X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fmule-charset.c;h=5d216a7901b01651a2daa27e1a83ab440f3dbe6f;hb=ea1ea793fe6e244ef5555ed983423a204101af13;hp=6e4c96ddfcf7351df4ff1b7d2f4fa806011734f8;hpb=77dcef404dc78635f6ffa8f71a803d2bc7cc8921;p=chise%2Fxemacs-chise.git- diff --git a/src/mule-charset.c b/src/mule-charset.c index 6e4c96d..5d216a7 100644 --- a/src/mule-charset.c +++ b/src/mule-charset.c @@ -19,7 +19,7 @@ along with XEmacs; see the file COPYING. If not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ -/* Synched up with: Mule 2.3. Not in FSF. */ +/* Synched up with: FSF 20.3. Not in FSF. */ /* Rewritten by Ben Wing . */ @@ -32,6 +32,7 @@ Boston, MA 02111-1307, USA. */ #include "lstream.h" #include "device.h" #include "faces.h" +#include "mule-ccl.h" /* The various pre-defined charsets. */ @@ -41,23 +42,25 @@ Lisp_Object Vcharset_latin_iso8859_1; Lisp_Object Vcharset_latin_iso8859_2; Lisp_Object Vcharset_latin_iso8859_3; Lisp_Object Vcharset_latin_iso8859_4; -Lisp_Object Vcharset_cyrillic_iso8859_5; -Lisp_Object Vcharset_arabic_iso8859_6; +Lisp_Object Vcharset_thai_tis620; Lisp_Object Vcharset_greek_iso8859_7; +Lisp_Object Vcharset_arabic_iso8859_6; Lisp_Object Vcharset_hebrew_iso8859_8; -Lisp_Object Vcharset_latin_iso8859_9; -Lisp_Object Vcharset_thai_tis620; Lisp_Object Vcharset_katakana_jisx0201; Lisp_Object Vcharset_latin_jisx0201; +Lisp_Object Vcharset_cyrillic_iso8859_5; +Lisp_Object Vcharset_latin_iso8859_9; Lisp_Object Vcharset_japanese_jisx0208_1978; +Lisp_Object Vcharset_chinese_gb2312; Lisp_Object Vcharset_japanese_jisx0208; +Lisp_Object Vcharset_korean_ksc5601; Lisp_Object Vcharset_japanese_jisx0212; -Lisp_Object Vcharset_chinese_gb2312; -Lisp_Object Vcharset_chinese_big5_1; -Lisp_Object Vcharset_chinese_big5_2; Lisp_Object Vcharset_chinese_cns11643_1; Lisp_Object Vcharset_chinese_cns11643_2; -Lisp_Object Vcharset_korean_ksc5601; +Lisp_Object Vcharset_chinese_big5_1; +Lisp_Object Vcharset_chinese_big5_2; + +#ifdef ENABLE_COMPOSITE_CHARS Lisp_Object Vcharset_composite; /* Hash tables for composite chars. One maps string representing @@ -66,15 +69,23 @@ Lisp_Object Vcharset_composite; Lisp_Object Vcomposite_char_char2string_hash_table; Lisp_Object Vcomposite_char_string2char_hash_table; -/* Table of charsets indexed by leading byte. */ -Lisp_Object charset_by_leading_byte[128]; - -/* Table of charsets indexed by type/final-byte/direction. */ -Lisp_Object charset_by_attributes[4][128][2]; - static int composite_char_row_next; static int composite_char_col_next; +#endif /* ENABLE_COMPOSITE_CHARS */ + +struct charset_lookup *chlook; + +static const struct lrecord_description charset_lookup_description_1[] = { + { XD_LISP_OBJECT, offsetof(struct charset_lookup, charset_by_leading_byte), 128+4*128*2 }, + { XD_END } +}; + +static const struct struct_description charset_lookup_description = { + sizeof(struct charset_lookup), + charset_lookup_description_1 +}; + /* Table of number of bytes in the string representation of a character indexed by the first byte of that representation. @@ -107,32 +118,33 @@ Lisp_Object Qcharsetp; Lisp_Object Qregistry, Qfinal, Qgraphic; Lisp_Object Qdirection; Lisp_Object Qreverse_direction_charset; -Lisp_Object Qccl_program; - -Lisp_Object Qascii, Qcontrol_1, +Lisp_Object Qleading_byte; +Lisp_Object Qshort_name, Qlong_name; +Lisp_Object Qascii, + Qcontrol_1, Qlatin_iso8859_1, Qlatin_iso8859_2, Qlatin_iso8859_3, Qlatin_iso8859_4, - Qcyrillic_iso8859_5, - Qarabic_iso8859_6, + Qthai_tis620, Qgreek_iso8859_7, + Qarabic_iso8859_6, Qhebrew_iso8859_8, + Qkatakana_jisx0201, + Qlatin_jisx0201, + Qcyrillic_iso8859_5, Qlatin_iso8859_9, - - Qthai_tis620, - - Qkatakana_jisx0201, Qlatin_jisx0201, Qjapanese_jisx0208_1978, + Qchinese_gb2312, Qjapanese_jisx0208, + Qkorean_ksc5601, Qjapanese_jisx0212, - - Qchinese_gb2312, - Qchinese_big5_1, Qchinese_big5_2, - Qchinese_cns11643_1, Qchinese_cns11643_2, - - Qkorean_ksc5601, Qcomposite; + Qchinese_cns11643_1, + Qchinese_cns11643_2, + Qchinese_big5_1, + Qchinese_big5_2, + Qcomposite; Lisp_Object Ql2r, Qr2l; @@ -277,6 +289,7 @@ non_ascii_valid_char_p (Emchar ch) if (f2 < 0x20 || f3 < 0x20) return 0; +#ifdef ENABLE_COMPOSITE_CHARS if (f1 + FIELD1_TO_OFFICIAL_LEADING_BYTE == LEADING_BYTE_COMPOSITE) { if (UNBOUNDP (Fgethash (make_int (ch), @@ -285,6 +298,7 @@ non_ascii_valid_char_p (Emchar ch) return 0; return 1; } +#endif /* ENABLE_COMPOSITE_CHARS */ if (f2 != 0x20 && f2 != 0x7F && f3 != 0x20 && f3 != 0x7F) return 1; @@ -387,13 +401,15 @@ Lstream_funget_emchar (Lstream *stream, Emchar ch) /************************************************************************/ static Lisp_Object -mark_charset (Lisp_Object obj, void (*markobj) (Lisp_Object)) +mark_charset (Lisp_Object obj) { struct Lisp_Charset *cs = XCHARSET (obj); - markobj (cs->doc_string); - markobj (cs->registry); - markobj (cs->ccl_program); + mark_object (cs->short_name); + mark_object (cs->long_name); + mark_object (cs->doc_string); + mark_object (cs->registry); + mark_object (cs->ccl_program); return cs->name; } @@ -411,6 +427,10 @@ print_charset (Lisp_Object obj, Lisp_Object printcharfun, int escapeflag) write_c_string ("#charset_by_attributes[type][final][direction])); + chlook->charset_by_attributes[type][final][direction] = obj; } - assert (NILP (charset_by_leading_byte[leading_byte - 128])); - charset_by_leading_byte[leading_byte - 128] = obj; - if (leading_byte < 0xA0) + assert (NILP (chlook->charset_by_leading_byte[id - 128])); + chlook->charset_by_leading_byte[id - 128] = obj; + if (id < 0xA0) /* official leading byte */ - rep_bytes_by_first_byte[leading_byte] = rep_bytes; + rep_bytes_by_first_byte[id] = rep_bytes; /* Some charsets are "faux" and don't have names or really exist at all except in the leading-byte table. */ @@ -609,6 +636,8 @@ DOC-STRING is a string describing the character set. PROPS is a property list, describing the specific nature of the character set. Recognized properties are: +'short-name Short version of the charset name (ex: Latin-1) +'long-name Long version of the charset name (ex: ISO8859-1 (Latin-1)) 'registry A regular expression matching the font registry field for this character set. 'dimension Number of octets used to index a character in this charset. @@ -648,13 +677,14 @@ character set. Recognized properties are: */ (name, doc_string, props)) { - int lb, dimension = 1, chars = 94, graphic = 0, final = 0, columns = -1; + int id, dimension = 1, chars = 94, graphic = 0, final = 0, columns = -1; int direction = CHARSET_LEFT_TO_RIGHT; int type; Lisp_Object registry = Qnil; Lisp_Object charset; Lisp_Object rest, keyword, value; Lisp_Object ccl_program = Qnil; + Lisp_Object short_name = Qnil, long_name = Qnil; CHECK_SYMBOL (name); if (!NILP (doc_string)) @@ -666,7 +696,19 @@ character set. Recognized properties are: EXTERNAL_PROPERTY_LIST_LOOP (rest, keyword, value, props) { - if (EQ (keyword, Qdimension)) + if (EQ (keyword, Qshort_name)) + { + CHECK_STRING (value); + short_name = value; + } + + if (EQ (keyword, Qlong_name)) + { + CHECK_STRING (value); + long_name = value; + } + + else if (EQ (keyword, Qdimension)) { CHECK_INT (value); dimension = XINT (value); @@ -749,7 +791,7 @@ character set. Recognized properties are: error ("Character set already defined for this DIMENSION/CHARS/FINAL combo"); - lb = get_unallocated_leading_byte (dimension); + id = get_unallocated_leading_byte (dimension); if (NILP (doc_string)) doc_string = build_string (""); @@ -757,10 +799,16 @@ character set. Recognized properties are: if (NILP (registry)) registry = build_string (""); + if (NILP (short_name)) + XSETSTRING (short_name, XSYMBOL (name)->name); + + if (NILP (long_name)) + long_name = doc_string; + if (columns == -1) columns = dimension; - charset = make_charset (-1, name, lb, dimension + 2, type, columns, graphic, - final, direction, doc_string, registry); + charset = make_charset (id, name, dimension + 2, type, columns, graphic, + final, direction, short_name, long_name, doc_string, registry); if (!NILP (ccl_program)) XCHARSET_CCL_PROGRAM (charset) = ccl_program; return charset; @@ -774,9 +822,9 @@ NEW-NAME is the name of the new charset. Return the new charset. (charset, new_name)) { Lisp_Object new_charset = Qnil; - int lb, dimension, columns, graphic, final; + int id, dimension, columns, graphic, final; int direction, type; - Lisp_Object registry, doc_string; + Lisp_Object registry, doc_string, short_name, long_name; struct Lisp_Charset *cs; charset = Fget_charset (charset); @@ -793,7 +841,7 @@ NEW-NAME is the name of the new charset. Return the new charset. type = CHARSET_TYPE (cs); columns = CHARSET_COLUMNS (cs); dimension = CHARSET_DIMENSION (cs); - lb = get_unallocated_leading_byte (dimension); + id = get_unallocated_leading_byte (dimension); graphic = CHARSET_GRAPHIC (cs); final = CHARSET_FINAL (cs); @@ -801,10 +849,13 @@ NEW-NAME is the name of the new charset. Return the new charset. if (CHARSET_DIRECTION (cs) == CHARSET_RIGHT_TO_LEFT) direction = CHARSET_LEFT_TO_RIGHT; doc_string = CHARSET_DOC_STRING (cs); + short_name = CHARSET_SHORT_NAME (cs); + long_name = CHARSET_LONG_NAME (cs); registry = CHARSET_REGISTRY (cs); - new_charset = make_charset (-1, new_name, lb, dimension + 2, type, columns, - graphic, final, direction, doc_string, registry); + new_charset = make_charset (id, new_name, dimension + 2, type, columns, + graphic, final, direction, short_name, long_name, + doc_string, registry); CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset; XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset; @@ -884,8 +935,24 @@ will be returned if character sets exist for both directions). return obj; } -DEFUN ("charset-doc-string", Fcharset_doc_string, 1, 1, 0, /* -Return doc string of CHARSET. +DEFUN ("charset-short-name", Fcharset_short_name, 1, 1, 0, /* +Return short name of CHARSET. +*/ + (charset)) +{ + return XCHARSET_SHORT_NAME (Fget_charset (charset)); +} + +DEFUN ("charset-long-name", Fcharset_long_name, 1, 1, 0, /* +Return long name of CHARSET. +*/ + (charset)) +{ + return XCHARSET_LONG_NAME (Fget_charset (charset)); +} + +DEFUN ("charset-description", Fcharset_description, 1, 1, 0, /* +Return description of CHARSET. */ (charset)) { @@ -914,6 +981,8 @@ Recognized properties are those listed in `make-charset', as well as CHECK_SYMBOL (prop); if (EQ (prop, Qname)) return CHARSET_NAME (cs); + if (EQ (prop, Qshort_name)) return CHARSET_SHORT_NAME (cs); + if (EQ (prop, Qlong_name)) return CHARSET_LONG_NAME (cs); if (EQ (prop, Qdoc_string)) return CHARSET_DOC_STRING (cs); if (EQ (prop, Qdimension)) return make_int (CHARSET_DIMENSION (cs)); if (EQ (prop, Qcolumns)) return make_int (CHARSET_COLUMNS (cs)); @@ -941,7 +1010,7 @@ Return charset identification number of CHARSET. */ (charset)) { - return make_int(XCHARSET_ID (Fget_charset (charset))); + return make_int(XCHARSET_LEADING_BYTE (Fget_charset (charset))); } /* #### We need to figure out which properties we really want to @@ -992,7 +1061,10 @@ Set the 'registry property of CHARSET to REGISTRY. /************************************************************************/ DEFUN ("make-char", Fmake_char, 2, 3, 0, /* -Make a multi-byte character from CHARSET and octets ARG1 and ARG2. +Make a character from CHARSET and octets ARG1 and ARG2. +ARG2 is required only for characters from two-dimensional charsets. +For example, (make-char 'latin-iso8859-2 185) will return the Latin 2 +character s with caron. */ (charset, arg1, arg2)) { @@ -1009,7 +1081,11 @@ Make a multi-byte character from CHARSET and octets ARG1 and ARG2. else /* CHARSET_CHARS (cs) == 96) */ lowlim = 32, highlim = 127; CHECK_INT (arg1); - a1 = XINT (arg1); + /* It is useful (and safe, according to Olivier Galibert) to strip + the 8th bit off ARG1 and ARG2 becaue it allows programmers to + write (make-char 'latin-iso8859-2 CODE) where code is the actual + Latin 2 code of the character. */ + a1 = XINT (arg1) & 0x7f; if (a1 < lowlim || a1 > highlim) args_out_of_range_3 (arg1, make_int (lowlim), make_int (highlim)); @@ -1022,7 +1098,7 @@ Make a multi-byte character from CHARSET and octets ARG1 and ARG2. } CHECK_INT (arg2); - a2 = XINT (arg2); + a2 = XINT (arg2) & 0x7f; if (a2 < lowlim || a2 > highlim) args_out_of_range_3 (arg2, make_int (lowlim), make_int (highlim)); @@ -1040,30 +1116,37 @@ Return the character set of char CH. (CHAR_LEADING_BYTE (XCHAR (ch)))); } -DEFUN ("char-octet", Fchar_octet, 1, 2, 0, /* -Return the octet numbered N (should be 0 or 1) of char CH. -N defaults to 0 if omitted. +DEFUN ("split-char", Fsplit_char, 1, 1, 0, /* +Return list of charset and one or two position-codes of CHAR. */ - (ch, n)) + (character)) { - Lisp_Object charset; - int c1, c2, int_n; + /* This function can GC */ + struct gcpro gcpro1, gcpro2; + Lisp_Object charset = Qnil; + Lisp_Object rc = Qnil; + int c1, c2; - CHECK_CHAR_COERCE_INT (ch); - if (NILP (n)) - int_n = 0; + GCPRO2 (charset, rc); + CHECK_CHAR_COERCE_INT (character); + + BREAKUP_CHAR (XCHAR (character), charset, c1, c2); + + if (XCHARSET_DIMENSION (Fget_charset (charset)) == 2) + { + rc = list3 (XCHARSET_NAME (charset), make_int (c1), make_int (c2)); + } else { - CHECK_INT (n); - int_n = XINT (n); - if (int_n != 0 && int_n != 1) - signal_simple_error ("Octet number must be 0 or 1", n); + rc = list2 (XCHARSET_NAME (charset), make_int (c1)); } - BREAKUP_CHAR (XCHAR (ch), charset, c1, c2); - return make_int (int_n == 0 ? c1 : c2); + UNGCPRO; + + return rc; } +#ifdef ENABLE_COMPOSITE_CHARS /************************************************************************/ /* composite character functions */ /************************************************************************/ @@ -1109,7 +1192,7 @@ composite_char_string (Emchar ch) return str; } -DEFUN ("make-composite-char", Fmake_composite_char, 1, 1, 0, /* +xxDEFUN ("make-composite-char", Fmake_composite_char, 1, 1, 0, /* Convert a string into a single composite character. The character is the result of overstriking all the characters in the string. @@ -1121,7 +1204,7 @@ the string. XSTRING_LENGTH (string))); } -DEFUN ("composite-char-string", Fcomposite_char_string, 1, 1, 0, /* +xxDEFUN ("composite-char-string", Fcomposite_char_string, 1, 1, 0, /* Return a string of the characters comprising a composite character. */ (ch)) @@ -1134,6 +1217,7 @@ Return a string of the characters comprising a composite character. signal_simple_error ("Must be composite char", ch); return composite_char_string (emch); } +#endif /* ENABLE_COMPOSITE_CHARS */ /************************************************************************/ @@ -1152,7 +1236,9 @@ syms_of_mule_charset (void) DEFSUBR (Fmake_reverse_direction_charset); /* DEFSUBR (Freverse_direction_charset); */ DEFSUBR (Fcharset_from_attributes); - DEFSUBR (Fcharset_doc_string); + DEFSUBR (Fcharset_short_name); + DEFSUBR (Fcharset_long_name); + DEFSUBR (Fcharset_description); DEFSUBR (Fcharset_dimension); DEFSUBR (Fcharset_property); DEFSUBR (Fcharset_id); @@ -1161,10 +1247,12 @@ syms_of_mule_charset (void) DEFSUBR (Fmake_char); DEFSUBR (Fchar_charset); - DEFSUBR (Fchar_octet); + DEFSUBR (Fsplit_char); +#ifdef ENABLE_COMPOSITE_CHARS DEFSUBR (Fmake_composite_char); DEFSUBR (Fcomposite_char_string); +#endif defsymbol (&Qcharsetp, "charsetp"); defsymbol (&Qregistry, "registry"); @@ -1172,12 +1260,13 @@ syms_of_mule_charset (void) defsymbol (&Qgraphic, "graphic"); defsymbol (&Qdirection, "direction"); defsymbol (&Qreverse_direction_charset, "reverse-direction-charset"); - defsymbol (&Qccl_program, "ccl-program"); + defsymbol (&Qshort_name, "short-name"); + defsymbol (&Qlong_name, "long-name"); defsymbol (&Ql2r, "l2r"); defsymbol (&Qr2l, "r2l"); - /* Charsets, compatible with Emacs/Mule 19.33-delta + /* Charsets, compatible with FSF 20.3 Naming convention is Script-Charset[-Edition] */ defsymbol (&Qascii, "ascii"); defsymbol (&Qcontrol_1, "control-1"); @@ -1185,26 +1274,24 @@ syms_of_mule_charset (void) defsymbol (&Qlatin_iso8859_2, "latin-iso8859-2"); defsymbol (&Qlatin_iso8859_3, "latin-iso8859-3"); defsymbol (&Qlatin_iso8859_4, "latin-iso8859-4"); - defsymbol (&Qcyrillic_iso8859_5, "cyrillic-iso8859-5"); - defsymbol (&Qarabic_iso8859_6, "arabic-iso8859-6"); + defsymbol (&Qthai_tis620, "thai-tis620"); defsymbol (&Qgreek_iso8859_7, "greek-iso8859-7"); + defsymbol (&Qarabic_iso8859_6, "arabic-iso8859-6"); defsymbol (&Qhebrew_iso8859_8, "hebrew-iso8859-8"); - defsymbol (&Qlatin_iso8859_9, "latin-iso8859-9"); - defsymbol (&Qthai_tis620, "thai-tis620"); - defsymbol (&Qkatakana_jisx0201, "katakana-jisx0201"); defsymbol (&Qlatin_jisx0201, "latin-jisx0201"); + defsymbol (&Qcyrillic_iso8859_5, "cyrillic-iso8859-5"); + defsymbol (&Qlatin_iso8859_9, "latin-iso8859-9"); defsymbol (&Qjapanese_jisx0208_1978, "japanese-jisx0208-1978"); + defsymbol (&Qchinese_gb2312, "chinese-gb2312"); defsymbol (&Qjapanese_jisx0208, "japanese-jisx0208"); + defsymbol (&Qkorean_ksc5601, "korean-ksc5601"); defsymbol (&Qjapanese_jisx0212, "japanese-jisx0212"); - - defsymbol (&Qchinese_gb2312, "chinese-gb2312"); - defsymbol (&Qchinese_big5_1, "chinese-big5-1"); - defsymbol (&Qchinese_big5_2, "chinese-big5-2"); defsymbol (&Qchinese_cns11643_1, "chinese-cns11643-1"); defsymbol (&Qchinese_cns11643_2, "chinese-cns11643-2"); + defsymbol (&Qchinese_big5_1, "chinese-big5-1"); + defsymbol (&Qchinese_big5_2, "chinese-big5-2"); - defsymbol (&Qkorean_ksc5601, "korean-ksc5601"); defsymbol (&Qcomposite, "composite"); } @@ -1213,15 +1300,18 @@ vars_of_mule_charset (void) { int i, j, k; + chlook = xnew (struct charset_lookup); + dumpstruct (&chlook, &charset_lookup_description); + /* Table of charsets indexed by leading byte. */ - for (i = 0; i < countof (charset_by_leading_byte); i++) - charset_by_leading_byte[i] = Qnil; + for (i = 0; i < countof (chlook->charset_by_leading_byte); i++) + chlook->charset_by_leading_byte[i] = Qnil; /* Table of charsets indexed by type/final-byte/direction. */ - for (i = 0; i < countof (charset_by_attributes); i++) - for (j = 0; j < countof (charset_by_attributes[0]); j++) - for (k = 0; k < countof (charset_by_attributes[0][0]); k++) - charset_by_attributes[i][j][k] = Qnil; + for (i = 0; i < countof (chlook->charset_by_attributes); i++) + for (j = 0; j < countof (chlook->charset_by_attributes[0]); j++) + for (k = 0; k < countof (chlook->charset_by_attributes[0][0]); k++) + chlook->charset_by_attributes[i][j][k] = Qnil; next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1; next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2; @@ -1237,172 +1327,237 @@ complex_vars_of_mule_charset (void) /* Predefined character sets. We store them into variables for ease of access. */ + staticpro (&Vcharset_ascii); Vcharset_ascii = - make_charset (0, Qascii, LEADING_BYTE_ASCII, 1, + make_charset (LEADING_BYTE_ASCII, Qascii, 1, CHARSET_TYPE_94, 1, 0, 'B', CHARSET_LEFT_TO_RIGHT, - build_string ("ASCII (ISO 646 IRV)"), - build_string ("iso8859-1")); + build_string ("ASCII"), + build_string ("ASCII)"), + build_string ("ASCII (ISO646 IRV)"), + build_string ("\\(iso8859-[0-9]*\\|-ascii\\)")); + staticpro (&Vcharset_control_1); Vcharset_control_1 = - make_charset (-1, Qcontrol_1, LEADING_BYTE_CONTROL_1, 2, + make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2, CHARSET_TYPE_94, 1, 1, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("C1"), build_string ("Control characters"), + build_string ("Control characters 128-191"), build_string ("")); + staticpro (&Vcharset_latin_iso8859_1); Vcharset_latin_iso8859_1 = - make_charset (129, Qlatin_iso8859_1, LEADING_BYTE_LATIN_ISO8859_1, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2, CHARSET_TYPE_96, 1, 1, 'A', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-1 (Latin-1)"), + build_string ("Latin-1"), + build_string ("ISO8859-1 (Latin-1)"), + build_string ("ISO8859-1 (Latin-1)"), build_string ("iso8859-1")); + staticpro (&Vcharset_latin_iso8859_2); Vcharset_latin_iso8859_2 = - make_charset (130, Qlatin_iso8859_2, LEADING_BYTE_LATIN_ISO8859_2, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2, CHARSET_TYPE_96, 1, 1, 'B', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-2 (Latin-2)"), + build_string ("Latin-2"), + build_string ("ISO8859-2 (Latin-2)"), + build_string ("ISO8859-2 (Latin-2)"), build_string ("iso8859-2")); + staticpro (&Vcharset_latin_iso8859_3); Vcharset_latin_iso8859_3 = - make_charset (131, Qlatin_iso8859_3, LEADING_BYTE_LATIN_ISO8859_3, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2, CHARSET_TYPE_96, 1, 1, 'C', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-3 (Latin-3)"), + build_string ("Latin-3"), + build_string ("ISO8859-3 (Latin-3)"), + build_string ("ISO8859-3 (Latin-3)"), build_string ("iso8859-3")); + staticpro (&Vcharset_latin_iso8859_4); Vcharset_latin_iso8859_4 = - make_charset (132, Qlatin_iso8859_4, LEADING_BYTE_LATIN_ISO8859_4, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2, CHARSET_TYPE_96, 1, 1, 'D', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-4 (Latin-4)"), + build_string ("Latin-4"), + build_string ("ISO8859-4 (Latin-4)"), + build_string ("ISO8859-4 (Latin-4)"), build_string ("iso8859-4")); - Vcharset_cyrillic_iso8859_5 = - make_charset (140, Qcyrillic_iso8859_5, LEADING_BYTE_CYRILLIC_ISO8859_5, 2, - CHARSET_TYPE_96, 1, 1, 'L', + staticpro (&Vcharset_thai_tis620); + Vcharset_thai_tis620 = + make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2, + CHARSET_TYPE_96, 1, 1, 'T', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-5 (Cyrillic)"), - build_string ("iso8859-5")); - Vcharset_arabic_iso8859_6 = - make_charset (135, Qarabic_iso8859_6, LEADING_BYTE_ARABIC_ISO8859_6, 2, - CHARSET_TYPE_96, 1, 1, 'G', - CHARSET_RIGHT_TO_LEFT, - build_string ("ISO 8859-6 (Arabic)"), - build_string ("iso8859-6")); + build_string ("TIS620"), + build_string ("TIS620 (Thai)"), + build_string ("TIS620.2529 (Thai)"), + build_string ("tis620")); + staticpro (&Vcharset_greek_iso8859_7); Vcharset_greek_iso8859_7 = - make_charset (134, Qgreek_iso8859_7, LEADING_BYTE_GREEK_ISO8859_7, 2, + make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2, CHARSET_TYPE_96, 1, 1, 'F', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-7 (Greek)"), + build_string ("ISO8859-7"), + build_string ("ISO8859-7 (Greek)"), + build_string ("ISO8859-7 (Greek)"), build_string ("iso8859-7")); + staticpro (&Vcharset_arabic_iso8859_6); + Vcharset_arabic_iso8859_6 = + make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 2, + CHARSET_TYPE_96, 1, 1, 'G', + CHARSET_RIGHT_TO_LEFT, + build_string ("ISO8859-6"), + build_string ("ISO8859-6 (Arabic)"), + build_string ("ISO8859-6 (Arabic)"), + build_string ("iso8859-6")); + staticpro (&Vcharset_hebrew_iso8859_8); Vcharset_hebrew_iso8859_8 = - make_charset (136, Qhebrew_iso8859_8, LEADING_BYTE_HEBREW_ISO8859_8, 2, + make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2, CHARSET_TYPE_96, 1, 1, 'H', CHARSET_RIGHT_TO_LEFT, - build_string ("ISO 8859-8 (Hebrew)"), + build_string ("ISO8859-8"), + build_string ("ISO8859-8 (Hebrew)"), + build_string ("ISO8859-8 (Hebrew)"), build_string ("iso8859-8")); - Vcharset_latin_iso8859_9 = - make_charset (141, Qlatin_iso8859_9, LEADING_BYTE_LATIN_ISO8859_9, 2, - CHARSET_TYPE_96, 1, 1, 'M', - CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-9 (Latin-5)"), - build_string ("iso8859-9")); - Vcharset_thai_tis620 = - make_charset (133, Qthai_tis620, LEADING_BYTE_THAI_TIS620, 2, - CHARSET_TYPE_96, 1, 1, 'T', - CHARSET_LEFT_TO_RIGHT, - build_string ("TIS 620.2529 (Thai)"), - build_string ("tis620")); - - /* Japanese */ + staticpro (&Vcharset_katakana_jisx0201); Vcharset_katakana_jisx0201 = - make_charset (137, Qkatakana_jisx0201, - LEADING_BYTE_KATAKANA_JISX0201, 2, + make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2, CHARSET_TYPE_94, 1, 1, 'I', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0201-Katakana"), + build_string ("JISX0201 Kana"), + build_string ("JISX0201.1976 (Japanese Kana)"), + build_string ("JISX0201.1976 Japanese Kana"), build_string ("jisx0201.1976")); + staticpro (&Vcharset_latin_jisx0201); Vcharset_latin_jisx0201 = - make_charset (138, Qlatin_jisx0201, - LEADING_BYTE_LATIN_JISX0201, 2, + make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2, CHARSET_TYPE_94, 1, 0, 'J', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0201-Latin"), + build_string ("JISX0201 Roman"), + build_string ("JISX0201.1976 (Japanese Roman)"), + build_string ("JISX0201.1976 Japanese Roman"), build_string ("jisx0201.1976")); + staticpro (&Vcharset_cyrillic_iso8859_5); + Vcharset_cyrillic_iso8859_5 = + make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2, + CHARSET_TYPE_96, 1, 1, 'L', + CHARSET_LEFT_TO_RIGHT, + build_string ("ISO8859-5"), + build_string ("ISO8859-5 (Cyrillic)"), + build_string ("ISO8859-5 (Cyrillic)"), + build_string ("iso8859-5")); + staticpro (&Vcharset_latin_iso8859_9); + Vcharset_latin_iso8859_9 = + make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2, + CHARSET_TYPE_96, 1, 1, 'M', + CHARSET_LEFT_TO_RIGHT, + build_string ("Latin-5"), + build_string ("ISO8859-9 (Latin-5)"), + build_string ("ISO8859-9 (Latin-5)"), + build_string ("iso8859-9")); + staticpro (&Vcharset_japanese_jisx0208_1978); Vcharset_japanese_jisx0208_1978 = - make_charset (144, Qjapanese_jisx0208_1978, - LEADING_BYTE_JAPANESE_JISX0208_1978, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3, CHARSET_TYPE_94X94, 2, 0, '@', CHARSET_LEFT_TO_RIGHT, + build_string ("JISX0208.1978"), + build_string ("JISX0208.1978 (Japanese)"), build_string - ("JIS X0208-1978 (Japanese Kanji; Old Version)"), - build_string ("\\(jisx0208\\|jisc6226\\).19")); + ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"), + build_string ("\\(jisx0208\\|jisc6226\\)\\.1978")); + staticpro (&Vcharset_chinese_gb2312); + Vcharset_chinese_gb2312 = + make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3, + CHARSET_TYPE_94X94, 2, 0, 'A', + CHARSET_LEFT_TO_RIGHT, + build_string ("GB2312"), + build_string ("GB2312)"), + build_string ("GB2312 Chinese simplified"), + build_string ("gb2312")); + staticpro (&Vcharset_japanese_jisx0208); Vcharset_japanese_jisx0208 = - make_charset (146, Qjapanese_jisx0208, - LEADING_BYTE_JAPANESE_JISX0208, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3, CHARSET_TYPE_94X94, 2, 0, 'B', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0208-1983 (Japanese Kanji)"), + build_string ("JISX0208"), + build_string ("JISX0208.1983/1990 (Japanese)"), + build_string ("JISX0208.1983/1990 Japanese Kanji"), build_string ("jisx0208.19\\(83\\|90\\)")); + staticpro (&Vcharset_korean_ksc5601); + Vcharset_korean_ksc5601 = + make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3, + CHARSET_TYPE_94X94, 2, 0, 'C', + CHARSET_LEFT_TO_RIGHT, + build_string ("KSC5601"), + build_string ("KSC5601 (Korean"), + build_string ("KSC5601 Korean Hangul and Hanja"), + build_string ("ksc5601")); + staticpro (&Vcharset_japanese_jisx0212); Vcharset_japanese_jisx0212 = - make_charset (148, Qjapanese_jisx0212, - LEADING_BYTE_JAPANESE_JISX0212, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3, CHARSET_TYPE_94X94, 2, 0, 'D', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0212 (Japanese Supplement)"), + build_string ("JISX0212"), + build_string ("JISX0212 (Japanese)"), + build_string ("JISX0212 Japanese Supplement"), build_string ("jisx0212")); - /* Chinese */ - Vcharset_chinese_gb2312 = - make_charset (145, Qchinese_gb2312, LEADING_BYTE_CHINESE_GB2312, 3, - CHARSET_TYPE_94X94, 2, 0, 'A', - CHARSET_LEFT_TO_RIGHT, - build_string ("GB 2312 (Simplified Chinese)"), - build_string ("gb2312")); #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$" + staticpro (&Vcharset_chinese_cns11643_1); Vcharset_chinese_cns11643_1 = - make_charset (149, Qchinese_cns11643_1, - LEADING_BYTE_CHINESE_CNS11643_1, 3, + make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 3, CHARSET_TYPE_94X94, 2, 0, 'G', CHARSET_LEFT_TO_RIGHT, + build_string ("CNS11643-1"), + build_string ("CNS11643-1 (Chinese traditional)"), build_string - ("CNS 11643 Plane 1 (Traditional Chinese for daily use)"), + ("CNS 11643 Plane 1 Chinese traditional"), build_string (CHINESE_CNS_PLANE_RE("1"))); + staticpro (&Vcharset_chinese_cns11643_2); Vcharset_chinese_cns11643_2 = - make_charset (150, Qchinese_cns11643_2, - LEADING_BYTE_CHINESE_CNS11643_2, 3, + make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3, CHARSET_TYPE_94X94, 2, 0, 'H', CHARSET_LEFT_TO_RIGHT, + build_string ("CNS11643-2"), + build_string ("CNS11643-2 (Chinese traditional)"), build_string - ("CNS 11643 Plane 2 (Traditional Chinese for daily use)"), + ("CNS 11643 Plane 2 Chinese traditional"), build_string (CHINESE_CNS_PLANE_RE("2"))); + staticpro (&Vcharset_chinese_big5_1); Vcharset_chinese_big5_1 = - make_charset (152, Qchinese_big5_1, LEADING_BYTE_CHINESE_BIG5_1, 3, + make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3, CHARSET_TYPE_94X94, 2, 0, '0', CHARSET_LEFT_TO_RIGHT, + build_string ("Big5"), + build_string ("Big5 (Level-1)"), build_string - ("Big5 Level 1 (Traditional Chinese for daily use)"), + ("Big5 Level-1 Chinese traditional"), build_string ("big5")); + staticpro (&Vcharset_chinese_big5_2); Vcharset_chinese_big5_2 = - make_charset (153, Qchinese_big5_2, LEADING_BYTE_CHINESE_BIG5_2, 3, + make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3, CHARSET_TYPE_94X94, 2, 0, '1', CHARSET_LEFT_TO_RIGHT, + build_string ("Big5"), + build_string ("Big5 (Level-2)"), build_string - ("Big5 Level 2 (Traditional Chinese for daily use)"), + ("Big5 Level-2 Chinese traditional"), build_string ("big5")); - Vcharset_korean_ksc5601 = - make_charset (147, Qkorean_ksc5601, LEADING_BYTE_KOREAN_KSC5601, 3, - CHARSET_TYPE_94X94, 2, 0, 'C', - CHARSET_LEFT_TO_RIGHT, - build_string ("KS C5601 (Hangul and Korean Hanja)"), - build_string ("ksc5601")); + +#ifdef ENABLE_COMPOSITE_CHARS /* #### For simplicity, we put composite chars into a 96x96 charset. This is going to lead to problems because you can run out of room, esp. as we don't yet recycle numbers. */ + staticpro (&Vcharset_composite); Vcharset_composite = - make_charset (-1, Qcomposite, LEADING_BYTE_COMPOSITE, 3, + make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, 3, CHARSET_TYPE_96X96, 2, 0, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("Composite"), + build_string ("Composite characters"), build_string ("Composite characters"), build_string ("")); + /* #### not dumped properly */ composite_char_row_next = 32; composite_char_col_next = 32; @@ -1412,5 +1567,6 @@ complex_vars_of_mule_charset (void) make_lisp_hash_table (500, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ); staticpro (&Vcomposite_char_string2char_hash_table); staticpro (&Vcomposite_char_char2string_hash_table); +#endif /* ENABLE_COMPOSITE_CHARS */ }