intl/icu/source/data/unidata/SpecialCasing.txt@fc2d59ddac77 (annotated)
intl/icu/source/data/unidata/SpecialCasing.txt
Wed, 31 Dec 2014 07:22:50 +0100
- author
- Michael Schloh von Bennewitz <michael@schloh.com>
- date
- Wed, 31 Dec 2014 07:22:50 +0100
- branch
- TOR_BUG_3246
- changeset 4
- fc2d59ddac77
- permissions
- -rw-r--r--
Correct previous dual key logic pending first delivery installment.
| michael@0 | 1 | # SpecialCasing-6.3.0.txt |
| michael@0 | 2 | # Date: 2013-05-08, 13:54:51 GMT [MD] |
| michael@0 | 3 | # |
| michael@0 | 4 | # Unicode Character Database |
| michael@0 | 5 | # Copyright (c) 1991-2013 Unicode, Inc. |
| michael@0 | 6 | # For terms of use, see http://www.unicode.org/terms_of_use.html |
| michael@0 | 7 | # For documentation, see http://www.unicode.org/reports/tr44/ |
| michael@0 | 8 | # |
| michael@0 | 9 | # Special Casing Properties |
| michael@0 | 10 | # |
| michael@0 | 11 | # This file is a supplement to the UnicodeData file. |
| michael@0 | 12 | # It contains additional information about the casing of Unicode characters. |
| michael@0 | 13 | # (For compatibility, the UnicodeData.txt file only contains case mappings for |
| michael@0 | 14 | # characters where they are 1-1, and independent of context and language. |
| michael@0 | 15 | # For more information, see the discussion of Case Mappings in the Unicode Standard. |
| michael@0 | 16 | # |
| michael@0 | 17 | # All code points not listed in this file that do not have a simple case mappings |
| michael@0 | 18 | # in UnicodeData.txt map to themselves. |
| michael@0 | 19 | # ================================================================================ |
| michael@0 | 20 | # Format |
| michael@0 | 21 | # ================================================================================ |
| michael@0 | 22 | # The entries in this file are in the following machine-readable format: |
| michael@0 | 23 | # |
| michael@0 | 24 | # <code>; <lower> ; <title> ; <upper> ; (<condition_list> ;)? # <comment> |
| michael@0 | 25 | # |
| michael@0 | 26 | # <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more |
| michael@0 | 27 | # than one character, they are separated by spaces. Other than as used to separate |
| michael@0 | 28 | # elements, spaces are to be ignored. |
| michael@0 | 29 | # |
| michael@0 | 30 | # The <condition_list> is optional. Where present, it consists of one or more language IDs |
| michael@0 | 31 | # or contexts, separated by spaces. In these conditions: |
| michael@0 | 32 | # - A condition list overrides the normal behavior if all of the listed conditions are true. |
| michael@0 | 33 | # - The context is always the context of the characters in the original string, |
| michael@0 | 34 | # NOT in the resulting string. |
| michael@0 | 35 | # - Case distinctions in the condition list are not significant. |
| michael@0 | 36 | # - Conditions preceded by "Not_" represent the negation of the condition. |
| michael@0 | 37 | # The condition list is not represented in the UCD as a formal property. |
| michael@0 | 38 | # |
| michael@0 | 39 | # A language ID is defined by BCP 47, with '-' and '_' treated equivalently. |
| michael@0 | 40 | # |
| michael@0 | 41 | # A context for a character C is defined by Section 3.13 Default Case |
| michael@0 | 42 | # Algorithms, of The Unicode Standard, Version 6.3. |
| michael@0 | 43 | # (This is identical to the context defined by Unicode 4.1.0, |
| michael@0 | 44 | # as specified in http://www.unicode.org/versions/Unicode4.1.0/) |
| michael@0 | 45 | # |
| michael@0 | 46 | # Parsers of this file must be prepared to deal with future additions to this format: |
| michael@0 | 47 | # * Additional contexts |
| michael@0 | 48 | # * Additional fields |
| michael@0 | 49 | # ================================================================================ |
| michael@0 | 50 | |
| michael@0 | 51 | # @missing: 0000..10FFFF; <slc>; <stc>; <suc>; |
| michael@0 | 52 | |
| michael@0 | 53 | # ================================================================================ |
| michael@0 | 54 | # Unconditional mappings |
| michael@0 | 55 | # ================================================================================ |
| michael@0 | 56 | |
| michael@0 | 57 | # The German es-zed is special--the normal mapping is to SS. |
| michael@0 | 58 | # Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>)) |
| michael@0 | 59 | |
| michael@0 | 60 | 00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S |
| michael@0 | 61 | |
| michael@0 | 62 | # Preserve canonical equivalence for I with dot. Turkic is handled below. |
| michael@0 | 63 | |
| michael@0 | 64 | 0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| michael@0 | 65 | |
| michael@0 | 66 | # Ligatures |
| michael@0 | 67 | |
| michael@0 | 68 | FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF |
| michael@0 | 69 | FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI |
| michael@0 | 70 | FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL |
| michael@0 | 71 | FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI |
| michael@0 | 72 | FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL |
| michael@0 | 73 | FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T |
| michael@0 | 74 | FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST |
| michael@0 | 75 | |
| michael@0 | 76 | 0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN |
| michael@0 | 77 | FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW |
| michael@0 | 78 | FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH |
| michael@0 | 79 | FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI |
| michael@0 | 80 | FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW |
| michael@0 | 81 | FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH |
| michael@0 | 82 | |
| michael@0 | 83 | # No corresponding uppercase precomposed character |
| michael@0 | 84 | |
| michael@0 | 85 | 0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE |
| michael@0 | 86 | 0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS |
| michael@0 | 87 | 03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS |
| michael@0 | 88 | 01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON |
| michael@0 | 89 | 1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW |
| michael@0 | 90 | 1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS |
| michael@0 | 91 | 1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE |
| michael@0 | 92 | 1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE |
| michael@0 | 93 | 1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING |
| michael@0 | 94 | 1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI |
| michael@0 | 95 | 1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA |
| michael@0 | 96 | 1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA |
| michael@0 | 97 | 1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI |
| michael@0 | 98 | 1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI |
| michael@0 | 99 | 1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI |
| michael@0 | 100 | 1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA |
| michael@0 | 101 | 1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA |
| michael@0 | 102 | 1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI |
| michael@0 | 103 | 1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI |
| michael@0 | 104 | 1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA |
| michael@0 | 105 | 1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA |
| michael@0 | 106 | 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI |
| michael@0 | 107 | 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI |
| michael@0 | 108 | 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI |
| michael@0 | 109 | 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI |
| michael@0 | 110 | |
| michael@0 | 111 | # IMPORTANT-when iota-subscript (0345) is uppercased or titlecased, |
| michael@0 | 112 | # the result will be incorrect unless the iota-subscript is moved to the end |
| michael@0 | 113 | # of any sequence of combining marks. Otherwise, the accents will go on the capital iota. |
| michael@0 | 114 | # This process can be achieved by first transforming the text to NFC before casing. |
| michael@0 | 115 | # E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA> |
| michael@0 | 116 | |
| michael@0 | 117 | # The following cases are already in the UnicodeData file, so are only commented here. |
| michael@0 | 118 | |
| michael@0 | 119 | # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI |
| michael@0 | 120 | |
| michael@0 | 121 | # All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript) |
| michael@0 | 122 | # have special uppercases. |
| michael@0 | 123 | # Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase! |
| michael@0 | 124 | |
| michael@0 | 125 | 1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI |
| michael@0 | 126 | 1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI |
| michael@0 | 127 | 1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI |
| michael@0 | 128 | 1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI |
| michael@0 | 129 | 1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI |
| michael@0 | 130 | 1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI |
| michael@0 | 131 | 1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 132 | 1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 133 | 1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI |
| michael@0 | 134 | 1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI |
| michael@0 | 135 | 1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI |
| michael@0 | 136 | 1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI |
| michael@0 | 137 | 1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI |
| michael@0 | 138 | 1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI |
| michael@0 | 139 | 1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI |
| michael@0 | 140 | 1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI |
| michael@0 | 141 | 1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI |
| michael@0 | 142 | 1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI |
| michael@0 | 143 | 1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI |
| michael@0 | 144 | 1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI |
| michael@0 | 145 | 1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI |
| michael@0 | 146 | 1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI |
| michael@0 | 147 | 1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 148 | 1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 149 | 1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI |
| michael@0 | 150 | 1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI |
| michael@0 | 151 | 1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI |
| michael@0 | 152 | 1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI |
| michael@0 | 153 | 1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI |
| michael@0 | 154 | 1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI |
| michael@0 | 155 | 1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI |
| michael@0 | 156 | 1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI |
| michael@0 | 157 | 1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI |
| michael@0 | 158 | 1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI |
| michael@0 | 159 | 1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI |
| michael@0 | 160 | 1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI |
| michael@0 | 161 | 1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI |
| michael@0 | 162 | 1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI |
| michael@0 | 163 | 1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 164 | 1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 165 | 1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI |
| michael@0 | 166 | 1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI |
| michael@0 | 167 | 1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI |
| michael@0 | 168 | 1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI |
| michael@0 | 169 | 1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI |
| michael@0 | 170 | 1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI |
| michael@0 | 171 | 1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI |
| michael@0 | 172 | 1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI |
| michael@0 | 173 | 1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI |
| michael@0 | 174 | 1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI |
| michael@0 | 175 | 1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI |
| michael@0 | 176 | 1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI |
| michael@0 | 177 | 1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI |
| michael@0 | 178 | 1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI |
| michael@0 | 179 | |
| michael@0 | 180 | # Some characters with YPOGEGRAMMENI also have no corresponding titlecases |
| michael@0 | 181 | |
| michael@0 | 182 | 1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI |
| michael@0 | 183 | 1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI |
| michael@0 | 184 | 1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI |
| michael@0 | 185 | 1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI |
| michael@0 | 186 | 1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI |
| michael@0 | 187 | 1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI |
| michael@0 | 188 | |
| michael@0 | 189 | 1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 190 | 1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 191 | 1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI |
| michael@0 | 192 | |
| michael@0 | 193 | # ================================================================================ |
| michael@0 | 194 | # Conditional Mappings |
| michael@0 | 195 | # The remainder of this file provides conditional casing data used to produce |
| michael@0 | 196 | # full case mappings. |
| michael@0 | 197 | # ================================================================================ |
| michael@0 | 198 | # Language-Insensitive Mappings |
| michael@0 | 199 | # These are characters whose full case mappings do not depend on language, but do |
| michael@0 | 200 | # depend on context (which characters come before or after). For more information |
| michael@0 | 201 | # see the header of this file and the Unicode Standard. |
| michael@0 | 202 | # ================================================================================ |
| michael@0 | 203 | |
| michael@0 | 204 | # Special case for final form of sigma |
| michael@0 | 205 | |
| michael@0 | 206 | 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA |
| michael@0 | 207 | |
| michael@0 | 208 | # Note: the following cases for non-final are already in the UnicodeData file. |
| michael@0 | 209 | |
| michael@0 | 210 | # 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA |
| michael@0 | 211 | # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA |
| michael@0 | 212 | # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA |
| michael@0 | 213 | |
| michael@0 | 214 | # Note: the following cases are not included, since they would case-fold in lowercasing |
| michael@0 | 215 | |
| michael@0 | 216 | # 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA |
| michael@0 | 217 | # 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA |
| michael@0 | 218 | |
| michael@0 | 219 | # ================================================================================ |
| michael@0 | 220 | # Language-Sensitive Mappings |
| michael@0 | 221 | # These are characters whose full case mappings depend on language and perhaps also |
| michael@0 | 222 | # context (which characters come before or after). For more information |
| michael@0 | 223 | # see the header of this file and the Unicode Standard. |
| michael@0 | 224 | # ================================================================================ |
| michael@0 | 225 | |
| michael@0 | 226 | # Lithuanian |
| michael@0 | 227 | |
| michael@0 | 228 | # Lithuanian retains the dot in a lowercase i when followed by accents. |
| michael@0 | 229 | |
| michael@0 | 230 | # Remove DOT ABOVE after "i" with upper or titlecase |
| michael@0 | 231 | |
| michael@0 | 232 | 0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE |
| michael@0 | 233 | |
| michael@0 | 234 | # Introduce an explicit dot above when lowercasing capital I's and J's |
| michael@0 | 235 | # whenever there are more accents above. |
| michael@0 | 236 | # (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek) |
| michael@0 | 237 | |
| michael@0 | 238 | 0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I |
| michael@0 | 239 | 004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J |
| michael@0 | 240 | 012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK |
| michael@0 | 241 | 00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE |
| michael@0 | 242 | 00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE |
| michael@0 | 243 | 0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE |
| michael@0 | 244 | |
| michael@0 | 245 | # ================================================================================ |
| michael@0 | 246 | |
| michael@0 | 247 | # Turkish and Azeri |
| michael@0 | 248 | |
| michael@0 | 249 | # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri |
| michael@0 | 250 | # The following rules handle those cases. |
| michael@0 | 251 | |
| michael@0 | 252 | 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| michael@0 | 253 | 0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE |
| michael@0 | 254 | |
| michael@0 | 255 | # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i. |
| michael@0 | 256 | # This matches the behavior of the canonically equivalent I-dot_above |
| michael@0 | 257 | |
| michael@0 | 258 | 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE |
| michael@0 | 259 | 0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE |
| michael@0 | 260 | |
| michael@0 | 261 | # When lowercasing, unless an I is before a dot_above, it turns into a dotless i. |
| michael@0 | 262 | |
| michael@0 | 263 | 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I |
| michael@0 | 264 | 0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I |
| michael@0 | 265 | |
| michael@0 | 266 | # When uppercasing, i turns into a dotted capital I |
| michael@0 | 267 | |
| michael@0 | 268 | 0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I |
| michael@0 | 269 | 0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I |
| michael@0 | 270 | |
| michael@0 | 271 | # Note: the following case is already in the UnicodeData file. |
| michael@0 | 272 | |
| michael@0 | 273 | # 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I |
| michael@0 | 274 | |
| michael@0 | 275 | # EOF |
| michael@0 | 276 |
