dslinux/user/perl/ext/Encode/CN CN.pm Makefile.PL
cayenne
dslinux_cayenne at user.in-berlin.de
Tue Dec 5 05:26:36 CET 2006
Update of /cvsroot/dslinux/dslinux/user/perl/ext/Encode/CN
In directory antilope:/tmp/cvs-serv7729/ext/Encode/CN
Added Files:
CN.pm Makefile.PL
Log Message:
Adding fresh perl source to HEAD to branch from
--- NEW FILE: CN.pm ---
package Encode::CN;
BEGIN {
if (ord("A") == 193) {
die "Encode::CN not supported on EBCDIC\n";
}
}
our $VERSION = do { my @r = (q$Revision: 1.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Encode;
use XSLoader;
XSLoader::load(__PACKAGE__,$VERSION);
# Relocated from Encode.pm
use Encode::CN::HZ;
# use Encode::CN::2022_CN;
1;
__END__
=head1 NAME
Encode::CN - China-based Chinese Encodings
=head1 SYNOPSIS
use Encode qw/encode decode/;
$euc_cn = encode("euc-cn", $utf8); # loads Encode::CN implicitly
$utf8 = decode("euc-cn", $euc_cn); # ditto
=head1 DESCRIPTION
This module implements China-based Chinese charset encodings.
Encodings supported are as follows.
Canonical Alias Description
--------------------------------------------------------------------
euc-cn /\beuc.*cn$/i EUC (Extended Unix Character)
/\bcn.*euc$/i
/\bGB[-_ ]?2312(?:\D.*$|$)/i (see below)
gb2312-raw The raw (low-bit) GB2312 character map
gb12345-raw Traditional chinese counterpart to
GB2312 (raw)
iso-ir-165 GB2312 + GB6345 + GB8565 + additions
MacChineseSimp GB2312 + Apple Additions
cp936 Code Page 936, also known as GBK
(Extended GuoBiao)
hz 7-bit escaped GB2312 encoding
--------------------------------------------------------------------
To find how to use this module in detail, see L<Encode>.
=head1 NOTES
Due to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
separately on CPAN, under the name L<Encode::HanExtra>. That module
also contains extra Taiwan-based encodings.
=head1 BUGS
When you see C<charset=gb2312> on mails and web pages, they really
mean C<euc-cn> encodings. To fix that, C<gb2312> is aliased to C<euc-cn>.
Use C<gb2312-raw> when you really mean it.
The ASCII region (0x00-0x7f) is preserved for all encodings, even though
this conflicts with mappings by the Unicode Consortium. See
L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
to find out why it is implemented that way.
=head1 SEE ALSO
L<Encode>
=cut
--- NEW FILE: Makefile.PL ---
use 5.7.2;
use strict;
use ExtUtils::MakeMaker;
use strict;
my %tables = (euc_cn_t => ['euc-cn.ucm',
'cp936.ucm',
'macChinsimp.ucm',
],
'2312_t' => ['gb2312.ucm'],
'12345_t' => ['gb12345.ucm'],
ir_165_t => ['ir-165.ucm'],
);
unless ($ENV{AGGREGATE_TABLES}){
my @ucm;
for my $k (keys %tables){
push @ucm, @{$tables{$k}};
}
%tables = ();
my $seq = 0;
for my $ucm (sort @ucm){
# 8.3 compliance !
my $t = sprintf ("%s_%02d_t", substr($ucm, 0, 2), $seq++);
$tables{$t} = [ $ucm ];
}
}
my $name = 'CN';
WriteMakefile(
INC => "-I../Encode",
NAME => 'Encode::'.$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',
XSPROTOARG => '-noprototypes',
);
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->{SOURCE} .= " $name.c"
if $^O eq 'MacOS' && $self->{SOURCE} !~ /\b$name\.c\b/;
$self->{'H'} = [$self->catfile($self->updir,'Encode', '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 .exh .fnm)) {
push (@files,$table.$ext);
}
$self->{SOURCE} .= " $table.c"
if $^O eq 'MacOS' && $self->{SOURCE} !~ /\b$table\.c\b/;
}
$self->{'XS'} = { "$name.xs" => "$name.c" };
$self->{'clean'}{'FILES'} .= join(' ', at files);
open(XS,">$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}.exh"\n];
}
print XS "}\n";
close(XS);
return "# Built $name.xs\n\n";
}
sub postamble
{
my $self = shift;
my $dir = $self->catdir($self->updir,'ucm');
my $str = "# $name\$(OBJ_EXT) depends on .h and .exh files not .c files - but all written by enc2xs\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 $enc2xs = $self->catfile($self->updir,'bin', 'enc2xs');
foreach my $table (keys %tables)
{
my $numlines = 1;
my $lengthsofar = length($str);
my $continuator = '';
$str .= "$table.c : $enc2xs 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 = '';
}
}
my $plib = $self->{PERL_CORE} ? '"-I$(PERL_LIB)"' : '';
$plib .= " -MCross=$::Cross::platform" if defined $::Cross::platform;
my $ucopts = '-"Q"';
$str .=
qq{\n\t\$(PERL) $plib $enc2xs $ucopts -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;
}
More information about the dslinux-commit
mailing list