diff options
Diffstat (limited to 'lib/unicore/SpecialCasing.txt')
| -rw-r--r-- | lib/unicore/SpecialCasing.txt | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/lib/unicore/SpecialCasing.txt b/lib/unicore/SpecialCasing.txt index 92e70a4a3d..1dba776cb5 100644 --- a/lib/unicore/SpecialCasing.txt +++ b/lib/unicore/SpecialCasing.txt @@ -1,10 +1,10 @@ -# SpecialCasing-5.1.0.txt -# Date: 2008-03-03, 21:58:10 GMT [MD] +# SpecialCasing-5.2.0.txt +# Date: 2009-09-22, 23:25:59 GMT [MD] # # Unicode Character Database -# Copyright (c) 1991-2008 Unicode, Inc. +# Copyright (c) 1991-2009 Unicode, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see UCD.html +# For documentation, see http://www.unicode.org/reports/tr44/ # # Special Casing Properties # @@ -106,11 +106,11 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH 1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI 1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI -# IMPORTANT-when capitalizing iota-subscript (0345) -# It MUST be in normalized form--moved to the end of any sequence of combining marks. -# This is because logically it represents a following base character! -# E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript> -# It should never be the first character in a word, so in titlecasing it can be left as is. +# IMPORTANT-when iota-subscript (0345) is uppercased or titlecased, +# the result will be incorrect unless the iota-subscript is moved to the end +# of any sequence of combining marks. Otherwise, the accents will go on the capital iota. +# This process can be achieved by first transforming the text to NFC before casing. +# E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA> # The following cases are already in the UnicodeData file, so are only commented here. |