Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commitb8c798e

Browse files
committed
Tweak tsmatchsel() so that it examines the structure of the tsquery whenever
possible (ie, whenever the tsquery is a constant), even when no statisticsare available for the tsvector. For example, foo @@ 'a & b'::tsquerycan be expected to be more selective than foo @@ 'a'::tsquery, whetheror not we know anything about foo. We use DEFAULT_TS_MATCH_SEL as the assumedselectivity of individual query terms when no stats are available, thencombine the terms according to the query's AND/OR structure as usual.Per experimentation with Artur Dabrowski's example. (The fact that thereare no stats available in that example is a problem in itself, butnonetheless tsmatchsel should be smarter about the case.)Back-patch to 8.4 to keep all versions of tsmatchsel() in sync.
1 parent2ab57e0 commitb8c798e

File tree

1 file changed

+25
-16
lines changed

1 file changed

+25
-16
lines changed

‎src/backend/tsearch/ts_selfuncs.c

Lines changed: 25 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77
*
88
*
99
* IDENTIFICATION
10-
* $PostgreSQL: pgsql/src/backend/tsearch/ts_selfuncs.c,v 1.7 2010/01/04 02:44:39 tgl Exp $
10+
* $PostgreSQL: pgsql/src/backend/tsearch/ts_selfuncs.c,v 1.8 2010/07/31 03:27:40 tgl Exp $
1111
*
1212
*-------------------------------------------------------------------------
1313
*/
@@ -52,6 +52,9 @@ static Selectivity tsquery_opr_selec(QueryItem *item, char *operand,
5252
TextFreq*lookup,intlength,float4minfreq);
5353
staticintcompare_lexeme_textfreq(constvoid*e1,constvoid*e2);
5454

55+
#definetsquery_opr_selec_no_stats(query) \
56+
tsquery_opr_selec(GETQUERY(query), GETOPERAND(query), NULL, 0, 0)
57+
5558

5659
/*
5760
*tsmatchsel -- Selectivity of "@@"
@@ -101,21 +104,20 @@ tsmatchsel(PG_FUNCTION_ARGS)
101104
}
102105

103106
/*
104-
* OK, there's a Var and a Const we're dealing with here. We need the Var
105-
* to be a TSVector (or else we don't have any useful statistic for it).
106-
* We have to check this because the Var might be the TSQuery not the
107-
* TSVector.
107+
* OK, there's a Var and a Const we're dealing with here. We need the
108+
* Const to be a TSQuery, else we can't do anything useful. We have to
109+
* check this because the Var might be the TSQuery not the TSVector.
108110
*/
109-
if (vardata.vartype==TSVECTOROID)
111+
if (((Const*)other)->consttype==TSQUERYOID)
110112
{
111113
/* tsvector @@ tsquery or the other way around */
112-
Assert(((Const*)other)->consttype==TSQUERYOID);
114+
Assert(vardata.vartype==TSVECTOROID);
113115

114116
selec=tsquerysel(&vardata, ((Const*)other)->constvalue);
115117
}
116118
else
117119
{
118-
/*The Var is somethingwedon'thave useful statistics for */
120+
/*Ifwecan'tsee the query structure, must punt */
119121
selec=DEFAULT_TS_MATCH_SEL;
120122
}
121123

@@ -184,14 +186,14 @@ tsquerysel(VariableStatData *vardata, Datum constval)
184186
}
185187
else
186188
{
187-
/* No most-common-elements info, sowe must punt */
188-
selec=(Selectivity)DEFAULT_TS_MATCH_SEL;
189+
/* No most-common-elements info, sodo without */
190+
selec=tsquery_opr_selec_no_stats(query);
189191
}
190192
}
191193
else
192194
{
193-
/* No stats at all, sowe must punt */
194-
selec=(Selectivity)DEFAULT_TS_MATCH_SEL;
195+
/* No stats at all, sodo without */
196+
selec=tsquery_opr_selec_no_stats(query);
195197
}
196198

197199
returnselec;
@@ -214,7 +216,7 @@ mcelem_tsquery_selec(TSQuery query, Datum *mcelem, int nmcelem,
214216
* cells are taken for minimal and maximal frequency. Punt if not.
215217
*/
216218
if (nnumbers!=nmcelem+2)
217-
returnDEFAULT_TS_MATCH_SEL;
219+
returntsquery_opr_selec_no_stats(query);
218220

219221
/*
220222
* Transpose the data into a single array so we can use bsearch().
@@ -258,9 +260,12 @@ mcelem_tsquery_selec(TSQuery query, Datum *mcelem, int nmcelem,
258260
* freq[val] in VAL nodes, if the value is in MCELEM
259261
* min(freq[MCELEM]) / 2 in VAL nodes, if it is not
260262
*
261-
*
262263
* The MCELEM array is already sorted (see ts_typanalyze.c), so we can use
263264
* binary search for determining freq[MCELEM].
265+
*
266+
* If we don't have stats for the tsvector, we still use this logic,
267+
* except we always use DEFAULT_TS_MATCH_SEL for VAL nodes. This case
268+
* is signaled by lookup == NULL.
264269
*/
265270
staticSelectivity
266271
tsquery_opr_selec(QueryItem*item,char*operand,
@@ -279,6 +284,10 @@ tsquery_opr_selec(QueryItem *item, char *operand,
279284
{
280285
QueryOperand*oper= (QueryOperand*)item;
281286

287+
/* If no stats for the variable, use DEFAULT_TS_MATCH_SEL */
288+
if (lookup==NULL)
289+
return (Selectivity)DEFAULT_TS_MATCH_SEL;
290+
282291
/*
283292
* Prepare the key for bsearch().
284293
*/
@@ -292,15 +301,15 @@ tsquery_opr_selec(QueryItem *item, char *operand,
292301
if (searchres)
293302
{
294303
/*
295-
* The element is in MCELEM. Return precise selectivity (or at
304+
* The element is in MCELEM.Return precise selectivity (or at
296305
* least as precise as ANALYZE could find out).
297306
*/
298307
return (Selectivity)searchres->frequency;
299308
}
300309
else
301310
{
302311
/*
303-
* The element is not in MCELEM. Punt, butassert that the
312+
* The element is not in MCELEM.Punt, butassume that the
304313
* selectivity cannot be more than minfreq / 2.
305314
*/
306315
return (Selectivity)Min(DEFAULT_TS_MATCH_SEL,minfreq /2);

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp