regexp.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

										  VARDATA(s),
										  VARSIZE(s) - VARHDRSZ,
										  regex_flavor,
										  0, NULL));
}

Datum
textregexne(PG_FUNCTION_ARGS)
{
	text	   *s = PG_GETARG_TEXT_P(0);
	text	   *p = PG_GETARG_TEXT_P(1);

	PG_RETURN_BOOL(!RE_compile_and_execute(p,
										   VARDATA(s),
										   VARSIZE(s) - VARHDRSZ,
										   regex_flavor,
										   0, NULL));
}


/*
 *	routines that use the regexp stuff, but ignore the case.
 *	for this, we use the REG_ICASE flag to pg_regcomp
 */


Datum
nameicregexeq(PG_FUNCTION_ARGS)
{
	Name		n = PG_GETARG_NAME(0);
	text	   *p = PG_GETARG_TEXT_P(1);

	PG_RETURN_BOOL(RE_compile_and_execute(p,
										  NameStr(*n),
										  strlen(NameStr(*n)),
										  regex_flavor | REG_ICASE,
										  0, NULL));
}

Datum
nameicregexne(PG_FUNCTION_ARGS)
{
	Name		n = PG_GETARG_NAME(0);
	text	   *p = PG_GETARG_TEXT_P(1);

	PG_RETURN_BOOL(!RE_compile_and_execute(p,
										   NameStr(*n),
										   strlen(NameStr(*n)),
										   regex_flavor | REG_ICASE,
										   0, NULL));
}

Datum
texticregexeq(PG_FUNCTION_ARGS)
{
	text	   *s = PG_GETARG_TEXT_P(0);
	text	   *p = PG_GETARG_TEXT_P(1);

	PG_RETURN_BOOL(RE_compile_and_execute(p,
										  VARDATA(s),
										  VARSIZE(s) - VARHDRSZ,
										  regex_flavor | REG_ICASE,
										  0, NULL));
}

Datum
texticregexne(PG_FUNCTION_ARGS)
{
	text	   *s = PG_GETARG_TEXT_P(0);
	text	   *p = PG_GETARG_TEXT_P(1);

	PG_RETURN_BOOL(!RE_compile_and_execute(p,
										   VARDATA(s),
										   VARSIZE(s) - VARHDRSZ,
										   regex_flavor | REG_ICASE,
										   0, NULL));
}


/*
 * textregexsubstr()
 *		Return a substring matched by a regular expression.
 */
Datum
textregexsubstr(PG_FUNCTION_ARGS)
{
	text	   *s = PG_GETARG_TEXT_P(0);
	text	   *p = PG_GETARG_TEXT_P(1);
	bool		match;
	regmatch_t	pmatch[2];

	/*
	 * We pass two regmatch_t structs to get info about the overall match and
	 * the match for the first parenthesized subexpression (if any). If there
	 * is a parenthesized subexpression, we return what it matched; else
	 * return what the whole regexp matched.
	 */
	match = RE_compile_and_execute(p,
								   VARDATA(s),
								   VARSIZE(s) - VARHDRSZ,
								   regex_flavor,
								   2, pmatch);

	/* match? then return the substring matching the pattern */
	if (match)
	{
		int			so,
					eo;

		so = pmatch[1].rm_so;
		eo = pmatch[1].rm_eo;
		if (so < 0 || eo < 0)
		{
			/* no parenthesized subexpression */
			so = pmatch[0].rm_so;
			eo = pmatch[0].rm_eo;
		}

		return DirectFunctionCall3(text_substr,
								   PointerGetDatum(s),
								   Int32GetDatum(so + 1),
								   Int32GetDatum(eo - so));
	}

	PG_RETURN_NULL();
}

/*
 * textregexreplace_noopt()
 *		Return a string matched by a regular expression, with replacement.
 *
 * This version doesn't have an option argument: we default to case
 * sensitive match, replace the first instance only.
 */
Datum
textregexreplace_noopt(PG_FUNCTION_ARGS)
{
	text	   *s = PG_GETARG_TEXT_P(0);
	text	   *p = PG_GETARG_TEXT_P(1);
	text	   *r = PG_GETARG_TEXT_P(2);
	regex_t    *re;

	re = RE_compile_and_cache(p, regex_flavor);

	PG_RETURN_TEXT_P(replace_text_regexp(s, (void *) re, r, false));
}

/*
 * textregexreplace()
 *		Return a string matched by a regular expression, with replacement.
 */
Datum
textregexreplace(PG_FUNCTION_ARGS)
{
	text	   *s = PG_GETARG_TEXT_P(0);
	text	   *p = PG_GETARG_TEXT_P(1);
	text	   *r = PG_GETARG_TEXT_P(2);
	text	   *opt = PG_GETARG_TEXT_P(3);
	char	   *opt_p = VARDATA(opt);
	int			opt_len = (VARSIZE(opt) - VARHDRSZ);
	int			i;
	bool		glob = false;
	bool		ignorecase = false;
	regex_t    *re;

	/* parse options */
	for (i = 0; i < opt_len; i++)
	{
		switch (opt_p[i])
		{
			case 'i':
				ignorecase = true;
				break;
			case 'g':
				glob = true;
				break;
			default:
				ereport(ERROR,
						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
						 errmsg("invalid option of regexp_replace: %c",
								opt_p[i])));
				break;
		}
	}

	if (ignorecase)
		re = RE_compile_and_cache(p, regex_flavor | REG_ICASE);
	else
		re = RE_compile_and_cache(p, regex_flavor);

	PG_RETURN_TEXT_P(replace_text_regexp(s, (void *) re, r, glob));
}

/* similar_escape()
 * Convert a SQL99 regexp pattern to POSIX style, so it can be used by
 * our regexp engine.
 */
Datum
similar_escape(PG_FUNCTION_ARGS)
{
	text	   *pat_text;
	text	   *esc_text;
	text	   *result;
	char	   *p,
			   *e,
			   *r;
	int			plen,
				elen;
	bool		afterescape = false;
	int			nquotes = 0;

	/* This function is not strict, so must test explicitly */
	if (PG_ARGISNULL(0))
		PG_RETURN_NULL();
	pat_text = PG_GETARG_TEXT_P(0);
	p = VARDATA(pat_text);
	plen = (VARSIZE(pat_text) - VARHDRSZ);
	if (PG_ARGISNULL(1))
	{
		/* No ESCAPE clause provided; default to backslash as escape */
		e = "\\";
		elen = 1;
	}
	else
	{
		esc_text = PG_GETARG_TEXT_P(1);
		e = VARDATA(esc_text);
		elen = (VARSIZE(esc_text) - VARHDRSZ);
		if (elen == 0)
			e = NULL;			/* no escape character */
		else if (elen != 1)
			ereport(ERROR,
					(errcode(ERRCODE_INVALID_ESCAPE_SEQUENCE),
					 errmsg("invalid escape string"),
				  errhint("Escape string must be empty or one character.")));
	}

	/*----------
	 * We surround the transformed input string with
	 *			***:^(?: ... )$
	 * which is bizarre enough to require some explanation.  "***:" is a
	 * director prefix to force the regex to be treated as an ARE regardless
	 * of the current regex_flavor setting.  We need "^" and "$" to force
	 * the pattern to match the entire input string as per SQL99 spec.  The
	 * "(?:" and ")" are a non-capturing set of parens; we have to have
	 * parens in case the string contains "|", else the "^" and "$" will
	 * be bound into the first and last alternatives which is not what we
	 * want, and the parens must be non capturing because we don't want them
	 * to count when selecting output for SUBSTRING.
	 *----------
	 */

	/*
	 * We need room for the prefix/postfix plus as many as 2 output bytes per
	 * input byte
	 */
	result = (text *) palloc(VARHDRSZ + 10 + 2 * plen);
	r = VARDATA(result);

	*r++ = '*';
	*r++ = '*';
	*r++ = '*';
	*r++ = ':';
	*r++ = '^';
	*r++ = '(';
	*r++ = '?';
	*r++ = ':';

	while (plen > 0)
	{
		char		pchar = *p;

		if (afterescape)
		{
			if (pchar == '"')	/* for SUBSTRING patterns */
				*r++ = ((nquotes++ % 2) == 0) ? '(' : ')';
			else
			{
				*r++ = '\\';
				*r++ = pchar;
			}
			afterescape = false;
		}
		else if (e && pchar == *e)
		{
			/* SQL99 escape character; do not send to output */
			afterescape = true;
		}
		else if (pchar == '%')
		{
			*r++ = '.';
			*r++ = '*';
		}
		else if (pchar == '_')
			*r++ = '.';
		else if (pchar == '\\' || pchar == '.' || pchar == '?' ||
				 pchar == '{')
		{
			*r++ = '\\';
			*r++ = pchar;
		}
		else
			*r++ = pchar;
		p++, plen--;
	}

	*r++ = ')';
	*r++ = '$';

	VARATT_SIZEP(result) = r - ((char *) result);

	PG_RETURN_TEXT_P(result);
}