Upgrade to CPAN-1.88_53.

[p5sagit/p5-mst-13.2.git] / lib / unicore / SpecialCasing.txt

diff --git a/lib/unicore/SpecialCasing.txt b/lib/unicore/SpecialCasing.txt
index f25ac9b..4bfe148 100644 (file)
--- a/lib/unicore/SpecialCasing.txt
+++ b/lib/unicore/SpecialCasing.txt
@@ -1,5 +1,10 @@
-# SpecialCasing-3.2.0.txt
-# Date: 2002-03-19,23:31:42 GMT [MD]
+# SpecialCasing-5.0.0.txt
+# Date: 2006-03-03, 08:23:36 GMT [MD]
+#
+# Unicode Character Database
+# Copyright (c) 1991-2006 Unicode, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For documentation, see UCD.html
 #
 # Special Casing Properties
 #
@@ -7,9 +12,10 @@
 # It contains additional information about the casing of Unicode characters.
 # (For compatibility, the UnicodeData.txt file only contains case mappings for
 # characters where they are 1-1, and does not have locale-specific mappings.)
-# For more information, see
-# UTR #21 Case Mappings, at http://www.unicode.org/unicode/reports/tr21/
+# For more information, see the discussion of Case Mappings in the Unicode Standard.
 #
+# All code points not listed in this file that do not have a simple case mappings
+# in UnicodeData.txt map to themselves.
 # ================================================================================
 # Format
 # ================================================================================
@@ -17,27 +23,27 @@
 #
 # <code>; <lower> ; <title> ; <upper> ; (<condition_list> ;)? # <comment>
 #
-# <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more than
-# one character, they are separated by spaces. Other than as used to separate elements,
-# spaces are to be ignored.
+# <code>, <lower>, <title>, and <upper> provide character values in hex. If there is more
+# than one character, they are separated by spaces. Other than as used to separate 
+# elements, spaces are to be ignored.
 #
-# The <condition_list> is optional. Where present, it consists of one or more locales or contexts,
-# separated by spaces. In these conditions:
+# The <condition_list> is optional. Where present, it consists of one or more locale IDs
+# or contexts, separated by spaces. In these conditions:
 # - A condition list overrides the normal behavior if all of the listed conditions are true.
 # - The context is always the context of the characters in the original string,
 #   NOT in the resulting string.
 # - Case distinctions in the condition list are not significant.
 # - Conditions preceded by "Not_" represent the negation of the condition.
 #
-# A locale is defined as:
-# <locale> := <ISO_639_code> ( "_" <ISO_3166_code> ( "_" <variant> )? )?
-# <ISO_3166_code> := 2-letter ISO country code,
-# <ISO_639_code> :=  2-letter ISO language code
+# A locale ID is defined by taking any language tag as defined by
+# RFC 3066 (or its successor), and replacing '-' by '_'.
 #
-# A context is one of the following, as defined in UAX #21: Case Mappings:
-#   Final_Sigma, After_Soft_Dotted, More_Above, Before_Dot
+# A context for a character C is defined by Section 3.13 Default Case 
+# Operations, of The Unicode Standard, Version 5.0.
+# (This is identical to the context defined by Unicode 4.1.0,
+#  as specified in http://www.unicode.org/versions/Unicode4.1.0/)
 #
-# Parsers of this file must be prepared to deal future additions to this format:
+# Parsers of this file must be prepared to deal with future additions to this format:
 #  * Additional contexts
 #  * Additional fields
 # ================================================================================
@@ -169,7 +175,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
 1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
 1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
 
-# Some characters with YPOGEGRAMMENI are also have no corresponding titlecases
+# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
 
 1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
 1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
@@ -231,14 +237,14 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
 # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
 # The following rules handle those cases.
 
-0130; 0069; 0130; 0130; tr # LATIN CAPITAL LETTER I WITH DOT ABOVE
-0130; 0069; 0130; 0130; az # LATIN CAPITAL LETTER I WITH DOT ABOVE
+0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
 
 # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
 # This matches the behavior of the canonically equivalent I-dot_above
 
-0307; ; 0307; 0307; tr After_Soft_Dotted; # COMBINING DOT ABOVE
-0307; ; 0307; 0307; az After_Soft_Dotted; # COMBINING DOT ABOVE
+0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
+0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
 
 # When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
 
@@ -253,3 +259,6 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
 # Note: the following case is already in the UnicodeData file.
 
 # 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
+
+# EOF
+