lib/typo3/unidata/Translit.txt

   1
   2 # Latin (iso-8859-1)
   3
   4 00A5; 0079 0065 006E;   YEN SIGN => yen
   5 00A6; 007C;             BROKEN BAR => |
   6 00AB; 003C 003C;        LEFT-POINTING DOUBLE ANGLE QUOTATION MARK => <<
   7 00A9; 0028 0063 0029;   COPYRIGHT SIGN => (c)
   8 00AE; 0028 0052 0029;   REGISTERED SIGN => (R)
   9 00B1; 002B 002F 002D;   PLUS-MINUS SIGN => +/-
  10 00B5; 0075;             MICRO SIGN => u (American style)
  11 00B7; 002A;             MIDDLE DOT => *
  12 00BB; 003E 003E;        RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK => <<
  13 00C4; 0041 0045;        LATIN CAPITAL LETTER A WITH DIAERESIS => AE (German)
  14 00C5; 0041 0041;        LATIN CAPITAL LETTER A WITH RING ABOVE => AA (Danish)
  15 00C6; 0041 0045;        LATIN CAPITAL LETTER AE => AE (Danish)
  16 00D6; 004F 0045;        LATIN CAPITAL LETTER O WITH DIAERESIS => OE (German)
  17 00D7; 0078;             MULTIPLICATION SIGN => x
  18 00D8; 004F 0045;        LATIN CAPITAL LETTER O WITH STROKE => OE (Danish)
  19 00DC; 0055 0045;        LATIN CAPITAL LETTER U WITH DIAERESIS => UE (German)
  20 00E4; 0061 0065;        LATIN SMALL LETTER A WITH DIAERESIS => ae (German)
  21 00E5; 0061 0061;        LATIN SMALL LETTER A WITH RING ABOVE => aa (Danish)
  22 00DF; 0073 0073;        LATIN SMALL LETTER SHARP S => ss (German)
  23 00E6; 0061 0065;        LATIN SMALL LETTER AE => ae (Danish)
  24 00F6; 006F 0065;        LATIN SMALL LETTER O WITH DIAERESIS => oe (German)
  25 00F7; 002F;             DIVISION SIGN => /
  26 00F8; 006F 0065;        LATIN SMALL LETTER O WITH STROKE => oe (Danish)
  27 00FC; 0075 0065;        LATIN SMALL LETTER U WITH DIAERESIS => ue (German)
  28
  29 # more Latin (windows-1252, windows-1254, windows-1257)
  30
  31 0100; 0041 0041;        LATIN CAPITAL LETTER A WITH MACRON => AA (Latvian)
  32 0101; 0061 0061;        LATIN SMALL LETTER A WITH MACRON => aa (Latvian)
  33 0112; 0045 0045;        LATIN CAPITAL LETTER E WITH MACRON => EE (Latvian)
  34 0113; 0065 0065;        LATIN SMALL LETTER E WITH MACRON => ee (Latvian)
  35 012A; 0049 0049;        LATIN CAPITAL LETTER I WITH MACRON => II (Latvian)
  36 012B; 0060 0069;        LATIN SMALL LETTER I WITH MACRON => ii(Latvian)
  37 014C; 004F 004F;        LATIN CAPITAL LETTER O WITH MACRON => OO
  38 014D; 006F 006F;        LATIN SMALL LETTER O WITH MACRON => oo
  39 016A; 0055 0055;        LATIN CAPITAL LETTER U WITH MACRON => UU (Latvian)
  40 016B; 0075 0075;        LATIN SMALL LETTER U WITH MACRON => uu (Latvian)
  41 0131; 0069;             LATIN SMALL LETTER DOTLESS I => i (Turkish)
  42 0152; 004F 0045;        LATIN CAPITAL LETTER OE => OE
  43 0153; 006F 0065;        LATIN SMALL LETTER OE => oe
  44 0192; 0066;             LATIN SMALL LETTER F WITH HOOK => f
  45 02BC; 0027;             MODIFIER LETTER APOSTROPHE => '
  46 02CA; 0027;             MODIFIER LETTER ACUTE ACCENT => '
  47 2010; 002D;             HYPHEN => -
  48 2013; 002D;             EN DASH => -
  49 2014; 002D;             EM DASH => -
  50 2018; 0060;             LEFT SINGLE QUOTATION MARK => `
  51 2019; 0027;             RIGHT SINGLE QUOTATION MARK >= '
  52 201C; 0022;             LEFT DOUBLE QUOTATION MARK => "
  53 201D; 0022;             RIGHT DOUBLE QUOTATION MARK => "
  54 201E; 0022;             DOUBLE LOW-9 QUOTATION MARK => "
  55 2022; 002A;             BULLET => *
  56 2039; 003C;             SINGLE LEFT-POINTING ANGLE QUOTATION MARK => <
  57 203A; 003E;             SINGLE RIGHT-POINTING ANGLE QUOTATION MARK => >
  58 2044; 002F;             FRACTION SLASH => /
  59 20A0; 0045 0055 0052;   EURO-CURRENCY SIGN => EUR
  60 20AC; 0045 0055 0052;   EURO-CURRENCY SIGN => EUR
  61
  62 # Cyrillic (Russian transliteration: modified GOST)
  63
  64 0401; 004A 004F;                CYRILLIC CAPITAL LETTER IO => JO
  65 #0402; ;                        CYRILLIC CAPITAL LETTER DJE
  66 #0403; ;                        CYRILLIC CAPITAL LETTER GJE
  67 0404; 004A 0045;                CYRILLIC CAPITAL LETTER UKRAINIAN IE => JE
  68 #0405; ;                        CYRILLIC CAPITAL LETTER DZE
  69 0406; 0049;                     CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I => I
  70 0407; 0049;                     CYRILLIC CAPITAL LETTER YI => I
  71 #0408; ;                        CYRILLIC CAPITAL LETTER JE ?? J
  72 #0409; ;                        CYRILLIC CAPITAL LETTER LJE ?? LJ
  73 #040A; ;                        CYRILLIC CAPITAL LETTER NJE ??  NJ
  74 #040B; ;                        CYRILLIC CAPITAL LETTER TSHE ?? TSH
  75 #040C; ;                        CYRILLIC CAPITAL LETTER KJE ?? KJ KY
  76 040E; 0055;                     CYRILLIC CAPITAL LETTER SHORT U => U (Belorussian)
  77 #040F; ;                        CYRILLIC CAPITAL LETTER DZHE ?? DZH
  78 0410; 0041;                     CYRILLIC CAPITAL LETTER A => A
  79 0411; 0042;                     CYRILLIC CAPITAL LETTER BE => B
  80 0412; 0056;                     CYRILLIC CAPITAL LETTER VE => V
  81 0413; 0047;                     CYRILLIC CAPITAL LETTER GHE => G
  82 0414; 0044;                     CYRILLIC CAPITAL LETTER DE => D
  83 0415; 0045;                     CYRILLIC CAPITAL LETTER IE => E
  84 0416; 005A 0048;                CYRILLIC CAPITAL LETTER ZHE => ZH
  85 0417; 005A;                     CYRILLIC CAPITAL LETTER ZE => Z
  86 0418; 0049;                     CYRILLIC CAPITAL LETTER I=> I
  87 0419; 0049;                     CYRILLIC CAPITAL LETTER SHORT I => I (GOST has I)
  88 041A; 004B;                     CYRILLIC CAPITAL LETTER KA => K
  89 041B; 004C;                     CYRILLIC CAPITAL LETTER EL => L
  90 041C; 004D;                     CYRILLIC CAPITAL LETTER EM => M
  91 041D; 004E;                     CYRILLIC CAPITAL LETTER EN => N
  92 041E; 004F;                     CYRILLIC CAPITAL LETTER O => O
  93 041F; 0050;                     CYRILLIC CAPITAL LETTER PE => P
  94 0420; 0052;                     CYRILLIC CAPITAL LETTER ER => R
  95 0421; 0053;                     CYRILLIC CAPITAL LETTER ES => S
  96 0422; 0054;                     CYRILLIC CAPITAL LETTER TE => T
  97 0423; 0055;                     CYRILLIC CAPITAL LETTER U => U
  98 0424; 0046;                     CYRILLIC CAPITAL LETTER EF => F
  99 0425; 004B 0048;                CYRILLIC CAPITAL LETTER HA => KH
 100 0426; 0043;                     CYRILLIC CAPITAL LETTER TSE => C
 101 0427; 0043 0048;                CYRILLIC CAPITAL LETTER CHE => CH
 102 0428; 0053 0048;                CYRILLIC CAPITAL LETTER SHA => SH
 103 0429; 0053 0048 0043 0048;      CYRILLIC CAPITAL LETTER SHCHA => SHCH (GOST has SHH)
 104 042A; ;                         CYRILLIC CAPITAL LETTER HARD SIGN => omit (GOST has ")
 105 042B; 0059;                     CYRILLIC CAPITAL LETTER YERU => Y
 106 042C; ;                         CYRILLIC CAPITAL LETTER SOFT SIGN => omit (GOST has ')
 107 042D; 0045 0048;                CYRILLIC CAPITAL LETTER E => EH
 108 042E; 004A 0055;                CYRILLIC CAPITAL LETTER YU => JU
 109 042F; 004A 0041;                CYRILLIC CAPITAL LETTER YA => JA
 110
 111 0430; 0061;                     CYRILLIC SMALL LETTER A => a
 112 0431; 0062;                     CYRILLIC SMALL LETTER BE => b
 113 0432; 0076;                     CYRILLIC SMALL LETTER VE => v
 114 0433; 0067;                     CYRILLIC SMALL LETTER GHE => g
 115 0434; 0064;                     CYRILLIC SMALL LETTER DE => d
 116 0435; 0065;                     CYRILLIC SMALL LETTER IE => e
 117 0436; 007A 0068;                CYRILLIC SMALL LETTER ZHE => zh
 118 0437; 007A;                     CYRILLIC SMALL LETTER ZE => z
 119 0438; 0069;                     CYRILLIC SMALL LETTER I => i
 120 0439; 0069;                     CYRILLIC SMALL LETTER SHORT I => i (GOST has j)
 121 043A; 006B;                     CYRILLIC SMALL LETTER KA => k
 122 043B; 006C;                     CYRILLIC SMALL LETTER EL => l
 123 043C; 006D;                     CYRILLIC SMALL LETTER EM => m
 124 043D; 006E;                     CYRILLIC SMALL LETTER EN => n
 125 043E; 006F;                     CYRILLIC SMALL LETTER O => o
 126 043F; 0070;                     CYRILLIC SMALL LETTER PE => p
 127 0440; 0072;                     CYRILLIC SMALL LETTER ER => r
 128 0441; 0073;                     CYRILLIC SMALL LETTER ES => s
 129 0442; 0074;                     CYRILLIC SMALL LETTER TE => t
 130 0443; 0075;                     CYRILLIC SMALL LETTER U => u
 131 0444; 0066;                     CYRILLIC SMALL LETTER EF => f
 132 0445; 006B 0068;                CYRILLIC SMALL LETTER HA => kh
 133 0446; 0063;                     CYRILLIC SMALL LETTER TSE => c
 134 0447; 0063 0068;                CYRILLIC SMALL LETTER CHE => ch
 135 0448; 0073 0068;                CYRILLIC SMALL LETTER SHA => sh
 136 0449; 0073 0068 0063 0068;      CYRILLIC SMALL LETTER SHCHA => shch (GOST has shh)
 137 044A; ;                         CYRILLIC SMALL LETTER HARD SIGN => omit (GOST has ")
 138 044B; 0079;                     CYRILLIC SMALL LETTER YERU => y
 139 044C; ;                         CYRILLIC SMALL LETTER SOFT SIGN => omit (GOST has ')
 140 044D; 0065 0068;                CYRILLIC SMALL LETTER E => eh
 141 044E; 006A 0075;                CYRILLIC SMALL LETTER YU => ju
 142 044F; 006A 0061;                CYRILLIC SMALL LETTER YA => ja
 143 0451; 006A 006F;                CYRILLIC SMALL LETTER IO => jo
 144 #0452; ;                        CYRILLIC SMALL LETTER DJE => dj dy ??
 145 #0453; ;                        CYRILLIC SMALL LETTER GJE => gj gy ??
 146 0454; 006A 0065;                CYRILLIC SMALL LETTER UKRAINIAN IE => je
 147 #0455; ;                        CYRILLIC SMALL LETTER DZE => dz ??
 148 0456; 0069;                     CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I => i
 149 0457; 006A 0069;                CYRILLIC SMALL LETTER YI => ji
 150 #0458; ;                        CYRILLIC SMALL LETTER JE ?? j y
 151 #0459; ;                        CYRILLIC SMALL LETTER LJE ?? lj ly
 152 #045A; ;                        CYRILLIC SMALL LETTER NJE ?? nj ny
 153 #045B; ;                        CYRILLIC SMALL LETTER TSHE => ??? tsh ch (Serbocroatian)
 154 #045C; ;                        CYRILLIC SMALL LETTER KJE
 155 045E; 0075;                     CYRILLIC SMALL LETTER SHORT U => U (Belorussian)
 156 #045F; ;                        CYRILLIC SMALL LETTER DZHE ???
 157
 158 0490; 0047 0047;                CYRILLIC CAPITAL LETTER GHE WITH UPTURN => GG (Belorussian, Ukrainian)
 159 0491; 0067 0076;                CYRILLIC SMALL LETTER GHE WITH UPTURN => gg (Belorussian, Ukrainian)
 160
 161 # Hebrew
 162
 163 #05B0; ;                HEBREW POINT SHEVA ??? win1255
 164 #05B1; ;                HEBREW POINT HATAF SEGOL ??? win1255
 165 #05B2; ;                HEBREW POINT HATAF PATAH ??? win1255
 166 #05B3; ;                HEBREW POINT HATAF QAMATS ??? win1255
 167 #05B4; ;                HEBREW POINT HIRIQ ??? win1255
 168 #05B5; ;                HEBREW POINT TSERE ??? win1255
 169 #05B6; ;                HEBREW POINT SEGOL ??? win1255
 170 #05B7; ;                HEBREW POINT PATAH ??? win1255
 171 #05B8; ;                HEBREW POINT QAMATS ??? win1255
 172 #05B9; ;                HEBREW POINT HOLAM ??? win1255
 173 #05BB; ;                HEBREW POINT QUBUTS ??? win1255
 174 #05BC; ;                HEBREW POINT DAGESH OR MAPIQ ??? win1255
 175 #05BD; ;                HEBREW POINT METEG ??? win1255
 176 #05BE; ;                HEBREW PUNCTUATION MAQAF ??? win1255
 177 #05BF; ;                HEBREW POINT RAFE ??? win1255
 178 #05C0; ;                HEBREW PUNCTUATION PASEQ ??? win1255
 179 #05C1; ;                HEBREW POINT SHIN DOT ??? win1255
 180 #05C2; ;                HEBREW POINT SIN DOT ??? win1255
 181 05D0; 0041;             HEBREW LETTER ALEF => A
 182 05D1; 0042;             HEBREW LETTER BET => B
 183 05D2; 0047;             HEBREW LETTER GIMEL => G
 184 05D3; 0044;             HEBREW LETTER DALET => D
 185 05D4; 0048 0061;        HEBREW LETTER HE => Ha
 186 05D5; 004F;             HEBREW LETTER VAV => O
 187 05D6; 005A;             HEBREW LETTER ZAYIN => Z
 188 05D7; 0048;             HEBREW LETTER HET => H
 189 05D8; 0054;             HEBREW LETTER TET => T
 190 05D9; 0049;             HEBREW LETTER YOD => I
 191 05DA; 004B 0068;        HEBREW LETTER FINAL KAF => Kh
 192 05DB; 004B 0068;        HEBREW LETTER KAF => Kh
 193 05DC; 004C;             HEBREW LETTER LAMED => L
 194 05DD; 004D;             HEBREW LETTER FINAL MEM => M
 195 05DE; 004D;             HEBREW LETTER MEM => M
 196 05DF; 004E;             HEBREW LETTER FINAL NUN => N
 197 05E0; 004E;             HEBREW LETTER NUN => N
 198 05E1; 0053;             HEBREW LETTER SAMEKH => S
 199 05E2; 0041;             HEBREW LETTER AYIN => A
 200 05E3; 0050 0066;        HEBREW LETTER FINAL PE => Pf
 201 05E4; 0050 0066;        HEBREW LETTER PE => Pf
 202 05E5; 0054 0073;        HEBREW LETTER FINAL TSADI => Ts
 203 05E6; 0054 0073;        HEBREW LETTER TSADI => Ts
 204 05E7; 004B;             HEBREW LETTER QOF => K
 205 05E8; 0052;             HEBREW LETTER RESH => R
 206 05E9; 0053 0068;        HEBREW LETTER SHIN => Sh
 207 05EA; 0054;             HEBREW LETTER TAV => T
 208 05F0; 0056;             HEBREW LIGATURE YIDDISH DOUBLE VAV => V
 209 #05F1; ;                HEBREW LIGATURE YIDDISH VAV YOD ??? win1255
 210 #05F2; ;                HEBREW LIGATURE YIDDISH DOUBLE YOD ??? win1255
 211 #05F3; ;                HEBREW PUNCTUATION GERESH ??? win1255
 212 #05F4; ;                HEBREW PUNCTUATION GERSHAYIM ??? win1255
 213
 214 #20AA; ;                NEW SHEQEL SIGN ??? win1255
 215