* Merging all changes from TYPO3_4-0 branch back into HEAD
[Packages/TYPO3.CMS.git] / t3lib / 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 # Uncomment the following 8 lines if you want to double Latvian "long" letters
32 # in URLs (non-typical but worked this way prior to TYPO3 4.0)
33 #0100; 0041 0041;       LATIN CAPITAL LETTER A WITH MACRON => AA (Latvian)
34 #0101; 0061 0061;       LATIN SMALL LETTER A WITH MACRON => aa (Latvian)
35 #0112; 0045 0045;       LATIN CAPITAL LETTER E WITH MACRON => EE (Latvian)
36 #0113; 0065 0065;       LATIN SMALL LETTER E WITH MACRON => ee (Latvian)
37 #012A; 0049 0049;       LATIN CAPITAL LETTER I WITH MACRON => II (Latvian)
38 #012B; 0060 0069;       LATIN SMALL LETTER I WITH MACRON => ii(Latvian)
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
42 014C; 004F 004F;        LATIN CAPITAL LETTER O WITH MACRON => OO
43 014D; 006F 006F;        LATIN SMALL LETTER O WITH MACRON => oo
44 0131; 0069;             LATIN SMALL LETTER DOTLESS I => i (Turkish)
45 0152; 004F 0045;        LATIN CAPITAL LETTER OE => OE
46 0153; 006F 0065;        LATIN SMALL LETTER OE => oe
47 0192; 0066;             LATIN SMALL LETTER F WITH HOOK => f
48 02BC; 0027;             MODIFIER LETTER APOSTROPHE => '
49 02CA; 0027;             MODIFIER LETTER ACUTE ACCENT => '
50 2010; 002D;             HYPHEN => -
51 2013; 002D;             EN DASH => -
52 2014; 002D;             EM DASH => -
53 2018; 0060;             LEFT SINGLE QUOTATION MARK => `
54 2019; 0027;             RIGHT SINGLE QUOTATION MARK >= '
55 201C; 0022;             LEFT DOUBLE QUOTATION MARK => "
56 201D; 0022;             RIGHT DOUBLE QUOTATION MARK => "
57 201E; 0022;             DOUBLE LOW-9 QUOTATION MARK => "
58 2022; 002A;             BULLET => *
59 2039; 003C;             SINGLE LEFT-POINTING ANGLE QUOTATION MARK => <
60 203A; 003E;             SINGLE RIGHT-POINTING ANGLE QUOTATION MARK => >
61 2044; 002F;             FRACTION SLASH => /
62 20A0; 0045 0055 0052;   EURO-CURRENCY SIGN => EUR
63 20AC; 0045 0055 0052;   EURO-CURRENCY SIGN => EUR
64
65 # Cyrillic (Russian transliteration: modified GOST)
66
67 0401; 004A 004F;                CYRILLIC CAPITAL LETTER IO => JO
68 #0402; ;                        CYRILLIC CAPITAL LETTER DJE
69 #0403; ;                        CYRILLIC CAPITAL LETTER GJE
70 0404; 004A 0045;                CYRILLIC CAPITAL LETTER UKRAINIAN IE => JE
71 #0405; ;                        CYRILLIC CAPITAL LETTER DZE
72 0406; 0049;                     CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I => I
73 0407; 0049;                     CYRILLIC CAPITAL LETTER YI => I
74 #0408; ;                        CYRILLIC CAPITAL LETTER JE ?? J
75 #0409; ;                        CYRILLIC CAPITAL LETTER LJE ?? LJ
76 #040A; ;                        CYRILLIC CAPITAL LETTER NJE ??  NJ
77 #040B; ;                        CYRILLIC CAPITAL LETTER TSHE ?? TSH
78 #040C; ;                        CYRILLIC CAPITAL LETTER KJE ?? KJ KY
79 040E; 0055;                     CYRILLIC CAPITAL LETTER SHORT U => U (Belorussian)
80 #040F; ;                        CYRILLIC CAPITAL LETTER DZHE ?? DZH
81 0410; 0041;                     CYRILLIC CAPITAL LETTER A => A
82 0411; 0042;                     CYRILLIC CAPITAL LETTER BE => B
83 0412; 0056;                     CYRILLIC CAPITAL LETTER VE => V
84 0413; 0047;                     CYRILLIC CAPITAL LETTER GHE => G
85 0414; 0044;                     CYRILLIC CAPITAL LETTER DE => D
86 0415; 0045;                     CYRILLIC CAPITAL LETTER IE => E
87 0416; 005A 0048;                CYRILLIC CAPITAL LETTER ZHE => ZH
88 0417; 005A;                     CYRILLIC CAPITAL LETTER ZE => Z
89 0418; 0049;                     CYRILLIC CAPITAL LETTER I=> I
90 0419; 0049;                     CYRILLIC CAPITAL LETTER SHORT I => I (GOST has I)
91 041A; 004B;                     CYRILLIC CAPITAL LETTER KA => K
92 041B; 004C;                     CYRILLIC CAPITAL LETTER EL => L
93 041C; 004D;                     CYRILLIC CAPITAL LETTER EM => M
94 041D; 004E;                     CYRILLIC CAPITAL LETTER EN => N
95 041E; 004F;                     CYRILLIC CAPITAL LETTER O => O
96 041F; 0050;                     CYRILLIC CAPITAL LETTER PE => P
97 0420; 0052;                     CYRILLIC CAPITAL LETTER ER => R
98 0421; 0053;                     CYRILLIC CAPITAL LETTER ES => S
99 0422; 0054;                     CYRILLIC CAPITAL LETTER TE => T
100 0423; 0055;                     CYRILLIC CAPITAL LETTER U => U
101 0424; 0046;                     CYRILLIC CAPITAL LETTER EF => F
102 0425; 004B 0048;                CYRILLIC CAPITAL LETTER HA => KH
103 0426; 0043;                     CYRILLIC CAPITAL LETTER TSE => C
104 0427; 0043 0048;                CYRILLIC CAPITAL LETTER CHE => CH
105 0428; 0053 0048;                CYRILLIC CAPITAL LETTER SHA => SH
106 0429; 0053 0048 0043 0048;      CYRILLIC CAPITAL LETTER SHCHA => SHCH (GOST has SHH)
107 042A; ;                         CYRILLIC CAPITAL LETTER HARD SIGN => omit (GOST has ")
108 042B; 0059;                     CYRILLIC CAPITAL LETTER YERU => Y
109 042C; ;                         CYRILLIC CAPITAL LETTER SOFT SIGN => omit (GOST has ')
110 042D; 0045 0048;                CYRILLIC CAPITAL LETTER E => EH
111 042E; 004A 0055;                CYRILLIC CAPITAL LETTER YU => JU
112 042F; 004A 0041;                CYRILLIC CAPITAL LETTER YA => JA
113
114 0430; 0061;                     CYRILLIC SMALL LETTER A => a
115 0431; 0062;                     CYRILLIC SMALL LETTER BE => b
116 0432; 0076;                     CYRILLIC SMALL LETTER VE => v
117 0433; 0067;                     CYRILLIC SMALL LETTER GHE => g
118 0434; 0064;                     CYRILLIC SMALL LETTER DE => d
119 0435; 0065;                     CYRILLIC SMALL LETTER IE => e
120 0436; 007A 0068;                CYRILLIC SMALL LETTER ZHE => zh
121 0437; 007A;                     CYRILLIC SMALL LETTER ZE => z
122 0438; 0069;                     CYRILLIC SMALL LETTER I => i
123 0439; 0069;                     CYRILLIC SMALL LETTER SHORT I => i (GOST has j)
124 043A; 006B;                     CYRILLIC SMALL LETTER KA => k
125 043B; 006C;                     CYRILLIC SMALL LETTER EL => l
126 043C; 006D;                     CYRILLIC SMALL LETTER EM => m
127 043D; 006E;                     CYRILLIC SMALL LETTER EN => n
128 043E; 006F;                     CYRILLIC SMALL LETTER O => o
129 043F; 0070;                     CYRILLIC SMALL LETTER PE => p
130 0440; 0072;                     CYRILLIC SMALL LETTER ER => r
131 0441; 0073;                     CYRILLIC SMALL LETTER ES => s
132 0442; 0074;                     CYRILLIC SMALL LETTER TE => t
133 0443; 0075;                     CYRILLIC SMALL LETTER U => u
134 0444; 0066;                     CYRILLIC SMALL LETTER EF => f
135 0445; 006B 0068;                CYRILLIC SMALL LETTER HA => kh
136 0446; 0063;                     CYRILLIC SMALL LETTER TSE => c
137 0447; 0063 0068;                CYRILLIC SMALL LETTER CHE => ch
138 0448; 0073 0068;                CYRILLIC SMALL LETTER SHA => sh
139 0449; 0073 0068 0063 0068;      CYRILLIC SMALL LETTER SHCHA => shch (GOST has shh)
140 044A; ;                         CYRILLIC SMALL LETTER HARD SIGN => omit (GOST has ")
141 044B; 0079;                     CYRILLIC SMALL LETTER YERU => y
142 044C; ;                         CYRILLIC SMALL LETTER SOFT SIGN => omit (GOST has ')
143 044D; 0065 0068;                CYRILLIC SMALL LETTER E => eh
144 044E; 006A 0075;                CYRILLIC SMALL LETTER YU => ju
145 044F; 006A 0061;                CYRILLIC SMALL LETTER YA => ja
146 0451; 006A 006F;                CYRILLIC SMALL LETTER IO => jo
147 #0452; ;                        CYRILLIC SMALL LETTER DJE => dj dy ??
148 #0453; ;                        CYRILLIC SMALL LETTER GJE => gj gy ??
149 0454; 006A 0065;                CYRILLIC SMALL LETTER UKRAINIAN IE => je
150 #0455; ;                        CYRILLIC SMALL LETTER DZE => dz ??
151 0456; 0069;                     CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I => i
152 0457; 006A 0069;                CYRILLIC SMALL LETTER YI => ji
153 #0458; ;                        CYRILLIC SMALL LETTER JE ?? j y
154 #0459; ;                        CYRILLIC SMALL LETTER LJE ?? lj ly
155 #045A; ;                        CYRILLIC SMALL LETTER NJE ?? nj ny
156 #045B; ;                        CYRILLIC SMALL LETTER TSHE => ??? tsh ch (Serbocroatian)
157 #045C; ;                        CYRILLIC SMALL LETTER KJE
158 045E; 0075;                     CYRILLIC SMALL LETTER SHORT U => U (Belorussian)
159 #045F; ;                        CYRILLIC SMALL LETTER DZHE ???
160
161 0490; 0047 0047;                CYRILLIC CAPITAL LETTER GHE WITH UPTURN => GG (Belorussian, Ukrainian)
162 0491; 0067 0076;                CYRILLIC SMALL LETTER GHE WITH UPTURN => gg (Belorussian, Ukrainian)
163
164 # Hebrew
165
166 #05B0; ;                HEBREW POINT SHEVA ??? win1255
167 #05B1; ;                HEBREW POINT HATAF SEGOL ??? win1255
168 #05B2; ;                HEBREW POINT HATAF PATAH ??? win1255
169 #05B3; ;                HEBREW POINT HATAF QAMATS ??? win1255
170 #05B4; ;                HEBREW POINT HIRIQ ??? win1255
171 #05B5; ;                HEBREW POINT TSERE ??? win1255
172 #05B6; ;                HEBREW POINT SEGOL ??? win1255
173 #05B7; ;                HEBREW POINT PATAH ??? win1255
174 #05B8; ;                HEBREW POINT QAMATS ??? win1255
175 #05B9; ;                HEBREW POINT HOLAM ??? win1255
176 #05BB; ;                HEBREW POINT QUBUTS ??? win1255
177 #05BC; ;                HEBREW POINT DAGESH OR MAPIQ ??? win1255
178 #05BD; ;                HEBREW POINT METEG ??? win1255
179 #05BE; ;                HEBREW PUNCTUATION MAQAF ??? win1255
180 #05BF; ;                HEBREW POINT RAFE ??? win1255
181 #05C0; ;                HEBREW PUNCTUATION PASEQ ??? win1255
182 #05C1; ;                HEBREW POINT SHIN DOT ??? win1255
183 #05C2; ;                HEBREW POINT SIN DOT ??? win1255
184 05D0; 0041;             HEBREW LETTER ALEF => A
185 05D1; 0042;             HEBREW LETTER BET => B
186 05D2; 0047;             HEBREW LETTER GIMEL => G
187 05D3; 0044;             HEBREW LETTER DALET => D
188 05D4; 0048 0061;        HEBREW LETTER HE => Ha
189 05D5; 004F;             HEBREW LETTER VAV => O
190 05D6; 005A;             HEBREW LETTER ZAYIN => Z
191 05D7; 0048;             HEBREW LETTER HET => H
192 05D8; 0054;             HEBREW LETTER TET => T
193 05D9; 0049;             HEBREW LETTER YOD => I
194 05DA; 004B 0068;        HEBREW LETTER FINAL KAF => Kh
195 05DB; 004B 0068;        HEBREW LETTER KAF => Kh
196 05DC; 004C;             HEBREW LETTER LAMED => L
197 05DD; 004D;             HEBREW LETTER FINAL MEM => M
198 05DE; 004D;             HEBREW LETTER MEM => M
199 05DF; 004E;             HEBREW LETTER FINAL NUN => N
200 05E0; 004E;             HEBREW LETTER NUN => N
201 05E1; 0053;             HEBREW LETTER SAMEKH => S
202 05E2; 0041;             HEBREW LETTER AYIN => A
203 05E3; 0050 0066;        HEBREW LETTER FINAL PE => Pf
204 05E4; 0050 0066;        HEBREW LETTER PE => Pf
205 05E5; 0054 0073;        HEBREW LETTER FINAL TSADI => Ts
206 05E6; 0054 0073;        HEBREW LETTER TSADI => Ts
207 05E7; 004B;             HEBREW LETTER QOF => K
208 05E8; 0052;             HEBREW LETTER RESH => R
209 05E9; 0053 0068;        HEBREW LETTER SHIN => Sh
210 05EA; 0054;             HEBREW LETTER TAV => T
211 05F0; 0056;             HEBREW LIGATURE YIDDISH DOUBLE VAV => V
212 #05F1; ;                HEBREW LIGATURE YIDDISH VAV YOD ??? win1255
213 #05F2; ;                HEBREW LIGATURE YIDDISH DOUBLE YOD ??? win1255
214 #05F3; ;                HEBREW PUNCTUATION GERESH ??? win1255
215 #05F4; ;                HEBREW PUNCTUATION GERSHAYIM ??? win1255
216
217 #20AA; ;                NEW SHEQEL SIGN ??? win1255
218