/* Rewritten by Ben Wing <ben@xemacs.org>. */
-#ifndef _XEMACS_MULE_CHARSET_H
-#define _XEMACS_MULE_CHARSET_H
+#ifndef INCLUDED_mule_charset_h_
+#define INCLUDED_mule_charset_h_
/*
1. Character Sets
Character set Encoding (PC == position-code)
------------- -------- (LB == leading-byte)
- ASCII PC1 |
+ ASCII PC1 |
Control-1 LB | PC1 + 0xA0
Dimension-1 official LB | PC1 + 0x80
Dimension-1 private 0x9E | LB | PC1 + 0x80
/* Definition of leading bytes */
/************************************************************************/
+typedef unsigned char Charset_ID;
+
#define MIN_LEADING_BYTE 0x80
/* These need special treatment in a string and/or character */
#define LEADING_BYTE_ASCII 0x8E /* Omitted in a buffer */
#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. **/
+/* Note the gap in each official charset can cause core dump
+ as first and last values are used to determine whether
+ charset is defined or not in non_ascii_valid_char_p */
-#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 */
+/** The following are for 1-byte characters in an official charset. **/
+enum LEADING_BYTE_OFFICIAL_1
+{
+ LEADING_BYTE_LATIN_ISO8859_1 = 0x81, /* Right half of ISO 8859-1 */
+ LEADING_BYTE_LATIN_ISO8859_2, /* 0x82 Right half of ISO 8859-2 */
+ LEADING_BYTE_LATIN_ISO8859_3, /* 0x83 Right half of ISO 8859-3 */
+ LEADING_BYTE_LATIN_ISO8859_4, /* 0x84 Right half of ISO 8859-4 */
+ LEADING_BYTE_THAI_TIS620, /* 0x85 TIS620-2533 */
+ LEADING_BYTE_GREEK_ISO8859_7, /* 0x86 Right half of ISO 8859-7 */
+ LEADING_BYTE_ARABIC_ISO8859_6, /* 0x87 Right half of ISO 8859-6 */
+ LEADING_BYTE_HEBREW_ISO8859_8, /* 0x88 Right half of ISO 8859-8 */
+ LEADING_BYTE_KATAKANA_JISX0201, /* 0x89 Right half of JIS X0201-1976 */
+ LEADING_BYTE_LATIN_JISX0201, /* 0x8A Left half of JIS X0201-1976 */
+ LEADING_BYTE_CYRILLIC_ISO8859_5,/* 0x8B Right half of ISO 8859-5 */
+ LEADING_BYTE_LATIN_ISO8859_9 /* 0x8C Right half of ISO 8859-9 */
+ /* 0x8D unused */
+};
#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 */
+enum LEADING_BYTE_OFFICIAL_2
+{
+ LEADING_BYTE_JAPANESE_JISX0208_1978 = 0x90, /* Japanese JIS X0208-1978 */
+ LEADING_BYTE_CHINESE_GB2312, /* 0x91 Chinese Hanzi GB2312-1980 */
+ LEADING_BYTE_JAPANESE_JISX0208, /* 0x92 Japanese JIS X0208-1983 */
+ LEADING_BYTE_KOREAN_KSC5601, /* 0x93 Hangul KS C5601-1987 */
+ LEADING_BYTE_JAPANESE_JISX0212, /* 0x94 Japanese JIS X0212-1990 */
+ LEADING_BYTE_CHINESE_CNS11643_1, /* 0x95 Chinese CNS11643 Set 1 */
+ LEADING_BYTE_CHINESE_CNS11643_2, /* 0x96 Chinese CNS11643 Set 2 */
+ LEADING_BYTE_CHINESE_BIG5_1, /* 0x97 Big5 Level 1 */
+ LEADING_BYTE_CHINESE_BIG5_2 /* 0x98 Big5 Level 2 */
+ /* 0x99 unused */
+ /* 0x9A unused */
+ /* 0x9B unused */
+ /* 0x9C unused */
+};
#define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978
#define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_CHINESE_BIG5_2
/* 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)
+INLINE_HEADER int LEADING_BYTE_PREFIX_P (Bufbyte lb);
+INLINE_HEADER int
+LEADING_BYTE_PREFIX_P (Bufbyte 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 */
+ in a string. */
#define PRIVATE_LEADING_BYTE_PREFIX(lb) \
- ((lb) < MIN_LEADING_BYTE_PRIVATE_2 ? \
+ ((unsigned int) (lb) < MIN_LEADING_BYTE_PRIVATE_2 ? \
PRE_LEADING_BYTE_PRIVATE_1 : \
PRE_LEADING_BYTE_PRIVATE_2)
/* of any format */
/************************************************************************/
-/* Argument `c' should be (unsigned int) or (unsigned char). */
-/* Note that SP and DEL are not included. */
+/* These are carefully designed to work if BYTE is signed or unsigned. */
+/* Note that SPC and DEL are considered ASCII, not control. */
-#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 BYTE_ASCII_P(byte) (((byte) & ~0x7f) == 0)
+#define BYTE_C0_P(byte) (((byte) & ~0x1f) == 0)
+#define BYTE_C1_P(byte) (((byte) & ~0x1f) == 0x80)
\f
/************************************************************************/
/* in a Mule-formatted string */
/************************************************************************/
-/* Does this byte represent the first byte of a character? */
+/* Does BYTE represent the first byte of a character? */
-#define BUFBYTE_FIRST_BYTE_P(c) ((c) < 0xA0)
+#define BUFBYTE_FIRST_BYTE_P(byte) ((byte) < 0xA0)
-/* Does this byte represent the first byte of a multi-byte character? */
+/* Does BYTE represent the first byte of a multi-byte character? */
-#define BUFBYTE_LEADING_BYTE_P(c) BYTE_C1_P (c)
+#define BUFBYTE_LEADING_BYTE_P(byte) BYTE_C1_P (byte)
\f
/************************************************************************/
int id;
Lisp_Object name;
- Lisp_Object doc_string, registry, short_name, long_name;
+ Lisp_Object doc_string;
+ Lisp_Object registry;
+ Lisp_Object short_name;
+ Lisp_Object long_name;
Lisp_Object reverse_direction_charset;
/* Which half of font to be used to display this character set */
unsigned int graphic;
};
+typedef struct Lisp_Charset Lisp_Charset;
-DECLARE_LRECORD (charset, struct Lisp_Charset);
-#define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
+DECLARE_LRECORD (charset, Lisp_Charset);
+#define XCHARSET(x) XRECORD (x, charset, 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)
/* 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_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 XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
-/* Table of charsets indexed by (leading byte - 128). */
-extern Lisp_Object charset_by_leading_byte[128];
-
-/* Table of charsets indexed by type/final-byte/direction. */
-extern Lisp_Object charset_by_attributes[4][128][2];
+struct charset_lookup {
+ /* Table of charsets indexed by (leading byte - MIN_LEADING_BYTE). */
+ Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
-/* Table of number of bytes in the string representation of a character
- indexed by the first byte of that representation.
+ /* Table of charsets indexed by type/final-byte/direction. */
+ Lisp_Object charset_by_attributes[4][128][2];
- 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)))
+ Charset_ID next_allocated_1_byte_leading_byte;
+ Charset_ID next_allocated_2_byte_leading_byte;
+};
- but it's faster this way. */
-extern Bytecount rep_bytes_by_first_byte[0xA0];
+INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Bufbyte lb);
+INLINE_HEADER Lisp_Object
+CHARSET_BY_LEADING_BYTE (Bufbyte lb)
+{
+ extern struct charset_lookup *chlook;
#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)
-{
- assert (lb >= 0x80 && lb <= 0xFF);
- return charset_by_leading_byte[lb - 128];
+ /* When error-checking is on, x86 GCC 2.95.2 -O3 miscompiles the
+ following unless we introduce `tem'. */
+ int tem = lb;
+ type_checking_assert (tem >= MIN_LEADING_BYTE &&
+ tem < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
+#endif
+ return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
}
-#else
-
-#define CHARSET_BY_LEADING_BYTE(lb) (charset_by_leading_byte[(lb) - 128])
+INLINE_HEADER Lisp_Object
+CHARSET_BY_ATTRIBUTES (unsigned int type, unsigned char final, int dir);
+INLINE_HEADER Lisp_Object
+CHARSET_BY_ATTRIBUTES (unsigned int type, unsigned char final, int dir)
+{
+ extern struct charset_lookup *chlook;
-#endif
+ type_checking_assert (type < countof (chlook->charset_by_attributes) &&
+ final < countof (chlook->charset_by_attributes[0]) &&
+ dir < countof (chlook->charset_by_attributes[0][0]));
+ return chlook->charset_by_attributes[type][final][dir];
+}
-#define CHARSET_BY_ATTRIBUTES(type, final, dir) \
- (charset_by_attributes[type][final][dir])
+/* Table of number of bytes in the string representation of a character
+ indexed by the first byte of that representation.
-#ifdef ERROR_CHECK_TYPECHECK
+ This value can be derived in other ways -- e.g. something like
+ XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (first_byte))
+ but it's faster this way. */
+extern const Bytecount rep_bytes_by_first_byte[0xA0];
-/* 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)
+/* Number of bytes in the string representation of a character. */
+INLINE_HEADER int REP_BYTES_BY_FIRST_BYTE (Bufbyte fb);
+INLINE_HEADER int
+REP_BYTES_BY_FIRST_BYTE (Bufbyte fb)
{
- assert (fb >= 0 && fb < 0xA0);
+ type_checking_assert (fb < 0xA0);
return rep_bytes_by_first_byte[fb];
}
-#else
-#define REP_BYTES_BY_FIRST_BYTE(fb) (rep_bytes_by_first_byte[fb])
-#endif
-
\f
/************************************************************************/
/* 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))
+#define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
/* The bit fields of character are divided into 3 parts:
FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */
-#define CHAR_FIELD1_MASK (0x7F << 14)
+#define CHAR_FIELD1_MASK (0x1F << 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)
+#define CHAR_FIELD2(c) (((c) & CHAR_FIELD2_MASK) >> 7)
+#define CHAR_FIELD3(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
#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)
-{
- 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 FIELD1_TO_OFFICIAL_LEADING_BYTE 0x8F
+#define FIELD1_TO_PRIVATE_LEADING_BYTE 0xE1
/* Minimum and maximum allowed values for the fields. */
/* Minimum character code of each <type> 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))
+#define MIN_CHAR_OFFICIAL_TYPE9N (MIN_CHAR_FIELD2_OFFICIAL << 7)
+#define MIN_CHAR_PRIVATE_TYPE9N (MIN_CHAR_FIELD2_PRIVATE << 7)
+#define MIN_CHAR_OFFICIAL_TYPE9NX9N (MIN_CHAR_FIELD1_OFFICIAL << 14)
+#define MIN_CHAR_PRIVATE_TYPE9NX9N (MIN_CHAR_FIELD1_PRIVATE << 14)
+#define MIN_CHAR_COMPOSITION (0x1F << 14)
/* Leading byte of a character.
FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
*/
-INLINE Bufbyte CHAR_LEADING_BYTE (Emchar c);
-INLINE Bufbyte
+INLINE_HEADER Bufbyte CHAR_LEADING_BYTE (Emchar c);
+INLINE_HEADER 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_FIELD2 (c) + FIELD2_TO_OFFICIAL_LEADING_BYTE;
+ else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N)
return CHAR_FIELD1 (c) + FIELD1_TO_OFFICIAL_LEADING_BYTE;
+ else if (c < MIN_CHAR_COMPOSITION)
+ return CHAR_FIELD1 (c) + FIELD1_TO_PRIVATE_LEADING_BYTE;
else
{
#ifdef ENABLE_COMPOSITE_CHARS
FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
*/
-INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
-INLINE Emchar
+INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
+INLINE_HEADER 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);
+ return ((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);
+ return ((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);
+ return ((XCHARSET_LEADING_BYTE (charset) -
+ FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
}
/* The charset of character C is set to CHARSET, and the
: ((c1) = CHAR_FIELD2 (c), \
(c2) = CHAR_FIELD3 (c))
-INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
-INLINE void
+INLINE_HEADER void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
+INLINE_HEADER void
breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
{
*charset = CHAR_CHARSET (c);
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,
+int copy_internal_to_external (const Bufbyte *internal, Bytecount len,
unsigned char *external);
-Bytecount copy_external_to_internal (CONST unsigned char *external,
+Bytecount copy_external_to_internal (const unsigned char *external,
int len, Bufbyte *internal);
-#endif /* _XEMACS_MULE_CHARSET_H */
+#endif /* INCLUDED_mule_charset_h_ */
projects / chise / xemacs-chise.git- / blobdiff