mbutils.c

来自「postgresql8.3.4源码,开源数据库」· C语言 代码 · 共 768 行 · 第 1/2 页

	/*
	 * build bytea data type structure.
	 */
	len = strlen((char *) result) + VARHDRSZ;
	retval = palloc(len);
	SET_VARSIZE(retval, len);
	memcpy(VARDATA(retval), result, len - VARHDRSZ);

	if (result != str)
		pfree(result);
	pfree(str);

	/* free memory if allocated by the toaster */
	PG_FREE_IF_COPY(string, 0);

	PG_RETURN_BYTEA_P(retval);
}

/*
 * get the length of the string considered as text in the specified
 * encoding. Raises an error if the data is not valid in that
 * encoding.
 *
 * INT4 length (BYTEA string, NAME src_encoding_name)
 */
Datum
length_in_encoding(PG_FUNCTION_ARGS)
{
	bytea	   *string = PG_GETARG_BYTEA_P(0);
	char	   *src_encoding_name = NameStr(*PG_GETARG_NAME(1));
	int			src_encoding = pg_char_to_encoding(src_encoding_name);
	int			len = VARSIZE(string) - VARHDRSZ;
	int			retval;

	if (src_encoding < 0)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("invalid encoding name \"%s\"",
						src_encoding_name)));

	retval = pg_verify_mbstr_len(src_encoding, VARDATA(string), len, false);
	PG_RETURN_INT32(retval);

}

/*
 * convert client encoding to server encoding.
 */
char *
pg_client_to_server(const char *s, int len)
{
	Assert(DatabaseEncoding);
	Assert(ClientEncoding);

	if (len <= 0)
		return (char *) s;

	if (ClientEncoding->encoding == DatabaseEncoding->encoding ||
		ClientEncoding->encoding == PG_SQL_ASCII)
	{
		/*
		 * No conversion is needed, but we must still validate the data.
		 */
		(void) pg_verify_mbstr(DatabaseEncoding->encoding, s, len, false);
		return (char *) s;
	}

	if (DatabaseEncoding->encoding == PG_SQL_ASCII)
	{
		/*
		 * No conversion is possible, but we must still validate the data,
		 * because the client-side code might have done string escaping using
		 * the selected client_encoding.  If the client encoding is ASCII-safe
		 * then we just do a straight validation under that encoding.  For an
		 * ASCII-unsafe encoding we have a problem: we dare not pass such data
		 * to the parser but we have no way to convert it.	We compromise by
		 * rejecting the data if it contains any non-ASCII characters.
		 */
		if (PG_VALID_BE_ENCODING(ClientEncoding->encoding))
			(void) pg_verify_mbstr(ClientEncoding->encoding, s, len, false);
		else
		{
			int			i;

			for (i = 0; i < len; i++)
			{
				if (s[i] == '\0' || IS_HIGHBIT_SET(s[i]))
					ereport(ERROR,
							(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
					 errmsg("invalid byte value for encoding \"%s\": 0x%02x",
							pg_enc2name_tbl[PG_SQL_ASCII].name,
							(unsigned char) s[i])));
			}
		}
		return (char *) s;
	}

	return perform_default_encoding_conversion(s, len, true);
}

/*
 * convert server encoding to client encoding.
 */
char *
pg_server_to_client(const char *s, int len)
{
	Assert(DatabaseEncoding);
	Assert(ClientEncoding);

	if (len <= 0)
		return (char *) s;

	if (ClientEncoding->encoding == DatabaseEncoding->encoding ||
		ClientEncoding->encoding == PG_SQL_ASCII ||
		DatabaseEncoding->encoding == PG_SQL_ASCII)
		return (char *) s;		/* assume data is valid */

	return perform_default_encoding_conversion(s, len, false);
}

/*
 *	Perform default encoding conversion using cached FmgrInfo. Since
 *	this function does not access database at all, it is safe to call
 *	outside transactions. Explicit setting client encoding required
 *	before calling this function. Otherwise no conversion is
 *	performed.
*/
static char *
perform_default_encoding_conversion(const char *src, int len, bool is_client_to_server)
{
	char	   *result;
	int			src_encoding,
				dest_encoding;
	FmgrInfo   *flinfo;

	if (is_client_to_server)
	{
		src_encoding = ClientEncoding->encoding;
		dest_encoding = DatabaseEncoding->encoding;
		flinfo = ToServerConvProc;
	}
	else
	{
		src_encoding = DatabaseEncoding->encoding;
		dest_encoding = ClientEncoding->encoding;
		flinfo = ToClientConvProc;
	}

	if (flinfo == NULL)
		return (char *) src;

	/*
	 * Allocate space for conversion result, being wary of integer overflow
	 */
	if ((Size) len >= (MaxAllocSize / (Size) MAX_CONVERSION_GROWTH))
		ereport(ERROR,
				(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
				 errmsg("out of memory"),
		 errdetail("String of %d bytes is too long for encoding conversion.",
				   len)));

	result = palloc(len * MAX_CONVERSION_GROWTH + 1);

	FunctionCall5(flinfo,
				  Int32GetDatum(src_encoding),
				  Int32GetDatum(dest_encoding),
				  CStringGetDatum(src),
				  CStringGetDatum(result),
				  Int32GetDatum(len));
	return result;
}

/* convert a multibyte string to a wchar */
int
pg_mb2wchar(const char *from, pg_wchar *to)
{
	return (*pg_wchar_table[DatabaseEncoding->encoding].mb2wchar_with_len) ((const unsigned char *) from, to, strlen(from));
}

/* convert a multibyte string to a wchar with a limited length */
int
pg_mb2wchar_with_len(const char *from, pg_wchar *to, int len)
{
	return (*pg_wchar_table[DatabaseEncoding->encoding].mb2wchar_with_len) ((const unsigned char *) from, to, len);
}

/* same, with any encoding */
int
pg_encoding_mb2wchar_with_len(int encoding,
							  const char *from, pg_wchar *to, int len)
{
	return (*pg_wchar_table[encoding].mb2wchar_with_len) ((const unsigned char *) from, to, len);
}

/* returns the byte length of a multibyte word */
int
pg_mblen(const char *mbstr)
{
	return ((*pg_wchar_table[DatabaseEncoding->encoding].mblen) ((const unsigned char *) mbstr));
}

/* returns the display length of a multibyte word */
int
pg_dsplen(const char *mbstr)
{
	return ((*pg_wchar_table[DatabaseEncoding->encoding].dsplen) ((const unsigned char *) mbstr));
}

/* returns the length (counted in wchars) of a multibyte string */
int
pg_mbstrlen(const char *mbstr)
{
	int			len = 0;

	/* optimization for single byte encoding */
	if (pg_database_encoding_max_length() == 1)
		return strlen(mbstr);

	while (*mbstr)
	{
		mbstr += pg_mblen(mbstr);
		len++;
	}
	return len;
}

/* returns the length (counted in wchars) of a multibyte string
 * (not necessarily NULL terminated)
 */
int
pg_mbstrlen_with_len(const char *mbstr, int limit)
{
	int			len = 0;

	/* optimization for single byte encoding */
	if (pg_database_encoding_max_length() == 1)
		return limit;

	while (limit > 0 && *mbstr)
	{
		int			l = pg_mblen(mbstr);

		limit -= l;
		mbstr += l;
		len++;
	}
	return len;
}

/*
 * returns the byte length of a multibyte string
 * (not necessarily  NULL terminated)
 * that is no longer than limit.
 * this function does not break multibyte word boundary.
 */
int
pg_mbcliplen(const char *mbstr, int len, int limit)
{
	int			clen = 0;
	int			l;

	/* optimization for single byte encoding */
	if (pg_database_encoding_max_length() == 1)
		return cliplen(mbstr, len, limit);

	while (len > 0 && *mbstr)
	{
		l = pg_mblen(mbstr);
		if ((clen + l) > limit)
			break;
		clen += l;
		if (clen == limit)
			break;
		len -= l;
		mbstr += l;
	}
	return clen;
}

/*
 * Similar to pg_mbcliplen except the limit parameter specifies the
 * character length, not the byte length.  */
int
pg_mbcharcliplen(const char *mbstr, int len, int limit)
{
	int			clen = 0;
	int			nch = 0;
	int			l;

	/* optimization for single byte encoding */
	if (pg_database_encoding_max_length() == 1)
		return cliplen(mbstr, len, limit);

	while (len > 0 && *mbstr)
	{
		l = pg_mblen(mbstr);
		nch++;
		if (nch > limit)
			break;
		clen += l;
		len -= l;
		mbstr += l;
	}
	return clen;
}

void
SetDatabaseEncoding(int encoding)
{
	if (!PG_VALID_BE_ENCODING(encoding))
		elog(ERROR, "invalid database encoding: %d", encoding);

	DatabaseEncoding = &pg_enc2name_tbl[encoding];
	Assert(DatabaseEncoding->encoding == encoding);

	/*
	 * On Windows, we allow UTF-8 database encoding to be used with any
	 * locale setting, because UTF-8 requires special handling anyway.
	 * But this means that gettext() might be misled about what output
	 * encoding it should use, so we have to tell it explicitly.
	 *
	 * In future we might want to call bind_textdomain_codeset
	 * unconditionally, but that requires knowing how to spell the codeset
	 * name properly for all encodings on all platforms, which might be
	 * problematic.
	 *
	 * This is presently unnecessary, but harmless, on non-Windows platforms.
	 */
#ifdef ENABLE_NLS
	if (encoding == PG_UTF8)
		if (bind_textdomain_codeset("postgres", "UTF-8") == NULL)
			elog(LOG, "bind_textdomain_codeset failed");
#endif
}

void
SetDefaultClientEncoding(void)
{
	ClientEncoding = &pg_enc2name_tbl[GetDatabaseEncoding()];
}

int
GetDatabaseEncoding(void)
{
	Assert(DatabaseEncoding);
	return DatabaseEncoding->encoding;
}

const char *
GetDatabaseEncodingName(void)
{
	Assert(DatabaseEncoding);
	return DatabaseEncoding->name;
}

Datum
getdatabaseencoding(PG_FUNCTION_ARGS)
{
	Assert(DatabaseEncoding);
	return DirectFunctionCall1(namein, CStringGetDatum(DatabaseEncoding->name));
}

Datum
pg_client_encoding(PG_FUNCTION_ARGS)
{
	Assert(ClientEncoding);
	return DirectFunctionCall1(namein, CStringGetDatum(ClientEncoding->name));
}

static int
cliplen(const char *str, int len, int limit)
{
	int			l = 0;
	const char *s;

	for (s = str; *s; s++, l++)
	{
		if (l >= len || l >= limit)
			return l;
	}
	return (s - str);
}