SpecialCasing.txt revision 8845:4be14673b9bf
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 6000DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S 61 62# Preserve canonical equivalence for I with dot. Turkic is handled below. 63 640130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE 65 66# Ligatures 67 68FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF 69FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI 70FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL 71FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI 72FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL 73FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T 74FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST 75 760587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN 77FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW 78FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH 79FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI 80FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW 81FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH 82 83# No corresponding uppercase precomposed character 84 850149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE 860390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS 8703B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS 8801F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON 891E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW 901E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS 911E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE 921E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE 931E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING 941F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI 951F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA 961F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA 971F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI 981FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI 991FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI 1001FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA 1011FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA 1021FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI 1031FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI 1041FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA 1051FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA 1061FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI 1071FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI 1081FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI 1091FF6; 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 1251F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI 1261F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI 1271F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI 1281F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI 1291F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI 1301F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI 1311F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI 1321F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI 1331F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI 1341F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI 1351F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI 1361F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI 1371F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI 1381F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI 1391F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI 1401F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI 1411F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI 1421F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI 1431F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI 1441F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI 1451F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI 1461F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI 1471F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI 1481F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI 1491F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI 1501F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI 1511F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI 1521F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI 1531F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI 1541F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI 1551F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI 1561F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI 1571FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI 1581FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI 1591FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI 1601FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI 1611FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI 1621FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI 1631FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI 1641FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI 1651FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI 1661FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI 1671FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI 1681FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI 1691FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI 1701FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI 1711FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI 1721FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI 1731FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI 1741FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI 1751FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI 1761FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI 1771FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI 1781FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI 179 180# Some characters with YPOGEGRAMMENI also have no corresponding titlecases 181 1821FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI 1831FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI 1841FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI 1851FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI 1861FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI 1871FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI 188 1891FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI 1901FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI 1911FF7; 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 20603A3; 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. 229 230# Remove DOT ABOVE after "i" with upper or titlecase 231 2320307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE 233 234# Introduce an explicit dot above when lowercasing capital I's and J's 235# whenever there are more accents above. 236# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek) 237 2380049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I 239004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J 240012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK 24100CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE 24200CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE 2430128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE 244 245# ================================================================================ 246 247# Turkish and Azeri 248 249# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri 250# The following rules handle those cases. 251 2520130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE 2530130; 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 2580307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE 2590307; ; 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 2630049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I 2640049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I 265 266# When uppercasing, i turns into a dotted capital I 267 2680069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I 2690069; 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 276 277