update.

[chise/omega.git] / outCMAP

diff --git a/outCMAP b/outCMAP
index eec980f..dd9411d 100755 (executable)
--- a/outCMAP
+++ b/outCMAP
@@ -12,7 +12,6 @@ use vars qw($omegadb_path
            $char $char_id $out_char
            $ids $ids_argc %ids $idsdb
            $idsdata_file $ids_start $font_start
-           %utf8mcs_map_from
            $inotp $perl56 $perl58
            @CDP @HZK @GT
            );
@@ -25,7 +24,8 @@ my $omegadb_path="/usr/local/lib/chise/omega";
 
 ### Options ###
 
-$opt_order='jtcgk';
+$opt_order='jcgk';
+#$opt_order='jtcgkhd';
 $opt_protrude=0;# 1=true, 0=false.
 
 ###
@@ -130,7 +130,7 @@ $ids="";
      "=gt-pj-1","=gt-pj-2","=gt-pj-3","=gt-pj-4","=gt-pj-5","=gt-pj-6","=gt-pj-7","=gt-pj-8","=gt-pj-9","=gt-pj-10","=gt-pj-11"
      #,"=gt-pj-k1","=gt-pj-k2"
      );
-@HZK=("=hanziku-1","=hanziku-10","=hanziku-11","=hanziku-12","=hanziku-2","=hanziku-3","=hanziku-4","=hanziku-5","=hanziku-6","=hanziku-7","=hanziku-8","=hanziku-9");
+@HZK=("=hanziku-1","=hanziku-2","=hanziku-3","=hanziku-4","=hanziku-5","=hanziku-6","=hanziku-7","=hanziku-8","=hanziku-9","=hanziku-10","=hanziku-11","=hanziku-12");
 @CDP=("=big5-cdp");
 
 %order=('c'=>'UniCNS',
@@ -138,13 +138,12 @@ $ids="";
        'j'=>'UniJIS',
        'k'=>'UniKS',
        't'=>'GT',
-#      not implemented yet.
-#      'h'=>'HZK',
-#      'd'=>'CDP',
+       'h'=>'HZK',
+       'd'=>'CDP',
        );
 
 if(defined($opt_order)){
-    if($opt_order=~/^[cgjkt]*$/){
+    if($opt_order=~/^[cgjkthd]*$/){
        @order=split(//,$opt_order);
        @order=map {$order{$_}} @order;
     }else{
@@ -167,7 +166,7 @@ while(<>){
        s/(.)/pack("U",&get_char_id(unpack("U",$1),$in_cs))/ge;
     }
     s/(amp.+?;)/&de_er($1)/ge;
-#    s/(&.+?;)/&tex_de_er($1)/ge;
+#    s/(&.+?;)/&de_er($1)/ge;
     @chars=split(//);
     for($i=0;$i<=$#chars;$i++){
        $char=$chars[$i];
@@ -176,35 +175,42 @@ while(<>){
        if($char_id<=0x20){
            print $chars[$i];
            next;
-       }elsif($char_id>0x20 and $char_id<=0xff){
+       }elsif($char_id>0x20 and $char_id<=0x02af){
            # Basic Latin
            # Latin-1 Supplement
+           # Latin Extended-A
+           # Latin Extended-B
+           # IPA Extensions
            print &latin_parse();
            next;
        }elsif($char_id>=0x2ff0 and $char_id<=0x2fff){
            # Ideographic Description Characters
            print &ids_parse();
            next;
-       }elsif($char_id >= 0x20000 && $char_id <=0x2a6df){
-           # CJK Unified Ideographs Extension B
-           if(not defined($ids{$char}) and $ids{$char}[1]>=0){
-               $ids{$char}[0]=$font_start;
-               $ids{$char}[1]=$ids_start;
-               $ids_start++;
-               if($ids_start>255){
-                   $ids_start=0;
-                   $font_start++;
-               }
-           }
-           print "{\\fontencoding{OT1}\\fontfamily{" .
-               sprintf("chise%03d",$ids{$char}[0]) .
-               "}\\selectfont\\char$ids{$char}[1]}",&add_break($i);
-           next;
        }else{
            if(($out_char=&get_output_char($char_id,$out_cs))){
                print $out_char,&add_break($i);
+           }elsif($char_id >= 0x20000 && $char_id <=0x2a6df){
+               # CJK Unified Ideographs Extension B
+               if(not defined($ids{$char}) and $ids{$char}[1]>=0){
+                   $ids{$char}[0]=$font_start;
+                   $ids{$char}[1]=$ids_start;
+                   $ids_start++;
+                   if($ids_start>255){
+                       $ids_start=0;
+                       $font_start++;
+                   }
+               }
+               print "{\\fontencoding{OT1}\\fontfamily{" .
+                   sprintf("chise%03d",$ids{$char}[0]) .
+                   "}\\selectfont\\char$ids{$char}[1]}",&add_break($i);
+               next;
            }else{
-               print &get_macro_for_ids(&get_ids($char)),&add_break($i);
+               if($ids=&get_ids($char)){
+                   print &get_macro_for_ids($ids),&add_break($i);
+               }else{
+                   print '\rule{1ex}{1ex}',&add_break($i);
+               }
            }
        }
     }
@@ -274,7 +280,7 @@ sub latin_parse{
     $i++;
     while($i<=$#chars){
        $char_id=unpack("U",$chars[$i]);
-       if($char_id<=0xff){
+       if($char_id>0x20 and $char_id<=0x02af){
            $out_str.=pack("U",$char_id);
        }else{
            $i--;
@@ -282,7 +288,7 @@ sub latin_parse{
        }
        $i++;
     }
-    return '{\fontfamily{\rmdefault}\selectfont {'.$out_str.'}}';
+    return '{\normalfont {'.$out_str.'}}';
 }
 
 sub ids_parse{
@@ -390,7 +396,7 @@ sub get_output_char{
     $char=pack('U',$char_id);
 
     if($out_cs eq 'UniJIS'
-       and &get_char_attribute($char,"adobe-unijis-utf16-h")){
+       and &get_char_attribute($char,"vnd-adobe-cid-unijis-utf16-h")){
        if($out_char_id=&get_char_attribute($char,'=ucs@jis')
           or $out_char_id=&get_char_attribute($char,'=ucs')
           or $out_char_id=&get_char_attribute($char,'=>ucs@jis')
@@ -399,7 +405,7 @@ sub get_output_char{
            return pack("U",$out_char_id);
        }
     }elsif($out_cs eq 'UniGB'
-          and &get_char_attribute($char,"adobe-unigb-ucs2-h")){
+          and &get_char_attribute($char,"vnd-adobe-cid-unigb-ucs2-h")){
        if($out_char_id=&get_char_attribute($char,'=ucs@gb')
           or $out_char_id=&get_char_attribute($char,'=ucs')
           or $out_char_id=&get_char_attribute($char,'=>ucs@gb')
@@ -408,7 +414,7 @@ sub get_output_char{
            return pack("U",$out_char_id);
        }
     }elsif($out_cs eq 'UniCNS'
-          and &get_char_attribute($char,"adobe-unicns-ucs2-h")){
+          and &get_char_attribute($char,"vnd-adobe-cid-unicns-ucs2-h")){
        if($out_char_id=&get_char_attribute($char,'=ucs@cns')
           or $out_char_id=&get_char_attribute($char,'=ucs')
           or $out_char_id=&get_char_attribute($char,'=>ucs@cns')
@@ -417,7 +423,7 @@ sub get_output_char{
            return pack("U",$out_char_id);
        }
     }elsif($out_cs eq 'UniKS'
-          and &get_char_attribute($char,"adobe-uniks-ucs2-h")){
+          and &get_char_attribute($char,"vnd-adobe-cid-uniks-ucs2-h")){
        if($out_char_id=&get_char_attribute($char,'=ucs@ks')
           or $out_char_id=&get_char_attribute($char,'=ucs')
           or $out_char_id=&get_char_attribute($char,'=>ucs@ks')
@@ -429,7 +435,7 @@ sub get_output_char{
        foreach $out_cs (@order){
     
            if($out_cs eq 'UniJIS'
-              and &get_char_attribute($char,"adobe-unijis-utf16-h")){
+              and &get_char_attribute($char,"vnd-adobe-cid-unijis-utf16-h")){
                if($out_char_id=&get_char_attribute($char,'=ucs@jis')
                   or $out_char_id=&get_char_attribute($char,'=ucs')
                   or $out_char_id=&get_char_attribute($char,'=>ucs@jis')
@@ -438,7 +444,7 @@ sub get_output_char{
                    return '{\selectjisfont\char'.$out_char_id.'}';
                }
            }elsif($out_cs eq 'UniGB'
-                  and &get_char_attribute($char,"adobe-unigb-ucs2-h")){
+                  and &get_char_attribute($char,"vnd-adobe-cid-unigb-ucs2-h")){
                if($out_char_id=&get_char_attribute($char,'=ucs@gb')
                   or $out_char_id=&get_char_attribute($char,'=ucs')
                   or $out_char_id=&get_char_attribute($char,'=>ucs@gb')
@@ -447,7 +453,7 @@ sub get_output_char{
                    return '{\selectgbsfont\char'.$out_char_id.'}';
                }
            }elsif($out_cs eq 'UniCNS'
-                  and &get_char_attribute($char,"adobe-unicns-ucs2-h")){
+                  and &get_char_attribute($char,"vnd-adobe-cid-unicns-ucs2-h")){
                if($out_char_id=&get_char_attribute($char,'=ucs@cns')
                   or $out_char_id=&get_char_attribute($char,'=ucs')
                   or $out_char_id=&get_char_attribute($char,'=>ucs@cns')
@@ -456,7 +462,7 @@ sub get_output_char{
                    return '{\selectcnsfont\char'.$out_char_id.'}';
                }
            }elsif($out_cs eq 'UniKS'
-                  and &get_char_attribute($char,"adobe-uniks-ucs2-h")){
+                  and &get_char_attribute($char,"vnd-adobe-cid-uniks-ucs2-h")){
                if($out_char_id=&get_char_attribute($char,'=ucs@ks')
                   or $out_char_id=&get_char_attribute($char,'=ucs')
                   or $out_char_id=&get_char_attribute($char,'=>ucs@ks')
@@ -482,8 +488,8 @@ sub get_ids{
     my($char)=@_;
     my $ids="";
     $ids=&get_char_attribute($char,"ids-aggregated")
-       or &get_char_attribute($char,"ids");
-#      or &get_char_attribute($char,"ideographic-structure");
+       or $ids=&get_char_attribute($char,"ids");
+#        or $ids=&get_char_attribute($char,"ideographic-structure");
     $ids=decode('utf8', $ids) if($perl58);
 #    $ids=~s/[? ()]//g;
     return $ids;
@@ -550,7 +556,7 @@ sub get_macro_for_HZK{
        }
     }
     if($hzk){
-       return "{\\fontencoding{OT1}\\fontfamily{".sprintf("hzk%02d",$HZK)."}\\selectfont\\char".($hzk|0x8080)."}";
+       return "{\\fontencoding{OT1}\\fontfamily{".sprintf("hzk%02d",$HZK)."}\\selectfont\\char".$hzk."}";
     }else{
        return undef;
     }
@@ -558,7 +564,7 @@ sub get_macro_for_HZK{
 
 sub get_macro_for_CDP{
     my($char_id)=@_;
-    my($char,$cdp);
+    my($char,$cdp,$ucs);
     $char=pack("U",$char_id);
     foreach (@CDP){
        if($cdp=&get_char_attribute($char,$_)){
@@ -566,7 +572,15 @@ sub get_macro_for_CDP{
        }
     }
     if($cdp){
-       return "{\\fontencoding{OT1}\\fontfamily{cdp}\\selectfont\\char".($cdp|0x8080)."}";
+       $ucs=&get_char_attribute(&get_chars_matching("=big5-pua",$cdp),"=ucs");
+       if($ucs){
+           return "{\\fontencoding{OT1}\\fontfamily{cdp}\\selectfont\\char"
+               .$ucs.
+                   "}";
+       }else{
+           print STDERR "This hould not happen.\n";
+           print STDERR "ucs code point of CDP: $cdp not found.\n";
+       }
     }else{
        return undef;
     }