X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fcharacter.h;h=94fa286b5a025c03d22f3d2deab6103cd1a76b26;hb=38a1a2ccbd34c86c059ff980013ae96748d816f8;hp=2c5aaa99190fd0ff8007ac803ce558d3d9552972;hpb=0a7e8462acb4861fe3fc2193319cec3552ea1c2f;p=chise%2Fxemacs-chise.git- diff --git a/src/character.h b/src/character.h index 2c5aaa9..94fa286 100644 --- a/src/character.h +++ b/src/character.h @@ -1,6 +1,5 @@ -/* Header for UCS-4 character representation. - Copyright (C) 1999 Electrotechnical Laboratory, JAPAN. - Licensed to the Free Software Foundation. +/* Header for character representation. + Copyright (C) 1999,2000 MORIOKA Tomohiko This file is part of XEmacs. @@ -19,634 +18,128 @@ 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. */ -/* Rewritten by MORIOKA Tomohiko . */ - #ifndef _XEMACS_CHARACTER_H #define _XEMACS_CHARACTER_H -#ifndef CHAR_IS_UCS4 -#include "mule-charset.h" -#else - -/************************************************************************/ -/* Definition of leading bytes */ -/************************************************************************/ - -typedef int Charset_ID; - -#define MIN_LEADING_BYTE 0x80 - -#define LEADING_BYTE_UCS_BMP 0x80 -#define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */ - - -#define CHARSET_ID_OFFSET_94 0x60 - -#define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') -#define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') - -/* ISO 646 IRV */ -#define LEADING_BYTE_ASCII (CHARSET_ID_OFFSET_94 + 'B') - -/* Right half of JIS X0201-1976 */ -#define LEADING_BYTE_KATAKANA_JISX0201 (CHARSET_ID_OFFSET_94 + 'I') - -/* Left half of JIS X0201-1976 */ -#define LEADING_BYTE_LATIN_JISX0201 (CHARSET_ID_OFFSET_94 + 'J') - - -#define CHARSET_ID_OFFSET_96 0x70 - -/* Right half of ISO 8859-1 */ -#define LEADING_BYTE_LATIN_ISO8859_1 (CHARSET_ID_OFFSET_96 + 'A') - -/* Right half of ISO 8859-2 */ -#define LEADING_BYTE_LATIN_ISO8859_2 (CHARSET_ID_OFFSET_96 + 'B') - -/* Right half of ISO 8859-3 */ -#define LEADING_BYTE_LATIN_ISO8859_3 (CHARSET_ID_OFFSET_96 + 'C') - -/* Right half of ISO 8859-4 */ -#define LEADING_BYTE_LATIN_ISO8859_4 (CHARSET_ID_OFFSET_96 + 'D') - -/* Right half of ISO 8859-7 */ -#define LEADING_BYTE_GREEK_ISO8859_7 (CHARSET_ID_OFFSET_96 + 'F') - -/* Right half of ISO 8859-6 */ -#define LEADING_BYTE_ARABIC_ISO8859_6 (CHARSET_ID_OFFSET_96 + 'G') - -/* Right half of ISO 8859-8 */ -#define LEADING_BYTE_HEBREW_ISO8859_8 (CHARSET_ID_OFFSET_96 + 'H') - -/* Right half of ISO 8859-5 */ -#define LEADING_BYTE_CYRILLIC_ISO8859_5 (CHARSET_ID_OFFSET_96 + 'L') - -/* Right half of ISO 8859-9 */ -#define LEADING_BYTE_LATIN_ISO8859_9 (CHARSET_ID_OFFSET_96 + 'M') - -/* TIS620-2533 */ -#define LEADING_BYTE_THAI_TIS620 (CHARSET_ID_OFFSET_96 + 'T') - - -#define MIN_LEADING_BYTE_PRIVATE_1 0xD0 -#define MAX_LEADING_BYTE_PRIVATE_1 0xDF - - -#define CHARSET_ID_OFFSET_94x94 0xB0 - -/* Big5 Level 1 */ -#define LEADING_BYTE_CHINESE_BIG5_1 ('0' + CHARSET_ID_OFFSET_94x94) - -/* Big5 Level 2 */ -#define LEADING_BYTE_CHINESE_BIG5_2 ('1' + CHARSET_ID_OFFSET_94x94) - -#define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) -#define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) - -/* Japanese JIS X0208-1978 */ -#define LEADING_BYTE_JAPANESE_JISX0208_1978 \ - ('@' + CHARSET_ID_OFFSET_94x94) - -/* Chinese Hanzi GB2312-1980 */ -#define LEADING_BYTE_CHINESE_GB2312 ('A' + CHARSET_ID_OFFSET_94x94) - -/* Japanese JIS X0208-1983 */ -#define LEADING_BYTE_JAPANESE_JISX0208 ('B' + CHARSET_ID_OFFSET_94x94) - -/* Hangul KS C5601-1987 */ -#define LEADING_BYTE_KOREAN_KSC5601 ('C' + CHARSET_ID_OFFSET_94x94) - -/* Japanese JIS X0212-1990 */ -#define LEADING_BYTE_JAPANESE_JISX0212 ('D' + CHARSET_ID_OFFSET_94x94) - -/* CCITT Extended GB */ -#define LEADING_BYTE_CHINESE_CCITT_GB ('E' + CHARSET_ID_OFFSET_94x94) - -/* Chinese CNS11643 Set 1 */ -#define LEADING_BYTE_CHINESE_CNS11643_1 ('G' + CHARSET_ID_OFFSET_94x94) - -/* Chinese CNS11643 Set 2 */ -#define LEADING_BYTE_CHINESE_CNS11643_2 ('H' + CHARSET_ID_OFFSET_94x94) - -/* Chinese CNS11643 Set 3 */ -#define LEADING_BYTE_CHINESE_CNS11643_3 ('I' + CHARSET_ID_OFFSET_94x94) +#if !defined(MULE) /* unibyte representation */ +# include "char-1byte.h" +#elif !defined(CHAR_IS_UCS4) /* leading-byte representation */ +# include "char-lb.h" +#else /* CHAR_IS_UCS4 */ +# include "char-ucs.h" +#endif /* CHAR_IS_UCS4 */ -/* Chinese CNS11643 Set 4 */ -#define LEADING_BYTE_CHINESE_CNS11643_4 ('J' + CHARSET_ID_OFFSET_94x94) +/********************************/ +/* */ +/* Interface for characters */ +/* */ +/********************************/ +/* + valid_char_p (ch): + Return whether the given Emchar is valid. -/* Chinese CNS11643 Set 5 */ -#define LEADING_BYTE_CHINESE_CNS11643_5 ('K' + CHARSET_ID_OFFSET_94x94) + CHARP (ch): + Return whether the given Lisp_Object is a character. -/* Chinese CNS11643 Set 6 */ -#define LEADING_BYTE_CHINESE_CNS11643_6 ('L' + CHARSET_ID_OFFSET_94x94) + CHECK_CHAR_COERCE_INT (ch): + Signal an error if CH is not a valid character or integer + Lisp_Object. + If CH is an integer Lisp_Object, convert it to a character + Lisp_Object, but merely by repackaging, without performing + tests for char validity. -/* Chinese CNS11643 Set 7 */ -#define LEADING_BYTE_CHINESE_CNS11643_7 ('M' + CHARSET_ID_OFFSET_94x94) +Functions/macros when MULE is defined: -/* DPRK Hangul KPS 9566-1997 */ -#define LEADING_BYTE_KOREAN_KPS9566 ('N' + CHARSET_ID_OFFSET_94x94) + CHAR_ASCII_P (ch): + Return whether the given Emchar is ASCII. -#define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978 -#define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_KOREAN_KPS9566 + MAKE_CHAR (CHARSET, B1, B2): + Return a character whose coded-charset is CHARSET and + position-codes are B1 and B2. 1 byte character ignores B2. -#define NUM_LEADING_BYTES 256 + BREAKUP_CHAR (ch, charset, B1, B2): + Break up the given Emchar, and store found coded-charset and + position-codes to CHARSET, B1 and B2. - -/************************************************************************/ -/* Operations on individual bytes */ -/* of any format */ -/************************************************************************/ + CHAR_CHARSET (CH): + Return coded-charset object of Emchar CH. -/* Argument `c' should be (unsigned int) or (unsigned char). */ -/* Note that SP and DEL are not included. */ + CHAR_LEADING_BYTE (CH): + Return Charset-ID of Emchar CH. +*/ -#define BYTE_ASCII_P(c) ((c) < 0x80) -#define BYTE_C0_P(c) ((c) < 0x20) -/* Do some forced casting just to make *sure* things are gotten right. */ -#define BYTE_C1_P(c) ((unsigned int) ((unsigned int) (c) - 0x80) < 0x20) +#define CHAR_INTP(x) (INTP (x) && valid_char_p (XINT (x))) - -/************************************************************************/ -/* Information about a particular character set */ -/************************************************************************/ +#define CHAR_OR_CHAR_INTP(x) (CHARP (x) || CHAR_INTP (x)) -struct Lisp_Charset +INLINE_HEADER Emchar XCHAR_OR_CHAR_INT (Lisp_Object obj); +INLINE_HEADER Emchar +XCHAR_OR_CHAR_INT (Lisp_Object obj) { - struct lcrecord_header header; - - int id; - Lisp_Object name; - Lisp_Object doc_string, registry, short_name, long_name; - - Lisp_Object reverse_direction_charset; - - Lisp_Object ccl_program; - - /* Final byte of this character set in ISO2022 designating escape sequence */ - Bufbyte final; - - /* Number of bytes (1 - 4) required in the internal representation - for characters in this character set. This is *not* the - same as the dimension of the character set). */ - unsigned int rep_bytes; - - /* Number of columns a character in this charset takes up, on TTY - devices. Not used for X devices. */ - unsigned int columns; - - /* Direction of this character set */ - unsigned int direction; - - /* Type of this character set (94, 96, 94x94, 96x96) */ - unsigned int type; - - /* Number of bytes used in encoding of this character set (1 or 2) */ - unsigned int dimension; - - /* Number of chars in each dimension (usually 94 or 96) */ - unsigned int chars; - - /* Which half of font to be used to display this character set */ - unsigned int graphic; -}; - -DECLARE_LRECORD (charset, struct Lisp_Charset); -#define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset) -#define XSETCHARSET(x, p) XSETRECORD (x, p, charset) -#define CHARSETP(x) RECORDP (x, charset) -#define GC_CHARSETP(x) GC_RECORDP (x, charset) -#define CHECK_CHARSET(x) CHECK_RECORD (x, charset) -#define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset) - -#define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */ -#define CHARSET_TYPE_96 1 /* This charset includes 96 characters. */ -#define CHARSET_TYPE_94X94 2 /* This charset includes 94x94 characters. */ -#define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */ -#define CHARSET_TYPE_128X128 4 /* This charset includes 128x128 characters. */ -#define CHARSET_TYPE_256X256 5 /* This charset includes 256x256 characters. */ - -#define CHARSET_LEFT_TO_RIGHT 0 -#define CHARSET_RIGHT_TO_LEFT 1 - -/* Leading byte and id have been regrouped. -- OG */ -#define CHARSET_ID(cs) ((cs)->id) -#define CHARSET_LEADING_BYTE(cs) ((Bufbyte)(CHARSET_ID(cs))) -#define CHARSET_NAME(cs) ((cs)->name) -#define CHARSET_SHORT_NAME(cs) ((cs)->short_name) -#define CHARSET_LONG_NAME(cs) ((cs)->long_name) -#define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes) -#define CHARSET_COLUMNS(cs) ((cs)->columns) -#define CHARSET_GRAPHIC(cs) ((cs)->graphic) -#define CHARSET_TYPE(cs) ((cs)->type) -#define CHARSET_DIRECTION(cs) ((cs)->direction) -#define CHARSET_FINAL(cs) ((cs)->final) -#define CHARSET_DOC_STRING(cs) ((cs)->doc_string) -#define CHARSET_REGISTRY(cs) ((cs)->registry) -#define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program) -#define CHARSET_DIMENSION(cs) ((cs)->dimension) -#define CHARSET_CHARS(cs) ((cs)->chars) -#define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset) - + return CHARP (obj) ? XCHAR (obj) : XINT (obj); +} -#define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs)) -#define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs)) -#define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs)) -#define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs)) -#define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs)) -#define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (XCHARSET (cs)) -#define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs)) -#define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs)) -#define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs)) -#define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs)) -#define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs)) -#define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs)) -#define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs)) -#define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs)) -#define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs)) -#define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs)) -#define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \ - CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs)) +#define CHECK_CHAR_COERCE_INT(x) do { \ + if (CHARP (x)) \ + ; \ + else if (CHAR_INTP (x)) \ + x = make_char (XINT (x)); \ + else \ + x = wrong_type_argument (Qcharacterp, x); \ +} while (0) -/* Table of charsets indexed by (leading byte - 128). */ -extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES]; -/* Table of charsets indexed by type/final-byte. */ -extern Lisp_Object charset_by_attributes[4][128]; +#define CHARC_CHARSET(cc) ((cc).charset) +#define CHARC_CHARSET_ID(cc) XCHARSET_ID (CHARC_CHARSET (cc)) +#define CHARC_CODE_POINT(cc) ((cc).code_point) +#define CHARC_COLUMNS(cc) CHARSET_COLUMNS (XCHARSET (CHARC_CHARSET (cc))) -#ifdef ERROR_CHECK_TYPECHECK -/* int not Bufbyte even though that is the actual type of a leading byte. - This way, out-ot-range values will get caught rather than automatically - truncated. */ -INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb); -INLINE Lisp_Object -CHARSET_BY_LEADING_BYTE (Charset_ID lb) +INLINE_HEADER Emchar CHARC_TO_CHAR (Charc cc); +INLINE_HEADER Emchar +CHARC_TO_CHAR (Charc cc) { - assert (lb >= MIN_LEADING_BYTE && - lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES)); - return charset_by_leading_byte[lb - MIN_LEADING_BYTE]; + return DECODE_CHAR (cc.charset, cc.code_point); } -#else - -#define CHARSET_BY_LEADING_BYTE(lb) \ - (charset_by_leading_byte[(lb) - MIN_LEADING_BYTE]) - -#endif - -#define CHARSET_BY_ATTRIBUTES(type, final, dir) \ - (charset_by_attributes[type][final]) - -INLINE int REP_BYTES_BY_FIRST_BYTE (int fb); -INLINE int -REP_BYTES_BY_FIRST_BYTE (int fb) +INLINE_HEADER int CHARC_EQ (Charc cc1, Charc cc2); +INLINE_HEADER int +CHARC_EQ (Charc cc1, Charc cc2) { - if ( fb < 0xc0 ) - return 1; - else if ( fb < 0xe0 ) - return 2; - else if ( fb < 0xf0 ) - return 3; - else if ( fb < 0xf8 ) - return 4; - else if ( fb < 0xfc ) - return 5; - else - return 6; + return EQ (cc1.charset, cc2.charset) && (cc1.code_point == cc2.code_point); } - -/************************************************************************/ -/* Dealing with characters */ -/************************************************************************/ - -/* Is this character represented by more than one byte in a string? */ - -#define CHAR_MULTIBYTE_P(c) ((c) >= 0x80) - -#define CHAR_ASCII_P(c) (!CHAR_MULTIBYTE_P (c)) - -/* The bit fields of character are divided into 3 parts: - FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */ - -#define CHAR_FIELD1_MASK (0x7F << 14) -#define CHAR_FIELD2_MASK (0x7F << 7) -#define CHAR_FIELD3_MASK 0x7F - -#define MIN_CHAR_GREEK 0x0370 -#define MAX_CHAR_GREEK 0x03CF - -#define MIN_CHAR_CYRILLIC 0x0400 -#define MAX_CHAR_CYRILLIC 0x045F - -#define MIN_CHAR_HEBREW 0x0590 -#define MAX_CHAR_HEBREW 0x05EF - -#define MIN_CHAR_THAI 0x0E00 -#define MAX_CHAR_THAI 0x0E5F - -#define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60 -#define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F - -#define MIN_CHAR_94 0xE90940 -#define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1) -#define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80) -#define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1) - -#define MIN_CHAR_94x94 0xE9F6C0 -#define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1) -#define MIN_CHAR_96x96 0xF4C000 -#define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1) - -/* Macros to access each field of a character code of C. */ - -#define CHAR_FIELD1(c) (((c) & CHAR_FIELD1_MASK) >> 14) -#define CHAR_FIELD2_INTERNAL(c) (((c) & CHAR_FIELD2_MASK) >> 7) -#define CHAR_FIELD3_INTERNAL(c) ((c) & CHAR_FIELD3_MASK) - -/* Field 1, if non-zero, usually holds a leading byte for a - dimension-2 charset. Field 2, if non-zero, usually holds a leading - byte for a dimension-1 charset. */ - -/* Converting between field values and leading bytes. */ - -#define FIELD1_TO_PRIVATE_LEADING_BYTE CHARSET_ID_OFFSET_94x94 -#define FIELD1_TO_OFFICIAL_LEADING_BYTE CHARSET_ID_OFFSET_94x94 -#define FIELD2_TO_PRIVATE_LEADING_BYTE (MIN_LEADING_BYTE_PRIVATE_1 - 32) -#define FIELD2_TO_OFFICIAL_LEADING_BYTE LEADING_BYTE_ASCII - -/* Minimum and maximum allowed values for the fields. */ - -#define MIN_CHAR_FIELD1_OFFICIAL \ - (MIN_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE) -#define MAX_CHAR_FIELD1_OFFICIAL \ - (MAX_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE) - -#define MIN_CHAR_FIELD2_PRIVATE \ - (MIN_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE) -#define MAX_CHAR_FIELD2_PRIVATE \ - (MAX_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE) - -#define MIN_CHAR_FIELD1_PRIVATE \ - (MIN_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE) -#define MAX_CHAR_FIELD1_PRIVATE \ - (MAX_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE) - -/* Minimum character code of each character. */ - -#define MULE_CHAR_PRIVATE_OFFSET (0xe0 << 16) - -#define MIN_CHAR_PRIVATE_TYPE9N \ - (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_PRIVATE << 7)) -#define MAX_CHAR_PRIVATE_TYPE9N \ - (MULE_CHAR_PRIVATE_OFFSET | (MAX_CHAR_FIELD2_PRIVATE << 7) | 0x7f) -#define MIN_CHAR_PRIVATE_TYPE9NX9N \ - (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_PRIVATE << 14)) -#define MIN_CHAR_OFFICIAL_TYPE9NX9N \ - (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_OFFICIAL << 14)) -#define MIN_CHAR_COMPOSITION \ - (MULE_CHAR_PRIVATE_OFFSET | (0x7f << 14)) - -/* Return a character whose charset is CHARSET and position-codes - are C1 and C2. TYPE9N character ignores C2. - - NOTE: This takes advantage of the fact that - FIELD2_TO_OFFICIAL_LEADING_BYTE and - FIELD2_TO_PRIVATE_LEADING_BYTE are the same. - */ - -INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2); -INLINE Emchar -MAKE_CHAR (Lisp_Object charset, int c1, int c2) +INLINE_HEADER int CHARC_ASCII_EQ (Charc cc, int ch); +INLINE_HEADER int +CHARC_ASCII_EQ (Charc cc, int ch) { - if (EQ (charset, Vcharset_ascii)) - return c1; - else if (EQ (charset, Vcharset_control_1)) - return c1 | 0x80; - else if (EQ (charset, Vcharset_latin_iso8859_1)) - return c1 | 0x80; - else if (EQ (charset, Vcharset_greek_iso8859_7)) - return c1 + MIN_CHAR_GREEK - 0x20; - else if (EQ (charset, Vcharset_cyrillic_iso8859_5)) - return c1 + MIN_CHAR_CYRILLIC - 0x20; - else if (EQ (charset, Vcharset_hebrew_iso8859_8)) - return c1 + MIN_CHAR_HEBREW - 0x20; - else if (EQ (charset, Vcharset_thai_tis620)) - return c1 + MIN_CHAR_THAI - 0x20; - else if (EQ (charset, Vcharset_katakana_jisx0201)) - if (c1 < 0x60) - return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20; - else - return 32; - else if (XCHARSET_DIMENSION (charset) == 1) - { - switch (XCHARSET_CHARS (charset)) - { - case 94: - return MIN_CHAR_94 - + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33); - case 96: - return MIN_CHAR_96 - + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32); - default: - abort (); - } - } - else - { - switch (XCHARSET_CHARS (charset)) - { - case 94: - return MIN_CHAR_94x94 - + (XCHARSET_FINAL (charset) - '0') * 94 * 94 - + (c1 - 33) * 94 + (c2 - 33); - case 96: - return MIN_CHAR_96x96 - + (XCHARSET_FINAL (charset) - '0') * 96 * 96 - + (c1 - 32) * 96 + (c2 - 32); - default: - abort (); - } - } + return EQ (cc.charset, Vcharset_ascii) && (cc.code_point == ch); } -extern Charset_ID latin_a_char_to_charset[128]; -extern unsigned char latin_a_char_to_byte1[128]; -extern unsigned char latin_a_char_to_byte2[128]; - -INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2); -INLINE void -breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2) +INLINE_HEADER int CHARC_IS_SPACE (Charc cc); +INLINE_HEADER int +CHARC_IS_SPACE (Charc cc) { - if (CHAR_ASCII_P (c)) - { - *charset = Vcharset_ascii; - *c1 = c; - *c2 = 0; - } - else if (c < 0xA0) - { - *charset = Vcharset_control_1; - *c1 = CHAR_FIELD3_INTERNAL (c); - *c2 = 0; - } - else if (c <= 0xff) - { - *charset = Vcharset_latin_iso8859_1; - *c1 = CHAR_FIELD3_INTERNAL (c); - *c2 = 0; - } - else if (c <= 0x17f) - { - *charset - = CHARSET_BY_LEADING_BYTE (latin_a_char_to_charset[c - 0x100]); - *c1 = latin_a_char_to_byte1[c - 0x100]; - *c2 = latin_a_char_to_byte2[c - 0x100]; - } - else if (c < MIN_CHAR_GREEK) - { - printf("not break up u+%x", c); - abort (); - } - else if (c <= MAX_CHAR_GREEK) - { - *charset = Vcharset_greek_iso8859_7; - *c1 = c - MIN_CHAR_GREEK + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_CYRILLIC) - { - printf("not break up u+%x", c); - abort (); - } - else if (c <= MAX_CHAR_CYRILLIC) - { - *charset = Vcharset_cyrillic_iso8859_5; - *c1 = c - MIN_CHAR_CYRILLIC + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_HEBREW) - { - printf("not break up u+%x", c); - abort (); - } - else if (c <= MAX_CHAR_HEBREW) - { - *charset = Vcharset_hebrew_iso8859_8; - *c1 = c - MIN_CHAR_HEBREW + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_THAI) - { - printf("not break up u+%x", c); - abort (); - } - else if (c <= MAX_CHAR_THAI) - { - *charset = Vcharset_thai_tis620; - *c1 = c - MIN_CHAR_THAI + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_HALFWIDTH_KATAKANA) - { - printf("not break up u+%x", c); - abort (); - } - else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA) - { - *charset = Vcharset_katakana_jisx0201; - *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20; - *c2 = 0; - } - else if (c <= MAX_CHAR_94) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94, - ((c - MIN_CHAR_94) / 94) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = ((c - MIN_CHAR_94) % 94) + 33; - *c2 = 0; - } - else if (c <= MAX_CHAR_96) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96, - ((c - MIN_CHAR_96) / 96) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = ((c - MIN_CHAR_96) % 96) + 32; - *c2 = 0; - } - else if (c <= MAX_CHAR_94x94) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94, - ((c - MIN_CHAR_94x94) / (94 * 94)) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = (((c - MIN_CHAR_94x94) / 94) % 94) + 33; - *c2 = ((c - MIN_CHAR_94x94) % 94) + 33; - } - else if (c <= MAX_CHAR_96x96) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96X96, - ((c - MIN_CHAR_96x96) / (96 * 96)) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = (((c - MIN_CHAR_96x96) / 96) % 96) + 32; - *c2 = ((c - MIN_CHAR_96x96) % 96) + 32; - } - else - { - printf("u+%x", c); - abort(); - } + return (EQ (cc.charset, Vcharset_ascii) || + EQ (cc.charset, Vcharset_control_1) || + EQ (cc.charset, Vcharset_latin_iso8859_1)) + && isspace (cc.code_point); } -#define BREAKUP_CHAR(c, charset, c1, c2) \ - breakup_char_1 (c, &(charset), &(c1), &(c2)) - -INLINE Lisp_Object CHAR_CHARSET (Emchar c); -INLINE Lisp_Object -CHAR_CHARSET (Emchar c) +INLINE_HEADER Charc ASCII_TO_CHARC (int ch); +INLINE_HEADER Charc +ASCII_TO_CHARC (int ch) { - Lisp_Object charset; - int c1, c2; + Charc cc; - BREAKUP_CHAR(c, charset, c1, c2); - return charset; + cc.charset = Vcharset_ascii; + cc.code_point = ch; + return cc; } -#define CHAR_LEADING_BYTE(c) (XCHARSET_LEADING_BYTE(CHAR_CHARSET(c))) - - -#ifdef ENABLE_COMPOSITE_CHARS -/************************************************************************/ -/* Composite characters */ -/************************************************************************/ - -Emchar lookup_composite_char (Bufbyte *str, int len); -Lisp_Object composite_char_string (Emchar ch); -#endif /* ENABLE_COMPOSITE_CHARS */ - -/************************************************************************/ -/* Exported functions */ -/************************************************************************/ - -EXFUN (Ffind_charset, 1); -EXFUN (Fget_charset, 1); - -extern Lisp_Object Vcharset_chinese_big5_1; -extern Lisp_Object Vcharset_chinese_big5_2; -extern Lisp_Object Vcharset_japanese_jisx0208; -extern Lisp_Object Vcharset_japanese_jisx0212; - -Emchar Lstream_get_emchar_1 (Lstream *stream, int first_char); -int Lstream_fput_emchar (Lstream *stream, Emchar ch); -void Lstream_funget_emchar (Lstream *stream, Emchar ch); - -int copy_internal_to_external (CONST Bufbyte *internal, Bytecount len, - unsigned char *external); -Bytecount copy_external_to_internal (CONST unsigned char *external, - int len, Bufbyte *internal); +typedef struct +{ + Dynarr_declare (Charc); +} Charc_dynarr; -#endif /* CHAR_IS_UCS4 */ #endif /* _XEMACS_CHARACTER_H */