sl@0: # SpecialCasing-2.txt sl@0: # sl@0: # Special Casing Properties sl@0: # sl@0: # This file is a supplement to the UnicodeData file. sl@0: # It contains additional information about the casing of Unicode characters. sl@0: # (For compatibility, the UnicodeData.txt file only contains case mappings for sl@0: # characters where they are 1-1, and does not have locale-specific mappings.) sl@0: # These are informative character properties. sl@0: # sl@0: # Send comments to mark@unicode.org sl@0: # sl@0: # ================================================================================ sl@0: # Format sl@0: # ================================================================================ sl@0: # The entries in this file are in the following machine-readable format: sl@0: # sl@0: # := ? (* "#" )? sl@0: # sl@0: # := <sep> <upper> <sep> sl@0: # sl@0: # <source> := <code_point> sl@0: # <sep> := <s>* ";" <s>* sl@0: # <lower> := <code_point_list> sl@0: # <title> := <code_point_list> sl@0: # <upper> := <code_point_list> sl@0: # <code_point_list> := <code_point> (<s>+ <code_point>)* sl@0: # <code_point> := <hex><hex><hex><hex> sl@0: # <hex> := [0-1A-Fa-f] sl@0: # <s> := <space> sl@0: # sl@0: # <condition_list> := <locale>? (<s>+ <context>)* sl@0: # <locale> := <ISO_3166_code> ( "_" <ISO_639_code> )? ( "_" <variant> )? sl@0: # <ISO_3166_code> := 2-letter country code, sl@0: # as in http://www.unicode.org/unicode/onlinedat/countries.html sl@0: # <ISO_639_code> := 2-letter code, sl@0: # as in http://www.unicode.org/unicode/onlinedat/languages.html sl@0: # <context> := "FINAL" | "NON_FINAL" | "MODERN" | "NON_MODERN" sl@0: # sl@0: # A condition list overrides the normal behavior if any of the listed conditions is true. sl@0: # FINAL: The letter is not followed by a letter of category L* (e.g. Ll, Lt, Lu, Lm, or Lo). sl@0: # MODERN: The mapping is only used for modern text. sl@0: # Conditions preceded by "NON_" represent the negation of the condition sl@0: # sl@0: # New contexts may be added in the future. sl@0: # Parsers of this file must be prepared to deal with that situation. sl@0: # Additional whitespace around elements is optional. Blank lines are ignored in parsing. sl@0: # On any line, all text following "#" is a comment, and are ignored in parsing. sl@0: # ================================================================================ sl@0: sl@0: # ================================================================================ sl@0: # Unconditional mappings sl@0: # ================================================================================ sl@0: sl@0: # The German es-zed is special--the normal mapping is to SS. sl@0: # Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>)) sl@0: sl@0: 00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S sl@0: sl@0: # Ligatures sl@0: sl@0: FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF sl@0: FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI sl@0: FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL sl@0: FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI sl@0: FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL sl@0: FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T sl@0: FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST sl@0: sl@0: 0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN sl@0: FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW sl@0: FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH sl@0: FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI sl@0: FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW sl@0: FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH sl@0: sl@0: # No corresponding uppercase precomposed character sl@0: sl@0: 0149; 0149; 02BC 006E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE sl@0: 0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS sl@0: 03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS sl@0: 01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON sl@0: 1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW sl@0: 1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS sl@0: 1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE sl@0: 1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE sl@0: 1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING sl@0: 1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI sl@0: 1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA sl@0: 1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA sl@0: 1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI sl@0: 1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI sl@0: 1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI sl@0: 1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA sl@0: 1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA sl@0: 1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI sl@0: 1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI sl@0: 1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA sl@0: 1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA sl@0: 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI sl@0: 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI sl@0: 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI sl@0: 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI sl@0: sl@0: # IMPORTANT-when capitalizing iota-subscript (0345) sl@0: # It MUST be in normalized form--moved to the end of any sequence of combining marks. sl@0: # This is because logically it represents a following base character! sl@0: # E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript> sl@0: # It should never be the first character in a word, so in titlecasing it can be left as is. sl@0: sl@0: # The following cases are already in the UnicodeData file, so are only commented here. sl@0: sl@0: # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI sl@0: sl@0: # All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript) sl@0: # have special uppercases. sl@0: # Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase! sl@0: sl@0: 1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI sl@0: 1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI sl@0: 1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI sl@0: 1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI sl@0: 1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI sl@0: 1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI sl@0: 1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI sl@0: 1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI sl@0: 1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI sl@0: 1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI sl@0: 1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI sl@0: 1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI sl@0: 1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI sl@0: 1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI sl@0: 1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI sl@0: 1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI sl@0: 1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI sl@0: 1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI sl@0: 1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI sl@0: 1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI sl@0: 1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI sl@0: 1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI sl@0: 1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI sl@0: 1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI sl@0: 1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI sl@0: 1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI sl@0: 1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI sl@0: 1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI sl@0: 1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI sl@0: 1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI sl@0: 1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI sl@0: 1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI sl@0: 1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI sl@0: 1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI sl@0: 1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI sl@0: 1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI sl@0: 1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI sl@0: 1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI sl@0: 1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI sl@0: 1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI sl@0: 1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI sl@0: 1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI sl@0: 1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI sl@0: 1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI sl@0: 1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI sl@0: 1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI sl@0: 1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI sl@0: 1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI sl@0: sl@0: 1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI sl@0: 1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI sl@0: 1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI sl@0: 1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI sl@0: 1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI sl@0: 1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI sl@0: sl@0: # Some characters with YPOGEGRAMMENI are also have no corresponding titlecases sl@0: sl@0: 1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI sl@0: 1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI sl@0: 1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI sl@0: 1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI sl@0: 1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI sl@0: 1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI sl@0: sl@0: 1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI sl@0: 1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI sl@0: 1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI sl@0: sl@0: # ================================================================================ sl@0: # Conditional mappings sl@0: # ================================================================================ sl@0: sl@0: # Special case for final form of sigma sl@0: sl@0: 03A3; 03C2; 03A3; 03A3; FINAL; # GREEK CAPITAL LETTER SIGMA sl@0: sl@0: # Note: the following cases for non-final are already in the UnicodeData file. sl@0: sl@0: # 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA sl@0: # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA sl@0: # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA sl@0: sl@0: # Note: the following cases are not included, since they would normalize in lowercasing sl@0: sl@0: # 03C3; 03C2; 03A3; 03A3; FINAL; # GREEK SMALL LETTER SIGMA sl@0: # 03C2; 03C3; 03A3; 03A3; NON_FINAL; # GREEK SMALL LETTER FINAL SIGMA sl@0: sl@0: # ================================================================================ sl@0: # Locale-sensitive mappings sl@0: # ================================================================================ sl@0: sl@0: # Turkish sl@0: sl@0: 0049; 0131; 0049; 0049; TR; # LATIN CAPITAL LETTER I sl@0: 0069; 0069; 0130; 0130; TR; # LATIN SMALL LETTER I sl@0: sl@0: # Note: the following cases are already in the UnicodeData file. sl@0: sl@0: # 0131; 0131; 0049; 0049; TR; # LATIN SMALL LETTER DOTLESS I sl@0: # 0130; 0069; 0130; 0130; TR; # LATIN CAPITAL LETTER I WITH DOT ABOVE