/*
* RE_compile_and_execute - compile and execute a RE
*
* Returns TRUE on match, FALSE on no match
*
* text_re --- the pattern, expressed as a TEXT object
* dat --- the data to match against (need not be null-terminated)
* dat_len --- the length of the data string
* cflags --- compile options for the pattern
* nmatch, pmatch --- optional return area for match details
*
* Both pattern and data are given in the database encoding. We internally
* convert to array of pg_wchar which is what Spencer's regex package wants.
*/
static bool
RE_compile_and_execute(text *text_re, char *dat, int dat_len,
int cflags, int nmatch, regmatch_t *pmatch)
{
regex_t *re;
/* Compile RE */
re = RE_compile_and_cache(text_re, cflags);
return RE_execute(re, dat, dat_len, nmatch, pmatch);
}
/*
* textregexsubstr()
* Return a substring matched by a regular expression.
*/
Datum
textregexsubstr(PG_FUNCTION_ARGS)
{
text *s = PG_GETARG_TEXT_PP(0);
text *p = PG_GETARG_TEXT_PP(1);
regex_t *re;
regmatch_t pmatch[2];
int so,
eo;
/* Compile RE */
re = RE_compile_and_cache(p, REG_ADVANCED, PG_GET_COLLATION());
/*
* 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.
*/
if (!RE_execute(re,
VARDATA_ANY(s), VARSIZE_ANY_EXHDR(s),
2, pmatch))
PG_RETURN_NULL(); /* definitely no match */
if (re->re_nsub > 0)
{
/* has parenthesized subexpressions, use the first one */
so = pmatch[1].rm_so;
eo = pmatch[1].rm_eo;
}
else
{
/* no parenthesized subexpression, use whole match */
so = pmatch[0].rm_so;
eo = pmatch[0].rm_eo;
}
/*
* It is possible to have a match to the whole pattern but no match for a
* subexpression; for example 'foo(bar)?' is considered to match 'foo' but
* there is no subexpression match. So this extra test for match failure
* is not redundant.
*/
if (so < 0 || eo < 0)
PG_RETURN_NULL();
return DirectFunctionCall3(text_substr,
PointerGetDatum(s),
Int32GetDatum(so + 1),
Int32GetDatum(eo - so));
}