X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fcharacter.h;h=94fa286b5a025c03d22f3d2deab6103cd1a76b26;hb=38a1a2ccbd34c86c059ff980013ae96748d816f8;hp=a396638815abd861f21bf2825ca59e4babd66843;hpb=04d223198858890a78a0a040f57268d179a945ba;p=chise%2Fxemacs-chise.git- diff --git a/src/character.h b/src/character.h index a396638..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. @@ -19,594 +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 -/************************************************************************/ -/* Definition of leading bytes */ -/************************************************************************/ - -#define MIN_LEADING_BYTE 0x80 -/* These need special treatment in a string and/or character */ -#define LEADING_BYTE_ASCII 0x8E /* Omitted in a buffer */ -#ifdef ENABLE_COMPOSITE_CHARS -#endif -#define LEADING_BYTE_COMPOSITE 0x80 /* for a composite character */ -#define LEADING_BYTE_CONTROL_1 0x8F /* represent normal 80-9F */ - -/** The following are for 1-byte characters in an official charset. **/ - -#define LEADING_BYTE_LATIN_ISO8859_1 0x81 /* Right half of ISO 8859-1 */ -#define LEADING_BYTE_LATIN_ISO8859_2 0x82 /* Right half of ISO 8859-2 */ -#define LEADING_BYTE_LATIN_ISO8859_3 0x83 /* Right half of ISO 8859-3 */ -#define LEADING_BYTE_LATIN_ISO8859_4 0x84 /* Right half of ISO 8859-4 */ -#define LEADING_BYTE_THAI_TIS620 0x85 /* TIS620-2533 */ -#define LEADING_BYTE_GREEK_ISO8859_7 0x86 /* Right half of ISO 8859-7 */ -#define LEADING_BYTE_ARABIC_ISO8859_6 0x87 /* Right half of ISO 8859-6 */ -#define LEADING_BYTE_HEBREW_ISO8859_8 0x88 /* Right half of ISO 8859-8 */ -#define LEADING_BYTE_KATAKANA_JISX0201 0x89 /* Right half of JIS X0201-1976 */ -#define LEADING_BYTE_LATIN_JISX0201 0x8A /* Left half of JIS X0201-1976 */ -#define LEADING_BYTE_CYRILLIC_ISO8859_5 0x8C /* Right half of ISO 8859-5 */ -#define LEADING_BYTE_LATIN_ISO8859_9 0x8D /* Right half of ISO 8859-9 */ - -#define MIN_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_1 -#define MAX_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_9 - -/** The following are for 2-byte characters in an official charset. **/ - -#define LEADING_BYTE_JAPANESE_JISX0208_1978 0x90/* Japanese JIS X0208-1978 */ -#define LEADING_BYTE_CHINESE_GB2312 0x91 /* Chinese Hanzi GB2312-1980 */ -#define LEADING_BYTE_JAPANESE_JISX0208 0x92 /* Japanese JIS X0208-1983 */ -#define LEADING_BYTE_KOREAN_KSC5601 0x93 /* Hangul KS C5601-1987 */ -#define LEADING_BYTE_JAPANESE_JISX0212 0x94 /* Japanese JIS X0212-1990 */ -#define LEADING_BYTE_CHINESE_CCITT_GB 0x95 /* CCITT Extended GB */ -#define LEADING_BYTE_CHINESE_BIG5_1 0x96 /* Big5 Level 1 */ -#define LEADING_BYTE_CHINESE_CNS11643_1 0x97 /* Chinese CNS11643 Set 1 */ -#define LEADING_BYTE_CHINESE_CNS11643_2 0x98 /* Chinese CNS11643 Set 2 */ -#define LEADING_BYTE_CHINESE_CNS11643_3 0x99 /* Chinese CNS11643 Set 3 */ -#define LEADING_BYTE_CHINESE_CNS11643_4 0x9A /* Chinese CNS11643 Set 4 */ -#define LEADING_BYTE_CHINESE_CNS11643_5 0x9B /* Chinese CNS11643 Set 5 */ -#define LEADING_BYTE_CHINESE_CNS11643_6 0x9C /* Chinese CNS11643 Set 6 */ -#define LEADING_BYTE_CHINESE_CNS11643_7 0x9D /* Chinese CNS11643 Set 7 */ -#define LEADING_BYTE_CHINESE_BIG5_2 0x9D /* Big5 Level 2 */ -#define LEADING_BYTE_KOREAN_KPS9566 0x9E /* DPRK Hangul KPS 9566-1997 */ - -#define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978 -#define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_CHINESE_BIG5_2 - -/** The following are for 1- and 2-byte characters in a private charset. **/ - -#define PRE_LEADING_BYTE_PRIVATE_1 0x9E /* 1-byte char-set */ -#define PRE_LEADING_BYTE_PRIVATE_2 0x9F /* 2-byte char-set */ - -#define MIN_LEADING_BYTE_PRIVATE_1 0xA0 -#define MAX_LEADING_BYTE_PRIVATE_1 0xEF -#define MIN_LEADING_BYTE_PRIVATE_2 0xF0 -#define MAX_LEADING_BYTE_PRIVATE_2 0xFF - -#define NUM_LEADING_BYTES 128 - - -/************************************************************************/ -/* Operations on leading bytes */ -/************************************************************************/ - -/* Is this leading byte for a private charset? */ - -#define LEADING_BYTE_PRIVATE_P(lb) ((lb) >= MIN_LEADING_BYTE_PRIVATE_1) - -/* Is this a prefix for a private leading byte? */ - -INLINE int LEADING_BYTE_PREFIX_P (unsigned char lb); -INLINE int -LEADING_BYTE_PREFIX_P (unsigned char lb) -{ - return (lb == PRE_LEADING_BYTE_PRIVATE_1 || - lb == PRE_LEADING_BYTE_PRIVATE_2); -} - -/* Given a private leading byte, return the leading byte prefix stored - in a string */ - -#define PRIVATE_LEADING_BYTE_PREFIX(lb) \ - ((lb) < MIN_LEADING_BYTE_PRIVATE_2 ? \ - PRE_LEADING_BYTE_PRIVATE_1 : \ - PRE_LEADING_BYTE_PRIVATE_2) - - -/************************************************************************/ -/* Operations on individual bytes */ -/* of any format */ -/************************************************************************/ - -/* Argument `c' should be (unsigned int) or (unsigned char). */ -/* Note that SP and DEL are not included. */ - -#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) - - -/************************************************************************/ -/* Operations on individual bytes */ -/* in a Mule-formatted string */ -/************************************************************************/ - -/* Does this byte represent the first byte of a character? */ - -#ifdef UTF2000 -INLINE int -BUFBYTE_FIRST_BYTE_P(Bufbyte c) -{ - return (c <= 0x7f) || (0xc0 <= c); -} -#else -#define BUFBYTE_FIRST_BYTE_P(c) ((c) < 0xA0) -#endif - -/* Does this byte represent the first byte of a multi-byte character? */ - -#define BUFBYTE_LEADING_BYTE_P(c) BYTE_C1_P (c) - - -/************************************************************************/ -/* Information about a particular character set */ -/************************************************************************/ - -struct Lisp_Charset -{ - 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. */ +#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 */ -#define CHARSET_LEFT_TO_RIGHT 0 -#define CHARSET_RIGHT_TO_LEFT 1 +/********************************/ +/* */ +/* Interface for characters */ +/* */ +/********************************/ +/* + valid_char_p (ch): + Return whether the given Emchar is valid. -/* 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) + CHARP (ch): + Return whether the given Lisp_Object is a character. + 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. -#define CHARSET_PRIVATE_P(cs) LEADING_BYTE_PRIVATE_P (CHARSET_LEADING_BYTE (cs)) +Functions/macros when MULE is defined: -#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_PRIVATE_P(cs) CHARSET_PRIVATE_P (XCHARSET (cs)) -#define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \ - CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs)) + CHAR_ASCII_P (ch): + Return whether the given Emchar is ASCII. -/* Table of charsets indexed by (leading byte - 128). */ -extern Lisp_Object charset_by_leading_byte[128]; + 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. -/* Table of charsets indexed by type/final-byte/direction. */ -extern Lisp_Object charset_by_attributes[4][128][2]; + BREAKUP_CHAR (ch, charset, B1, B2): + Break up the given Emchar, and store found coded-charset and + position-codes to CHARSET, B1 and B2. -/* Table of number of bytes in the string representation of a character - indexed by the first byte of that representation. + CHAR_CHARSET (CH): + Return coded-charset object of Emchar CH. - This value can be derived other ways -- e.g. something like + CHAR_LEADING_BYTE (CH): + Return Charset-ID of Emchar CH. +*/ - (BYTE_ASCII_P (first_byte) ? 1 : - XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (first_byte))) +#define CHAR_INTP(x) (INTP (x) && valid_char_p (XINT (x))) - but it's faster this way. */ -extern Bytecount rep_bytes_by_first_byte[0xA0]; +#define CHAR_OR_CHAR_INTP(x) (CHARP (x) || CHAR_INTP (x)) -#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 (int lb); -INLINE Lisp_Object -CHARSET_BY_LEADING_BYTE (int lb) +INLINE_HEADER Emchar XCHAR_OR_CHAR_INT (Lisp_Object obj); +INLINE_HEADER Emchar +XCHAR_OR_CHAR_INT (Lisp_Object obj) { - assert (lb >= 0x80 && lb <= 0xFF); - return charset_by_leading_byte[lb - 128]; + return CHARP (obj) ? XCHAR (obj) : XINT (obj); } -#else +#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) -#define CHARSET_BY_LEADING_BYTE(lb) (charset_by_leading_byte[(lb) - 128]) -#endif +#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))) -#define CHARSET_BY_ATTRIBUTES(type, final, dir) \ - (charset_by_attributes[type][final][dir]) - -#ifdef UTF2000 -INLINE int REP_BYTES_BY_FIRST_BYTE (int fb); -INLINE int -REP_BYTES_BY_FIRST_BYTE (int fb) +INLINE_HEADER Emchar CHARC_TO_CHAR (Charc cc); +INLINE_HEADER Emchar +CHARC_TO_CHAR (Charc cc) { - if ( fb >= 0xfc ) - return 6; - else if ( fb >= 0xf8 ) - return 5; - else if ( fb >= 0xf0 ) - return 4; - else if ( fb >= 0xe0 ) - return 3; - else if ( fb >= 0xc0 ) - return 2; - else - return 1; + return DECODE_CHAR (cc.charset, cc.code_point); } -#else /* MULE */ -#ifdef ERROR_CHECK_TYPECHECK -/* Number of bytes in the string representation of a character */ -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) { - assert (fb >= 0 && fb < 0xA0); - return rep_bytes_by_first_byte[fb]; + return EQ (cc1.charset, cc2.charset) && (cc1.code_point == cc2.code_point); } -#else -#define REP_BYTES_BY_FIRST_BYTE(fb) (rep_bytes_by_first_byte[fb]) -#endif -#endif /* end MULE */ - - -/************************************************************************/ -/* 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 - -/* 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 FIELD2_TO_OFFICIAL_LEADING_BYTE 0x80 -#define FIELD2_TO_PRIVATE_LEADING_BYTE 0x80 - -#define FIELD1_TO_PRIVATE_LEADING_BYTE 0xc0 -#define FIELD1_TO_OFFICIAL_LEADING_BYTE 0x50 - -INLINE Emchar -CHAR_FIELD2 (Emchar c) +INLINE_HEADER int CHARC_ASCII_EQ (Charc cc, int ch); +INLINE_HEADER int +CHARC_ASCII_EQ (Charc cc, int ch) { - if( (MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK) ) - return LEADING_BYTE_GREEK_ISO8859_7 - - FIELD2_TO_OFFICIAL_LEADING_BYTE; - else if( (MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC) ) - return LEADING_BYTE_CYRILLIC_ISO8859_5 - - FIELD2_TO_OFFICIAL_LEADING_BYTE; - else if( (MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW) ) - return LEADING_BYTE_HEBREW_ISO8859_8 - - FIELD2_TO_OFFICIAL_LEADING_BYTE; - else if( (MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI) ) - return LEADING_BYTE_THAI_TIS620 - - FIELD2_TO_OFFICIAL_LEADING_BYTE; - else if( (MIN_CHAR_HALFWIDTH_KATAKANA <= c) - && (c <= MAX_CHAR_HALFWIDTH_KATAKANA) ) - return LEADING_BYTE_KATAKANA_JISX0201 - - FIELD2_TO_OFFICIAL_LEADING_BYTE; - else - return CHAR_FIELD2_INTERNAL(c); + return EQ (cc.charset, Vcharset_ascii) && (cc.code_point == ch); } -INLINE Emchar -CHAR_FIELD3 (Emchar c) +INLINE_HEADER int CHARC_IS_SPACE (Charc cc); +INLINE_HEADER int +CHARC_IS_SPACE (Charc cc) { - if( (MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK) ) - return c - MIN_CHAR_GREEK + 0x20; - else if( (MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC) ) - return c - MIN_CHAR_CYRILLIC + 0x20; - else if( (MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW) ) - return c - MIN_CHAR_HEBREW + 0x20; - else if( (MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI) ) - return c - MIN_CHAR_THAI + 0x20; - else if( (MIN_CHAR_HALFWIDTH_KATAKANA <= c) - && (c <= MAX_CHAR_HALFWIDTH_KATAKANA) ) - return c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20; - else - return CHAR_FIELD3_INTERNAL(c); + return (EQ (cc.charset, Vcharset_ascii) || + EQ (cc.charset, Vcharset_control_1) || + EQ (cc.charset, Vcharset_latin_iso8859_1)) + && isspace (cc.code_point); } -/* Minimum and maximum allowed values for the fields. */ - -#define MIN_CHAR_FIELD2_OFFICIAL \ - (MIN_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE) -#define MAX_CHAR_FIELD2_OFFICIAL \ - (MAX_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE) - -#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_OFFICIAL_TYPE9N \ - (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_OFFICIAL << 7)) -#define MIN_CHAR_PRIVATE_TYPE9N \ - (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_PRIVATE << 7)) -#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)) - -/* Leading byte of a character. - - NOTE: This takes advantage of the fact that - FIELD2_TO_OFFICIAL_LEADING_BYTE and - FIELD2_TO_PRIVATE_LEADING_BYTE are the same. - */ - -INLINE Bufbyte CHAR_LEADING_BYTE (Emchar c); -INLINE Bufbyte -CHAR_LEADING_BYTE (Emchar c) +INLINE_HEADER Charc ASCII_TO_CHARC (int ch); +INLINE_HEADER Charc +ASCII_TO_CHARC (int ch) { - if (CHAR_ASCII_P (c)) - return LEADING_BYTE_ASCII; - else if (c < 0xA0) - return LEADING_BYTE_CONTROL_1; - else if (c <= 0xff) - return LEADING_BYTE_LATIN_ISO8859_1; - else if (c <= MAX_CHAR_GREEK) - return LEADING_BYTE_GREEK_ISO8859_7; - else if (c <= MAX_CHAR_CYRILLIC) - return LEADING_BYTE_CYRILLIC_ISO8859_5; - else if (c <= MAX_CHAR_HEBREW) - return LEADING_BYTE_HEBREW_ISO8859_8; - else if (c <= MAX_CHAR_THAI) - return LEADING_BYTE_THAI_TIS620; - else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA) - return LEADING_BYTE_KATAKANA_JISX0201; - else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N) - return CHAR_FIELD2 (c) + FIELD2_TO_OFFICIAL_LEADING_BYTE; - else if (c < MIN_CHAR_OFFICIAL_TYPE9NX9N) - return CHAR_FIELD1 (c) + FIELD1_TO_PRIVATE_LEADING_BYTE; - else if (c < MIN_CHAR_COMPOSITION) - return CHAR_FIELD1 (c) + FIELD1_TO_OFFICIAL_LEADING_BYTE; - else - { -#ifdef ENABLE_COMPOSITE_CHARS - return LEADING_BYTE_COMPOSITE; -#else - abort(); - return 0; -#endif /* ENABLE_COMPOSITE_CHARS */ - } -} + Charc cc; -#define CHAR_CHARSET(c) CHARSET_BY_LEADING_BYTE (CHAR_LEADING_BYTE (c)) - -/* 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) -{ - 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; -#ifdef ENABLE_COMPOSITE_CHARS - else if (EQ (charset, Vcharset_composite)) - return (0x1F << 14) | ((c1) << 7) | (c2); -#endif - else if (XCHARSET_DIMENSION (charset) == 1) - return MULE_CHAR_PRIVATE_OFFSET - | ((XCHARSET_LEADING_BYTE (charset) - - FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7) | (c1); - else if (!XCHARSET_PRIVATE_P (charset)) - return MULE_CHAR_PRIVATE_OFFSET - | ((XCHARSET_LEADING_BYTE (charset) - - FIELD1_TO_OFFICIAL_LEADING_BYTE) << 14) | ((c1) << 7) | (c2); - else - return MULE_CHAR_PRIVATE_OFFSET - | ((XCHARSET_LEADING_BYTE (charset) - - FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2); + cc.charset = Vcharset_ascii; + cc.code_point = ch; + return cc; } -/* The charset of character C is set to CHARSET, and the - position-codes of C are set to C1 and C2. C2 of TYPE9N character - is 0. */ - -/* BREAKUP_CHAR_1_UNSAFE assumes that the charset has already been - calculated, and just computes c1 and c2. - - BREAKUP_CHAR also computes and stores the charset. */ -#define BREAKUP_CHAR_1_UNSAFE(c, charset, c1, c2) \ - XCHARSET_DIMENSION (charset) == 1 \ - ? ((c1) = CHAR_FIELD3 (c), (c2) = 0) \ - : ((c1) = CHAR_FIELD2 (c), \ - (c2) = CHAR_FIELD3 (c)) - -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) +typedef struct { - *charset = CHAR_CHARSET (c); - BREAKUP_CHAR_1_UNSAFE (c, *charset, *c1, *c2); -} - -#define BREAKUP_CHAR(c, charset, c1, c2) \ - breakup_char_1 (c, &(charset), &(c1), &(c2)) - - - -#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; - -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); + Dynarr_declare (Charc); +} Charc_dynarr; #endif /* _XEMACS_CHARACTER_H */