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

49
contrib/pg_trgm/trgm_gin.c
View File

@ -80,13 +80,15 @@ gin_extract_query_trgm(PG_FUNCTION_ARGS)
StrategyNumber strategy = PG_GETARG_UINT16(2);
/* bool **pmatch = (bool **) PG_GETARG_POINTER(3); */
/* Pointer *extra_data = (Pointer *) PG_GETARG_POINTER(4); */
Pointer **extra_data = (Pointer **) PG_GETARG_POINTER(4);
/* bool **nullFlags = (bool **) PG_GETARG_POINTER(5); */
int32 *searchMode = (int32 *) PG_GETARG_POINTER(6);
Datum *entries = NULL;
TRGM *trg;
int32 trglen;
trgm *ptr;
TrgmPackedGraph *graph;
int32 i;
switch (strategy)
@ -107,6 +109,33 @@ gin_extract_query_trgm(PG_FUNCTION_ARGS)
*/
trg = generate_wildcard_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
break;
case RegExpICaseStrategyNumber:
#ifndef IGNORECASE
elog(ERROR, "cannot handle ~* with case-sensitive trigrams");
#endif
/* FALL THRU */
case RegExpStrategyNumber:
trg = createTrgmNFA(val, &graph, PG_GET_COLLATION());
if (trg && ARRNELEM(trg) > 0)
{
/*
* Successful regex processing: store NFA-like graph as
* extra_data. GIN API requires an array of nentries
* Pointers, but we just put the same value in each element.
*/
trglen = ARRNELEM(trg);
*extra_data = (Pointer *) palloc(sizeof(Pointer) * trglen);
for (i = 0; i < trglen; i++)
(*extra_data)[i] = (Pointer) graph;
}
else
{
/* No result: have to do full index scan. */
*nentries = 0;
*searchMode = GIN_SEARCH_MODE_ALL;
PG_RETURN_POINTER(entries);
}
break;
default:
elog(ERROR, "unrecognized strategy number: %d", strategy);
trg = NULL; /* keep compiler quiet */
@ -146,8 +175,7 @@ gin_trgm_consistent(PG_FUNCTION_ARGS)
/* text *query = PG_GETARG_TEXT_P(2); */
int32 nkeys = PG_GETARG_INT32(3);
/* Pointer *extra_data = (Pointer *) PG_GETARG_POINTER(4); */
Pointer *extra_data = (Pointer *) PG_GETARG_POINTER(4);
bool *recheck = (bool *) PG_GETARG_POINTER(5);
bool res;
int32 i,
@ -189,6 +217,21 @@ gin_trgm_consistent(PG_FUNCTION_ARGS)
}
}
break;
case RegExpICaseStrategyNumber:
#ifndef IGNORECASE
elog(ERROR, "cannot handle ~* with case-sensitive trigrams");
#endif
/* FALL THRU */
case RegExpStrategyNumber:
if (nkeys < 1)
{
/* Regex processing gave no result: do full index scan */
res = true;
}
else
res = trigramsMatchGraph((TrgmPackedGraph *) extra_data[0],
check);
break;
default:
elog(ERROR, "unrecognized strategy number: %d", strategy);
res = false; /* keep compiler quiet */