ext/DynaLoader/README Dynamic Loader notes and intro
ext/DynaLoader/XSLoader_pm.PL Simple XS Loader perl module
ext/Encode/AUTHORS Encode extension
+ext/Encode/Byte/Byte.pm Encode extension
+ext/Encode/Byte/Makefile.PL Encode extension
ext/Encode/Changes Encode extension
ext/Encode/CN/CN.pm Encode extension
ext/Encode/CN/Makefile.PL Encode extension
ext/Encode/compile Encode extension
+ext/Encode/EBCDIC/EBCDIC.pm Encode extension
+ext/Encode/EBCDIC/Makefile.PL Encode extension
ext/Encode/encengine.c Encode extension
ext/Encode/encode.h Encode extension
ext/Encode/Encode.pm Encode extension
ext/Encode/Makefile.PL Encode extension makefile writer
ext/Encode/MANIFEST Encode extension
ext/Encode/README Encode extension
+ext/Encode/Symbol/Makefile.PL Encode extension
+ext/Encode/Symbol/Symbol.pm Encode extension
ext/Encode/t/Aliases.t Encode extension
ext/Encode/t/CN.t Encode extension test
ext/Encode/t/Encode.t Encode extension test
lib/Pod/t/Functions.t See if Pod::Functions works
lib/Pod/t/htmlescp.pod pod2html escape test input data
lib/Pod/t/htmlescp.t pod2html escape test
-lib/Pod/t/htmlview.t pod2html render test
lib/Pod/t/htmlview.pod pod2html render test input data
+lib/Pod/t/htmlview.t pod2html render test
lib/Pod/t/InputObjects.t See if Pod::InputObjects works
lib/Pod/t/latex.t See if Pod::LaTeX works
lib/Pod/t/man.t podlators test
Autrijus Tang <autrijus@autrijus.org>
Dan Kogai <dankogai@dan.co.jp>
Jarkko Hietaniemi <jhi@iki.fi>
+Michael G Schwern <schwern@pobox.com>
Nick Ing-Simmons <nick@ing-simmons.net>
Paul Marquess <paul_marquess@yahoo.co.uk>
SADAHIRO Tomoyuki <SADAHIRO@cpan.org>
--- /dev/null
+package Encode::Byte;
+use Encode;
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+
+use XSLoader;
+XSLoader::load('Encode::Byte',$VERSION);
+
+1;
+__END__
+=head1 NAME
+
+Encode::Byte - Single Byte Encodings
+
+=head1 SYNOPSIS
+
+ use Encode qw/encode decode/;
+ $latin1 = encode("iso-8859-1", $utf8); # loads Encode::Byte implicitly
+ $utf8 = decode("iso-8859-1", $latin1); # ditto
+
+=head1 ABSTRACT
+
+This module implements various single byte encodings. For most cases it uses
+\x80-\xff (upper half) to map non-ASCII characters. Encodings
+supported are as follows.
+
+ Canonical Alias Description
+ --------------------------------------------------------------------
+ iso-8859-1 latin1
+ iso-8859-2 latin2
+ iso-8859-3 latin3
+ iso-8859-4 latin4
+ iso-8859-5 latin
+ iso-8859-6 latin
+ iso-8859-7
+ iso-8859-8
+ iso-8859-9 latin5
+ iso-8859-10 latin6
+ iso-8859-11
+ (iso-8859-12 is nonexistent)
+ iso-8859-13 latin7
+ iso-8859-14 latin8
+ iso-8859-15 latin9
+ iso-8859-16 latin10
+
+ koi8-f
+ koi8-r
+ koi8-u
+
+ viscii # ASCII + vietnamese
+
+ cp1250 WinLatin2
+ cp1251 WinCyrillic
+ cp1252 WinLatin1
+ cp1253 WinGreek
+ cp1254 WinTurkiskh
+ cp1255 WinHebrew
+ cp1256 WinArabic
+ cp1257 WinBaltic
+ cp1258 WinVietnamese
+ # all cp* are also available as ibm-* and ms-*
+
+ maccentraleuropean
+ maccroatian
+ macroman
+ maccyrillic
+ macromanian
+ macdingbats
+ macsami
+ macgreek
+ macthai
+ macicelandic
+ macturkish
+ macukraine
+
+=head1 DESCRIPTION
+
+To find how to use this module in detail, see L<Encode>.
+
+=head1 SEE ALSO
+
+L<Encode>
+
+=cut
--- /dev/null
+use 5.7.2;
+use strict;
+use ExtUtils::MakeMaker;
+
+my $name = 'Byte';
+my %tables = (
+ '8bit' =>
+ [
+ 'ascii.ucm',
+ 'koi8-r.ucm',
+ 'viscii.ucm',
+ ],
+ Mac =>
+ [
+ qw(macCentEuro.enc macCroatian.enc
+ macCyrillic.enc macDingbats.enc
+ macGreek.enc macIceland.enc
+ macRoman.enc macRumanian.enc
+ macSami.enc macThai.enc
+ macTurkish.enc macUkraine.enc),
+ ],
+
+ );
+
+opendir(ENC,'../Encode');
+while (defined(my $file = readdir(ENC)))
+{
+ if ($file =~ /(8859|ibm).*\.ucm/io)
+ {
+ push(@{$tables{$1}},$file);
+ }
+}
+closedir(ENC);
+
+WriteMakefile(
+ INC => "-I..",
+ NAME => 'Encode::'.$name,
+ VERSION_FROM => "$name.pm",
+ OBJECT => '$(O_FILES)',
+ 'dist' => {
+ COMPRESS => 'gzip -9f',
+ SUFFIX => 'gz',
+ DIST_DEFAULT => 'all tardist',
+ },
+ MAN3PODS => {},
+ # OS 390 winges about line numbers > 64K ???
+ XSOPT => '-nolinenumbers',
+ );
+
+package MY;
+
+sub post_initialize
+{
+ my ($self) = @_;
+ my %o;
+ my $x = $self->{'OBJ_EXT'};
+ # Add the table O_FILES
+ foreach my $e (keys %tables)
+ {
+ $o{$e.$x} = 1;
+ }
+ $o{"$name$x"} = 1;
+ $self->{'O_FILES'} = [sort keys %o];
+ my @files = ("$name.xs");
+ $self->{'C'} = ["$name.c"];
+ $self->{'H'} = [$self->catfile($self->updir,'encode.h')];
+ my %xs;
+ foreach my $table (keys %tables) {
+ push (@{$self->{'C'}},"$table.c");
+ # Do NOT add $table.h etc. to H_FILES unless we own up as to how they
+ # get built.
+ foreach my $ext (qw($(OBJ_EXT) .c .h _def.h .fnm)) {
+ push (@files,$table.$ext);
+ }
+ }
+ $self->{'XS'} = { "$name.xs" => "$name.c" };
+ $self->{'clean'}{'FILES'} .= join(' ',@files);
+ open(XS,">$name.xs") || die "Cannot open $name.xs:$!";
+ print XS <<'END';
+#include <EXTERN.h>
+#include <perl.h>
+#include <XSUB.h>
+#define U8 U8
+#include "../encode.h"
+END
+ foreach my $table (keys %tables) {
+ print XS qq[#include "${table}.h"\n];
+ }
+ print XS <<"END";
+
+static void
+Encode_XSEncoding(pTHX_ encode_t *enc)
+{
+ dSP;
+ HV *stash = gv_stashpv("Encode::XS", TRUE);
+ SV *sv = sv_bless(newRV_noinc(newSViv(PTR2IV(enc))),stash);
+ int i = 0;
+ PUSHMARK(sp);
+ XPUSHs(sv);
+ while (enc->name[i])
+ {
+ const char *name = enc->name[i++];
+ XPUSHs(sv_2mortal(newSVpvn(name,strlen(name))));
+ }
+ PUTBACK;
+ call_pv("Encode::define_encoding",G_DISCARD);
+ SvREFCNT_dec(sv);
+}
+
+MODULE = Encode::$name PACKAGE = Encode::$name
+PROTOTYPES: DISABLE
+BOOT:
+{
+END
+ foreach my $table (keys %tables) {
+ print XS qq[#include "${table}_def.h"\n];
+ }
+ print XS "}\n";
+ close(XS);
+ return "# Built $name.xs\n\n";
+}
+
+sub postamble
+{
+ my $self = shift;
+ my $dir = $self->catdir($self->updir,'Encode');
+ my $str = "# $name\$(OBJ_EXT) depends on .h and _def.h files not .c files - but all written by compile\n";
+ $str .= "$name.c : $name.xs ";
+ foreach my $table (keys %tables)
+ {
+ $str .= " $table.c";
+ }
+ $str .= "\n\n";
+ $str .= "$name\$(OBJ_EXT) : $name.c\n\n";
+
+ my $compile = $self->catfile($self->updir,'compile');
+ foreach my $table (keys %tables)
+ {
+ my $numlines = 1;
+ my $lengthsofar = length($str);
+ my $continuator = '';
+ $str .= "$table.c : $compile Makefile.PL";
+ foreach my $file (@{$tables{$table}})
+ {
+ $str .= $continuator.' '.$self->catfile($dir,$file);
+ if ( length($str)-$lengthsofar > 128*$numlines )
+ {
+ $continuator .= " \\\n\t";
+ $numlines++;
+ } else {
+ $continuator = '';
+ }
+ }
+ $str .= $^O eq 'VMS' # In VMS quote to preserve case
+ ? qq{\n\t\$(PERL) $compile -"Q" -o \$\@ -f $table.fnm\n\n}
+ : qq{\n\t\$(PERL) $compile -Q -o \$\@ -f $table.fnm\n\n};
+ open (FILELIST, ">$table.fnm")
+ || die "Could not open $table.fnm: $!";
+ foreach my $file (@{$tables{$table}})
+ {
+ print FILELIST $self->catfile($dir,$file) . "\n";
+ }
+ close(FILELIST);
+ }
+ return $str;
+}
+
package Encode::CN;
-our $VERSION = do { my @r = (q$Revision: 0.95 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Encode;
use Encode::CN::HZ;
use XSLoader;
XSLoader::load('Encode::CN',$VERSION);
-Encode::define_alias( qr/euc.*cn$/i => '"euc-cn"' );
-Encode::define_alias( qr/cn.*euc/i => '"euc-cn"' );
-
# Relocated from Encode.pm
# CP936 doesn't have vendor-addon for GBK, so they're identical.
Encode::define_alias( qr/^gbk$/i => '"cp936"');
cp936 Code Page 936, also known as GBK
(Extended GuoBiao)
hz 7-bit escaped GB2312 encoding
+ --------------------------------------------------------------------
To find how to use this module in detail, see L<Encode>.
# Revision history for Perl extension Encode.
#
-# $Id: Changes,v 0.95 2002/03/21 15:52:20 dankogai Exp dankogai $
+# $Id: Changes,v 0.96 2002/03/22 22:22:53 dankogai Exp dankogai $
#
-0.95 Thu Mar 22 2002
+
+0.96 Sat Mar 23 2002
+! TW/TW.pm
+! lib/Encode/Encoding.pm
+! lib/Encode/Alias.pm
+! lib/Encode/Supported.pod
+! KR/KR.pm
+ Pod Fixes by Michael G Schwern <schwern@pobox.com> via jhi
+ Message-ID: <20020322073908.GB10539@blackrider>
+! Makefile.PL
+! Encode.pm
+ "...I think we should include ISO 8859-1 as well." -- NI-S
+ Message-Id: <20020322120230.1332.8@bactrian.elixent.com>
+! JP/JP.pm
+! CN/CN.pm
+! KR/KR.pm
+! TW/TW.pm
+! lib/Encode/Alias.pm
+ alias definitions relocated to Encode::Alias so module autoloading
+ works for aliases also.
+! Encode.pm
+ encodings() now accepts args to check ExtModules.
++ Byte/Byte.pm
++ Byte/Makefile.PL
++ EBCDIC/EBCDIC.pm
++ EBCDIC/Makefile.PL
++ Symbol/Makefile.PL
++ Symbol/Symbol.pm
+! Encode.pm
+! Encode.xs
+ Latin and single byte encodings are reorganized so they are
+ demand-loaded like Encode::XX. Now only ascii is compiled into
+ Encode itself.
+! lib/Encode/Alias.pm
+ for my $k (keys %hash){ delete $hash{$k}; }
+ is depreciated; fixed.
+
+0.95 Fri Mar 22 2002
In this update, pod rewrites and alias fixes are the main issues
+ lib/Encode/Supported.pod
Describes supported encodings
gbk => cp936 relocated to CN.pm
! t/CJKalias.t
Test::More with plans (by jhi)
+
0.94 Thu Mar 21 2002
+ lib/Encode/Description.pod
! lib/Encode/Encoding.pm
--- /dev/null
+package Encode::EBCDIC;
+use Encode;
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+
+use XSLoader;
+XSLoader::load('Encode::EBCDIC',$VERSION);
+
+1;
+__END__
+=head1 NAME
+
+Encode::EBCDIC - EBCDIC Encodings
+
+=head1 SYNOPSIS
+
+ use Encode qw/encode decode/;
+ $posix_bc = encode("posix-bc", $utf8); # loads Encode::EBCDIC implicitly
+ $utf8 = decode("", $posix_bc); # ditto
+
+=head1 ABSTRACT
+
+This module implements various EBCDIC-Based encodings. Encodings
+supported are as follows.
+
+ Canonical Alias Description
+ --------------------------------------------------------------------
+ cp1047
+ cp37
+ posix-bc
+
+=head1 DESCRIPTION
+
+To find how to use this module in detail, see L<Encode>.
+
+=head1 SEE ALSO
+
+L<Encode>, L<perlebcdic>
+
+=cut
--- /dev/null
+use 5.7.2;
+use strict;
+use ExtUtils::MakeMaker;
+
+my $name = 'EBCDIC';
+my %tables = (
+ ebcdic => ['cp1047.ucm','cp37.ucm','posix-bc.ucm'],
+ );
+
+WriteMakefile(
+ INC => "-I..",
+ NAME => 'Encode::'.$name,
+ VERSION_FROM => "$name.pm",
+ OBJECT => '$(O_FILES)',
+ 'dist' => {
+ COMPRESS => 'gzip -9f',
+ SUFFIX => 'gz',
+ DIST_DEFAULT => 'all tardist',
+ },
+ MAN3PODS => {},
+ # OS 390 winges about line numbers > 64K ???
+ XSOPT => '-nolinenumbers',
+ );
+
+package MY;
+
+sub post_initialize
+{
+ my ($self) = @_;
+ my %o;
+ my $x = $self->{'OBJ_EXT'};
+ # Add the table O_FILES
+ foreach my $e (keys %tables)
+ {
+ $o{$e.$x} = 1;
+ }
+ $o{"$name$x"} = 1;
+ $self->{'O_FILES'} = [sort keys %o];
+ my @files = ("$name.xs");
+ $self->{'C'} = ["$name.c"];
+ $self->{'H'} = [$self->catfile($self->updir,'encode.h')];
+ my %xs;
+ foreach my $table (keys %tables) {
+ push (@{$self->{'C'}},"$table.c");
+ # Do NOT add $table.h etc. to H_FILES unless we own up as to how they
+ # get built.
+ foreach my $ext (qw($(OBJ_EXT) .c .h _def.h .fnm)) {
+ push (@files,$table.$ext);
+ }
+ }
+ $self->{'XS'} = { "$name.xs" => "$name.c" };
+ $self->{'clean'}{'FILES'} .= join(' ',@files);
+ open(XS,">$name.xs") || die "Cannot open $name.xs:$!";
+ print XS <<'END';
+#include <EXTERN.h>
+#include <perl.h>
+#include <XSUB.h>
+#define U8 U8
+#include "../encode.h"
+END
+ foreach my $table (keys %tables) {
+ print XS qq[#include "${table}.h"\n];
+ }
+ print XS <<"END";
+
+static void
+Encode_XSEncoding(pTHX_ encode_t *enc)
+{
+ dSP;
+ HV *stash = gv_stashpv("Encode::XS", TRUE);
+ SV *sv = sv_bless(newRV_noinc(newSViv(PTR2IV(enc))),stash);
+ int i = 0;
+ PUSHMARK(sp);
+ XPUSHs(sv);
+ while (enc->name[i])
+ {
+ const char *name = enc->name[i++];
+ XPUSHs(sv_2mortal(newSVpvn(name,strlen(name))));
+ }
+ PUTBACK;
+ call_pv("Encode::define_encoding",G_DISCARD);
+ SvREFCNT_dec(sv);
+}
+
+MODULE = Encode::$name PACKAGE = Encode::$name
+PROTOTYPES: DISABLE
+BOOT:
+{
+END
+ foreach my $table (keys %tables) {
+ print XS qq[#include "${table}_def.h"\n];
+ }
+ print XS "}\n";
+ close(XS);
+ return "# Built $name.xs\n\n";
+}
+
+sub postamble
+{
+ my $self = shift;
+ my $dir = $self->catdir($self->updir,'Encode');
+ my $str = "# $name\$(OBJ_EXT) depends on .h and _def.h files not .c files - but all written by compile\n";
+ $str .= "$name.c : $name.xs ";
+ foreach my $table (keys %tables)
+ {
+ $str .= " $table.c";
+ }
+ $str .= "\n\n";
+ $str .= "$name\$(OBJ_EXT) : $name.c\n\n";
+
+ my $compile = $self->catfile($self->updir,'compile');
+ foreach my $table (keys %tables)
+ {
+ my $numlines = 1;
+ my $lengthsofar = length($str);
+ my $continuator = '';
+ $str .= "$table.c : $compile Makefile.PL";
+ foreach my $file (@{$tables{$table}})
+ {
+ $str .= $continuator.' '.$self->catfile($dir,$file);
+ if ( length($str)-$lengthsofar > 128*$numlines )
+ {
+ $continuator .= " \\\n\t";
+ $numlines++;
+ } else {
+ $continuator = '';
+ }
+ }
+ $str .= $^O eq 'VMS' # In VMS quote to preserve case
+ ? qq{\n\t\$(PERL) $compile -"Q" -o \$\@ -f $table.fnm\n\n}
+ : qq{\n\t\$(PERL) $compile -Q -o \$\@ -f $table.fnm\n\n};
+ open (FILELIST, ">$table.fnm")
+ || die "Could not open $table.fnm: $!";
+ foreach my $file (@{$tables{$table}})
+ {
+ print FILELIST $self->catfile($dir,$file) . "\n";
+ }
+ close(FILELIST);
+ }
+ return $str;
+}
+
package Encode;
use strict;
-our $VERSION = do { my @r = (q$Revision: 0.95 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $DEBUG = 0;
require DynaLoader;
require Exporter;
our @EXPORT_OK =
qw(
define_encoding
- define_alias
from_to
is_utf8
is_8bit
use Encode::Alias;
-# Make a %encoding package variable to allow a certain amount of cheating
-our %encoding;
+# Make a %Encoding package variable to allow a certain amount of cheating
+our %Encoding;
-our %external_tables =
+our %ExtModule =
(
- 'euc-cn' => 'Encode/CN.pm',
- gb2312 => 'Encode/CN.pm',
- gb12345 => 'Encode/CN.pm',
- gbk => 'Encode/CN.pm',
- cp936 => 'Encode/CN.pm',
- 'iso-ir-165' => 'Encode/CN.pm',
- 'euc-jp' => 'Encode/JP.pm',
- 'iso-2022-jp' => 'Encode/JP.pm',
- '7bit-jis' => 'Encode/JP.pm',
- shiftjis => 'Encode/JP.pm',
- macjapan => 'Encode/JP.pm',
- cp932 => 'Encode/JP.pm',
- 'euc-kr' => 'Encode/KR.pm',
- ksc5601 => 'Encode/KR.pm',
- cp949 => 'Encode/KR.pm',
- big5 => 'Encode/TW.pm',
- 'big5-hkscs' => 'Encode/TW.pm',
- cp950 => 'Encode/TW.pm',
- gb18030 => 'Encode/HanExtra.pm',
- big5plus => 'Encode/HanExtra.pm',
- 'euc-tw' => 'Encode/HanExtra.pm',
+ viscii => 'Encode/Byte.pm',
+ 'koi8-r' => 'Encode/Byte.pm',
+ cp1047 => 'Encode/EBCDIC.pm',
+ cp37 => 'Encode/EBCDIC.pm',
+ 'posix-bc' => 'Encode/EBCDIC.pm',
+ symbol => 'Encode/Symbol.pm',
+ dingbats => 'Encode/Symbol.pm',
+ 'euc-cn' => 'Encode/CN.pm',
+ gb2312 => 'Encode/CN.pm',
+ gb12345 => 'Encode/CN.pm',
+ gbk => 'Encode/CN.pm',
+ cp936 => 'Encode/CN.pm',
+ 'iso-ir-165' => 'Encode/CN.pm',
+ 'euc-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp' => 'Encode/JP.pm',
+ '7bit-jis' => 'Encode/JP.pm',
+ shiftjis => 'Encode/JP.pm',
+ macjapan => 'Encode/JP.pm',
+ cp932 => 'Encode/JP.pm',
+ 'euc-kr' => 'Encode/KR.pm',
+ ksc5601 => 'Encode/KR.pm',
+ cp949 => 'Encode/KR.pm',
+ big5 => 'Encode/TW.pm',
+ 'big5-hkscs' => 'Encode/TW.pm',
+ cp950 => 'Encode/TW.pm',
+ gb18030 => 'Encode/HanExtra.pm',
+ big5plus => 'Encode/HanExtra.pm',
+ 'euc-tw' => 'Encode/HanExtra.pm',
);
+for my $k (2..11,13..16){
+ $ExtModule{"iso-8859-$k"} = 'Encode/Byte.pm';
+}
+
+for my $k (1250..1258){
+ $ExtModule{"cp$k"} = 'Encode/Byte.pm';
+}
+
+for my $k (qw(centeuro croatian cyrillic dingbats greek
+ iceland roman rumanian sami
+ thai turkish ukraine))
+{
+ $ExtModule{"mac$k"} = 'Encode/Byte.pm';
+}
+
+
sub encodings
{
- my ($class) = @_;
- return
- map { $_->[0] }
- sort { $a->[1] cmp $b->[1] }
- map { [$_, lc $_] }
- grep { $_ ne 'Internal' }
- keys %encoding;
+ my $class = shift;
+ my @modules = ($_[0] eq ":all") ? values %ExtModule : @_;
+ for my $m (@modules)
+ {
+ $DEBUG and warn "about to require $m;";
+ eval { require $m; };
+ }
+ return
+ map({$_->[0]}
+ sort({$a->[1] cmp $b->[1]}
+ map({[$_, lc $_]}
+ grep({ $_ ne 'Internal' } keys %Encoding))));
}
sub define_encoding
{
my $obj = shift;
my $name = shift;
- $encoding{$name} = $obj;
+ $Encoding{$name} = $obj;
my $lc = lc($name);
define_alias($lc => $obj) unless $lc eq $name;
while (@_)
return $name;
}
my $lc = lc $name;
- if (exists $encoding{$name})
+ if (exists $Encoding{$name})
{
- return $encoding{$name};
+ return $Encoding{$name};
}
- if (exists $encoding{$lc})
+ if (exists $Encoding{$lc})
{
- return $encoding{$lc};
+ return $Encoding{$lc};
}
- my $oc = $class->findAlias($name);
+ my $oc = $class->find_alias($name);
return $oc if defined $oc;
- $oc = $class->findAlias($lc) if $lc ne $name;
+ $oc = $class->find_alias($lc) if $lc ne $name;
return $oc if defined $oc;
- if (!$skip_external and exists $external_tables{$lc})
+ if (!$skip_external and exists $ExtModule{$lc})
{
- require $external_tables{$lc};
- return $encoding{$name} if exists $encoding{$name};
+ eval{ require $ExtModule{$lc}; };
+ return $Encoding{$name} if exists $Encoding{$name};
}
return;
=head2 Listing available encodings
- use Encode qw(encodings);
- @list = encodings();
+ use Encode;
+ @list = Encode->encodings();
+
+Returns a list of the canonical names of the available encodings that
+are loaded. To get a list of all available encodings including the
+ones that are not loaded yet, say
+
+ @all_encodings = Encode->encodings(":all");
+
+Or you can give the name of specific module.
+
+ @with_jp = Encode->encodings("Encode/JP.pm");
-Returns a list of the canonical names of the available encodings.
+Note in this case you have to say "Encode/JP.pm instead of Encode::JP.
To find which encodings are suppoted by this package in details,
see L<Encode::Supported>.
=head2 Defining Aliases
- use Encode qw(define_alias);
+ use Encode;
+ use Encode::Alias;
define_alias( newName => ENCODING);
Allows newName to be used as am alias for ENCODING. ENCODING may be
#include "XSUB.h"
#define U8 U8
#include "encode.h"
-#include "8859.h"
-#include "EBCDIC.h"
-#include "Symbols.h"
-
+/* #include "8859.h" */
+/* #include "EBCDIC.h" */
+/* #include "Symbols.h" */
+#include "defcodes.h"
#define UNIMPLEMENTED(x,y) y x (SV *sv, char *encoding) {dTHX; \
Perl_croak(aTHX_ "panic_unimplemented"); \
#if defined(USE_PERLIO) && !defined(USE_SFIO)
PerlIO_define_layer(aTHX_ &PerlIO_encode);
#endif
-#include "8859_def.h"
-#include "EBCDIC_def.h"
-#include "Symbols_def.h"
+/* #include "8859_def.h" */
+/* #include "EBCDIC_def.h" */
+/* #include "Symbols_def.h" */
+#include "defcodes_def.h"
}
}
}
use Encode;
-our $VERSION = do { my @r = (q$Revision: 0.94 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use XSLoader;
XSLoader::load('Encode::JP',$VERSION);
use Encode::JP::JIS;
use Encode::JP::ISO_2022_JP;
-Encode::define_alias( qr/euc.*jp$/i => '"euc-jp"' );
-Encode::define_alias( qr/jp.*euc/i => '"euc-jp"' );
-Encode::define_alias( qr/ujis$/i => '"euc-jp"' );
-Encode::define_alias( qr/shift.*jis$/i => '"shiftjis"' );
-Encode::define_alias( qr/sjis$/i => '"shiftjis"' );
-Encode::define_alias( qr/^jis$/i => '"7bit-jis"' );
-
1;
__END__
=head1 NAME
(7bit JIS with all Halfwidth Kana
converted to Fullwidth)
macjapan Mac Japan (Shift JIS + Apple vendor mappings)
- cp932 Code Page 932 (Shift JIS + Microsoft vendor mappings)
+ cp932 Code Page 932 (Shift JIS + MS/IBM vendor mappings)
+ --------------------------------------------------------------------
=head1 DESCRIPTION
package Encode::KR;
-our $VERSION = do { my @r = (q$Revision: 0.94 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Encode;
use XSLoader;
XSLoader::load('Encode::KR',$VERSION);
-Encode::define_alias( qr/euc.*kr$/i => '"euc-kr"' );
-Encode::define_alias( qr/kr.*euc/i => '"euc-kr"' );
-
1;
__END__
=head1 NAME
ksc5601 Korean standard code set
cp949 Code Page 949
(EUC-KR + Unified Hangul Code)
+ --------------------------------------------------------------------
To find how to use this module in detail, see L<Encode>.
AUTHORS List of authors
+Byte/Byte.pm Encode extension
+Byte/Makefile.PL Encode extension
CN/CN.pm Encode extension
CN/Makefile.PL Encode extension
Changes Change Log
+EBCDIC/EBCDIC.pm Encode extension
+EBCDIC/Makefile.PL Encode extension
Encode.pm Encode extension
Encode.xs Encode extension
Encode/11643-1.enc Encode table
MANIFEST Encode extension
Makefile.PL Encode extension makefile writer
README Encode extension
+Symbol/Makefile.PL Encode extension
+Symbol/Symbol.pm Encode extension
TW/Makefile.PL Encode extension
TW/TW.pm Encode extension
compile Encode extension
my %tables =
(
- 8859 => ['ascii.ucm', 'koi8-r.ucm', 'viscii.ucm',
- 'ibm-1250.ucm', 'ibm-1251.ucm',
- 'ibm-1253.ucm', 'ibm-1254.ucm',
- 'ibm-1255.ucm', 'ibm-1256.ucm',
- 'ibm-1257.ucm', 'ibm-1258.ucm',
- 'ibm-1252.ucm',
- qw(macCentEuro.enc macCroatian.enc
- macCyrillic.enc macDingbats.enc
- macGreek.enc macIceland.enc
- macRoman.enc macRumanian.enc
- macSami.enc macThai.enc
- macTurkish.enc macUkraine.enc),
- ],
- EBCDIC => ['cp1047.ucm','cp37.ucm','posix-bc.ucm'],
- Symbols => ['symbol.ucm','dingbats.ucm'],
+ defcodes => ['ascii.ucm',
+ '8859-1.ucm',
+ ]
);
-opendir(ENC,'Encode');
-while (defined(my $file = readdir(ENC)))
-{
- if ($file =~ /8859.*\.ucm/)
- {
- push(@{$tables{8859}},$file);
- }
-}
-closedir(ENC);
-
-
WriteMakefile(
NAME => "Encode",
VERSION_FROM => 'Encode.pm',
--- /dev/null
+use 5.7.2;
+use strict;
+use ExtUtils::MakeMaker;
+
+my $name = 'Symbol';
+my %tables = (
+ symbol => ['symbol.ucm','dingbats.ucm'],
+ );
+
+WriteMakefile(
+ INC => "-I..",
+ NAME => 'Encode::'.$name,
+ VERSION_FROM => "$name.pm",
+ OBJECT => '$(O_FILES)',
+ 'dist' => {
+ COMPRESS => 'gzip -9f',
+ SUFFIX => 'gz',
+ DIST_DEFAULT => 'all tardist',
+ },
+ MAN3PODS => {},
+ # OS 390 winges about line numbers > 64K ???
+ XSOPT => '-nolinenumbers',
+ );
+
+package MY;
+
+sub post_initialize
+{
+ my ($self) = @_;
+ my %o;
+ my $x = $self->{'OBJ_EXT'};
+ # Add the table O_FILES
+ foreach my $e (keys %tables)
+ {
+ $o{$e.$x} = 1;
+ }
+ $o{"$name$x"} = 1;
+ $self->{'O_FILES'} = [sort keys %o];
+ my @files = ("$name.xs");
+ $self->{'C'} = ["$name.c"];
+ $self->{'H'} = [$self->catfile($self->updir,'encode.h')];
+ my %xs;
+ foreach my $table (keys %tables) {
+ push (@{$self->{'C'}},"$table.c");
+ # Do NOT add $table.h etc. to H_FILES unless we own up as to how they
+ # get built.
+ foreach my $ext (qw($(OBJ_EXT) .c .h _def.h .fnm)) {
+ push (@files,$table.$ext);
+ }
+ }
+ $self->{'XS'} = { "$name.xs" => "$name.c" };
+ $self->{'clean'}{'FILES'} .= join(' ',@files);
+ open(XS,">$name.xs") || die "Cannot open $name.xs:$!";
+ print XS <<'END';
+#include <EXTERN.h>
+#include <perl.h>
+#include <XSUB.h>
+#define U8 U8
+#include "../encode.h"
+END
+ foreach my $table (keys %tables) {
+ print XS qq[#include "${table}.h"\n];
+ }
+ print XS <<"END";
+
+static void
+Encode_XSEncoding(pTHX_ encode_t *enc)
+{
+ dSP;
+ HV *stash = gv_stashpv("Encode::XS", TRUE);
+ SV *sv = sv_bless(newRV_noinc(newSViv(PTR2IV(enc))),stash);
+ int i = 0;
+ PUSHMARK(sp);
+ XPUSHs(sv);
+ while (enc->name[i])
+ {
+ const char *name = enc->name[i++];
+ XPUSHs(sv_2mortal(newSVpvn(name,strlen(name))));
+ }
+ PUTBACK;
+ call_pv("Encode::define_encoding",G_DISCARD);
+ SvREFCNT_dec(sv);
+}
+
+MODULE = Encode::$name PACKAGE = Encode::$name
+PROTOTYPES: DISABLE
+BOOT:
+{
+END
+ foreach my $table (keys %tables) {
+ print XS qq[#include "${table}_def.h"\n];
+ }
+ print XS "}\n";
+ close(XS);
+ return "# Built $name.xs\n\n";
+}
+
+sub postamble
+{
+ my $self = shift;
+ my $dir = $self->catdir($self->updir,'Encode');
+ my $str = "# $name\$(OBJ_EXT) depends on .h and _def.h files not .c files - but all written by compile\n";
+ $str .= "$name.c : $name.xs ";
+ foreach my $table (keys %tables)
+ {
+ $str .= " $table.c";
+ }
+ $str .= "\n\n";
+ $str .= "$name\$(OBJ_EXT) : $name.c\n\n";
+
+ my $compile = $self->catfile($self->updir,'compile');
+ foreach my $table (keys %tables)
+ {
+ my $numlines = 1;
+ my $lengthsofar = length($str);
+ my $continuator = '';
+ $str .= "$table.c : $compile Makefile.PL";
+ foreach my $file (@{$tables{$table}})
+ {
+ $str .= $continuator.' '.$self->catfile($dir,$file);
+ if ( length($str)-$lengthsofar > 128*$numlines )
+ {
+ $continuator .= " \\\n\t";
+ $numlines++;
+ } else {
+ $continuator = '';
+ }
+ }
+ $str .= $^O eq 'VMS' # In VMS quote to preserve case
+ ? qq{\n\t\$(PERL) $compile -"Q" -o \$\@ -f $table.fnm\n\n}
+ : qq{\n\t\$(PERL) $compile -Q -o \$\@ -f $table.fnm\n\n};
+ open (FILELIST, ">$table.fnm")
+ || die "Could not open $table.fnm: $!";
+ foreach my $file (@{$tables{$table}})
+ {
+ print FILELIST $self->catfile($dir,$file) . "\n";
+ }
+ close(FILELIST);
+ }
+ return $str;
+}
+
--- /dev/null
+package Encode::Symbol;
+use Encode;
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+
+use XSLoader;
+XSLoader::load('Encode::Symbol',$VERSION);
+
+1;
+__END__
+=head1 NAME
+
+Encode::Symbol - EBCDIC Encodings
+
+=head1 SYNOPSIS
+
+ use Encode qw/encode decode/;
+ $symbol = encode("symbol", $utf8); # loads Encode::Symbol implicitly
+ $utf8 = decode("", $symbol); # ditto
+
+=head1 ABSTRACT
+
+This module implements symbol and dingbats encodings. Encodings
+supported are as follows.
+
+ Canonical Alias Description
+ --------------------------------------------------------------------
+ symbol
+ dingbats
+
+=head1 DESCRIPTION
+
+To find how to use this module in detail, see L<Encode>.
+
+=head1 SEE ALSO
+
+L<Encode>
+
+=cut
package Encode::TW;
-our $VERSION = do { my @r = (q$Revision: 0.94 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Encode;
use XSLoader;
XSLoader::load('Encode::TW',$VERSION);
-Encode::define_alias( qr/big-?5$/i => '"big5"' );
-Encode::define_alias( qr/big5-hk(?:scs)?/i => '"big5-hkscs"' );
-
1;
__END__
=head1 NAME
Hong Kong
cp950 Code Page 950
(Big5 + Microsoft vendor mappings)
-
+ --------------------------------------------------------------------
+
To find how to use this module in detail, see L<Encode>.
=head1 NOTES
package Encode::Alias;
use strict;
-use Encode qw(find_encoding);
-our $VERSION = do { my @r = (q$Revision: 0.95 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+use Encode;
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
our $DEBUG = 0;
require Exporter;
our @ISA = qw(Exporter);
# Public, encouraged API is exported by default
-our @EXPORT = qw (
- findAlias
- define_alias
- );
+
+our @EXPORT =
+ qw (
+ define_alias
+ find_alias
+ );
our @Alias; # ordered matching list
our %Alias; # cached known aliases
-sub findAlias
+sub find_alias
{
my $class = shift;
local $_ = shift;
unshift(@Alias, $alias => $name); # newer one has precedence
# clear %Alias cache to allow overrides
if (ref($alias)){
- for my $k (keys %Alias){
+ my @a = keys %Alias;
+ for my $k (@a){
if (ref($alias) eq 'Regexp' && $k =~ $alias)
{
$DEBUG and warn $k;
}
}
-
-# Allow variants of iso-8859-1 etc.
-define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/i => '"iso-$1-$2"' );
-
-# At least HP-UX has these.
-define_alias( qr/^iso8859(\d+)$/i => '"iso-8859-$1"' );
-
-# More HP stuff.
-define_alias( qr/^(?:hp-)?(arabic|greek|hebrew|kana|roman|thai|turkish)8$/i => '"${1}8"' );
-
-# The Official name of ASCII.
-define_alias( qr/^ANSI[-_]?X3\.4[-_]?1968$/i => '"ascii"' );
-
-# This is a font issue, not an encoding issue.
-# (The currency symbol of the Latin 1 upper half
-# has been redefined as the euro symbol.)
-define_alias( qr/^(.+)\@euro$/i => '"$1"' );
-
# Allow latin-1 style names as well
# 0 1 2 3 4 5 6 7 8 9 10
our @Latin2iso = ( 0, 1, 2, 3, 4, 9, 10, 13, 14, 15, 16 );
-define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/i
- => '"iso-8859-$Encode::Alias::Latin2iso[$1]"' );
-
# Allow winlatin1 style names as well
our %Winlatin2cp = (
'latin1' => 1252,
'vietnamese' => 1258,
);
-define_alias( qr/win(latin[12]|cyrillic|baltic|greek|turkish|
- hebrew|arabic|baltic|vietnamese)$/ix =>
- '"cp" . $Encode::Alias::Winlatin2cp{lc($1)}' );
+init_aliases();
+
+sub undef_aliases{
+ @Alias = ();
+ %Alias = ();
+}
+
+sub init_aliases
+{
+ undef_aliases();
+# Allow variants of iso-8859-1 etc.
+ define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/i => '"iso-$1-$2"' );
+
+# At least HP-UX has these.
+ define_alias( qr/^iso8859(\d+)$/i => '"iso-8859-$1"' );
+
+# More HP stuff.
+ define_alias( qr/^(?:hp-)?(arabic|greek|hebrew|kana|roman|thai|turkish)8$/i => '"${1}8"' );
+
+# The Official name of ASCII.
+ define_alias( qr/^ANSI[-_]?X3\.4[-_]?1968$/i => '"ascii"' );
+
+# This is a font issue, not an encoding issue.
+# (The currency symbol of the Latin 1 upper half
+# has been redefined as the euro symbol.)
+ define_alias( qr/^(.+)\@euro$/i => '"$1"' );
+
+ define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/i
+ => '"iso-8859-$Encode::Alias::Latin2iso[$1]"' );
+
+ define_alias( qr/win(latin[12]|cyrillic|baltic|greek|turkish|
+ hebrew|arabic|baltic|vietnamese)$/ix =>
+ '"cp" . $Encode::Alias::Winlatin2cp{lc($1)}' );
# Common names for non-latin prefered MIME names
-define_alias( 'ascii' => 'US-ascii',
- 'cyrillic' => 'iso-8859-5',
- 'arabic' => 'iso-8859-6',
- 'greek' => 'iso-8859-7',
- 'hebrew' => 'iso-8859-8',
- 'thai' => 'iso-8859-11',
- 'tis620' => 'iso-8859-11',
- );
+ define_alias( 'ascii' => 'US-ascii',
+ 'cyrillic' => 'iso-8859-5',
+ 'arabic' => 'iso-8859-6',
+ 'greek' => 'iso-8859-7',
+ 'hebrew' => 'iso-8859-8',
+ 'thai' => 'iso-8859-11',
+ 'tis620' => 'iso-8859-11',
+ );
# At least AIX has IBM-NNN (surprisingly...) instead of cpNNN.
# And Microsoft has their own naming (again, surprisingly).
-define_alias( qr/^(?:ibm|ms)[-_]?(\d\d\d\d?)$/i => '"cp$1"');
+ define_alias( qr/^(?:ibm|ms)[-_]?(\d\d\d\d?)$/i => '"cp$1"');
# Sometimes seen with a leading zero.
-define_alias( qr/^cp037$/i => '"cp37"');
+ define_alias( qr/^cp037$/i => '"cp37"');
# Ououououou.
-define_alias( qr/^macRomanian$/i => '"macRumanian"');
+ define_alias( qr/^macRomanian$/i => '"macRumanian"');
# Standardize on the dashed versions.
-define_alias( qr/^utf8$/i => 'utf-8' );
-define_alias( qr/^koi8r$/i => 'koi8-r' );
-define_alias( qr/^koi8u$/i => 'koi8-u' );
+ define_alias( qr/^utf8$/i => 'utf-8' );
+ define_alias( qr/^koi8r$/i => 'koi8-r' );
+ define_alias( qr/^koi8u$/i => 'koi8-u' );
+
+# for Encode::CN
+ define_alias( qr/euc.*cn$/i => '"euc-cn"' );
+ define_alias( qr/cn.*euc/i => '"euc-cn"' );
+
+# for Encode::JP
+ define_alias( qr/euc.*jp$/i => '"euc-jp"' );
+ define_alias( qr/jp.*euc/i => '"euc-jp"' );
+ define_alias( qr/ujis$/i => '"euc-jp"' );
+ define_alias( qr/shift.*jis$/i => '"shiftjis"' );
+ define_alias( qr/sjis$/i => '"shiftjis"' );
+ define_alias( qr/^jis$/i => '"7bit-jis"' );
+
+# for Encode::KR
+ define_alias( qr/euc.*kr$/i => '"euc-kr"' );
+ define_alias( qr/kr.*euc/i => '"euc-kr"' );
+
+# for Encode::TW
+ define_alias( qr/big-?5$/i => '"big5"' );
+ define_alias( qr/big5-hk(?:scs)?/i => '"big5-hkscs"' );
+
+# At last, Map white space and _ to '-'
+ define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' );
+}
+
+1;
+__END__
# TODO: HP-UX '8' encodings arabic8 greek8 hebrew8 kana8 thai8 turkish8
# TODO: HP-UX '15' encodings japanese15 korean15 roi15
# Kannada Khmer Korean Laotian Malayalam Mongolian
# Oriya Sinhalese Symbol Tamil Telugu Tibetan Vietnamese
-# Map white space and _ to '-'
-define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' );
-
-1;
-__END__
=head1 NAME
Encode::Alias - alias defintions to encodings
=head1 SYNOPSIS
- use Encode qw(define_alias);
+ use Encode;
+ use Encode::Alias;
define_alias( newName => ENCODING);
=head1 DESCRIPTION
is another way to names as used in X11 font names to alias the MIME
names for the iso-8859-* family.
-=item Alias overloading
+=back
+
+=head2 Alias overloading
You can override predefined aliases by simply applying define_alias().
New alias is always evaluated first and when neccessary define_alias()
# redirect SHIFT_JIS to MS/IBM Code Page 932, which is a
# superset of SHIFT_JIS
- Encode::define_alias( qr/shift.*jis$/i => '"cp932"' );
- Encode::define_alias( qr/sjis$/i => '"cp932"' );
+ define_alias( qr/shift.*jis$/i => '"cp932"' );
+ define_alias( qr/sjis$/i => '"cp932"' );
+
+If you want to zap all predefined aliases, you can
+
+ Encode::Alias->undef_aliases;
+
+to do so. And
+
+ Encode::Alias->init_aliases;
+
+gets factory setting back.
+
=head1 SEE ALSO
L<Encode>, L<Encode::Supported>
-=back
+=cut
package Encode::Encoding;
# Base class for classes which implement encodings
use strict;
-our $VERSION = do { my @r = (q$Revision: 0.94 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
sub Define
{
__PACKAGE__->Define(qw(myCanonical myAlias));
-=head 1 DESCRIPTION
+=head1 DESCRIPTION
As mentioned in L<Encode>, encodings are (in the current
implementation at least) defined by objects. The mapping of encoding
package Encode::Internal;
use strict;
-our $VERSION = do { my @r = (q$Revision: 0.92 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use base 'Encode::Encoding';
__PACKAGE__->Define('Internal');
-Encode::define_alias( 'Unicode' => 'Internal' ) if ord('A') == 65;
+if (ord('A') == 65){
+ Encode::define_alias( 'Unicode' => 'Internal' );
+}
sub decode
{
=head1 DESCRIPTION
-=Encoding Names
+=head2 Encoding Names
Encoding names are case insensitive. White space in names
is ignored. In addition an encoding may have aliases.
o The name in the IANA registry.
o The name used by the organization that defined it.
-Because of all the alias issues, and because in the gen-
-eral case encodings have state, "Encode" uses the encoding
-object internally once an operation is in progress.
+Because of all the alias issues, and because in the general case
+encodings have state, "Encode" uses the encoding object internally
+once an operation is in progress.
-=head2 Supported Encodings
+=head1 Supported Encodings
As of Perl 5.8.0, at least the following encodings are recognized.
Note that unless otherwise specified, they are all case insensitive
(via alias) and all occurance of spaces are replaced with '-'. In
other words, "ISO 8859 1" and "iso-8859-1" are identical.
-=head3 ASCII
+Encodings are categorized and implemented in several different modules
+but you don't have to C<use Encode::XX> to make them available for
+most cases. Encode.pm will automatically load those modules in need.
- Canonical Aliases
- -----------------------
- ascii uc-ascii
+=head2 Built-in Encodings
-=head3 The Unicode
+The following encodings are always available.
- utf8 UTF-8
- utf16 UTF-16
- ucs2 UCS-2, iso-10646-1
+ Canonical Aliases
+ -----------------------
+ iso-8859-1 latin1
+ US-ascii ascii
+ UCS-2 ucs2, iso-10646-1
+ UCS-2le
+ UTF-8 utf8
+ -----------------------
-=head3 The ISO 8859, KOI, and other 1-byte encodings
+=head2 Encode::Byte
-The following encodings are based upon ASCII. For most cases it uses
-\x80-\xff (upper half) to map non-ASCII characters.
+The following encodings are based single-byte encoding implemented as
+extended ASCII. For most cases it uses \x80-\xff (upper half) to map
+non-ASCII characters.
- iso-8859-1 latin1
+ -----------------------
+ iso-8859-1 latin
iso-8859-2 latin2
iso-8859-3 latin3
iso-8859-4 latin4
macicelandic
macturkish
macukraine
+ -----------------------
-=head3 The CJK: Chinese, Japanese, Korean (Multibyte)
+=head2 The CJK: Chinese, Japanese, Korean (Multibyte)
Note Vietnamese is listed above. Also read "Encoding vs Charset"
below. Also note these are impelemented in distinct module by
languages, due the the size concerns. See these perldocs also.
- cp936 gbk # Encode::CN
- euc-cn # Encode::CN
- gb12345 # Encode::CN
- gb2312 # Encode::CN
- gb2312 # Encode::CN
- hz # Encode::CN
- iso-ir-165 # Encode::CN
-
- 7bit-jis jis # Encode::JP
- cp932 # Encode::JP
- euc-jp ujis # Encode::JP
- iso-2022-jp # Encode::JP
- macjapan # Encode::JP
- shiftjis Shift_JIS, sjis # Encode::JP
-
- euc-kr # Encode::KR
- ksc5601 # Encode::KR
- cp949 # Encode::KR
-
- big5 # Encode::TW
- big5-hkscs # Encode::TW
- cp950 # Encode::TW
-
-Due to size concerns, additional Chinese encodings including "GB
-18030", "EUC-TW" and "BIG5PLUS" are distributed separately on CPAN,
-under the name Encode::HanExtra.
-
-=head3 EBCDIC
+=over 4
+
+=item Encode::CN -- Continental China
+
+ -----------------------
+ cp936 gbk
+ euc-cn
+ gb12345
+ gb2312
+ hz
+ iso-ir-165
+ -----------------------
+
+=item Encode::JP -- Japan
+
+ -----------------------
+ 7bit-jis jis
+ cp932
+ euc-jp ujis
+ iso-2022-jp
+ macjapan
+ shiftjis Shift_JIS, sjis
+ -----------------------
+
+=item Encode::KR -- Korea
+
+ -----------------------
+ euc-kr
+ ksc5601
+ cp949
+ -----------------------
+
+=item Encode::TW -- Taiwan
+
+ -----------------------
+ big5
+ big5-hkscs
+ cp950
+ -----------------------
+
+=item Encode::HanExtra -- More Chinese via CPAN
+
+Due to size concerns, additional Chinese encodings below are
+distributed separately on CPAN, under the name Encode::HanExtra.
+
+ -----------------------
+ gb18030
+ euc-tw
+ big5plus
+ -----------------------
+
+=back
+
+=head2 Miscellaneous encodings
+
+=over 4
+
+=item Encode::EBCDIC
See perlebcdic for details.
+ -----------------------
cp1047
cp37
posix-bc
+ -----------------------
+
+=item Enocode::Symbols
-=head3 Symbols and dingbats
+For symbols and dingbats.
+ -----------------------
symbol
dingbats
+ -----------------------
+
+=back
=head1 Encoding vs. Charset
=head1 See Also
-L<Encode>, L<Encode::CN>, L<Encode::JP>, L<Encode::KR>, L<Encode::TW>
+L<Encode>,
+L<Encode::Byte>,
+L<Encode::CN>, L<Encode::JP>, L<Encode::KR>, L<Encode::TW>
+L<Encode::EBCDIC>, L<Encode::Symbol>
=cut
#!../perl
use strict;
-use Encode::CN;
-use Encode::JP;
-use Encode::KR;
-use Encode::TW;
+use Encode;
+use Encode::Alias;
my %a2c;
}
}
-use Test::More tests => (scalar keys %a2c) * 2;
+use Test::More tests => (scalar keys %a2c) * 3;
print "# alias test\n";
# now we override some of the aliases and see if it works fine
-Encode::define_alias( qr/shift.*jis$/i => '"macjapan"' );
-Encode::define_alias( qr/sjis$/i => '"cp932"' );
+define_alias( qr/shift.*jis$/i => '"macjapan"' );
+define_alias( qr/sjis$/i => '"cp932"' );
@a2c{qw(Shift_JIS x-sjis)} = qw(macjapan cp932);
is((defined($e) and $e->name), $a2c{$a});
}
+print "# alias undef test\n";
+
+Encode::Alias->undef_aliases;
+foreach my $a (keys %a2c){
+ my $e = Encode::find_encoding($a);
+ ok(!defined($e));
+}
+
__END__
for (my $i = 0; $i < @Encode::Alias::Alias; $i+=2){
my ($k, $v) = @Encode::Alias::Alias[$i, $i+1];
projects / platform / upstream / perl.git / commitdiff