1# SpecialCasing-8.0.0.txt
2# Date: 2014-12-16, 23:08:04 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
6400DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
65
66# Preserve canonical equivalence for I with dot. Turkic is handled below.
67
680130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
69
70# Ligatures
71
72FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
73FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
74FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
75FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
76FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
77FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
78FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
79
800587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
81FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
82FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
83FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
84FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
85FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
86
87# No corresponding uppercase precomposed character
88
890149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
900390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
9103B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
9201F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
931E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
941E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
951E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
961E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
971E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
981F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
991F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
1001F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
1011F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
1021FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
1031FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
1041FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
1051FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
1061FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
1071FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
1081FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
1091FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
1101FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
1111FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
1121FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
1131FF6; 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
1291F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
1301F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
1311F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1321F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1331F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1341F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1351F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1361F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1371F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
1381F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
1391F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1401F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1411F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1421F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1431F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1441F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1451F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
1461F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
1471F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1481F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1491F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1501F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1511F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1521F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1531F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
1541F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
1551F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1561F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1571F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1581F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1591F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1601F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1611FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
1621FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
1631FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1641FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1651FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1661FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1671FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1681FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1691FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
1701FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
1711FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1721FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1731FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1741FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1751FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1761FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1771FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
1781FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
1791FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
1801FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
1811FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
1821FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
183
184# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
185
1861FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
1871FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
1881FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
1891FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
1901FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
1911FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
192
1931FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
1941FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
1951FF7; 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
21003A3; 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.
233
234# Remove DOT ABOVE after "i" with upper or titlecase
235
2360307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
237
238# Introduce an explicit dot above when lowercasing capital I's and J's
239# whenever there are more accents above.
240# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
241
2420049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
243004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
244012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
24500CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
24600CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
2470128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
248
249# ================================================================================
250
251# Turkish and Azeri
252
253# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
254# The following rules handle those cases.
255
2560130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
2570130; 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
2620307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
2630307; ; 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
2670049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
2680049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
269
270# When uppercasing, i turns into a dotted capital I
271
2720069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
2730069; 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
281