wchar.c

从一个开源软件中摘取的正则表达式模块

ucs_wcwidth(pg_wchar ucs)
{
	/* sorted list of non-overlapping intervals of non-spacing characters */
	static const struct mbinterval combining[] = {
		{0x0300, 0x034E}, {0x0360, 0x0362}, {0x0483, 0x0486},
		{0x0488, 0x0489}, {0x0591, 0x05A1}, {0x05A3, 0x05B9},
		{0x05BB, 0x05BD}, {0x05BF, 0x05BF}, {0x05C1, 0x05C2},
		{0x05C4, 0x05C4}, {0x064B, 0x0655}, {0x0670, 0x0670},
		{0x06D6, 0x06E4}, {0x06E7, 0x06E8}, {0x06EA, 0x06ED},
		{0x070F, 0x070F}, {0x0711, 0x0711}, {0x0730, 0x074A},
		{0x07A6, 0x07B0}, {0x0901, 0x0902}, {0x093C, 0x093C},
		{0x0941, 0x0948}, {0x094D, 0x094D}, {0x0951, 0x0954},
		{0x0962, 0x0963}, {0x0981, 0x0981}, {0x09BC, 0x09BC},
		{0x09C1, 0x09C4}, {0x09CD, 0x09CD}, {0x09E2, 0x09E3},
		{0x0A02, 0x0A02}, {0x0A3C, 0x0A3C}, {0x0A41, 0x0A42},
		{0x0A47, 0x0A48}, {0x0A4B, 0x0A4D}, {0x0A70, 0x0A71},
		{0x0A81, 0x0A82}, {0x0ABC, 0x0ABC}, {0x0AC1, 0x0AC5},
		{0x0AC7, 0x0AC8}, {0x0ACD, 0x0ACD}, {0x0B01, 0x0B01},
		{0x0B3C, 0x0B3C}, {0x0B3F, 0x0B3F}, {0x0B41, 0x0B43},
		{0x0B4D, 0x0B4D}, {0x0B56, 0x0B56}, {0x0B82, 0x0B82},
		{0x0BC0, 0x0BC0}, {0x0BCD, 0x0BCD}, {0x0C3E, 0x0C40},
		{0x0C46, 0x0C48}, {0x0C4A, 0x0C4D}, {0x0C55, 0x0C56},
		{0x0CBF, 0x0CBF}, {0x0CC6, 0x0CC6}, {0x0CCC, 0x0CCD},
		{0x0D41, 0x0D43}, {0x0D4D, 0x0D4D}, {0x0DCA, 0x0DCA},
		{0x0DD2, 0x0DD4}, {0x0DD6, 0x0DD6}, {0x0E31, 0x0E31},
		{0x0E34, 0x0E3A}, {0x0E47, 0x0E4E}, {0x0EB1, 0x0EB1},
		{0x0EB4, 0x0EB9}, {0x0EBB, 0x0EBC}, {0x0EC8, 0x0ECD},
		{0x0F18, 0x0F19}, {0x0F35, 0x0F35}, {0x0F37, 0x0F37},
		{0x0F39, 0x0F39}, {0x0F71, 0x0F7E}, {0x0F80, 0x0F84},
		{0x0F86, 0x0F87}, {0x0F90, 0x0F97}, {0x0F99, 0x0FBC},
		{0x0FC6, 0x0FC6}, {0x102D, 0x1030}, {0x1032, 0x1032},
		{0x1036, 0x1037}, {0x1039, 0x1039}, {0x1058, 0x1059},
		{0x1160, 0x11FF}, {0x17B7, 0x17BD}, {0x17C6, 0x17C6},
		{0x17C9, 0x17D3}, {0x180B, 0x180E}, {0x18A9, 0x18A9},
		{0x200B, 0x200F}, {0x202A, 0x202E}, {0x206A, 0x206F},
		{0x20D0, 0x20E3}, {0x302A, 0x302F}, {0x3099, 0x309A},
		{0xFB1E, 0xFB1E}, {0xFE20, 0xFE23}, {0xFEFF, 0xFEFF},
		{0xFFF9, 0xFFFB}
	};

	/* test for 8-bit control characters */
	if (ucs == 0)
		return 0;

	if (ucs < 0x20 || (ucs >= 0x7f && ucs < 0xa0) || ucs > 0x0010ffff)
		return -1;

	/* binary search in table of non-spacing characters */
	if (mbbisearch(ucs, combining,
				   sizeof(combining) / sizeof(struct mbinterval) - 1))
		return 0;

	/*
	 * if we arrive here, ucs is not a combining or C0/C1 control character
	 */

	return 1 +
		(ucs >= 0x1100 &&
		 (ucs <= 0x115f ||		/* Hangul Jamo init. consonants */
		  (ucs >= 0x2e80 && ucs <= 0xa4cf && (ucs & ~0x0011) != 0x300a &&
		   ucs != 0x303f) ||	/* CJK ... Yi */
		  (ucs >= 0xac00 && ucs <= 0xd7a3) ||	/* Hangul Syllables */
		  (ucs >= 0xf900 && ucs <= 0xfaff) ||	/* CJK Compatibility
												 * Ideographs */
		  (ucs >= 0xfe30 && ucs <= 0xfe6f) ||	/* CJK Compatibility Forms */
		  (ucs >= 0xff00 && ucs <= 0xff5f) ||	/* Fullwidth Forms */
		  (ucs >= 0xffe0 && ucs <= 0xffe6) ||
		  (ucs >= 0x20000 && ucs <= 0x2ffff)));
}

static pg_wchar
utf2ucs(const unsigned char *c)
{
	/*
	 * one char version of pg_utf2wchar_with_len. no control here, c must
	 * point to a large enough string
	 */
	if ((*c & 0x80) == 0)
		return (pg_wchar) c[0];
	else if ((*c & 0xe0) == 0xc0)
		return (pg_wchar) (((c[0] & 0x1f) << 6) |
						   (c[1] & 0x3f));
	else if ((*c & 0xf0) == 0xe0)
		return (pg_wchar) (((c[0] & 0x0f) << 12) |
						   ((c[1] & 0x3f) << 6) |
						   (c[2] & 0x3f));
	else if ((*c & 0xf8) == 0xf0)
		return (pg_wchar) (((c[0] & 0x07) << 18) |
						   ((c[1] & 0x3f) << 12) |
						   ((c[2] & 0x3f) << 6) |
						   (c[3] & 0x3f));
	else
		/* that is an invalid code on purpose */
		return 0xffffffff;
}

static int
pg_utf_dsplen(const unsigned char *s)
{
	return ucs_wcwidth(utf2ucs(s));
}

/*
 * convert mule internal code to pg_wchar
 * caller should allocate enough space for "to"
 * len: length of from.
 * "from" not necessarily null terminated.
 */
static int
pg_mule2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
{
	int			cnt = 0;

	while (len > 0 && *from)
	{
		if (IS_LC1(*from) && len >= 2)
		{
			*to = *from++ << 16;
			*to |= *from++;
			len -= 2;
		}
		else if (IS_LCPRV1(*from) && len >= 3)
		{
			from++;
			*to = *from++ << 16;
			*to |= *from++;
			len -= 3;
		}
		else if (IS_LC2(*from) && len >= 3)
		{
			*to = *from++ << 16;
			*to |= *from++ << 8;
			*to |= *from++;
			len -= 3;
		}
		else if (IS_LCPRV2(*from) && len >= 4)
		{
			from++;
			*to = *from++ << 16;
			*to |= *from++ << 8;
			*to |= *from++;
			len -= 4;
		}
		else
		{						/* assume ASCII */
			*to = (unsigned char) *from++;
			len--;
		}
		to++;
		cnt++;
	}
	*to = 0;
	return cnt;
}

int
pg_mule_mblen(const unsigned char *s)
{
	int			len;

	if (IS_LC1(*s))
		len = 2;
	else if (IS_LCPRV1(*s))
		len = 3;
	else if (IS_LC2(*s))
		len = 3;
	else if (IS_LCPRV2(*s))
		len = 4;
	else
		len = 1;				/* assume ASCII */
	return len;
}

static int
pg_mule_dsplen(const unsigned char *s)
{
	int			len;

	if (IS_LC1(*s))
		len = 1;
	else if (IS_LCPRV1(*s))
		len = 1;
	else if (IS_LC2(*s))
		len = 2;
	else if (IS_LCPRV2(*s))
		len = 2;
	else
		len = 1;				/* assume ASCII */

	return len;
}

/*
 * ISO8859-1
 */
static int
pg_latin12wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
{
	int			cnt = 0;

	while (len > 0 && *from)
	{
		*to++ = *from++;
		len--;
		cnt++;
	}
	*to = 0;
	return cnt;
}

static int
pg_latin1_mblen(const unsigned char *s)
{
	return 1;
}

static int
pg_latin1_dsplen(const unsigned char *s)
{
	return pg_ascii_dsplen(s);
}

/*
 * SJIS
 */
static int
pg_sjis_mblen(const unsigned char *s)
{
	int			len;

	if (*s >= 0xa1 && *s <= 0xdf)
		len = 1;				/* 1 byte kana? */
	else if (IS_HIGHBIT_SET(*s))
		len = 2;				/* kanji? */
	else
		len = 1;				/* should be ASCII */
	return len;
}

static int
pg_sjis_dsplen(const unsigned char *s)
{
	int			len;

	if (*s >= 0xa1 && *s <= 0xdf)
		len = 1;				/* 1 byte kana? */
	else if (IS_HIGHBIT_SET(*s))
		len = 2;				/* kanji? */
	else
		len = pg_ascii_dsplen(s);		/* should be ASCII */
	return len;
}

/*
 * Big5
 */
static int
pg_big5_mblen(const unsigned char *s)
{
	int			len;

	if (IS_HIGHBIT_SET(*s))
		len = 2;				/* kanji? */
	else
		len = 1;				/* should be ASCII */
	return len;
}

static int
pg_big5_dsplen(const unsigned char *s)
{
	int			len;

	if (IS_HIGHBIT_SET(*s))
		len = 2;				/* kanji? */
	else
		len = pg_ascii_dsplen(s);		/* should be ASCII */
	return len;
}

/*
 * GBK
 */
static int
pg_gbk_mblen(const unsigned char *s)
{
	int			len;

	if (IS_HIGHBIT_SET(*s))
		len = 2;				/* kanji? */
	else
		len = 1;				/* should be ASCII */
	return len;
}

static int
pg_gbk_dsplen(const unsigned char *s)
{
	int			len;

	if (IS_HIGHBIT_SET(*s))
		len = 2;				/* kanji? */
	else
		len = pg_ascii_dsplen(s);		/* should be ASCII */
	return len;
}

/*
 * UHC
 */
static int
pg_uhc_mblen(const unsigned char *s)
{
	int			len;

	if (IS_HIGHBIT_SET(*s))
		len = 2;				/* 2byte? */
	else
		len = 1;				/* should be ASCII */
	return len;
}

static int
pg_uhc_dsplen(const unsigned char *s)
{
	int			len;

	if (IS_HIGHBIT_SET(*s))
		len = 2;				/* 2byte? */
	else
		len = pg_ascii_dsplen(s);		/* should be ASCII */
	return len;
}

/*
 *	* GB18030
 *	 * Added by Bill Huang <[e-mail]>,<[e-mail]>
 *	  */
static int
pg_gb18030_mblen(const unsigned char *s)
{
	int			len;

	if (!IS_HIGHBIT_SET(*s))
		len = 1;				/* ASCII */
	else
	{
		if ((*(s + 1) >= 0x40 && *(s + 1) <= 0x7e) || (*(s + 1) >= 0x80 && *(s + 1) <= 0xfe))
			len = 2;
		else if (*(s + 1) >= 0x30 && *(s + 1) <= 0x39)
			len = 4;
		else
			len = 2;
	}
	return len;
}

static int
pg_gb18030_dsplen(const unsigned char *s)
{
	int			len;

	if (IS_HIGHBIT_SET(*s))
		len = 2;
	else
		len = pg_ascii_dsplen(s);		/* ASCII */
	return len;
}

/*
 *-------------------------------------------------------------------
 * multibyte sequence validators
 *
 * These functions accept "s", a pointer to the first byte of a string,
 * and "len", the remaining length of the string.  If there is a validly
 * encoded character beginning at *s, return its length in bytes; else
 * return -1.
 *
 * The functions can assume that len > 0 and that *s != '\0', but they must
 * test for and reject zeroes in any additional bytes of a multibyte character.
 *
 * Note that this definition allows the function for a single-byte
 * encoding to be just "return 1".
 *-------------------------------------------------------------------
 */

static int
pg_ascii_verifier(const unsigned char *s, int len)
{
	return 1;
}

#define IS_EUC_RANGE_VALID(c)	((c) >= 0xa1 && (c) <= 0xfe)

static int
pg_eucjp_verifier(const unsigned char *s, int len)
{
	int			l;
	unsigned char c1,
				c2;

	c1 = *s++;

	switch (c1)
	{
		case SS2:				/* JIS X 0201 */
			l = 2;
			if (l > len)
				return -1;
			c2 = *s++;
			if (c2 < 0xa1 || c2 > 0xdf)
				return -1;
			break;

		case SS3:				/* JIS X 0212 */
			l = 3;
			if (l > len)
				return -1;
			c2 = *s++;
			if (!IS_EUC_RANGE_VALID(c2))
				return -1;
			c2 = *s++;
			if (!IS_EUC_RANGE_VALID(c2))
				return -1;
			break;

		default:
			if (IS_HIGHBIT_SET(c1))		/* JIS X 0208? */
			{
				l = 2;
				if (l > len)
					return -1;
				if (!IS_EUC_RANGE_VALID(c1))
					return -1;
				c2 = *s++;
				if (!IS_EUC_RANGE_VALID(c2))
					return -1;
			}
			else
				/* must be ASCII */
			{
				l = 1;
			}
			break;
	}

	return l;
}

static int
pg_euckr_verifier(const unsigned char *s, int len)
{
	int			l;
	unsigned char c1,
				c2;

	c1 = *s++;

	if (IS_HIGHBIT_SET(c1))
	{
		l = 2;
		if (l > len)
			return -1;
		if (!IS_EUC_RANGE_VALID(c1))
			return -1;
		c2 = *s++;
		if (!IS_EUC_RANGE_VALID(c2))
			return -1;
	}
	else
		/* must be ASCII */
	{
		l = 1;
	}

	return l;
}

/* EUC-CN byte sequences are exactly same as EUC-KR */
#define pg_euccn_verifier	pg_euckr_verifier

static int
pg_euctw_verifier(const unsigned char *s, int len)
{
	int			l;
	unsigned char c1,
				c2;

	c1 = *s++;

	switch (c1)
	{
		case SS2:				/* CNS 11643 Plane 1-7 */
			l = 4;
			if (l > len)
				return -1;
			c2 = *s++;
			if (c2 < 0xa1 || c2 > 0xa7)
				return -1;
			c2 = *s++;
			if (!IS_EUC_RANGE_VALID(c2))
				return -1;
			c2 = *s++;
			if (!IS_EUC_RANGE_VALID(c2))
				return -1;
			break;

		case SS3:				/* unused */
			return -1;

		default:
			if (IS_HIGHBIT_SET(c1))		/* CNS 11643 Plane 1 */
			{
				l = 2;
				if (l > len)
					return -1;
				/* no further range check on c1? */
				c2 = *s++;
				if (!IS_EUC_RANGE_VALID(c2))
					return -1;
			}
			else
				/* must be ASCII */
			{