$opt_use_kage_for_Ext_B
%opt_order %order %order_map
$opt_in_cs $opt_out_cs
+ $opt_preserve_spaces
$opt_help $usage
$in_cs $out_cs $i @chars
$char $char_id $out_char
### Options ###
-#$opt_order{'UniMulti'}='jcgk';
-$opt_order{'UniMulti'}='jGcgkHC';
+$opt_order{'UniMulti'}='jGcgk';
+#$opt_order{'UniMulti'}='jGcgkHC';
$opt_order{'UniCNS'}='c';
$opt_order{'UniGB'}='g';
$opt_order{'UniJIS'}='j';
### End ###
-my $strictly_forbidden_after = '「【『[(〈“‘‘(〔{《{\[\(\x{3016}{「';
-# \x{3016} | # white 【
+my $strictly_forbidden_after = '「【『[(〈‘‛“‟(〔{《{\[\(〖{「';
my $forbidden_after = "\x{0000}";
# All these characters are allowed to protrude
# in the right margin
my $strictly_forbidden_before=
- '!,.:;?、。!,.:;?。\)#}’”〉》」』】〕\x{3017})]}}」\]';
-### \x{3017} | # white 】
+ '!,.:;?、。!,.:;?。\)\]}’”〉》」』】〕〗)]}」';
my $forbidden_before
= 'ー々ぁぃぅぇぉゃゅょっゎァィゥェォャュョッヮヵヶ';
my $slightly_forbidden_before
= '\x{000a}\#\-‐−‰′″℃゛゜ゝゞヽヾ"%-゙゚';
-my $asian = '\x{1100}-\x{11FF}\x{2E80}-\x{D7AF}\x{F900}-\x{FAFF}\x{FE30}-\x{FE4F}\x{FF00}-\x{FFFFFF}'; # need to fix.
+#my $asian = '\x{1100}-\x{11FF}\x{2E80}-\x{D7AF}\x{F900}-\x{FAFF}\x{FE30}-\x{FE4F}\x{FF00}-\x{FFFFFF}'; # need to be fixed.
+my $asian = '\x{2E80}-\x{312f}\x{3190}-\x{ABFF}\x{F900}-\x{FAFF}\x{FE30}-\x{FE4F}\x{FF00}-\x{FFFFFF}'; # need to be fixed.
my $space = '\x{0020}\x{0009}\x{000A}\x{000C}\x{000D}';
+my $hangul='\x{1100}-\x{11ff}\x{3130}-\x{318f}\x{AC00}-\x{D7AF}';
+
my %tex_meta=('#'=>'\#',
'$'=>'\\textdollar{}',
'%'=>'\%',
$in_cs=$opt_in_cs;
$out_cs=$opt_out_cs;
}elsif(@ARGV==0){
- ($in_cs,$out_cs)=($0=~/(Utf8.+)To(\w+)/);
+ ($in_cs
+ ,$out_cs
+ ,$opt_preserve_spaces)
+ =($0=~/(Utf8mcs|Utf8cns|Utf8gb|Utf8jis|Utf8ks|Utf8big5)
+ To (UniCNS|UniGB|UniJIS|UniKS|UniMulti)
+ (Sp)?/ox);
}
# $in_cs:
$omegadb_path=~s!/$!!;
-$idsdata_file="$omegadb_path/idsdata.pl";
+$idsdata_file="$omegadb_path/idsdata.txt";
$ids_start=0x00;
$font_start=0;
flock(IDSDATA,LOCK_EX);
seek(IDSDATA,0,0);
while(<IDSDATA>){
- eval $_;
+ utf8::decode($_);
+ if(m/^START\t(\d+)\t(\d+)/){
+ $font_start=$1,$ids_start=$2;
+ }elsif(m/^(.*?)\t(\d+)\t(\d+)/){
+ $ids{$1}=[$2,$3,];
+ }else{
+ die "Irregular IDS file: $idsdata_file.\n";
+ }
}
seek(IDSDATA,0,0);
-# require $idsdata_file;
+ truncate(IDSDATA,0);
}else{
open(IDSDATA,">:utf8",$idsdata_file) or die;
flock(IDSDATA,LOCK_EX);
}
}
+$/="";
+
while(<>){
utf8::decode($_);
+ print '{\relax{}';
+
if($in_cs ne 'ucs@mcs'){
s/(.)/&get_char_in_mcs($1,$in_cs)/ge;
}
s/(amp.+?;)/&de_tex_er($1)/ge;
# s/(&.+?;)/&de_tex_er($1)/ge;
- s/([$asian])\s+([$asian])/$1$2/g unless($out_cs eq 'UniKS');
- s/([$asian])\s*([^$asian])/$1 $2/g;
- s/([^$asian$idc])\s*([$asian])/$1 $2/g;
+ s/([$asian])[$space]+/$1/go unless($opt_preserve_spaces);
+ s/[$space]+([$asian])/$1/go unless($opt_preserve_spaces);
+ s/([$asian])\s*([^$asian$space])/$1 $2/go;
+ s/([^$asian$idc])\s*([$asian])/$1 $2/go;
s/\-\-\-/pack("U",0x2014)/geo;# EM DASH
s/\-\-/pack("U",0x2013)/geo;# EN DASH
- s/\`\`/pack("U",0x201f)/geo;# DOUBLE HIGH-REVERSED-9 QUOTATION MARK
- s/\`/pack("U",0x201b)/geo;# SINGLE HIGH-REVERSED-9 QUOTATION MARK
+# s/\`\`/pack("U",0x201f)/geo;# DOUBLE HIGH-REVERSED-9 QUOTATION MARK
+ s/\`\`/pack("U",0x201c)/geo;# _TeX compatible_
+# s/\`/pack("U",0x201b)/geo;# SINGLE HIGH-REVERSED-9 QUOTATION MARK
+ s/\`/pack("U",0x2018)/geo;# _TeX compatible_
s/\'\'/pack("U",0x201d)/geo;# RIGHT DOUBLE QUOTATION MARK
s/\'/pack("U",0x2019)/geo;# RIGHT DOUBLE QUOTATION MARK
@chars=split(//);
+
CHAR:
for($i=0;$i<=$#chars;$i++){
$char=$chars[$i];
- $char_id=unpack("U",$char);
+ if($char_id=&get_char_attribute($char,'=ucs@unicode')){
+ $char=pack("U",$char_id);
+ }else{
+ $char_id=unpack("U",$char);
+ }
if($char_id<=0x20){
# add quarter space between asian and non-asian.
){
print '';
}elsif(($chars[$i-1]=~/[$asian]/
- and $chars[$i+1]=~/[^$asian]/)
- or($chars[$i-1]=~/[^$asian]/
- and $chars[$i+1]=~/[$asian]/)){
- print '{\selectjisfont\hspace{.25ex}}';
+ and $chars[$i+1]=~/[^$asian]/)){
+ print '\unskip\kern.25ex';
+ }elsif($chars[$i-1]=~/[^$asian]/
+ and $chars[$i+1]=~/[$asian]/){
+ print '\kern.25ex';
}else{
print ' ';
}
+ }else{
+ print ' ';
}
next CHAR;
- }elsif($char=~m/($tex_meta_re)/o){
- print $tex_meta{$1};
- next CHAR;
}elsif(($char_id>0x20 and $char_id<=0x021f)
# Basic Latin
# Latin-1 Supplement
}
}
}
+ print '}';
}
-print IDSDATA 'use utf8;',"\n";
+print IDSDATA 'START',"\t",$font_start,"\t",$ids_start,"\n";
foreach $ids (keys %ids){
- print IDSDATA '$ids{\'',$ids,'\'}='
- ,'[',join ",",@{$ids{$ids}},"];\n";
+ print IDSDATA $ids,"\t",join("\t",@{$ids{$ids}}),"\n";
}
-print IDSDATA '$font_start=',$font_start,";\n";
-print IDSDATA '$ids_start=',$ids_start,";\n";
-print IDSDATA "1;";
flock(IDSDATA,LOCK_UN);
exit 0;
my $out_str="";
while($i<=$#chars){
$char_id=unpack("U",$chars[$i]);
- if(($char_id>0x20 and $char_id<=0x021f)
+ if($chars[$i]=~m/($tex_meta_re)/o){
+ $out_str.=$tex_meta{$chars[$i]};
+ }elsif(($char_id>0x20 and $char_id<=0x021f)
or($char_id>=0x0250 and $char_id<=0x02af)# IPA Extensions
or($char_id>=0x0300 and $char_id<=0x033f)# Combining Diacritical Marks
or($char_id>=0x0360 and $char_id<=0x036f)
}
return "{\\fontencoding{OT1}\\fontfamily{"
.sprintf("chise%03d",$ids{$ids}[0])
- ."}\\selectfont\\char$ids{$ids}[1]}";
+ ."}\\selectfont\\char$ids{$ids}[1]}\\relax{}";
}
sub normalize_ids{
# return: ids
my($char)=@_;
my $ids="";
- $ids=&get_char_attribute($char,"ids-aggregated")
- or $ids=&get_char_attribute($char,"ids");
-# $ids=&get_char_attribute($char,"ids-decomposed")
+# $ids=&get_char_attribute($char,"ids-aggregated")
# or $ids=&get_char_attribute($char,"ids");
-# or $ids=&get_char_attribute($char,"ideographic-structure");
-# $ids=~s/[? ()]//g;
+ $ids=&get_char_attribute($char,"ids-decomposed")
+ or $ids=&get_char_attribute($char,"ids")
+ or $ids=&get_char_attribute($char,"ideographic-structure");
+ $ids=~s/[? ()]//g;
return $ids;
}
my($char,$in_cs)=@_;
my($output_char);
- return $char if($in_cs eq 'ucs@mcs');
+ return $char if($in_cs eq 'ucs@mcs' or
+ $char le "~");
if(($output_char)=&get_chars_matching("=$in_cs",unpack("U",$char))){
return $output_char;
sub get_chars_unified{
my($char)=@_;
- my($chars,$ucs,$char_ucs);
+ my($chars,$ucs,$char_ucs,$char_sub);
my(@chars);
if($chars=&get_char_attribute($char,'->ucs-unified')){
$chars=~s/^\((.*)\)$/$1/;
return (split(/\s*\?/,$chars));
}elsif($ucs=&get_char_attribute($char,'=>ucs*')
- or $ucs=&get_char_attribute($char,'=>ucs')){
+ or $ucs=&get_char_attribute($char,'=>ucs')){
$char_ucs=pack("U",$ucs);
if($chars=&get_char_attribute($char_ucs,'->ucs-unified')){
$chars=~s/^\((.*)\)$/$1/;
push(@chars,$char_ucs);
return @chars;
}
+ }elsif($char_sub=&get_char_attribute($char,'<-subsumptive')){
+ $char_sub=~s/[? ()]//g;
+ $chars=&get_char_attribute($char_sub,'->subsumptive');
+ @chars=grep {not /^$char$/} (split(/\s*\?/,$chars));
+ push(@chars,$char_sub);
+ return @chars;
+ }else{
+ return ();
}
}