Update Unicode-Collate to CPAN version 0.97

  [DELTA]

  0.97  Sat Dec 22 14:25:50 2012
    - bug fix: XS of 0.96 (if UCA_Version is 9 to 11) wrongly referred to
      DUCET for completely ignorable characters, even though the collator
      don't use DUCET.
    - separated t/notable.t from t/test.t.

5 files changed, 174 insertions, 104 deletions

diff --git a/cpan/Unicode-Collate/Changes b/cpan/Unicode-Collate/Changes
index faaa985361..9fc2dc26c4 100644
--- a/cpan/Unicode-Collate/Changes
+++ b/cpan/Unicode-Collate/Changes
@@ -1,5 +1,11 @@
 Revision history for Perl module Unicode::Collate.
 
+0.97  Sat Dec 22 14:25:50 2012
+    - bug fix: XS of 0.96 (if UCA_Version is 9 to 11) wrongly referred to
+      DUCET for completely ignorable characters, even though the collator
+      don't use DUCET.
+    - separated t/notable.t from t/test.t.
+
 0.96  Sat Dec 15 19:43:10 2012
     - special noncharancter tailorings ('highestFFFF' and 'minimalFFFE')
       * some locales are modified for 'highestFFFF': as, bn, fa, gu, hi, hy,
diff --git a/cpan/Unicode-Collate/Collate.pm b/cpan/Unicode-Collate/Collate.pm
index 3085094472..4a1c837ab6 100644
--- a/cpan/Unicode-Collate/Collate.pm
+++ b/cpan/Unicode-Collate/Collate.pm
@@ -14,7 +14,7 @@ use File::Spec;
 
 no warnings 'utf8';
 
-our $VERSION = '0.96';
+our $VERSION = '0.97';
 our $PACKAGE = __PACKAGE__;
 
 ### begin XS only ###
@@ -502,7 +502,7 @@ sub splitEnt
 	} elsif ($ver9) {
 	    $src[$i] = undef if $map->{ $src[$i] }
 			   ? @{ $map->{ $src[$i] } } == 0
-			   : _ignorable_simple($src[$i]); ### XS only
+			   : $uXS && _ignorable_simple($src[$i]); ### XS only
 	}
     }
 
@@ -1217,7 +1217,7 @@ next to C<c>. For a certain language where C<ch> as the next letter,
 C<"abch"> is greater than C<"abc\x{FFFF}">, but lesser than C<"abd">.
 
 Note: This is equivalent to C<entry =E<gt> 'FFFF ; [.FFFE.0020.0005.FFFF]'>.
-C<entry> allows tailoring of any other character than U+FFFF.
+Any other character than C<U+FFFF> can be tailored by C<entry>.
 
 =item identical
 
@@ -1326,7 +1326,7 @@ then C<$a2> and C<$b2> at level 1, as followed.
         "bbb\x{FFFE}a"
 
 Note: This is equivalent to C<entry =E<gt> 'FFFE ; [.0001.0020.0005.FFFE]'>.
-C<entry> allows tailoring of any other character than U+FFFE.
+Any other character than C<U+FFFE> can be tailored by C<entry>.
 
 =item normalization
 
diff --git a/cpan/Unicode-Collate/README b/cpan/Unicode-Collate/README
index 3ec9dbc50b..fdd837b983 100644
--- a/cpan/Unicode-Collate/README
+++ b/cpan/Unicode-Collate/README
@@ -1,4 +1,4 @@
-Unicode/Collate version 0.96
+Unicode/Collate version 0.97
 ===============================
 
 NAME
diff --git a/cpan/Unicode-Collate/t/notable.t b/cpan/Unicode-Collate/t/notable.t
new file mode 100644
index 0000000000..124351760f
--- /dev/null
+++ b/cpan/Unicode-Collate/t/notable.t
@@ -0,0 +1,140 @@
+
+BEGIN {
+    unless ("A" eq pack('U', 0x41)) {
+	print "1..0 # Unicode::Collate " .
+	    "cannot stringify a Unicode code point\n";
+	exit 0;
+    }
+    if ($ENV{PERL_CORE}) {
+	chdir('t') if -d 't';
+	@INC = $^O eq 'MacOS' ? qw(::lib) : qw(../lib);
+    }
+}
+
+use strict;
+use warnings;
+BEGIN { $| = 1; print "1..32\n"; }
+my $count = 0;
+sub ok ($;$) {
+    my $p = my $r = shift;
+    if (@_) {
+	my $x = shift;
+	$p = !defined $x ? !defined $r : !defined $r ? 0 : $r eq $x;
+    }
+    print $p ? "ok" : "not ok", ' ', ++$count, "\n";
+}
+
+use Unicode::Collate;
+
+ok(1);
+
+#########################
+
+{
+    # Table is undefined, then no entry is defined.
+    my $undef_table = Unicode::Collate->new(
+	table => undef,
+	normalization => undef,
+	level => 1,
+    );
+
+    # in the Unicode code point order
+    ok($undef_table->lt('', 'A'));
+    ok($undef_table->lt('ABC', 'B'));
+
+    # Hangul should be decomposed (even w/o Unicode::Normalize).
+    ok($undef_table->lt("Perl", "\x{AC00}"));
+    ok($undef_table->eq("\x{AC00}", "\x{1100}\x{1161}"));
+    ok($undef_table->eq("\x{AE00}", "\x{1100}\x{1173}\x{11AF}"));
+    ok($undef_table->lt("\x{AE00}", "\x{3042}"));
+
+    # U+AC00: Hangul GA
+    # U+AE00: Hangul GEUL
+    # U+3042: Hiragana A
+
+    # Weight for CJK Ideographs is defined, though.
+    ok($undef_table->lt("", "\x{4E00}"));
+    ok($undef_table->lt("\x{4E8C}","ABC"));
+    ok($undef_table->lt("\x{4E00}","\x{3042}"));
+    ok($undef_table->lt("\x{4E00}","\x{4E8C}"));
+
+# 11
+
+    # U+4E00: Ideograph "ONE"
+    # U+4E8C: Ideograph "TWO"
+
+    for my $v ('', 8, 9, 11, 14) {
+	$undef_table->change(UCA_Version => $v) if $v;
+	ok($undef_table->lt("\x{4E00}","\0"));
+    }
+}
+
+# 16
+
+{
+    my $onlyABC = Unicode::Collate->new(
+	table => undef,
+	normalization => undef,
+	entry => << 'ENTRIES',
+0061 ; [.0101.0020.0002.0061] # LATIN SMALL LETTER A
+0041 ; [.0101.0020.0008.0041] # LATIN CAPITAL LETTER A
+0062 ; [.0102.0020.0002.0062] # LATIN SMALL LETTER B
+0042 ; [.0102.0020.0008.0042] # LATIN CAPITAL LETTER B
+0063 ; [.0103.0020.0002.0063] # LATIN SMALL LETTER C
+0043 ; [.0103.0020.0008.0043] # LATIN CAPITAL LETTER C
+ENTRIES
+    );
+    ok(
+	join(':', $onlyABC->sort( qw/ ABA BAC cc A Ab cAc aB / ) ),
+	join(':',                 qw/ A aB Ab ABA BAC cAc cc / ),
+    );
+}
+
+# 17
+
+{
+    my $few_entries = Unicode::Collate->new(
+	entry => <<'ENTRIES',
+0050 ; [.0101.0020.0002.0050]  # P
+0045 ; [.0102.0020.0002.0045]  # E
+0052 ; [.0103.0020.0002.0052]  # R
+004C ; [.0104.0020.0002.004C]  # L
+1100 ; [.0105.0020.0002.1100]  # Hangul Jamo initial G
+1175 ; [.0106.0020.0002.1175]  # Hangul Jamo middle I
+5B57 ; [.0107.0020.0002.5B57]  # CJK Ideograph "Letter"
+ENTRIES
+	table => undef,
+	normalization => undef,
+    );
+    # defined before undefined
+    my $sortABC = join '',
+	$few_entries->sort(split //, "ABCDEFGHIJKLMNOPQRSTUVWXYZ ");
+
+    ok($sortABC eq "PERL ABCDFGHIJKMNOQSTUVWXYZ");
+
+    ok($few_entries->lt('E', 'D'));
+    ok($few_entries->lt("\x{5B57}", "\x{4E00}"));
+    ok($few_entries->lt("\x{AE30}", "\x{AC00}"));
+
+    # Hangul must be decomposed.
+    ok($few_entries->eq("\x{AC00}", "\x{1100}\x{1161}"));
+}
+
+# 22
+
+{
+    my $highestNUL = Unicode::Collate->new(
+	table => undef,
+	normalization => undef,
+	level => 1,
+	entry => '0000 ; [.FFFE.0020.0005.0000]',
+    );
+
+    for my $v ('', 8, 9, 11, 14) {
+	$highestNUL->change(UCA_Version => $v) if $v;
+	ok($highestNUL->lt("abc\x{4E00}", "abc\0"));
+	ok($highestNUL->lt("abc\x{E0000}","abc\0"));
+    }
+}
+
+# 32
diff --git a/cpan/Unicode-Collate/t/test.t b/cpan/Unicode-Collate/t/test.t
index 552440f919..00feeadad9 100644
--- a/cpan/Unicode-Collate/t/test.t
+++ b/cpan/Unicode-Collate/t/test.t
@@ -13,7 +13,7 @@ BEGIN {
 
 use strict;
 use warnings;
-BEGIN { $| = 1; print "1..112\n"; }
+BEGIN { $| = 1; print "1..96\n"; }
 my $count = 0;
 sub ok ($;$) {
     my $p = my $r = shift;
@@ -40,7 +40,7 @@ my $acute   = _pack_U(0x0301);
 my $hiragana = "\x{3042}\x{3044}";
 my $katakana = "\x{30A2}\x{30A4}";
 
-##### 2..7
+# 1
 
 my $Collator = Unicode::Collate->new(
   table => 'keys.txt',
@@ -63,7 +63,7 @@ ok(
   join(':',                  qw/ ACA ACHA ACIA ACKA ADA / ),
 );
 
-##### 8..18
+# 7
 
 ok($Collator->cmp("A$acute", $A_acute), 0); # @version 3.1.1 (prev: -1)
 ok($Collator->cmp($a_acute, $A_acute), -1);
@@ -81,7 +81,7 @@ ok($Collator->lt("A", $A_acute));
 ok($Collator->lt("A", $a_acute));
 ok($Collator->lt($a_acute, $A_acute));
 
-##### 19..25
+# 18
 
 $Collator->change(level => 2);
 
@@ -94,7 +94,7 @@ ok( $Collator->cmp($hiragana, $katakana), 0);
 ok( $Collator->eq($hiragana, $katakana) );
 ok( $Collator->ge($hiragana, $katakana) );
 
-##### 26..31
+# 25
 
 # hangul
 ok( $Collator->eq("a\x{AC00}b", "a\x{1100}\x{1161}b") );
@@ -104,7 +104,7 @@ ok( $Collator->lt("a\x{AC00}b", "a\x{AE00}b") );
 ok( $Collator->gt("a\x{D7A3}b", "a\x{C544}b") );
 ok( $Collator->lt("a\x{C544}b", "a\x{30A2}b") ); # hangul < hiragana
 
-##### 32..40
+# 31
 
 $Collator->change(%old_level, katakana_before_hiragana => 1);
 
@@ -119,7 +119,7 @@ ok( $Collator->ne($hiragana, $katakana) );
 ok( $Collator->gt($hiragana, $katakana) );
 ok( $Collator->ge($hiragana, $katakana) );
 
-##### 41..46
+# 40
 
 $Collator->change(upper_before_lower => 1);
 
@@ -130,14 +130,14 @@ ok( $Collator->cmp($hiragana, $katakana), 1);
 ok( $Collator->ge($hiragana, $katakana), 1);
 ok( $Collator->gt($hiragana, $katakana), 1);
 
-##### 47..48
+# 46
 
 $Collator->change(katakana_before_hiragana => 0);
 
 ok( $Collator->cmp("abc", "ABC"), 1);
 ok( $Collator->cmp($hiragana, $katakana), -1);
 
-##### 49..52
+# 48
 
 $Collator->change(upper_before_lower => 0);
 
@@ -146,7 +146,8 @@ ok( $Collator->le("abc", "ABC") );
 ok( $Collator->cmp($hiragana, $katakana), -1);
 ok( $Collator->lt($hiragana, $katakana) );
 
-##### 53..54
+# 52
+
 {
     my $ignoreAE = Unicode::Collate->new(
 	table => 'keys.txt',
@@ -157,27 +158,8 @@ ok( $Collator->lt($hiragana, $katakana) );
     ok($ignoreAE->eq("Perl","ePrl"));
 }
 
-##### 55
-{
-    my $onlyABC = Unicode::Collate->new(
-	table => undef,
-	normalization => undef,
-	entry => << 'ENTRIES',
-0061 ; [.0101.0020.0002.0061] # LATIN SMALL LETTER A
-0041 ; [.0101.0020.0008.0041] # LATIN CAPITAL LETTER A
-0062 ; [.0102.0020.0002.0062] # LATIN SMALL LETTER B
-0042 ; [.0102.0020.0008.0042] # LATIN CAPITAL LETTER B
-0063 ; [.0103.0020.0002.0063] # LATIN SMALL LETTER C
-0043 ; [.0103.0020.0008.0043] # LATIN CAPITAL LETTER C
-ENTRIES
-    );
-    ok(
-	join(':', $onlyABC->sort( qw/ ABA BAC cc A Ab cAc aB / ) ),
-	join(':',                 qw/ A aB Ab ABA BAC cAc cc / ),
-    );
-}
+# 54
 
-##### 56..59
 {
     my $undefAE = Unicode::Collate->new(
 	table => 'keys.txt',
@@ -190,69 +172,8 @@ ENTRIES
     ok($Collator->lt("lake","like"));
 }
 
-##### 60..69
-{
-    # Table is undefined, then no entry is defined.
-    my $undef_table = Unicode::Collate->new(
-	table => undef,
-	normalization => undef,
-	level => 1,
-    );
-
-    # in the Unicode code point order
-    ok($undef_table->lt('', 'A'));
-    ok($undef_table->lt('ABC', 'B'));
-
-    # Hangul should be decomposed (even w/o Unicode::Normalize).
-    ok($undef_table->lt("Perl", "\x{AC00}"));
-    ok($undef_table->eq("\x{AC00}", "\x{1100}\x{1161}"));
-    ok($undef_table->eq("\x{AE00}", "\x{1100}\x{1173}\x{11AF}"));
-    ok($undef_table->lt("\x{AE00}", "\x{3042}"));
+# 58
 
-    # U+AC00: Hangul GA
-    # U+AE00: Hangul GEUL
-    # U+3042: Hiragana A
-
-    # Weight for CJK Ideographs is defined, though.
-    ok($undef_table->lt("", "\x{4E00}"));
-    ok($undef_table->lt("\x{4E8C}","ABC"));
-    ok($undef_table->lt("\x{4E00}","\x{3042}"));
-    ok($undef_table->lt("\x{4E00}","\x{4E8C}"));
-
-    # U+4E00: Ideograph "ONE"
-    # U+4E8C: Ideograph "TWO"
-}
-
-##### 70..74
-{
-    my $few_entries = Unicode::Collate->new(
-	entry => <<'ENTRIES',
-0050 ; [.0101.0020.0002.0050]  # P
-0045 ; [.0102.0020.0002.0045]  # E
-0052 ; [.0103.0020.0002.0052]  # R
-004C ; [.0104.0020.0002.004C]  # L
-1100 ; [.0105.0020.0002.1100]  # Hangul Jamo initial G
-1175 ; [.0106.0020.0002.1175]  # Hangul Jamo middle I
-5B57 ; [.0107.0020.0002.5B57]  # CJK Ideograph "Letter"
-ENTRIES
-	table => undef,
-	normalization => undef,
-    );
-    # defined before undefined
-    my $sortABC = join '',
-	$few_entries->sort(split //, "ABCDEFGHIJKLMNOPQRSTUVWXYZ ");
-
-    ok($sortABC eq "PERL ABCDFGHIJKMNOQSTUVWXYZ");
-
-    ok($few_entries->lt('E', 'D'));
-    ok($few_entries->lt("\x{5B57}", "\x{4E00}"));
-    ok($few_entries->lt("\x{AE30}", "\x{AC00}"));
-
-    # Hangul must be decomposed.
-    ok($few_entries->eq("\x{AC00}", "\x{1100}\x{1161}"));
-}
-
-##### 75..79
 {
     my $dropArticles = Unicode::Collate->new(
 	table => "keys.txt",
@@ -270,7 +191,8 @@ ENTRIES
     ok($Collator->gt("the pen", "a pencil"));
 }
 
-##### 80..83
+# 63
+
 {
     my $undefName = Unicode::Collate->new(
 	table => "keys.txt",
@@ -286,7 +208,8 @@ ENTRIES
     ok($Collator ->gt("\x{4E03}", $katakana));
 }
 
-##### 84..90
+# 67
+
 {
     my $O_str = Unicode::Collate->new(
 	table => "keys.txt",
@@ -321,7 +244,7 @@ ENTRIES
     ok($O_str   ->gt("\x{200B}", "A"));
 }
 
-##### 91..101
+# 74
 
 my %origVer = $Collator->change(UCA_Version => 8);
 
@@ -351,7 +274,7 @@ $Collator->change(level => 4);
 ok($Collator->gt("!\x{300}", ""));
 ok($Collator->eq("!\x{300}", "!"));
 
-##### 102..107
+# 85
 
 $_ = 'Foo';
 
@@ -385,7 +308,7 @@ $_ = 'Foo';
 @temp = $c->index("perl5", "LR");
 ok($_, 'Foo');
 
-##### 108..109
+# 91
 
 {
     my $caseless = Unicode::Collate->new(
@@ -397,7 +320,7 @@ ok($_, 'Foo');
     ok( $caseless->eq("ABC","abc") );
 }
 
-##### 110..112
+# 93
 
 {
     eval { require Unicode::Normalize; };
@@ -417,4 +340,5 @@ ok($_, 'Foo');
     }
 }
 
-#####
+# 96
+