summaryrefslogtreecommitdiff
path: root/cpan/lib/Jcode
diff options
context:
space:
mode:
Diffstat (limited to 'cpan/lib/Jcode')
-rw-r--r--cpan/lib/Jcode/Constants.pm33
-rw-r--r--cpan/lib/Jcode/H2Z.pm18
-rw-r--r--cpan/lib/Jcode/Tr.pm47
-rw-r--r--cpan/lib/Jcode/Unicode/Constants.pm69
-rw-r--r--cpan/lib/Jcode/Unicode/NoXS.pm34
5 files changed, 95 insertions, 106 deletions
diff --git a/cpan/lib/Jcode/Constants.pm b/cpan/lib/Jcode/Constants.pm
index 7bce2ea0..57a4b88e 100644
--- a/cpan/lib/Jcode/Constants.pm
+++ b/cpan/lib/Jcode/Constants.pm
@@ -1,5 +1,5 @@
#
-# $Id: Constants.pm,v 1.1 2000/11/15 05:44:53 dankogai Exp $
+# $Id: Constants.pm,v 1.2 2001/05/18 05:14:38 dankogai Exp dankogai $
#
package Jcode::Constants;
@@ -7,8 +7,8 @@ package Jcode::Constants;
use strict;
use vars qw($RCSID $VERSION);
-$RCSID = q$Id: Constants.pm,v 1.1 2000/11/15 05:44:53 dankogai Exp $;
-$VERSION = do { my @r = (q$Revision: 1.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+$RCSID = q$Id: Constants.pm,v 1.2 2001/05/18 05:14:38 dankogai Exp dankogai $;
+$VERSION = do { my @r = (q$Revision: 1.2 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Carp;
@@ -17,7 +17,7 @@ BEGIN {
use vars qw(@ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
@ISA = qw(Exporter);
@EXPORT = qw();
- @EXPORT_OK = qw(&_max &_mkbuf %CHARCODE %ESC %RE);
+ @EXPORT_OK = qw(%CHARCODE %ESC %RE);
%EXPORT_TAGS = ( 'all' => [ @EXPORT_OK, @EXPORT ] );
}
@@ -59,30 +59,5 @@ my %_0208 = (
UTF8 => '[\xc0-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf][\x80-\xbf]'
);
-#
-# Util. Functions
-#
-
-# Make buffer when and only when necessary
-
-sub _mkbuf {
- my $thingy = shift;
- if (ref $thingy){
- return $thingy;
- }
- else{
- my $buf = $thingy;
- return \$buf;
- }
-}
-
-sub _max {
- my $result = shift;
- for my $n (@_){
- $result = $n if $n > $result;
- }
- return $result;
-}
-
1;
diff --git a/cpan/lib/Jcode/H2Z.pm b/cpan/lib/Jcode/H2Z.pm
index 79aa3794..53c81201 100644
--- a/cpan/lib/Jcode/H2Z.pm
+++ b/cpan/lib/Jcode/H2Z.pm
@@ -1,5 +1,5 @@
#
-# $Id: H2Z.pm,v 0.61 2000/11/15 05:45:25 dankogai Exp $
+# $Id: H2Z.pm,v 0.70 2001/05/15 19:35:59 dankogai Exp $
#
package Jcode::H2Z;
@@ -7,8 +7,8 @@ package Jcode::H2Z;
use strict;
use vars qw($RCSID $VERSION);
-$RCSID = q$Id: H2Z.pm,v 0.61 2000/11/15 05:45:25 dankogai Exp $;
-$VERSION = do { my @r = (q$Revision: 0.61 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+$RCSID = q$Id: H2Z.pm,v 0.70 2001/05/15 19:35:59 dankogai Exp $;
+$VERSION = do { my @r = (q$Revision: 0.70 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Carp;
@@ -116,14 +116,14 @@ use vars qw(%_D2Z $_PAT_D2Z
# init only once;
-$_PAT_D2Z = join("|", keys %_D2Z);
-$_PAT_H2Z = join("|", keys %_H2Z);
+#$_PAT_D2Z = join("|", keys %_D2Z);
+#$_PAT_H2Z = join("|", keys %_H2Z);
%_Z2H = reverse %_H2Z;
%_Z2D = reverse %_D2Z;
-$_PAT_Z2H = join("|", keys %_Z2H);
-$_PAT_Z2D = join("|", keys %_Z2D);
+#$_PAT_Z2H = join("|", keys %_Z2H);
+#$_PAT_Z2D = join("|", keys %_Z2D);
sub h2z {
my $r_str = shift;
@@ -133,7 +133,7 @@ sub h2z {
$n = (
$$r_str =~ s(
($RE{EUC_KANA}
- (:?\x8e[\xde\xdf])?)
+ (?:\x8e[\xde\xdf])?)
){
my $str = $1;
$_D2Z{$str} || $_H2Z{$str} ||
@@ -157,7 +157,7 @@ sub z2h {
my $r_str = shift;
my $n = (
$$r_str =~ s(
- ($RE{EUC_C}|$RE{EUC_KANA})
+ ($RE{EUC_C})
){
$_Z2D{$1} || $_Z2H{$1} || $1;
}eogx
diff --git a/cpan/lib/Jcode/Tr.pm b/cpan/lib/Jcode/Tr.pm
index 4d8ee1ff..e29e29bb 100644
--- a/cpan/lib/Jcode/Tr.pm
+++ b/cpan/lib/Jcode/Tr.pm
@@ -1,5 +1,5 @@
#
-# $Id: Tr.pm,v 0.63 2000/11/22 09:05:01 dankogai Exp dankogai $
+# $Id: Tr.pm,v 0.70 2001/05/15 19:35:59 dankogai Exp $
#
package Jcode::Tr;
@@ -7,8 +7,8 @@ package Jcode::Tr;
use strict;
use vars qw($VERSION $RCSID);
-$RCSID = q$Id: Tr.pm,v 0.63 2000/11/22 09:05:01 dankogai Exp dankogai $;
-$VERSION = do { my @r = (q$Revision: 0.63 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+$RCSID = q$Id: Tr.pm,v 0.70 2001/05/15 19:35:59 dankogai Exp $;
+$VERSION = do { my @r = (q$Revision: 0.70 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Carp;
@@ -33,26 +33,29 @@ sub tr {
return $n;
}
-sub _maketable {
- my ($from, $to, $opt) = @_;
-
- grep(s/([\x8e\x8f]$RE{EUC_C}-[\x8e\x8f]$RE{EUC_C})/&_expnd3($1)/geo,
- $from,$to);
- grep(s/($RE{EUC_C}-$RE{EUC_C})/&_expnd2($1)/geo,
- $from,$to);
- grep(s/($RE{ASCII}-$RE{ASCII})/&_expnd1($1)/geo,
- $from,$to);
-
- my @to = $to =~ /[\x8e\x8f]$RE{EUC_C}|$RE{EUC_C}|[\x00-\xff]/go;
- my @from = $from =~ /[\x8e\x8f]$RE{EUC_C}|$RE{EUC_C}|[\x00-\xff]/go;
-
- push(@to, ($opt =~ /d/ ? '' : $to[$#to]) x (@from - @to)) if @to < @from;
+sub _maketable{
+ my( $from, $to, $opt ) = @_;
+
+ $from =~ s/($RE{EUC_0212}-$RE{EUC_0212})/&_expnd3($1)/geo;
+ $from =~ s/($RE{EUC_KANA}-$RE{EUC_KANA})/&_expnd2($1)/geo;
+ $from =~ s/($RE{EUC_C }-$RE{EUC_C })/&_expnd2($1)/geo;
+ $from =~ s/($RE{ASCII }-$RE{ASCII })/&_expnd1($1)/geo;
+ $to =~ s/($RE{EUC_0212}-$RE{EUC_0212})/&_expnd3($1)/geo;
+ $to =~ s/($RE{EUC_KANA}-$RE{EUC_KANA})/&_expnd2($1)/geo;
+ $to =~ s/($RE{EUC_C }-$RE{EUC_C })/&_expnd2($1)/geo;
+ $to =~ s/($RE{ASCII }-$RE{ASCII })/&_expnd1($1)/geo;
+
+ my @from = $from =~ /$RE{EUC_0212}|$RE{EUC_KANA}|$RE{EUC_C}|[\x00-\xff]/go;
+ my @to = $to =~ /$RE{EUC_0212}|$RE{EUC_KANA}|$RE{EUC_C}|[\x00-\xff]/go;
+
+ push @to, $to[-1] x $#from - $#to if $#to < $#from && $opt !~ /d/;
@_TABLE{@from} = @to;
+
}
sub _expnd1 {
my ($str) = @_;
- s/\\(.)/$1/og;
+ # s/\\(.)/$1/og; # I dunno what this was doing!?
my($c1, $c2) = unpack('CxC', $str);
if ($c1 <= $c2) {
for ($str = ''; $c1 <= $c2; $c1++) {
@@ -75,10 +78,10 @@ sub _expnd2 {
sub _expnd3 {
my ($str) = @_;
- my ($c1, $c2, $c3, $c4) = unpack('CCCxCCC', $str);
- if ($c1 == $c3 && $c2 <= $c4) {
- for ($str = ''; $c2 <= $c4; $c2++) {
- $str .= pack('CCC', $c1, $c2);
+ my ($c1, $c2, $c3, $c4, $c5, $c6) = unpack('CCCxCCC', $str);
+ if ($c1 == $c4 && $c2 == $c5 && $c3 <= $c6) {
+ for ($str = ''; $c3 <= $c6; $c3++) {
+ $str .= pack('CCC', $c1, $c2, $c3);
}
}
return $str;
diff --git a/cpan/lib/Jcode/Unicode/Constants.pm b/cpan/lib/Jcode/Unicode/Constants.pm
index 4538da03..f3769683 100644
--- a/cpan/lib/Jcode/Unicode/Constants.pm
+++ b/cpan/lib/Jcode/Unicode/Constants.pm
@@ -1,14 +1,45 @@
#
-# $Id: Constants.pm,v 1.1 2000/11/15 05:44:53 dankogai Exp $
+# $Id: Constants.pm,v 1.2 2001/05/18 05:14:38 dankogai Exp dankogai $
#
package Jcode::Unicode::Constants;
+=head1 NAME
+
+Jcode::Unicode::Constants -- UCS2-EUC conversion table
+
+=head1 SYNOPSIS
+
+NONE
+
+=head1 DESCRIPTION
+
+This module just contains a huge hash that converts UCS2 from/to EUC.
+
+=head1 SEE ALSO
+
+ftp://ftp.unicode.org/Public/MAPPINGS/EASTASIA/JIS/
+
+Unicode mapping data
+
+=head1 COPYRIGHT
+
+Copyright 1999 Dan Kogai <dankogai@dan.co.jp>
+
+This library is free software; you can redistribute it
+and/or modify it under the same terms as Perl itself.
+
+Unicode conversion table here is based on files at
+ftp://ftp.unicode.org/Public/MAPPINGS/EASTASIA/JIS/,
+Copyright (c) 1991-1994 Unicode, Inc.
+
+=cut
+
use strict;
use vars qw($RCSID $VERSION);
-$RCSID = q$Id: Constants.pm,v 1.1 2000/11/15 05:44:53 dankogai Exp $;
-$VERSION = do { my @r = (q$Revision: 1.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+$RCSID = q$Id: Constants.pm,v 1.2 2001/05/18 05:14:38 dankogai Exp dankogai $;
+$VERSION = do { my @r = (q$Revision: 1.2 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Carp;
@@ -13041,35 +13072,3 @@ for my $c (0x00..0x7f){
%_E2U = ();
1;
-
-
-=head1 NAME
-
-Jcode::Unicode::Constants -- UCS2-EUC conversion table
-
-=head1 SYNOPSIS
-
-NONE
-
-=head1 DESCRIPTION
-
-This module just contains a huge hash that converts UCS2 from/to EUC.
-
-=head1 SEE ALSO
-
-=item ftp://ftp.unicode.org/Public/MAPPINGS/EASTASIA/JIS/
-
-Unicode mapping data
-
-=head1 COPYRIGHT
-
-Copyright 1999 Dan Kogai <dankogai@dan.co.jp>
-
-This library is free software; you can redistribute it
-and/or modify it under the same terms as Perl itself.
-
-Unicode conversion table here is based on files at
-ftp://ftp.unicode.org/Public/MAPPINGS/EASTASIA/JIS/,
-Copyright (c) 1991-1994 Unicode, Inc.
-
-=cut
diff --git a/cpan/lib/Jcode/Unicode/NoXS.pm b/cpan/lib/Jcode/Unicode/NoXS.pm
index f0f0b57e..44800ea3 100644
--- a/cpan/lib/Jcode/Unicode/NoXS.pm
+++ b/cpan/lib/Jcode/Unicode/NoXS.pm
@@ -1,5 +1,5 @@
#
-# $Id: NoXS.pm,v 0.61 2000/11/15 05:45:25 dankogai Exp $
+# $Id: NoXS.pm,v 0.71 2001/05/18 05:14:38 dankogai Exp dankogai $
#
package Jcode::Unicode::NoXS;
@@ -7,8 +7,8 @@ package Jcode::Unicode::NoXS;
use strict;
use vars qw($RCSID $VERSION);
-$RCSID = q$Id: NoXS.pm,v 0.61 2000/11/15 05:45:25 dankogai Exp $;
-$VERSION = do { my @r = (q$Revision: 0.61 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+$RCSID = q$Id: NoXS.pm,v 0.71 2001/05/18 05:14:38 dankogai Exp dankogai $;
+$VERSION = do { my @r = (q$Revision: 0.71 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
use Carp;
@@ -55,7 +55,7 @@ sub _init_e2u{
sub Jcode::ucs2_euc{
my $thingy = shift;
- my $r_str = _mkbuf($thingy);
+ my $r_str = ref $thingy ? $thingy : \$thingy;
_init_u2e();
$$r_str =~ s(
@@ -70,13 +70,13 @@ sub Jcode::ucs2_euc{
sub Jcode::euc_ucs2{
my $thingy = shift;
- my $r_str = _mkbuf($thingy);
+ my $r_str = ref $thingy ? $thingy : \$thingy;
_init_e2u();
# 3 bytes
$$r_str =~ s(
($RE{EUC_0212}|$RE{EUC_C}|$RE{EUC_KANA}|[\x00-\xff])
- )
+ )
{
exists $_E2U{$1} ? $_E2U{$1} : $CHARCODE{UNDEF_UNICODE};
}geox;
@@ -86,21 +86,21 @@ sub Jcode::euc_ucs2{
sub Jcode::euc_utf8{
my $thingy = shift;
- my $r_str = _mkbuf($thingy);
+ my $r_str = ref $thingy ? $thingy : \$thingy;
&Jcode::euc_ucs2($r_str);
&Jcode::ucs2_utf8($r_str);
}
sub Jcode::utf8_euc{
my $thingy = shift;
- my $r_str = _mkbuf($thingy);
+ my $r_str = ref $thingy ? $thingy : \$thingy;
&Jcode::utf8_ucs2($r_str);
&Jcode::ucs2_euc($r_str);
}
sub Jcode::ucs2_utf8{
my $thingy = shift;
- my $r_str = _mkbuf($thingy);
+ my $r_str = ref $thingy ? $thingy : \$thingy;
my $result;
for my $uc (unpack("n*", $$r_str)) {
if ($uc < 0x80) {
@@ -123,7 +123,7 @@ sub Jcode::ucs2_utf8{
sub Jcode::utf8_ucs2{
my $thingy = shift;
- my $r_str = _mkbuf($thingy);
+ my $r_str = ref $thingy ? $thingy : \$thingy;
my $result;
$$r_str =~ s/^[\200-\277]+//o; # can't start with 10xxxxxx
$$r_str =~
@@ -162,6 +162,8 @@ This module is called by Jcode.pm on demand. This module is not intended for
direct use by users. This modules implements functions related to Unicode.
Following functions are defined here;
+=over 4
+
=item Jcode::ucs2_euc();
=item Jcode::euc_ucs2();
@@ -174,10 +176,14 @@ Following functions are defined here;
=item Jcode::utf8_euc();
+=back
+
=cut
=head1 VARIABLES
+=over 4
+
=item B<$Jcode::Unicode::PEDANTIC>
When set to non-zero, x-to-unicode conversion becomes pedantic.
@@ -186,12 +192,18 @@ That is, '\' (chr(0x5c)) is converted to zenkaku backslash and
By Default, Jcode::Unicode leaves ascii ([0x00-0x7f]) as it is.
+=back
+
=head1 MODULES
+=over 4
+
=item Jcode::Unicode::Constants
Jumbo hash that contains UCS2-EUC conversion table is there.
+=back
+
=head1 BUGS
* It's very slow to initialize, due to the size of the conversion
@@ -201,7 +213,7 @@ Jumbo hash that contains UCS2-EUC conversion table is there.
=head1 SEE ALSO
-=item http://www.unicode.org/
+http://www.unicode.org/
=head1 COPYRIGHT
generated by cgit v1.2.1 (git 2.18.0) at 2026-09-03 09:00:05 +0000