wchar.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

/*
 * conversion functions between pg_wchar and multibyte streams.
 * Tatsuo Ishii
 * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.47.2.2 2006/05/21 20:05:48 tgl Exp $
 *
 * WIN1250 client encoding updated by Pavel Behal
 *
 */
/* can be used in either frontend or backend */
#ifdef FRONTEND
#include "postgres_fe.h"
#define Assert(condition)
#else
#include "postgres.h"
#endif

#include "mb/pg_wchar.h"


/*
 * conversion to pg_wchar is done by "table driven."
 * to add an encoding support, define mb2wchar_with_len(), mblen()
 * for the particular encoding. Note that if the encoding is only
 * supported in the client, you don't need to define
 * mb2wchar_with_len() function (SJIS is the case).
 */

/*
 * SQL/ASCII
 */
static int	pg_ascii2wchar_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_ascii_mblen(const unsigned char *s)
{
	return (1);
}

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

/*
 * EUC
 */
static int	pg_euc2wchar_with_len
			(const unsigned char *from, pg_wchar *to, int len)
{
	int			cnt = 0;

	while (len > 0 && *from)
	{
		if (*from == SS2 && len >= 2)	/* JIS X 0201 (so called "1 byte KANA") */
		{
			from++;
			*to = (SS2 << 8) | *from++;
			len -= 2;
		}
		else if (*from == SS3 && len >= 3)		/* JIS X 0212 KANJI */
		{
			from++;
			*to = (SS3 << 16) | (*from++ << 8);
			*to |= *from++;
			len -= 3;
		}
		else if ((*from & 0x80) && len >= 2)	/* JIS X 0208 KANJI */
		{
			*to = *from++ << 8;
			*to |= *from++;
			len -= 2;
		}
		else	/* must be ASCII */
		{
			*to = *from++;
			len--;
		}
		to++;
		cnt++;
	}
	*to = 0;
	return (cnt);
}

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

	if (*s == SS2)
		len = 2;
	else if (*s == SS3)
		len = 3;
	else if (*s & 0x80)
		len = 2;
	else
		len = 1;
	return (len);
}

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

	if (*s == SS2)
		len = 2;
	else if (*s == SS3)
		len = 2;
	else if (*s & 0x80)
		len = 2;
	else
		len = 1;
	return (len);
}

/*
 * EUC_JP
 */
static int	pg_eucjp2wchar_with_len
			(const unsigned char *from, pg_wchar *to, int len)
{
	return (pg_euc2wchar_with_len(from, to, len));
}

static int
pg_eucjp_mblen(const unsigned char *s)
{
	return (pg_euc_mblen(s));
}

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

	if (*s == SS2)
		len = 1;
	else if (*s == SS3)
		len = 2;
	else if (*s & 0x80)
		len = 2;
	else
		len = 1;
	return (len);
}

/*
 * EUC_KR
 */
static int	pg_euckr2wchar_with_len
			(const unsigned char *from, pg_wchar *to, int len)
{
	return (pg_euc2wchar_with_len(from, to, len));
}

static int
pg_euckr_mblen(const unsigned char *s)
{
	return (pg_euc_mblen(s));
}

static int
pg_euckr_dsplen(const unsigned char *s)
{
	return (pg_euc_dsplen(s));
}

/*
 * EUC_CN
 *
 */
static int	pg_euccn2wchar_with_len
			(const unsigned char *from, pg_wchar *to, int len)
{
	int			cnt = 0;

	while (len > 0 && *from)
	{
		if (*from == SS2 && len >= 3)	/* code set 2 (unused?) */
		{
			from++;
			*to = (SS2 << 16) | (*from++ << 8);
			*to |= *from++;
			len -= 3;
		}
		else if (*from == SS3 && len >= 3)		/* code set 3 (unsed ?) */
		{
			from++;
			*to = (SS3 << 16) | (*from++ << 8);
			*to |= *from++;
			len -= 3;
		}
		else if ((*from & 0x80) && len >= 2)	/* code set 1 */
		{
			*to = *from++ << 8;
			*to |= *from++;
			len -= 2;
		}
		else
		{
			*to = *from++;
			len--;
		}
		to++;
		cnt++;
	}
	*to = 0;
	return (cnt);
}

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

	if (*s & 0x80)
		len = 2;
	else
		len = 1;
	return (len);
}

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

	if (*s & 0x80)
		len = 2;
	else
		len = 1;
	return (len);
}

/*
 * EUC_TW
 *
 */
static int	pg_euctw2wchar_with_len
			(const unsigned char *from, pg_wchar *to, int len)
{
	int			cnt = 0;

	while (len > 0 && *from)
	{
		if (*from == SS2 && len >= 4)	/* code set 2 */
		{
			from++;
			*to = (SS2 << 24) | (*from++ << 16) ;
			*to |= *from++ << 8;
			*to |= *from++;
			len -= 4;
		}
		else if (*from == SS3 && len >= 3)		/* code set 3 (unused?) */
		{
			from++;
			*to = (SS3 << 16) | (*from++ << 8);
			*to |= *from++;
			len -= 3;
		}
		else if ((*from & 0x80) && len >= 2)	/* code set 2 */
		{
			*to = *from++ << 8;
			*to |= *from++;
			len -= 2;
		}
		else
		{
			*to = *from++;
			len--;
		}
		to++;
		cnt++;
	}
	*to = 0;
	return (cnt);
}

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

	if (*s == SS2)
		len = 4;
	else if (*s == SS3)
		len = 3;
	else if (*s & 0x80)
		len = 2;
	else
		len = 1;
	return (len);
}

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

	if (*s == SS2)
		len = 2;
	else if (*s == SS3)
		len = 2;
	else if (*s & 0x80)
		len = 2;
	else
		len = 1;
	return (len);
}

/*
 * JOHAB
 */
static int
pg_johab2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
{
	return (pg_euc2wchar_with_len(from, to, len));
}

static int
pg_johab_mblen(const unsigned char *s)
{
	return (pg_euc_mblen(s));
}

static int
pg_johab_dsplen(const unsigned char *s)
{
	return (pg_euc_dsplen(s));
}

/*
 * convert UTF8 string to pg_wchar (UCS-2)
 * caller should allocate enough space for "to"
 * len: length of from.
 * "from" not necessarily null terminated.
 */
static int
pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
{
	unsigned char c1,
				c2,
				c3;
	int			cnt = 0;

	while (len > 0 && *from)
	{
		if ((*from & 0x80) == 0)
		{
			*to = *from++;
			len--;
		}
		else if ((*from & 0xe0) == 0xc0 && len >= 2)
		{
			c1 = *from++ & 0x1f;
			c2 = *from++ & 0x3f;
			*to = c1 << 6;
			*to |= c2;
			len -= 2;
		}
		else if ((*from & 0xe0) == 0xe0 && len >= 3)
		{
			c1 = *from++ & 0x0f;
			c2 = *from++ & 0x3f;
			c3 = *from++ & 0x3f;
			*to = c1 << 12;
			*to |= c2 << 6;
			*to |= c3;
			len -= 3;
		}
		else
		{
			*to = *from++;
			len--;
		}
		to++;
		cnt++;
	}
	*to = 0;
	return (cnt);
}

/*
 * returns the byte length of a UTF8 character pointed to by s
 */
int
pg_utf_mblen(const unsigned char *s)
{
	int			len = 1;

	if ((*s & 0x80) == 0)
		len = 1;
	else if ((*s & 0xe0) == 0xc0)
		len = 2;
	else if ((*s & 0xf0) == 0xe0)
		len = 3;
	else if ((*s & 0xf8) == 0xf0)
		len = 4;
	else if ((*s & 0xfc) == 0xf8)
		len = 5;
	else if ((*s & 0xfe) == 0xfc)
		len = 6;
	return (len);
}

static int
pg_utf_dsplen(const unsigned char *s)
{
	return 1;					/* XXX fix me! */
}

/*
 * 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
	{							/* assume ASCII */
		len = 1;
	}
	return (len);
}

static int
pg_mule_dsplen(const unsigned char *s)
{
	return 1;					/* XXX fix me! */
}

/*
 * 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 (1);
}

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

	if (*s >= 0xa1 && *s <= 0xdf)
	{							/* 1 byte kana? */
		len = 1;
	}
	else if (*s > 0x7f)
	{							/* kanji? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);
}

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

	if (*s >= 0xa1 && *s <= 0xdf)
	{							/* 1 byte kana? */
		len = 1;
	}
	else if (*s > 0x7f)
	{							/* kanji? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);
}

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

	if (*s > 0x7f)
	{							/* kanji? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);
}

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

	if (*s > 0x7f)
	{							/* kanji? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);
}

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

	if (*s > 0x7f)
	{							/* kanji? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);
}

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

	if (*s > 0x7f)
	{							/* kanji? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);
}

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

	if (*s > 0x7f)
	{							/* 2byte? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);
}

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

	if (*s > 0x7f)
	{							/* 2byte? */
		len = 2;
	}
	else
	{							/* should be ASCII */
		len = 1;
	}
	return (len);