icuSources/data/unidata/SpecialCasing.txt

   1 # SpecialCasing-6.0.0.txt
   2 # Date: 2010-05-18, 00:49:39 GMT [MD]
   3 #
   4 # Unicode Character Database
   5 # Copyright (c) 1991-2010 Unicode, Inc.
   6 # For terms of use, see http://www.unicode.org/terms_of_use.html
   7 # For documentation, see http://www.unicode.org/reports/tr44/
   8 #
   9 # Special Casing Properties
  10 #
  11 # This file is a supplement to the UnicodeData file.
  12 # It contains additional information about the casing of Unicode characters.
  13 # (For compatibility, the UnicodeData.txt file only contains case mappings for
  14 # characters where they are 1-1, and independent of context and language.
  15 # For more information, see the discussion of Case Mappings in the Unicode Standard.
  16 #
  17 # All code points not listed in this file that do not have a simple case mappings
  18 # in UnicodeData.txt map to themselves.
  19 # ================================================================================
  20 # Format
  21 # ================================================================================
  22 # The entries in this file are in the following machine-readable format:
  23 #
  24 # <code>; <lower> ; <title> ; <upper> ; (<condition_list> ;)? # <comment>
  25 #
  26 # <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more
  27 # than one character, they are separated by spaces. Other than as used to separate
  28 # elements, spaces are to be ignored.
  29 #
  30 # The <condition_list> is optional. Where present, it consists of one or more language IDs
  31 # or contexts, separated by spaces. In these conditions:
  32 # - A condition list overrides the normal behavior if all of the listed conditions are true.
  33 # - The context is always the context of the characters in the original string,
  34 #   NOT in the resulting string.
  35 # - Case distinctions in the condition list are not significant.
  36 # - Conditions preceded by "Not_" represent the negation of the condition.
  37 # The condition list is not represented in the UCD as a formal property.
  38 #
  39 # A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
  40 #
  41 # A context for a character C is defined by Section 3.13 Default Case
  42 # Operations, of The Unicode Standard, Version 5.0.
  43 # (This is identical to the context defined by Unicode 4.1.0,
  44 #  as specified in http://www.unicode.org/versions/Unicode4.1.0/)
  45 #
  46 # Parsers of this file must be prepared to deal with future additions to this format:
  47 #  * Additional contexts
  48 #  * Additional fields
  49 # ================================================================================
  50 # @missing 0000..10FFFF; <slc>; <stc>; <suc>
  51 # ================================================================================
  52 # Unconditional mappings
  53 # ================================================================================
  54
  55 # The German es-zed is special--the normal mapping is to SS.
  56 # Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
  57
  58 00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
  59
  60 # Preserve canonical equivalence for I with dot. Turkic is handled below.
  61
  62 0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
  63
  64 # Ligatures
  65
  66 FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
  67 FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
  68 FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
  69 FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
  70 FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
  71 FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
  72 FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
  73
  74 0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
  75 FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
  76 FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
  77 FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
  78 FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
  79 FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
  80
  81 # No corresponding uppercase precomposed character
  82
  83 0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
  84 0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
  85 03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
  86 01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
  87 1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
  88 1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
  89 1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
  90 1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
  91 1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
  92 1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
  93 1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
  94 1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
  95 1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
  96 1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
  97 1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
  98 1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
  99 1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
 100 1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
 101 1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
 102 1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
 103 1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
 104 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
 105 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
 106 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
 107 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
 108
 109 # IMPORTANT-when iota-subscript (0345) is uppercased or titlecased,
 110 #  the result will be incorrect unless the iota-subscript is moved to the end
 111 #  of any sequence of combining marks. Otherwise, the accents will go on the capital iota.
 112 #  This process can be achieved by first transforming the text to NFC before casing.
 113 #  E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA>
 114
 115 # The following cases are already in the UnicodeData file, so are only commented here.
 116
 117 # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
 118
 119 # All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
 120 # have special uppercases.
 121 # Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
 122
 123 1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
 124 1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
 125 1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
 126 1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
 127 1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
 128 1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
 129 1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
 130 1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
 131 1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
 132 1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
 133 1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
 134 1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
 135 1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
 136 1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
 137 1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
 138 1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
 139 1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
 140 1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
 141 1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
 142 1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
 143 1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
 144 1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
 145 1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
 146 1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
 147 1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
 148 1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
 149 1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
 150 1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
 151 1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
 152 1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
 153 1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
 154 1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
 155 1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
 156 1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
 157 1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
 158 1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
 159 1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
 160 1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
 161 1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
 162 1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
 163 1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
 164 1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
 165 1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
 166 1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
 167 1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
 168 1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
 169 1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
 170 1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
 171 1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
 172 1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
 173 1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
 174 1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
 175 1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
 176 1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
 177
 178 # Some characters with YPOGEGRAMMENI also have no corresponding titlecases
 179
 180 1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
 181 1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
 182 1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
 183 1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
 184 1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
 185 1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
 186
 187 1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
 188 1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
 189 1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
 190
 191 # ================================================================================
 192 # Conditional Mappings
 193 # The remainder of this file provides conditional casing data used to produce
 194 # full case mappings.
 195 # ================================================================================
 196 # Language-Insensitive Mappings
 197 # These are characters whose full case mappings do not depend on language, but do
 198 # depend on context (which characters come before or after). For more information
 199 # see the header of this file and the Unicode Standard.
 200 # ================================================================================
 201
 202 # Special case for final form of sigma
 203
 204 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
 205
 206 # Note: the following cases for non-final are already in the UnicodeData file.
 207
 208 # 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
 209 # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
 210 # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
 211
 212 # Note: the following cases are not included, since they would case-fold in lowercasing
 213
 214 # 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
 215 # 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
 216
 217 # ================================================================================
 218 # Language-Sensitive Mappings
 219 # These are characters whose full case mappings depend on language and perhaps also
 220 # context (which characters come before or after). For more information
 221 # see the header of this file and the Unicode Standard.
 222 # ================================================================================
 223
 224 # Lithuanian
 225
 226 # Lithuanian retains the dot in a lowercase i when followed by accents.
 227
 228 # Remove DOT ABOVE after "i" with upper or titlecase
 229
 230 0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
 231
 232 # Introduce an explicit dot above when lowercasing capital I's and J's
 233 # whenever there are more accents above.
 234 # (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
 235
 236 0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
 237 004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
 238 012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
 239 00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
 240 00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
 241 0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
 242
 243 # ================================================================================
 244
 245 # Turkish and Azeri
 246
 247 # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
 248 # The following rules handle those cases.
 249
 250 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
 251 0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
 252
 253 # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
 254 # This matches the behavior of the canonically equivalent I-dot_above
 255
 256 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
 257 0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
 258
 259 # When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
 260
 261 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
 262 0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
 263
 264 # When uppercasing, i turns into a dotted capital I
 265
 266 0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
 267 0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
 268
 269 # Note: the following case is already in the UnicodeData file.
 270
 271 # 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
 272
 273 # EOF
 274