-#!/usr/bin/perl
+#!/usr/bin/perl -w -CID
use strict;
use vars qw($opt_in_cs $opt_order $opt_kage $opt_replace
@CDP @HZK @GT
);
use Getopt::Long;
-use utf8;
use Fcntl ':flock';
+use utf8;
use Chise_utils ':all';
+require 5.008;
my $omegadb_path="/usr/local/lib/chise/omega";
$omegadb_path=~s!/$!!;
my $exec_makefonts=0;
my $geta=pack("S",8750|0x8080);
-if($^V and $^V ge v5.8){
- $perl58=1;
-}elsif($^V and $^V ge v5.6){
- $perl56=1;
-}else{
- print STDERR "This versin is not supported.";
-}
-if($perl58){
- eval "use Encode";
- binmode(STDIN, ':encoding(utf8)');
- binmode(STDOUT, ':encoding(utf8)');
-}
-
&GetOptions("in=s"=>\$opt_in_cs,
"order=s"=>\$opt_order,
"replace",\$opt_replace,
g: GB
j: JIS
k: KS
- t: GT
+ G: GT
m: Multi, use \\UTFM of otf.sty
You can also combine them, ex. jtcgkm
k: use Kage server.
'g'=>'UniGB',
'j'=>'UniJIS',
'k'=>'UniKS',
- 't'=>'GT',
+ 'G'=>'GT',
'm'=>'Multi',
);
}
if(defined($opt_order)){
- if($opt_order=~/^[cgjktm]+$/){
+ if($opt_order=~/^[cgjkGm]+$/){
@order=split(//,$opt_order);
@order=map {$order{$_}} @order;
}else{
if($in_cs ne 'ucs@mcs'){
s/(.)/pack("U",&get_char_id(unpack("U",$1),$in_cs))/ge;
}
- s/((?:^|[^\\])(?:\\\\)*)(&.*?;)/$1.&de_er($2)/ge;
+ s/((?:^|[^\\])(?:\\\\)*)(&.*?;)/&de_tex_er($1,$2)/ge;
s/((?:^|[^\\])(?:\\\\)*)\\([$idc])/$1.'\UTFM{'.sprintf("%X",unpack("U",$2)).'}'/ge;
@chars=split(//);
for($i=0;$i<=$#chars;$i++){
print IDSDATA 'use utf8;',"\n";
foreach $ids (keys %ids){
print IDSDATA '$ids{\'',$ids,'\'}='
- ,'[',join ",",@{$ids{$ids}},"];\n" if($perl56);
- print IDSDATA '$ids{\'',encode('utf8',$ids),'\'}='
- ,'[',join ",",@{$ids{$ids}},"];\n" if($perl58);
+ ,'[',join ",",@{$ids{$ids}},"];\n";
}
print IDSDATA '$font_start=',$font_start,";\n";
print IDSDATA '$ids_start=',$ids_start,";\n";
print IDSDATA "1;";
+flock(IDSDATA,LOCK_UN);
if($exec_makefonts){
if(-f $makefonts){
exit 0;
+sub de_tex_er{
+ my($before_er,$er)=@_;
+ my($prefix,$suffix);
+ my($output_char,$atr,$value);
+ $er=~/^(\&)(.*)(;)$/
+ and $prefix=$1,$er=$2,$suffix=$3;
+ $prefix or $prefix="",$suffix or $suffix="";
+ if($er=~/^U[\+|\-]([a-fA-F\d]+)/){
+ $output_char=pack("U",hex($1));
+ }elsif($er=~/^(?:I\-)?($er_prefix_re)\-?([0-9a-fA-F]+)$/){
+ ($atr,$value)=($1,$2);
+ unless($er_alias{$atr}=~/daikanwa|gt/){
+ $value=hex($value);
+ }
+ ($output_char)=&get_chars_matching($er_alias{$atr},$value);
+ utf8::decode($output_char);
+ }
+ if($output_char){
+ return $before_er.$output_char;
+ }else{
+ return $before_er.$prefix.$er.$suffix;
+ }
+}
+
sub ids_parse{
# arguments: none
# return: return character for output,
and($out_char=&get_output_char($char_id))){
return $out_char;
}else{
- return &get_macro_for_ids($ids) if($perl56);
- return encode('utf8', &get_macro_for_ids($ids)) if($perl58);
+ return &get_macro_for_ids($ids);
}
}
}
}else{
$ids_argc--;
}
- $ids.=$char if($perl56);
- $ids.=encode('utf8',$char) if($perl58);
+ $ids.=$char;
+# $ids.=$char if($perl56);
+# $ids.=encode('utf8',$char) if($perl58);
return ($ids,$ids_argc);
}
# argument: <ids>, <output coding system>
# return: ids or GETA character if ids is invalid for KAGE.
my($ids,$out_cs)=@_;
- $ids = decode('utf8', $ids) if $perl58;
$out_cs=~s/Uni(.+)/'ucs@'.lc($1)/e;
my $output_ids="";
my $ids="";
$ids=&get_char_attribute($char,"ids-aggregated")
or &get_char_attribute($char,"ids");
- $ids=decode('utf8', $ids) if($perl58);
return $ids;
}
# return: char-id
my($ids)=@_;
my($output_char);
- $ids=decode('utf8', $ids) if($perl58);
if(($output_char)=&get_chars_matching("ids",$ids)){
return unpack("U",$output_char);