varchar.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * varchar.c
 *	  Functions for the built-in types char(n) and varchar(n).
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  $PostgreSQL: pgsql/src/backend/utils/adt/varchar.c,v 1.126 2008/01/01 19:45:53 momjian Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"


#include "access/hash.h"
#include "access/tuptoaster.h"
#include "libpq/pqformat.h"
#include "utils/array.h"
#include "utils/builtins.h"
#include "mb/pg_wchar.h"


/* common code for bpchartypmodin and varchartypmodin */
static int32
anychar_typmodin(ArrayType *ta, const char *typename)
{
	int32		typmod;
	int32	   *tl;
	int			n;

	tl = ArrayGetIntegerTypmods(ta, &n);

	/*
	 * we're not too tense about good error message here because grammar
	 * shouldn't allow wrong number of modifiers for CHAR
	 */
	if (n != 1)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("invalid type modifier")));

	if (*tl < 1)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("length for type %s must be at least 1", typename)));
	if (*tl > MaxAttrSize)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("length for type %s cannot exceed %d",
						typename, MaxAttrSize)));

	/*
	 * For largely historical reasons, the typmod is VARHDRSZ plus the number
	 * of characters; there is enough client-side code that knows about that
	 * that we'd better not change it.
	 */
	typmod = VARHDRSZ + *tl;

	return typmod;
}

/* common code for bpchartypmodout and varchartypmodout */
static char *
anychar_typmodout(int32 typmod)
{
	char	   *res = (char *) palloc(64);

	if (typmod > VARHDRSZ)
		snprintf(res, 64, "(%d)", (int) (typmod - VARHDRSZ));
	else
		*res = '\0';

	return res;
}


/*
 * CHAR() and VARCHAR() types are part of the ANSI SQL standard. CHAR()
 * is for blank-padded string whose length is specified in CREATE TABLE.
 * VARCHAR is for storing string whose length is at most the length specified
 * at CREATE TABLE time.
 *
 * It's hard to implement these types because we cannot figure out
 * the length of the type from the type itself. I changed (hopefully all) the
 * fmgr calls that invoke input functions of a data type to supply the
 * length also. (eg. in INSERTs, we have the tupleDescriptor which contains
 * the length of the attributes and hence the exact length of the char() or
 * varchar(). We pass this to bpcharin() or varcharin().) In the case where
 * we cannot determine the length, we pass in -1 instead and the input
 * converter does not enforce any length check.
 *
 * We actually implement this as a varlena so that we don't have to pass in
 * the length for the comparison functions. (The difference between these
 * types and "text" is that we truncate and possibly blank-pad the string
 * at insertion time.)
 *
 *															  - ay 6/95
 */


/*****************************************************************************
 *	 bpchar - char()														 *
 *****************************************************************************/

/*
 * bpchar_input -- common guts of bpcharin and bpcharrecv
 *
 * s is the input text of length len (may not be null-terminated)
 * atttypmod is the typmod value to apply
 *
 * Note that atttypmod is measured in characters, which
 * is not necessarily the same as the number of bytes.
 *
 * 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 BpChar *
bpchar_input(const char *s, size_t len, int32 atttypmod)
{
	BpChar	   *result;
	char	   *r;
	size_t		maxlen;

	/* If typmod is -1 (or invalid), use the actual string length */
	if (atttypmod < (int32) VARHDRSZ)
		maxlen = len;
	else
	{
		size_t		charlen;	/* number of CHARACTERS in the input */

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

			/*
			 * at this point, len is the actual BYTE length of the input
			 * string, maxlen is the max number of CHARACTERS allowed for this
			 * bpchar type, mbmaxlen is the length in BYTES of those chars.
			 */
			for (j = mbmaxlen; j < len; j++)
			{
				if (s[j] != ' ')
					ereport(ERROR,
							(errcode(ERRCODE_STRING_DATA_RIGHT_TRUNCATION),
							 errmsg("value too long for type character(%d)",
									(int) maxlen)));
			}

			/*
			 * Now we set maxlen to the necessary byte length, not the number
			 * of CHARACTERS!
			 */
			maxlen = len = mbmaxlen;
		}
		else
		{
			/*
			 * Now we set maxlen to the necessary byte length, not the number
			 * of CHARACTERS!
			 */
			maxlen = len + (maxlen - charlen);
		}
	}

	result = (BpChar *) palloc(maxlen + VARHDRSZ);
	SET_VARSIZE(result, maxlen + VARHDRSZ);
	r = VARDATA(result);
	memcpy(r, s, len);

	/* blank pad the string if necessary */
	if (maxlen > len)
		memset(r + len, ' ', maxlen - len);

	return result;
}

/*
 * Convert a C string to CHARACTER internal representation.  atttypmod
 * is the declared length of the type plus VARHDRSZ.
 */
Datum
bpcharin(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);
	BpChar	   *result;

	result = bpchar_input(s, strlen(s), atttypmod);
	PG_RETURN_BPCHAR_P(result);
}


/*
 * Convert a CHARACTER value to a C string.
 */
Datum
bpcharout(PG_FUNCTION_ARGS)
{
	BpChar	   *s = PG_GETARG_BPCHAR_PP(0);
	char	   *result;
	int			len;

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

	PG_RETURN_CSTRING(result);
}

/*
 *		bpcharrecv			- converts external binary format to bpchar
 */
Datum
bpcharrecv(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);
	BpChar	   *result;
	char	   *str;
	int			nbytes;

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

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


/*
 * Converts a CHARACTER 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 char(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
bpchar(PG_FUNCTION_ARGS)
{
	BpChar	   *source = PG_GETARG_BPCHAR_PP(0);
	int32		maxlen = PG_GETARG_INT32(1);
	bool		isExplicit = PG_GETARG_BOOL(2);
	BpChar	   *result;
	int32		len;
	char	   *r;
	char	   *s;
	int			i;
	int			charlen;		/* number of characters in the input string +
								 * VARHDRSZ */

	/* No work if typmod is invalid */
	if (maxlen < (int32) VARHDRSZ)
		PG_RETURN_BPCHAR_P(source);

	maxlen -= VARHDRSZ;

	len = VARSIZE_ANY_EXHDR(source);
	s = VARDATA_ANY(source);

	charlen = pg_mbstrlen_with_len(s, len);

	/* No work if supplied data matches typmod already */
	if (charlen == maxlen)
		PG_RETURN_BPCHAR_P(source);

	if (charlen > maxlen)
	{
		/* Verify that extra characters are spaces, and clip them off */
		size_t		maxmblen;

		maxmblen = pg_mbcharcliplen(s, len, maxlen);

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

		len = maxmblen;

		/*
		 * At this point, maxlen is the necessary byte length, not the number
		 * of CHARACTERS!
		 */
		maxlen = len;
	}
	else
	{
		/*
		 * At this point, maxlen is the necessary byte length, not the number
		 * of CHARACTERS!
		 */
		maxlen = len + (maxlen - charlen);
	}

	Assert(maxlen >= len);

	result = palloc(maxlen + VARHDRSZ);
	SET_VARSIZE(result, maxlen + VARHDRSZ);
	r = VARDATA(result);

	memcpy(r, s, len);

	/* blank pad the string if necessary */
	if (maxlen > len)
		memset(r + len, ' ', maxlen - len);

	PG_RETURN_BPCHAR_P(result);
}


/* char_bpchar()
 * Convert char to bpchar(1).
 */
Datum
char_bpchar(PG_FUNCTION_ARGS)
{
	char		c = PG_GETARG_CHAR(0);
	BpChar	   *result;

	result = (BpChar *) palloc(VARHDRSZ + 1);

	SET_VARSIZE(result, VARHDRSZ + 1);
	*(VARDATA(result)) = c;

	PG_RETURN_BPCHAR_P(result);
}


/* bpchar_name()
 * Converts a bpchar() type to a NameData type.
 */
Datum
bpchar_name(PG_FUNCTION_ARGS)
{
	BpChar	   *s = PG_GETARG_BPCHAR_PP(0);
	char	   *s_data;
	Name		result;
	int			len;

	len = VARSIZE_ANY_EXHDR(s);
	s_data = VARDATA_ANY(s);

	/* Truncate to max length for a Name */
	if (len >= NAMEDATALEN)
		len = NAMEDATALEN - 1;

	/* Remove trailing blanks */
	while (len > 0)
	{
		if (s_data[len - 1] != ' ')
			break;
		len--;
	}

	result = (NameData *) palloc(NAMEDATALEN);
	memcpy(NameStr(*result), s_data, len);

	/* Now null pad to full length... */
	while (len < NAMEDATALEN)
	{
		*(NameStr(*result) + len) = '\0';
		len++;
	}

	PG_RETURN_NAME(result);
}

/* name_bpchar()
 * Converts a NameData type to a bpchar type.
 */
Datum
name_bpchar(PG_FUNCTION_ARGS)
{
	Name		s = PG_GETARG_NAME(0);
	BpChar	   *result;
	int			len;

	len = strlen(NameStr(*s));
	result = (BpChar *) palloc(VARHDRSZ + len);
	memcpy(VARDATA(result), NameStr(*s), len);
	SET_VARSIZE(result, VARHDRSZ + len);

	PG_RETURN_BPCHAR_P(result);
}

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

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

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

	PG_RETURN_CSTRING(anychar_typmodout(typmod));
}


/*****************************************************************************
 *	 varchar - varchar(n)
 *
 * Note: varchar piggybacks on type text for most operations, and so has no
 * C-coded functions except for I/O and typmod checking.
 *****************************************************************************/

/*
 * varchar_input -- common guts of varcharin and varcharrecv
 *
 * s is the input text of length len (may not be null-terminated)
 * atttypmod is the typmod value to apply
 *
 * Note that atttypmod is measured in characters, which
 * is not necessarily the same as the number of bytes.