Updated Unicode-Normalize to CPAN version 1.12

  [DELTA]

  1.12  Mon May 16 23:36:07 2011
    - removed Normalize/CompExcl.pl and Composition Exclusions are coded;
      how to load CompExcl.pl seems not good, but I'm not sure...

  1.11  Sun May 15 20:31:09 2011
    - As perl 5.14.0 has removed unicore/CompositionExclusions.txt
      in the installation, Normalize/CompExcl.pl in this distribution
      is used instead. (see [rt.cpan.org #68106])

5 files changed, 87 insertions, 44 deletions

diff --git a/cpan/Unicode-Normalize/Changes b/cpan/Unicode-Normalize/Changes
index f872619dbc..881fdf6257 100644
--- a/cpan/Unicode-Normalize/Changes
+++ b/cpan/Unicode-Normalize/Changes
@@ -1,5 +1,14 @@
 Revision history for Perl extension Unicode::Normalize.
 
+1.12  Mon May 16 23:36:07 2011
+    - removed Normalize/CompExcl.pl and Composition Exclusions are coded;
+      how to load CompExcl.pl seems not good, but I'm not sure...
+
+1.11  Sun May 15 20:31:09 2011
+    - As perl 5.14.0 has removed unicore/CompositionExclusions.txt
+      in the installation, Normalize/CompExcl.pl in this distribution
+      is used instead. (see [rt.cpan.org #68106])
+
 1.10  Sun Jan 16 21:00:34 2011
     - XSUB: reorder() and compose() treat with growing the string.
     - XSUB: provision against UTF8_ALLOW_* flags to be undefined in future.
diff --git a/cpan/Unicode-Normalize/Normalize.pm b/cpan/Unicode-Normalize/Normalize.pm
index f4bd7a4f1f..3ca56adca5 100644
--- a/cpan/Unicode-Normalize/Normalize.pm
+++ b/cpan/Unicode-Normalize/Normalize.pm
@@ -13,7 +13,7 @@ use Carp;
 
 no warnings 'utf8';
 
-our $VERSION = '1.10';
+our $VERSION = '1.12';
 our $PACKAGE = __PACKAGE__;
 
 our @EXPORT = qw( NFC NFD NFKC NFKD );
@@ -548,8 +548,8 @@ normalization implemented by this module depends on your perl's version.
      5.8.7-5.8.8          4.1.0
        5.10.0             5.0.0
     5.8.9, 5.10.1         5.1.0
-    5.12.0-5.12.2         5.2.0
-   (5.13.7-5.13.11)        6.0.0
+    5.12.0-5.12.3         5.2.0
+       5.14.0             6.0.0
 
 =item Correction of decomposition mapping
 
diff --git a/cpan/Unicode-Normalize/README b/cpan/Unicode-Normalize/README
index 8cddf34869..3fc6c75d18 100644
--- a/cpan/Unicode-Normalize/README
+++ b/cpan/Unicode-Normalize/README
@@ -1,4 +1,4 @@
-Unicode/Normalize version 1.10
+Unicode/Normalize version 1.12
 ===================================
 
 Unicode::Normalize - Unicode Normalization Forms
@@ -62,7 +62,6 @@ which are included in recent perl core distributions.
 
 - unicore/CombiningClass.pl (or unicode/CombiningClass.pl)
 - unicore/Decomposition.pl (or unicode/Decomposition.pl)
-- unicore/CompositionExclusions.txt (or unicode/CompExcl.txt)
 
 NOTES
 
diff --git a/cpan/Unicode-Normalize/mkheader b/cpan/Unicode-Normalize/mkheader
index acc7eaff77..c694b7e9eb 100644
--- a/cpan/Unicode-Normalize/mkheader
+++ b/cpan/Unicode-Normalize/mkheader
@@ -9,7 +9,6 @@
 # Input files:
 #    unicore/CombiningClass.pl (or unicode/CombiningClass.pl)
 #    unicore/Decomposition.pl (or unicode/Decomposition.pl)
-#    unicore/CompositionExclusions.txt (or unicode/CompExcl.txt)
 #
 # Output files:
 #    unfcan.h
@@ -54,7 +53,7 @@ our %Single;	# $codepoint => 1          : singletons
 our %NonStD;	# $codepoint => 1          : non-starter decompositions
 our %Comp2nd;	# $codepoint => 1          : may be composed with a prev char.
 
-# from Unicode database
+# from core Unicode database
 our $Combin = do "unicore/CombiningClass.pl"
     || do "unicode/CombiningClass.pl"
     || croak "$PACKAGE: CombiningClass.pl not found";
@@ -62,6 +61,17 @@ our $Decomp = do "unicore/Decomposition.pl"
     || do "unicode/Decomposition.pl"
     || croak "$PACKAGE: Decomposition.pl not found";
 
+# CompositionExclusions.txt since Unicode 3.2.0
+our @CompEx = qw(
+    0958 0959 095A 095B 095C 095D 095E 095F 09DC 09DD 09DF 0A33 0A36
+    0A59 0A5A 0A5B 0A5E 0B5C 0B5D 0F43 0F4D 0F52 0F57 0F5C 0F69 0F76
+    0F78 0F93 0F9D 0FA2 0FA7 0FAC 0FB9 FB1D FB1F FB2A FB2B FB2C FB2D
+    FB2E FB2F FB30 FB31 FB32 FB33 FB34 FB35 FB36 FB38 FB39 FB3A FB3B
+    FB3C FB3E FB40 FB41 FB43 FB44 FB46 FB47 FB48 FB49 FB4A FB4B FB4C
+    FB4D FB4E 2ADC 1D15E 1D15F 1D160 1D161 1D162 1D163 1D164 1D1BB
+    1D1BC 1D1BD 1D1BE 1D1BF 1D1C0
+);
+
 # definition of Hangul constants
 use constant SBase  => 0xAC00;
 use constant SFinal => 0xD7A3; # SBase -1 + SCount
@@ -91,27 +101,6 @@ sub decomposeHangul {
 }
 
 ########## getting full decomposition ##########
-{
-    my($f, $fh);
-    foreach my $d (@INC) {
-	$f = File::Spec->catfile($d, "unicore", "CompositionExclusions.txt");
-	last if open($fh, $f);
-	$f = File::Spec->catfile($d, "unicore", "CompExcl.txt");
-	last if open($fh, $f);
-	$f = File::Spec->catfile($d, "unicode", "CompExcl.txt");
-	last if open($fh, $f);
-	$f = undef;
-    }
-    croak "$PACKAGE: neither unicore/CompositionExclusions.txt "
-	. "nor unicode/CompExcl.txt is found in @INC" unless defined $f;
-
-    while (<$fh>) {
-	next if /^#/ or /^$/;
-	s/#.*//;
-	$Exclus{ hex($1) } = 1 if /([0-9A-Fa-f]+)/;
-    }
-    close $fh;
-}
 
 ## converts string "hhhh hhhh hhhh" to a numeric list
 ## (hex digits separated by spaces)
@@ -137,23 +126,32 @@ while ($Decomp =~ /(.+)/g) {
 
     foreach my $u ($ini .. $end) {
 	$Compat{$u} = $dec;
+	$Canon{$u} = $dec if ! $compat;
+    }
+}
 
-	if (! $compat) {
-	    $Canon{$u} = $dec;
-
-	    if (@$dec == 2) {
-		if ($Combin{ $dec->[0] }) {
-		    $NonStD{$u} = 1;
-		} else {
-		    $Compos{ $dec->[0] }{ $dec->[1] } = $u;
-		    $Comp2nd{ $dec->[1] } = 1 if ! $Exclus{$u};
-		}
-	    } elsif (@$dec == 1) {
-		$Single{$u} = 1;
-	    } else {
-		croak("Weird Canonical Decomposition of U+$tab[0]");
-	    }
+for my $s (@CompEx) {
+    my $u = hex $s;
+    next if !$Canon{$u}; # not assigned
+    next if $u == 0xFB1D && !$Canon{0x1D15E}; # 3.0.1 before Corrigendum #2
+    $Exclus{$u} = 1;
+}
+
+foreach my $u (keys %Canon) {
+    my $dec = $Canon{$u};
+
+    if (@$dec == 2) {
+	if ($Combin{ $dec->[0] }) {
+	    $NonStD{$u} = 1;
+	} else {
+	    $Compos{ $dec->[0] }{ $dec->[1] } = $u;
+	    $Comp2nd{ $dec->[1] } = 1 if ! $Exclus{$u};
 	}
+    } elsif (@$dec == 1) {
+	$Single{$u} = 1;
+    } else {
+	my $h = sprintf '%04X', $u;
+	croak("Weird Canonical Decomposition of U+$h");
     }
 }
 
diff --git a/cpan/Unicode-Normalize/t/func.t b/cpan/Unicode-Normalize/t/func.t
index 76ced03ea1..f18835ee8a 100644
--- a/cpan/Unicode-Normalize/t/func.t
+++ b/cpan/Unicode-Normalize/t/func.t
@@ -19,7 +19,7 @@ BEGIN {
 use Test;
 use strict;
 use warnings;
-BEGIN { plan tests => 211 };
+BEGIN { plan tests => 217 };
 use Unicode::Normalize qw(:all);
 ok(1); # If we made it this far, we're ok.
 
@@ -49,6 +49,8 @@ ok(getCanon(0x212C), undef);
 ok(getCanon(0x3243), undef);
 ok(getCanon(0xFA2D), _pack_U(0x9DB4));
 
+# 20
+
 ok(getCompat(   0), undef);
 ok(getCompat(0x29), undef);
 ok(getCompat(0x41), undef);
@@ -84,6 +86,8 @@ ok(getComposite(0xAC00, 0x11A7), undef);
 ok(getComposite(0xAC00, 0x11A8), 0xAC01);
 ok(getComposite(0xADF8, 0x11AF), 0xAE00);
 
+# 53
+
 sub uprops {
   my $uv = shift;
   my $r = "";
@@ -120,6 +124,8 @@ ok(uprops(0xF900), 'xSnFbDmCKyG'); # CJK COMPATIBILITY IDEOGRAPH-F900
 ok(uprops(0xFB4E), 'XsnFbDmCKyG'); # HEBREW LETTER PE WITH RAFE
 ok(uprops(0xFF71), 'xsnfbdmcKyG'); # HALFWIDTH KATAKANA LETTER A
 
+# 71
+
 ok(decompose(""), "");
 ok(decompose("A"), "A");
 ok(decompose("", 1), "");
@@ -133,6 +139,8 @@ ok(decompose(hexU("1E14 AC01"), 1), hexU("0045 0304 0300 1100 1161 11A8"));
 ok(decompose(hexU("AC00 AE00"), 1), hexU("1100 1161 1100 1173 11AF"));
 ok(decompose(hexU("304C FF76"), 1), hexU("304B 3099 30AB"));
 
+# 81
+
 # don't modify the source
 my $sDec = "\x{FA19}";
 ok(decompose($sDec), "\x{795E}");
@@ -165,6 +173,8 @@ my $sCom = "\x{304B}\x{3099}";
 ok(compose($sCom), "\x{304C}");
 ok($sCom, "\x{304B}\x{3099}");
 
+# 100
+
 ok(composeContiguous(""), "");
 ok(composeContiguous("A"), "A");
 ok(composeContiguous(hexU("0061 0300")),      hexU("00E0"));
@@ -180,6 +190,8 @@ my $sCtg = "\x{30DB}\x{309A}";
 ok(composeContiguous($sCtg), "\x{30DD}");
 ok($sCtg, "\x{30DB}\x{309A}");
 
+# 111
+
 sub answer { defined $_[0] ? $_[0] ? "YES" : "NO" : "MAYBE" }
 
 ok(answer(checkNFD("")),  "YES");
@@ -220,6 +232,8 @@ ok(answer(checkNFKC(hexU("0041 0327 030A"))), "MAYBE"); # A+cedilla+ring
 ok(answer(checkNFKC(hexU("0041 030A 0327"))), "NO");    # A+ring+cedilla
 ok(answer(check("NFKC", hexU("20 C1 212B 300"))), "NO");
 
+# 145
+
 "012ABC" =~ /(\d+)(\w+)/;
 ok("012" eq NFC $1 && "ABC" eq NFC $2);
 
@@ -240,6 +254,8 @@ ok(getComposite("065", "0768"), 192);
 ok(isNFD_NO ("0192"));
 ok(isNFKD_NO("0192"));
 
+# 156
+
 # DEVANAGARI LETTER QA
 ok(isExclusion("02392"));
 ok(isComp_Ex  ("02392"));
@@ -276,6 +292,8 @@ ok(getCanon("044032"),  _pack_U(0x1100, 0x1161));
 ok(getCompat("044032"), _pack_U(0x1100, 0x1161));
 ok(getComposite("04352", "04449"), 0xAC00);
 
+# 182
+
 # string with 22 combining characters: (0x300..0x315)
 my $str_cc22 = _pack_U(0x3041, 0x300..0x315, 0x3042);
 ok(decompose($str_cc22), $str_cc22);
@@ -302,6 +320,8 @@ ok(NFKC($str_cc40), $str_cc40);
 ok(FCD($str_cc40), $str_cc40);
 ok(FCC($str_cc40), $str_cc40);
 
+# 202
+
 my $precomp = hexU("304C 304E 3050 3052 3054");
 my $combseq = hexU("304B 3099 304D 3099 304F 3099 3051 3099 3053 3099");
 ok(decompose($precomp x 5),  $combseq x 5);
@@ -319,4 +339,21 @@ ok(decompose($precomp . $notcomp),     $combseq . $notcomp);
 ok(decompose($precomp . $notcomp x 5), $combseq . $notcomp x 5);
 ok(decompose($precomp . $notcomp x10), $combseq . $notcomp x10);
 
+# 211
+
+my $preUnicode3_1 = !defined getCanon(0x1D15E);
+my $preUnicode3_2 = !defined getCanon(0x2ADC);
+
+# HEBREW LETTER YOD WITH HIRIQ
+ok($preUnicode3_1 xor isExclusion(0xFB1D));
+ok($preUnicode3_1 xor isComp_Ex  (0xFB1D));
+
+# MUSICAL SYMBOL HALF NOTE
+ok($preUnicode3_1 xor isExclusion(0x1D15E));
+ok($preUnicode3_1 xor isComp_Ex  (0x1D15E));
+
+# FORKING
+ok($preUnicode3_2 xor isExclusion(0x2ADC));
+ok($preUnicode3_2 xor isComp_Ex  (0x2ADC));
 
+# 217