diff -urN a2ps-4.13.ORIG/Makefile.am a2ps-4.13/Makefile.am --- a2ps-4.13.ORIG/Makefile.am 2003-09-27 04:40:36.000000000 +0900 +++ a2ps-4.13/Makefile.am 2003-09-27 05:46:04.000000000 +0900 @@ -20,7 +20,7 @@ ## Make sure to drop doc at the end: it causes may problems, so ## let's do the maximum before it -SUBDIRS = auxdir m4 etc ps ogonkify \ +SUBDIRS = auxdir m4 etc ps ogonkify libjcode \ lib src po tests sheets encoding afm fonts ppd contrib doc man ACLOCAL_AMFLAGS = -I m4 diff -urN a2ps-4.13.ORIG/Makefile.in a2ps-4.13/Makefile.in --- a2ps-4.13.ORIG/Makefile.in 2003-09-27 05:07:20.000000000 +0900 +++ a2ps-4.13/Makefile.in 2003-09-27 05:46:35.000000000 +0900 @@ -275,7 +275,7 @@ target_alias = @target_alias@ tex = @tex@ AUTOMAKE_OPTIONS = check-news 1.6.3 dist-bzip2 readme-alpha -SUBDIRS = auxdir m4 etc ps ogonkify \ +SUBDIRS = auxdir m4 etc ps ogonkify libjcode \ lib src po tests sheets encoding afm fonts ppd contrib doc man ACLOCAL_AMFLAGS = -I m4 diff -urN a2ps-4.13.ORIG/README.jp a2ps-4.13/README.jp --- a2ps-4.13.ORIG/README.jp 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/README.jp 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,89 @@ +a2ps 4.12で漢字を印刷するためのパッチ + 慶應大学大学院 + 古川 泰之 + +composite font を使って漢字を表示するためのパッチです。 +composite fontには、片山 紀夫さん(はじめて日本語ghostscriptを作成した +人)のfixeucfont をベースにa2ps用に多少手をいれております。これを利用す +ることで、2バイトEUC＋ASCIIの文字列のPostscriptの扱いがぐっと簡単にな +ります。 + +●Compositeフォントの設定方法について +最低限の設定はパッチに含まれていますので、とりあえず大丈夫だとは思いま +す。一応メモしておきます。 + +encodingファイル($prefix/share/a2ps/encoding/の下のファイル)には +『Composite:』および、『DefaultComposite:』が新たに指定できます。たと +えば、英語フォントに対応するEUCエンコーディングの日本語フォントを書い +て行きます。また、この際、フォント幅と半角と漢字の比も指定しなくてはな +りません。手抜きによって、漢字は固定幅フォントしか指定してはいけません。 + +-------------------------------------------------- +# 日本語フォント フォン横幅 半角と漢字の比 +DefaultComposite: Ryumin-Light-EUC-H 1 1.1 +# 英語フォント 日本語フォント フォン横幅 半角と漢字の比 +Composite: Helvetica GothicBBB-Medium-EUC-H 1 1.1 +-------------------------------------------------- + +また、これだと斜体漢字がなく、さみしいので、SlantFontを使い、斜体の漢 +字フォントも作成できます。 + +-------------------------------------------------- +# 新規斜体日本語フォント名 ソース日本語フォント 傾き度 +SlantFont: Ryumin-Light-EUC-H-Italic Ryumin-Light-EUC-H 0.2 +-------------------------------------------------- + +SlantFontで生成した斜体フォントはCompositeフォント(第2引数)で利用でき +ます。 + +●このパッチの詳細データ + ・残念ながら2バイトEUCコードを前提としたコーディングをしています。 + そのため、あまり漢字以外の言語を考えておりません…。 + ・倉光 君郎氏のlibjcodeを使って内部で入力ファイルの漢字エンコーディ + ングをすべてEUCに変換して処理するようにしています。ただし、オリジ + ナルのlibjcodeは、SJISおよびEUCの判定が甘かったので多少カスタムし + ております。 + ・また、texのdelegate(contrib/texi2dvi4a2ps)中、TeXドライバにはpTeX + と決めうちしています。これがいやなら、例えばNTT-jTeXを使用したい場 + 合、環境変数TEXに『jtex』を、LATEXには『jlatex』を指定してください。 + ・compositefontをa2ps用に多少カスタマイズしていますが、フォントの高 + さなどの情報を完全に固定で決め打ちしている箇所があります(XXXでメモ + しています)。そのためあまり応用性が低いと思います。 + +●半角を全角の1/2の大きさにしたい +パッチデフォルトでは全角文字と半角文字の大きさのバランスは、見た感じが +(個人的なセンスで)安定するようにチューニングしています。もし、テキスト +で表を作成していて、そのため、半角文字を全角のちょうど半分にそろえたい +という場合の対処方法を書いておきます。 + +インストール後、$prefix/share/a2ps/encoding/euc-jp中に、 + +-------------------------------------------------- +DefaultComposite: Ryumin-Light-EUC-H 1.0 1.1 +-------------------------------------------------- + +というのがあると思います。最後の『1.1』を『0.8342』あたりに変更して下 +さい。ノーマル固定文字に関してはこれで望みの結果が得られると思います。 + +他の太字フォントなども、例えば + +-------------------------------------------------- +Composite: Courier-Bold GothicBBB-Medium-EUC-H 1.0 0.8342 +-------------------------------------------------- + +のように変更すればいいと思います。なお、Courierがつかないフォント +(Helvetica等)はもともとプロポーショナルフォントなので、固定幅にはでき +ません。 + + + +●再配布について +なんだかんだいって、このパッチは、 + +倉光 君郎さんのlibjcode ＋ 片山 紀夫さんのfixeucfont + +を組み合わてできたもので私自身のコードは実はほとんどありません…。 + +私自身のコードは再配付／改造に関してなんら制限を設けるつもりはありませ +ん。ただし、私以外のコードの方が多いため、一応それだけは御了承お願い致 +します。 diff -urN a2ps-4.13.ORIG/config.h.in a2ps-4.13/config.h.in --- a2ps-4.13.ORIG/config.h.in 2003-09-27 04:45:04.000000000 +0900 +++ a2ps-4.13/config.h.in 2003-09-27 05:47:34.000000000 +0900 @@ -24,6 +24,9 @@ /* Define if TIOCGWINSZ requires sys/ioctl.h */ #undef GWINSZ_IN_SYS_IOCTL +/* Define if you use libjcode for japanese */ +#undef USE_LIBJCODE + /* Define to 1 if you have the `alarm' function. */ #undef HAVE_ALARM diff -urN a2ps-4.13.ORIG/configure a2ps-4.13/configure --- a2ps-4.13.ORIG/configure 2003-09-27 05:06:56.000000000 +0900 +++ a2ps-4.13/configure 2003-09-27 05:51:39.000000000 +0900 @@ -1587,7 +1587,8 @@ --with-medium=medium specify the default medium (A4, Letter, Legal, etc.) default=A4 --with-encoding=enc specify the default encoding (ascii, latin1, - latin2... latin6, hp etc.) default=latin1 + latin2... latin6, euc-jp, hp etc.) default=latin1 + --enable-libjcode Japanese code auto convert library (default: yes) Some influential environment variables: CC C compiler command @@ -30943,6 +30944,46 @@ fi; +# Check whether --enable-libjcode or --disable-libjcode was given. +if test "${enable_libjcode+set}" = set; then + enableval="$enable_libjcode" + COMPILE_LIBJCODE=$enableval +else + COMPILE_LIBJCODE=yes +fi + +if test "$COMPILE_LIBJCODE" = "yes"; then + LIBJCODELIBS=\$\(top_builddir\)/libjcode/libjcode.a + cat >> confdefs.h <<\EOF +#define USE_LIBJCODE 1 +EOF + + ENCODING=euc-jp +fi + + + + +# Check whether --enable-libjcode or --disable-libjcode was given. +if test "${enable_libjcode+set}" = set; then + enableval="$enable_libjcode" + COMPILE_LIBJCODE=$enableval +else + COMPILE_LIBJCODE=yes +fi + +if test "$COMPILE_LIBJCODE" = "yes"; then + LIBJCODELIBS=\$\(top_builddir\)/libjcode/libjcode.a + cat >> confdefs.h <<\EOF +#define USE_LIBJCODE 1 +EOF + + ENCODING=euc-jp +fi + + + + ######################## # Nice special printers ######################## @@ -32925,7 +32966,7 @@ ac_config_files="$ac_config_files contrib/psset" -ac_config_files="$ac_config_files Makefile src/Makefile doc/Makefile man/Makefile tests/Makefile tests/defs lib/Makefile auxdir/Makefile m4/Makefile etc/Makefile etc/a2ps_cfg etc/a2ps-site.cfg po/Makefile.in sheets/Makefile encoding/Makefile ps/Makefile afm/Makefile contrib/Makefile contrib/sample/Makefile contrib/emacs/Makefile fonts/Makefile ppd/Makefile" +ac_config_files="$ac_config_files Makefile src/Makefile doc/Makefile man/Makefile tests/Makefile tests/defs lib/Makefile libjcode/Makefile auxdir/Makefile m4/Makefile etc/Makefile etc/a2ps_cfg etc/a2ps-site.cfg po/Makefile.in sheets/Makefile encoding/Makefile ps/Makefile afm/Makefile contrib/Makefile contrib/sample/Makefile contrib/emacs/Makefile fonts/Makefile ppd/Makefile" cat >confcache <<\_ACEOF # This file is a shell script that caches the results of configure @@ -33546,6 +33587,7 @@ "tests/Makefile") CONFIG_FILES="$CONFIG_FILES tests/Makefile" ;; "tests/defs") CONFIG_FILES="$CONFIG_FILES tests/defs" ;; "lib/Makefile") CONFIG_FILES="$CONFIG_FILES lib/Makefile" ;; + "libjcode/Makefile") CONFIG_FILES="$CONFIG_FILES libjcode/Makefile" ;; "auxdir/Makefile") CONFIG_FILES="$CONFIG_FILES auxdir/Makefile" ;; "m4/Makefile") CONFIG_FILES="$CONFIG_FILES m4/Makefile" ;; "etc/Makefile") CONFIG_FILES="$CONFIG_FILES etc/Makefile" ;; @@ -33804,6 +33846,8 @@ LPR_QUEUE_OPTION!$LPR_QUEUE_OPTION$ac_delim MEDIUM!$MEDIUM$ac_delim ENCODING!$ENCODING$ac_delim +COMPILE_LIBJCODE!$COMPILE_LIBJCODE$ac_delim +LIBJCODELIBS!$LIBJCODELIBS$ac_delim COM_gv!$COM_gv$ac_delim gv!$gv$ac_delim COM_ghostview!$COM_ghostview$ac_delim diff -urN a2ps-4.13.ORIG/configure.in a2ps-4.13/configure.in --- a2ps-4.13.ORIG/configure.in 2003-09-27 04:40:36.000000000 +0900 +++ a2ps-4.13/configure.in 2003-09-27 06:09:31.000000000 +0900 @@ -274,11 +274,27 @@ # AC_ARG_WITH(encoding, AC_HELP_STRING([--with-encoding=enc], - [specify the default encoding (ascii, latin1, latin2... latin6, hp etc.) [default=latin1]]), + [specify the default encoding (ascii, latin1, latin2... latin6, euc-jp, hp etc.) [default=latin1]]), ENCODING=$with_encoding, ENCODING=latin1) AC_SUBST(ENCODING) +# +# use libjcode +# +AC_ARG_ENABLE(libjcode, + [ --enable-libjcode Japanese code auto convert library (default: yes)], + COMPILE_LIBJCODE=$enableval, COMPILE_LIBJCODE=yes) +if test "$COMPILE_LIBJCODE" = "yes"; then + LIBJCODELIBS=\$\(top_builddir\)/libjcode/libjcode.a + AC_DEFINE(USE_LIBJCODE, 1, + [Define if you want to use libjcode.]) + ENCODING=euc-jp +fi +AC_SUBST(COMPILE_LIBJCODE) +AC_SUBST(LIBJCODELIBS) + + ######################## # Nice special printers ######################## @@ -386,6 +402,7 @@ tests/Makefile tests/defs lib/Makefile auxdir/Makefile + libjcode/Makefile m4/Makefile etc/Makefile etc/a2ps_cfg etc/a2ps-site.cfg po/Makefile.in diff -urN a2ps-4.13.ORIG/contrib/texi2dvi4a2ps a2ps-4.13/contrib/texi2dvi4a2ps --- a2ps-4.13.ORIG/contrib/texi2dvi4a2ps 2003-09-27 04:40:37.000000000 +0900 +++ a2ps-4.13/contrib/texi2dvi4a2ps 2003-09-27 05:45:02.000000000 +0900 @@ -374,7 +374,7 @@ makeinfo= # no point in running makeinfo on latex source. texindex=${MAKEINDEX:-makeindex} if test $oformat = dvi; then - tex=${LATEX:-latex} + tex=${LATEX:-platex} else tex=${PDFLATEX:-pdflatex} fi @@ -385,7 +385,7 @@ bibtex= texindex=${TEXINDEX:-texindex} if test $oformat = dvi; then - tex=${TEX:-tex} + tex=${TEX:-ptex} else tex=${PDFTEX:-pdftex} fi diff -urN a2ps-4.13.ORIG/encoding/Makefile.am a2ps-4.13/encoding/Makefile.am --- a2ps-4.13.ORIG/encoding/Makefile.am 2003-09-27 04:40:37.000000000 +0900 +++ a2ps-4.13/encoding/Makefile.am 2003-09-27 05:45:02.000000000 +0900 @@ -16,7 +16,7 @@ minor_encodings = \ ms-cp1250.edf hp.edf mac.edf ibm-cp437.edf ibm-cp850.edf iso2.edf \ iso3.edf iso4.edf iso5.edf iso7.edf iso9.edf iso10.edf iso13.edf \ -iso15.edf koi8.edf ms-cp1251.edf +iso15.edf koi8.edf ms-cp1251.edf euc-jp.edf if EXTENSIONS encodings_DATA = encoding.map $(major_encodings) $(minor_encodings) diff -urN a2ps-4.13.ORIG/encoding/Makefile.in a2ps-4.13/encoding/Makefile.in --- a2ps-4.13.ORIG/encoding/Makefile.in 2003-09-27 05:07:28.000000000 +0900 +++ a2ps-4.13/encoding/Makefile.in 2003-09-27 05:45:02.000000000 +0900 @@ -270,7 +270,7 @@ minor_encodings = \ ms-cp1250.edf hp.edf mac.edf ibm-cp437.edf ibm-cp850.edf iso2.edf \ iso3.edf iso4.edf iso5.edf iso7.edf iso9.edf iso10.edf iso13.edf \ -iso15.edf koi8.edf ms-cp1251.edf +iso15.edf koi8.edf ms-cp1251.edf euc-jp.edf @EXTENSIONS_FALSE@encodings_DATA = encoding.map $(major_encodings) @EXTENSIONS_TRUE@encodings_DATA = encoding.map $(major_encodings) $(minor_encodings) diff -urN a2ps-4.13.ORIG/encoding/encoding.map a2ps-4.13/encoding/encoding.map --- a2ps-4.13.ORIG/encoding/encoding.map 2002-03-05 03:46:24.000000000 +0900 +++ a2ps-4.13/encoding/encoding.map 2003-09-27 05:45:02.000000000 +0900 @@ -93,6 +93,12 @@ koi8 koi8 koi koi8 +euc-jp euc-jp +eucjp euc-jp +japanese euc-jp +ja euc-jp +jp euc-jp + ######################################################################## # Some architectures specific char sets ######################################################################## diff -urN a2ps-4.13.ORIG/encoding/euc-jp.edf a2ps-4.13/encoding/euc-jp.edf --- a2ps-4.13.ORIG/encoding/euc-jp.edf 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/encoding/euc-jp.edf 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,109 @@ +# Description of the EUC-JP encoding +# Copyright (c) 1988, 89, 90, 91, 92, 93 Miguel Santana +# Copyright (c) 1995, 96, 97, 98 Akim Demaille, Miguel Santana +# + +# +# This file is part of a2ps. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2, or (at your option) +# any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; see the file COPYING. If not, write to +# the Free Software Foundation, 59 Temple Place - Suite 330, +# Boston, MA 02111-1307, USA. +# + +Name: EUC-JP + +# This text is reproduced by a courtesy of Roman Czyborra +# http://czyborra.com/charsets/iso8859.html +Documentation +The EUC-JP character set, often simply referred to as Latin 1, +covers most West European languages, such as French, Spanish, Catalan, +Basque, Portuguese, Italian, Albanian, Rhaeto-Romanic, Dutch, German, +Danish, Swedish, Norwegian, Finnish, Faroese, Icelandic, Irish, +Scottish, and English, incidentally also Afrikaans and Swahili, thus +in effect also the entire American continent, Australia and the +southern two-thirds of Africa. The lack of the ligatures Dutch IJ, +French OE and ,,German`` quotation marks is considered tolerable. + +The lack of the new C=-resembling Euro currency symbol U+20AC has +opened the discussion of a new Latin0. +EndDocumentation + +# If there is an unknown font requested, use Courier +Default: Courier + +# Automatic spell checking :) +Substitute: Times Times-Roman +Substitute: Helvetica-Italic Helvetica-Oblique +Substitute: Helvetica-BoldItalic Helvetica-BoldOblique + + +# SlantFont for Japanese Italic Kanji font +# new font source font value +SlantFont: Ryumin-Light-EUC-H-Italic Ryumin-Light-EUC-H 0.2 +SlantFont: GothicBBB-Medium-EUC-H-Italic GothicBBB-Medium-EUC-H 0.2 + +# Compose font for japanese EUC code +# target font additional font width size rate +DefaultComposite: Ryumin-Light-EUC-H 1.0 1.1 + +# 1:2 fixed +#DefaultComposite: Ryumin-Light-EUC-H 1.0 0.8333 + +# 1:1 fixed +#DefaultComposite: Ryumin-Light-EUC-H 1.0 1.6666 + +Composite: Helvetica GothicBBB-Medium-EUC-H 1.0 1.1 +Composite: Helvetica-Oblique GothicBBB-Medium-EUC-H-Italic 1.0 1.1 +Composite: Helvetica-Bold GothicBBB-Medium-EUC-H 1.0 1.1 +Composite: Helvetica-BoldOblique GothicBBB-Medium-EUC-H-Italic 1.0 1.1 + +Composite: Courier-Oblique Ryumin-Light-EUC-H-Italic 1.0 1.1 +Composite: Courier-Bold GothicBBB-Medium-EUC-H 1.0 1.1 +Composite: Courier-BoldOblique GothicBBB-Medium-EUC-H-Italic 1.0 1.1 +Composite: Times-Bold GothicBBB-Medium-EUC-H 1.0 1.1 + +Vector: +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +space exclam quotedbl numbersign dollar percent ampersand quoteright +parenleft parenright asterisk plus comma minus period slash +zero one two three four five six seven +eight nine colon semicolon less equal greater question +at A B C D E F G +H I J K L M N O +P Q R S T U V W +X Y Z bracketleft backslash bracketright asciicircum underscore +quoteleft a b c d e f g +h i j k l m n o +p q r s t u v w +x y z braceleft bar braceright asciitilde .notdef +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +.notdef .notdef .notdef .notdef .notdef .notdef .notdef .notdef +space exclamdown cent sterling currency yen brokenbar section +dieresis copyright ordfeminine guillemotleft logicalnot hyphen registered macron +degree plusminus twosuperior threesuperior acute mu paragraph bullet +cedilla onesuperior ordmasculine guillemotright onequarter onehalf threequarters questiondown +Agrave Aacute Acircumflex Atilde Adieresis Aring AE Ccedilla +Egrave Eacute Ecircumflex Edieresis Igrave Iacute Icircumflex Idieresis +Eth Ntilde Ograve Oacute Ocircumflex Otilde Odieresis multiply +Oslash Ugrave Uacute Ucircumflex Udieresis Yacute Thorn germandbls +agrave aacute acircumflex atilde adieresis aring ae ccedilla +egrave eacute ecircumflex edieresis igrave iacute icircumflex idieresis +eth ntilde ograve oacute ocircumflex otilde odieresis divide +oslash ugrave uacute ucircumflex udieresis yacute thorn ydieresis diff -urN a2ps-4.13.ORIG/lib/encoding.c a2ps-4.13/lib/encoding.c --- a2ps-4.13.ORIG/lib/encoding.c 2003-09-27 04:40:37.000000000 +0900 +++ a2ps-4.13/lib/encoding.c 2003-09-27 05:45:02.000000000 +0900 @@ -37,6 +37,9 @@ #include "document.h" #include "quotearg.h" #include "strverscmp.h" +#ifdef USE_LIBJCODE +int use_libjcode = false; +#endif /* Suffix of the Encoding Description Files */ #define EDF_SUFFIX ".edf" @@ -389,15 +392,25 @@ * Association of suffixes rules, and corresponding style sheet * (The hashing is upon `alias') */ +struct slantfont_info { + char * name; + char * src; + float raito; +}; + struct encoding { char * key; /* e.g. latin1 */ char * name; /* e.g. ISO Latin 1 */ + int composite_flag; /* flag for composite font */ uchar * documentation; /* Useful pieces of text */ char * default_font; /* When a font can't be used define the font to use */ struct pair_htable * substitutes; /* e.g. in latin2, don't use * Courier, but Courier-Ogonki */ + struct pair_htable * composite; + + struct slantfont_info slantfont[NB_FACES]; char * vector[256]; /* Define the char set */ struct darray * font_names_used; @@ -407,6 +420,9 @@ struct hash_table_s * fonts; /* Contains cells that are * 1. name of font, 2. int wx[256] */ unsigned int * faces_wx[NB_FACES]; + + unsigned int composite_wx[NB_FACES]; /* fixed length font width*/ + float composite_raito[NB_FACES]; /* size raito of additonal and orinal font */ }; /* @@ -423,9 +439,12 @@ res->name = NULL; res->default_font = NULL; res->documentation = NULL; + res->composite_flag = false; /* Vector will be set by setup */ res->substitutes = pair_table_new (); + res->composite = pair_table_new (); + res->slantfont[0].name = NULL; res->font_names_used = da_new ("List of font names", 10, da_linear, 10, (da_print_func_t) da_str_print, @@ -471,6 +490,34 @@ } /* + * Add a composite font in the current encoding + */ +static void +encoding_add_composite_font (struct encoding * encoding, + const char * orig, const char * subs, + int wx, float raito) +{ + encoding->composite_flag = true; + pair_add2 (encoding->composite, orig, subs, wx, raito); +} + +/* + * Add a composite font in the current encoding + */ +static void +encoding_add_slant_font (struct encoding * encoding, + const char * new, const char * src, + float raito) +{ + static num = 0; + encoding->slantfont[num].name = strdup(new); + encoding->slantfont[num].src = strdup(src); + encoding->slantfont[num].raito = raito; + encoding->slantfont[num+1].name = NULL; + num++; +} + +/* * When FONT_NAME is used with ENCODING, return the * real font name to use (e.g., in latin2, Courier-Ogonki * should be returned when asked for Courier). @@ -514,6 +561,77 @@ } message (msg_enc, + (stderr, "In encoding %s, composite font for %s is resolved as %s\n", + encoding->key, font_name, res)); + return res; +} + +/* + * Get composite font size and raito + */ +static int +composite_font_info_get_wx(struct a2ps_job * job, + struct encoding * encoding, + const char * font_list) +{ + int wx= -1; + char * font_list_copy; + char * font_name; + astrcpy (font_list_copy, font_list); + font_name = strtok (font_list_copy, ",<>;"); + + wx = pair_get_wx (encoding->composite, font_name); + if (wx<0) + wx = pair_get_wx (encoding->composite, "default_composite__"); + + return wx; +} + +static float +composite_font_info_get_raito(struct a2ps_job * job, + struct encoding * encoding, + const char * font_list) +{ + float raito= -1; + char * font_list_copy; + char * font_name; + + astrcpy (font_list_copy, font_list); + font_name = strtok (font_list_copy, ",<>;"); + + raito = pair_get_raito (encoding->composite, font_name); + if (raito<0) + raito = pair_get_raito (encoding->composite, "default_composite__"); + return raito; +} + +const char * +encoding_resolve_composite_font (struct a2ps_job * job, + struct encoding * encoding, + const char * font_list) +{ + const char * res = NULL; + char * font_list_copy; + char * font_name; + + astrcpy (font_list_copy, font_list); + font_name = strtok (font_list_copy, ",<>;"); + + /* Find if there is a substitute for that font */ + res = pair_get (encoding->composite, font_name); + + /* We've found nothing interesting. Last chance is the default + * font */ + if (!res) + { + res = pair_get (encoding->composite, "default_composite__"); + + if (!res) + error (1, 0, "Cannot find font %s, nor any composite font", + font_name); + } + + message (msg_enc, (stderr, "In encoding %s, font %s is resolved as %s\n", encoding->key, font_name, res)); return res; @@ -585,6 +703,12 @@ { token2 = GET_TOKEN (NULL); CHECK_TOKEN (); +#ifdef USE_LIBJCODE + if( strcmp(token2, "EUC-JP")== 0) + use_libjcode = true; + else + use_libjcode = false; +#endif encoding->name = xstrdup (token2); } else if (strequ (token, "Default:")) @@ -633,6 +757,66 @@ subs = token2; encoding_add_font_substitute (encoding, orig, subs); } + else if (strequ (token, "DefaultComposite:")) + { + char * orig, * subs; + int wx; + float raito; + + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + subs = token2; + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + wx = (int)atof(token2)*1000; + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + raito = atof(token2); + encoding_add_composite_font(encoding, "default_composite__", + subs, wx, raito); + } + else if (strequ (token, "Composite:")) + { + char * orig, * subs; + int wx; + float raito; + + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + orig = token2; + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + subs = token2; + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + wx = (int)atof(token2)*1000; + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + raito = atof(token2); + encoding_add_composite_font(encoding, orig, subs, wx, raito); + } + else if (strequ (token, "SlantFont:")) + { + char * new, * src; + float raito; + unsigned int num; + + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + new = token2; + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + src = token2; + token2 = GET_TOKEN (NULL); + CHECK_TOKEN (); + raito = atof(token2); + for (num = 0 ; encoding->slantfont[num].name ; num ++ ); + if (num > sizeof encoding->slantfont - 1){ + error_at_line (1, 0, fname, firstline, + _("too many slant font: `%s'"), new); + } + encoding_add_slant_font(encoding, new, src, raito); + } else error_at_line (1, 0, fname, firstline, _("invalid option `%s'"), quotearg (token)); @@ -754,6 +938,15 @@ } /* + * Return the flag of composite flag + */ +int +encoding_get_composite_flag (struct encoding * enc) +{ + return enc->composite_flag; +} + +/* * Prepare the environment (a dictionary) for the support * of ENCODING, dump it into STREAM. * @@ -766,9 +959,11 @@ struct encoding * encoding) { size_t i, nb; + size_t ns; const char * real_font_name; /* After subsitution */ char ** font_names = (char **) encoding->font_names_used->content; + /* How many fonts are there? */ da_qsort (encoding->font_names_used); da_unique (encoding->font_names_used, (da_map_func_t) free); @@ -787,15 +982,46 @@ * in the current ENCODING */ nb = encoding->font_names_used->len; + /* The number of slant fonts */ + for (i= 0, ns=0 ; encoding->slantfont[i].name ; i++ ) + ns++; + /* Create the dictionary and fill it */ fprintf (stream, "%% Dictionary for %s support\n", encoding->name); - fprintf (stream, "/%sdict %d dict begin\n", encoding->key, nb); + fprintf (stream, "/%sdict %d dict begin\n", encoding->key, + (encoding->composite_flag == true)? nb+nb+ns:nb+ns); for (i = 0 ; i < nb ; i++) fprintf (stream, " /f%s %sEncoding /%s reencode_font\n", font_names [i], encoding->name, encoding_resolve_font_substitute (job, encoding, font_names [i])); + + /* Slant font setting */ + for (i = 0 ; encoding->slantfont[i].name ; i++ ) + fprintf (stream, " /%s /%s %f slantfont definefont pop\n", + encoding->slantfont[i].name, + encoding->slantfont[i].src, + encoding->slantfont[i].raito); + + /* + * Composite font setting. + * If kanji font size is larger than alphabet character, + * set base font size to kanji charactor size. + */ + if (encoding->composite_flag == true) { + for (i = 0 ; i < nb ; i++) + fprintf (stream, " /f%s /f%s /%s %f %f false compositefont " + "%f scalefont def\n", + font_names [i], + font_names [i], + encoding_resolve_composite_font (job, encoding, font_names [i]), + encoding->composite_raito[i], + (encoding->composite_raito[i] > 1.0)? + 0: (1-encoding->composite_raito[i])/2.0, + (encoding->composite_raito[i] > 1.0)? + 1.0/encoding->composite_raito[i]: 1.0 ); + } fputs ("currentdict end def\n", stream); } @@ -939,6 +1165,22 @@ true_font_name, encoding->vector, encoding->faces_wx [face]); + + if (encoding->composite_flag) + { + encoding->composite_raito[i] = + composite_font_info_get_raito(job, encoding, + job->face_eo_font [face]); + + encoding->composite_wx[i] = + composite_font_info_get_wx(job, encoding, + job->face_eo_font [face]); + + /* If kanji font size is larger than alphabet character, + fit kanji charactor size to base font size */ + if (encoding->composite_raito[i] < 1.0) + encoding->composite_wx[i] *= encoding->composite_raito[i]; + } } } @@ -1073,6 +1315,13 @@ return 0; /* For -Wall */ } +unsigned int +char_composite_WX (a2ps_job * job, uchar c) +{ + return (job->encoding->composite_wx[job->status->face]/ + job->encoding->composite_raito[job->status->face]); +} + /* * Returns the WX of a string (including M- and ^) */ diff -urN a2ps-4.13.ORIG/lib/encoding.h a2ps-4.13/lib/encoding.h --- a2ps-4.13.ORIG/lib/encoding.h 2003-09-27 04:40:37.000000000 +0900 +++ a2ps-4.13/lib/encoding.h 2003-09-27 05:45:02.000000000 +0900 @@ -43,6 +43,7 @@ */ unsigned int char_WX PARAMS ((struct a2ps_job * job, uchar c)); unsigned int string_WX PARAMS ((struct a2ps_job * job, uchar * string)); +unsigned int char_composite_WX PARAMS ((struct a2ps_job * job, uchar c)); /************************************************************************/ @@ -56,6 +57,7 @@ FILE * stream)); int encoding_char_exists PARAMS ((struct encoding * enc, enum face_e face, uchar c)); +int encoding_get_composite_flag (struct encoding * enc); struct encoding * get_encoding_by_alias PARAMS ((struct a2ps_job * job, char *string)); @@ -71,6 +73,12 @@ struct encoding * encoding, const char * font_name)); + +const char * encoding_resolve_composite_font + PARAMS ((struct a2ps_job * job, + struct encoding * encoding, + const char * font_name)); + /* * Have a struct encoding determine the faces_wx */ diff -urN a2ps-4.13.ORIG/lib/pair_ht.c a2ps-4.13/lib/pair_ht.c --- a2ps-4.13.ORIG/lib/pair_ht.c 2002-03-05 03:46:25.000000000 +0900 +++ a2ps-4.13/lib/pair_ht.c 2003-09-27 05:45:02.000000000 +0900 @@ -49,6 +49,8 @@ { char * key; char * value; + float raito; + int wx; }; /* @@ -165,6 +167,37 @@ } /* + * Add a pair, with your own allocation for them. + * It KEY is yet used, override its value with VALUE + */ +void +pair_add2 (struct hash_table_s * table, + const char * key, const char * value, int wx, float raito) +{ + struct pair * item, token; + + token.key = (char *) key; + item = (struct pair *) hash_find_item (table, &token); + + if (item) { + if (item->value) + free (item->value); + } else { + item = XMALLOC (struct pair, 1); + item->key = xstrdup(key); + item->wx = wx; + item->raito = raito; + } + + if (value) + item->value = xstrdup (value); + else + item->value = NULL; + + hash_insert (table, item); +} + +/* * Remove a pair and free it. * It KEY is yet used, override its value with VALUE */ @@ -201,6 +234,34 @@ return NULL; } +int +pair_get_wx (struct hash_table_s * table, const char * key) +{ + struct pair * item, token; + + token.key = (char *) key; + item = (struct pair *) hash_find_item (table, &token); + + if (item) + return item->wx; + else + return -1; +} + +float +pair_get_raito (struct hash_table_s * table, const char * key) +{ + struct pair * item, token; + + token.key = (char *) key; + item = (struct pair *) hash_find_item (table, &token); + + if (item) + return item->raito; + else + return -1; +} + /* * Return the content of the hash table, ordered */ diff -urN a2ps-4.13.ORIG/lib/pair_ht.h a2ps-4.13/lib/pair_ht.h --- a2ps-4.13.ORIG/lib/pair_ht.h 2002-03-05 03:46:25.000000000 +0900 +++ a2ps-4.13/lib/pair_ht.h 2003-09-27 05:45:02.000000000 +0900 @@ -56,6 +56,10 @@ void pair_add PARAMS ((struct pair_htable * table, const char * key, const char * value)); +void pair_add2 PARAMS ((struct pair_htable * table, + const char * key, const char * value, + int wx, float raito)); + /* * The key and value of the matching item will be free'd * (No problem if KEY matches nothing) @@ -68,6 +72,10 @@ */ char * pair_get PARAMS ((struct pair_htable * table, const char * key)); +int pair_get_wx PARAMS ((struct pair_htable * table, + const char * key)); +float pair_get_raito PARAMS ((struct pair_htable * table, + const char * key)); void pair_table_list_short PARAMS ((struct pair_htable * table, FILE * stream)); diff -urN a2ps-4.13.ORIG/lib/psgen.c a2ps-4.13/lib/psgen.c --- a2ps-4.13.ORIG/lib/psgen.c 2002-03-05 03:46:25.000000000 +0900 +++ a2ps-4.13/lib/psgen.c 2003-09-27 05:45:02.000000000 +0900 @@ -875,6 +875,7 @@ print: default: { + static mb_flag= 0; uchar buf[256]; int nchars; *buf = '\0'; @@ -889,6 +890,29 @@ job->status->face_declared = false; } + if (c > 127 && encoding_get_composite_flag (job->encoding) && + job->status->face != Symbol) { + if (mb_flag) { + nchars = ps_escape_char (job, mb_flag, buf) + + ps_escape_char (job, c, buf); + job->status->wx += char_composite_WX(job, c); + job->status->column += nchars; + if (line_full) { + if (job->folding) { + fold_line (job, new_face); + job->status->column = nchars*2; + job->status->wx = char_composite_WX(job, c); + } else { + job->status->is_in_cut = true; + return; + } + } + mb_flag = 0; + } else { + mb_flag = c; + return; + } + } else { nchars = ps_escape_char (job, c, buf); job->status->wx += char_WX (job, c); job->status->column += nchars; @@ -902,8 +926,9 @@ return; } } + } output (jdiv, "%s", buf); - job->status->chars++; + job->status->chars+=nchars; } break; } diff -urN a2ps-4.13.ORIG/libjcode/Doc/rfc1468.txt a2ps-4.13/libjcode/Doc/rfc1468.txt --- a2ps-4.13.ORIG/libjcode/Doc/rfc1468.txt 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/Doc/rfc1468.txt 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,339 @@ + + + + + + +Network Working Group J. Murai +Request for Comments: 1468 Keio University + M. Crispin + Panda Programming + E. van der Poel + June 1993 + + + Japanese Character Encoding for Internet Messages + +Status of this Memo + + This memo provides information for the Internet community. It does + not specify an Internet standard. Distribution of this memo is + unlimited. + +Introduction + + This document describes the encoding used in electronic mail [RFC822] + and network news [RFC1036] messages in several Japanese networks. It + was first specified by and used in JUNET [JUNET]. The encoding is now + also widely used in Japanese IP communities. + + The name given to this encoding is "ISO-2022-JP", which is intended + to be used in the "charset" parameter field of MIME headers (see + [MIME1] and [MIME2]). + +Description + + The text starts in ASCII [ASCII], and switches to Japanese characters + through an escape sequence. For example, the escape sequence ESC $ B + (three bytes, hexadecimal values: 1B 24 42) indicates that the bytes + following this escape sequence are Japanese characters, which are + encoded in two bytes each. To switch back to ASCII, the escape + sequence ESC ( B is used. + + The following table gives the escape sequences and the character sets + used in ISO-2022-JP messages. The ISOREG number is the registration + number in ISO's registry [ISOREG]. + + Esc Seq Character Set ISOREG + + ESC ( B ASCII 6 + ESC ( J JIS X 0201-1976 ("Roman" set) 14 + ESC $ @ JIS X 0208-1978 42 + ESC $ B JIS X 0208-1983 87 + + Note that JIS X 0208 was called JIS C 6226 until the name was changed + + + +Murai, Crispin & van der Poel [Page 1] + +RFC 1468 Japanese Character Encoding for Internet Messages June 1993 + + + on March 1st, 1987. Likewise, JIS C 6220 was renamed JIS X 0201. + + The "Roman" character set of JIS X 0201 [JISX0201] is identical to + ASCII except for backslash () and tilde (~). The backslash is + replaced by the Yen sign, and the tilde is replaced by overline. This + set is Japan's national variant of ISO 646 [ISO646]. + + The JIS X 0208 [JISX0208] character sets consist of Kanji, Hiragana, + Katakana and some other symbols and characters. Each character takes + up two bytes. + + For further details about the JIS Japanese national character set + standards, refer to [JISX0201] and [JISX0208]. For further + information about the escape sequences, see [ISO2022] and [ISOREG]. + + If there are JIS X 0208 characters on a line, there must be a switch + to ASCII or to the "Roman" set of JIS X 0201 before the end of the + line (i.e., before the CRLF). This means that the next line starts in + the character set that was switched to before the end of the previous + line. + + Also, the text must end in ASCII. + + Other restrictions are given in the Formal Syntax below. + +Formal Syntax + + The notational conventions used here are identical to those used in + RFC 822 [RFC822]. + + The * (asterisk) convention is as follows: + + l*m something + + meaning at least l and at most m somethings, with l and m taking + default values of 0 and infinity, respectively. + + + message = headers 1*( CRLF *single-byte-char *segment + single-byte-seq *single-byte-char ) + ; see also [MIME1] "body-part" + ; note: must end in ASCII + + headers = + + segment = single-byte-segment / double-byte-segment + + single-byte-segment = single-byte-seq 1*single-byte-char + + + +Murai, Crispin & van der Poel [Page 2] + +RFC 1468 Japanese Character Encoding for Internet Messages June 1993 + + + double-byte-segment = double-byte-seq 1*( one-of-94 one-of-94 ) + + single-byte-seq = ESC "(" ( "B" / "J" ) + + double-byte-seq = ESC "$" ( "@" / "B" ) + + CRLF = CR LF + + ; ( Octal, Decimal.) + + ESC = ; ( 33, 27.) + + SI = ; ( 17, 15.) + + SO = ; ( 16, 14.) + + CR = ; ( 15, 13.) + + LF = ; ( 12, 10.) + + one-of-94 = ; (41-176, 33.-126.) + + 7BIT = ; ( 0-177, 0.-127.) + + single-byte-char = + +MIME Considerations + + The name given to the JUNET character encoding is "ISO-2022-JP". This + name is intended to be used in MIME messages as follows: + + Content-Type: text/plain; charset=iso-2022-jp + + The ISO-2022-JP encoding is already in 7-bit form, so it is not + necessary to use a Content-Transfer-Encoding header. It should be + noted that applying the Base64 or Quoted-Printable encoding will + render the message unreadable in current JUNET software. + + ISO-2022-JP may also be used in MIME Part 2 headers. The "B" + encoding should be used with ISO-2022-JP text. + +Background Information + + The JUNET encoding was described in the JUNET User's Guide [JUNET] + (JUNET Riyou No Tebiki Dai Ippan). + + The encoding is based on the particular usage of ISO 2022 announced + + + +Murai, Crispin & van der Poel [Page 3] + +RFC 1468 Japanese Character Encoding for Internet Messages June 1993 + + + by 4/1 (see [ISO2022] for details). However, the escape sequence + normally used for this announcement is not included in ISO-2022-JP + messages. + + The Kana set of JIS X 0201 is not used in ISO-2022-JP messages. + + In the past, some systems erroneously used the escape sequence ESC ( + H in JUNET messages. This escape sequence is officially registered + for a Swedish character set [ISOREG], and should not be used in ISO- + 2022-JP messages. + + Some systems do not distinguish between ESC ( B and ESC ( J or + between ESC $ @ and ESC $ B for display. However, when relaying a + message to another system, the escape sequences must not be altered + in any way. + + The human user (not implementor) should try to keep lines within 80 + display columns, or, preferably, within 75 (or so) columns, to allow + insertion of ">" at the beginning of each line in excerpts. Each JIS + X 0208 character takes up two columns, and the escape sequences do + not take up any columns. The implementor is reminded that JIS X 0208 + characters take up two bytes and should not be split in the middle to + break lines for displaying, etc. + + The JIS X 0208 standard was revised in 1990, to add two characters at + the end of the table. Although ISO 2022 specifies special additional + escape sequences to indicate the use of revised character sets, it is + suggested here not to make use of this special escape sequence in + ISO-2022-JP text, even if the two characters added to JIS X 0208 in + 1990 are used. + + For further information about Japanese character encodings such as PC + codes, FTP locations of implementations, etc, see "Electronic + Handling of Japanese Text" [JPN.INF]. + +References + + [ASCII] American National Standards Institute, "Coded character set + -- 7-bit American national standard code for information + interchange", ANSI X3.4-1986. + + [ISO646] International Organization for Standardization (ISO), + "Information technology -- ISO 7-bit coded character set for + information interchange", International Standard, Ref. No. ISO/IEC + 646:1991. + + [ISO2022] International Organization for Standardization (ISO), + "Information processing -- ISO 7-bit and 8-bit coded character sets + + + +Murai, Crispin & van der Poel [Page 4] + +RFC 1468 Japanese Character Encoding for Internet Messages June 1993 + + + -- Code extension techniques", International Standard, Ref. No. ISO + 2022-1986 (E). + + [ISOREG] International Organization for Standardization (ISO), + "International Register of Coded Character Sets To Be Used With + Escape Sequences". + + [JISX0201] Japanese Standards Association, "Code for Information + Interchange", JIS X 0201-1976. + + [JISX0208] Japanese Standards Association, "Code of the Japanese + graphic character set for information interchange", JIS X 0208-1978, + -1983 and -1990. + + [JPN.INF] Ken R. Lunde , "Electronic Handling of + Japanese Text", March 1992, + msi.umn.edu(128.101.24.1):pub/lunde/japan[123].inf + + [JUNET] JUNET Riyou No Tebiki Sakusei Iin Kai (JUNET User's Guide + Drafting Committee), "JUNET Riyou No Tebiki (Dai Ippan)" ("JUNET + User's Guide (First Edition)"), February 1988. + + [MIME1] Borenstein N., and N. Freed, "MIME (Multipurpose + Internet Mail Extensions): Mechanisms for Specifying and + Describing the Format of Internet Message Bodies", RFC 1341, + Bellcore, Innosoft, June 1992. + + [MIME2] Moore, K., "Representation of Non-ASCII Text in Internet + Message Headers", RFC 1342, University of Tennessee, June 1992. + + [RFC822] Crocker, D., "Standard for the Format of ARPA Internet + Text Messages", STD 11, RFC 822, UDEL, August 1982. + + [RFC1036] Horton M., and R. Adams, "Standard for Interchange of USENET + Messages", RFC 1036, AT&T Bell Laboratories, Center for Seismic + Studies, December 1987. + +Acknowledgements + + Many people assisted in drafting this document. The authors wish to + thank in particular Akira Kato, Masahiro Sekiguchi and Ken'ichi + Handa. + +Security Considerations + + Security issues are not discussed in this memo. + + + + + +Murai, Crispin & van der Poel [Page 5] + +RFC 1468 Japanese Character Encoding for Internet Messages June 1993 + + +Authors' Addresses + + Jun Murai + Keio University + 5322 Endo, Fujisawa + Kanagawa 252 Japan + + Fax: +81 466 49 1101 + EMail: jun@wide.ad.jp + + + Mark Crispin + Panda Programming + 6158 Lariat Loop NE + Bainbridge Island, WA 98110-2098 + USA + + Phone: +1 206 842 2385 + EMail: MRC@PANDA.COM + + + Erik M. van der Poel + A-105 Park Avenue + 4-4-10 Ohta, Kisarazu + Chiba 292 Japan + + Phone: +81 438 22 5836 + Fax: +81 438 22 5837 + EMail: erik@poel.juice.or.jp + + + + + + + + + + + + + + + + + + + + + + +Murai, Crispin & van der Poel [Page 6] + \ No newline at end of file diff -urN a2ps-4.13.ORIG/libjcode/Doc/rfc1554.txt a2ps-4.13/libjcode/Doc/rfc1554.txt --- a2ps-4.13.ORIG/libjcode/Doc/rfc1554.txt 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/Doc/rfc1554.txt 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,339 @@ + + + + + + +Network Working Group M. Ohta +Request for Comments: 1554 Tokyo Institute of Technology +Category: Informational K. Handa + ETL + December 1993 + + + ISO-2022-JP-2: Multilingual Extension of ISO-2022-JP + +Status of this Memo + + This memo provides information for the Internet community. This memo + does not specify an Internet standard of any kind. Distribution of + this memo is unlimited. + +Introduction + + This memo describes a text encoding scheme: "ISO-2022-JP-2", which is + used experimentally for electronic mail [RFC822] and network news + [RFC1036] messages in several Japanese networks. The encoding is a + multilingual extension of "ISO-2022-JP", the existing encoding for + Japanese [2022JP]. The encoding is supported by an Emacs based + multilingual text editor: MULE [MULE]. + + The name, "ISO-2022-JP-2", is intended to be used in the "charset" + parameter field of MIME headers (see [MIME1] and [MIME2]). + +Description + + The text with "ISO-2022-JP-2" starts in ASCII [ASCII], and switches + to other character sets of ISO 2022 [ISO2022] through limited + combinations of escape sequences. All the characters are encoded + with 7 bits only. + + At the beginning of text, the existence of an announcer sequence: + "ESC 2/0 4/1 ESC 2/0 4/6 ESC 2/0 5/10" is (though omitted) assumed. + Thus, characters of 94 character sets are designated to G0 and + invoked as GL. C1 control characters are represented with 7 bits. + Characters of 96 character sets are designated to G2 and invoked with + SS2 (single shift two, "ESC 4/14" or "ESC N"). + + For example, the escape sequence "ESC 2/4 2/8 4/3" or "ESC $ ( C" + indicates that the bytes following the escape sequence are Korean KSC + characters, which are encoded in two bytes each. The escape sequence + "ESC 2/14 4/1" or "ESC . A" indicates that ISO 8859-1 is designated + to G2. After the designation, the single shifted sequence "ESC 4/14 + 4/1" or "ESC N A" is interpreted to represent a character "A with + acute". + + + +Ohta & Handa [Page 1] + +RFC 1554 Multilingual Extension of ISO-2022-JP December 1993 + + + The following table gives the escape sequences and the character sets + used in "ISO-2022-JP-2" messages. The reg# is the registration number + in ISO's registry [ISOREG]. + + 94 character sets + reg# character set ESC sequence designated to + ------------------------------------------------------------------ + 6 ASCII ESC 2/8 4/2 ESC ( B G0 + 42 JIS X 0208-1978 ESC 2/4 4/0 ESC $ @ G0 + 87 JIS X 0208-1983 ESC 2/4 4/2 ESC $ B G0 + 14 JIS X 0201-Roman ESC 2/8 4/10 ESC ( J G0 + 58 GB2312-1980 ESC 2/4 4/1 ESC $ A G0 + 149 KSC5601-1987 ESC 2/4 2/8 4/3 ESC $ ( C G0 + 159 JIS X 0212-1990 ESC 2/4 2/8 4/4 ESC $ ( D G0 + + 96 character sets + reg# character set ESC sequence designated to + ------------------------------------------------------------------ + 100 ISO8859-1 ESC 2/14 4/1 ESC . A G2 + 126 ISO8859-7(Greek) ESC 2/14 4/6 ESC . F G2 + + For further information about the character sets and the escape + sequences, see [ISO2022] and [ISOREG]. + + If there is any G0 designation in text, there must be a switch to + ASCII or to JIS X 0201-Roman before a space character (but not + necessarily before "ESC 4/14 2/0" or "ESC N ' '") or control + characters such as tab or CRLF. This means that the next line starts + in the character set that was switched to before the end of the + previous line. Though the designation to JIS X 0201-Roman is allowed + for backward compatibility to "ISO-2022-JP", its use is discouraged. + Applications such as pagers and editors which randomly seek within a + text file encoded with "ISO-2022-JP-2" may assume that all the lines + begin with ASCII, not with JIS X 0201-Roman. + + At the beginning of a line, information on G2 designation of the + previous line is cleared. New designation must be given before a + character in 96 character sets is used in the line. + + The text must end in ASCII designated to G0. + + As the "ISO-2022-JP", and thus, "ISO-2022-JP-2", is designed to + represent English and modern Japanese, left-to-right directionality + is assumed if the text is displayed horizontally. + + Users of "ISO-2022-JP-2" must be aware that some common transport + such as old Bnews can not relay a 7-bit value 7/15 (decimal 127), + which is used to encode, say, "y with diaeresis" of ISO 8859-1. + + + +Ohta & Handa [Page 2] + +RFC 1554 Multilingual Extension of ISO-2022-JP December 1993 + + + Other restrictions are given in the Formal Syntax section below. + +Formal Syntax + + The notational conventions used here are identical to those used in + STD 11, RFC 822 [RFC822]. + + The * (asterisk) convention is as follows: + + l*m something + + meaning at least l and at most m somethings, with l and m taking + default values of 0 and infinity, respectively. + + message = headers 1*(CRLF text) + ; see also [MIME1] "body-part" + ; note: must end in ASCII + + text = *(single-byte-char / + g2-desig-seq / + single-shift-char) + [*segment + reset-seq + *(single-byte-char / + g2-desig-seq / + single-shift-char ) ] + ; note: g2-desig-seq must + ; precede single-shift-char + + headers = + + segment = single-byte-segment / double-byte-segment + + single-byte-segment = single-byte-seq + *(single-byte-char / + g2-desig-seq / + single-shift-char ) + + double-byte-segment = double-byte-seq + *((one-of-94 one-of-94) / + g2-desig-seq / + single-shift-char ) + + reset-seq = ESC "(" ( "B" / "J" ) + + single-byte-seq = ESC "(" ( "B" / "J" ) + + double-byte-seq = (ESC "$" ( "@" / "A" / "B" )) / + + + +Ohta & Handa [Page 3] + +RFC 1554 Multilingual Extension of ISO-2022-JP December 1993 + + + (ESC "$" "(" ( "C" / "D" )) + + g2-desig-seq = ESC "." ( "A" / "F" ) + + single-shift-seq = ESC "N" + + single-shift-char = single-shift-seq one-of-96 + + CRLF = CR LF + + ; ( Octal, Decimal.) + + ESC = ; ( 33, 27.) + + SI = ; ( 17, 15.) + + SO = ; ( 16, 14.) + + CR = ; ( 15, 13.) + + LF = ; ( 12, 10.) + + one-of-94 = ; (41-176, 33.-126.) + + one-of-96 = ; (40-177, 32.-127.) + + 7BIT = ; ( 0-177, 0.-127.) + + single-byte-char = + +MIME Considerations + + The name given to the character encoding is "ISO-2022-JP-2". This + name is intended to be used in MIME messages as follows: + + Content-Type: text/plain; charset=iso-2022-jp-2 + + The "ISO-2022-JP-2" encoding is already in 7-bit form, so it is not + necessary to use a Content-Transfer-Encoding header. It should be + noted that applying the Base64 or Quoted-Printable encoding will + render the message unreadable in non-MIME-compliant software. + + "ISO-2022-JP-2" may also be used in MIME headers. Both "B" and "Q" + encoding could be useful with "ISO-2022-JP-2" text. + + + + + + +Ohta & Handa [Page 4] + +RFC 1554 Multilingual Extension of ISO-2022-JP December 1993 + + +References + + [ASCII] American National Standards Institute, "Coded character set + -- 7-bit American national standard code for information + interchange", ANSI X3.4-1986. + + + [ISO2022] International Organization for Standardization (ISO), + "Information processing -- ISO 7-bit and 8-bit coded + character sets -- Code extension techniques", + International Standard, Ref. No. ISO 2022-1986 (E). + + [ISOREG] International Organization for Standardization (ISO), + "International Register of Coded Character Sets To Be Used + With Escape Sequences". + + [MIME1] Borenstein, N., and N. Freed, "MIME (Multipurpose Internet + Mail Extensions) Part One: Mechanisms for Specifying and + Describing the Format of Internet Message Bodies", RFC 1521, + September 1993. + + [MIME2] Moore, K., "MIME (Multipurpose Internet Mail Extensions) Part + Two: Message Header Extensions for Non-ASCII Text", RFC 1522, + September 1993. + + [RFC822] Crocker, D., "Standard for the Format of ARPA Internet Text + Messages", STD 11, RFC 1522, UDEL, August 1982. + + [RFC1036] Horton M., and R. Adams, "Standard for Interchange of + USENET Messages", RFC 1036, AT&T Bell Laboratories, Center + for Seismic Studies, December 1987. + + [2022JP] Murai, J., Crispin, M., and E. van der Poel, "Japanese + Character Encoding for Internet Messages", RFC 1468, June + 1993. + + [MULE] Nishikimi, M., Handa, K., and S. Tomura, "Mule: MULtilingual + Enhancement to GNU Emacs", Proc. of INET'93, August, 1993. + +Acknowledgements + + This memo is the result of discussion between various people in a + news group: fj.kanji and is reviewed by a mailing list: jp-msg + @iij.ad.jp. The Authors wish to thank in particular Prof. Eiichi + Wada for his suggestions based on profound knowledge in ISO 2022 and + related standards. + + + + + +Ohta & Handa [Page 5] + +RFC 1554 Multilingual Extension of ISO-2022-JP December 1993 + + +Security Considerations + + Security issues are not discussed in this memo. + +Authors' Addresses + + Masataka Ohta + Tokyo Institute of Technology + 2-12-1, O-okayama, Meguro-ku, + Tokyo 152, JAPAN + + Phone: +81-3-5499-7084 + Fax: +81-3-3729-1940 + EMail: mohta@cc.titech.ac.jp + + + Ken'ichi Handa + Electrotechnical Laboratory + Umezono 1-1-4, Tsukuba, + Ibaraki 305, JAPAN + + Phone: +81-298-58-5916 + Fax: +81-298-58-5918 + EMail: handa@etl.go.jp + + + + + + + + + + + + + + + + + + + + + + + + + + + +Ohta & Handa [Page 6] + \ No newline at end of file diff -urN a2ps-4.13.ORIG/libjcode/Makefile.in a2ps-4.13/libjcode/Makefile.in --- a2ps-4.13.ORIG/libjcode/Makefile.in 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/Makefile.in 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,100 @@ +# Makefile for directory with library jcode +# by Kuramitsu Kimio + +PACKAGE = @PACKAGE@ +VERSION = @VERSION@ + +SHELL = /bin/sh + +srcdir = @srcdir@ +top_srcdir = @top_srcdir@ +top_builddir = .. +VPATH = @srcdir@ + +prefix = @prefix@ +exec_prefix = @exec_prefix@ +transform = @program_transform_name@ +libdir = $(exec_prefix)/lib +includedir = $(prefix)/include +datadir = $(prefix)/@DATADIRNAME@ +subdir = libjcode + +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ +MKINSTALLDIRS = @MKINSTALLDIRS@ + +AR = ar +CC = @CC@ +LIBTOOL = @LIBTOOL@ +RANLIB = @RANLIB@ + +DEFS = -DLOCALEDIR=\"$(localedir)\" -DGNULOCALEDIR=\"$(gnulocaledir)\" \ +-DLOCALE_ALIAS_PATH=\"$(aliaspath)\" @DEFS@ +CPPFLAGS = @CPPFLAGS@ +CFLAGS = @CFLAGS@ +LDFLAGS = @LDFLAGS@ + +COMPILE = $(CC) -c $(DEFS) $(INCLUDES) $(CPPFLAGS) $(CFLAGS) $(XCFLAGS) + +HEADERS = $(COMHDRS) +COMHDRS = jlib.h +SOURCES = $(COMSRCS) +COMSRCS = detect.c libjcode.c +OBJECTS = detect.$lo libjcode.$lo +DISTFILES.common = README +DISTFILES.normal = VERSION + +.SUFFIXES: +.SUFFIXES: .c .o .lo +.c.o: + $(COMPILE) $< +.c.lo: + $(LIBTOOL) --mode=compile $(COMPILE) $< + +INCLUDES = -I. -I$(top_srcdir)/ + +all: all-@COMPILE_LIBJCODE@ + +all-yes: libjcode.$la +all-no: + +libjcode.a: $(OBJECTS) + rm -f $@ + $(AR) cru $@ $(OBJECTS) + $(RANLIB) $@ + +libjcode.la: $(OBJECTS) + $(LIBTOOL) --mode=link $(CC) $(LDFLAGS) -o $@ $(OBJECTS) \ + -version-info 1:0 -rpath $(libdir) + +check: all + +install: install-exec install-data +install-exec: all + +install-data: all + +# Define this as empty until I found a useful application. +installcheck: + +uninstall: + +info dvi: + +$(OBJECTS): jlibconfig.h jlib.h + +mostlyclean: + rm -f *.a *.o *.lo core core.* + +clean: mostlyclean + +distclean: clean + rm -f Makefile ID TAGS po2msg.sed po2tbl.sed + +maintainer-clean: distclean + @echo "This command is intended for maintainers to use;" + @echo "it deletes files that may require special tools to rebuild." + +Makefile: Makefile.in ../config.status + cd .. \ + && CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= $(SHELL) ./config.status diff -urN a2ps-4.13.ORIG/libjcode/README a2ps-4.13/libjcode/README --- a2ps-4.13.ORIG/libjcode/README 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/README 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,158 @@ +libjcode ライブラリパッケージ 1.00 版/ 1996 + +ご存知の通り、日本語を表すための文字コードは、JIS(ISO-2022)、EUC、SJIS の +３種類がよく使われています。これは、パソコン間でSJISの文章をやり取りする時 +は、何にも問題のない話でした。しかし、WWW のようなインターネット時代になる +と、様々な文字コードが混在してしまい、大きな混乱を招く結果になります。 + +そんな中で多くのプログラマーが日本語コード処理の煩雑さの罠に陥らなくて済む +ようにまとめたのが、この C言語用の libjcode ライブラリです。 + +-- libjcode パッケージの特徴 ------------------------------------------------ + + 1. インターネットでの利用を前提とした日本語コード変換ライブラリ + 2. SJIS 半角カナを全角に変換可能 + +-- パッケージの中身 --------------------------------------------------------- + + / + README このファイル + Makefile Unix 版 Makefile + config.h 設定用 #include ファイル + libjcode.c JIS、SJIS、EUCの変換 + detect.c コード判定用 + sample.c 簡単なサンプルプログラム + jlib.h ライブラリ用 #include ファイル + + Doc/ + rfc1468.txt RFC1468 + "Japanese Character Encoding for Internet Messages." + rfc1554.txt RFC1554 + "ISO-2022-JP-2: Multilingual Extension of ISO-2022-JP" + +-- 利用上の注意 ------------------------------------------------------------- + +libjcode は、完全にフリーなライブラリです。インターネットにおける日本語環境 +の改善を最終目標にしております。日本語コードの変換を行いたい方なら誰でも、 +自由に改良して、自分のプログラムに合わせて組み込むことができます。 + +ただし、利用にする場合は次の条件を守ってください。 + + 1. libjcode を利用したために如何なる損害が生じても作者には一切の責任を + 取りません。 + 2. 国立大学のコンピュータ資源を使っているので、著作権表示、 + (C) Kuramitsu Kimio, Tokyo Univ. 1996-97 + を念のために残しておいてください。 + +ライブラリ利用中にバグを発見し直された方、より効率のよりアルゴリズムを実装 +なさった方は、それを作者に送って頂けると、libjcode としてもより信頼性の高い +ライブラリへと成長できます。よろしくお願いします。 + +また、libjcodeを組み込んだソフトウエアの名前も教えていただけると、実際の実 +装例として、紹介したいと思います。 + +-- 使い方 ------------------------------------------------------------------- + +1. まず、make によって、libjcode.a ライブラリを作ります。 + config.h を直すことで、多少機能を変えることができますが、ソースコード + を読んだ方が早いでしょう。 + +2. サンプルプログラム sample.c と Makefile を見ると、このライブラリをどの + ように組み込むか参考にしてください。 + +-- 動作確認環境 ------------------------------------------------------------- + +ANSI C コンパイラを使っていれば、普通にコンパイルできるはずです。 + + Solaris 2.5 (Sparc) with gcc 2.7.2 + Linux 2.0 with gcc 2.7.2 + +-- ライブラリの一覧 --------------------------------------------------------- + +普通に使えるライブラリ関数は、jlib.h ヘッダファイルに書かれています。最初 +に #include "jlib.h" を追加します。 + +#define ディレクティブの内容 + +#define ASCII ASCII コード +#define JIS iso-2022-jp コード +#define EUC x-euc-jp コード +#define SJIS x-sjis コード + +関数: + +extern int detectKanjiCode(char *str); + + 文字列 str のコードを判定します。 + 返り値は、ASCII, JIS, EUC, SJIS のどれかです。 + +extern char *toStringJIS(char *str); + + 文字列 str をJIS コードに変換します。 + +extern char *toStringEUC(char *str); + + 文字列 str をEUC コードに変換します。 + +extern char *toStringSJIS(char *str); + + 文字列 str をSJIS コードに変換します。 + +-- 知られている問題点 ------------------------------------------------------- + +半角SJISが含まれたテキストを想定しているので、EUC と SJIS の自動判定が +かなり弱い。 + +-- 今後の予定 --------------------------------------------------------------- + +確実にやろうと思っていること。 + JIS X 0212-1990 (俗称 補助漢字)の変換に対応 + MIME ヘッダのエンコード/デコード + +できたらやりたいこと(CGI 向けライブラリ) + 全角 --> 半角 + (例 ｆｏｏ＠ｍａｉｌ．ｃｏｍ --> foo@mail.com) + 平仮名 <--> カタカナ + ROMAN 字 --> かな + (Kuramitsu --> くらみつ) + +挑戦したいこと。 + SJIS と ISO-8859-1(laten) の自動識別 + +道義的に悩むところ + Unicode への対応 + + +-- 歴史 --------------------------------------------------------------------- + +libjcode を作る直接のきっかけとなったのは、Thomus Boutell 著の +"CGI Programming with C and Perl"(Addison-Wesley)に付属するサンプルCGIプロ +グラムを日本語の入力を受け付けるようにするために、漢字コード変換に触れる必 +要性がありました。ところが、Perl用には優れた漢字変換のライブラリが存在しま +したが、残念ながらC版には、優れたライブラリが手に入れることができませんで +した。 + +そこで、Ken Lunde 著の「日本語情報処理」(O'Reilly)を参考にライブラリ作成を +始めることにしました。 + +1996/12/10 ホームページ上で公開開始。 + http://www.lib.m.u-tokyo.ac.jp/~kiki/libjcode/ + +1996/12/19 "CGI Programming with C and Perl5"の日本語版付録CD-ROM付録 + として、libjcode-1.00 配布開始 + +-- 謝辞 --------------------------------------------------------------------- + +坂村研究室の先輩である川幡 太一(kawabata@is.s.u-tokyo.ac.jp)さんには、日本 +語処理という狭い観点にとらわれず、広く多国語環境や処理について様々な助言や +アドバイスをして頂きました。また、本ライブラリ実現のためのバグ取りも手伝っ +て頂きました。 + +--- +本ライブラリを活用して多くのCGIプログラムやWindows/Macintosh 用のフリーウ +エア、また商用アプリケーションの日本語版が正しく漢字コードを扱えるように +なって頂けれれば、幸いです。 + + 1996年 12月 + 倉光 君郎 / Kuramitsu Kimio + kiki@is.s.u-tokyo.ac.jp diff -urN a2ps-4.13.ORIG/libjcode/detect.c a2ps-4.13/libjcode/detect.c --- a2ps-4.13.ORIG/libjcode/detect.c 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/detect.c 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,204 @@ +/* + * detect.c - libjcode コード自動判定ルーチン + * (C) Kuramitsu Kimio, Tokyo Univ. 1996-97 + * + * Ken Lunde 著 「日本語情報処理」 と jconv.c を参考に作り + * ました。 + * CGI プログラムでの利用を考えて、ひらがな、かたかなの並び + * によるSJIS, EUC の推定アルゴリズム等を加えてあります。 + * + * 更新履歴 + * - jcode.plのSJIS/EUC判定にコードを用いた + * Yasuyuki Furukawa (yasu@on.cs.keio.ac.jp) + */ + +#include +#include "config.h" +#include "jlibconfig.h" + +static int _detect(unsigned char *str, int expected); +static int _detect_euc_or_sjis(unsigned char *str); +void printDetectCode(int detected); +int detectKanjiCode(char *str); + + +/* ------------------------------------------------------ 漢字コードの識別 --*/ + +static int _detect(unsigned char *str, int expected) +{ + register int c; + + while((c = (int)*str)!= '\0') { + + /* JIS コードの判定 */ + if(c == ESC) { + if((c = (int)*(++str)) == '\0') return expected; + if (c == '$') { + if((c = (int)*(++str)) == '\0') return expected; + /* ESC $ B --> 新JIS + ESC $ @ --> 旧JIS */ + if (c == 'B' || c == '@') return JIS; + } +#ifdef NECKANJI + if (c == 'K') + return NEC; /* ESC K --> NEC JIS */ +#endif + str++; + continue; + } + + /* SJIS に一意に決定 */ + if ((c >= 129 && c <= 141) || (c >= 143 && c <= 159)) + return SJIS; + /* SS2 */ + if (c == SS2) { + if((c = (int)*(++str)) == '\0') return expected; + if ((c >= 64 && c <= 126) || (c >= 128 && c <= 160) || + (c >= 224 && c <= 252)) return SJIS; + if (c >= 161 && c <= 223) expected = EUCORSJIS; + str++; + continue; + } + + if (c >= 161 && c <= 223) { + if((c = (int)*(++str)) == '\0') return expected; + + if (c >= 240 && c <= 254) + return EUC; + if (c >= 161 && c <= 223) { + expected = EUCORSJIS; + str++; + continue; + } + if (c <= 159) return SJIS; + if (c >= 240 && c <= 254) return EUC; + + if (c >= 224 && c <= 239) { + expected = EUCORSJIS; + while (c >= 64) { + if (c >= 129) { + if (c <= 141 || (c >= 143 && c <= 159)) + return SJIS; + else if (c >= 253 && c <= 254) { + return EUC; + } + } + if((c = (int)*(++str)) == '\0') return EUCORSJIS; + } + str++; + continue; + } + + if (c >= 224 && c <= 239) { + if((c = (int)*(++str)) == '\0') return expected; + if ((c >= 64 && c <= 126) || (c >= 128 && c <= 160)) + return SJIS; + if (c >= 253 && c <= 254) return EUC; + if (c >= 161 && c <= 252) + expected = EUCORSJIS; + } + } + str++; + } + return expected; +} + +/* ---------------------------------------------------SJIS か EUC の判定 -- */ +/* 日本語の特徴(ひらがな、カタカナ)から判定するため、 + 判定ミスが発生する場合もあります。 */ + +static int _detect_euc_or_sjis(unsigned char *str) { + int c1, c2; + int euc_c = 0, sjis_c = 0; + unsigned char *ptr; + static int expected = EUCORSJIS; + +#ifdef USE_CACHE_KANA_NARABI + if (expected != EUCORSJIS) + return expected; +#endif + + ptr = str, c2 = 0; + while ((c1 = (int)*ptr++) != '\0') { + if ((c2 > 0x80 && c2 < 0xa0) && (c2 >= 0xe0 && c2 < 0xfd) && + (c1 >= 0x40 && c1 < 0x7f) && (c1 >= 0x80 && c1 < 0xfd)) + sjis_c++, c1 = *ptr++; + c2 = c1; + } + if (sjis_c == 0) + expected = EUC; + else { + ptr = str, c2 = 0; + while ((c1 = (int)*ptr++) != '\0') { + if ((c2 > 0xa0 && c2 < 0xff) && + (c1 > 0xa0 && c1 < 0xff)) + euc_c++, c1 = *ptr++; + c2 = c1; + } + if (sjis_c > euc_c) + expected = SJIS; + else + expected = EUC; + } + return expected; +} + +/* ---------------------------------------------------------- Public 関数 -- */ + + +#ifdef DEBUG +void printDetectCode(int detected) { + switch(detected) { + case ASCII: + fprintf(stderr, "ASCII/JIS-Roman characters(94 printable)\n"); + break; + case JIS: + fprintf(stderr, "JIS(iso-2022-jp)\n"); + break; + case EUC: + fprintf(stderr, "EUC(x-euc-jp)\n"); + break; + case SJIS: + fprintf(stderr, "SJIS(x-sjis)\n"); + break; + case NEW: + fprintf(stderr, "JIS X 0208-1990\n"); + break; + case OLD: + fprintf(stderr, "JIS X 0208-1978\n"); + break; + case EUCORSJIS: + fprintf(stderr, "EUC or SJIS\n"); + break; + default: + printf("Another Codes!!\n"); + } +} +#endif + +int detectKanjiCode(char *str) +{ + static int detected = ASCII; + + if(!str) return (0); + + /* JIS, EUC, SJIS, EUCORSJIS の判定 */ + detected = _detect((unsigned char *)str, ASCII); + + /* 新JIS, 旧JIS, NEC JIS の場合、JIS に変更する */ + if(detected == NEW || detected == OLD || detected == NEC) + return JIS; + + /* SJIS か EUC の区別をカナの並びから推定する */ + if(detected == EUCORSJIS) +#ifdef KANA_NARABI + detected = _detect_euc_or_sjis((unsigned char *)str); +#else + detected = EUC; /* デフォルト EUC */ +#endif +#ifdef DEBUG + printDetectCode(detected); +#endif + + return detected; +} diff -urN a2ps-4.13.ORIG/libjcode/jlib.h a2ps-4.13/libjcode/jlib.h --- a2ps-4.13.ORIG/libjcode/jlib.h 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/jlib.h 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,17 @@ +/* + * jlib.h -- jlib.c 用のヘッダファイル by. 倉光 君郎 + * + * jlib.c を利用する場合は、include してください。 + * + */ + +#define ASCII 0 +#define JIS 1 +#define EUC 2 +#define SJIS 3 + +extern int detectKanjiCode(char *str); +extern char *toStringJIS(char *str); +extern char *toStringEUC(char *str); +extern char *toStringSJIS(char *str); +extern char *toStringAuto(char *str); diff -urN a2ps-4.13.ORIG/libjcode/jlibconfig.h a2ps-4.13/libjcode/jlibconfig.h --- a2ps-4.13.ORIG/libjcode/jlibconfig.h 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/jlibconfig.h 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,42 @@ +/* + * config.h + */ + +#define ASCII 0 +#define JIS 1 +#define EUC 2 +#define SJIS 3 +#define NEW 4 +#define OLD 5 +#define NEC 6 +#define EUCORSJIS 7 +#define NUL 0 +#define LF 10 +#define FF 12 +#define CR 13 +#define ESC 27 +#define SS2 142 +#define TRUE 1 +#define FALSE 0 + +/* 半角カナ(SJIS) を強制的に全角カナに変更する */ +#undef NO_HANKAKU_SJIS + +/* ひらがな、カタカナの並びから EUC , SJIS を推定する */ +#define KANA_NARABI + +/* EUC , SJIS を推定を始めの一度しか行なわない */ +/* (ファイルを一つしかひらかないなら有効でいい) */ +#undef USE_CACHE_KANA_NARABI + +/* strdup関数がシステムにあればdefine */ +#define HAVE_STRDUP 1 + +/* デバック用の関数を有効にする */ +#undef DEBUG + +/* ロケール名(大文字、小文字は区別されない) */ +#define SJIS_LOCALE_NAME "ja_JP.SJIS", "ja_JP.PCK" +#define JIS_LOCALE_NAME "ja_JP.JIS", "ja_JP.jis7" +#define EUC_LOCALE_NAME "ja_JP.ujis", "ja_JP.EUC",\ + "ja_JP.eucJP","japanese", "ja" diff -urN a2ps-4.13.ORIG/libjcode/libjcode.c a2ps-4.13/libjcode/libjcode.c --- a2ps-4.13.ORIG/libjcode/libjcode.c 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/libjcode.c 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,554 @@ +/* + * libjcode.c -- 漢字変換ライブラリ 1.0 版 + * (C) Kuramitsu Kimio, Tokyo Univ. 1996-97 + * + * このライブラリは、CGI Programming with C and Perl のために + * Ken Lunde 著 「日本語情報処理」 (O'llery) を参考にして、 + * ストリーム用だったjconv.c を、ストリング対応にしてライブラリ化 + * しました。 + * ただし、CGI (INTERNET)での利用を考えて、変更してあります。 + */ + +#include +#include +#include +#include +#include "jlib.h" +#include "config.h" +#include "jlibconfig.h" + +extern int detectKanjiCode(char *str); +static unsigned char *_to_jis(unsigned char *str); +static unsigned char *_to_ascii(unsigned char *str); +static void _jis_shift(int *p1, int *p2); +static void _sjis_shift(int *p1, int *p2); +static unsigned char *_sjis_han2zen(unsigned char *str, int *p1, int *p2); +static void _shift2seven(unsigned char *str, unsigned char *str2); +static void _shift2euc(unsigned char *str, unsigned char *str2); +static void _shift_self(unsigned char *str, unsigned char *str2); +static void _euc2seven(unsigned char *str, unsigned char *str2); +static void _euc2shift(unsigned char *str, unsigned char *str2); +static unsigned char *_skip_esc(unsigned char *str, int *esc_in); +static void _seven2shift(unsigned char *str, unsigned char *str2); +static void _seven2euc(unsigned char *str, unsigned char *str2); + + + +#define CHAROUT(ch) *str2 = (unsigned char)(ch); str2++; + +#ifndef HAVE_STRDUP +#define strdup(str) _strdup(str) +static char *_str_dup(unsigned char *buf) { + + unsigned char *p, *str; + if((str = (char *)malloc(strlen(buf) + 1)) == NULL) { + fprintf(stderr, "Can't malloc string buffer\n"); + exit(2); + } + + p = (unsigned char *)str; + + while(*buf) + *p++ = *buf++; + + *p = '\0'; + + return str; +} +#endif + +/* --------------------------------------- JIS(ISO-2022) コードへ切り替え -- */ + +static unsigned char *_to_jis(unsigned char *str) { + *str = (unsigned char)ESC; str++; + *str = (unsigned char)'$'; str++; + *str = (unsigned char)'B'; str++; + return str; +} + +/* ----------------------------------------------- ASCII コードへ切り替え -- */ + +/* ESC ( B と ESC ( J の違い。 + 本来は、 ESC ( J が正しいJIS-Roman 体系であるが、 + インターネットの上では、英数字はASCII の方が自然かと思われる。 + \ 記号と ~記号が違うだけである。 */ + +static unsigned char *_to_ascii(unsigned char *str) { + *str = (unsigned char)ESC; str++; + *str = (unsigned char)'('; str++; + *str = (unsigned char)'B'; str++; + return str; +} + +/* -------------------------------------- JIS コード を SJISとしてシフト -- */ + +static void _jis_shift(int *p1, int *p2) +{ + unsigned char c1 = *p1; + unsigned char c2 = *p2; + int rowOffset = c1 < 95 ? 112 : 176; + int cellOffset = c1 % 2 ? (c2 > 95 ? 32 : 31) : 126; + + *p1 = ((c1 + 1) >> 1) + rowOffset; + *p2 += cellOffset; +} + +/* --------------------------------- SJIS コードをJIS コードとしてシフト -- */ + +static void _sjis_shift(int *p1, int *p2) +{ + unsigned char c1 = *p1; + unsigned char c2 = *p2; + int adjust = c2 < 159; + int rowOffset = c1 < 160 ? 112 : 176; + int cellOffset = adjust ? (c2 > 127 ? 32 : 31) : 126; + + *p1 = ((c1 - rowOffset) << 1) - adjust; + *p2 -= cellOffset; +} + +/* ---------------------------------------------- SJIS 半角を全角に変換 -- */ +#define HANKATA(a) (a >= 161 && a <= 223) +#define ISMARU(a) (a >= 202 && a <= 206) +#define ISNIGORI(a) ((a >= 182 && a <= 196) || (a >= 202 && a <= 206) || (a == 179)) + +static int stable[][2] = { + {129,66},{129,117},{129,118},{129,65},{129,69},{131,146},{131,64}, + {131,66},{131,68},{131,70},{131,72},{131,131},{131,133},{131,135}, + {131,98},{129,91},{131,65},{131,67},{131,69},{131,71},{131,73}, + {131,74},{131,76},{131,78},{131,80},{131,82},{131,84},{131,86}, + {131,88},{131,90},{131,92},{131,94},{131,96},{131,99},{131,101}, + {131,103},{131,105},{131,106},{131,107},{131,108},{131,109}, + {131,110},{131,113},{131,116},{131,119},{131,122},{131,125}, + {131,126},{131,128},{131,129},{131,130},{131,132},{131,134}, + {131,136},{131,137},{131,138},{131,139},{131,140},{131,141}, + {131,143},{131,147},{129,74},{129,75}}; + +static unsigned char *_sjis_han2zen(unsigned char *str, int *p1, int *p2) +{ + register int c1, c2; + + c1 = (int)*str; str++; + *p1 = stable[c1 - 161][0]; + *p2 = stable[c1 - 161][1]; + + /* 濁音、半濁音の処理 */ + c2 = (int)*str; + if (c2 == 222 && ISNIGORI(c1)) { + if ((*p2 >= 74 && *p2 <= 103) || (*p2 >= 110 && *p2 <= 122)) + (*p2)++; + else if (*p1 == 131 && *p2 == 69) + *p2 = 148; + str++; + } + + if (c2 == 223 && ISMARU(c1) && (*p2 >= 110 && *p2 <= 122) ) { + *p2 += 2; + str++; + } + return str++; +} + +/* -------------------------------------------------- SJIS コードを変換 -- */ + +#define SJIS1(A) ((A >= 129 && A <= 159) || (A >= 224 && A <= 239)) +#define SJIS2(A) (A >= 64 && A <= 252) + +static void _shift2seven(unsigned char *str, unsigned char *str2) +{ + int p1,p2,esc_in = FALSE; + + while ((p1 = (int)*str) != '\0') { + + if (SJIS1(p1)) { + if((p2 = (int)*(++str)) == '\0') break; + if (SJIS2(p2)) { + _sjis_shift(&p1,&p2); + if (!esc_in) { + esc_in = TRUE; + str2 = _to_jis(str2); + } + } + CHAROUT(p1); + CHAROUT(p2); + str++; + continue; + } + +#ifdef NO_HANKAKU_SJIS + /* 半角 SJIS は、強制的に全角に変える */ + if (HANKATA(p1)) { + str = _sjis_han2zen(str, &p1, &p2); + _sjis_shift(&p1,&p2); + if (!esc_in) { + esc_in = TRUE; + str2 = _to_jis(str2); + } + CHAROUT(p1); + CHAROUT(p2); + continue; + } +#endif + + if (esc_in) { + /* LF / CR の場合は、正常にエスケープアウトされる */ + esc_in = FALSE; + str2 = _to_ascii(str2); + } + CHAROUT(p1); + str++; + } + + if (esc_in) + str2 = _to_ascii(str2); + *str2='\0'; +} + +/* --------------------------------------------- SJIS を EUC に変換する -- */ + +static void _shift2euc(unsigned char *str, unsigned char *str2) +{ + int p1,p2; + + while ((p1 = (int)*str) != '\0') { + if (SJIS1(p1)) { + if((p2 = (int)*(++str)) == '\0') break; + if (SJIS2(p2)) { + _sjis_shift(&p1,&p2); + p1 += 128; + p2 += 128; + } + CHAROUT(p1); + CHAROUT(p2); + str++; + continue; + } + +#ifdef NO_HANKAKU_SJIS + /* 半角 SJIS は、強制的に全角に変える */ + if (HANKATA(p1)) { + str = _sjis_han2zen(str,&p1,&p2); + _sjis_shift(&p1,&p2); + p1 += 128; + p2 += 128; + CHAROUT(p1); + CHAROUT(p2); + continue; + } +#endif + CHAROUT(p1); + str++; + } + *str2='\0'; +} + +/* ------------------------------------------------- 半角 SJIS を取り除く -- */ + +static void _shift_self(unsigned char *str, unsigned char *str2) +{ + int p1,p2; + + while ((p1 = (int)*str) != '\0') { +#ifdef NO_HANKAKU_SJIS + /* 半角 SJIS は、強制的に全角に変える */ + if (HANKATA(p1)) { + str = _sjis_han2zen(str, &p1, &p2); + CHAROUT(p1); + CHAROUT(p2); + continue; + } +#endif + CHAROUT(p1); + str++; + } + *str2='\0'; +} + +/* ------------------------------------------------------EUC から JIS へ -- */ + +#define ISEUC(A) (A >= 161 && A <= 254) + +static void _euc2seven(unsigned char *str, unsigned char *str2) +{ + int p1, p2, esc_in = FALSE; + + while ((p1 = (int)*str) != '\0') { + + if (p1 == LF || p1 == CR) { + if (esc_in) { + esc_in = FALSE; + str2 = _to_ascii(str2); + } + CHAROUT(p1); + str++; + continue; + } + + if (ISEUC(p1)) { + if((p2 = (int)*(++str)) == '\0') break; + if (ISEUC(p2)) { + + if (!esc_in) { + esc_in = TRUE; + str2 =_to_jis(str2); + } + + CHAROUT(p1-128); + CHAROUT(p2-128); + str++; + continue; + } + } + + if (esc_in) { + esc_in = FALSE; + str2 = _to_ascii(str2); + } + CHAROUT(p1); + str++; + } + *str2='\0'; +} + +/* ------------------------------------------------ EUC から SJIS に変換 -- */ + +static void _euc2shift(unsigned char *str, unsigned char *str2) +{ + int p1,p2; + + while ((p1 = (int)*str) != '\0') { + if (ISEUC(p1)) { + if((p2 = (int)*(++str)) == '\0') break; + if (ISEUC(p2)) { + p1 -= 128; + p2 -= 128; + _jis_shift(&p1,&p2); + } + CHAROUT(p1); + CHAROUT(p2); + str++; + continue; + } + + CHAROUT(p1); + str++; + } + *str2='\0'; +} + +/* -------------------------------------- ESC シーケンスをスキップする ----- */ + +static unsigned char *_skip_esc(unsigned char *str, int *esc_in) { + int c; + + c = (int)*(++str); + if ((c == '$') || (c == '(')) str++; + if ((c == 'K') || (c == '$')) *esc_in = TRUE; + else *esc_in = FALSE; + + if(*str != '\0') str++; + return str; +} + + +/* ----------------------------------------------- JIS を SJIS に変換する -- */ + +static void _seven2shift(unsigned char *str, unsigned char *str2) +{ + int p1, p2, esc_in = FALSE; + + while ((p1 = (int)*str) != '\0') { + + /* ESCシーケンスをスキップする */ + if (p1 == ESC) { + str = _skip_esc(str, &esc_in); + continue; + } + + if (p1 == LF || p1 == CR) { + if (esc_in) esc_in = FALSE; + } + + if(esc_in) { /* ISO-2022-JP コード */ + if((p2 = (int)*(++str)) == '\0') break; + + _jis_shift(&p1, &p2); + + CHAROUT(p1); + CHAROUT(p2); + }else{ /* ASCII コード */ + CHAROUT(p1); + } + str++; + } + *str2 = '\0'; +} + +/* ------------------------------------------------ JIS を EUC に変換する -- */ + +static void _seven2euc(unsigned char *str, unsigned char *str2) +{ + int p1, esc_in = FALSE; + + while ((p1 = (int)*str) != '\0') { + + /* ESCシーケンスをスキップする */ + if (p1 == ESC) { + str = _skip_esc(str, &esc_in); + continue; + } + + if (p1 == LF || p1 == CR) { + if (esc_in) esc_in = FALSE; + } + + if(esc_in) { /* ISO-2022-JP コード */ + CHAROUT(p1 + 128); + + if((p1 = (int)*(++str)) == '\0') break; + CHAROUT(p1 + 128); + }else{ /* ASCII コード */ + CHAROUT(p1); + } + str++; + } + *str2 = '\0'; +} + +/* ------------------------------------------------------------------------ */ +/* --------------------------------------------------------- Public 関数 -- */ +char *toStringJIS(char *str) { + int detected; + unsigned char *buf, *ret; + + if(!str) return (NULL); + detected = detectKanjiCode(str); + if(detected == ASCII || detected == JIS) + return strdup(str); + + buf = (unsigned char*)malloc(strlen(str)*2); + if (!buf) return NULL; + + switch(detected) { + case SJIS : + _shift2seven((unsigned char *)str, buf); + break; + case EUC : + _euc2seven((unsigned char *)str, buf); + break; + default: + free(buf); + return strdup(str); + break; + } + + ret = strdup(buf); + free(buf); + return ret; +} + +char *toStringEUC(char *str) { + int detected; + unsigned char *buf, *ret; + + if(!str) return (NULL); + detected = detectKanjiCode(str); + if(detected == ASCII || detected == EUC) return strdup(str); + + buf = (unsigned char*)malloc(strlen(str)*2); + if (!buf) return NULL; + + switch(detected) { + case SJIS : + _shift2euc((unsigned char *)str, buf); + break; + case JIS : + case NEW : case OLD : case NEC : + _seven2euc((unsigned char *)str, buf); + break; + default: + free(buf); + return strdup(str); + break; + } + + ret = strdup(buf); + free(buf); + return ret; +} + +char *toStringSJIS(char *str) { + int detected; + unsigned char *buf, *ret; + + if (!str) return NULL; + detected = detectKanjiCode(str); + if(detected == ASCII) return strdup(str); + + buf = (unsigned char*)malloc(strlen(str)*2); + if (!buf) return NULL; + + switch(detected) { + case NEW : case OLD : case NEC : + case JIS : + _seven2shift((unsigned char *)str, buf); + break; + case EUC : + _euc2shift((unsigned char *)str, buf); + break; + case SJIS : + default: + _shift_self((unsigned char *)str, buf); + } + + ret = strdup(buf); + free(buf); + return ret; +} + +char *toStringAuto(char *str) { + static int jpcode = -1; + static char *sjis_locale_name[] = {SJIS_LOCALE_NAME, NULL}; + static char *jis_locale_name[] = {JIS_LOCALE_NAME, NULL}; + static char *euc_locale_name[] = {EUC_LOCALE_NAME, NULL}; + static struct LOCALETABLE { + int code; + char **name_list; + } locale_table[] = { {SJIS, sjis_locale_name}, + {EUC, euc_locale_name}, + {JIS, jis_locale_name}}; + + if(!str) return (NULL); + + if (jpcode == -1) { + char *ctype = setlocale(LC_CTYPE, ""); + int i, j; + for( j=0; jpcode == -1 && + j < sizeof(locale_table)/sizeof(struct LOCALETABLE); j++ ) { + char **name = locale_table[j].name_list; + for( i=0; name[i]; i++ ) + if (strcasecmp(ctype, name[i]) == 0) { + jpcode = locale_table[j].code; + break; + } + } + if(jpcode == -1) + jpcode = ASCII; + } + + switch (jpcode) { + case SJIS: + return (toStringSJIS(str)); + break; + case JIS: + case NEW : case OLD : case NEC : + return (toStringJIS(str)); + break; + case EUC: + return (toStringEUC(str)); + break; + default: + return (strdup(str)); + break; + } +} diff -urN a2ps-4.13.ORIG/libjcode/sample.c a2ps-4.13/libjcode/sample.c --- a2ps-4.13.ORIG/libjcode/sample.c 1970-01-01 09:00:00.000000000 +0900 +++ a2ps-4.13/libjcode/sample.c 2003-09-27 05:45:02.000000000 +0900 @@ -0,0 +1,41 @@ +/* + sample.c -- サンプルプログラム by. 倉光 君郎, 1996 + + このプログラムは、サンプルプログラムです。 + 標準入力から読み込んだテキストをオプションにあわせて、 + コード変換します。 +*/ + +#include +#include +#include "jlib.h" + +extern void printDetectCode(int code); + +void main(int ac, char *av[]) { + char buffer[BUFSIZ]; + int mode=JIS; + + if(ac == 2) { + if(!strcmp(av[1], "-e")) mode = EUC; + if(!strcmp(av[1], "-s")) mode =SJIS; + } + + while(fgets(buffer,BUFSIZ,stdin) != NULL) { + switch(mode) { + case EUC: + printf("%s", toStringEUC(buffer)); + break; + case SJIS: + printf("%s", toStringSJIS(buffer)); + break; + default: + printf("%s", toStringJIS(buffer)); + break; + } + } + exit(0); +} + + + diff -urN a2ps-4.13.ORIG/ps/base.ps a2ps-4.13/ps/base.ps --- a2ps-4.13.ORIG/ps/base.ps 2003-09-27 04:40:41.000000000 +0900 +++ a2ps-4.13/ps/base.ps 2003-09-27 05:45:02.000000000 +0900 @@ -153,7 +153,11 @@ % Return the y size of the current font % - => fontsize /currentfontsize { - currentfont /FontMatrix get 3 get 1000 mul + currentfont /FontType get 0 eq { + currentfont /FontMatrix get 3 get + }{ + currentfont /FontMatrix get 3 get 1000 mul + } ifelse } bind def % reencode the font @@ -200,6 +204,144 @@ end } bind def +% composite fonts for ASCII-EUC mixed string +% Version 1.2 1/31/1990 +% Orignal Ken'ichi HANDA (handa@etl.go.jp) +% Modified Norio Katayama (katayama@rd.nacsis.ac.jp),1998 +% Extend & Fix Koji Nakamaru (maru@on.cs.keio.ac.jp), 1999 +% Anyone can freely copy, modify, distribute this program. + +/copyfont { % font-dic extra-entry-count copyfont font-dic + 1 index maxlength add dict begin + { 1 index /FID ne 2 index /UniqueID ne and + {def} {pop pop} ifelse + } forall + currentdict + end +} bind def + +/compositefont { % ASCIIFontName EUCFontName RomanScale RomanOffset Rot(T/F) compositefont font + /RomanRotation exch def + /RomanOffset exch def + /RomanScale exch def + userdict /fixeucfont_dict known not { + userdict begin + /fixeucfont_dict 2 dict begin + /UpperByteEncoding [ + 16#00 1 16#20 { pop 0 } for + 16#21 1 16#28 { 16#20 sub } for + 16#29 1 16#2F { pop 0 } for + 16#30 1 16#74 { 16#27 sub } for + 16#75 1 16#FF { pop 0 } for + ] def + /LowerByteEncoding [ + 16#00 1 16#A0 { pop /.notdef } for + 16#A1 1 16#FE { 16#80 sub 16 2 string cvrs + (cXX) dup 1 4 -1 roll + putinterval cvn } for + /.notdef + ] def + currentdict + end def + end + } if + findfont dup /FontType get 0 eq { + 14 dict begin + % + % 7+8 bit EUC font + % + 12 dict begin + /EUCFont exch def + /FontInfo (7+8 bit EUC font) readonly def + /PaintType 0 def + /FontType 0 def + /FontMatrix matrix def + % /FontName + /Encoding fixeucfont_dict /UpperByteEncoding get def + /FMapType 2 def + EUCFont /WMode known + { EUCFont /WMode get /WMode exch def } + { /WMode 0 def } ifelse + /FDepVector [ + EUCFont /FDepVector get 0 get + [ 16#21 1 16#28 {} for 16#30 1 16#74 {} for ] + { + 13 dict begin + /EUCFont EUCFont def + /UpperByte exch 16#80 add def + % /FontName + /FontInfo (EUC lower byte font) readonly def + /PaintType 0 def + /FontType 3 def + /FontMatrix matrix def + /FontBBox {0 0 0 0} def + /Encoding + fixeucfont_dict /LowerByteEncoding get def + % /UniqueID + % /WMode + /BuildChar { + gsave + exch dup /EUCFont get setfont + /UpperByte get + 2 string + dup 0 4 -1 roll put + dup 1 4 -1 roll put + dup stringwidth setcharwidth + 0 0 moveto show + grestore + } bind def + currentdict + end + /lowerbytefont exch definefont + } forall + ] def + currentdict + end + /eucfont exch definefont + exch + findfont 1 copyfont dup begin + RomanRotation { + /FontMatrix FontMatrix + [ 0 RomanScale neg RomanScale 0 RomanOffset neg 0 ] + matrix concatmatrix def + }{ + /FontMatrix FontMatrix + [ RomanScale 0 0 RomanScale 0 RomanOffset ] matrix concatmatrix + def + /CDevProc + {pop pop pop pop 0 exch -1000 exch 2 div 880} def + } ifelse + end + /asciifont exch definefont + exch + /FDepVector [ 4 2 roll ] def + /FontType 0 def + /WMode 0 def + /FMapType 4 def + /FontMatrix matrix def + /Encoding [0 1] def + /FontBBox {0 0 0 0} def +% /FontHeight 1.0 def % XXXX + /FontHeight RomanScale 1.0 ge { RomanScale }{ 1.0 } ifelse def + /Descent -0.3 def % XXXX + currentdict + end + /tmpfont exch definefont + pop + /tmpfont findfont + }{ + pop findfont 0 copyfont + } ifelse +} def + +/slantfont { % FontName slant-degree slantfont font' + exch findfont 1 copyfont begin + [ 1 0 4 -1 roll 1 0 0 ] FontMatrix exch matrix concatmatrix + /FontMatrix exch def + currentdict + end +} def + % Function print line number ( # -) /# { gsave diff -urN a2ps-4.13.ORIG/src/Makefile.am a2ps-4.13/src/Makefile.am --- a2ps-4.13.ORIG/src/Makefile.am 2003-09-27 04:40:42.000000000 +0900 +++ a2ps-4.13/src/Makefile.am 2003-09-27 05:53:23.000000000 +0900 @@ -49,8 +49,8 @@ # I don't really understand why I have to put srcdir here, but # it is needed for yacc and lex files (seems related to #line, but # I really don't understand why)... -INCLUDES = -I.. -I$(srcdir) -I$(top_srcdir)/lib -I$(top_builddir)/intl +INCLUDES = -I.. -I$(srcdir) -I$(top_srcdir)/lib -I$(top_builddir)/intl -I$(top_builddir)/libjcode -a2ps_LDADD = $(top_builddir)/lib/liba2ps.la @LIBINTL@ -lm +a2ps_LDADD = $(top_builddir)/lib/liba2ps.la @LIBINTL@ @LEXLIB@ @LIBJCODELIBS@ -lm EXTRA_DIST = $(BUILT_SOURCES) diff -urN a2ps-4.13.ORIG/src/Makefile.in a2ps-4.13/src/Makefile.in --- a2ps-4.13.ORIG/src/Makefile.in 2003-09-27 05:07:37.000000000 +0900 +++ a2ps-4.13/src/Makefile.in 2003-09-27 05:54:18.000000000 +0900 @@ -304,8 +304,8 @@ # I don't really understand why I have to put srcdir here, but # it is needed for yacc and lex files (seems related to #line, but # I really don't understand why)... -INCLUDES = -I.. -I$(srcdir) -I$(top_srcdir)/lib -I$(top_builddir)/intl +INCLUDES = -I.. -I$(srcdir) -I$(top_srcdir)/lib -I$(top_builddir)/intl -I$(top_builddir)/libjcode -a2ps_LDADD = $(top_builddir)/lib/liba2ps.la @LIBINTL@ -lm +a2ps_LDADD = $(top_builddir)/lib/liba2ps.la @LIBINTL@ @LEXLIB@ @LIBJCODELIBS@ -lm EXTRA_DIST = $(BUILT_SOURCES) all: $(BUILT_SOURCES) $(MAKE) $(AM_MAKEFLAGS) all-am diff -urN a2ps-4.13.ORIG/src/buffer.c a2ps-4.13/src/buffer.c --- a2ps-4.13.ORIG/src/buffer.c 2003-09-27 04:40:42.000000000 +0900 +++ a2ps-4.13/src/buffer.c 2003-09-27 05:45:02.000000000 +0900 @@ -41,6 +41,10 @@ #include "argmatch.h" #include "buffer.h" #include +#ifdef USE_LIBJCODE +#include "jlib.h" +extern use_libjcode; +#endif /****************************************************************/ /* Handling of the various eol styles */ @@ -418,9 +422,21 @@ match_keyword, which looks one char after the current char. With this sentinel, which is probably not in the alphabet, we save a test on the length of the buffer. */ +#ifdef USE_LIBJCODE + obstack_1grow (&buffer->obstack, '\0'); + if (use_libjcode == true) + { + if(buffer->content) free(buffer->content); + buffer->content = toStringEUC(obstack_finish (&buffer->obstack)); + } + else + buffer->content = (uchar *) obstack_finish (&buffer->obstack); + buffer->len = strlen(buffer->content); +#else buffer->len = obstack_object_size (&buffer->obstack); obstack_1grow (&buffer->obstack, '\0'); buffer->content = (uchar *) obstack_finish (&buffer->obstack); +#endif /* One more line read */ buffer->line++;