From 5768b212c1907a8e94f297321839175df4cdf37d Mon Sep 17 00:00:00 2001 From: tomo Date: Mon, 30 Aug 1999 17:28:20 +0000 Subject: [PATCH] (LEADING_BYTE_*): Delete definition for non-UTF-2000. (LEADING_BYTE_PRIVATE_P): Deleted unconditionally. (LEADING_BYTE_PREFIX_P): Deleted. (PRIVATE_LEADING_BYTE_PREFIX): Deleted. (BUFBYTE_FIRST_BYTE_P): Delete definition for non-UTF-2000. (BUFBYTE_LEADING_BYTE_P): Deleted. (CHARSET_PRIVATE_P): Deleted unconditionally. (rep_bytes_by_first_byte): Deleted unconditionally. (REP_BYTES_BY_FIRST_BYTE): Delete definition for non-UTF-2000. (FIELD1_TO_PRIVATE_LEADING_BYTE): Likewise. (FIELD1_TO_OFFICIAL_LEADING_BYTE): Likewise. (FIELD2_TO_PRIVATE_LEADING_BYTE): Likewise. (CHAR_FIELD2): Deleted. (CHAR_FIELD3): Deleted. (MAKE_CHAR): Delete definition for non-UTF-2000. (BREAKUP_CHAR_1_UNSAFE): Deleted. (breakup_char_1): New implementation. (CHAR_CHARSET): Use `BREAKUP_CHAR'. (CHAR_LEADING_BYTE): Use `CHAR_CHARSET'. --- src/character.h | 358 ++++++++++++++++--------------------------------------- 1 file changed, 106 insertions(+), 252 deletions(-) diff --git a/src/character.h b/src/character.h index e9e09c7..db8df92 100644 --- a/src/character.h +++ b/src/character.h @@ -39,8 +39,6 @@ Boston, MA 02111-1307, USA. */ /** The following are for 1-byte characters in an official charset. **/ -#ifdef UTF2000 - #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 */ @@ -90,91 +88,10 @@ Boston, MA 02111-1307, USA. */ #define MIN_LEADING_BYTE_PRIVATE_1 0x0D0 #define MAX_LEADING_BYTE_PRIVATE_1 0x11f -#else - -#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 - -#endif - #define NUM_LEADING_BYTES 256 /************************************************************************/ -/* Operations on leading bytes */ -/************************************************************************/ - -/* Is this leading byte for a private charset? */ - -#ifndef UTF2000 -#define LEADING_BYTE_PRIVATE_P(lb) ((lb) >= MIN_LEADING_BYTE_PRIVATE_1) -#endif - -/* 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 */ /************************************************************************/ @@ -195,19 +112,11 @@ LEADING_BYTE_PREFIX_P (unsigned char lb) /* 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) /************************************************************************/ @@ -290,10 +199,6 @@ DECLARE_LRECORD (charset, struct Lisp_Charset); #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset) -#ifdef LEADING_BYTE_PRIVATE_P -#define CHARSET_PRIVATE_P(cs) LEADING_BYTE_PRIVATE_P (CHARSET_LEADING_BYTE (cs)) -#endif - #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)) @@ -322,19 +227,6 @@ extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES]; /* Table of charsets indexed by type/final-byte/direction. */ extern Lisp_Object charset_by_attributes[4][128][2]; -#ifndef UTF2000 -/* Table of number of bytes in the string representation of a character - indexed by the first byte of that representation. - - This value can be derived other ways -- e.g. something like - - (BYTE_ASCII_P (first_byte) ? 1 : - XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (first_byte))) - - but it's faster this way. */ -extern Bytecount rep_bytes_by_first_byte[0xA0]; -#endif - #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 @@ -358,7 +250,6 @@ CHARSET_BY_LEADING_BYTE (int lb) #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) @@ -376,22 +267,6 @@ REP_BYTES_BY_FIRST_BYTE (int fb) else return 6; } -#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) -{ - assert (fb >= 0 && fb < 0xA0); - return rep_bytes_by_first_byte[fb]; -} - -#else -#define REP_BYTES_BY_FIRST_BYTE(fb) (rep_bytes_by_first_byte[fb]) -#endif -#endif /* end MULE */ /************************************************************************/ @@ -438,62 +313,10 @@ REP_BYTES_BY_FIRST_BYTE (int fb) /* Converting between field values and leading bytes. */ -#define FIELD2_TO_OFFICIAL_LEADING_BYTE 0x80 - -#ifdef UTF2000 - #define FIELD1_TO_PRIVATE_LEADING_BYTE 0x80 #define FIELD1_TO_OFFICIAL_LEADING_BYTE 0x80 #define FIELD2_TO_PRIVATE_LEADING_BYTE 0xb0 - -#else - -#define FIELD1_TO_PRIVATE_LEADING_BYTE 0xc0 -#define FIELD1_TO_OFFICIAL_LEADING_BYTE 0x50 -#define FIELD2_TO_PRIVATE_LEADING_BYTE 0x80 - -#endif - -INLINE Emchar -CHAR_FIELD2 (Emchar c) -{ - 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); -} - -INLINE Emchar -CHAR_FIELD3 (Emchar c) -{ - 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); -} +#define FIELD2_TO_OFFICIAL_LEADING_BYTE 0x80 /* Minimum and maximum allowed values for the fields. */ @@ -532,52 +355,6 @@ CHAR_FIELD3 (Emchar c) #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) -{ - 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 */ - } -} - -#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. @@ -617,49 +394,126 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2) return MULE_CHAR_PRIVATE_OFFSET | ((XCHARSET_LEADING_BYTE (charset) - FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7) | (c1); -#ifdef UTF2000 else return MULE_CHAR_PRIVATE_OFFSET | ((XCHARSET_LEADING_BYTE (charset) - FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2); -#else - 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); -#endif } -/* 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) { - *charset = CHAR_CHARSET (c); - BREAKUP_CHAR_1_UNSAFE (c, *charset, *c1, *c2); + 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 < MIN_CHAR_GREEK) + { + 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) + { + 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) + { + 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) + { + 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) + { + abort (); + } + else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA) + { + *charset = Vcharset_katakana_jisx0201; + *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20; + *c2 = 0; + } + else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N) + { + *charset + = CHARSET_BY_LEADING_BYTE (CHAR_FIELD2_INTERNAL (c) + + FIELD2_TO_OFFICIAL_LEADING_BYTE); + *c1 = CHAR_FIELD3_INTERNAL(c); + *c2 = 0; + } + else if (c < MIN_CHAR_COMPOSITION) + { + *charset + = CHARSET_BY_LEADING_BYTE (CHAR_FIELD1 (c) + + FIELD1_TO_OFFICIAL_LEADING_BYTE); + *c1 = CHAR_FIELD2_INTERNAL(c); + *c2 = CHAR_FIELD3_INTERNAL(c); + } + else + { +#ifdef ENABLE_COMPOSITE_CHARS + return LEADING_BYTE_COMPOSITE; +#else + printf("u+%x", c); + abort(); +#endif /* ENABLE_COMPOSITE_CHARS */ + } } #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) +{ + Lisp_Object charset; + int c1, c2; + + BREAKUP_CHAR(c, charset, c1, c2); + return charset; +} + +#define CHAR_LEADING_BYTE(c) (XCHARSET_LEADING_BYTE(CHAR_CHARSET(c))) #ifdef ENABLE_COMPOSITE_CHARS -- 1.7.10.4