/*
* pg_set_regex_collation: set collation for these functions to obey
*
* This is called when beginning compilation or execution of a regexp.
* Since there's no need for re-entrancy of regexp operations, it's okay
* to store the results in static variables.
*/
void
pg_set_regex_collation(Oid collation)
{
if (lc_ctype_is_c(collation))
{
/* C/POSIX collations use this path regardless of database encoding */
pg_regex_strategy = PG_REGEX_LOCALE_C;
pg_regex_locale = 0;
pg_regex_collation = C_COLLATION_OID;
}
else
{
if (collation == DEFAULT_COLLATION_OID)
pg_regex_locale = 0;
else if (OidIsValid(collation))
{
/*
* NB: pg_newlocale_from_collation will fail if not HAVE_LOCALE_T;
* the case of pg_regex_locale != 0 but not HAVE_LOCALE_T does not
* have to be considered below.
*/
pg_regex_locale = pg_newlocale_from_collation(collation);
}
else
{
/*
* This typically means that the parser could not resolve a
* conflict of implicit collations, so report it that way.
*/
ereport(ERROR,
(errcode(ERRCODE_INDETERMINATE_COLLATION),
errmsg("could not determine which collation to use for regular expression"),
errhint("Use the COLLATE clause to set the collation explicitly.")));
}
#ifdef USE_WIDE_UPPER_LOWER
if (GetDatabaseEncoding() == PG_UTF8)
{
if (pg_regex_locale)
pg_regex_strategy = PG_REGEX_LOCALE_WIDE_L;
else
pg_regex_strategy = PG_REGEX_LOCALE_WIDE;
}
else
#endif /* USE_WIDE_UPPER_LOWER */
{
if (pg_regex_locale)
pg_regex_strategy = PG_REGEX_LOCALE_1BYTE_L;
else
pg_regex_strategy = PG_REGEX_LOCALE_1BYTE;
}
pg_regex_collation = collation;
}
}
static inline int
Generic_Text_IC_like(text *str, text *pat, Oid collation)
{
char *s,
*p;
int slen,
plen;
/*
* For efficiency reasons, in the single byte case we don't call lower()
* on the pattern and text, but instead call SB_lower_char on each
* character. In the multi-byte case we don't have much choice :-(
*/
if (pg_database_encoding_max_length() > 1)
{
/* lower's result is never packed, so OK to use old macros here */
pat = DatumGetTextP(DirectFunctionCall1Coll(lower, collation,
PointerGetDatum(pat)));
p = VARDATA(pat);
plen = (VARSIZE(pat) - VARHDRSZ);
str = DatumGetTextP(DirectFunctionCall1Coll(lower, collation,
PointerGetDatum(str)));
s = VARDATA(str);
slen = (VARSIZE(str) - VARHDRSZ);
if (GetDatabaseEncoding() == PG_UTF8)
return UTF8_MatchText(s, slen, p, plen, 0, true);
else
return MB_MatchText(s, slen, p, plen, 0, true);
}
else
{
/*
* Here we need to prepare locale information for SB_lower_char. This
* should match the methods used in str_tolower().
*/
pg_locale_t locale = 0;
bool locale_is_c = false;
if (lc_ctype_is_c(collation))
locale_is_c = true;
else if (collation != DEFAULT_COLLATION_OID)
{
if (!OidIsValid(collation))
{
/*
* This typically means that the parser could not resolve a
* conflict of implicit collations, so report it that way.
*/
ereport(ERROR,
(errcode(ERRCODE_INDETERMINATE_COLLATION),
errmsg("could not determine which collation to use for ILIKE"),
errhint("Use the COLLATE clause to set the collation explicitly.")));
}
locale = pg_newlocale_from_collation(collation);
}
p = VARDATA_ANY(pat);
plen = VARSIZE_ANY_EXHDR(pat);
s = VARDATA_ANY(str);
slen = VARSIZE_ANY_EXHDR(str);
return SB_IMatchText(s, slen, p, plen, locale, locale_is_c);
}
}
