diff -up a2ps-4.14/config.h.in.euc a2ps-4.14/config.h.in --- a2ps-4.14/config.h.in.euc 2007-12-29 04:28:05.000000000 +0100 +++ a2ps-4.14/config.h.in 2008-04-27 10:39:24.000000000 +0200 @@ -24,6 +24,9 @@ /* Define if TIOCGWINSZ requires sys/ioctl.h */ #undef GWINSZ_IN_SYS_IOCTL +/* Define if you want to support japanese */ +#undef ENABLE_KANJI + /* Define to 1 if you have the `alarm' function. */ #undef HAVE_ALARM diff -up a2ps-4.14/configure.euc a2ps-4.14/configure --- a2ps-4.14/configure.euc 2008-04-27 10:39:24.000000000 +0200 +++ a2ps-4.14/configure 2008-04-27 10:41:39.000000000 +0200 @@ -1587,7 +1587,8 @@ Optional Packages: --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-kanji support Japanese (default=yes) Some influential environment variables: CC C compiler command @@ -22521,7 +22522,7 @@ fi for ac_header in sys/time.h sys/stat.h sys/types.h sys/ioctl.h \ math.h string.h strings.h stdlib.h unistd.h stdarg.h pwd.h malloc.h \ - memory.h errno.h fcntl.h stdbool.h fnmatch.h + memory.h errno.h fcntl.h stdbool.h fnmatch.h iconv.h do as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` if { as_var=$as_ac_Header; eval "test \"\${$as_var+set}\" = set"; }; then @@ -30947,6 +30948,22 @@ fi +# Check whether --enable-kanji or --disable-kanji was given. +if test "${enable_kanji+set}" = set; then + enableval="$enable_kanji" + SUPPORT_KANJI=$enableval +else + SUPPORT_KANJI=yes +fi + +if test "$SUPPORT_KANJI" = "yes"; then + cat >> confdefs.h <<\EOF +#define ENABLE_KANJI 1 +EOF +# ENCODING=euc-jp +fi + + ######################## # Nice special printers ######################## diff -up a2ps-4.14/configure.in.euc a2ps-4.14/configure.in --- a2ps-4.14/configure.in.euc 2008-04-27 10:39:24.000000000 +0200 +++ a2ps-4.14/configure.in 2008-04-27 10:39:24.000000000 +0200 @@ -72,7 +72,7 @@ AC_HEADER_SYS_WAIT AC_HEADER_DIRENT AC_CHECK_HEADERS(sys/time.h sys/stat.h sys/types.h sys/ioctl.h \ math.h string.h strings.h stdlib.h unistd.h stdarg.h pwd.h malloc.h \ - memory.h errno.h fcntl.h stdbool.h fnmatch.h) + memory.h errno.h fcntl.h stdbool.h fnmatch.h iconv.h) ## --------------------- ## ## Checks for typedefs. ## @@ -276,11 +276,23 @@ AC_SUBST(MEDIUM) # AC_ARG_WITH(encoding, AC_HELP_STRING([--with-encoding=enc], - [specify the default encoding (ascii, latin1, latin2... latin6, hp etc.) [default=latin1]]), + [specify the default encoding (ascii, latin1, latin2... latin6, euc-jp, hp etc.) [default=latin1]]), ENCODING=$with_encoding, ENCODING=latin1) AC_SUBST(ENCODING) +# +# use libjcode +# +AC_ARG_ENABLE(kanji, + [ --enable-kanji support Japanese/kanji (default: yes)], + SUPPORT_KANJI=$enableval, SUPPORT_KANJI=yes) +if test "$SUPPORT_KANJI" = "yes"; then + AC_DEFINE(ENABLE_KANJI) + dnl ENCODING=euc-jp +fi + + ######################## # Nice special printers ######################## diff -up a2ps-4.14/encoding/encoding.map.euc a2ps-4.14/encoding/encoding.map --- a2ps-4.14/encoding/encoding.map.euc 2007-12-29 02:39:21.000000000 +0100 +++ a2ps-4.14/encoding/encoding.map 2008-04-27 10:39:24.000000000 +0200 @@ -93,6 +93,12 @@ koi8r koi8 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 -up /dev/null a2ps-4.14/encoding/euc-jp.edf --- /dev/null 2008-04-27 11:55:27.307012118 +0200 +++ a2ps-4.14/encoding/euc-jp.edf 2008-04-27 10:39:24.000000000 +0200 @@ -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 -up a2ps-4.14/encoding/Makefile.am.euc a2ps-4.14/encoding/Makefile.am --- a2ps-4.14/encoding/Makefile.am.euc 2007-12-29 02:39:27.000000000 +0100 +++ a2ps-4.14/encoding/Makefile.am 2008-04-27 10:39:24.000000000 +0200 @@ -16,7 +16,7 @@ major_encodings = ascii.edf iso1.edf 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 -up a2ps-4.14/encoding/Makefile.in.euc a2ps-4.14/encoding/Makefile.in --- a2ps-4.14/encoding/Makefile.in.euc 2007-12-29 04:28:07.000000000 +0100 +++ a2ps-4.14/encoding/Makefile.in 2008-04-27 10:39:24.000000000 +0200 @@ -270,7 +270,7 @@ major_encodings = ascii.edf iso1.edf 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 -up a2ps-4.14/lib/encoding.c.euc a2ps-4.14/lib/encoding.c --- a2ps-4.14/lib/encoding.c.euc 2007-12-29 02:37:54.000000000 +0100 +++ a2ps-4.14/lib/encoding.c 2008-04-27 10:39:24.000000000 +0200 @@ -37,6 +37,9 @@ #include "document.h" #include "quotearg.h" #include "strverscmp.h" +#ifdef ENABLE_KANJI +int use_jcode = false; +#endif /* Suffix of the Encoding Description Files */ #define EDF_SUFFIX ".edf" @@ -389,15 +392,25 @@ font_entry_set_used (struct hash_table_s * 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 encoding { 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 @@ encoding_new (const char * key) 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 @@ encoding_add_font_substitute (struct enc } /* + * 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 @@ encoding_resolve_font_substitute (struct } 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 @@ load_encoding_description_file (a2ps_job { token2 = GET_TOKEN (NULL); CHECK_TOKEN (); +#ifdef ENABLE_KANJI + if( strcmp(token2, "EUC-JP")== 0) + use_jcode = true; + else + use_jcode = false; +#endif encoding->name = xstrdup (token2); } else if (strequ (token, "Default:")) @@ -633,6 +757,66 @@ load_encoding_description_file (a2ps_job 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 @@ encoding_char_exists (struct encoding * } /* + * 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 @@ dump_encoding_setup (FILE * stream, 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 @@ dump_encoding_setup (FILE * stream, * 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 @@ encoding_build_faces_wx (a2ps_job * job, 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 @@ char_WX (a2ps_job * job, uchar c) 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 -up a2ps-4.14/lib/encoding.h.euc a2ps-4.14/lib/encoding.h --- a2ps-4.14/lib/encoding.h.euc 2007-12-29 02:58:17.000000000 +0100 +++ a2ps-4.14/lib/encoding.h 2008-04-27 10:39:24.000000000 +0200 @@ -43,6 +43,7 @@ struct a2ps_job; /* Declared in jobs.h w */ 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 @@ void encoding_self_print PARAMS ((struct 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 @@ const char * encoding_resolve_font_subst 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 -up a2ps-4.14/lib/pair_ht.c.euc a2ps-4.14/lib/pair_ht.c --- a2ps-4.14/lib/pair_ht.c.euc 2007-12-29 02:58:21.000000000 +0100 +++ a2ps-4.14/lib/pair_ht.c 2008-04-27 10:39:24.000000000 +0200 @@ -49,6 +49,8 @@ struct pair { char * key; char * value; + float raito; + int wx; }; /* @@ -165,6 +167,37 @@ pair_add (struct hash_table_s * table, } /* + * 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 @@ pair_get (struct hash_table_s * table, c 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 -up a2ps-4.14/lib/pair_ht.h.euc a2ps-4.14/lib/pair_ht.h --- a2ps-4.14/lib/pair_ht.h.euc 2007-12-29 02:58:21.000000000 +0100 +++ a2ps-4.14/lib/pair_ht.h 2008-04-27 10:39:24.000000000 +0200 @@ -56,6 +56,10 @@ void pair_table_free PARAMS ((struct pai 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 @@ void pair_delete PARAMS ((struct pair_ht */ 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 -up a2ps-4.14/lib/psgen.c.euc a2ps-4.14/lib/psgen.c --- a2ps-4.14/lib/psgen.c.euc 2007-12-29 02:58:22.000000000 +0100 +++ a2ps-4.14/lib/psgen.c 2008-04-27 10:39:24.000000000 +0200 @@ -875,6 +875,7 @@ ps_print_char (a2ps_job * job, int c, en print: default: { + static mb_flag= 0; uchar buf[256]; int nchars; *buf = '\0'; @@ -889,6 +890,29 @@ ps_print_char (a2ps_job * job, int c, en 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 @@ ps_print_char (a2ps_job * job, int c, en return; } } + } output (jdiv, "%s", buf); - job->status->chars++; + job->status->chars+=nchars; } break; } diff -up a2ps-4.14/ps/base.ps.euc a2ps-4.14/ps/base.ps --- a2ps-4.14/ps/base.ps.euc 2007-12-29 02:58:26.000000000 +0100 +++ a2ps-4.14/ps/base.ps 2008-04-27 10:39:24.000000000 +0200 @@ -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 -up /dev/null a2ps-4.14/README.eucJP --- /dev/null 2008-04-27 11:55:27.307012118 +0200 +++ a2ps-4.14/README.eucJP 2008-04-27 10:39:24.000000000 +0200 @@ -0,0 +1,100 @@ +a2ps euc-jp kanji supported patch: +by SATO Satoru + +These patches enables a2ps to support the files written in EUC-JP (and other +Japanese encodings). I only arranged patches created by FURUKAWA Yasuyuki, +KATAYAMA Yukio, and replaced libjcode by customized jcode.[ch] (by KITAME +Takuo). + +Notes from the orginal patch by FURUKAWA Yukihiro is follows. +(sorry, it is written in japanese only): + +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 -up a2ps-4.14/src/buffer.c.euc a2ps-4.14/src/buffer.c --- a2ps-4.14/src/buffer.c.euc 2007-12-29 02:58:34.000000000 +0100 +++ a2ps-4.14/src/buffer.c 2008-04-27 10:39:24.000000000 +0200 @@ -41,6 +41,21 @@ #include "argmatch.h" #include "buffer.h" #include + +#ifdef HAVE_CONFIG_H +# include +#endif + +#ifdef ENABLE_KANJI +# include +# include +# include +# include +# include +# include +extern use_jcode; +#endif + /****************************************************************/ /* Handling of the various eol styles */ @@ -526,3 +541,278 @@ buffer_test (const char *filename) buffer_release (&buffer); } #endif + +/** + * from jcode.c by Takuo KITAME + */ +#ifdef ENABLE_KANJI + +enum { + JCODE_ASCII, + JCODE_EUC, + JCODE_JIS, + JCODE_SJIS, + EUCORSJIS }; + +#define ESC 0x1b +#define SS2 0x8e + +#define JCODE_LOCALE_EUC "ja", "ja_JP", "ja_JP.ujis", "ja_JP.EUC", "ja_JP.eucJP" +#define JCODE_LOCALE_JIS "ja_JP.JIS", "ja_JP.jis", "ja_JP.iso-2022-jp" +#define JCODE_LOCALE_SJIS "ja_JP.SJIS", "ja_JP.sjis" + +/****************************************************************************/ +/* Japanese string code detector */ +/****************************************************************************/ +int +detect_kanji(unsigned char *str) +{ + int expected = JCODE_ASCII; + register int c; + int c1, c2; + int euc_c = 0, sjis_c = 0; + unsigned char *ptr = str; + + while((c = (int)*ptr)!= '\0') { + if(c == ESC) { + if((c = (int)*(++ptr)) == '\0') + break; + if(c == '$') { + if((c = (int)*(++ptr)) == '\0') + break; + if(c == 'B' || c == '@') + return JCODE_JIS; + } + ptr++; + continue; + } + if((c >= 0x81 && c <= 0x8d) || (c >= 0x8f && c <= 0x9f)) + return JCODE_SJIS; + + if(c == SS2) { + if((c = (int)*(++ptr)) == '\0') + break; + if((c >= 0x40 && c <= 0x7e) || + (c >= 0x80 && c <= 0xa0) || + (c >= 0xe0 && c <= 0xfc)) + return JCODE_SJIS; + if(c >= 0xa1 && c <= 0xdf) + break; + + ptr++; + continue; + } + if(c >= 0xa1 && c <= 0xdf) { + if((c = (int)*(++ptr)) == '\0') + break; + + if (c >= 0xe0 && c <= 0xfe) + return JCODE_EUC; + if (c >= 0xa1 && c <= 0xdf) { + expected = EUCORSJIS; + ptr++; + continue; + } +#if 1 + if(c == 0xa0 || (0xe0 <= c && c <= 0xfe)) + return JCODE_EUC; + else { + expected = EUCORSJIS; + ptr++; + continue; + } +#else + if(c <= 0x9f) + return JCODE_SJIS; + if(c >= 0xf0 && c <= 0xfe) + return JCODE_EUC; +#endif + + if(c >= 0xe0 && c <= 0xef) { + expected = EUCORSJIS; + while(c >= 0x40) { + if(c >= 0x81) { + if(c <= 0x8d || (c >= 0x8f && c <= 0x9f)) + return JCODE_SJIS; + else if(c >= 0xfd && c <= 0xfe) { + return JCODE_EUC; + } + } + if((c = (int)*(++ptr)) == '\0') + break; + } + ptr++; + continue; + } + + if(c >= 0xe0 && c <= 0xef) { + if((c = (int)*(++ptr)) == '\0') + break; + if((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xa0)) + return JCODE_SJIS; + if(c >= 0xfd && c <= 0xfe) + return JCODE_EUC; + if(c >= 0xa1 && c <= 0xfc) + expected = EUCORSJIS; + } + } +#if 1 + if (0xf0 <= c && c <= 0xfe) + return JCODE_EUC; +#endif + ptr++; + } + + 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 = JCODE_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 = JCODE_SJIS; + else + expected = JCODE_EUC; + } + return expected; +} + +int +int_detect_JCode(char *str) +{ + int detected; + + if(!str) + return 0; + + detected = detect_kanji((unsigned char *)str); + + if(detected == JCODE_ASCII) + return JCODE_ASCII; + + switch(detected) { + case JCODE_EUC: + return JCODE_EUC; + break; + case JCODE_JIS: + return JCODE_JIS; + break; + case JCODE_SJIS: + return JCODE_SJIS; + break; + default: + return JCODE_ASCII; + break; + } + + /* not reached */ + return 0; +} + +const char * +detect_JCode(char *str) +{ + int detected; + + if(!str) + return NULL; + + detected = detect_kanji((unsigned char *)str); + + if(detected == JCODE_ASCII) + return "ASCII"; + + switch(detected) { + case JCODE_EUC: + return "EUC-JP"; + break; + case JCODE_JIS: + return "ISO-2022-JP"; + break; + case JCODE_SJIS: + return "SJIS"; + break; + default: + return "ASCII"; + break; + } + + /* not reached */ + return 0; +} + +char * +kanji_conv_auto(char *str, const char *dstset) +{ + unsigned char *buf, *ret; + iconv_t cd; + size_t insize = 0; + size_t outsize = 0; + size_t nconv = 0; + char *inptr; + char *outptr; + char srcset[16]; + + if(!str) + return NULL; + + switch (int_detect_JCode(str)) { + case JCODE_EUC: + strcpy(srcset, "EUC-JP"); + break; + case JCODE_JIS: + strcpy(srcset, "ISO-2022-JP"); + break; + case JCODE_SJIS: + strcpy(srcset, "SJIS"); + break; + default: + return strdup(str); + break; + } + + buf = (unsigned char *)malloc(strlen(str)* 4 + 1); + if(!buf) + return NULL; + + insize = strlen(str); + inptr = str; + outsize = strlen(str) * 4 ; + outptr = buf; + + cd = iconv_open(dstset, srcset); + if(cd == (iconv_t) -1) { + if(errno == EINVAL) + return strdup(str); + } + + nconv = iconv(cd, (const char **)&inptr, &insize, &outptr, &outsize); + if(nconv == (size_t) -1) { + if (errno == EINVAL) + memmove (buf, inptr, insize); + } else + iconv(cd, NULL, NULL, &outptr, &outsize); + + *outptr = '\0'; + iconv_close(cd); + + ret = strdup(buf); + free(buf); + + return ret; +} + +#endif + diff -up a2ps-4.14/src/buffer.h.euc a2ps-4.14/src/buffer.h --- a2ps-4.14/src/buffer.h.euc 2007-12-29 02:58:35.000000000 +0100 +++ a2ps-4.14/src/buffer.h 2008-04-27 10:39:24.000000000 +0200 @@ -104,4 +104,15 @@ void buffer_sample_get PARAMS ((buffer_t void buffer_save PARAMS ((buffer_t * buffer, const char * filename)); #define buffer_is_empty(Buf) (Buf->curr >= Buf->len) + + +/** + * from jcode.h by Takuo KITAME + */ + +char *kanji_conv_auto(char *str, const char *dstset); + +const char *detect_JCode(char *str); +int int_detect_JCode(char *str); + #endif diff -up a2ps-4.14/src/Makefile.am.euc a2ps-4.14/src/Makefile.am --- a2ps-4.14/src/Makefile.am.euc 2007-12-29 02:36:09.000000000 +0100 +++ a2ps-4.14/src/Makefile.am 2008-04-27 10:39:24.000000000 +0200 @@ -33,13 +33,13 @@ DEFS = @DEFS@ -DLOCALEDIR=\"$(datadir)/l a2ps_SOURCES = main.c \ read.c sshread.c ssheet.c select.c generate.c \ delegate.c regex.c buffer.c versions.c ffaces.c \ -version-etc.c long-options.c \ +version-etc.c long-options.c jcode.c \ parsessh.y lexssh.l lexps.l sheets-map.l noinst_HEADERS = main.h \ read.h sshread.h ssheet.h select.h generate.h \ delegate.h regex.h buffer.h versions.h ffaces.h \ -version-etc.h long-options.h \ +version-etc.h long-options.h jcode.h \ yy2ssh.h lexps.h BUILT_SOURCES = parsessh.c parsessh.h