X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=inCHISE;h=7a498302b1c741ce9c70efc26677e324b2e762f2;hb=5a5e431819878e0b4e9c46ebe2ff43678d7f3ca3;hp=115809f5cabdeeb7e4205c461bd4403845b81553;hpb=da4a98967af72d2e69b06f5451cf75a7a8f6daaa;p=chise%2Fomega.git diff --git a/inCHISE b/inCHISE index 115809f..7a49830 100755 --- a/inCHISE +++ b/inCHISE @@ -5,6 +5,7 @@ use strict; use vars qw($omegadb_path $opt_protrude $opt_allow_unify + $opt_use_kage_for_Ext_B %opt_order %order %order_map $opt_in_cs $opt_out_cs $opt_help $usage @@ -21,8 +22,6 @@ use Fcntl ':flock'; use Chise_utils ':all'; require 5.008; -my $omegadb_path="/usr/local/lib/chise/omega"; - ### Options ### #$opt_order{'UniMulti'}='jcgk'; @@ -35,6 +34,9 @@ $opt_order{'UniKS'}='k'; $opt_allow_unify=1; # 1=true, 0=false. $opt_protrude=0;# 1=true, 0=false. +# currently does not work. +$opt_use_kage_for_Ext_B=0;# 1=true, 0=false. + ### End ### my $strictly_forbidden_after = '「【『［（〈“‘‘（〔｛《{\[\(\x{3016}｛｢'; @@ -58,10 +60,22 @@ my $forbidden_before 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}'; +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 $space = '\x{0020}\x{0009}\x{000A}\x{000C}\x{000D}'; +my %tex_meta=('#'=>'\#', + '$'=>'\\textdollar{}', + '%'=>'\%', + '&'=>'\&', + '{'=>'\\textbraceleft{}', + '}'=>'\\textbraceright{}', + '\\'=>'\\textbackslash{}', + '_'=>'\\textunderscore', + ); + +my $tex_meta_re=join('|',map {quotemeta($_)} keys %tex_meta); + &GetOptions("in=s"=>\$opt_in_cs, "out=s"=>\$opt_out_cs, "help",\$opt_help); @@ -69,7 +83,7 @@ my $space = '\x{0020}\x{0009}\x{000A}\x{000C}\x{000D}'; $usage=< -o input coding system: - Utf8mcs, Utf8cns, Utf8gb, Utf8jis, Utf8ks + Utf8mcs, Utf8cns, Utf8gb, Utf8jis, Utf8ks, Utf8big5 cmap encoding: UniCNS, UniGB, UniJIS, UniKS, UniMulti EOF @@ -82,7 +96,7 @@ if($opt_in_cs or $opt_out_cs){ } # $in_cs: -# Utf8mcs,Utf8cns,Utf8gb,Utf8jis,Utf8ks, +# Utf8mcs,Utf8cns,Utf8gb,Utf8jis,Utf8ks,Utf8big5 # $out_cs: # UniCNS,UniGB,UniJIS,UniKS,UniMulti @@ -119,8 +133,8 @@ if(-e $idsdata_file){ $ids_argc=0; $ids=""; -$geta=pack("U",0x3013); -#$geta=pack("U",0xfffd); +#$geta=pack("U",0x3013); +$geta=pack("U",0xfffd); @GT=(#"=gt","=gt-k", "=gt-pj-1","=gt-pj-2","=gt-pj-3","=gt-pj-4","=gt-pj-5", @@ -156,9 +170,19 @@ foreach $out_cs ('UniCNS','UniGB','UniJIS','UniKS','UniMulti'){ while(<>){ utf8::decode($_); + 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(//); @@ -168,14 +192,50 @@ while(<>){ $char_id=unpack("U",$char); if($char_id<=0x20){ - print $chars[$i]; + # add quarter space between asian and non-asian. + if($i>0 and $i<$#chars){ + if(($chars[$i-1]=~/[$asian]/ + and $chars[$i+1]=~/[^$asian]/ + and $chars[$i+1]=~/[$strictly_forbidden_before$slightly_forbidden_before]/) + or($chars[$i-1]=~/[^$asian]/ + and $chars[$i+1]=~/[$asian]/ + and $chars[$i-1]=~/[$strictly_forbidden_after$slightly_forbidden_after]/) + ){ + print ''; + }elsif(($chars[$i-1]=~/[$asian]/ + and $chars[$i+1]=~/[^$asian]/) + or($chars[$i-1]=~/[^$asian]/ + and $chars[$i+1]=~/[$asian]/)){ + print '{\selectjisfont\hspace{.25ex}}'; + }else{ + print ' '; + } + } + next CHAR; + }elsif($char=~m/($tex_meta_re)/o){ + print $tex_meta{$1}; next CHAR; - }elsif($char_id>0x20 and $char_id<=0x02af){ - # Basic Latin - # Latin-1 Supplement - # Latin Extended-A - # Latin Extended-B - # IPA Extensions + }elsif(($char_id>0x20 and $char_id<=0x021f) + # Basic Latin + # Latin-1 Supplement + # Latin Extended-A + # Latin Extended-B (not all) + or($char_id>=0x0250 and $char_id<=0x02af) + # IPA Extensions + or($char_id>=0x0300 and $char_id<=0x033f) + or($char_id>=0x0360 and $char_id<=0x036f) + # Combining Diacritical Marks + or($char_id>=0x1e00 and $char_id<=0x1eff) + # Latin Extended Additional + or($char_id>=0x0370 and $char_id<=0x03ff) + # Greek and Coptic + or($char_id>=0x0400 and $char_id<=0x04ff) + # Cyrillic + or($char_id>=0x0530 and $char_id<=0x058f) + # Armenian + or($char_id>=0x2010 and $char_id<=0x2046) + # General Punctuation (partial) + ){ print &latin_parse(); next CHAR; }elsif($char_id>=0x2ff0 and $char_id<=0x2fff){ @@ -185,21 +245,6 @@ while(<>){ }else{ if(($out_char=&get_output_char($char,$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 CHAR; }else{ if($opt_allow_unify){ @chars_unified=&get_chars_unified($char); @@ -213,6 +258,24 @@ while(<>){ } } } + if($opt_use_kage_for_Ext_B){ + if($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 CHAR; + } + } if($ids=&get_ids($char)){ print &get_macro_for_ids($ids),&add_break($i); }else{ @@ -264,41 +327,46 @@ sub add_break{ if($i<($#chars-1)){ if(($chars[$i+1]=~m/[$strictly_forbidden_before]/o) and($chars[$i+2]=~m/[$strictly_forbidden_before]/o)){ - return "\\CJKunbreakablekernone "; + return "\\CJKunbreakablekernone{}"; }elsif($opt_protrude){ if(($chars[$i+1]=~m/[$strictly_forbidden_before]/o) and($chars[$i+2]=~m/[^$strictly_forbidden_before]/o)){ - return "\\CJKunbreakablekernone \\CJKprotrude "; + return "\\CJKunbreakablekernone \\CJKprotrude{}"; } } } if(($i<$#chars) + and($chars[$i+1]eq" ")){ + # preserve space. + return ""; + } + if(($i<$#chars) and($chars[$i+1]=~m/[$strictly_forbidden_before]/o)){ - return "\\CJKunbreakablekernone "; + return "\\CJKunbreakablekernone{}"; } if($chars[$i]=~m/[$strictly_forbidden_after]/o){ - return "\\CJKunbreakablekernone "; + return "\\CJKunbreakablekernone{}"; } if(($i<$#chars) and($chars[$i+1]=~m/[$forbidden_before]/o)){ - return "\\CJKunbreakablekerntwo "; + return "\\CJKunbreakablekerntwo{}"; } if($chars[$i]=~m/[$forbidden_after]/o){ - return "\\CJKunbreakablekerntwo "; + return "\\CJKunbreakablekerntwo{}"; } if(($i<$#chars) and($chars[$i+1]=~m/[$slightly_forbidden_before]/o)){ - return "\\CJKunbreakablekernthree "; + return "\\CJKunbreakablekernthree{}"; } if($chars[$i]=~m/[$slightly_forbidden_after]/o){ - return "\\CJKunbreakablekernthree "; + return "\\CJKunbreakablekernthree{}"; } if($chars[$i]=~m/[$asian]/o){ - return "\\CJKbreakablekern "; + return "\\CJKbreakablekern{}"; } if(($i<$#chars)and($chars[$i+1]=~m/[$asian]/o)){ - return "\\CJKbreakablekern "; + return "\\CJKbreakablekern{}"; } } @@ -306,19 +374,32 @@ sub latin_parse{ # arguments: none # return: string for output with TeX macro. my($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 $char_id<=0x02af){ + if(($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 $char_id<=0x036f) + or($char_id>=0x0370 and $char_id<=0x03ff)# Greek and Coptic + or($char_id>=0x0400 and $char_id<=0x04ff)# Cyrillic + or($char_id>=0x0530 and $char_id<=0x058f)# Armenian + ){ $out_str.=$chars[$i]; + }elsif($char_id>=0x1e00 and $char_id<=0x1eff){ + # 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; } $i++; } - return '{\normalfont {'.$out_str.'}}'; + return '{\fontencoding{OT1}\fontfamily{omlgc}\selectfont '.$out_str.'}';###UT1? } sub ids_parse{ @@ -368,11 +449,11 @@ sub get_macro_for_ids{ # return: TeX macro for ids # or GETA character if ids is invalid for KAGE. my($ids)=@_; - $ids=&normalize_ids($ids,"UniJIS"); + # $ids=&normalize_ids($ids,"UniJIS"); return $geta if(($ids!~/[$idc]/) or($ids=~/[\x{10000}-]/)); #irregular for KAGE. - if(not defined($ids{$ids}) and $ids{$ids}[1]>=0){ + if(not defined($ids{$ids})){ $ids{$ids}[0]=$font_start; $ids{$ids}[1]=$ids_start; $ids_start++; @@ -478,6 +559,8 @@ sub get_ids{ my $ids=""; $ids=&get_char_attribute($char,"ids-aggregated") or $ids=&get_char_attribute($char,"ids"); +# $ids=&get_char_attribute($char,"ids-decomposed") +# or $ids=&get_char_attribute($char,"ids"); # or $ids=&get_char_attribute($char,"ideographic-structure"); # $ids=~s/[? ()]//g; return $ids;