X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fmule-charset.c;h=b83166db2f17a54a03d1d650fc590135f2601aee;hb=02276b8e7e7b7e647493d52f77beb00d64951836;hp=eb866108719cd8b90ef167573fc65298e6fb824b;hpb=2e3e3f9ee27fec50f45c282d71eaddf7c673bc56;p=chise%2Fxemacs-chise.git- diff --git a/src/mule-charset.c b/src/mule-charset.c index eb86610..b83166d 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. */ @@ -41,40 +42,58 @@ 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; +#ifdef UTF2000 +Lisp_Object Vcharset_ucs_bmp; +Lisp_Object Vcharset_latin_viscii; +Lisp_Object Vcharset_latin_viscii_lower; +Lisp_Object Vcharset_latin_viscii_upper; +Lisp_Object Vcharset_ethiopic_ucs; +Lisp_Object Vcharset_hiragana_jisx0208; +Lisp_Object Vcharset_katakana_jisx0208; +#endif +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; +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 */ /* Table of charsets indexed by leading byte. */ -Lisp_Object charset_by_leading_byte[128]; +Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES]; /* Table of charsets indexed by type/final-byte/direction. */ +#ifdef UTF2000 +Lisp_Object charset_by_attributes[4][128]; +#else Lisp_Object charset_by_attributes[4][128][2]; +#endif -static int composite_char_row_next; -static int composite_char_col_next; - +#ifndef UTF2000 /* Table of number of bytes in the string representation of a character indexed by the first byte of that representation. @@ -94,12 +113,670 @@ Bytecount rep_bytes_by_first_byte[0xA0] = 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, /* 0x80 - 0x8f are for Dimension-1 official charsets */ +#ifdef CHAR_IS_UCS4 + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, +#else 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, +#endif /* 0x90 - 0x9d are for Dimension-2 official charsets */ /* 0x9e is for Dimension-1 private charsets */ /* 0x9f is for Dimension-2 private charsets */ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4 }; +#endif + +#ifdef UTF2000 + +static Lisp_Object +mark_char_byte_table (Lisp_Object obj, void (*markobj) (Lisp_Object)) +{ + struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (obj); + int i; + + for (i = 0; i < 256; i++) + { + markobj (cte->property[i]); + } + return Qnil; +} + +static int +char_byte_table_equal (Lisp_Object obj1, Lisp_Object obj2, int depth) +{ + struct Lisp_Char_Byte_Table *cte1 = XCHAR_BYTE_TABLE (obj1); + struct Lisp_Char_Byte_Table *cte2 = XCHAR_BYTE_TABLE (obj2); + int i; + + for (i = 0; i < 256; i++) + if (CHAR_BYTE_TABLE_P (cte1->property[i])) + { + if (CHAR_BYTE_TABLE_P (cte2->property[i])) + { + if (!char_byte_table_equal (cte1->property[i], + cte2->property[i], depth + 1)) + return 0; + } + else + return 0; + } + else + if (!internal_equal (cte1->property[i], cte2->property[i], depth + 1)) + return 0; + return 1; +} + +static unsigned long +char_byte_table_hash (Lisp_Object obj, int depth) +{ + struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (obj); + + return internal_array_hash (cte->property, 256, depth); +} + +static const struct lrecord_description char_byte_table_description[] = { + { XD_LISP_OBJECT, offsetof(struct Lisp_Char_Byte_Table, property), 256 }, + { XD_END } +}; + +DEFINE_LRECORD_IMPLEMENTATION ("char-byte-table", char_byte_table, + mark_char_byte_table, + internal_object_printer, + 0, char_byte_table_equal, + char_byte_table_hash, + char_byte_table_description, + struct Lisp_Char_Byte_Table); + +static Lisp_Object +make_char_byte_table (Lisp_Object initval) +{ + Lisp_Object obj; + int i; + struct Lisp_Char_Byte_Table *cte = + alloc_lcrecord_type (struct Lisp_Char_Byte_Table, + &lrecord_char_byte_table); + + for (i = 0; i < 256; i++) + cte->property[i] = initval; + + XSETCHAR_BYTE_TABLE (obj, cte); + return obj; +} + +static Lisp_Object +copy_char_byte_table (Lisp_Object entry) +{ + struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (entry); + Lisp_Object obj; + int i; + struct Lisp_Char_Byte_Table *ctenew = + alloc_lcrecord_type (struct Lisp_Char_Byte_Table, + &lrecord_char_byte_table); + + for (i = 0; i < 256; i++) + { + Lisp_Object new = cte->property[i]; + if (CHAR_BYTE_TABLE_P (new)) + ctenew->property[i] = copy_char_byte_table (new); + else + ctenew->property[i] = new; + } + + XSETCHAR_BYTE_TABLE (obj, ctenew); + return obj; +} + + +static Lisp_Object +mark_char_code_table (Lisp_Object obj, void (*markobj) (Lisp_Object)) +{ + struct Lisp_Char_Code_Table *cte = XCHAR_CODE_TABLE (obj); + + return cte->table; +} + +static int +char_code_table_equal (Lisp_Object obj1, Lisp_Object obj2, int depth) +{ + struct Lisp_Char_Code_Table *cte1 = XCHAR_CODE_TABLE (obj1); + struct Lisp_Char_Code_Table *cte2 = XCHAR_CODE_TABLE (obj2); + + return char_byte_table_equal (cte1->table, cte2->table, depth + 1); +} + +static unsigned long +char_code_table_hash (Lisp_Object obj, int depth) +{ + struct Lisp_Char_Code_Table *cte = XCHAR_CODE_TABLE (obj); + + return char_code_table_hash (cte->table, depth + 1); +} + +static const struct lrecord_description char_code_table_description[] = { + { XD_LISP_OBJECT, offsetof(struct Lisp_Char_Code_Table, table), 1 }, + { XD_END } +}; + +DEFINE_LRECORD_IMPLEMENTATION ("char-code-table", char_code_table, + mark_char_code_table, + internal_object_printer, + 0, char_code_table_equal, + char_code_table_hash, + char_code_table_description, + struct Lisp_Char_Code_Table); + +static Lisp_Object +make_char_code_table (Lisp_Object initval) +{ + Lisp_Object obj; + struct Lisp_Char_Code_Table *cte = + alloc_lcrecord_type (struct Lisp_Char_Code_Table, + &lrecord_char_code_table); + + cte->table = make_char_byte_table (initval); + + XSETCHAR_CODE_TABLE (obj, cte); + return obj; +} + +static Lisp_Object +copy_char_code_table (Lisp_Object entry) +{ + struct Lisp_Char_Code_Table *cte = XCHAR_CODE_TABLE (entry); + Lisp_Object obj; + struct Lisp_Char_Code_Table *ctenew = + alloc_lcrecord_type (struct Lisp_Char_Code_Table, + &lrecord_char_code_table); + + ctenew->table = copy_char_byte_table (cte->table); + XSETCHAR_CODE_TABLE (obj, ctenew); + return obj; +} + + +Lisp_Object +get_char_code_table (Emchar ch, Lisp_Object table) +{ + unsigned int code = ch; + struct Lisp_Char_Byte_Table* cpt + = XCHAR_BYTE_TABLE (XCHAR_CODE_TABLE (table)->table); + Lisp_Object ret = cpt->property [(unsigned char)(code >> 24)]; + + if (CHAR_BYTE_TABLE_P (ret)) + cpt = XCHAR_BYTE_TABLE (ret); + else + return ret; + + ret = cpt->property [(unsigned char) (code >> 16)]; + if (CHAR_BYTE_TABLE_P (ret)) + cpt = XCHAR_BYTE_TABLE (ret); + else + return ret; + + ret = cpt->property [(unsigned char) (code >> 8)]; + if (CHAR_BYTE_TABLE_P (ret)) + cpt = XCHAR_BYTE_TABLE (ret); + else + return ret; + + return cpt->property [(unsigned char) code]; +} + +void +put_char_code_table (Emchar ch, Lisp_Object value, Lisp_Object table) +{ + unsigned int code = ch; + struct Lisp_Char_Byte_Table* cpt1 + = XCHAR_BYTE_TABLE (XCHAR_CODE_TABLE (table)->table); + Lisp_Object ret = cpt1->property[(unsigned char)(code >> 24)]; + + if (CHAR_BYTE_TABLE_P (ret)) + { + struct Lisp_Char_Byte_Table* cpt2 = XCHAR_BYTE_TABLE (ret); + + ret = cpt2->property[(unsigned char)(code >> 16)]; + if (CHAR_BYTE_TABLE_P (ret)) + { + struct Lisp_Char_Byte_Table* cpt3 = XCHAR_BYTE_TABLE (ret); + + ret = cpt3->property[(unsigned char)(code >> 8)]; + if (CHAR_BYTE_TABLE_P (ret)) + { + struct Lisp_Char_Byte_Table* cpt4 + = XCHAR_BYTE_TABLE (ret); + + cpt4->property[(unsigned char)code] = value; + } + else if (!EQ (ret, value)) + { + Lisp_Object cpt4 = make_char_byte_table (ret); + + XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)code] = value; + cpt3->property[(unsigned char)(code >> 8)] = cpt4; + } + } + else if (!EQ (ret, value)) + { + Lisp_Object cpt3 = make_char_byte_table (ret); + Lisp_Object cpt4 = make_char_byte_table (ret); + + XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)code] = value; + XCHAR_BYTE_TABLE(cpt3)->property[(unsigned char)(code >> 8)] + = cpt4; + cpt2->property[(unsigned char)(code >> 16)] = cpt3; + } + } + else if (!EQ (ret, value)) + { + Lisp_Object cpt2 = make_char_byte_table (ret); + Lisp_Object cpt3 = make_char_byte_table (ret); + Lisp_Object cpt4 = make_char_byte_table (ret); + + XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)code] = value; + XCHAR_BYTE_TABLE(cpt3)->property[(unsigned char)(code >> 8)] = cpt4; + XCHAR_BYTE_TABLE(cpt2)->property[(unsigned char)(code >> 16)] = cpt3; + cpt1->property[(unsigned char)(code >> 24)] = cpt2; + } +} + + +Lisp_Object Vcharacter_attribute_table; +Lisp_Object Vcharacter_composition_table; +Lisp_Object Vcharacter_variant_table; + +Lisp_Object Q_decomposition; +Lisp_Object Q_ucs; +Lisp_Object Qcompat; +Lisp_Object QnoBreak; +Lisp_Object Qfraction; +Lisp_Object Qsuper; +Lisp_Object Qsub; +Lisp_Object Qcircle; +Lisp_Object Qsquare; +Lisp_Object Qwide; +Lisp_Object Qnarrow; +Lisp_Object Qfont; + +Emchar +to_char_code (Lisp_Object v, char* err_msg, Lisp_Object err_arg) +{ + if (INTP (v)) + return XINT (v); + if (CHARP (v)) + return XCHAR (v); + else if (EQ (v, Qcompat)) + return -1; + else if (EQ (v, QnoBreak)) + return -2; + else if (EQ (v, Qfraction)) + return -3; + else if (EQ (v, Qsuper)) + return -4; + else if (EQ (v, Qsub)) + return -5; + else if (EQ (v, Qcircle)) + return -6; + else if (EQ (v, Qsquare)) + return -7; + else if (EQ (v, Qwide)) + return -8; + else if (EQ (v, Qnarrow)) + return -9; + else if (EQ (v, Qfont)) + return -10; + else + signal_simple_error (err_msg, err_arg); +} + +DEFUN ("get-composite-char", Fget_composite_char, 1, 1, 0, /* +Return character corresponding with list. +*/ + (list)) +{ + Lisp_Object table = Vcharacter_composition_table; + Lisp_Object rest = list; + + while (CONSP (rest)) + { + Lisp_Object v = Fcar (rest); + Lisp_Object ret; + Emchar c = to_char_code (v, "Invalid value for composition", list); + + ret = get_char_code_table (c, table); + + rest = Fcdr (rest); + if (NILP (rest)) + { + if (!CHAR_CODE_TABLE_P (ret)) + return ret; + else + return Qt; + } + else if (!CONSP (rest)) + break; + else if (CHAR_CODE_TABLE_P (ret)) + table = ret; + else + signal_simple_error ("Invalid table is found with", list); + } + signal_simple_error ("Invalid value for composition", list); +} + +DEFUN ("char-variants", Fchar_variants, 1, 1, 0, /* +Return variants of CHARACTER. +*/ + (character)) +{ + CHECK_CHAR (character); + return Fcopy_list (get_char_code_table (XCHAR (character), + Vcharacter_variant_table)); +} + +DEFUN ("char-attribute-alist", Fchar_attribute_alist, 1, 1, 0, /* +Return the alist of attributes of CHARACTER. +*/ + (character)) +{ + CHECK_CHAR (character); + return Fcopy_alist (get_char_code_table (XCHAR (character), + Vcharacter_attribute_table)); +} + +DEFUN ("get-char-attribute", Fget_char_attribute, 2, 2, 0, /* +Return the value of CHARACTER's ATTRIBUTE. +*/ + (character, attribute)) +{ + Lisp_Object ret + = get_char_code_table (XCHAR (character), Vcharacter_attribute_table); + Lisp_Object ccs; + + if (EQ (ret, Qnil)) + return Qnil; + + if (!NILP (ccs = Ffind_charset (attribute))) + attribute = ccs; + + return Fcdr (Fassq (attribute, ret)); +} + +Lisp_Object +put_char_attribute (Lisp_Object character, Lisp_Object attribute, + Lisp_Object value) +{ + Emchar char_code = XCHAR (character); + Lisp_Object ret + = get_char_code_table (char_code, Vcharacter_attribute_table); + Lisp_Object cell; + + cell = Fassq (attribute, ret); + + if (NILP (cell)) + { + ret = Fcons (Fcons (attribute, value), ret); + } + else if (!EQ (Fcdr (cell), value)) + { + Fsetcdr (cell, value); + } + put_char_code_table (char_code, ret, Vcharacter_attribute_table); + return ret; +} + +DEFUN ("put-char-attribute", Fput_char_attribute, 3, 3, 0, /* +Store CHARACTER's ATTRIBUTE with VALUE. +*/ + (character, attribute, value)) +{ + Lisp_Object ccs; + + ccs = Ffind_charset (attribute); + if (!NILP (ccs)) + { + Lisp_Object rest; + Lisp_Object v = XCHARSET_DECODING_TABLE (ccs); + Lisp_Object nv; + int i = -1; + int ccs_len; + + /* ad-hoc method for `ascii' */ + if ((XCHARSET_CHARS (ccs) == 94) && + (XCHARSET_BYTE_OFFSET (ccs) != 33)) + ccs_len = 128 - XCHARSET_BYTE_OFFSET (ccs); + else + ccs_len = XCHARSET_CHARS (ccs); + + if (!CONSP (value)) + signal_simple_error ("Invalid value for coded-charset", + value); + + attribute = ccs; + rest = Fget_char_attribute (character, attribute); + if (VECTORP (v)) + { + if (!NILP (rest)) + { + while (!NILP (rest)) + { + Lisp_Object ei = Fcar (rest); + + i = XINT (ei) - XCHARSET_BYTE_OFFSET (ccs); + nv = XVECTOR_DATA(v)[i]; + if (!VECTORP (nv)) + break; + v = nv; + rest = Fcdr (rest); + } + if (i >= 0) + XVECTOR_DATA(v)[i] = Qnil; + v = XCHARSET_DECODING_TABLE (ccs); + } + } + else + { + XCHARSET_DECODING_TABLE (ccs) = v = make_vector (ccs_len, Qnil); + } + + if (XCHARSET_GRAPHIC (ccs) == 1) + value = Fcopy_list (value); + rest = value; + i = -1; + while (CONSP (rest)) + { + Lisp_Object ei = Fcar (rest); + + if (!INTP (ei)) + signal_simple_error ("Invalid value for coded-charset", value); + i = XINT (ei); + if ((i < 0) || (255 < i)) + signal_simple_error ("Invalid value for coded-charset", value); + if (XCHARSET_GRAPHIC (ccs) == 1) + { + i &= 0x7F; + Fsetcar (rest, make_int (i)); + } + i -= XCHARSET_BYTE_OFFSET (ccs); + nv = XVECTOR_DATA(v)[i]; + rest = Fcdr (rest); + if (CONSP (rest)) + { + if (!VECTORP (nv)) + { + nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil)); + } + v = nv; + } + else + break; + } + XVECTOR_DATA(v)[i] = character; + } + else if (EQ (attribute, Q_decomposition)) + { + Lisp_Object rest = value; + Lisp_Object table = Vcharacter_composition_table; + + if (!CONSP (value)) + signal_simple_error ("Invalid value for ->decomposition", + value); + + while (CONSP (rest)) + { + Lisp_Object v = Fcar (rest); + Lisp_Object ntable; + Emchar c + = to_char_code (v, "Invalid value for ->decomposition", value); + + rest = Fcdr (rest); + if (!CONSP (rest)) + { + put_char_code_table (c, character, table); + break; + } + else + { + ntable = get_char_code_table (c, table); + if (!CHAR_CODE_TABLE_P (ntable)) + { + ntable = make_char_code_table (Qnil); + put_char_code_table (c, ntable, table); + } + table = ntable; + } + } + } + else if (EQ (attribute, Q_ucs)) + { + Lisp_Object ret; + Emchar c; + + if (!INTP (value)) + signal_simple_error ("Invalid value for ->ucs", value); + + c = XINT (value); + + ret = get_char_code_table (c, Vcharacter_variant_table); + if (NILP (Fmemq (character, ret))) + { + put_char_code_table (c, Fcons (character, ret), + Vcharacter_variant_table); + } + } + return put_char_attribute (character, attribute, value); +} + +Lisp_Object Qucs; + +DEFUN ("define-char", Fdefine_char, 1, 1, 0, /* +Store character's ATTRIBUTES. +*/ + (attributes)) +{ + Lisp_Object rest = attributes; + Lisp_Object code = Fcdr (Fassq (Qucs, attributes)); + Lisp_Object character; + + if (NILP (code)) + { + while (CONSP (rest)) + { + Lisp_Object cell = Fcar (rest); + Lisp_Object ccs; + + if (!LISTP (cell)) + signal_simple_error ("Invalid argument", attributes); + if (!NILP (ccs = Ffind_charset (Fcar (cell))) + && XCHARSET_FINAL (ccs)) + { + Emchar code; + + if (XCHARSET_DIMENSION (ccs) == 1) + { + Lisp_Object eb1 = Fcar (Fcdr (cell)); + int b1; + + if (!INTP (eb1)) + signal_simple_error ("Invalid argument", attributes); + b1 = XINT (eb1); + switch (XCHARSET_CHARS (ccs)) + { + case 94: + code = MIN_CHAR_94 + + (XCHARSET_FINAL (ccs) - '0') * 94 + (b1 - 33); + break; + case 96: + code = MIN_CHAR_96 + + (XCHARSET_FINAL (ccs) - '0') * 96 + (b1 - 32); + break; + default: + abort (); + } + } + else if (XCHARSET_DIMENSION (ccs) == 2) + { + Lisp_Object eb1 = Fcar (Fcdr (cell)); + Lisp_Object eb2 = Fcar (Fcdr (Fcdr (cell))); + int b1, b2; + + if (!INTP (eb1)) + signal_simple_error ("Invalid argument", attributes); + b1 = XINT (eb1); + if (!INTP (eb2)) + signal_simple_error ("Invalid argument", attributes); + b2 = XINT (eb2); + switch (XCHARSET_CHARS (ccs)) + { + case 94: + code = MIN_CHAR_94x94 + + (XCHARSET_FINAL (ccs) - '0') * 94 * 94 + + (b1 - 33) * 94 + (b2 - 33); + break; + case 96: + code = MIN_CHAR_96x96 + + (XCHARSET_FINAL (ccs) - '0') * 96 * 96 + + (b1 - 32) * 96 + (b2 - 32); + break; + default: + abort (); + } + } + else + { + rest = Fcdr (rest); + continue; + } + character = make_char (code); + goto setup_attributes; + } + rest = Fcdr (rest); + } + return Qnil; + } + else if (!INTP (code)) + signal_simple_error ("Invalid argument", attributes); + else + character = make_char (XINT (code)); + + setup_attributes: + rest = attributes; + while (CONSP (rest)) + { + Lisp_Object cell = Fcar (rest); + + if (!LISTP (cell)) + signal_simple_error ("Invalid argument", attributes); + Fput_char_attribute (character, Fcar (cell), Fcdr (cell)); + rest = Fcdr (rest); + } + return + get_char_code_table (XCHAR (character), Vcharacter_attribute_table); +} + +Lisp_Object Vutf_2000_version; +#endif + +#ifndef UTF2000 +int leading_code_private_11; +#endif Lisp_Object Qcharsetp; @@ -107,39 +784,55 @@ 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, +#ifdef UTF2000 + Qucs_bmp, + Qlatin_viscii, + Qlatin_viscii_lower, + Qlatin_viscii_upper, + Qvietnamese_viscii_lower, + Qvietnamese_viscii_upper, + Qethiopic_ucs, + Qhiragana_jisx0208, + Qkatakana_jisx0208, +#endif + Qchinese_big5_1, + Qchinese_big5_2, + Qcomposite; Lisp_Object Ql2r, Qr2l; -Lisp_Object Vcharset_hashtable; +Lisp_Object Vcharset_hash_table; -static Bufbyte next_allocated_1_byte_leading_byte; -static Bufbyte next_allocated_2_byte_leading_byte; +#ifdef UTF2000 +static Charset_ID next_allocated_leading_byte; +#else +static Charset_ID next_allocated_1_byte_leading_byte; +static Charset_ID next_allocated_2_byte_leading_byte; +#endif /* Composite characters are characters constructed by overstriking two or more regular characters. @@ -184,11 +877,54 @@ Bytecount non_ascii_set_charptr_emchar (Bufbyte *str, Emchar c) { Bufbyte *p; - Bufbyte lb; +#ifndef UTF2000 + Charset_ID lb; int c1, c2; Lisp_Object charset; +#endif p = str; +#ifdef UTF2000 + if ( c <= 0x7f ) + { + *p++ = c; + } + else if ( c <= 0x7ff ) + { + *p++ = (c >> 6) | 0xc0; + *p++ = (c & 0x3f) | 0x80; + } + else if ( c <= 0xffff ) + { + *p++ = (c >> 12) | 0xe0; + *p++ = ((c >> 6) & 0x3f) | 0x80; + *p++ = (c & 0x3f) | 0x80; + } + else if ( c <= 0x1fffff ) + { + *p++ = (c >> 18) | 0xf0; + *p++ = ((c >> 12) & 0x3f) | 0x80; + *p++ = ((c >> 6) & 0x3f) | 0x80; + *p++ = (c & 0x3f) | 0x80; + } + else if ( c <= 0x3ffffff ) + { + *p++ = (c >> 24) | 0xf8; + *p++ = ((c >> 18) & 0x3f) | 0x80; + *p++ = ((c >> 12) & 0x3f) | 0x80; + *p++ = ((c >> 6) & 0x3f) | 0x80; + *p++ = (c & 0x3f) | 0x80; + } + else + { + *p++ = (c >> 30) | 0xfc; + *p++ = ((c >> 24) & 0x3f) | 0x80; + *p++ = ((c >> 18) & 0x3f) | 0x80; + *p++ = ((c >> 12) & 0x3f) | 0x80; + *p++ = ((c >> 6) & 0x3f) | 0x80; + *p++ = (c & 0x3f) | 0x80; + } +#else BREAKUP_CHAR (c, charset, c1, c2); lb = CHAR_LEADING_BYTE (c); if (LEADING_BYTE_PRIVATE_P (lb)) @@ -199,7 +935,7 @@ non_ascii_set_charptr_emchar (Bufbyte *str, Emchar c) *p++ = c1 | 0x80; if (c2) *p++ = c2 | 0x80; - +#endif return (p - str); } @@ -210,6 +946,49 @@ non_ascii_set_charptr_emchar (Bufbyte *str, Emchar c) Emchar non_ascii_charptr_emchar (CONST Bufbyte *str) { +#ifdef UTF2000 + Bufbyte b; + Emchar ch; + int len; + + b = *str++; + if ( b >= 0xfc ) + { + ch = (b & 0x01); + len = 5; + } + else if ( b >= 0xf8 ) + { + ch = b & 0x03; + len = 4; + } + else if ( b >= 0xf0 ) + { + ch = b & 0x07; + len = 3; + } + else if ( b >= 0xe0 ) + { + ch = b & 0x0f; + len = 2; + } + else if ( b >= 0xc0 ) + { + ch = b & 0x1f; + len = 1; + } + else + { + ch = b; + len = 0; + } + for( ; len > 0; len-- ) + { + b = *str++; + ch = ( ch << 6 ) | ( b & 0x3f ); + } + return ch; +#else Bufbyte i0 = *str, i1, i2 = 0; Lisp_Object charset; @@ -226,11 +1005,13 @@ non_ascii_charptr_emchar (CONST Bufbyte *str) i2 = *++str & 0x7F; return MAKE_CHAR (charset, i1, i2); +#endif } /* Return whether CH is a valid Emchar, assuming it's non-ASCII. Do not call this directly. Use the macro valid_char_p() instead. */ +#ifndef UTF2000 int non_ascii_valid_char_p (Emchar ch) { @@ -277,14 +1058,16 @@ 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) return 1; @@ -299,6 +1082,7 @@ non_ascii_valid_char_p (Emchar ch) return (XCHARSET_CHARS (charset) == 96); } } +#endif /************************************************************************/ @@ -317,6 +1101,10 @@ non_ascii_charptr_copy_char (CONST Bufbyte *ptr, Bufbyte *str) switch (REP_BYTES_BY_FIRST_BYTE (*strptr)) { /* Notice fallthrough. */ +#ifdef UTF2000 + case 6: *++strptr = *ptr++; + case 5: *++strptr = *ptr++; +#endif case 4: *++strptr = *ptr++; case 3: *++strptr = *ptr++; case 2: *++strptr = *ptr; @@ -346,6 +1134,16 @@ Lstream_get_emchar_1 (Lstream *stream, int ch) switch (REP_BYTES_BY_FIRST_BYTE (ch)) { /* Notice fallthrough. */ +#ifdef UTF2000 + case 6: + ch = Lstream_getc (stream); + assert (ch >= 0); + *++strptr = (Bufbyte) ch; + case 5: + ch = Lstream_getc (stream); + assert (ch >= 0); + *++strptr = (Bufbyte) ch; +#endif case 4: ch = Lstream_getc (stream); assert (ch >= 0); @@ -391,9 +1189,14 @@ mark_charset (Lisp_Object obj, void (*markobj) (Lisp_Object)) { struct Lisp_Charset *cs = XCHARSET (obj); - (markobj) (cs->doc_string); - (markobj) (cs->registry); - (markobj) (cs->ccl_program); + markobj (cs->short_name); + markobj (cs->long_name); + markobj (cs->doc_string); + markobj (cs->registry); + markobj (cs->ccl_program); +#ifdef UTF2000 + markobj (cs->decoding_table); +#endif return cs->name; } @@ -411,6 +1214,10 @@ print_charset (Lisp_Object obj, Lisp_Object printcharfun, int escapeflag) write_c_string ("# MAX_LEADING_BYTE_PRIVATE) + lb = 0; + else + lb = next_allocated_leading_byte++; +#else if (dimension == 1) { if (next_allocated_1_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_1) @@ -503,6 +1389,7 @@ get_unallocated_leading_byte (int dimension) else lb = next_allocated_2_byte_leading_byte++; } +#endif if (!lb) signal_simple_error @@ -512,6 +1399,208 @@ get_unallocated_leading_byte (int dimension) return lb; } +#ifdef UTF2000 +Lisp_Object +range_charset_code_point (Lisp_Object charset, Emchar ch) +{ + int d; + + if ((XCHARSET_UCS_MIN (charset) <= ch) + && (ch <= XCHARSET_UCS_MAX (charset))) + { + d = ch - XCHARSET_UCS_MIN (charset) + XCHARSET_CODE_OFFSET (charset); + + if (XCHARSET_DIMENSION (charset) == 1) + return list1 (make_int (d + XCHARSET_BYTE_OFFSET (charset))); + else if (XCHARSET_DIMENSION (charset) == 2) + return list2 (make_int (d / XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset)), + make_int (d % XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset))); + else if (XCHARSET_DIMENSION (charset) == 3) + return list3 (make_int (d / (XCHARSET_CHARS (charset) + * XCHARSET_CHARS (charset)) + + XCHARSET_BYTE_OFFSET (charset)), + make_int (d / XCHARSET_CHARS (charset) + % XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset)), + make_int (d % XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset))); + else /* if (XCHARSET_DIMENSION (charset) == 4) */ + return list4 (make_int (d / (XCHARSET_CHARS (charset) + * XCHARSET_CHARS (charset) + * XCHARSET_CHARS (charset)) + + XCHARSET_BYTE_OFFSET (charset)), + make_int (d / (XCHARSET_CHARS (charset) + * XCHARSET_CHARS (charset)) + % XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset)), + make_int (d / XCHARSET_CHARS (charset) + % XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset)), + make_int (d % XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset))); + } + else if (XCHARSET_CODE_OFFSET (charset) == 0) + { + if (XCHARSET_DIMENSION (charset) == 1) + { + if (XCHARSET_CHARS (charset) == 94) + { + if (((d = ch - (MIN_CHAR_94 + + (XCHARSET_FINAL (charset) - '0') * 94)) >= 0) + && (d < 94)) + return list1 (make_int (d + 33)); + } + else if (XCHARSET_CHARS (charset) == 96) + { + if (((d = ch - (MIN_CHAR_96 + + (XCHARSET_FINAL (charset) - '0') * 96)) >= 0) + && (d < 96)) + return list1 (make_int (d + 32)); + } + else + return Qnil; + } + else if (XCHARSET_DIMENSION (charset) == 2) + { + if (XCHARSET_CHARS (charset) == 94) + { + if (((d = ch - (MIN_CHAR_94x94 + + (XCHARSET_FINAL (charset) - '0') * 94 * 94)) + >= 0) + && (d < 94 * 94)) + return list2 (make_int ((d / 94) + 33), + make_int (d % 94 + 33)); + } + else if (XCHARSET_CHARS (charset) == 96) + { + if (((d = ch - (MIN_CHAR_96x96 + + (XCHARSET_FINAL (charset) - '0') * 96 * 96)) + >= 0) + && (d < 96 * 96)) + return list2 (make_int ((d / 96) + 32), + make_int (d % 96 + 32)); + } + } + } + return Qnil; +} + +Lisp_Object +split_builtin_char (Emchar c) +{ + if (c < MIN_CHAR_OBS_94x94) + { + if (c <= MAX_CHAR_BASIC_LATIN) + { + return list2 (Vcharset_ascii, make_int (c)); + } + else if (c < 0xA0) + { + return list2 (Vcharset_control_1, make_int (c & 0x7F)); + } + else if (c <= 0xff) + { + return list2 (Vcharset_latin_iso8859_1, make_int (c & 0x7F)); + } + else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK)) + { + return list2 (Vcharset_greek_iso8859_7, + make_int (c - MIN_CHAR_GREEK + 0x20)); + } + else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC)) + { + return list2 (Vcharset_cyrillic_iso8859_5, + make_int (c - MIN_CHAR_CYRILLIC + 0x20)); + } + else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW)) + { + return list2 (Vcharset_hebrew_iso8859_8, + make_int (c - MIN_CHAR_HEBREW + 0x20)); + } + else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI)) + { + return list2 (Vcharset_thai_tis620, + make_int (c - MIN_CHAR_THAI + 0x20)); + } + else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c) + && (c <= MAX_CHAR_HALFWIDTH_KATAKANA)) + { + return list2 (Vcharset_katakana_jisx0201, + make_int (c - MIN_CHAR_HALFWIDTH_KATAKANA + 33)); + } + else + { + return list3 (Vcharset_ucs_bmp, + make_int (c >> 8), make_int (c & 0xff)); + } + } + else if (c <= MAX_CHAR_OBS_94x94) + { + return list3 (CHARSET_BY_ATTRIBUTES + (CHARSET_TYPE_94X94, + ((c - MIN_CHAR_OBS_94x94) / (94 * 94)) + '@', + CHARSET_LEFT_TO_RIGHT), + make_int ((((c - MIN_CHAR_OBS_94x94) / 94) % 94) + 33), + make_int (((c - MIN_CHAR_OBS_94x94) % 94) + 33)); + } + else if (c <= MAX_CHAR_94) + { + return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94, + ((c - MIN_CHAR_94) / 94) + '0', + CHARSET_LEFT_TO_RIGHT), + make_int (((c - MIN_CHAR_94) % 94) + 33)); + } + else if (c <= MAX_CHAR_96) + { + return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96, + ((c - MIN_CHAR_96) / 96) + '0', + CHARSET_LEFT_TO_RIGHT), + make_int (((c - MIN_CHAR_96) % 96) + 32)); + } + else if (c <= MAX_CHAR_94x94) + { + return list3 (CHARSET_BY_ATTRIBUTES + (CHARSET_TYPE_94X94, + ((c - MIN_CHAR_94x94) / (94 * 94)) + '0', + CHARSET_LEFT_TO_RIGHT), + make_int ((((c - MIN_CHAR_94x94) / 94) % 94) + 33), + make_int (((c - MIN_CHAR_94x94) % 94) + 33)); + } + else if (c <= MAX_CHAR_96x96) + { + return list3 (CHARSET_BY_ATTRIBUTES + (CHARSET_TYPE_96X96, + ((c - MIN_CHAR_96x96) / (96 * 96)) + '0', + CHARSET_LEFT_TO_RIGHT), + make_int ((((c - MIN_CHAR_96x96) / 96) % 96) + 32), + make_int (((c - MIN_CHAR_96x96) % 96) + 32)); + } + else + { + return Qnil; + } +} + +Lisp_Object +charset_code_point (Lisp_Object charset, Emchar ch) +{ + Lisp_Object cdef = get_char_code_table (ch, Vcharacter_attribute_table); + + if (!EQ (cdef, Qnil)) + { + Lisp_Object field = Fassq (charset, cdef); + + if (!EQ (field, Qnil)) + return Fcdr (field); + } + return range_charset_code_point (charset, ch); +} + +Lisp_Object Vdefault_coded_charset_priority_list; +#endif + /************************************************************************/ /* Basic charset Lisp functions */ @@ -537,7 +1626,7 @@ 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 +1652,15 @@ 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 +1675,7 @@ 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; @@ -613,6 +1698,8 @@ 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 +1739,15 @@ 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; + int byte_offset = -1; CHECK_SYMBOL (name); if (!NILP (doc_string)) @@ -670,7 +1759,19 @@ 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); @@ -698,7 +1799,11 @@ character set. Recognized properties are: { CHECK_INT (value); graphic = XINT (value); +#ifdef UTF2000 + if (graphic < 0 || graphic > 2) +#else if (graphic < 0 || graphic > 1) +#endif signal_simple_error ("Invalid value for 'graphic", value); } @@ -753,7 +1858,7 @@ 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 +1866,29 @@ 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); + + if (byte_offset < 0) + { + if (chars == 94) + byte_offset = 33; + else if (chars == 96) + byte_offset = 32; + else + byte_offset = 0; + } + + charset = make_charset (id, name, type, columns, graphic, + final, direction, short_name, long_name, + doc_string, registry, + Qnil, 0, 0, 0, byte_offset); if (!NILP (ccl_program)) XCHARSET_CCL_PROGRAM (charset) = ccl_program; return charset; @@ -778,9 +1902,9 @@ 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); @@ -797,7 +1921,7 @@ 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 +1929,23 @@ 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, type, columns, + graphic, final, direction, short_name, long_name, + doc_string, registry, +#ifdef UTF2000 + CHARSET_DECODING_TABLE(cs), + CHARSET_UCS_MIN(cs), + CHARSET_UCS_MAX(cs), + CHARSET_CODE_OFFSET(cs), + CHARSET_BYTE_OFFSET(cs) +#else + Qnil, 0, 0, 0, 0 +#endif +); CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset; XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset; @@ -816,6 +1953,16 @@ NEW-NAME is the name of the new charset. Return the new charset. return new_charset; } +DEFUN ("define-charset-alias", Fdefine_charset_alias, 2, 2, 0, /* +Define symbol ALIAS as an alias for CHARSET. +*/ + (alias, charset)) +{ + CHECK_SYMBOL (alias); + charset = Fget_charset (charset); + return Fputhash (alias, charset, Vcharset_hash_table); +} + /* #### Reverse direction charsets not yet implemented. */ #if 0 DEFUN ("charset-reverse-direction-charset", Fcharset_reverse_direction_charset, @@ -888,8 +2035,24 @@ 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)) { @@ -918,6 +2081,8 @@ 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)); @@ -945,7 +2110,7 @@ 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 @@ -966,17 +2131,16 @@ 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); } } -/* Japanese folks may want to (set-charset-registry 'ascii "jisx0201") */ DEFUN ("set-charset-registry", Fset_charset_registry, 2, 2, 0, /* Set the 'registry property of CHARSET to REGISTRY. */ @@ -990,13 +2154,115 @@ Set the 'registry property of CHARSET to REGISTRY. return Qnil; } +#ifdef UTF2000 +DEFUN ("charset-mapping-table", Fcharset_mapping_table, 1, 1, 0, /* +Return mapping-table of CHARSET. +*/ + (charset)) +{ + return XCHARSET_DECODING_TABLE (Fget_charset (charset)); +} + +DEFUN ("set-charset-mapping-table", Fset_charset_mapping_table, 2, 2, 0, /* +Set mapping-table of CHARSET to TABLE. +*/ + (charset, table)) +{ + struct Lisp_Charset *cs; + Lisp_Object old_table; + size_t i; + + charset = Fget_charset (charset); + cs = XCHARSET (charset); + + if (EQ (table, Qnil)) + { + CHARSET_DECODING_TABLE(cs) = table; + return table; + } + else if (VECTORP (table)) + { + int ccs_len; + + /* ad-hoc method for `ascii' */ + if ((CHARSET_CHARS (cs) == 94) && + (CHARSET_BYTE_OFFSET (cs) != 33)) + ccs_len = 128 - CHARSET_BYTE_OFFSET (cs); + else + ccs_len = CHARSET_CHARS (cs); + + if (XVECTOR_LENGTH (table) > ccs_len) + args_out_of_range (table, make_int (CHARSET_CHARS (cs))); + old_table = CHARSET_DECODING_TABLE(cs); + CHARSET_DECODING_TABLE(cs) = table; + } + else + signal_error (Qwrong_type_argument, + list2 (build_translated_string ("vector-or-nil-p"), + table)); + /* signal_simple_error ("Wrong type argument: vector-or-nil-p", table); */ + + switch (CHARSET_DIMENSION (cs)) + { + case 1: + for (i = 0; i < XVECTOR_LENGTH (table); i++) + { + Lisp_Object c = XVECTOR_DATA(table)[i]; + + if (CHARP (c)) + put_char_attribute + (c, charset, + list1 (make_int (i + CHARSET_BYTE_OFFSET (cs)))); + } + break; + case 2: + for (i = 0; i < XVECTOR_LENGTH (table); i++) + { + Lisp_Object v = XVECTOR_DATA(table)[i]; + + if (VECTORP (v)) + { + size_t j; + + if (XVECTOR_LENGTH (v) > CHARSET_CHARS (cs)) + { + CHARSET_DECODING_TABLE(cs) = old_table; + args_out_of_range (v, make_int (CHARSET_CHARS (cs))); + } + for (j = 0; j < XVECTOR_LENGTH (v); j++) + { + Lisp_Object c = XVECTOR_DATA(v)[j]; + + if (CHARP (c)) + put_char_attribute (c, charset, + list2 + (make_int + (i + CHARSET_BYTE_OFFSET (cs)), + make_int + (j + CHARSET_BYTE_OFFSET (cs)))); + } + } + else if (CHARP (v)) + put_char_attribute (v, charset, + list1 + (make_int (i + CHARSET_BYTE_OFFSET (cs)))); + } + break; + } + return table; +} +#endif + /************************************************************************/ /* Lisp primitives for working with characters */ /************************************************************************/ 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)) { @@ -1009,11 +2275,24 @@ Make a multi-byte character from CHARSET and octets ARG1 and ARG2. if (EQ (charset, Vcharset_ascii)) lowlim = 0, highlim = 127; else if (EQ (charset, Vcharset_control_1)) lowlim = 0, highlim = 31; +#ifdef UTF2000 + else if (CHARSET_CHARS (cs) == 256) lowlim = 0, highlim = 255; +#endif else if (CHARSET_CHARS (cs) == 94) lowlim = 33, highlim = 126; else /* CHARSET_CHARS (cs) == 96) */ lowlim = 32, highlim = 127; CHECK_INT (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. */ +#ifdef UTF2000 + a1 = XINT (arg1); + if (highlim < 128) + a1 &= 0x7f; +#else a1 = XINT (arg1); +#endif if (a1 < lowlim || a1 > highlim) args_out_of_range_3 (arg1, make_int (lowlim), make_int (highlim)); @@ -1026,7 +2305,13 @@ Make a multi-byte character from CHARSET and octets ARG1 and ARG2. } CHECK_INT (arg2); +#ifdef UTF2000 a2 = XINT (arg2); + if (highlim < 128) + a2 &= 0x7f; +#else + a2 = XINT (arg2) & 0x7f; +#endif if (a2 < lowlim || a2 > highlim) args_out_of_range_3 (arg2, make_int (lowlim), make_int (highlim)); @@ -1040,34 +2325,40 @@ Return the character set of char CH. { CHECK_CHAR_COERCE_INT (ch); - return XCHARSET_NAME (CHARSET_BY_LEADING_BYTE - (CHAR_LEADING_BYTE (XCHAR (ch)))); + return XCHARSET_NAME (CHAR_CHARSET (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 */ /************************************************************************/ @@ -1077,7 +2368,7 @@ 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 +2379,9 @@ 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 +2398,13 @@ 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 +2416,7 @@ 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 +2429,7 @@ 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 */ /************************************************************************/ @@ -1155,20 +2447,35 @@ syms_of_mule_charset (void) DEFSUBR (Fmake_charset); DEFSUBR (Fmake_reverse_direction_charset); /* DEFSUBR (Freverse_direction_charset); */ + DEFSUBR (Fdefine_charset_alias); 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); DEFSUBR (Fset_charset_ccl_program); DEFSUBR (Fset_charset_registry); +#ifdef UTF2000 + DEFSUBR (Fchar_attribute_alist); + DEFSUBR (Fget_char_attribute); + DEFSUBR (Fput_char_attribute); + DEFSUBR (Fdefine_char); + DEFSUBR (Fchar_variants); + DEFSUBR (Fget_composite_char); + DEFSUBR (Fcharset_mapping_table); + DEFSUBR (Fset_charset_mapping_table); +#endif 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 +2483,13 @@ 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"); @@ -1189,232 +2497,443 @@ 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"); +#ifdef UTF2000 + defsymbol (&Q_ucs, "->ucs"); + defsymbol (&Q_decomposition, "->decomposition"); + defsymbol (&Qcompat, "compat"); + defsymbol (&QnoBreak, "noBreak"); + defsymbol (&Qfraction, "fraction"); + defsymbol (&Qsuper, "super"); + defsymbol (&Qsub, "sub"); + defsymbol (&Qcircle, "circle"); + defsymbol (&Qsquare, "square"); + defsymbol (&Qwide, "wide"); + defsymbol (&Qnarrow, "narrow"); + defsymbol (&Qfont, "font"); + defsymbol (&Qucs, "ucs"); + defsymbol (&Qucs_bmp, "ucs-bmp"); + defsymbol (&Qlatin_viscii, "latin-viscii"); + defsymbol (&Qlatin_viscii_lower, "latin-viscii-lower"); + defsymbol (&Qlatin_viscii_upper, "latin-viscii-upper"); + defsymbol (&Qvietnamese_viscii_lower, "vietnamese-viscii-lower"); + defsymbol (&Qvietnamese_viscii_upper, "vietnamese-viscii-upper"); + defsymbol (&Qethiopic_ucs, "ethiopic-ucs"); + defsymbol (&Qhiragana_jisx0208, "hiragana-jisx0208"); + defsymbol (&Qkatakana_jisx0208, "katakana-jisx0208"); +#endif + defsymbol (&Qchinese_big5_1, "chinese-big5-1"); + defsymbol (&Qchinese_big5_2, "chinese-big5-2"); - defsymbol (&Qkorean_ksc5601, "korean-ksc5601"); defsymbol (&Qcomposite, "composite"); } void vars_of_mule_charset (void) { - int i, j, k; + int i, j; +#ifndef UTF2000 + int k; +#endif /* Table of charsets indexed by leading byte. */ for (i = 0; i < countof (charset_by_leading_byte); i++) charset_by_leading_byte[i] = Qnil; +#ifdef UTF2000 + /* Table of charsets indexed by type/final-byte. */ + for (i = 0; i < countof (charset_by_attributes); i++) + for (j = 0; j < countof (charset_by_attributes[0]); j++) + charset_by_attributes[i][j] = Qnil; +#else /* 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; +#endif +#ifdef UTF2000 + next_allocated_leading_byte = MIN_LEADING_BYTE_PRIVATE; +#else next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1; next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2; +#endif + +#ifndef UTF2000 + leading_code_private_11 = PRE_LEADING_BYTE_PRIVATE_1; + DEFVAR_INT ("leading-code-private-11", &leading_code_private_11 /* +Leading-code of private TYPE9N charset of column-width 1. +*/ ); + leading_code_private_11 = PRE_LEADING_BYTE_PRIVATE_1; +#endif + +#ifdef UTF2000 + Vutf_2000_version = build_string("0.12 (Kashiwara)"); + DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /* +Version number of UTF-2000. +*/ ); + + staticpro (&Vcharacter_attribute_table); + Vcharacter_attribute_table = make_char_code_table (Qnil); + + staticpro (&Vcharacter_composition_table); + Vcharacter_composition_table = make_char_code_table (Qnil); + + staticpro (&Vcharacter_variant_table); + Vcharacter_variant_table = make_char_code_table (Qnil); + + Vdefault_coded_charset_priority_list = Qnil; + DEFVAR_LISP ("default-coded-charset-priority-list", + &Vdefault_coded_charset_priority_list /* +Default order of preferred coded-character-sets. +*/ ); +#endif } 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. */ +#ifdef UTF2000 + Vcharset_ucs_bmp = + make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp, + CHARSET_TYPE_256X256, 1, 2, 0, + CHARSET_LEFT_TO_RIGHT, + build_string ("BMP"), + build_string ("BMP"), + build_string ("ISO/IEC 10646 Group 0 Plane 0 (BMP)"), + build_string ("\\(ISO10646.*-1\\|UNICODE[23]?-0\\)"), + Qnil, 0, 0xFFFF, 0, 0); +#else +# define MIN_CHAR_THAI 0 +# define MAX_CHAR_THAI 0 +# define MIN_CHAR_GREEK 0 +# define MAX_CHAR_GREEK 0 +# define MIN_CHAR_HEBREW 0 +# define MAX_CHAR_HEBREW 0 +# define MIN_CHAR_HALFWIDTH_KATAKANA 0 +# define MAX_CHAR_HALFWIDTH_KATAKANA 0 +# define MIN_CHAR_CYRILLIC 0 +# define MAX_CHAR_CYRILLIC 0 +#endif Vcharset_ascii = - make_charset (0, Qascii, LEADING_BYTE_ASCII, 1, + make_charset (LEADING_BYTE_ASCII, Qascii, 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\\)"), + Qnil, 0, 0x7F, 0, 0); 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, + CHARSET_TYPE_94, 1, 1, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("C1"), build_string ("Control characters"), - build_string ("")); + build_string ("Control characters 128-191"), + build_string (""), + Qnil, 0x80, 0x9F, 0, 0); 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, CHARSET_TYPE_96, 1, 1, 'A', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-1 (Latin-1)"), - build_string ("iso8859-1")); + build_string ("Latin-1"), + build_string ("ISO8859-1 (Latin-1)"), + build_string ("ISO8859-1 (Latin-1)"), + build_string ("iso8859-1"), + Qnil, 0xA0, 0xFF, 0, 32); 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, CHARSET_TYPE_96, 1, 1, 'B', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-2 (Latin-2)"), - build_string ("iso8859-2")); + build_string ("Latin-2"), + build_string ("ISO8859-2 (Latin-2)"), + build_string ("ISO8859-2 (Latin-2)"), + build_string ("iso8859-2"), + Qnil, 0, 0, 0, 32); 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, CHARSET_TYPE_96, 1, 1, 'C', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-3 (Latin-3)"), - build_string ("iso8859-3")); + build_string ("Latin-3"), + build_string ("ISO8859-3 (Latin-3)"), + build_string ("ISO8859-3 (Latin-3)"), + build_string ("iso8859-3"), + Qnil, 0, 0, 0, 32); 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, CHARSET_TYPE_96, 1, 1, 'D', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-4 (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', + build_string ("Latin-4"), + build_string ("ISO8859-4 (Latin-4)"), + build_string ("ISO8859-4 (Latin-4)"), + build_string ("iso8859-4"), + Qnil, 0, 0, 0, 32); + Vcharset_thai_tis620 = + make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, + 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"), + Qnil, MIN_CHAR_THAI, MAX_CHAR_THAI, 0, 32); 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, CHARSET_TYPE_96, 1, 1, 'F', CHARSET_LEFT_TO_RIGHT, - build_string ("ISO 8859-7 (Greek)"), - build_string ("iso8859-7")); + build_string ("ISO8859-7"), + build_string ("ISO8859-7 (Greek)"), + build_string ("ISO8859-7 (Greek)"), + build_string ("iso8859-7"), + Qnil, MIN_CHAR_GREEK, MAX_CHAR_GREEK, 0, 32); + Vcharset_arabic_iso8859_6 = + make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, + 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"), + Qnil, 0, 0, 0, 32); 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, CHARSET_TYPE_96, 1, 1, 'H', CHARSET_RIGHT_TO_LEFT, - build_string ("ISO 8859-8 (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 */ + build_string ("ISO8859-8"), + build_string ("ISO8859-8 (Hebrew)"), + build_string ("ISO8859-8 (Hebrew)"), + build_string ("iso8859-8"), + Qnil, MIN_CHAR_HEBREW, MAX_CHAR_HEBREW, 0, 32); Vcharset_katakana_jisx0201 = - make_charset (137, Qkatakana_jisx0201, - LEADING_BYTE_KATAKANA_JISX0201, 2, + make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, CHARSET_TYPE_94, 1, 1, 'I', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0201-Katakana"), - build_string ("jisx0201.1976")); + build_string ("JISX0201 Kana"), + build_string ("JISX0201.1976 (Japanese Kana)"), + build_string ("JISX0201.1976 Japanese Kana"), + build_string ("jisx0201\\.1976"), + Qnil, + MIN_CHAR_HALFWIDTH_KATAKANA, + MAX_CHAR_HALFWIDTH_KATAKANA, 0, 33); Vcharset_latin_jisx0201 = - make_charset (138, Qlatin_jisx0201, - LEADING_BYTE_LATIN_JISX0201, 2, + make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, CHARSET_TYPE_94, 1, 0, 'J', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0201-Latin"), - build_string ("jisx0201.1976")); + build_string ("JISX0201 Roman"), + build_string ("JISX0201.1976 (Japanese Roman)"), + build_string ("JISX0201.1976 Japanese Roman"), + build_string ("jisx0201\\.1976"), + Qnil, 0, 0, 0, 33); + Vcharset_cyrillic_iso8859_5 = + make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, + 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"), + Qnil, MIN_CHAR_CYRILLIC, MAX_CHAR_CYRILLIC, 0, 32); + Vcharset_latin_iso8859_9 = + make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, + 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"), + Qnil, 0, 0, 0, 32); 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, CHARSET_TYPE_94X94, 2, 0, '@', CHARSET_LEFT_TO_RIGHT, + build_string ("JIS X0208:1978"), + build_string ("JIS X0208:1978 (Japanese)"), build_string - ("JIS X0208-1978 (Japanese Kanji; Old Version)"), - build_string ("\\(jisx0208\\|jisc6226\\).19")); + ("JIS X0208:1978 Japanese Kanji (so called \"old JIS\")"), + build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"), + Qnil, 0, 0, 0, 33); + Vcharset_chinese_gb2312 = + make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, + CHARSET_TYPE_94X94, 2, 0, 'A', + CHARSET_LEFT_TO_RIGHT, + build_string ("GB2312"), + build_string ("GB2312)"), + build_string ("GB2312 Chinese simplified"), + build_string ("gb2312"), + Qnil, 0, 0, 0, 33); Vcharset_japanese_jisx0208 = - make_charset (146, Qjapanese_jisx0208, - LEADING_BYTE_JAPANESE_JISX0208, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, CHARSET_TYPE_94X94, 2, 0, 'B', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0208-1983 (Japanese Kanji)"), - build_string ("jisx0208.19\\(83\\|90\\)")); + build_string ("JISX0208"), + build_string ("JIS X0208:1983 (Japanese)"), + build_string ("JIS X0208:1983 Japanese Kanji"), + build_string ("jisx0208\\.1983"), + Qnil, 0, 0, 0, 33); + Vcharset_korean_ksc5601 = + make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, + 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"), + Qnil, 0, 0, 0, 33); Vcharset_japanese_jisx0212 = - make_charset (148, Qjapanese_jisx0212, - LEADING_BYTE_JAPANESE_JISX0212, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, CHARSET_TYPE_94X94, 2, 0, 'D', CHARSET_LEFT_TO_RIGHT, - build_string ("JIS X0212 (Japanese Supplement)"), - build_string ("jisx0212")); + build_string ("JISX0212"), + build_string ("JISX0212 (Japanese)"), + build_string ("JISX0212 Japanese Supplement"), + build_string ("jisx0212"), + Qnil, 0, 0, 0, 33); - /* 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 "$" 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, 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)"), - build_string (CHINESE_CNS_PLANE_RE("1"))); + ("CNS 11643 Plane 1 Chinese traditional"), + build_string (CHINESE_CNS_PLANE_RE("1")), + Qnil, 0, 0, 0, 33); 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, 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)"), - build_string (CHINESE_CNS_PLANE_RE("2"))); + ("CNS 11643 Plane 2 Chinese traditional"), + build_string (CHINESE_CNS_PLANE_RE("2")), + Qnil, 0, 0, 0, 33); +#ifdef UTF2000 + Vcharset_latin_viscii_lower = + make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower, + CHARSET_TYPE_96, 1, 1, '1', + CHARSET_LEFT_TO_RIGHT, + build_string ("VISCII lower"), + build_string ("VISCII lower (Vietnamese)"), + build_string ("VISCII lower (Vietnamese)"), + build_string ("MULEVISCII-LOWER"), + Qnil, 0, 0, 0, 32); + Vcharset_latin_viscii_upper = + make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper, + CHARSET_TYPE_96, 1, 1, '2', + CHARSET_LEFT_TO_RIGHT, + build_string ("VISCII upper"), + build_string ("VISCII upper (Vietnamese)"), + build_string ("VISCII upper (Vietnamese)"), + build_string ("MULEVISCII-UPPER"), + Qnil, 0, 0, 0, 32); + Vcharset_latin_viscii = + make_charset (LEADING_BYTE_LATIN_VISCII, Qlatin_viscii, + CHARSET_TYPE_256, 1, 2, 0, + CHARSET_LEFT_TO_RIGHT, + build_string ("VISCII"), + build_string ("VISCII 1.1 (Vietnamese)"), + build_string ("VISCII 1.1 (Vietnamese)"), + build_string ("VISCII1\\.1"), + Qnil, 0, 0, 0, 0); + Vcharset_ethiopic_ucs = + make_charset (LEADING_BYTE_ETHIOPIC_UCS, Qethiopic_ucs, + CHARSET_TYPE_256X256, 2, 2, 0, + CHARSET_LEFT_TO_RIGHT, + build_string ("Ethiopic (UCS)"), + build_string ("Ethiopic (UCS)"), + build_string ("Ethiopic of UCS"), + build_string ("Ethiopic-Unicode"), + Qnil, 0x1200, 0x137F, 0x1200, 0); + Vcharset_hiragana_jisx0208 = + make_charset (LEADING_BYTE_HIRAGANA_JISX0208, Qhiragana_jisx0208, + CHARSET_TYPE_94X94, 2, 0, 'B', + CHARSET_LEFT_TO_RIGHT, + build_string ("Hiragana"), + build_string ("Hiragana of JIS X0208"), + build_string ("Japanese Hiragana of JIS X0208"), + build_string ("jisx0208\\.19\\(78\\|83\\|90\\)"), + Qnil, MIN_CHAR_HIRAGANA, MAX_CHAR_HIRAGANA, + (0x24 - 33) * 94 + (0x21 - 33), 33); + Vcharset_katakana_jisx0208 = + make_charset (LEADING_BYTE_KATAKANA_JISX0208, Qkatakana_jisx0208, + CHARSET_TYPE_94X94, 2, 0, 'B', + CHARSET_LEFT_TO_RIGHT, + build_string ("Katakana"), + build_string ("Katakana of JIS X0208"), + build_string ("Japanese Katakana of JIS X0208"), + build_string ("jisx0208\\.19\\(78\\|83\\|90\\)"), + Qnil, MIN_CHAR_KATAKANA, MAX_CHAR_KATAKANA, + (0x25 - 33) * 94 + (0x21 - 33), 33); +#endif 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, 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)"), - build_string ("big5")); + ("Big5 Level-1 Chinese traditional"), + build_string ("big5"), + Qnil, 0, 0, 0, 33); 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, 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)"), - build_string ("big5")); + ("Big5 Level-2 Chinese traditional"), + build_string ("big5"), + Qnil, 0, 0, 0, 33); - 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. */ Vcharset_composite = - make_charset (-1, Qcomposite, LEADING_BYTE_COMPOSITE, 3, + make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, CHARSET_TYPE_96X96, 2, 0, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("Composite"), + build_string ("Composite characters"), build_string ("Composite characters"), build_string ("")); 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 */ }