +# Table version: 2.0 +# Table format: Format A +# Date: 2003-Nov-12 +# Authors: Ken Whistler +# +# Copyright (c) 1991-2003 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 8859-7:2003 characters map into Unicode. +# +# ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928, +# and ECMA 118. ISO 8859-7:2003 adds two currency signs +# and one other character not in the earlier standard. +# +# Format: Three tab-separated columns +# Column #1 is the ISO 8859-7 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO 8859-7 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7 +# Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7 +# +# 2.0 version updates 1.0 version by adding mappings for the +# three newly added characters 0xA4, 0xA5, 0xAA. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact the Unicode Consortium at: +# +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x0080 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x2018 # LEFT SINGLE QUOTATION MARK +0xA2 0x2019 # RIGHT SINGLE QUOTATION MARK +0xA3 0x00A3 # POUND SIGN +0xA4 0x20AC # EURO SIGN +0xA5 0x20AF # DRACHMA SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x037A # GREEK YPOGEGRAMMENI +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAF 0x2015 # HORIZONTAL BAR +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x0384 # GREEK TONOS +0xB5 0x0385 # GREEK DIALYTIKA TONOS +0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS +0xB9 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS +0xBA 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS +0xBF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS +0xC0 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0xC1 0x0391 # GREEK CAPITAL LETTER ALPHA +0xC2 0x0392 # GREEK CAPITAL LETTER BETA +0xC3 0x0393 # GREEK CAPITAL LETTER GAMMA +0xC4 0x0394 # GREEK CAPITAL LETTER DELTA +0xC5 0x0395 # GREEK CAPITAL LETTER EPSILON +0xC6 0x0396 # GREEK CAPITAL LETTER ZETA +0xC7 0x0397 # GREEK CAPITAL LETTER ETA +0xC8 0x0398 # GREEK CAPITAL LETTER THETA +0xC9 0x0399 # GREEK CAPITAL LETTER IOTA +0xCA 0x039A # GREEK CAPITAL LETTER KAPPA +0xCB 0x039B # GREEK CAPITAL LETTER LAMDA +0xCC 0x039C # GREEK CAPITAL LETTER MU +0xCD 0x039D # GREEK CAPITAL LETTER NU +0xCE 0x039E # GREEK CAPITAL LETTER XI +0xCF 0x039F # GREEK CAPITAL LETTER OMICRON +0xD0 0x03A0 # GREEK CAPITAL LETTER PI +0xD1 0x03A1 # GREEK CAPITAL LETTER RHO +0xD3 0x03A3 # GREEK CAPITAL LETTER SIGMA +0xD4 0x03A4 # GREEK CAPITAL LETTER TAU +0xD5 0x03A5 # GREEK CAPITAL LETTER UPSILON +0xD6 0x03A6 # GREEK CAPITAL LETTER PHI +0xD7 0x03A7 # GREEK CAPITAL LETTER CHI +0xD8 0x03A8 # GREEK CAPITAL LETTER PSI +0xD9 0x03A9 # GREEK CAPITAL LETTER OMEGA +0xDA 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +0xDB 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +0xDC 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS +0xDD 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS +0xDE 0x03AE # GREEK SMALL LETTER ETA WITH TONOS +0xDF 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS +0xE0 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +0xE1 0x03B1 # GREEK SMALL LETTER ALPHA +0xE2 0x03B2 # GREEK SMALL LETTER BETA +0xE3 0x03B3 # GREEK SMALL LETTER GAMMA +0xE4 0x03B4 # GREEK SMALL LETTER DELTA +0xE5 0x03B5 # GREEK SMALL LETTER EPSILON +0xE6 0x03B6 # GREEK SMALL LETTER ZETA +0xE7 0x03B7 # GREEK SMALL LETTER ETA +0xE8 0x03B8 # GREEK SMALL LETTER THETA +0xE9 0x03B9 # GREEK SMALL LETTER IOTA +0xEA 0x03BA # GREEK SMALL LETTER KAPPA +0xEB 0x03BB # GREEK SMALL LETTER LAMDA +0xEC 0x03BC # GREEK SMALL LETTER MU +0xED 0x03BD # GREEK SMALL LETTER NU +0xEE 0x03BE # GREEK SMALL LETTER XI +0xEF 0x03BF # GREEK SMALL LETTER OMICRON +0xF0 0x03C0 # GREEK SMALL LETTER PI +0xF1 0x03C1 # GREEK SMALL LETTER RHO +0xF2 0x03C2 # GREEK SMALL LETTER FINAL SIGMA +0xF3 0x03C3 # GREEK SMALL LETTER SIGMA +0xF4 0x03C4 # GREEK SMALL LETTER TAU +0xF5 0x03C5 # GREEK SMALL LETTER UPSILON +0xF6 0x03C6 # GREEK SMALL LETTER PHI +0xF7 0x03C7 # GREEK SMALL LETTER CHI +0xF8 0x03C8 # GREEK SMALL LETTER PSI +0xF9 0x03C9 # GREEK SMALL LETTER OMEGA +0xFA 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA +0xFB 0x03CB # GREEK SMALL LETTER UPSILON WITH DIALYTIKA +0xFC 0x03CC # GREEK SMALL LETTER OMICRON WITH TONOS +0xFD 0x03CD # GREEK SMALL LETTER UPSILON WITH TONOS +0xFE 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS diff --git a/program/lib/encoding/ISO-8859-8.map b/program/lib/encoding/ISO-8859-8.map new file mode 100644 index 000000000..bc8da4c7f --- /dev/null +++ b/program/lib/encoding/ISO-8859-8.map @@ -0,0 +1,270 @@ +# +# Name: ISO/IEC 8859-8:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.1 +# Table format: Format A +# Date: 2000-Jan-03 +# Authors: Ken Whistler +# +# 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 +# ISO/IEC 8859-8:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-8 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-8 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# 1.1 version updates to the published 8859-8:1999, correcting +# the mapping of 0xAF and adding mappings for LRM and RLM. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00D7 # MULTIPLICATION SIGN +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00F7 # DIVISION SIGN +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC # VULGAR FRACTION ONE QUARTER +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS +0xDF 0x2017 # DOUBLE LOW LINE +0xE0 0x05D0 # HEBREW LETTER ALEF +0xE1 0x05D1 # HEBREW LETTER BET +0xE2 0x05D2 # HEBREW LETTER GIMEL +0xE3 0x05D3 # HEBREW LETTER DALET +0xE4 0x05D4 # HEBREW LETTER HE +0xE5 0x05D5 # HEBREW LETTER VAV +0xE6 0x05D6 # HEBREW LETTER ZAYIN +0xE7 0x05D7 # HEBREW LETTER HET +0xE8 0x05D8 # HEBREW LETTER TET +0xE9 0x05D9 # HEBREW LETTER YOD +0xEA 0x05DA # HEBREW LETTER FINAL KAF +0xEB 0x05DB # HEBREW LETTER KAF +0xEC 0x05DC # HEBREW LETTER LAMED +0xED 0x05DD # HEBREW LETTER FINAL MEM +0xEE 0x05DE # HEBREW LETTER MEM +0xEF 0x05DF # HEBREW LETTER FINAL NUN +0xF0 0x05E0 # HEBREW LETTER NUN +0xF1 0x05E1 # HEBREW LETTER SAMEKH +0xF2 0x05E2 # HEBREW LETTER AYIN +0xF3 0x05E3 # HEBREW LETTER FINAL PE +0xF4 0x05E4 # HEBREW LETTER PE +0xF5 0x05E5 # HEBREW LETTER FINAL TSADI +0xF6 0x05E6 # HEBREW LETTER TSADI +0xF7 0x05E7 # HEBREW LETTER QOF +0xF8 0x05E8 # HEBREW LETTER RESH +0xF9 0x05E9 # HEBREW LETTER SHIN +0xFA 0x05EA # HEBREW LETTER TAV +0xFD 0x200E # LEFT-TO-RIGHT MARK +0xFE 0x200F # RIGHT-TO-LEFT MARK + diff --git a/program/lib/encoding/ISO-8859-9.map b/program/lib/encoding/ISO-8859-9.map new file mode 100644 index 000000000..22901f107 --- /dev/null +++ b/program/lib/encoding/ISO-8859-9.map @@ -0,0 +1,307 @@ +# +# Name: ISO/IEC 8859-9:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 +# Table format: Format A +# Date: 1999 July 27 +# Authors: Ken Whistler +# +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on magnetic media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# ISO/IEC 8859-9:1999 characters map into Unicode. +# +# Format: Three tab-separated columns +# Column #1 is the ISO/IEC 8859-9 code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in ISO/IEC 8859-9 order. +# +# ISO/IEC 8859-9 is also equivalent to ISO-IR-148. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact +# Please note that 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 # +0x81 0x0081 # +0x82 0x0082 # +0x83 0x0083 # +0x84 0x0084 # +0x85 0x0085 # +0x86 0x0086 # +0x87 0x0087 # +0x88 0x0088 # +0x89 0x0089 # +0x8A 0x008A # +0x8B 0x008B # +0x8C 0x008C # +0x8D 0x008D # +0x8E 0x008E # +0x8F 0x008F # +0x90 0x0090 # +0x91 0x0091 # +0x92 0x0092 # +0x93 0x0093 # +0x94 0x0094 # +0x95 0x0095 # +0x96 0x0096 # +0x97 0x0097 # +0x98 0x0098 # +0x99 0x0099 # +0x9A 0x009A # +0x9B 0x009B # +0x9C 0x009C # +0x9D 0x009D # +0x9E 0x009E # +0x9F 0x009F # +0xA0 0x00A0 # NO-BREAK SPACE +0xA1 0x00A1 # INVERTED EXCLAMATION MARK +0xA2 0x00A2 # CENT SIGN +0xA3 0x00A3 # POUND SIGN +0xA4 0x00A4 # CURRENCY SIGN +0xA5 0x00A5 # YEN SIGN +0xA6 0x00A6 # BROKEN BAR +0xA7 0x00A7 # SECTION SIGN +0xA8 0x00A8 # DIAERESIS +0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x00AA # FEMININE ORDINAL INDICATOR +0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xAC 0x00AC # NOT SIGN +0xAD 0x00AD # SOFT HYPHEN +0xAE 0x00AE # REGISTERED SIGN +0xAF 0x00AF # MACRON +0xB0 0x00B0 # DEGREE SIGN +0xB1 0x00B1 # PLUS-MINUS SIGN +0xB2 0x00B2 # SUPERSCRIPT TWO +0xB3 0x00B3 # SUPERSCRIPT THREE +0xB4 0x00B4 # ACUTE ACCENT +0xB5 0x00B5 # MICRO SIGN +0xB6 0x00B6 # PILCROW SIGN +0xB7 0x00B7 # MIDDLE DOT +0xB8 0x00B8 # CEDILLA +0xB9 0x00B9 # SUPERSCRIPT ONE +0xBA 0x00BA # MASCULINE ORDINAL INDICATOR +0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xBC 0x00BC # VULGAR FRACTION ONE QUARTER +0xBD 0x00BD # VULGAR FRACTION ONE HALF +0xBE 0x00BE # VULGAR FRACTION THREE QUARTERS +0xBF 0x00BF # INVERTED QUESTION MARK +0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xC3 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0xC5 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0xC6 0x00C6 # LATIN CAPITAL LETTER AE +0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0xC8 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0xCA 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xCC 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xCF 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xD0 0x011E # LATIN CAPITAL LETTER G WITH BREVE +0xD1 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE +0xD2 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xD5 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0xD7 0x00D7 # MULTIPLICATION SIGN +0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xD9 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xDB 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0xDD 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE +0xDE 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA +0xDF 0x00DF # LATIN SMALL LETTER SHARP S +0xE0 0x00E0 # LATIN SMALL LETTER A WITH GRAVE +0xE1 0x00E1 # LATIN SMALL LETTER A WITH ACUTE +0xE2 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0xE3 0x00E3 # LATIN SMALL LETTER A WITH TILDE +0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0xE5 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0xE6 0x00E6 # LATIN SMALL LETTER AE +0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA +0xE8 0x00E8 # LATIN SMALL LETTER E WITH GRAVE +0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE +0xEA 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS +0xEC 0x00EC # LATIN SMALL LETTER I WITH GRAVE +0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE +0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0xEF 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS +0xF0 0x011F # LATIN SMALL LETTER G WITH BREVE +0xF1 0x00F1 # LATIN SMALL LETTER N WITH TILDE +0xF2 0x00F2 # LATIN SMALL LETTER O WITH GRAVE +0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE +0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0xF5 0x00F5 # LATIN SMALL LETTER O WITH TILDE +0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0xF7 0x00F7 # DIVISION SIGN +0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE +0xF9 0x00F9 # LATIN SMALL LETTER U WITH GRAVE +0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE +0xFB 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xFD 0x0131 # LATIN SMALL LETTER DOTLESS I +0xFE 0x015F # LATIN SMALL LETTER S WITH CEDILLA +0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS + + diff --git a/program/lib/utf8.class.php b/program/lib/utf8.class.php new file mode 100644 index 000000000..57126a78a --- /dev/null +++ b/program/lib/utf8.class.php @@ -0,0 +1,173 @@ +loadCharset(CP1252); + Then call + $res = $utfConverter->strToUtf8($str); + or + $res = $utfConverter->utf8ToStr($utf); + to get the needed encoding. +--------------------------------------------------------------------------------- +Note: + Rewrite or Override the onError method if needed. It's the error handler used from everywhere and takes 2 parameters: + err_code and err_text. By default it just prints out a message about the error. +*/ + +// Charset maps +// Adapted to fit RoundCube +define("UTF8_MAP_DIR", "program/lib/encoding"); +$utf8_maps = array( + "CP1250" => UTF8_MAP_DIR . "/CP1250.map", + "CP1251" => UTF8_MAP_DIR . "/CP1251.map", + "CP1252" => UTF8_MAP_DIR . "/CP1252.map", + "CP1253" => UTF8_MAP_DIR . "/CP1253.map", + "CP1254" => UTF8_MAP_DIR . "/CP1254.map", + "CP1255" => UTF8_MAP_DIR . "/CP1255.map", + "CP1256" => UTF8_MAP_DIR . "/CP1256.map", + "CP1257" => UTF8_MAP_DIR . "/CP1257.map", + "CP1258" => UTF8_MAP_DIR . "/CP1258.map", + "ISO-8859-1" => UTF8_MAP_DIR . "/ISO-8859-1.map", + "ISO-8859-2" => UTF8_MAP_DIR . "/ISO-8859-2.map", + "ISO-8859-3" => UTF8_MAP_DIR . "/ISO-8859-3.map", + "ISO-8859-4" => UTF8_MAP_DIR . "/ISO-8859-4.map"); + +//Error constants +define("ERR_OPEN_MAP_FILE","ERR_OPEN_MAP_FILE"); + +//Class definition +Class utf8{ + + var $charset = CP1250; + var $ascMap = array(); + var $utfMap = array(); + + // made PHP5 capable by RoundCube + function __construct($charset="ISO-8859-1"){ + $this->loadCharset($charset); + } + + //Constructor + function utf8($charset="ISO-8859-1"){ + $this->__construct($charset); + } + + //Load charset + function loadCharset($charset){ + global $utf8_maps; + + if (!is_file($utf8_maps[$charset])) + { + $this->onError(ERR_OPEN_MAP_FILE, "Failed to open map file for $charset"); + return; + } + + if (empty($this->ascMap[$charset])) + { + $lines = file_get_contents($utf8_maps[$charset]); + $lines = preg_replace("/#.*$/m","",$lines); + $lines = preg_replace("/\n\n/","",$lines); + $lines = explode("\n",$lines); + foreach($lines as $line){ + $parts = explode('0x',$line); + if(count($parts)==3){ + $asc=hexdec(substr($parts[1],0,2)); + $utf=hexdec(substr($parts[2],0,4)); + $this->ascMap[$charset][$asc]=$utf; + } + } + } + + $this->charset = $charset; + $this->utfMap = array_flip($this->ascMap[$charset]); + } + + //Error handler + function onError($err_code,$err_text){ + //print($err_code . " : " . $err_text . "
\n"); + raise_error(array('code' => 500, + 'file' => __FILE__, + 'message' => $err_text), TRUE, FALSE); + } + + //Translate string ($str) to UTF-8 from given charset + function strToUtf8($str){ + $chars = unpack('C*', $str); + $cnt = count($chars); + for($i=1;$i<=$cnt;$i++) $this->_charToUtf8($chars[$i]); + return implode("",$chars); + } + + //Translate UTF-8 string to single byte string in the given charset + function utf8ToStr($utf){ + $chars = unpack('C*', $utf); + $cnt = count($chars); + $res = ""; //No simple way to do it in place... concatenate char by char + for ($i=1;$i<=$cnt;$i++){ + $res .= $this->_utf8ToChar($chars, $i); + } + return $res; + } + + //Char to UTF-8 sequence + function _charToUtf8(&$char){ + $c = (int)$this->ascMap[$this->charset][$char]; + if ($c < 0x80){ + $char = chr($c); + } + else if($c<0x800) // 2 bytes + $char = (chr(0xC0 | $c>>6) . chr(0x80 | $c & 0x3F)); + else if($c<0x10000) // 3 bytes + $char = (chr(0xE0 | $c>>12) . chr(0x80 | $c>>6 & 0x3F) . chr(0x80 | $c & 0x3F)); + else if($c<0x200000) // 4 bytes + $char = (chr(0xF0 | $c>>18) . chr(0x80 | $c>>12 & 0x3F) . chr(0x80 | $c>>6 & 0x3F) . chr(0x80 | $c & 0x3F)); + } + + //UTF-8 sequence to single byte character + function _utf8ToChar(&$chars, &$idx){ + if(($chars[$idx] >= 240) && ($chars[$idx] <= 255)){ // 4 bytes + $utf = (intval($chars[$idx]-240) << 18) + + (intval($chars[++$idx]-128) << 12) + + (intval($chars[++$idx]-128) << 6) + + (intval($chars[++$idx]-128) << 0); + } + else if (($chars[$idx] >= 224) && ($chars[$idx] <= 239)){ // 3 bytes + $utf = (intval($chars[$idx]-224) << 12) + + (intval($chars[++$idx]-128) << 6) + + (intval($chars[++$idx]-128) << 0); + } + else if (($chars[$idx] >= 192) && ($chars[$idx] <= 223)){ // 2 bytes + $utf = (intval($chars[$idx]-192) << 6) + + (intval($chars[++$idx]-128) << 0); + } + else{ // 1 byte + $utf = $chars[$idx]; + } + if(array_key_exists($utf,$this->utfMap)) + return chr($this->utfMap[$utf]); + else + return "?"; + } + +} +?> diff --git a/program/lib/utf8.inc b/program/lib/utf8.inc deleted file mode 100644 index 43ecb328b..000000000 --- a/program/lib/utf8.inc +++ /dev/null @@ -1,104 +0,0 @@ - -// -// Description: -// UTF-8 handling functions -// -// This file is part of IlohaMail. IlohaMail is free software released -// under the GPL license. See enclosed file COPYING for details, or -// see http://www.fsf.org/copyleft/gpl.html -//////////////////////////// - -/** -* takes a string of utf-8 encoded characters and converts it to a string of unicode entities -* each unicode entitiy has the form &#nnnnn; n={0..9} and can be displayed by utf-8 supporting -* browsers -* @param $source string encoded using utf-8 [STRING] -* @return string of unicode entities [STRING] -* @access public -*/ -/** -* Author: ronen at greyzone dot com -* Taken from php.net comment: -* http://www.php.net/manual/en/function.utf8-decode.php -**/ -function utf8ToUnicodeEntities ($source) { - // array used to figure what number to decrement from character order value - // according to number of characters used to map unicode to ascii by utf-8 - $decrement[4] = 240; - $decrement[3] = 224; - $decrement[2] = 192; - $decrement[1] = 0; - - // the number of bits to shift each charNum by - $shift[1][0] = 0; - $shift[2][0] = 6; - $shift[2][1] = 0; - $shift[3][0] = 12; - $shift[3][1] = 6; - $shift[3][2] = 0; - $shift[4][0] = 18; - $shift[4][1] = 12; - $shift[4][2] = 6; - $shift[4][3] = 0; - - $pos = 0; - $len = strlen ($source); - $encodedString = ''; - while ($pos < $len) { - $asciiPos = ord (substr ($source, $pos, 1)); - if (($asciiPos >= 240) && ($asciiPos <= 255)) { - // 4 chars representing one unicode character - $thisLetter = substr ($source, $pos, 4); - $pos += 4; - } - else if (($asciiPos >= 224) && ($asciiPos <= 239)) { - // 3 chars representing one unicode character - $thisLetter = substr ($source, $pos, 3); - $pos += 3; - } - else if (($asciiPos >= 192) && ($asciiPos <= 223)) { - // 2 chars representing one unicode character - $thisLetter = substr ($source, $pos, 2); - $pos += 2; - } - else { - // 1 char (lower ascii) - $thisLetter = substr ($source, $pos, 1); - $pos += 1; - } - - // process the string representing the letter to a unicode entity - $thisLen = strlen ($thisLetter); - $thisPos = 0; - $decimalCode = 0; - while ($thisPos < $thisLen) { - $thisCharOrd = ord (substr ($thisLetter, $thisPos, 1)); - if ($thisPos == 0) { - $charNum = intval ($thisCharOrd - $decrement[$thisLen]); - $decimalCode += ($charNum << $shift[$thisLen][$thisPos]); - } - else { - $charNum = intval ($thisCharOrd - 128); - $decimalCode += ($charNum << $shift[$thisLen][$thisPos]); - } - - $thisPos++; - } - - if ($decimalCode<128) - $encodedLetter = chr($decimalCode); - else if ($thisLen == 1) - $encodedLetter = "&#". str_pad($decimalCode, 3, "0", STR_PAD_LEFT) . ';'; - else - $encodedLetter = "&#". str_pad($decimalCode, 5, "0", STR_PAD_LEFT) . ';'; - - $encodedString .= $encodedLetter; - } - - return $encodedString; -} - -?> \ No newline at end of file -- cgit v1.2.3