dslinux/user/perl/ext/Encode/TW Makefile.PL TW.pm

cayenne dslinux_cayenne at user.in-berlin.de
Tue Dec 5 05:26:37 CET 2006


Update of /cvsroot/dslinux/dslinux/user/perl/ext/Encode/TW
In directory antilope:/tmp/cvs-serv7729/ext/Encode/TW

Added Files:
	Makefile.PL TW.pm 
Log Message:
Adding fresh perl source to HEAD to branch from

--- NEW FILE: Makefile.PL ---
use 5.7.2;
use strict;
use ExtUtils::MakeMaker;
use strict;

my %tables = (big5_t	=> ['big5-eten.ucm',
			    'big5-hkscs.ucm',
			    'macChintrad.ucm',
			    'cp950.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 = 'TW';

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',
	      );

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;
}


--- NEW FILE: TW.pm ---
package Encode::TW;
BEGIN {
    if (ord("A") == 193) {
	die "Encode::TW 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);

1;
__END__

=head1 NAME

Encode::TW - Taiwan-based Chinese Encodings

=head1 SYNOPSIS

    use Encode qw/encode decode/; 
    $big5 = encode("big5", $utf8); # loads Encode::TW implicitly
    $utf8 = decode("big5", $big5); # ditto

=head1 DESCRIPTION

This module implements tradition Chinese charset encodings as used
in Taiwan and Hong Kong.
Encodings supported are as follows.

  Canonical   Alias		Description
  --------------------------------------------------------------------
  big5-eten   /\bbig-?5$/i	Big5 encoding (with ETen extensions)
	      /\bbig5-?et(en)?$/i
	      /\btca-?big5$/i
  big5-hkscs  /\bbig5-?hk(scs)?$/i
              /\bhk(scs)?-?big5$/i
                                Big5 + Cantonese characters in Hong Kong
  MacChineseTrad		Big5 + Apple Vendor Mappings
  cp950		                Code Page 950 
                                = Big5 + Microsoft vendor mappings
  --------------------------------------------------------------------

To find out how to use this module in detail, see L<Encode>.

=head1 NOTES

Due to size concerns, C<EUC-TW> (Extended Unix Character), C<CCCII>
(Chinese Character Code for Information Interchange), C<BIG5PLUS>
(CMEX's Big5+) and C<BIG5EXT> (CMEX's Big5e) are distributed separately
on CPAN, under the name L<Encode::HanExtra>. That module also contains
extra China-based encodings.

=head1 BUGS

Since the original C<big5> encoding (1984) is not supported anywhere
(glibc and DOS-based systems uses C<big5> to mean C<big5-eten>; Microsoft
uses C<big5> to mean C<cp950>), a conscious decision was made to alias
C<big5> to C<big5-eten>, which is the de facto superset of the original
big5.

The C<CNS11643> encoding files are not complete. For common C<CNS11643>
manipulation, please use C<EUC-TW> in L<Encode::HanExtra>, which contains
planes 1-7.

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




More information about the dslinux-commit mailing list