Unicode 6.1

This commit delivers the official Unicode character database files for
release 6.1, plus the final bits needed to cope with the changes in them
from release 6.0, including documentation.

Author: Karl Williamson

l1_char_class_tab.h

@@ -172,7 +172,7 @@
 /* U+A4 CURRENCY SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
 /* U+A5 YEN SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
 /* U+A6 BROKEN BAR */ _CC_GRAPH_L1|_CC_PRINT_L1,
-/* U+A7 SECTION SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
+/* U+A7 SECTION SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1|_CC_PUNCT_L1,
 /* U+A8 DIAERESIS */ _CC_GRAPH_L1|_CC_PRINT_L1,
 /* U+A9 COPYRIGHT SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
 /* U+AA FEMININE ORDINAL INDICATOR */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
@@ -187,7 +187,7 @@
 /* U+B3 SUPERSCRIPT THREE */ _CC_GRAPH_L1|_CC_PRINT_L1,
 /* U+B4 ACUTE ACCENT */ _CC_GRAPH_L1|_CC_PRINT_L1,
 /* U+B5 MICRO SIGN */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+B6 PILCROW SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
+/* U+B6 PILCROW SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1|_CC_PUNCT_L1,
 /* U+B7 MIDDLE DOT */ _CC_GRAPH_L1|_CC_PRINT_L1|_CC_PUNCT_L1,
 /* U+B8 CEDILLA */ _CC_GRAPH_L1|_CC_PRINT_L1,
 /* U+B9 SUPERSCRIPT ONE */ _CC_GRAPH_L1|_CC_PRINT_L1,

lib/Unicode/UCD.pm

@@ -2252,20 +2252,56 @@ Devanagari, Gurmukhi, and Oriya  scripts.
 
 The Name_Alias property is of this form.  But each scalar consists of two
 components:  1) the name, and 2) the type of alias this is.  They are
-separated by a colon and a space.  In Unicode 6.0, there are two alias types:
-C<"correction">, which indicates that the name is a corrected form for the
-original name (which remains valid) for the same code point; and C<"control">,
-which adds a new name for a control character.
+separated by a colon and a space.  In Unicode 6.1, there are several alias types:
+
+=over
+
+=item C<correction>
+
+indicates that the name is a corrected form for the
+original name (which remains valid) for the same code point.
+
+=item C<control>
+
+adds a new name for a control character.
+
+=item C<alternate>
+
+is an alternate name for a character
+
+=item C<figment>
+
+is a name for a character that has been documented but was never in any
+actual standard.
+
+=item C<abbreviation>
+
+is a common abbreviation for a character
+
+=back
+
+The lists are ordered (roughly) so the most preferred names come before less
+preferred ones.
 
 For example,
 
- @aliases_ranges  @alias_maps
+ @aliases_ranges        @alias_maps
+    ...
+    0x009E        [ 'PRIVACY MESSAGE: control', 'PM: abbreviation' ]
+    0x009F        [ 'APPLICATION PROGRAM COMMAND: control',
+                    'APC: abbreviation'
+                  ]
+    0x00A0        'NBSP: abbreviation'
+    0x00A1        ""
+    0x00AD        'SHY: abbreviation'
+    0x00AE        ""
+    0x01A2        'LATIN CAPITAL LETTER GHA: correction'
+    0x01A3        'LATIN SMALL LETTER GHA: correction'
+    0x01A4        ""
     ...
-    0x01A2        LATIN CAPITAL LETTER GHA: correction
-    0x01A3        LATIN SMALL LETTER GHA: correction
 
-Unicode 6.1 will introduce other types, and some map entries will be lists of
-multiple name-alias pairs for a single code point.
+A map to the empty string means that there is no alias defined for the code
+point.
 
 =item C<r>
 
@@ -2409,7 +2445,9 @@ the function L<charnames/charnames::viacode(code)>.
 
 Note that for control characters (C<Gc=cc>), Unicode's data files have the
 string "C<E<lt>controlE<gt>>", but the real name of each of these characters is the empty
-string.  This function returns that real name, the empty string.
+string.  This function returns that real name, the empty string.  (There are
+names for these characters, but they are aliases, not the real name, and are
+contained in the C<Name_Alias> property.)
 
 =item C<d>
 
@@ -3179,6 +3217,9 @@ To convert from new-style to old-style, follow this recipe:
 gets the lower end of the range (0th element) and then looks up the old name
 for its block using C<charblock>).
 
+Note that starting in Unicode 6.1, many of the block names have shorter
+synonyms.  These are always given in the new style.
+
 =head1 BUGS
 
 Does not yet support EBCDIC platforms.

lib/Unicode/UCD.t

@@ -342,7 +342,7 @@ is($bt->{AL}, 'Right-to-Left Arabic', 'AL is Right-to-Left Arabic');
 
 # If this fails, then maybe one should look at the Unicode changes to see
 # what else might need to be updated.
-is(Unicode::UCD::UnicodeVersion, '6.0.0', 'UnicodeVersion');
+is(Unicode::UCD::UnicodeVersion, '6.1.0', 'UnicodeVersion');
 
 use Unicode::UCD qw(compexcl);
 
@@ -470,7 +470,7 @@ is(Unicode::UCD::_getcode('U+123x'),  undef, "_getcode(x123)");
 {
     my $r1 = charscript('Latin');
     my $n1 = @$r1;
-    is($n1, 30, "number of ranges in Latin script (Unicode 6.0.0)");
+    is($n1, 30, "number of ranges in Latin script (Unicode 6.1.0)");
     shift @$r1 while @$r1;
     my $r2 = charscript('Latin');
     is(@$r2, $n1, "modifying results should not mess up internal caches");