SYN SYN
[p5sagit/p5-mst-13.2.git] / lib / unicode / SpecCase.txt
CommitLineData
22d4bb9c 1# SpecialCasing-3.txt
c529f79d 2#
3# Special Casing Properties
4#
5# This file is a supplement to the UnicodeData file.
6# It contains additional information about the casing of Unicode characters.
7# (For compatibility, the UnicodeData.txt file only contains case mappings for
8# characters where they are 1-1, and does not have locale-specific mappings.)
9# These are informative character properties.
10#
11# Send comments to mark@unicode.org
12#
13# ================================================================================
14# Format
15# ================================================================================
16# The entries in this file are in the following machine-readable format:
17#
18# <entry> := <case_mapping> <condition_list>? (<s>* "#" <comment>)?
19#
20# <case_mapping> := <source> <sep> <lower> <sep> <title> <sep> <upper> <sep>
21#
22# <source> := <code_point>
23# <sep> := <s>* ";" <s>*
24# <lower> := <code_point_list>
25# <title> := <code_point_list>
26# <upper> := <code_point_list>
27# <code_point_list> := <code_point> (<s>+ <code_point>)*
28# <code_point> := <hex><hex><hex><hex>
22d4bb9c 29# <hex> := [0-9A-Fa-f]
c529f79d 30# <s> := <space>
31#
22d4bb9c 32# <condition_list> := <locale>? (<s>+ <context>)* <sep>
33# <locale> := <ISO_639_code> ( "_" <ISO_3166_code> )? ( "_" <variant> )?
c529f79d 34# <ISO_3166_code> := 2-letter country code,
35# as in http://www.unicode.org/unicode/onlinedat/countries.html
36# <ISO_639_code> := 2-letter code,
37# as in http://www.unicode.org/unicode/onlinedat/languages.html
22d4bb9c 38# <context> := "FINAL" | "NON_FINAL" | "MODERN" | "NON_MODERN" | "AFTER_i"
39#
40# A condition list overrides the normal behavior if all of the listed conditions are true.
41# Case distinctions in the condition list are not significant.
c529f79d 42#
c529f79d 43# FINAL: The letter is not followed by a letter of category L* (e.g. Ll, Lt, Lu, Lm, or Lo).
44# MODERN: The mapping is only used for modern text.
22d4bb9c 45# AFTER_i: The last base character was "i" 0069
46#
c529f79d 47# Conditions preceded by "NON_" represent the negation of the condition
48#
49# New contexts may be added in the future.
c529f79d 50# Additional whitespace around elements is optional. Blank lines are ignored in parsing.
51# On any line, all text following "#" is a comment, and are ignored in parsing.
22d4bb9c 52#
53# Parsers of this file must be prepared to deal future additions to this format:
54# * Additional contexts
55# * Additional fields
c529f79d 56# ================================================================================
57
58# ================================================================================
59# Unconditional mappings
60# ================================================================================
61
62# The German es-zed is special--the normal mapping is to SS.
63# Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
64
6500DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
66
67# Ligatures
68
69FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
70FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
71FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
72FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
73FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
74FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
75FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
76
770587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
78FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
79FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
80FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
81FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
82FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
83
84# No corresponding uppercase precomposed character
85
22d4bb9c 860149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
c529f79d 870390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
8803B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
8901F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
901E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
911E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
921E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
931E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
941E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
951F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
961F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
971F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
981F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
991FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
1001FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
1011FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
1021FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
1031FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
1041FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
1051FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
1061FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
1071FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
1081FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
1091FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
1101FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
111
112# IMPORTANT-when capitalizing iota-subscript (0345)
113# It MUST be in normalized form--moved to the end of any sequence of combining marks.
114# This is because logically it represents a following base character!
115# E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript>
116# It should never be the first character in a word, so in titlecasing it can be left as is.
117
118# The following cases are already in the UnicodeData file, so are only commented here.
119
120# 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
121
122# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
123# have special uppercases.
124# Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
125
1261F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
1271F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
1281F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1291F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1301F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1311F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1321F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1331F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1341F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
1351F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
1361F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1371F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1381F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1391F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1401F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1411F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1421F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
1431F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
1441F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1451F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1461F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1471F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1481F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1491F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1501F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
1511F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
1521F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1531F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1541F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1551F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1561F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1571F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
1581FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
1591FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
1601FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
1611FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
1621FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
1631FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
1641FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
1651FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
1661FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
1671FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
1681FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
1691FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
1701FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
1711FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
1721FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
1731FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
174
1751FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
1761FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
1771FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
1781FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
1791FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
1801FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
181
182# Some characters with YPOGEGRAMMENI are also have no corresponding titlecases
183
1841FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
1851FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
1861FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
1871FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
1881FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
1891FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
190
1911FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
1921FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
1931FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
194
195# ================================================================================
196# Conditional mappings
197# ================================================================================
198
199# Special case for final form of sigma
200
20103A3; 03C2; 03A3; 03A3; FINAL; # GREEK CAPITAL LETTER SIGMA
202
203# Note: the following cases for non-final are already in the UnicodeData file.
204
205# 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
206# 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
207# 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
208
22d4bb9c 209# Note: the following cases are not included, since they would case-fold in lowercasing
c529f79d 210
211# 03C3; 03C2; 03A3; 03A3; FINAL; # GREEK SMALL LETTER SIGMA
212# 03C2; 03C3; 03A3; 03A3; NON_FINAL; # GREEK SMALL LETTER FINAL SIGMA
213
214# ================================================================================
215# Locale-sensitive mappings
216# ================================================================================
217
22d4bb9c 218# Lithuanian
219
2200307; 0307; ; ; lt AFTER_i; # Remove DOT ABOVE after "i" with upper or titlecase
221
c529f79d 222# Turkish
223
22d4bb9c 2240049; 0131; 0049; 0049; tr; # LATIN CAPITAL LETTER I
2250069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
c529f79d 226
227# Note: the following cases are already in the UnicodeData file.
228
22d4bb9c 229# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
230# 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE