1 # SpecialCasing-5.1.0.txt |
1 # SpecialCasing-6.0.0.txt |
2 # Date: 2008-03-03, 21:58:10 GMT [MD] |
2 # Date: 2010-05-18, 00:49:39 GMT [MD] |
3 # |
3 # |
4 # Unicode Character Database |
4 # Unicode Character Database |
5 # Copyright (c) 1991-2008 Unicode, Inc. |
5 # Copyright (c) 1991-2010 Unicode, Inc. |
6 # For terms of use, see http://www.unicode.org/terms_of_use.html |
6 # For terms of use, see http://www.unicode.org/terms_of_use.html |
7 # For documentation, see UCD.html |
7 # For documentation, see http://www.unicode.org/reports/tr44/ |
8 # |
8 # |
9 # Special Casing Properties |
9 # Special Casing Properties |
10 # |
10 # |
11 # This file is a supplement to the UnicodeData file. |
11 # This file is a supplement to the UnicodeData file. |
12 # It contains additional information about the casing of Unicode characters. |
12 # It contains additional information about the casing of Unicode characters. |
104 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI |
104 1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI |
105 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI |
105 1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI |
106 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI |
106 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI |
107 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI |
107 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI |
108 |
108 |
109 # IMPORTANT-when capitalizing iota-subscript (0345) |
109 # IMPORTANT-when iota-subscript (0345) is uppercased or titlecased, |
110 # It MUST be in normalized form--moved to the end of any sequence of combining marks. |
110 # the result will be incorrect unless the iota-subscript is moved to the end |
111 # This is because logically it represents a following base character! |
111 # of any sequence of combining marks. Otherwise, the accents will go on the capital iota. |
112 # E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript> |
112 # This process can be achieved by first transforming the text to NFC before casing. |
113 # It should never be the first character in a word, so in titlecasing it can be left as is. |
113 # E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA> |
114 |
114 |
115 # The following cases are already in the UnicodeData file, so are only commented here. |
115 # The following cases are already in the UnicodeData file, so are only commented here. |
116 |
116 |
117 # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI |
117 # 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI |
118 |
118 |