X-Git-Url: http://git.chise.org/gitweb/?p=chise%2Fxemacs-chise.git.1;a=blobdiff_plain;f=src%2Fmule-charset.c;h=c54162853b7f9cc07194751bd2ea52d13d827ae0;hp=eb866108719cd8b90ef167573fc65298e6fb824b;hb=ee38d21b330f5001b47a577cefb5ba7b82a3b7d3;hpb=2e3e3f9ee27fec50f45c282d71eaddf7c673bc56 diff --git a/src/mule-charset.c b/src/mule-charset.c index eb86610..c541628 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. */ @@ -41,49 +42,59 @@ 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; -/* Hashtables for composite chars. One maps string representing +/* Hash tables for composite chars. One maps string representing composed chars to their equivalent chars; one goes the other way. */ -Lisp_Object Vcomposite_char_char2string_hashtable; -Lisp_Object Vcomposite_char_string2char_hashtable; - -/* 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]; +Lisp_Object Vcomposite_char_char2string_hash_table; +Lisp_Object Vcomposite_char_string2char_hash_table; 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_ARRAY, 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. rep_bytes_by_first_byte(c) is more efficient than the equivalent canonical computation: - (BYTE_ASCII_P (c) ? 1 : XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (c))) */ + XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (c)) */ -Bytecount rep_bytes_by_first_byte[0xA0] = +const Bytecount rep_bytes_by_first_byte[0xA0] = { /* 0x00 - 0x7f are for straight ASCII */ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, @@ -107,39 +118,37 @@ 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; -Lisp_Object Vcharset_hashtable; - -static Bufbyte next_allocated_1_byte_leading_byte; -static Bufbyte next_allocated_2_byte_leading_byte; +Lisp_Object Vcharset_hash_table; /* Composite characters are characters constructed by overstriking two or more regular characters. @@ -208,7 +217,7 @@ non_ascii_set_charptr_emchar (Bufbyte *str, Emchar c) Use the macro charptr_emchar() instead. */ Emchar -non_ascii_charptr_emchar (CONST Bufbyte *str) +non_ascii_charptr_emchar (const Bufbyte *str) { Bufbyte i0 = *str, i1, i2 = 0; Lisp_Object charset; @@ -255,7 +264,8 @@ non_ascii_valid_char_p (Emchar ch) if (f3 < 0x20) return 0; - if (f3 != 0x20 && f3 != 0x7F) + if (f3 != 0x20 && f3 != 0x7F && !(f2 >= MIN_CHAR_FIELD2_PRIVATE && + f2 <= MAX_CHAR_FIELD2_PRIVATE)) return 1; /* @@ -264,6 +274,8 @@ non_ascii_valid_char_p (Emchar ch) FIELD2_TO_PRIVATE_LEADING_BYTE are the same. */ charset = CHARSET_BY_LEADING_BYTE (f2 + FIELD2_TO_OFFICIAL_LEADING_BYTE); + if (EQ (charset, Qnil)) + return 0; return (XCHARSET_CHARS (charset) == 96); } else @@ -277,16 +289,19 @@ 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), - Vcomposite_char_char2string_hashtable, + Vcomposite_char_char2string_hash_table, Qunbound))) return 0; return 1; } +#endif /* ENABLE_COMPOSITE_CHARS */ - if (f2 != 0x20 && f2 != 0x7F && f3 != 0x20 && f3 != 0x7F) + if (f2 != 0x20 && f2 != 0x7F && f3 != 0x20 && f3 != 0x7F + && !(f1 >= MIN_CHAR_FIELD1_PRIVATE && f1 <= MAX_CHAR_FIELD1_PRIVATE)) return 1; if (f1 <= MAX_CHAR_FIELD1_OFFICIAL) @@ -296,6 +311,8 @@ non_ascii_valid_char_p (Emchar ch) charset = CHARSET_BY_LEADING_BYTE (f1 + FIELD1_TO_PRIVATE_LEADING_BYTE); + if (EQ (charset, Qnil)) + return 0; return (XCHARSET_CHARS (charset) == 96); } } @@ -305,26 +322,18 @@ non_ascii_valid_char_p (Emchar ch) /* Basic string functions */ /************************************************************************/ -/* Copy the character pointed to by PTR into STR, assuming it's - non-ASCII. Do not call this directly. Use the macro - charptr_copy_char() instead. */ +/* Copy the character pointed to by SRC into DST. Do not call this + directly. Use the macro charptr_copy_char() instead. + Return the number of bytes copied. */ Bytecount -non_ascii_charptr_copy_char (CONST Bufbyte *ptr, Bufbyte *str) +non_ascii_charptr_copy_char (const Bufbyte *src, Bufbyte *dst) { - Bufbyte *strptr = str; - *strptr = *ptr++; - switch (REP_BYTES_BY_FIRST_BYTE (*strptr)) - { - /* Notice fallthrough. */ - case 4: *++strptr = *ptr++; - case 3: *++strptr = *ptr++; - case 2: *++strptr = *ptr; - break; - default: - abort (); - } - return strptr + 1 - str; + unsigned int bytes = REP_BYTES_BY_FIRST_BYTE (*src); + unsigned int i; + for (i = bytes; i; i--, dst++, src++) + *dst = *src; + return bytes; } @@ -341,26 +350,15 @@ Lstream_get_emchar_1 (Lstream *stream, int ch) { Bufbyte str[MAX_EMCHAR_LEN]; Bufbyte *strptr = str; + unsigned int bytes; str[0] = (Bufbyte) ch; - switch (REP_BYTES_BY_FIRST_BYTE (ch)) + + for (bytes = REP_BYTES_BY_FIRST_BYTE (ch) - 1; bytes; bytes--) { - /* Notice fallthrough. */ - case 4: - ch = Lstream_getc (stream); - assert (ch >= 0); - *++strptr = (Bufbyte) ch; - case 3: - ch = Lstream_getc (stream); - assert (ch >= 0); - *++strptr = (Bufbyte) ch; - case 2: - ch = Lstream_getc (stream); - assert (ch >= 0); - *++strptr = (Bufbyte) ch; - break; - default: - abort (); + int c = Lstream_getc (stream); + bufpos_checking_assert (c >= 0); + *++strptr = (Bufbyte) c; } return charptr_emchar (str); } @@ -387,20 +385,22 @@ 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); + 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; } static void print_charset (Lisp_Object obj, Lisp_Object printcharfun, int escapeflag) { - struct Lisp_Charset *cs = XCHARSET (obj); + Lisp_Charset *cs = XCHARSET (obj); char buf[200]; if (print_readably) @@ -411,6 +411,10 @@ 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) - /* official leading byte */ - rep_bytes_by_first_byte[leading_byte] = rep_bytes; + assert (NILP (chlook->charset_by_leading_byte[id - 128])); + chlook->charset_by_leading_byte[id - 128] = obj; /* Some charsets are "faux" and don't have names or really exist at all except in the leading-byte table. */ if (!NILP (name)) - Fputhash (name, obj, Vcharset_hashtable); + Fputhash (name, obj, Vcharset_hash_table); return obj; } @@ -491,17 +508,24 @@ get_unallocated_leading_byte (int dimension) if (dimension == 1) { - if (next_allocated_1_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_1) + if (chlook->next_allocated_1_byte_leading_byte > + MAX_LEADING_BYTE_PRIVATE_1) lb = 0; else - lb = next_allocated_1_byte_leading_byte++; + lb = chlook->next_allocated_1_byte_leading_byte++; } else { - if (next_allocated_2_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_2) - lb = 0; + /* awfully fragile, but correct */ +#if MAX_LEADING_BYTE_PRIVATE_2 == 255 + if (chlook->next_allocated_2_byte_leading_byte == 0) +#else + if (chlook->next_allocated_2_byte_leading_byte > + MAX_LEADING_BYTE_PRIVATE_2) +#endif + lb = 0; else - lb = next_allocated_2_byte_leading_byte++; + lb = chlook->next_allocated_2_byte_leading_byte++; } if (!lb) @@ -537,7 +561,7 @@ nil is returned. Otherwise the associated charset object is returned. return charset_or_name; CHECK_SYMBOL (charset_or_name); - return Fgethash (charset_or_name, Vcharset_hashtable, Qnil); + return Fgethash (charset_or_name, Vcharset_hash_table, Qnil); } DEFUN ("get-charset", Fget_charset, 1, 1, 0, /* @@ -563,19 +587,15 @@ struct charset_list_closure }; static int -add_charset_to_list_mapper (CONST void *hash_key, void *hash_contents, +add_charset_to_list_mapper (Lisp_Object key, Lisp_Object value, void *charset_list_closure) { /* This function can GC */ - Lisp_Object key, contents; - Lisp_Object *charset_list; struct charset_list_closure *chcl = (struct charset_list_closure*) charset_list_closure; - CVOID_TO_LISP (key, hash_key); - VOID_TO_LISP (contents, hash_contents); - charset_list = chcl->charset_list; + Lisp_Object *charset_list = chcl->charset_list; - *charset_list = Fcons (XCHARSET_NAME (contents), *charset_list); + *charset_list = Fcons (XCHARSET_NAME (value), *charset_list); return 0; } @@ -590,7 +610,7 @@ Return a list of the names of all defined charsets. GCPRO1 (charset_list); charset_list_closure.charset_list = &charset_list; - elisp_maphash (add_charset_to_list_mapper, Vcharset_hashtable, + elisp_maphash (add_charset_to_list_mapper, Vcharset_hash_table, &charset_list_closure); UNGCPRO; @@ -598,13 +618,14 @@ Return a list of the names of all defined charsets. } DEFUN ("charset-name", Fcharset_name, 1, 1, 0, /* -Return the name of the given charset. +Return the name of charset CHARSET. */ (charset)) { return XCHARSET_NAME (Fget_charset (charset)); } +/* #### SJT Should generic properties be allowed? */ DEFUN ("make-charset", Fmake_charset, 3, 3, 0, /* Define a new character set. This function is for use with Mule support. @@ -613,6 +634,8 @@ 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. @@ -652,13 +675,13 @@ 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)) @@ -668,73 +691,90 @@ character set. Recognized properties are: if (!NILP (charset)) signal_simple_error ("Cannot redefine existing charset", name); - EXTERNAL_PROPERTY_LIST_LOOP (rest, keyword, value, props) - { - if (EQ (keyword, Qdimension)) - { - CHECK_INT (value); - dimension = XINT (value); - if (dimension < 1 || dimension > 2) - signal_simple_error ("Invalid value for 'dimension", value); - } - - else if (EQ (keyword, Qchars)) - { - CHECK_INT (value); - chars = XINT (value); - if (chars != 94 && chars != 96) - signal_simple_error ("Invalid value for 'chars", value); - } - - else if (EQ (keyword, Qcolumns)) - { - CHECK_INT (value); - columns = XINT (value); - if (columns != 1 && columns != 2) - signal_simple_error ("Invalid value for 'columns", value); - } - - else if (EQ (keyword, Qgraphic)) - { - CHECK_INT (value); - graphic = XINT (value); - if (graphic < 0 || graphic > 1) - signal_simple_error ("Invalid value for 'graphic", value); - } - - else if (EQ (keyword, Qregistry)) - { - CHECK_STRING (value); - registry = value; - } - - else if (EQ (keyword, Qdirection)) - { - if (EQ (value, Ql2r)) - direction = CHARSET_LEFT_TO_RIGHT; - else if (EQ (value, Qr2l)) - direction = CHARSET_RIGHT_TO_LEFT; - else - signal_simple_error ("Invalid value for 'direction", value); - } - - else if (EQ (keyword, Qfinal)) - { - CHECK_CHAR_COERCE_INT (value); - final = XCHAR (value); - if (final < '0' || final > '~') - signal_simple_error ("Invalid value for 'final", value); - } - - else if (EQ (keyword, Qccl_program)) - { - CHECK_VECTOR (value); - ccl_program = value; - } - - else - signal_simple_error ("Unrecognized property", keyword); - } + { + EXTERNAL_PROPERTY_LIST_LOOP_3 (keyword, value, props) + { + if (EQ (keyword, Qshort_name)) + { + CHECK_STRING (value); + short_name = value; + } + + else if (EQ (keyword, Qlong_name)) + { + CHECK_STRING (value); + long_name = value; + } + + else if (EQ (keyword, Qdimension)) + { + CHECK_INT (value); + dimension = XINT (value); + if (dimension < 1 || dimension > 2) + signal_simple_error ("Invalid value for 'dimension", value); + } + + else if (EQ (keyword, Qchars)) + { + CHECK_INT (value); + chars = XINT (value); + if (chars != 94 && chars != 96) + signal_simple_error ("Invalid value for 'chars", value); + } + + else if (EQ (keyword, Qcolumns)) + { + CHECK_INT (value); + columns = XINT (value); + if (columns != 1 && columns != 2) + signal_simple_error ("Invalid value for 'columns", value); + } + + else if (EQ (keyword, Qgraphic)) + { + CHECK_INT (value); + graphic = XINT (value); + if (graphic < 0 || graphic > 1) + signal_simple_error ("Invalid value for 'graphic", value); + } + + else if (EQ (keyword, Qregistry)) + { + CHECK_STRING (value); + registry = value; + } + + else if (EQ (keyword, Qdirection)) + { + if (EQ (value, Ql2r)) + direction = CHARSET_LEFT_TO_RIGHT; + else if (EQ (value, Qr2l)) + direction = CHARSET_RIGHT_TO_LEFT; + else + signal_simple_error ("Invalid value for 'direction", value); + } + + else if (EQ (keyword, Qfinal)) + { + CHECK_CHAR_COERCE_INT (value); + final = XCHAR (value); + if (final < '0' || final > '~') + signal_simple_error ("Invalid value for 'final", value); + } + + else if (EQ (keyword, Qccl_program)) + { + struct ccl_program test_ccl; + + if (setup_ccl_program (&test_ccl, value) < 0) + signal_simple_error ("Invalid value for 'ccl-program", value); + ccl_program = value; + } + + else + signal_simple_error ("Unrecognized property", keyword); + } + } if (!final) error ("'final must be specified"); @@ -753,7 +793,7 @@ 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 (""); @@ -761,10 +801,16 @@ 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; @@ -778,10 +824,10 @@ 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; - struct Lisp_Charset *cs; + Lisp_Object registry, doc_string, short_name, long_name; + Lisp_Charset *cs; charset = Fget_charset (charset); if (!NILP (XCHARSET_REVERSE_DIRECTION_CHARSET (charset))) @@ -797,7 +843,7 @@ 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); @@ -805,10 +851,13 @@ 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; @@ -888,8 +937,24 @@ 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)) { @@ -905,19 +970,21 @@ Return dimension of CHARSET. } DEFUN ("charset-property", Fcharset_property, 2, 2, 0, /* -Return property PROP of CHARSET. +Return property PROP of CHARSET, a charset object or symbol naming a charset. Recognized properties are those listed in `make-charset', as well as 'name and 'doc-string. */ (charset, prop)) { - struct Lisp_Charset *cs; + Lisp_Charset *cs; charset = Fget_charset (charset); cs = XCHARSET (charset); 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)); @@ -931,10 +998,8 @@ Recognized properties are those listed in `make-charset', as well as if (EQ (prop, Qreverse_direction_charset)) { Lisp_Object obj = CHARSET_REVERSE_DIRECTION_CHARSET (cs); - if (NILP (obj)) - return Qnil; - else - return XCHARSET_NAME (obj); + /* #### Is this translation OK? If so, error checking sufficient? */ + return CHARSETP (obj) ? XCHARSET_NAME (obj) : obj; } signal_simple_error ("Unrecognized charset property name", prop); return Qnil; /* not reached */ @@ -945,7 +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 @@ -956,8 +1021,11 @@ Set the 'ccl-program property of CHARSET to CCL-PROGRAM. */ (charset, ccl_program)) { + struct ccl_program test_ccl; + charset = Fget_charset (charset); - CHECK_VECTOR (ccl_program); + if (setup_ccl_program (&test_ccl, ccl_program) < 0) + signal_simple_error ("Invalid ccl-program", ccl_program); XCHARSET_CCL_PROGRAM (charset) = ccl_program; return Qnil; } @@ -966,13 +1034,13 @@ static void invalidate_charset_font_caches (Lisp_Object charset) { /* Invalidate font cache entries for charset on all devices. */ - Lisp_Object devcons, concons, hashtab; + Lisp_Object devcons, concons, hash_table; DEVICE_LOOP_NO_BREAK (devcons, concons) { struct device *d = XDEVICE (XCAR (devcons)); - hashtab = Fgethash (charset, d->charset_font_cache, Qunbound); - if (!UNBOUNDP (hashtab)) - Fclrhash (hashtab); + hash_table = Fgethash (charset, d->charset_font_cache, Qunbound); + if (!UNBOUNDP (hash_table)) + Fclrhash (hash_table); } } @@ -996,11 +1064,14 @@ 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)) { - struct Lisp_Charset *cs; + Lisp_Charset *cs; int a1, a2; int lowlim, highlim; @@ -1013,7 +1084,11 @@ 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 because 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)); @@ -1026,7 +1101,7 @@ 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)); @@ -1034,40 +1109,68 @@ Make a multi-byte character from CHARSET and octets ARG1 and ARG2. } DEFUN ("char-charset", Fchar_charset, 1, 1, 0, /* -Return the character set of char CH. +Return the character set of CHARACTER. */ - (ch)) + (character)) { - CHECK_CHAR_COERCE_INT (ch); + CHECK_CHAR_COERCE_INT (character); return XCHARSET_NAME (CHARSET_BY_LEADING_BYTE - (CHAR_LEADING_BYTE (XCHAR (ch)))); + (CHAR_LEADING_BYTE (XCHAR (character)))); } DEFUN ("char-octet", Fchar_octet, 1, 2, 0, /* -Return the octet numbered N (should be 0 or 1) of char CH. +Return the octet numbered N (should be 0 or 1) of CHARACTER. N defaults to 0 if omitted. */ - (ch, n)) + (character, n)) { Lisp_Object charset; - int c1, c2, int_n; + int octet0, octet1; + + CHECK_CHAR_COERCE_INT (character); + + BREAKUP_CHAR (XCHAR (character), charset, octet0, octet1); + + if (NILP (n) || EQ (n, Qzero)) + return make_int (octet0); + else if (EQ (n, make_int (1))) + return make_int (octet1); + else + signal_simple_error ("Octet number must be 0 or 1", n); +} + +DEFUN ("split-char", Fsplit_char, 1, 1, 0, /* +Return list of charset and one or two position-codes of CHARACTER. +*/ + (character)) +{ + /* This function can GC */ + struct gcpro gcpro1, gcpro2; + Lisp_Object charset = Qnil; + Lisp_Object rc = Qnil; + int c1, c2; + + GCPRO2 (charset, rc); + CHECK_CHAR_COERCE_INT (character); + + BREAKUP_CHAR (XCHAR (character), charset, c1, c2); - CHECK_CHAR_COERCE_INT (ch); - if (NILP (n)) - int_n = 0; + 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 */ /************************************************************************/ @@ -1077,7 +1180,7 @@ lookup_composite_char (Bufbyte *str, int len) { Lisp_Object lispstr = make_string (str, len); Lisp_Object ch = Fgethash (lispstr, - Vcomposite_char_string2char_hashtable, + Vcomposite_char_string2char_hash_table, Qunbound); Emchar emch; @@ -1088,9 +1191,9 @@ lookup_composite_char (Bufbyte *str, int len) emch = MAKE_CHAR (Vcharset_composite, composite_char_row_next, composite_char_col_next); Fputhash (make_char (emch), lispstr, - Vcomposite_char_char2string_hashtable); + Vcomposite_char_char2string_hash_table); Fputhash (lispstr, make_char (emch), - Vcomposite_char_string2char_hashtable); + Vcomposite_char_string2char_hash_table); composite_char_col_next++; if (composite_char_col_next >= 128) { @@ -1107,13 +1210,13 @@ Lisp_Object composite_char_string (Emchar ch) { Lisp_Object str = Fgethash (make_char (ch), - Vcomposite_char_char2string_hashtable, + Vcomposite_char_char2string_hash_table, Qunbound); assert (!UNBOUNDP (str)); 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. @@ -1125,7 +1228,7 @@ 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)) @@ -1138,6 +1241,7 @@ 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 */ /************************************************************************/ @@ -1147,6 +1251,8 @@ Return a string of the characters comprising a composite character. void syms_of_mule_charset (void) { + INIT_LRECORD_IMPLEMENTATION (charset); + DEFSUBR (Fcharsetp); DEFSUBR (Ffind_charset); DEFSUBR (Fget_charset); @@ -1156,7 +1262,9 @@ 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); @@ -1166,9 +1274,12 @@ 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"); @@ -1176,12 +1287,13 @@ 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"); @@ -1189,26 +1301,24 @@ 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"); } @@ -1217,204 +1327,273 @@ vars_of_mule_charset (void) { int i, j, k; + chlook = xnew_and_zero (struct charset_lookup); /* zero for Purify. */ + dump_add_root_struct_ptr (&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; + chlook->next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1; + chlook->next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2; } void complex_vars_of_mule_charset (void) { - staticpro (&Vcharset_hashtable); - Vcharset_hashtable = make_lisp_hashtable (50, HASHTABLE_NONWEAK, - HASHTABLE_EQ); + staticpro (&Vcharset_hash_table); + Vcharset_hash_table = + make_lisp_hash_table (50, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ); /* 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, - CHARSET_TYPE_94, 1, 0, 0, + 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; - Vcomposite_char_string2char_hashtable = - make_lisp_hashtable (500, HASHTABLE_NONWEAK, HASHTABLE_EQUAL); - Vcomposite_char_char2string_hashtable = - make_lisp_hashtable (500, HASHTABLE_NONWEAK, HASHTABLE_EQ); - staticpro (&Vcomposite_char_string2char_hashtable); - staticpro (&Vcomposite_char_char2string_hashtable); + Vcomposite_char_string2char_hash_table = + make_lisp_hash_table (500, HASH_TABLE_NON_WEAK, HASH_TABLE_EQUAL); + Vcomposite_char_char2string_hash_table = + 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 */ }