Ensure that a tsquery like '!foo' matches empty tsvectors.

!foo means "the tsvector does not contain foo", and therefore it should
match an empty tsvector.  ts_match_vq() overenthusiastically supposed
that an empty tsvector could never match any query, so it forcibly
returned FALSE, the wrong answer.  Remove the premature optimization.

Our behavior on this point was inconsistent, because while seqscans and
GIST index searches both failed to match empty tsvectors, GIN index
searches would find them, since GIN scans don't rely on ts_match_vq().
That makes this certainly a bug, not a debatable definition disagreement,
so back-patch to all supported branches.

Report and diagnosis by Tom Dunstan (bug #14515); added test cases by me.

Discussion: https://postgr.es/m/20170126025524.1434.97828@wrigleys.postgresql.org

diff --git a/src/backend/utils/adt/tsvector_op.c b/src/backend/utils/adt/tsvector_op.c
index eb5c45b3d81480e7ea56ca7eded8811e7018c477..5eca0ce21b9b4e3fe1db39adc839ee33122f5556 100644 (file)
--- a/src/backend/utils/adt/tsvector_op.c
+++ b/src/backend/utils/adt/tsvector_op.c
@@ -784,7 +784,8 @@ ts_match_vq(PG_FUNCTION_ARGS)
        CHKVAL          chkval;
        bool            result;
 
-       if (!val->size || !query->size)
+       /* empty query matches nothing */
+       if (!query->size)
        {
                PG_FREE_IF_COPY(val, 0);
                PG_FREE_IF_COPY(query, 1);

diff --git a/src/test/regress/expected/tsearch.out b/src/test/regress/expected/tsearch.out
index 31dab9309aa20eb0bdfb879529be1f143e8dc841..a2af064c10e273622a31e57c3b9af8bff9bbe455 100644 (file)
--- a/src/test/regress/expected/tsearch.out
+++ b/src/test/regress/expected/tsearch.out
@@ -98,8 +98,108 @@ SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
    494
 (1 row)
 
+SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
+ count 
+-------
+   158
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+ count 
+-------
+     0
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
+ count 
+-------
+   508
+(1 row)
+
 create index wowidx on test_tsvector using gist (a);
 SET enable_seqscan=OFF;
+SET enable_indexscan=ON;
+SET enable_bitmapscan=OFF;
+explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
+                      QUERY PLAN                       
+-------------------------------------------------------
+ Aggregate
+   ->  Index Scan using wowidx on test_tsvector
+         Index Cond: (a @@ '''wr'' | ''qh'''::tsquery)
+(3 rows)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
+ count 
+-------
+   158
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'wr&qh';
+ count 
+-------
+    17
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'eq&yt';
+ count 
+-------
+     6
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'eq|yt';
+ count 
+-------
+    98
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ '(eq&yt)|(wr&qh)';
+ count 
+-------
+    23
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ '(eq|yt)&(wr|qh)';
+ count 
+-------
+    39
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
+ count 
+-------
+   494
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
+ count 
+-------
+   158
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+ count 
+-------
+     0
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
+ count 
+-------
+   508
+(1 row)
+
+SET enable_indexscan=OFF;
+SET enable_bitmapscan=ON;
+explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
+                         QUERY PLAN                          
+-------------------------------------------------------------
+ Aggregate
+   ->  Bitmap Heap Scan on test_tsvector
+         Recheck Cond: (a @@ '''wr'' | ''qh'''::tsquery)
+         ->  Bitmap Index Scan on wowidx
+               Index Cond: (a @@ '''wr'' | ''qh'''::tsquery)
+(5 rows)
+
 SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
  count 
 -------
@@ -148,10 +248,35 @@ SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
    158
 (1 row)
 
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+ count 
+-------
+     0
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
+ count 
+-------
+   508
+(1 row)
+
 RESET enable_seqscan;
+RESET enable_indexscan;
+RESET enable_bitmapscan;
 DROP INDEX wowidx;
 CREATE INDEX wowidx ON test_tsvector USING gin (a);
 SET enable_seqscan=OFF;
+-- GIN only supports bitmapscan, so no need to test plain indexscan
+explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
+                         QUERY PLAN                          
+-------------------------------------------------------------
+ Aggregate
+   ->  Bitmap Heap Scan on test_tsvector
+         Recheck Cond: (a @@ '''wr'' | ''qh'''::tsquery)
+         ->  Bitmap Index Scan on wowidx
+               Index Cond: (a @@ '''wr'' | ''qh'''::tsquery)
+(5 rows)
+
 SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
  count 
 -------
@@ -200,6 +325,18 @@ SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
    158
 (1 row)
 
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+ count 
+-------
+     0
+(1 row)
+
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
+ count 
+-------
+   508
+(1 row)
+
 RESET enable_seqscan;
 INSERT INTO test_tsvector VALUES ('???', 'DFG:1A,2B,6C,10 FGH');
 SELECT * FROM ts_stat('SELECT a FROM test_tsvector') ORDER BY ndoc DESC, nentry DESC, word LIMIT 10;

diff --git a/src/test/regress/expected/tstypes.out b/src/test/regress/expected/tstypes.out
index 6284fb6181340dd806089384c8d74e9392869132..da4c760175bac00ac544a0e3fd3eb56a226dadf1 100644 (file)
--- a/src/test/regress/expected/tstypes.out
+++ b/src/test/regress/expected/tstypes.out
@@ -625,3 +625,15 @@ SELECT ts_rank_cd(' a:1 s:2 d g'::tsvector, 'a & s');
         0.1
 (1 row)
 
+select to_tsvector('simple', 'x y q y') @@ '!foo' AS "true";
+ true 
+------
+ t
+(1 row)
+
+select to_tsvector('simple', '') @@ '!foo' AS "true";
+ true 
+------
+ t
+(1 row)
+

diff --git a/src/test/regress/sql/tsearch.sql b/src/test/regress/sql/tsearch.sql
index df2d54581410126923f5eba281c229ddf4cde754..00c9cf6ab6020b60fbdd24a43b12aaa43eecb3f7 100644 (file)
--- a/src/test/regress/sql/tsearch.sql
+++ b/src/test/regress/sql/tsearch.sql
@@ -48,10 +48,17 @@ SELECT count(*) FROM test_tsvector WHERE a @@ 'eq|yt';
 SELECT count(*) FROM test_tsvector WHERE a @@ '(eq&yt)|(wr&qh)';
 SELECT count(*) FROM test_tsvector WHERE a @@ '(eq|yt)&(wr|qh)';
 SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
+SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
 
 create index wowidx on test_tsvector using gist (a);
 
 SET enable_seqscan=OFF;
+SET enable_indexscan=ON;
+SET enable_bitmapscan=OFF;
+
+explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
 
 SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
 SELECT count(*) FROM test_tsvector WHERE a @@ 'wr&qh';
@@ -61,14 +68,37 @@ SELECT count(*) FROM test_tsvector WHERE a @@ '(eq&yt)|(wr&qh)';
 SELECT count(*) FROM test_tsvector WHERE a @@ '(eq|yt)&(wr|qh)';
 SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
 SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
+
+SET enable_indexscan=OFF;
+SET enable_bitmapscan=ON;
+
+explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
+
+SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
+SELECT count(*) FROM test_tsvector WHERE a @@ 'wr&qh';
+SELECT count(*) FROM test_tsvector WHERE a @@ 'eq&yt';
+SELECT count(*) FROM test_tsvector WHERE a @@ 'eq|yt';
+SELECT count(*) FROM test_tsvector WHERE a @@ '(eq&yt)|(wr&qh)';
+SELECT count(*) FROM test_tsvector WHERE a @@ '(eq|yt)&(wr|qh)';
+SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
+SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
 
 RESET enable_seqscan;
+RESET enable_indexscan;
+RESET enable_bitmapscan;
 
 DROP INDEX wowidx;
 
 CREATE INDEX wowidx ON test_tsvector USING gin (a);
 
 SET enable_seqscan=OFF;
+-- GIN only supports bitmapscan, so no need to test plain indexscan
+
+explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
 
 SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
 SELECT count(*) FROM test_tsvector WHERE a @@ 'wr&qh';
@@ -78,8 +108,11 @@ SELECT count(*) FROM test_tsvector WHERE a @@ '(eq&yt)|(wr&qh)';
 SELECT count(*) FROM test_tsvector WHERE a @@ '(eq|yt)&(wr|qh)';
 SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
 SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
+SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
+SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
 
 RESET enable_seqscan;
+
 INSERT INTO test_tsvector VALUES ('???', 'DFG:1A,2B,6C,10 FGH');
 SELECT * FROM ts_stat('SELECT a FROM test_tsvector') ORDER BY ndoc DESC, nentry DESC, word LIMIT 10;
 SELECT * FROM ts_stat('SELECT a FROM test_tsvector', 'AB') ORDER BY ndoc DESC, nentry DESC, word;

diff --git a/src/test/regress/sql/tstypes.sql b/src/test/regress/sql/tstypes.sql
index fd7c7024f5e547018323b1766eb229afb8c541d9..6bc47c007f70a502968c7a4576bb4dd392549144 100644 (file)
--- a/src/test/regress/sql/tstypes.sql
+++ b/src/test/regress/sql/tstypes.sql
@@ -115,3 +115,6 @@ SELECT ts_rank_cd(' a:1 s:2 d g'::tsvector, 'a | s');
 SELECT ts_rank_cd(' a:1 s:2C d g'::tsvector, 'a & s');
 SELECT ts_rank_cd(' a:1 s:2B d g'::tsvector, 'a & s');
 SELECT ts_rank_cd(' a:1 s:2 d g'::tsvector, 'a & s');
+
+select to_tsvector('simple', 'x y q y') @@ '!foo' AS "true";
+select to_tsvector('simple', '') @@ '!foo' AS "true";