localisation/localesupport/OtherTools/SpecialCasing-2.txt
branchanywhere
changeset 41 d32f34975bbf
parent 40 04a1b74efd48
parent 37 a9bf1d2c555e
child 48 10816385149a
equal deleted inserted replaced
40:04a1b74efd48 41:d32f34975bbf
     1 # SpecialCasing-2.txt
       
     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>
       
    29 # <hex> := [0-1A-Fa-f]
       
    30 # <s> := <space>
       
    31 #
       
    32 # <condition_list> := <locale>? (<s>+ <context>)*
       
    33 # <locale> := <ISO_3166_code> ( "_" <ISO_639_code> )? ( "_" <variant> )?
       
    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
       
    38 # <context> := "FINAL" | "NON_FINAL" | "MODERN" | "NON_MODERN"
       
    39 #
       
    40 #  A condition list overrides the normal behavior if any of the listed conditions is true.
       
    41 #   FINAL:  The letter is not followed by a letter of category L* (e.g. Ll, Lt, Lu, Lm, or Lo).
       
    42 #   MODERN: The mapping is only used for modern text.
       
    43 #  Conditions preceded by "NON_" represent the negation of the condition
       
    44 #
       
    45 # New contexts may be added in the future.
       
    46 # Parsers of this file must be prepared to deal with that situation.
       
    47 # Additional whitespace around elements is optional. Blank lines are ignored in parsing.
       
    48 # On any line, all text following "#" is a comment, and are ignored in parsing.
       
    49 # ================================================================================
       
    50 
       
    51 # ================================================================================
       
    52 # Unconditional mappings
       
    53 # ================================================================================
       
    54 
       
    55 # The German es-zed is special--the normal mapping is to SS.
       
    56 # Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
       
    57 
       
    58 00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
       
    59 
       
    60 # Ligatures
       
    61 
       
    62 FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
       
    63 FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
       
    64 FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
       
    65 FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
       
    66 FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
       
    67 FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
       
    68 FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
       
    69 
       
    70 0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
       
    71 FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
       
    72 FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
       
    73 FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
       
    74 FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
       
    75 FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
       
    76 
       
    77 # No corresponding uppercase precomposed character
       
    78 
       
    79 0149; 0149; 02BC 006E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
       
    80 0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
       
    81 03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
       
    82 01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
       
    83 1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
       
    84 1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
       
    85 1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
       
    86 1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
       
    87 1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
       
    88 1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
       
    89 1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
       
    90 1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
       
    91 1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
       
    92 1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
       
    93 1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
       
    94 1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
       
    95 1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
       
    96 1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
       
    97 1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
       
    98 1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
       
    99 1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
       
   100 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
       
   101 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
       
   102 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
       
   103 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
       
   104 
       
   105 # IMPORTANT-when capitalizing iota-subscript (0345)
       
   106 #  It MUST be in normalized form--moved to the end of any sequence of combining marks.
       
   107 #  This is because logically it represents a following base character!
       
   108 #  E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript>
       
   109 # It should never be the first character in a word, so in titlecasing it can be left as is.
       
   110 
       
   111 # The following cases are already in the UnicodeData file, so are only commented here.
       
   112 
       
   113 # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
       
   114 
       
   115 # All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
       
   116 # have special uppercases.
       
   117 # Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
       
   118 
       
   119 1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
       
   120 1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
       
   121 1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
       
   122 1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
       
   123 1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
       
   124 1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
       
   125 1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
       
   126 1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
       
   127 1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
       
   128 1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
       
   129 1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
       
   130 1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
       
   131 1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
       
   132 1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
       
   133 1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
       
   134 1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
       
   135 1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
       
   136 1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
       
   137 1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
       
   138 1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
       
   139 1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
       
   140 1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
       
   141 1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
       
   142 1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
       
   143 1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
       
   144 1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
       
   145 1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
       
   146 1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
       
   147 1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
       
   148 1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
       
   149 1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
       
   150 1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
       
   151 1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
       
   152 1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
       
   153 1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
       
   154 1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
       
   155 1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
       
   156 1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
       
   157 1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
       
   158 1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
       
   159 1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
       
   160 1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
       
   161 1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
       
   162 1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
       
   163 1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
       
   164 1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
       
   165 1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
       
   166 1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
       
   167 
       
   168 1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
       
   169 1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
       
   170 1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
       
   171 1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
       
   172 1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
       
   173 1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
       
   174 
       
   175 # Some characters with YPOGEGRAMMENI are also have no corresponding titlecases
       
   176 
       
   177 1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
       
   178 1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
       
   179 1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
       
   180 1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
       
   181 1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
       
   182 1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
       
   183 
       
   184 1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
       
   185 1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
       
   186 1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
       
   187 
       
   188 # ================================================================================
       
   189 # Conditional mappings
       
   190 # ================================================================================
       
   191 
       
   192 # Special case for final form of sigma
       
   193 
       
   194 03A3; 03C2; 03A3; 03A3; FINAL; # GREEK CAPITAL LETTER SIGMA
       
   195 
       
   196 # Note: the following cases for non-final are already in the UnicodeData file.
       
   197 
       
   198 # 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
       
   199 # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
       
   200 # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
       
   201 
       
   202 # Note: the following cases are not included, since they would normalize in lowercasing
       
   203 
       
   204 # 03C3; 03C2; 03A3; 03A3; FINAL; # GREEK SMALL LETTER SIGMA
       
   205 # 03C2; 03C3; 03A3; 03A3; NON_FINAL; # GREEK SMALL LETTER FINAL SIGMA
       
   206 
       
   207 # ================================================================================
       
   208 # Locale-sensitive mappings
       
   209 # ================================================================================
       
   210 
       
   211 # Turkish
       
   212 
       
   213 0049; 0131; 0049; 0049; TR; # LATIN CAPITAL LETTER I
       
   214 0069; 0069; 0130; 0130; TR; # LATIN SMALL LETTER I
       
   215 
       
   216 # Note: the following cases are already in the UnicodeData file.
       
   217 
       
   218 # 0131; 0131; 0049; 0049; TR; # LATIN SMALL LETTER DOTLESS I
       
   219 # 0130; 0069; 0130; 0130; TR; # LATIN CAPITAL LETTER I WITH DOT ABOVE