From: Dan Kogai <dankogai@dan.co.jp>
Date: Sun, 6 Oct 2002 12:52:52 +0000 (+0900)
Subject: [Encode] 1.77 Released
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=4b291ae6c6eed18b8842058ee57489c11dec5862;p=p5sagit%2Fp5-mst-13.2.git

[Encode] 1.77 Released
Message-Id: <16D4C6C9-D8DF-11D6-A5EA-0003939A104C@dan.co.jp>

p4raw-id: //depot/perl@18002
---

diff --git a/ext/Encode/Changes b/ext/Encode/Changes
index 7eb50a4..18995ec 100644
--- a/ext/Encode/Changes
+++ b/ext/Encode/Changes
@@ -1,9 +1,20 @@
 # Revision history for Perl extension Encode.
 #
-# $Id: Changes,v 1.76 2002/08/25 15:09:51 dankogai Exp dankogai $
+# $Id: Changes,v 1.77 2002/10/06 03:27:02 dankogai Exp dankogai $
 #
 
-$Revision: 1.76 $ $Date: 2002/08/25 15:09:51 $
+$Revision: 1.77 $ $Date: 2002/10/06 03:27:02 $
+! t/jperl.t
+  * Modified to accomodate up and comming patch by Inaba-san that
+    will fix tr/// needing eval qq{}
+    Message-Id: <9F78A19C-D6C3-11D6-BAC6-0003939A104C@dan.co.jp>
+! encoding.pm 
+  * pod fixes/enhancements to reflect the changes above
+! lib/Encode/Alias.pm
+  "Encode::TW is correct, Encode::Alias not." - /Autrijus/
+  Message-Id: <20021001015648.GB18710@not.autrijus.org>
+
+1.76 2002/08/25 15:09:51
 ! t/big5-eten.utf
   To reflect ucm change by Autrijus.  t/big5-eten.enc was regenerated
   but naturally identical to previous version -- dankogai
@@ -706,7 +717,7 @@ $Revision: 1.76 $ $Date: 2002/08/25 15:09:51 $
   Typo fixes and improvements by jhi
   Message-Id: <200204010201.FAA03564@alpha.hut.fi>, et al.
 
-1.11  $Date: 2002/08/25 15:09:51 $
+1.11  $Date: 2002/10/06 03:27:02 $
 + t/encoding.t
 + t/jperl.t
 ! MANIFEST
diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm
index ded46b8..2500e14 100644
--- a/ext/Encode/Encode.pm
+++ b/ext/Encode/Encode.pm
@@ -1,9 +1,9 @@
 #
-# $Id: Encode.pm,v 1.76 2002/08/25 15:09:51 dankogai Exp dankogai $
+# $Id: Encode.pm,v 1.77 2002/10/06 03:26:54 dankogai Exp $
 #
 package Encode;
 use strict;
-our $VERSION = do { my @r = (q$Revision: 1.76 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.77 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 our $DEBUG = 0;
 use XSLoader ();
 XSLoader::load(__PACKAGE__, $VERSION);
diff --git a/ext/Encode/Unicode/Unicode.pm b/ext/Encode/Unicode/Unicode.pm
index b09e126..fa508eb 100644
--- a/ext/Encode/Unicode/Unicode.pm
+++ b/ext/Encode/Unicode/Unicode.pm
@@ -60,7 +60,7 @@ sub set_transcoder{
 	*encode = \&encode_classic;
     }else{
 	require Carp; 
-	Carp::croak(__PACKAGE__, "::set_transcoder(modern|classic|xs)");
+	Carp::croak __PACKAGE__, "::set_transcoder(modern|classic|xs)";
     }
 }
 
@@ -258,7 +258,7 @@ sub poisoned2death{
     my $msg = shift;
     my $pair = join(", ", map {sprintf "\\x%x", $_} @_);
     require Carp;
-    Carp::croak($obj->name, ":", $msg, "<$pair>.", caller);
+    Carp::croak $obj->name, ":", $msg, "<$pair>.", caller;
 }
 
 1;
diff --git a/ext/Encode/encoding.pm b/ext/Encode/encoding.pm
index 182d7c6..778b44b 100644
--- a/ext/Encode/encoding.pm
+++ b/ext/Encode/encoding.pm
@@ -1,5 +1,5 @@
 package encoding;
-our $VERSION = do { my @r = (q$Revision: 1.36 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.37 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 use Encode;
 use strict;
@@ -144,7 +144,7 @@ the code in UTF-8:
   s/\bCamel\b/$Rakuda/;
 
 The B<encoding> pragma also modifies the filehandle disciplines of
-STDIN, STDOUT, and STDERR to the specified encoding.  Therefore,
+STDIN and STDOUT to the specified encoding.  Therefore,
 
   use encoding "euc-jp";
   my $message = "Camel is the symbol of perl.\n";
@@ -237,6 +237,53 @@ resort to \x{....} just to spell your name in a native encoding.
 So feel free to put your strings in your encoding in quotes and
 regexes.
 
+=head2 tr/// with ranges remain unaffected
+
+The B<encoding> pragma works by decoding string literals in
+C<q//,qq//,qr//,qw///, qx//> and so forth.  As of perl 5.8.0, this
+does not apply to C<tr///>.  Therefore,
+
+  use encoding 'euc-jp';
+  #....
+  $kana =~ tr/\xA4\xA1-\xA4\xF3/\xA5\xA1-\xA5\xF3/;
+  #           -------- -------- -------- --------
+
+Does not work as
+
+  $kana =~ tr/\x{3041}-\x{3093}/\x{30a1}-\x{30f3}/;
+
+=over
+
+=item Legend of characters above
+
+  utf8     euc-jp   charnames::viacode()
+  -----------------------------------------
+  \x{3041} \xA4\xA1 HIRAGANA LETTER SMALL A
+  \x{3093} \xA4\xF3 HIRAGANA LETTER N
+  \x{30a1} \xA5\xA1 KATAKANA LETTER SMALL A
+  \x{30f3} \xA5\xF3 KATAKANA LETTER N
+
+=back
+
+=head3 workaround to tr///;
+
+You can, however, achieve the same as simply as follows;
+
+  use encoding 'euc-jp';
+  # ....
+  eval qq{ \$kana =~ tr/\xA4\xA1-\xA4\xF3/\xA5\xA1-\xA5\xF3/ };
+
+Note the C<tr//> expression is surronded by C<qq{}>.  The idea behind
+is the same as classic idiom that makes C<tr///> 'interpolate'.
+
+   tr/$from/$to/;            # wrong!
+   eval qq{ tr/$from/$to/ }; # workaround.
+
+Nevertheless, in case of B<encoding> pragma even C<q//> is affected so
+C<tr///> not being decoded was obviously against the will of Perl5
+Porters.  In future version of perl, this counter-intuitive behaviour
+of C<tr///> will be fixed so C<eval qq{}> trick will be unneccesary.
+
 =head1 Non-ASCII Identifiers and Filter option
 
 The magic of C<use encoding> is not applied to the names of
diff --git a/ext/Encode/lib/Encode/Alias.pm b/ext/Encode/lib/Encode/Alias.pm
index 4572fb6..0622602 100644
--- a/ext/Encode/lib/Encode/Alias.pm
+++ b/ext/Encode/lib/Encode/Alias.pm
@@ -1,7 +1,7 @@
 package Encode::Alias;
 use strict;
 use Encode;
-our $VERSION = do { my @r = (q$Revision: 1.33 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.34 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 our $DEBUG = 0;
 
 use base qw(Exporter);
@@ -219,7 +219,7 @@ sub init_aliases
         define_alias( qr/\bks_c_5601-1987$/i      => '"cp949"' );
         # for Encode::TW
 	define_alias( qr/\bbig-?5$/i		  => '"big5-eten"' );
-	define_alias( qr/\bbig5-?et(?:en)$/i	  => '"big5-eten"' );
+	define_alias( qr/\bbig5-?et(?:en)?$/i	  => '"big5-eten"' );
 	define_alias( qr/\btca[-_]?big5$/i	  => '"big5-eten"' );
 	define_alias( qr/\bbig5-?hk(?:scs)?$/i	  => '"big5-hkscs"' );
 	define_alias( qr/\bhk(?:scs)?[-_]?big5$/i  => '"big5-hkscs"' );
diff --git a/ext/Encode/lib/Encode/Encoding.pm b/ext/Encode/lib/Encode/Encoding.pm
index 1d24e9c..1876cb7 100644
--- a/ext/Encode/lib/Encode/Encoding.pm
+++ b/ext/Encode/lib/Encode/Encoding.pm
@@ -36,14 +36,14 @@ sub encode {
     require Carp;
     my $obj = shift;
     my $class = ref($obj) ? ref($obj) : $obj;
-    Carp::croak($class, "->encode() not defined!");
+    Carp::croak $class, "->encode() not defined!";
 }
 
 sub decode{
     require Carp;
     my $obj = shift;
     my $class = ref($obj) ? ref($obj) : $obj;
-    Carp::croak($class, "->encode() not defined!");
+    Carp::croak $class, "->encode() not defined!";
 }
 
 sub DESTROY {}
diff --git a/ext/Encode/t/jperl.t b/ext/Encode/t/jperl.t
index 82f7a84..e281624 100644
--- a/ext/Encode/t/jperl.t
+++ b/ext/Encode/t/jperl.t
@@ -1,5 +1,5 @@
 #
-# $Id: jperl.t,v 1.24 2002/04/26 03:02:04 dankogai Exp $
+# $Id: jperl.t,v 1.25 2002/10/06 03:27:02 dankogai Exp dankogai $
 #
 # This script is written in euc-jp
 
@@ -23,7 +23,8 @@ BEGIN {
 no utf8; # we have raw Japanese encodings here
 
 use strict;
-use Test::More tests => 18;
+#use Test::More tests => 18;
+use Test::More tests => 15; # black magic tests commented out
 my $Debug = shift;
 
 no encoding; # ensure
@@ -60,14 +61,18 @@ is(length($Namae), 4, q{utf8:length});
 }
 # should've been isnt() but no scoping is suported -- yet
 ok(! defined(${^ENCODING}), q{not scoped yet});
-{
-    # now let's try some real black magic!
-    local(${^ENCODING}) = Encode::find_encoding("euc-jp");
-    my $str = "\xbe\xae\xbb\xf4\x20\xc3\xc6";
-   is (length($str), 4, q{black magic:length});
-   is ($str, $Enamae,   q{black magic:eq});
-}
-ok(! defined(${^ENCODING}), q{out of black magic});
+
+#
+# The following tests are commented out to accomodate
+# Inaba-San's patch to make tr/// work w/o eval qq{}
+#{
+#    # now let's try some real black magic!
+#    local(${^ENCODING}) = Encode::find_encoding("euc-jp");
+#    my $str = "\xbe\xae\xbb\xf4\x20\xc3\xc6";
+#   is (length($str), 4, q{black magic:length});
+#   is ($str, $Enamae,   q{black magic:eq});
+#}
+#ok(! defined(${^ENCODING}), q{out of black magic});
 use bytes;
 is (length($Namae), 10);
 
diff --git a/ext/Encode/ucm/big5-eten.ucm b/ext/Encode/ucm/big5-eten.ucm
index 1fe3a99..e3e4d58 100644
--- a/ext/Encode/ucm/big5-eten.ucm
+++ b/ext/Encode/ucm/big5-eten.ucm
@@ -1,5 +1,5 @@
 #
-# $Id: big5-eten.ucm,v 1.3 2002/08/25 15:09:51 dankogai Exp dankogai $
+# $Id: big5-eten.ucm,v 1.3 2002/08/25 15:09:51 dankogai Exp $
 #
 # ./compile -n big5-eten -o Encode/big5-eten.ucm Encode/big5-eten.enc
 <code_set_name> "big5-eten"