From: imiyazaki <imiyazaki>
Date: Mon, 26 Jan 2004 13:26:06 +0000 (+0000)
Subject: insert explicit space.
X-Git-Url: http://git.chise.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c08ad8a7d0d044f82adbcda33c39a77f72f8d4b8;p=chise%2Fomega.git

insert explicit space.
correct punctuation characters like ``'' `'.
fix &latin_parse(). The first character will be also processed.
---

diff --git a/inCHISE b/inCHISE
index 9be4492..c2d2ebe 100755
--- a/inCHISE
+++ b/inCHISE
@@ -171,12 +171,18 @@ foreach $out_cs ('UniCNS','UniGB','UniJIS','UniKS','UniMulti'){
 while(<>){
     utf8::decode($_);
 
-    s/([$asian])\s+([$asian])/$1$2/g unless($out_cs eq 'UniKS');
-    s/([$asian])\s*([^$asian])/$1 $2/g;
-    s/([^$asian])\s*([$asian])/$1 $2/g;
     if($in_cs ne 'ucs@mcs'){
 	s/(.)/&get_char_in_mcs($1,$in_cs)/ge;
     }
+    s/([$asian])\s+([$asian])/$1$2/g unless($out_cs eq 'UniKS');
+    s/([$asian])\s*([^$asian])/$1 $2/g;
+    s/([^$asian])\s*([$asian])/$1 $2/g;
+    s/\-\-\-/pack("U",0x2014)/geo;# EM DASH
+    s/\-\-/pack("U",0x2013)/geo;# EN DASH
+    s/\`\`/pack("U",0x201f)/geo;# DOUBLE HIGH-REVERSED-9 QUOTATION MARK
+    s/\`/pack("U",0x201b)/geo;# SINGLE HIGH-REVERSED-9 QUOTATION MARK
+    s/\'\'/pack("U",0x201d)/geo;# RIGHT DOUBLE QUOTATION MARK
+    s/\'/pack("U",0x2019)/geo;# RIGHT DOUBLE QUOTATION MARK
     s/(amp.+?;)/&de_tex_er($1)/ge;
 #    s/(&.+?;)/&de_tex_er($1)/ge;
     @chars=split(//);
@@ -194,7 +200,7 @@ while(<>){
 		      and($chars[$i+1]=~/[$asian]/))){
 		    print '{\selectjisfont\hspace{.25ex}}';
 		}else{
-		    print " ";
+		    print '{\fontencoding{UT1}\fontfamily{omlgc}\selectfont{} }';
 		}
 	    }
 	    next CHAR;
@@ -219,6 +225,8 @@ while(<>){
                # Cyrillic
 	       or($char_id>=0x0530 and $char_id<=0x058f)
                # Armenian
+	       or($char_id>=0x2010 and $char_id<=0x2046)
+	       # General Punctuation (partial)
 	       ){
 	    print &latin_parse();
 	    next CHAR;
@@ -358,8 +366,7 @@ sub latin_parse{
     # arguments: none
     # return: string for output with TeX macro.
     my($char_id);
-    my $out_str=$chars[$i];
-    $i++;
+    my $out_str="";
     while($i<=$#chars){
 	$char_id=unpack("U",$chars[$i]);
 	if(($char_id>0x20 and $char_id<=0x021f)
@@ -375,6 +382,9 @@ sub latin_parse{
 	    # Latin Extended Additional
             # 0x1e00 -> 0x0600, etc.
 	    $out_str.=pack("U",$char_id-0x1800);
+	}elsif($char_id>=0x2010 and $char_id<=0x2046){
+	    # General Punctuation (partial)
+	    $out_str.=pack("U",$char_id-0x1000);
 	}else{
 	    $i--;
 	    last;