1 # SpecialCasing-6.2.0.txt
2 # Date: 2012-05-23, 20:35:15 GMT [MD]
3 #
4 # Unicode Character Database
5 # Copyright (c) 1991-2012 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
51 # @missing: 0000..10FFFF; <slc>; <stc>; <suc>;
52
53 # ================================================================================
54 # Unconditional mappings
55 # ================================================================================
56
57 # The German es-zed is special--the normal mapping is to SS.
58 # Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
59
60 00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
61
62 # Preserve canonical equivalence for I with dot. Turkic is handled below.
63
64 0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
65
66 # Ligatures
67
68 FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
69 FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
70 FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
71 FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
72 FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
97 1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
98 1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
99 1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
100 1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
101 1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
102 1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
103 1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
104 1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
105 1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
106 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
107 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
108 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
109 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
110
111 # IMPORTANT-when iota-subscript (0345) is uppercased or titlecased,
112 # the result will be incorrect unless the iota-subscript is moved to the end
113 # of any sequence of combining marks. Otherwise, the accents will go on the capital iota.
114 # This process can be achieved by first transforming the text to NFC before casing.
115 # E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA>
116
117 # The following cases are already in the UnicodeData file, so are only commented here.
118
119 # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
120
121 # All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
122 # have special uppercases.
123 # Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
124
125 1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
126 1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
127 1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
128 1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
129 1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
130 1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
131 1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
132 1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
133 1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
134 1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
135 1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
136 1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
137 1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
188
189 1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
190 1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
191 1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
192
193 # ================================================================================
194 # Conditional Mappings
195 # The remainder of this file provides conditional casing data used to produce
196 # full case mappings.
197 # ================================================================================
198 # Language-Insensitive Mappings
199 # These are characters whose full case mappings do not depend on language, but do
200 # depend on context (which characters come before or after). For more information
201 # see the header of this file and the Unicode Standard.
202 # ================================================================================
203
204 # Special case for final form of sigma
205
206 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
207
208 # Note: the following cases for non-final are already in the UnicodeData file.
209
210 # 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
211 # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
212 # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
213
214 # Note: the following cases are not included, since they would case-fold in lowercasing
215
216 # 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
217 # 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
218
219 # ================================================================================
220 # Language-Sensitive Mappings
221 # These are characters whose full case mappings depend on language and perhaps also
222 # context (which characters come before or after). For more information
223 # see the header of this file and the Unicode Standard.
224 # ================================================================================
225
226 # Lithuanian
227
228 # Lithuanian retains the dot in a lowercase i when followed by accents.
251
252 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
253 0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
254
255 # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
256 # This matches the behavior of the canonically equivalent I-dot_above
257
258 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
259 0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
260
261 # When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
262
263 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
264 0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
265
266 # When uppercasing, i turns into a dotted capital I
267
268 0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
269 0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
270
271 # Note: the following case is already in the UnicodeData file.
272
273 # 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
274
275 # EOF
276
|
1 # SpecialCasing-7.0.0.txt
2 # Date: 2014-03-18, 07:18:02 GMT [MD]
3 #
4 # Unicode Character Database
5 # Copyright (c) 1991-2014 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
10 #
11 # This file is a supplement to the UnicodeData.txt file. It does not define any
12 # properties, but rather provides additional information about the casing of
13 # Unicode characters, for situations when casing incurs a change in string length
14 # or is dependent on context or locale. For compatibility, the UnicodeData.txt
15 # file only contains simple case mappings for characters where they are one-to-one
16 # and independent of context and language. The data in this file, combined with
17 # the simple case mappings in UnicodeData.txt, defines the full case mappings
18 # Lowercase_Mapping (lc), Titlecase_Mapping (tc), and Uppercase_Mapping (uc).
19 #
20 # Note that the preferred mechanism for defining tailored casing operations is
21 # the Unicode Common Locale Data Repository (CLDR). For more information, see the
22 # discussion of case mappings and case algorithms in the Unicode Standard.
23 #
24 # All code points not listed in this file that do not have a simple case mappings
25 # in UnicodeData.txt map to themselves.
26 # ================================================================================
27 # Format
28 # ================================================================================
29 # The entries in this file are in the following machine-readable format:
30 #
31 # <code>; <lower>; <title>; <upper>; (<condition_list>;)? # <comment>
32 #
33 # <code>, <lower>, <title>, and <upper> provide the respective full case mappings
34 # of <code>, expressed as character values in hex. If there is more than one character,
35 # they are separated by spaces. Other than as used to separate elements, spaces are
36 # to be ignored.
37 #
38 # The <condition_list> is optional. Where present, it consists of one or more language IDs
39 # or casing contexts, separated by spaces. In these conditions:
40 # - A condition list overrides the normal behavior if all of the listed conditions are true.
41 # - The casing context is always the context of the characters in the original string,
42 # NOT in the resulting string.
43 # - Case distinctions in the condition list are not significant.
44 # - Conditions preceded by "Not_" represent the negation of the condition.
45 # The condition list is not represented in the UCD as a formal property.
46 #
47 # A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
48 #
49 # A casing context for a character is defined by Section 3.13 Default Case Algorithms
50 # of The Unicode Standard.
51 #
52 # Parsers of this file must be prepared to deal with future additions to this format:
53 # * Additional contexts
54 # * Additional fields
55 # ================================================================================
56
57 # ================================================================================
58 # Unconditional mappings
59 # ================================================================================
60
61 # The German es-zed is special--the normal mapping is to SS.
62 # Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
63
64 00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
65
66 # Preserve canonical equivalence for I with dot. Turkic is handled below.
67
68 0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
69
70 # Ligatures
71
72 FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
73 FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
74 FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
75 FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
76 FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
101 1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
102 1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
103 1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
104 1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
105 1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
106 1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
107 1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
108 1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
109 1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
110 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
111 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
112 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
113 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
114
115 # IMPORTANT-when iota-subscript (0345) is uppercased or titlecased,
116 # the result will be incorrect unless the iota-subscript is moved to the end
117 # of any sequence of combining marks. Otherwise, the accents will go on the capital iota.
118 # This process can be achieved by first transforming the text to NFC before casing.
119 # E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA>
120
121 # The following cases are already in the UnicodeData.txt file, so are only commented here.
122
123 # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
124
125 # All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
126 # have special uppercases.
127 # Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
128
129 1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
130 1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
131 1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
132 1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
133 1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
134 1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
135 1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
136 1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
137 1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
138 1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
139 1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
140 1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
141 1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
192
193 1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
194 1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
195 1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
196
197 # ================================================================================
198 # Conditional Mappings
199 # The remainder of this file provides conditional casing data used to produce
200 # full case mappings.
201 # ================================================================================
202 # Language-Insensitive Mappings
203 # These are characters whose full case mappings do not depend on language, but do
204 # depend on context (which characters come before or after). For more information
205 # see the header of this file and the Unicode Standard.
206 # ================================================================================
207
208 # Special case for final form of sigma
209
210 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
211
212 # Note: the following cases for non-final are already in the UnicodeData.txt file.
213
214 # 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
215 # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
216 # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
217
218 # Note: the following cases are not included, since they would case-fold in lowercasing
219
220 # 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
221 # 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
222
223 # ================================================================================
224 # Language-Sensitive Mappings
225 # These are characters whose full case mappings depend on language and perhaps also
226 # context (which characters come before or after). For more information
227 # see the header of this file and the Unicode Standard.
228 # ================================================================================
229
230 # Lithuanian
231
232 # Lithuanian retains the dot in a lowercase i when followed by accents.
255
256 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
257 0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
258
259 # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
260 # This matches the behavior of the canonically equivalent I-dot_above
261
262 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
263 0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
264
265 # When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
266
267 0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
268 0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
269
270 # When uppercasing, i turns into a dotted capital I
271
272 0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
273 0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
274
275 # Note: the following case is already in the UnicodeData.txt file.
276
277 # 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
278
279 # EOF
280
|