Encode] 1.96 Released

Message-Id: <E7FFAE2E-A174-11D7-ACE4-000393AE4244@dan.co.jp>

p4raw-id: //depot/perl@19811

diff --git a/ext/Encode/Changes b/ext/Encode/Changes
index f729d18..18f5788 100644 (file)
--- a/ext/Encode/Changes
+++ b/ext/Encode/Changes
@@ -1,8 +1,30 @@
 # Revision history for Perl extension Encode.
 #
-# $Id: Changes,v 1.95 2003/05/21 08:41:11 dankogai Exp $
+# $Id: Changes,v 1.96 2003/06/18 09:29:02 dankogai Exp $
 #
-$Revision: 1.95 $ $Date: 2003/05/21 08:41:11 $
+$Revision: 1.96 $ $Date: 2003/06/18 09:29:02 $
+! lib/Encode/JP/JP.pm t/guess.t
+  m/(...)/ in void context then $1 is considered a Bad Thing
+  Message-Id: <B5AB34D0-A019-11D7-AF03-000393AE4244@dan.co.jp>
+! Encode.pm
+  Mentions in POD that as of perl 5.8.1 utf8::is_utf8() is
+  also available.
+! encengine.c
+  More typecast from maintperl@19739
+  Message-Id: <200306110645.h5B6j5D2009640@smtp3.ActiveState.com>
+! t/perlio.t
+  Tests 37 & 38 failed on Win32 -- yet another CRLF issue
+  Message-Id: <200306090733.h597XQPA031646@smtp3.ActiveState.com>
+! t/Encode.t
+  Now skips for EBCDIC platform.
+  Message-Id: <OF44B38062.A3998148-ON80256D27.004CF379@portsmouth.uk.ibm.com>
+! t/perlio.t
+  Craig's patch applied that addresses "Many systems (DOS, VMS) cannot
+  have more than one C<.> in their filenames." -- perlport.
+  Message-Id: <3ED79E01.8050401@mac.com>
+! bin/piconv
+  Found and fixed the back that -p,--perlqq does not work.
+  Induced by the change from Getopt::Std to Getopt::Long.
 ! encoding.pm
   Addressed [cpan #2629] Wrong assumption in numeric comparison
   Message-Id: <rt-2629-7326.19.5700583232515@cpan.org>

diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm
index 4959b5f..57bcc2b 100644 (file)
--- a/ext/Encode/Encode.pm
+++ b/ext/Encode/Encode.pm
@@ -1,9 +1,9 @@
 #
-# $Id: Encode.pm,v 1.95 2003/05/21 08:40:59 dankogai Exp $
+# $Id: Encode.pm,v 1.96 2003/06/18 09:29:02 dankogai Exp $
 #
 package Encode;
 use strict;
-our $VERSION = do { my @r = (q$Revision: 1.95 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 our $DEBUG = 0;
 use XSLoader ();
 XSLoader::load(__PACKAGE__, $VERSION);
@@ -739,6 +739,8 @@ implementation.  As such, they are efficient but may change.
 If CHECK is true, also checks the data in STRING for being well-formed
 UTF-8.  Returns true if successful, false otherwise.
 
+As of perl 5.8.1, L<utf8> also has utf8::is_utif8().
+
 =item _utf8_on(STRING)
 
 [INTERNAL] Turns on the UTF-8 flag in STRING.  The data in STRING is

diff --git a/ext/Encode/Encode.xs b/ext/Encode/Encode.xs
index 7970058..8bdcdfa 100644 (file)
--- a/ext/Encode/Encode.xs
+++ b/ext/Encode/Encode.xs
@@ -1,5 +1,5 @@
 /*
- $Id: Encode.xs,v 1.55 2003/02/28 01:40:27 dankogai Exp dankogai $
+ $Id: Encode.xs,v 1.56 2003/06/18 09:29:02 dankogai Exp $
  */
 
 #define PERL_NO_GET_CONTEXT

diff --git a/ext/Encode/META.yml b/ext/Encode/META.yml
index f48c93f..075c6a9 100644 (file)
--- a/ext/Encode/META.yml
+++ b/ext/Encode/META.yml
@@ -1,9 +1,9 @@
 #XXXXXXX This is a prototype!!!  It will change in the future!!! XXXXX#
 name:         Encode
-version:      1.95
+version:      1.96
 version_from: Encode.pm
 installdirs:  perl
 requires:
 
 distribution_type: module
-generated_by: ExtUtils::MakeMaker version 6.10_03
+generated_by: ExtUtils::MakeMaker version 6.10_05

diff --git a/ext/Encode/Unicode/Unicode.pm b/ext/Encode/Unicode/Unicode.pm
index 9648fd3..4c23c0e 100644 (file)
--- a/ext/Encode/Unicode/Unicode.pm
+++ b/ext/Encode/Unicode/Unicode.pm
@@ -4,7 +4,7 @@ use strict;
 use warnings;
 no warnings 'redefine';
 
-our $VERSION = do { my @r = (q$Revision: 1.39 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.40 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 use XSLoader;
 XSLoader::load(__PACKAGE__,$VERSION);

diff --git a/ext/Encode/Unicode/Unicode.xs b/ext/Encode/Unicode/Unicode.xs
index cb27bb3..70b9a5d 100644 (file)
--- a/ext/Encode/Unicode/Unicode.xs
+++ b/ext/Encode/Unicode/Unicode.xs
@@ -1,5 +1,5 @@
 /*
- $Id: Unicode.xs,v 1.7 2003/02/20 14:42:34 dankogai Exp dankogai $
+ $Id: Unicode.xs,v 1.8 2003/06/18 09:29:02 dankogai Exp $
  */
 
 #define PERL_NO_GET_CONTEXT

diff --git a/ext/Encode/bin/piconv b/ext/Encode/bin/piconv
index ee400f5..fbdb580 100644 (file)
--- a/ext/Encode/bin/piconv
+++ b/ext/Encode/bin/piconv
@@ -1,5 +1,5 @@
 #!./perl
-# $Id: piconv,v 1.26 2003/05/10 18:13:59 dankogai Exp $
+# $Id: piconv,v 1.27 2003/06/18 09:29:02 dankogai Exp $
 #
 use 5.8.0;
 use strict;

diff --git a/ext/Encode/encoding.pm b/ext/Encode/encoding.pm
index 5c922bd..3fc6e43 100644 (file)
--- a/ext/Encode/encoding.pm
+++ b/ext/Encode/encoding.pm
@@ -1,6 +1,6 @@
-# $Id: encoding.pm,v 1.44 2003/03/09 20:07:37 dankogai Exp $
+# $Id: encoding.pm,v 1.45 2003/06/18 09:29:02 dankogai Exp $
 package encoding;
-our $VERSION = do { my @r = (q$Revision: 1.44 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.45 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 use Encode;
 use strict;
@@ -21,11 +21,11 @@ unless ($@){
 
 sub _exception{
     my $name = shift;
-    $] > 5.008 and return 0;             # 5.8.1 then no
+    $] > 5.008 and return 0;               # 5.8.1 or higher then no
     my %utfs = map {$_=>1}
        qw(utf8 UCS-2BE UCS-2LE UTF-16 UTF-16BE UTF-16LE
           UTF-32 UTF-32BE UTF-32LE);
-    $utfs{$name} or return 0;            # UTFs or no
+    $utfs{$name} or return 0;               # UTFs or no
     require Config; Config->import(); our %Config;
     return $Config{perl_patchlevel} ? 0 : 1 # maintperl then no
 }

diff --git a/ext/Encode/lib/Encode/Encoding.pm b/ext/Encode/lib/Encode/Encoding.pm
index 3978e9d..6f19627 100644 (file)
--- a/ext/Encode/lib/Encode/Encoding.pm
+++ b/ext/Encode/lib/Encode/Encoding.pm
@@ -1,7 +1,7 @@
 package Encode::Encoding;
 # Base class for classes which implement encodings
 use strict;
-our $VERSION = do { my @r = (q$Revision: 1.32 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.33 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 require Encode;
 

diff --git a/ext/Encode/lib/Encode/JP/JIS7.pm b/ext/Encode/lib/Encode/JP/JIS7.pm
index d194c5a..01a7f0e 100644 (file)
--- a/ext/Encode/lib/Encode/JP/JIS7.pm
+++ b/ext/Encode/lib/Encode/JP/JIS7.pm
@@ -1,7 +1,7 @@
 package Encode::JP::JIS7;
 use strict;
 
-our $VERSION = do { my @r = (q$Revision: 1.10 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.11 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 use Encode qw(:fallbacks);
 
@@ -35,8 +35,7 @@ sub decode($$;$)
     my ($obj, $str, $chk) = @_;
     my $residue = '';
     if ($chk){
-       $str =~ s/([^\x00-\x7f].*)$//so;
-       $1 and $residue = $1;
+       $str =~ s/([^\x00-\x7f].*)$//so and $residue = $1;
     }
     $residue .= jis_euc(\$str);
     $_[1] = $residue if $chk;

diff --git a/ext/Encode/t/Unicode.t b/ext/Encode/t/Unicode.t
index 0d5c6b9..4c72922 100644 (file)
--- a/ext/Encode/t/Unicode.t
+++ b/ext/Encode/t/Unicode.t
@@ -1,5 +1,5 @@
 #
-# $Id: Unicode.t,v 1.12 2003/05/21 08:41:11 dankogai Exp $
+# $Id: Unicode.t,v 1.13 2003/06/18 09:29:02 dankogai Exp $
 #
 # This script is written entirely in ASCII, even though quoted literals
 # do include non-BMP unicode characters -- Are you happy, jhi?

diff --git a/ext/Encode/t/guess.t b/ext/Encode/t/guess.t
index d3ff58c..55a75b4 100644 (file)
--- a/ext/Encode/t/guess.t
+++ b/ext/Encode/t/guess.t
@@ -21,7 +21,7 @@ use File::Spec;
 use Encode qw(decode encode find_encoding _utf8_off);
 
 #use Test::More qw(no_plan);
-use Test::More tests => 23;
+use Test::More tests => 29;
 use_ok("Encode::Guess");
 {
     no warnings;
@@ -99,4 +99,19 @@ for my $bl (qw/BE LE/){
     my $result = guess_encoding($test);
     ok(! ref($result), "UTF-16$bl:$result");
 }
+
+
+
+Encode::Guess->set_suspects();
+for my $jp (@jp){
+    # intentionally set $1 a priori -- see Changes
+    my $test = "English";
+    '$1' =~ m/^(.*)/o;
+    is(guess_encoding($test, ($jp))->name, 'ascii', 
+       "ascii vs $jp (\$1 messed)");
+    $test = encode($jp, $test . "\n\x{65e5}\x{672c}\x{8a9e}");
+    is(guess_encoding($test, ($jp))->name, 
+       $jp, "$jp vs ascii (\$1 messed)");
+}
+
 __END__;