database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-30 11:03:19 +03:00
Code Activity

Support indexing of regular-expression searches in contrib/pg_trgm.

Browse Source 
This works by extracting trigrams from the given regular expression,
in generally the same spirit as the previously-existing support for
LIKE searches, though of course the details are far more complicated.

Currently, only GIN indexes are supported.  We might be able to make
it work with GiST indexes later.

The implementation includes adding API functions to backend/regex/
to provide a view of the search NFA created from a regular expression.
These functions are meant to be generic enough to be supportable in
a standalone version of the regex library, should that ever happen.

Alexander Korotkov, reviewed by Heikki Linnakangas and Tom Lane
This commit is contained in:
Tom Lane
2013-04-09 01:05:55 -04:00
parent e60d20a35e
commit 3ccae48f44
17 changed files with 2865 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
contrib/pg_trgm/trgm_op.c
View File

@ -77,12 +77,6 @@ unique_array(trgm *a, int len)
return curend + 1 - a;
}
#ifdef KEEPONLYALNUM
#define iswordchr(c) (t_isalpha(c) || t_isdigit(c))
#else
#define iswordchr(c) (!t_isspace(c))
#endif
/*
* Finds first word in string, returns pointer to the word,
* endword points to the character after word
@ -92,7 +86,7 @@ find_word(char *str, int lenstr, char **endword, int *charlen)
{
char *beginword = str;
while (beginword - str < lenstr && !iswordchr(beginword))
while (beginword - str < lenstr && !ISWORDCHR(beginword))
beginword += pg_mblen(beginword);
if (beginword - str >= lenstr)
@ -100,7 +94,7 @@ find_word(char *str, int lenstr, char **endword, int *charlen)
*endword = beginword;
*charlen = 0;
while (*endword - str < lenstr && iswordchr(*endword))
while (*endword - str < lenstr && ISWORDCHR(*endword))
{
*endword += pg_mblen(*endword);
(*charlen)++;
@ -114,7 +108,7 @@ find_word(char *str, int lenstr, char **endword, int *charlen)
* which is always exactly three bytes. If we have three single-byte
* characters, we just use them as-is; otherwise we form a hash value.
*/
static void
void
compact_trigram(trgm *tptr, char *str, int bytelen)
{
if (bytelen == 3)
@ -290,7 +284,7 @@ get_wildcard_part(const char *str, int lenstr,
{
if (in_escape)
{
if (iswordchr(beginword))
if (ISWORDCHR(beginword))
break;
in_escape = false;
in_leading_wildcard_meta = false;
@ -301,7 +295,7 @@ get_wildcard_part(const char *str, int lenstr,
in_escape = true;
else if (ISWILDCARDCHAR(beginword))
in_leading_wildcard_meta = true;
else if (iswordchr(beginword))
else if (ISWORDCHR(beginword))
break;
else
in_leading_wildcard_meta = false;
@ -344,7 +338,7 @@ get_wildcard_part(const char *str, int lenstr,
clen = pg_mblen(endword);
if (in_escape)
{
if (iswordchr(endword))
if (ISWORDCHR(endword))
{
memcpy(s, endword, clen);
(*charlen)++;
@ -372,7 +366,7 @@ get_wildcard_part(const char *str, int lenstr,
in_trailing_wildcard_meta = true;
break;
}
else if (iswordchr(endword))
else if (ISWORDCHR(endword))
{
memcpy(s, endword, clen);
(*charlen)++;