varchar.c

postgresql8.3.4源码,开源数据库

 *
 * If the input string is too long, raise an error, unless the extra
 * characters are spaces, in which case they're truncated.  (per SQL)
 */
static VarChar *
varchar_input(const char *s, size_t len, int32 atttypmod)
{
	VarChar    *result;
	size_t		maxlen;

	maxlen = atttypmod - VARHDRSZ;

	if (atttypmod >= (int32) VARHDRSZ && len > maxlen)
	{
		/* Verify that extra characters are spaces, and clip them off */
		size_t		mbmaxlen = pg_mbcharcliplen(s, len, maxlen);
		size_t		j;

		for (j = mbmaxlen; j < len; j++)
		{
			if (s[j] != ' ')
				ereport(ERROR,
						(errcode(ERRCODE_STRING_DATA_RIGHT_TRUNCATION),
					  errmsg("value too long for type character varying(%d)",
							 (int) maxlen)));
		}

		len = mbmaxlen;
	}

	result = (VarChar *) palloc(len + VARHDRSZ);
	SET_VARSIZE(result, len + VARHDRSZ);
	memcpy(VARDATA(result), s, len);

	return result;
}

/*
 * Convert a C string to VARCHAR internal representation.  atttypmod
 * is the declared length of the type plus VARHDRSZ.
 */
Datum
varcharin(PG_FUNCTION_ARGS)
{
	char	   *s = PG_GETARG_CSTRING(0);

#ifdef NOT_USED
	Oid			typelem = PG_GETARG_OID(1);
#endif
	int32		atttypmod = PG_GETARG_INT32(2);
	VarChar    *result;

	result = varchar_input(s, strlen(s), atttypmod);
	PG_RETURN_VARCHAR_P(result);
}


/*
 * Convert a VARCHAR value to a C string.
 */
Datum
varcharout(PG_FUNCTION_ARGS)
{
	VarChar    *s = PG_GETARG_VARCHAR_PP(0);
	char	   *result;
	int32		len;

	/* copy and add null term */
	len = VARSIZE_ANY_EXHDR(s);
	result = palloc(len + 1);
	memcpy(result, VARDATA_ANY(s), len);
	result[len] = '\0';

	PG_RETURN_CSTRING(result);
}

/*
 *		varcharrecv			- converts external binary format to varchar
 */
Datum
varcharrecv(PG_FUNCTION_ARGS)
{
	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);

#ifdef NOT_USED
	Oid			typelem = PG_GETARG_OID(1);
#endif
	int32		atttypmod = PG_GETARG_INT32(2);
	VarChar    *result;
	char	   *str;
	int			nbytes;

	str = pq_getmsgtext(buf, buf->len - buf->cursor, &nbytes);
	result = varchar_input(str, nbytes, atttypmod);
	pfree(str);
	PG_RETURN_VARCHAR_P(result);
}

/*
 *		varcharsend			- converts varchar to binary format
 */
Datum
varcharsend(PG_FUNCTION_ARGS)
{
	/* Exactly the same as textsend, so share code */
	return textsend(fcinfo);
}


/*
 * Converts a VARCHAR type to the specified size.
 *
 * maxlen is the typmod, ie, declared length plus VARHDRSZ bytes.
 * isExplicit is true if this is for an explicit cast to varchar(N).
 *
 * Truncation rules: for an explicit cast, silently truncate to the given
 * length; for an implicit cast, raise error unless extra characters are
 * all spaces.	(This is sort-of per SQL: the spec would actually have us
 * raise a "completion condition" for the explicit cast case, but Postgres
 * hasn't got such a concept.)
 */
Datum
varchar(PG_FUNCTION_ARGS)
{
	VarChar    *source = PG_GETARG_VARCHAR_PP(0);
	int32		typmod = PG_GETARG_INT32(1);
	bool		isExplicit = PG_GETARG_BOOL(2);
	VarChar    *result;
	int32		len,
				maxlen;
	size_t		maxmblen;
	int			i;
	char	   *s_data;

	len = VARSIZE_ANY_EXHDR(source);
	s_data = VARDATA_ANY(source);
	maxlen = typmod - VARHDRSZ;

	/* No work if typmod is invalid or supplied data fits it already */
	if (maxlen < 0 || len <= maxlen)
		PG_RETURN_VARCHAR_P(source);

	/* only reach here if string is too long... */

	/* truncate multibyte string preserving multibyte boundary */
	maxmblen = pg_mbcharcliplen(s_data, len, maxlen);

	if (!isExplicit)
	{
		for (i = maxmblen; i < len; i++)
			if (s_data[i] != ' ')
				ereport(ERROR,
						(errcode(ERRCODE_STRING_DATA_RIGHT_TRUNCATION),
					  errmsg("value too long for type character varying(%d)",
							 maxlen)));
	}

	result = palloc(maxmblen + VARHDRSZ);
	SET_VARSIZE(result, maxmblen + VARHDRSZ);
	memcpy(VARDATA(result), s_data, maxmblen);

	PG_RETURN_VARCHAR_P(result);
}

Datum
varchartypmodin(PG_FUNCTION_ARGS)
{
	ArrayType  *ta = PG_GETARG_ARRAYTYPE_P(0);

	PG_RETURN_INT32(anychar_typmodin(ta, "varchar"));
}

Datum
varchartypmodout(PG_FUNCTION_ARGS)
{
	int32		typmod = PG_GETARG_INT32(0);

	PG_RETURN_CSTRING(anychar_typmodout(typmod));
}


/*****************************************************************************
 * Exported functions
 *****************************************************************************/

/* "True" length (not counting trailing blanks) of a BpChar */
static int
bcTruelen(BpChar *arg)
{
	char	   *s = VARDATA_ANY(arg);
	int			i;
	int			len;

	len = VARSIZE_ANY_EXHDR(arg);
	for (i = len - 1; i >= 0; i--)
	{
		if (s[i] != ' ')
			break;
	}
	return i + 1;
}

Datum
bpcharlen(PG_FUNCTION_ARGS)
{
	BpChar	   *arg = PG_GETARG_BPCHAR_PP(0);
	int			len;

	/* get number of bytes, ignoring trailing spaces */
	len = bcTruelen(arg);

	/* in multibyte encoding, convert to number of characters */
	if (pg_database_encoding_max_length() != 1)
		len = pg_mbstrlen_with_len(VARDATA_ANY(arg), len);

	PG_RETURN_INT32(len);
}

Datum
bpcharoctetlen(PG_FUNCTION_ARGS)
{
	Datum		arg = PG_GETARG_DATUM(0);

	/* We need not detoast the input at all */
	PG_RETURN_INT32(toast_raw_datum_size(arg) - VARHDRSZ);
}


/*****************************************************************************
 *	Comparison Functions used for bpchar
 *
 * Note: btree indexes need these routines not to leak memory; therefore,
 * be careful to free working copies of toasted datums.  Most places don't
 * need to be so careful.
 *****************************************************************************/

Datum
bpchareq(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	bool		result;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	/*
	 * Since we only care about equality or not-equality, we can avoid all the
	 * expense of strcoll() here, and just do bitwise comparison.
	 */
	if (len1 != len2)
		result = false;
	else
		result = (strncmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) == 0);

	PG_FREE_IF_COPY(arg1, 0);
	PG_FREE_IF_COPY(arg2, 1);

	PG_RETURN_BOOL(result);
}

Datum
bpcharne(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	bool		result;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	/*
	 * Since we only care about equality or not-equality, we can avoid all the
	 * expense of strcoll() here, and just do bitwise comparison.
	 */
	if (len1 != len2)
		result = true;
	else
		result = (strncmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) != 0);

	PG_FREE_IF_COPY(arg1, 0);
	PG_FREE_IF_COPY(arg2, 1);

	PG_RETURN_BOOL(result);
}

Datum
bpcharlt(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	int			cmp;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	cmp = varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2);

	PG_FREE_IF_COPY(arg1, 0);
	PG_FREE_IF_COPY(arg2, 1);

	PG_RETURN_BOOL(cmp < 0);
}

Datum
bpcharle(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	int			cmp;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	cmp = varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2);

	PG_FREE_IF_COPY(arg1, 0);
	PG_FREE_IF_COPY(arg2, 1);

	PG_RETURN_BOOL(cmp <= 0);
}

Datum
bpchargt(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	int			cmp;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	cmp = varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2);

	PG_FREE_IF_COPY(arg1, 0);
	PG_FREE_IF_COPY(arg2, 1);

	PG_RETURN_BOOL(cmp > 0);
}

Datum
bpcharge(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	int			cmp;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	cmp = varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2);

	PG_FREE_IF_COPY(arg1, 0);
	PG_FREE_IF_COPY(arg2, 1);

	PG_RETURN_BOOL(cmp >= 0);
}

Datum
bpcharcmp(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	int			cmp;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	cmp = varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2);

	PG_FREE_IF_COPY(arg1, 0);
	PG_FREE_IF_COPY(arg2, 1);

	PG_RETURN_INT32(cmp);
}

Datum
bpchar_larger(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	int			cmp;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	cmp = varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2);

	PG_RETURN_BPCHAR_P((cmp >= 0) ? arg1 : arg2);
}

Datum
bpchar_smaller(PG_FUNCTION_ARGS)
{
	BpChar	   *arg1 = PG_GETARG_BPCHAR_PP(0);
	BpChar	   *arg2 = PG_GETARG_BPCHAR_PP(1);
	int			len1,
				len2;
	int			cmp;

	len1 = bcTruelen(arg1);
	len2 = bcTruelen(arg2);

	cmp = varstr_cmp(VARDATA_ANY(arg1), len1, VARDATA_ANY(arg2), len2);

	PG_RETURN_BPCHAR_P((cmp <= 0) ? arg1 : arg2);
}


/*
 * bpchar needs a specialized hash function because we want to ignore
 * trailing blanks in comparisons.
 *
 * Note: currently there is no need for locale-specific behavior here,
 * but if we ever change the semantics of bpchar comparison to trust
 * strcoll() completely, we'd need to do something different in non-C locales.
 */
Datum
hashbpchar(PG_FUNCTION_ARGS)
{
	BpChar	   *key = PG_GETARG_BPCHAR_PP(0);
	char	   *keydata;
	int			keylen;
	Datum		result;

	keydata = VARDATA_ANY(key);
	keylen = bcTruelen(key);

	result = hash_any((unsigned char *) keydata, keylen);

	/* Avoid leaking memory for toasted inputs */
	PG_FREE_IF_COPY(key, 0);

	return result;
}