Unicode::Normalize 0.14 synch, from SADAHIRO Tomoyuki.

p4raw-id: //depot/perl@14888

diff --git a/ext/Unicode/Normalize/Changes b/ext/Unicode/Normalize/Changes
index 4426648..35c1b94 100644 (file)
--- a/ext/Unicode/Normalize/Changes
+++ b/ext/Unicode/Normalize/Changes
@@ -1,5 +1,19 @@
 Revision history for Perl extension Unicode::Normalize.
 
+0.14  Sat Feb 02 20:40:14 2002
+       - synchronization with bleadperl.
+       - Change 14128: by Arthur
+       - Change 14129: by jhi
+       - Change 14156: 
+       - Change 14199: by Nikola Knezevic
+       - Change 14308: by Benjamin Goldberg
+       - Change 14370: by jhi
+
+0.13  Sat Dec 01 11:42:43 2001
+       - modify Makefile.PL to enable rebuild.
+         (This problem is pointed out by David Dyck.)
+       - Change 13388: by Jarkko Hietaniemi.
+
 0.12  Wed Nov 29 22:49:02 2001
        - documentation in .pod is appended to .pm and the .pod is removed.
         (only POD in NON-XS refers to Lingua::KO::Hangul::Util.)

diff --git a/ext/Unicode/Normalize/Normalize.pm b/ext/Unicode/Normalize/Normalize.pm
index db173c5..cec5fa7 100644 (file)
--- a/ext/Unicode/Normalize/Normalize.pm
+++ b/ext/Unicode/Normalize/Normalize.pm
@@ -11,7 +11,7 @@ use strict;
 use warnings;
 use Carp;
 
-our $VERSION = '0.13';
+our $VERSION = '0.14';
 our $PACKAGE = __PACKAGE__;
 
 require Exporter;
@@ -168,7 +168,7 @@ SADAHIRO Tomoyuki, E<lt>SADAHIRO@cpan.orgE<gt>
 
   http://homepage1.nifty.com/nomenclator/perl/
 
-  Copyright(C) 2001, SADAHIRO Tomoyuki. Japan. All rights reserved.
+  Copyright(C) 2001-2002, SADAHIRO Tomoyuki. Japan. All rights reserved.
 
   This program is free software; you can redistribute it and/or 
   modify it under the same terms as Perl itself.

diff --git a/ext/Unicode/Normalize/Normalize.xs b/ext/Unicode/Normalize/Normalize.xs
index 0b0809e..7a11095 100644 (file)
--- a/ext/Unicode/Normalize/Normalize.xs
+++ b/ext/Unicode/Normalize/Normalize.xs
@@ -16,9 +16,9 @@
 #endif /* uvuni_to_utf8 */ 
 
 /* Perl 5.6.1 ? */
-#ifndef utf8n_to_uvchr
-#define utf8n_to_uvchr  utf8_to_uv
-#endif /* utf8n_to_uvchr */ 
+#ifndef utf8n_to_uvuni
+#define utf8n_to_uvuni  utf8_to_uv
+#endif /* utf8n_to_uvuni */ 
 
 /* At present, char > 0x10ffff are unaffected without complaint, right? */
 #define VALID_UTF_MAX    (0x10ffff)
@@ -172,7 +172,7 @@ decompose(arg, compat = &PL_sv_no)
     s = (U8*)SvPV(src,srclen);
     e = s + srclen;
     for(p = s; p < e;){
-       uv = utf8n_to_uvchr(p, e - p, &retlen, 0);
+       uv = utf8n_to_uvuni(p, e - p, &retlen, 0);
        p += retlen;
        if(Hangul_IsS(uv)) sv_cat_decompHangul(dst, uv);
        else {
@@ -211,7 +211,7 @@ reorder(arg)
        U8 *cc_in;
        STRLEN cc_len, cc_iter, cc_pos;
 
-       uv = utf8n_to_uvchr(p, e - p, &retlen, 0);
+       uv = utf8n_to_uvuni(p, e - p, &retlen, 0);
        curCC = getCombinClass(uv);
        p += retlen;
 
@@ -223,7 +223,7 @@ reorder(arg)
        stk_cc[cc_pos].pos = cc_pos;
 
        while(p < e) {
-           uv = utf8n_to_uvchr(p, e - p, &retlen, 0);
+           uv = utf8n_to_uvuni(p, e - p, &retlen, 0);
            curCC = getCombinClass(uv);
            if(!curCC) break;
            p += retlen;
@@ -288,7 +288,7 @@ compose(arg)
 
     for(p = s; p < e;){
        if(beginning) {
-           uvS = utf8n_to_uvchr(p, e - p, &retlen, 0);
+           uvS = utf8n_to_uvuni(p, e - p, &retlen, 0);
            p += retlen;
 
             if (getCombinClass(uvS)){ /* no Starter found yet */
@@ -304,7 +304,7 @@ compose(arg)
 
     /* to the next Starter */
        while(p < e) {
-           uv = utf8n_to_uvchr(p, e - p, &retlen, 0);
+           uv = utf8n_to_uvuni(p, e - p, &retlen, 0);
            p += retlen;
            curCC = getCombinClass(uv);
 
@@ -345,7 +345,6 @@ compose(arg)
        }
        uvS = uv;
     } /* for */
-
     SvCUR_set(dst, d - (U8*)SvPVX(dst));
     RETVAL = dst;
   OUTPUT:

diff --git a/ext/Unicode/Normalize/README b/ext/Unicode/Normalize/README
index 96c456a..2404f2f 100644 (file)
--- a/ext/Unicode/Normalize/README
+++ b/ext/Unicode/Normalize/README
@@ -1,4 +1,4 @@
-Unicode/Normalize version 0.12
+Unicode/Normalize version 0.14
 ===================================
 
 Unicode::Normalize - normalized forms of Unicode text
@@ -40,6 +40,15 @@ type the following:
    make test
    make install
 
+If you decide to install the NoXS version after trying to build the XS,
+type the following:
+
+   make clean
+   perl Makefile.PL noxs
+   make
+   make test
+   make install
+
 DEPENDENCIES
 
 This module requires these other modules and libraries:
@@ -48,12 +57,23 @@ Carp
 Exporter
 File::Copy
 File::Spec
-unicore/CombiningClass.pl         or unicode/CombiningClass.pl
-unicore/Decomposition.pl          or unicode/Decomposition.pl
-unicore/CompositionExclusions.txt or unicode/CompExcl.txt
 
-and for the Non-XS version, in addition to the above,
-Lingua::KO::Hangul::Util 0.06
+unicore/CombiningClass.pl
+  (or unicode/CombiningClass.pl)
+unicore/Decomposition.pl
+  (or unicode/Decomposition.pl)
+unicore/CompositionExclusions.txt
+  (or unicode/CompExcl.txt)
+
+# CAVEAT:
+# In bleadperl, unicore/CompExcl.txt is renamed
+# unicore/CompositionExclusions.txt.
+
+And for the NoXS version, in addition to the above,
+
+  Lingua::KO::Hangul::Util 0.06
+
+is required.
 
 COPYRIGHT AND LICENCE
 
@@ -61,8 +81,8 @@ SADAHIRO Tomoyuki, E<lt>SADAHIRO@cpan.orgE<gt>
 
   http://homepage1.nifty.com/nomenclator/perl/
 
-  Copyright(C) 2001, SADAHIRO Tomoyuki. Japan. All rights reserved.
+  Copyright(C) 2001-2002, SADAHIRO Tomoyuki. Japan. All rights reserved.
 
-  This program is free software; you can redistribute it and/or 
+  This program is free software; you can redistribute it and/or
   modify it under the same terms as Perl itself.
 

diff --git a/ext/Unicode/Normalize/t/func.t b/ext/Unicode/Normalize/t/func.t
index 6f0ff08..c436a7c 100644 (file)
--- a/ext/Unicode/Normalize/t/func.t
+++ b/ext/Unicode/Normalize/t/func.t
@@ -66,8 +66,8 @@ print ! defined getComposite( 0,  0)
    && 0x1E14 == getComposite(0x0112, 0x0300)
    && 0xAC00 == getComposite(0x1100, 0x1161)
    && 0xADF8 == getComposite(0x1100, 0x1173)
-   && ! getComposite(0x1100, 0x11AF)
-   && ! getComposite(0x1173, 0x11AF)
+   && ! defined getComposite(0x1100, 0x11AF)
+   && ! defined getComposite(0x1173, 0x11AF)
    && 0xAE00 == getComposite(0xADF8, 0x11AF)
   ? "ok" : "not ok", " 5\n";
 

diff --git a/ext/Unicode/Normalize/t/test.t b/ext/Unicode/Normalize/t/test.t
index 198bf07..fe42aae 100644 (file)
--- a/ext/Unicode/Normalize/t/test.t
+++ b/ext/Unicode/Normalize/t/test.t
@@ -49,5 +49,10 @@ ok(hexNFC("0000 0041 0000 0000"), "0000 0041 0000 0000");
 ok(hexNFD("0000 0041 0000 0000"), "0000 0041 0000 0000");
 
 # should be unary.
-ok(NFC "\x{41}\x{0302}\x{0301}\x62" eq "\x{1EA4}\x62");
-ok(NFD "\x{E0}\x{AC00}" eq "\x{61}\x{0300}\x{1100}\x{1161}");
+my $str11 = pack('U*', 0x41, 0x0302, 0x0301, 0x62);
+my $str12 = pack('U*', 0x1EA4, 0x62);
+ok(NFC $str11 eq $str12);
+
+my $str21 = pack('U*', 0xE0, 0xAC00);
+my $str22 = pack('U*', 0x61, 0x0300, 0x1100, 0x1161);
+ok(NFD $str21 eq $str22);