source: for-distributions/trunk/bin/windows/perl/lib/unicore/SpecialCasing.txt@ 14489

Last change on this file since 14489 was 14489, checked in by oranfry, 17 years ago

upgrading to perl 5.8

File size: 15.2 KB
Line 
1# SpecialCasing-4.1.0.txt
2# Date: 2005-03-26, 00:35:45 GMT [MD]
3#
4# Unicode Character Database
5# Copyright (c) 1991-2005 Unicode, Inc.
6# For terms of use, see http://www.unicode.org/terms_of_use.html
7# For documentation, see UCD.html
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 does not have locale-specific mappings.)
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 locale 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#
38# A locale ID is defined by taking any language tag as defined by
39# RFC 3066 (or its successor), and replacing '-' by '_'.
40#
41# A context for a character C is defined by Section 3.13 Default Case Operations,
42# on p. 89-90 of The Unicode Standard, Version 4.0, as amended by Unicode 4.1.0,
43# as specified in http://www.unicode.org/versions/Unicode4.1.0/
44#
45# Parsers of this file must be prepared to deal with future additions to this format:
46# * Additional contexts
47# * Additional fields
48# ================================================================================
49
50# ================================================================================
51# Unconditional mappings
52# ================================================================================
53
54# The German es-zed is special--the normal mapping is to SS.
55# Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
56
5700DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
58
59# Preserve canonical equivalence for I with dot. Turkic is handled below.
60
610130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
62
63# Ligatures
64
65FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
66FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
67FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
68FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
69FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
70FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
71FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
72
730587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
74FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
75FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
76FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
77FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
78FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
79
80# No corresponding uppercase precomposed character
81
820149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
830390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
8403B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
8501F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
861E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
871E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
881E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
891E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
901E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
911F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
921F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
931F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
941F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
951FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
961FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
971FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
981FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
991FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
1001FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
1011FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
1021FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
1031FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
1041FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
1051FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
1061FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
107
108# IMPORTANT-when capitalizing iota-subscript (0345)
109# It MUST be in normalized form--moved to the end of any sequence of combining marks.
110# This is because logically it represents a following base character!
111# E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript>
112# It should never be the first character in a word, so in titlecasing it can be left as is.
113
114# The following cases are already in the UnicodeData file, so are only commented here.
115
116# 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
117
118# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
119# have special uppercases.
120# Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
121
1221F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
1231F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
1241F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1251F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1261F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1271F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1281F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1291F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1301F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
1311F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
1321F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1331F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1341F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1351F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1361F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1371F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1381F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
1391F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
1401F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1411F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1421F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1431F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1441F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1451F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1461F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
1471F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
1481F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1491F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1501F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1511F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1521F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1531F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1541FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
1551FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
1561FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1571FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1581FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1591FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1601FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1611FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1621FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
1631FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
1641FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1651FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1661FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1671FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1681FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1691FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1701FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
1711FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
1721FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
1731FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
1741FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
1751FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
176
177# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
178
1791FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
1801FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
1811FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
1821FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
1831FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
1841FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
185
1861FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
1871FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
1881FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
189
190# ================================================================================
191# Conditional mappings
192# ================================================================================
193
194# Special case for final form of sigma
195
19603A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
197
198# Note: the following cases for non-final are already in the UnicodeData file.
199
200# 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
201# 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
202# 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
203
204# Note: the following cases are not included, since they would case-fold in lowercasing
205
206# 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
207# 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
208
209# ================================================================================
210# Locale-sensitive mappings
211# ================================================================================
212
213# Lithuanian
214
215# Lithuanian retains the dot in a lowercase i when followed by accents.
216
217# Remove DOT ABOVE after "i" with upper or titlecase
218
2190307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
220
221# Introduce an explicit dot above when lowercasing capital I's and J's
222# whenever there are more accents above.
223# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
224
2250049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
226004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
227012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
22800CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
22900CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
2300128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
231
232# ================================================================================
233
234# Turkish and Azeri
235
236# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
237# The following rules handle those cases.
238
2390130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
2400130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
241
242# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
243# This matches the behavior of the canonically equivalent I-dot_above
244
2450307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
2460307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
247
248# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
249
2500049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
2510049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
252
253# When uppercasing, i turns into a dotted capital I
254
2550069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
2560069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
257
258# Note: the following case is already in the UnicodeData file.
259
260# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
Note: See TracBrowser for help on using the repository browser.