J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | # SpecialCasing-4.0.0.txt |
| 2 | # Date: 2003-03-14, 20:22:04 GMT [MD] |
| 3 | # |
| 4 | # Special Casing Properties |
| 5 | # |
| 6 | # This file is a supplement to the UnicodeData file. |
| 7 | # It contains additional information about the casing of Unicode characters. |
| 8 | # (For compatibility, the UnicodeData.txt file only contains case mappings for |
| 9 | # characters where they are 1-1, and does not have locale-specific mappings.) |
| 10 | # For more information, see the discussion of Case Mappings in the Unicode Standard. |
| 11 | # |
| 12 | # All code points not listed in this file that do not have a simple case mappings |
| 13 | # in UnicodeData.txt map to themselves. |
| 14 | # ================================================================================ |
| 15 | # Format |
| 16 | # ================================================================================ |
| 17 | # The entries in this file are in the following machine-readable format: |
| 18 | # |
| 19 | # <code>; <lower> ; <title> ; <upper> ; (<condition_list> ;)? # <comment> |
| 20 | # |
| 21 | # <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more than |
| 22 | # one character, they are separated by spaces. Other than as used to separate elements, |
| 23 | # spaces are to be ignored. |
| 24 | # |
| 25 | # The <condition_list> is optional. Where present, it consists of one or more locales or contexts, |
| 26 | # separated by spaces. In these conditions: |
| 27 | # - A condition list overrides the normal behavior if all of the listed conditions are true. |
| 28 | # - The context is always the context of the characters in the original string, |
| 29 | # NOT in the resulting string. |
| 30 | # - Case distinctions in the condition list are not significant. |
| 31 | # - Conditions preceded by "Not_" represent the negation of the condition. |
| 32 | # |
| 33 | # A locale is defined as: |
| 34 | # <locale> := <ISO_639_code> ( "_" <ISO_3166_code> ( "_" <variant> )? )? |
| 35 | # <ISO_3166_code> := 2-letter ISO country code, |
| 36 | # <ISO_639_code> := 2-letter ISO language code |
| 37 | # |
| 38 | # A context is one of the following, as defined in the Unicode Standard: |
| 39 | # Final_Sigma, After_Soft_Dotted, More_Above, Before_Dot, Not_Before_Dot, After_I |
| 40 | # |
| 41 | # Parsers of this file must be prepared to deal with future additions to this format: |
| 42 | # * Additional contexts |
| 43 | # * Additional fields |
| 44 | # ================================================================================ |
| 45 | |
| 46 | # ================================================================================ |
| 47 | # Unconditional mappings |
| 48 | # ================================================================================ |
| 49 | |
| 50 | # The German es-zed is special--the normal mapping is to SS. |
| 51 | # Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>)) |
| 52 | |
| 53 | 00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S |
| 54 | |
| 55 | # Preserve canonical equivalence for I with dot. Turkic is handled below. |
| 56 | |
| 57 | 0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| 58 | |
| 59 | # Ligatures |
| 60 | |
| 61 | FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF |
| 62 | FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI |
| 63 | FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL |
| 64 | FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI |
| 65 | FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL |
| 66 | FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T |
| 67 | FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST |
| 68 | |
| 69 | 0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN |
| 70 | FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW |
| 71 | FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH |
| 72 | FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI |
| 73 | FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW |
| 74 | FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH |
| 75 | |
| 76 | # No corresponding uppercase precomposed character |
| 77 | |
| 78 | 0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE |
| 79 | 0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS |
| 80 | 03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS |
| 81 | 01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON |
| 82 | 1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW |
| 83 | 1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS |
| 84 | 1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE |
| 85 | 1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE |
| 86 | 1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING |
| 87 | 1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI |
| 88 | 1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA |
| 89 | 1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA |
| 90 | 1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI |
| 91 | 1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI |
| 92 | 1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI |
| 93 | 1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA |
| 94 | 1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA |
| 95 | 1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI |
| 96 | 1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI |
| 97 | 1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA |
| 98 | 1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA |
| 99 | 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI |
| 100 | 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI |
| 101 | 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI |
| 102 | 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI |
| 103 | |
| 104 | # IMPORTANT-when capitalizing iota-subscript (0345) |
| 105 | # It MUST be in normalized form--moved to the end of any sequence of combining marks. |
| 106 | # This is because logically it represents a following base character! |
| 107 | # E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript> |
| 108 | # It should never be the first character in a word, so in titlecasing it can be left as is. |
| 109 | |
| 110 | # The following cases are already in the UnicodeData file, so are only commented here. |
| 111 | |
| 112 | # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI |
| 113 | |
| 114 | # All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript) |
| 115 | # have special uppercases. |
| 116 | # Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase! |
| 117 | |
| 118 | 1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI |
| 119 | 1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI |
| 120 | 1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI |
| 121 | 1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI |
| 122 | 1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI |
| 123 | 1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI |
| 124 | 1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI |
| 125 | 1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI |
| 126 | 1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI |
| 127 | 1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI |
| 128 | 1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI |
| 129 | 1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI |
| 130 | 1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI |
| 131 | 1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI |
| 132 | 1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI |
| 133 | 1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI |
| 134 | 1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI |
| 135 | 1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI |
| 136 | 1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI |
| 137 | 1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI |
| 138 | 1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI |
| 139 | 1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI |
| 140 | 1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI |
| 141 | 1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI |
| 142 | 1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI |
| 143 | 1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI |
| 144 | 1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI |
| 145 | 1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI |
| 146 | 1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI |
| 147 | 1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI |
| 148 | 1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI |
| 149 | 1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI |
| 150 | 1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI |
| 151 | 1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI |
| 152 | 1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI |
| 153 | 1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI |
| 154 | 1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI |
| 155 | 1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI |
| 156 | 1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI |
| 157 | 1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI |
| 158 | 1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI |
| 159 | 1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI |
| 160 | 1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI |
| 161 | 1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI |
| 162 | 1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI |
| 163 | 1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI |
| 164 | 1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI |
| 165 | 1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI |
| 166 | 1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI |
| 167 | 1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI |
| 168 | 1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI |
| 169 | 1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI |
| 170 | 1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI |
| 171 | 1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI |
| 172 | |
| 173 | # Some characters with YPOGEGRAMMENI are also have no corresponding titlecases |
| 174 | |
| 175 | 1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI |
| 176 | 1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI |
| 177 | 1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI |
| 178 | 1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI |
| 179 | 1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI |
| 180 | 1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI |
| 181 | |
| 182 | 1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI |
| 183 | 1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI |
| 184 | 1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI |
| 185 | |
| 186 | # ================================================================================ |
| 187 | # Conditional mappings |
| 188 | # ================================================================================ |
| 189 | |
| 190 | # Special case for final form of sigma |
| 191 | |
| 192 | 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA |
| 193 | |
| 194 | # Note: the following cases for non-final are already in the UnicodeData file. |
| 195 | |
| 196 | # 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA |
| 197 | # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA |
| 198 | # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA |
| 199 | |
| 200 | # Note: the following cases are not included, since they would case-fold in lowercasing |
| 201 | |
| 202 | # 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA |
| 203 | # 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA |
| 204 | |
| 205 | # ================================================================================ |
| 206 | # Locale-sensitive mappings |
| 207 | # ================================================================================ |
| 208 | |
| 209 | # Lithuanian |
| 210 | |
| 211 | # Lithuanian retains the dot in a lowercase i when followed by accents. |
| 212 | |
| 213 | # Remove DOT ABOVE after "i" with upper or titlecase |
| 214 | |
| 215 | 0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE |
| 216 | |
| 217 | # Introduce an explicit dot above when lowercasing capital I's and J's |
| 218 | # whenever there are more accents above. |
| 219 | # (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek) |
| 220 | |
| 221 | 0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I |
| 222 | 004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J |
| 223 | 012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK |
| 224 | 00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE |
| 225 | 00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE |
| 226 | 0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE |
| 227 | |
| 228 | # ================================================================================ |
| 229 | |
| 230 | # Turkish and Azeri |
| 231 | |
| 232 | # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri |
| 233 | # The following rules handle those cases. |
| 234 | |
| 235 | 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| 236 | 0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| 237 | |
| 238 | # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i. |
| 239 | # This matches the behavior of the canonically equivalent I-dot_above |
| 240 | |
| 241 | 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE |
| 242 | 0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE |
| 243 | |
| 244 | # When lowercasing, unless an I is before a dot_above, it turns into a dotless i. |
| 245 | |
| 246 | 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I |
| 247 | 0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I |
| 248 | |
| 249 | # When uppercasing, i turns into a dotted capital I |
| 250 | |
| 251 | 0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I |
| 252 | 0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I |
| 253 | |
| 254 | # Note: the following case is already in the UnicodeData file. |
| 255 | |
| 256 | # 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I |