2007-08-21 03:11:32 +02:00
|
|
|
--
|
|
|
|
-- Sanity checks for text search catalogs
|
|
|
|
--
|
|
|
|
-- NB: we assume the oidjoins test will have caught any dangling links,
|
|
|
|
-- that is OID or REGPROC fields that are not zero and do not match some
|
|
|
|
-- row in the linked-to table. However, if we want to enforce that a link
|
|
|
|
-- field can't be 0, we have to check it here.
|
|
|
|
|
|
|
|
-- Find unexpected zero link entries
|
|
|
|
|
|
|
|
SELECT oid, prsname
|
|
|
|
FROM pg_ts_parser
|
|
|
|
WHERE prsnamespace = 0 OR prsstart = 0 OR prstoken = 0 OR prsend = 0 OR
|
|
|
|
-- prsheadline is optional
|
|
|
|
prslextype = 0;
|
|
|
|
|
|
|
|
SELECT oid, dictname
|
|
|
|
FROM pg_ts_dict
|
|
|
|
WHERE dictnamespace = 0 OR dictowner = 0 OR dicttemplate = 0;
|
|
|
|
|
|
|
|
SELECT oid, tmplname
|
|
|
|
FROM pg_ts_template
|
|
|
|
WHERE tmplnamespace = 0 OR tmpllexize = 0; -- tmplinit is optional
|
|
|
|
|
|
|
|
SELECT oid, cfgname
|
|
|
|
FROM pg_ts_config
|
|
|
|
WHERE cfgnamespace = 0 OR cfgowner = 0 OR cfgparser = 0;
|
|
|
|
|
|
|
|
SELECT mapcfg, maptokentype, mapseqno
|
|
|
|
FROM pg_ts_config_map
|
|
|
|
WHERE mapcfg = 0 OR mapdict = 0;
|
|
|
|
|
|
|
|
-- Look for pg_ts_config_map entries that aren't one of parser's token types
|
|
|
|
SELECT * FROM
|
|
|
|
( SELECT oid AS cfgid, (ts_token_type(cfgparser)).tokid AS tokid
|
2010-11-23 21:27:50 +01:00
|
|
|
FROM pg_ts_config ) AS tt
|
2007-08-21 03:11:32 +02:00
|
|
|
RIGHT JOIN pg_ts_config_map AS m
|
|
|
|
ON (tt.cfgid=m.mapcfg AND tt.tokid=m.maptokentype)
|
|
|
|
WHERE
|
|
|
|
tt.cfgid IS NULL OR tt.tokid IS NULL;
|
|
|
|
|
|
|
|
-- test basic text search behavior without indexes, then with
|
|
|
|
|
|
|
|
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)';
|
2008-05-16 18:31:02 +02:00
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
|
2017-01-26 18:17:47 +01:00
|
|
|
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';
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
create index wowidx on test_tsvector using gist (a);
|
|
|
|
|
|
|
|
SET enable_seqscan=OFF;
|
2017-01-26 18:17:47 +01:00
|
|
|
SET enable_indexscan=ON;
|
|
|
|
SET enable_bitmapscan=OFF;
|
|
|
|
|
|
|
|
explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
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)';
|
2008-05-16 18:31:02 +02:00
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
|
2011-12-21 01:57:34 +01:00
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
|
2017-01-26 18:17:47 +01:00
|
|
|
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';
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
RESET enable_seqscan;
|
2017-01-26 18:17:47 +01:00
|
|
|
RESET enable_indexscan;
|
|
|
|
RESET enable_bitmapscan;
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
DROP INDEX wowidx;
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
CREATE INDEX wowidx ON test_tsvector USING gin (a);
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
SET enable_seqscan=OFF;
|
2017-01-26 18:17:47 +01:00
|
|
|
-- GIN only supports bitmapscan, so no need to test plain indexscan
|
|
|
|
|
|
|
|
explain (costs off) SELECT count(*) FROM test_tsvector WHERE a @@ 'wr|qh';
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
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)';
|
2008-05-16 18:31:02 +02:00
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ 'w:*|q:*';
|
2011-12-21 01:57:34 +01:00
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ any ('{wr,qh}');
|
2017-01-26 18:17:47 +01:00
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ 'no_such_lexeme';
|
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ '!no_such_lexeme';
|
2010-11-23 21:27:50 +01:00
|
|
|
|
2007-08-21 03:11:32 +02:00
|
|
|
RESET enable_seqscan;
|
2017-01-26 18:17:47 +01:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
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;
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
--dictionaries and to_tsvector
|
|
|
|
|
2007-08-25 03:06:25 +02:00
|
|
|
SELECT ts_lexize('english_stem', 'skies');
|
|
|
|
SELECT ts_lexize('english_stem', 'identity');
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT * FROM ts_token_type('default');
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2016-03-29 16:59:58 +02:00
|
|
|
SELECT * FROM ts_parse('default', '345 qwe@efd.r '' http://www.com/ http://aew.werc.ewr/?ad=qwe&dw 1aew.werc.ewr/?ad=qwe&dw 2aew.werc.ewr http://3aew.werc.ewr/?ad=qwe&dw http://4aew.werc.ewr http://5aew.werc.ewr:8100/? ad=qwe&dw 6aew.werc.ewr:8100/?ad=qwe&dw 7aew.werc.ewr:8100/?ad=qwe&dw=%20%32 +4.0e-10 qwe qwe qwqwe 234.435 455 5.005 teodor@stack.net teodor@123-stack.net 123_teodor@stack.net 123-teodor@stack.net qwe-wer asdf <fr>qwer jf sdjk<we hjwer <werrwe> ewr1> ewri2 <a href="qwe<qwe>">
|
2007-08-21 03:11:32 +02:00
|
|
|
/usr/local/fff /awdf/dwqe/4325 rewt/ewr wefjn /wqe-324/ewr gist.h gist.h.c gist.c. readline 4.2 4.2. 4.2, readline-4.2 readline-4.2. 234
|
|
|
|
<i <b> wow < jqw <> qwerty');
|
|
|
|
|
2016-03-29 16:59:58 +02:00
|
|
|
SELECT to_tsvector('english', '345 qwe@efd.r '' http://www.com/ http://aew.werc.ewr/?ad=qwe&dw 1aew.werc.ewr/?ad=qwe&dw 2aew.werc.ewr http://3aew.werc.ewr/?ad=qwe&dw http://4aew.werc.ewr http://5aew.werc.ewr:8100/? ad=qwe&dw 6aew.werc.ewr:8100/?ad=qwe&dw 7aew.werc.ewr:8100/?ad=qwe&dw=%20%32 +4.0e-10 qwe qwe qwqwe 234.435 455 5.005 teodor@stack.net teodor@123-stack.net 123_teodor@stack.net 123-teodor@stack.net qwe-wer asdf <fr>qwer jf sdjk<we hjwer <werrwe> ewr1> ewri2 <a href="qwe<qwe>">
|
2007-08-21 03:11:32 +02:00
|
|
|
/usr/local/fff /awdf/dwqe/4325 rewt/ewr wefjn /wqe-324/ewr gist.h gist.h.c gist.c. readline 4.2 4.2. 4.2, readline-4.2 readline-4.2. 234
|
|
|
|
<i <b> wow < jqw <> qwerty');
|
|
|
|
|
2016-03-29 16:59:58 +02:00
|
|
|
SELECT length(to_tsvector('english', '345 qwe@efd.r '' http://www.com/ http://aew.werc.ewr/?ad=qwe&dw 1aew.werc.ewr/?ad=qwe&dw 2aew.werc.ewr http://3aew.werc.ewr/?ad=qwe&dw http://4aew.werc.ewr http://5aew.werc.ewr:8100/? ad=qwe&dw 6aew.werc.ewr:8100/?ad=qwe&dw 7aew.werc.ewr:8100/?ad=qwe&dw=%20%32 +4.0e-10 qwe qwe qwqwe 234.435 455 5.005 teodor@stack.net teodor@123-stack.net 123_teodor@stack.net 123-teodor@stack.net qwe-wer asdf <fr>qwer jf sdjk<we hjwer <werrwe> ewr1> ewri2 <a href="qwe<qwe>">
|
2007-08-21 03:11:32 +02:00
|
|
|
/usr/local/fff /awdf/dwqe/4325 rewt/ewr wefjn /wqe-324/ewr gist.h gist.h.c gist.c. readline 4.2 4.2. 4.2, readline-4.2 readline-4.2. 234
|
|
|
|
<i <b> wow < jqw <> qwerty'));
|
|
|
|
|
2007-11-25 16:37:11 +01:00
|
|
|
-- ts_debug
|
|
|
|
|
2008-01-13 22:17:46 +01:00
|
|
|
SELECT * from ts_debug('english', '<myns:foo-bar_baz.blurfl>abc&nm1;def©ghiõjkl</myns:foo-bar_baz.blurfl>');
|
2007-11-25 16:37:11 +01:00
|
|
|
|
Modify the built-in text search parser to handle URLs more nearly according
to RFC 3986. In particular, these characters now terminate the path part
of a URL: '"', '<', '>', '\', '^', '`', '{', '|', '}'. The previous behavior
was inconsistent and depended on whether a "?" was present in the path.
Per gripe from Donald Fraser and spec research by Kevin Grittner.
This is a pre-existing bug, but not back-patching since the risks of
breaking existing applications seem to outweigh the benefits.
2010-04-28 04:04:16 +02:00
|
|
|
-- check parsing of URLs
|
|
|
|
SELECT * from ts_debug('english', 'http://www.harewoodsolutions.co.uk/press.aspx</span>');
|
|
|
|
SELECT * from ts_debug('english', 'http://aew.wer0c.ewr/id?ad=qwe&dw<span>');
|
|
|
|
SELECT * from ts_debug('english', 'http://5aew.werc.ewr:8100/?');
|
|
|
|
SELECT * from ts_debug('english', '5aew.werc.ewr:8100/?xx');
|
|
|
|
|
2007-08-21 03:11:32 +02:00
|
|
|
-- to_tsquery
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT to_tsquery('english', 'qwe & sKies ');
|
|
|
|
SELECT to_tsquery('simple', 'qwe & sKies ');
|
|
|
|
SELECT to_tsquery('english', '''the wether'':dc & '' sKies '':BC ');
|
|
|
|
SELECT to_tsquery('english', 'asd&(and|fghj)');
|
|
|
|
SELECT to_tsquery('english', '(asd&and)|fghj');
|
|
|
|
SELECT to_tsquery('english', '(asd&!and)|fghj');
|
|
|
|
SELECT to_tsquery('english', '(the|and&(i&1))&fghj');
|
|
|
|
|
|
|
|
SELECT plainto_tsquery('english', 'the and z 1))& fghj');
|
|
|
|
SELECT plainto_tsquery('english', 'foo bar') && plainto_tsquery('english', 'asd');
|
|
|
|
SELECT plainto_tsquery('english', 'foo bar') || plainto_tsquery('english', 'asd fg');
|
|
|
|
SELECT plainto_tsquery('english', 'foo bar') || !!plainto_tsquery('english', 'asd fg');
|
|
|
|
SELECT plainto_tsquery('english', 'foo bar') && 'asd | fg';
|
|
|
|
|
2016-04-07 17:44:18 +02:00
|
|
|
-- Check stop word deletion, a and s are stop-words
|
2016-07-15 18:22:18 +02:00
|
|
|
SELECT to_tsquery('english', '!(a & !b) & c');
|
|
|
|
SELECT to_tsquery('english', '!(a & !b)');
|
|
|
|
|
2016-04-07 17:44:18 +02:00
|
|
|
SELECT to_tsquery('english', '(1 <-> 2) <-> a');
|
|
|
|
SELECT to_tsquery('english', '(1 <-> a) <-> 2');
|
|
|
|
SELECT to_tsquery('english', '(a <-> 1) <-> 2');
|
|
|
|
SELECT to_tsquery('english', 'a <-> (1 <-> 2)');
|
|
|
|
SELECT to_tsquery('english', '1 <-> (a <-> 2)');
|
|
|
|
SELECT to_tsquery('english', '1 <-> (2 <-> a)');
|
|
|
|
|
|
|
|
SELECT to_tsquery('english', '(1 <-> 2) <3> a');
|
|
|
|
SELECT to_tsquery('english', '(1 <-> a) <3> 2');
|
|
|
|
SELECT to_tsquery('english', '(a <-> 1) <3> 2');
|
|
|
|
SELECT to_tsquery('english', 'a <3> (1 <-> 2)');
|
|
|
|
SELECT to_tsquery('english', '1 <3> (a <-> 2)');
|
|
|
|
SELECT to_tsquery('english', '1 <3> (2 <-> a)');
|
|
|
|
|
|
|
|
SELECT to_tsquery('english', '(1 <3> 2) <-> a');
|
|
|
|
SELECT to_tsquery('english', '(1 <3> a) <-> 2');
|
|
|
|
SELECT to_tsquery('english', '(a <3> 1) <-> 2');
|
|
|
|
SELECT to_tsquery('english', 'a <-> (1 <3> 2)');
|
|
|
|
SELECT to_tsquery('english', '1 <-> (a <3> 2)');
|
|
|
|
SELECT to_tsquery('english', '1 <-> (2 <3> a)');
|
|
|
|
|
|
|
|
SELECT to_tsquery('english', '((a <-> 1) <-> 2) <-> s');
|
|
|
|
SELECT to_tsquery('english', '(2 <-> (a <-> 1)) <-> s');
|
|
|
|
SELECT to_tsquery('english', '((1 <-> a) <-> 2) <-> s');
|
|
|
|
SELECT to_tsquery('english', '(2 <-> (1 <-> a)) <-> s');
|
|
|
|
SELECT to_tsquery('english', 's <-> ((a <-> 1) <-> 2)');
|
|
|
|
SELECT to_tsquery('english', 's <-> (2 <-> (a <-> 1))');
|
|
|
|
SELECT to_tsquery('english', 's <-> ((1 <-> a) <-> 2)');
|
|
|
|
SELECT to_tsquery('english', 's <-> (2 <-> (1 <-> a))');
|
|
|
|
|
|
|
|
SELECT to_tsquery('english', '((a <-> 1) <-> s) <-> 2');
|
|
|
|
SELECT to_tsquery('english', '(s <-> (a <-> 1)) <-> 2');
|
|
|
|
SELECT to_tsquery('english', '((1 <-> a) <-> s) <-> 2');
|
|
|
|
SELECT to_tsquery('english', '(s <-> (1 <-> a)) <-> 2');
|
|
|
|
SELECT to_tsquery('english', '2 <-> ((a <-> 1) <-> s)');
|
|
|
|
SELECT to_tsquery('english', '2 <-> (s <-> (a <-> 1))');
|
|
|
|
SELECT to_tsquery('english', '2 <-> ((1 <-> a) <-> s)');
|
|
|
|
SELECT to_tsquery('english', '2 <-> (s <-> (1 <-> a))');
|
|
|
|
|
2016-04-07 18:28:31 +02:00
|
|
|
SELECT to_tsquery('english', 'foo <-> (a <-> (the <-> bar))');
|
|
|
|
SELECT to_tsquery('english', '((foo <-> a) <-> the) <-> bar');
|
|
|
|
SELECT to_tsquery('english', 'foo <-> a <-> the <-> bar');
|
|
|
|
SELECT phraseto_tsquery('english', 'PostgreSQL can be extended by the user in many ways');
|
2016-04-07 17:44:18 +02:00
|
|
|
|
|
|
|
|
2007-12-09 22:01:18 +01:00
|
|
|
SELECT ts_rank_cd(to_tsvector('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
2007-12-10 01:12:31 +01:00
|
|
|
S. T. Coleridge (1772-1834)
|
2007-12-09 22:01:18 +01:00
|
|
|
'), to_tsquery('english', 'paint&water'));
|
|
|
|
|
|
|
|
SELECT ts_rank_cd(to_tsvector('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
2007-12-10 01:12:31 +01:00
|
|
|
S. T. Coleridge (1772-1834)
|
2007-12-09 22:01:18 +01:00
|
|
|
'), to_tsquery('english', 'breath&motion&water'));
|
|
|
|
|
|
|
|
SELECT ts_rank_cd(to_tsvector('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
2007-12-10 01:12:31 +01:00
|
|
|
S. T. Coleridge (1772-1834)
|
2007-12-09 22:01:18 +01:00
|
|
|
'), to_tsquery('english', 'ocean'));
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2016-04-07 17:44:18 +02:00
|
|
|
SELECT ts_rank_cd(to_tsvector('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
|
|
|
S. T. Coleridge (1772-1834)
|
|
|
|
'), to_tsquery('english', 'painted <-> Ship'));
|
|
|
|
|
2014-03-24 19:36:36 +01:00
|
|
|
SELECT ts_rank_cd(strip(to_tsvector('both stripped')),
|
|
|
|
to_tsquery('both & stripped'));
|
|
|
|
|
|
|
|
SELECT ts_rank_cd(to_tsvector('unstripped') || strip(to_tsvector('stripped')),
|
|
|
|
to_tsquery('unstripped & stripped'));
|
|
|
|
|
2007-08-21 03:11:32 +02:00
|
|
|
--headline tests
|
2007-12-09 22:01:18 +01:00
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
2007-12-10 01:12:31 +01:00
|
|
|
S. T. Coleridge (1772-1834)
|
2007-12-09 22:01:18 +01:00
|
|
|
', to_tsquery('english', 'paint&water'));
|
|
|
|
|
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
2007-12-10 01:12:31 +01:00
|
|
|
S. T. Coleridge (1772-1834)
|
2007-12-09 22:01:18 +01:00
|
|
|
', to_tsquery('english', 'breath&motion&water'));
|
|
|
|
|
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
2007-12-10 01:12:31 +01:00
|
|
|
S. T. Coleridge (1772-1834)
|
2007-12-09 22:01:18 +01:00
|
|
|
', to_tsquery('english', 'ocean'));
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2016-04-07 17:44:18 +02:00
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
|
|
|
S. T. Coleridge (1772-1834)
|
|
|
|
', phraseto_tsquery('english', 'painted Ocean'));
|
|
|
|
|
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
|
|
|
S. T. Coleridge (1772-1834)
|
|
|
|
', phraseto_tsquery('english', 'idle as a painted Ship'));
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT ts_headline('english', '
|
2007-08-21 03:11:32 +02:00
|
|
|
<html>
|
|
|
|
<!-- some comment -->
|
|
|
|
<body>
|
|
|
|
Sea view wow <u>foo bar</u> <i>qq</i>
|
|
|
|
<a href="http://www.google.com/foo.bar.html" target="_blank">YES </a>
|
|
|
|
ff-bg
|
|
|
|
<script>
|
|
|
|
document.write(15);
|
|
|
|
</script>
|
|
|
|
</body>
|
|
|
|
</html>',
|
|
|
|
to_tsquery('english', 'sea&foo'), 'HighlightAll=true');
|
|
|
|
|
2016-04-07 17:44:18 +02:00
|
|
|
SELECT ts_headline('simple', '1 2 3 1 3'::text, '1 <-> 3', 'MaxWords=2, MinWords=1');
|
|
|
|
SELECT ts_headline('simple', '1 2 3 1 3'::text, '1 & 3', 'MaxWords=4, MinWords=1');
|
|
|
|
SELECT ts_headline('simple', '1 2 3 1 3'::text, '1 <-> 3', 'MaxWords=4, MinWords=1');
|
|
|
|
|
2010-11-23 21:27:50 +01:00
|
|
|
--Check if headline fragments work
|
2008-10-17 20:05:19 +02:00
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
|
|
|
S. T. Coleridge (1772-1834)
|
|
|
|
', to_tsquery('english', 'ocean'), 'MaxFragments=1');
|
|
|
|
|
|
|
|
--Check if more than one fragments are displayed
|
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
|
|
|
S. T. Coleridge (1772-1834)
|
|
|
|
', to_tsquery('english', 'Coleridge & stuck'), 'MaxFragments=2');
|
|
|
|
|
|
|
|
--Fragments when there all query words are not in the document
|
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
|
|
|
S. T. Coleridge (1772-1834)
|
|
|
|
', to_tsquery('english', 'ocean & seahorse'), 'MaxFragments=1');
|
|
|
|
|
|
|
|
--FragmentDelimiter option
|
|
|
|
SELECT ts_headline('english', '
|
|
|
|
Day after day, day after day,
|
|
|
|
We stuck, nor breath nor motion,
|
|
|
|
As idle as a painted Ship
|
|
|
|
Upon a painted Ocean.
|
|
|
|
Water, water, every where
|
|
|
|
And all the boards did shrink;
|
|
|
|
Water, water, every where,
|
|
|
|
Nor any drop to drink.
|
|
|
|
S. T. Coleridge (1772-1834)
|
|
|
|
', to_tsquery('english', 'Coleridge & stuck'), 'MaxFragments=2,FragmentDelimiter=***');
|
|
|
|
|
2007-08-21 03:11:32 +02:00
|
|
|
--Rewrite sub system
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
CREATE TABLE test_tsquery (txtkeyword TEXT, txtsample TEXT);
|
2007-08-21 03:11:32 +02:00
|
|
|
\set ECHO none
|
|
|
|
\copy test_tsquery from stdin
|
|
|
|
'New York' new & york | big & apple | nyc
|
|
|
|
Moscow moskva | moscow
|
|
|
|
'Sanct Peter' Peterburg | peter | 'Sanct Peterburg'
|
|
|
|
'foo bar qq' foo & (bar | qq) & city
|
2016-04-07 17:44:18 +02:00
|
|
|
1 & (2 <-> 3) 2 <-> 4
|
|
|
|
5 <-> 6 5 <-> 7
|
2007-08-21 03:11:32 +02:00
|
|
|
\.
|
|
|
|
\set ECHO all
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
ALTER TABLE test_tsquery ADD COLUMN keyword tsquery;
|
|
|
|
UPDATE test_tsquery SET keyword = to_tsquery('english', txtkeyword);
|
|
|
|
ALTER TABLE test_tsquery ADD COLUMN sample tsquery;
|
|
|
|
UPDATE test_tsquery SET sample = to_tsquery('english', txtsample::text);
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword < 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword <= 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword = 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword >= 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword > 'new & york';
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
CREATE UNIQUE INDEX bt_tsq ON test_tsquery (keyword);
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
SET enable_seqscan=OFF;
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword < 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword <= 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword = 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword >= 'new & york';
|
|
|
|
SELECT COUNT(*) FROM test_tsquery WHERE keyword > 'new & york';
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
RESET enable_seqscan;
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT ts_rewrite('foo & bar & qq & new & york', 'new & york'::tsquery, 'big & apple | nyc | new & york & city');
|
2016-10-30 20:24:40 +01:00
|
|
|
SELECT ts_rewrite(ts_rewrite('new & !york ', 'york', '!jersey'),
|
|
|
|
'jersey', 'mexico');
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT ts_rewrite('moscow', 'SELECT keyword, sample FROM test_tsquery'::text );
|
|
|
|
SELECT ts_rewrite('moscow & hotel', 'SELECT keyword, sample FROM test_tsquery'::text );
|
2007-10-24 04:24:49 +02:00
|
|
|
SELECT ts_rewrite('bar & new & qq & foo & york', 'SELECT keyword, sample FROM test_tsquery'::text );
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-10-24 04:24:49 +02:00
|
|
|
SELECT ts_rewrite( 'moscow', 'SELECT keyword, sample FROM test_tsquery');
|
|
|
|
SELECT ts_rewrite( 'moscow & hotel', 'SELECT keyword, sample FROM test_tsquery');
|
|
|
|
SELECT ts_rewrite( 'bar & new & qq & foo & york', 'SELECT keyword, sample FROM test_tsquery');
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2016-04-07 17:44:18 +02:00
|
|
|
SELECT ts_rewrite('1 & (2 <-> 3)', 'SELECT keyword, sample FROM test_tsquery'::text );
|
|
|
|
SELECT ts_rewrite('1 & (2 <2> 3)', 'SELECT keyword, sample FROM test_tsquery'::text );
|
|
|
|
SELECT ts_rewrite('5 <-> (1 & (2 <-> 3))', 'SELECT keyword, sample FROM test_tsquery'::text );
|
|
|
|
SELECT ts_rewrite('5 <-> (6 | 8)', 'SELECT keyword, sample FROM test_tsquery'::text );
|
|
|
|
|
2016-12-11 19:09:57 +01:00
|
|
|
-- Check empty substitution
|
|
|
|
SELECT ts_rewrite(to_tsquery('5 & (6 | 5)'), to_tsquery('5'), to_tsquery(''));
|
|
|
|
SELECT ts_rewrite(to_tsquery('!5'), to_tsquery('5'), to_tsquery(''));
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword @> 'new';
|
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword @> 'moscow';
|
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword <@ 'new';
|
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword <@ 'moscow';
|
2007-10-24 04:24:49 +02:00
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow & hotel') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'bar & new & qq & foo & york') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow & hotel') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'bar & new & qq & foo & york') AS query;
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
CREATE INDEX qq ON test_tsquery USING gist (keyword tsquery_ops);
|
2007-08-21 03:11:32 +02:00
|
|
|
SET enable_seqscan=OFF;
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword @> 'new';
|
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword @> 'moscow';
|
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword <@ 'new';
|
|
|
|
SELECT keyword FROM test_tsquery WHERE keyword <@ 'moscow';
|
2007-10-24 04:24:49 +02:00
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow & hotel') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'bar & new & qq & foo & york') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'moscow & hotel') AS query;
|
|
|
|
SELECT ts_rewrite( query, 'SELECT keyword, sample FROM test_tsquery' ) FROM to_tsquery('english', 'bar & new & qq & foo & york') AS query;
|
2007-08-21 03:11:32 +02:00
|
|
|
|
Fix strange behavior (and possible crashes) in full text phrase search.
In an attempt to simplify the tsquery matching engine, the original
phrase search patch invented rewrite rules that would rearrange a
tsquery so that no AND/OR/NOT operator appeared below a PHRASE operator.
But this approach had numerous problems. The rearrangement step was
missed by ts_rewrite (and perhaps other places), allowing tsqueries
to be created that would cause Assert failures or perhaps crashes at
execution, as reported by Andreas Seltenreich. The rewrite rules
effectively defined semantics for operators underneath PHRASE that were
buggy, or at least unintuitive. And because rewriting was done in
tsqueryin() rather than at execution, the rearrangement was user-visible,
which is not very desirable --- for example, it might cause unexpected
matches or failures to match in ts_rewrite.
As a somewhat independent problem, the behavior of nested PHRASE operators
was only sane for left-deep trees; queries like "x <-> (y <-> z)" did not
behave intuitively at all.
To fix, get rid of the rewrite logic altogether, and instead teach the
tsquery execution engine to manage AND/OR/NOT below a PHRASE operator
by explicitly computing the match location(s) and match widths for these
operators.
This requires introducing some additional fields into the publicly visible
ExecPhraseData struct; but since there's no way for third-party code to
pass such a struct to TS_phrase_execute, it shouldn't create an ABI problem
as long as we don't move the offsets of the existing fields.
Another related problem was that index searches supposed that "!x <-> y"
could be lossily approximated as "!x & y", which isn't correct because
the latter will reject, say, "x q y" which the query itself accepts.
This required some tweaking in TS_execute_ternary along with the main
tsquery engine.
Back-patch to 9.6 where phrase operators were introduced. While this
could be argued to change behavior more than we'd like in a stable branch,
we have to do something about the crash hazards and index-vs-seqscan
inconsistency, and it doesn't seem desirable to let the unintuitive
behaviors induced by the rewriting implementation stand as precedent.
Discussion: https://postgr.es/m/28215.1481999808@sss.pgh.pa.us
Discussion: https://postgr.es/m/26706.1482087250@sss.pgh.pa.us
2016-12-21 21:18:25 +01:00
|
|
|
SELECT ts_rewrite(tsquery_phrase('foo', 'foo'), 'foo', 'bar | baz');
|
|
|
|
SELECT to_tsvector('foo bar') @@
|
|
|
|
ts_rewrite(tsquery_phrase('foo', 'foo'), 'foo', 'bar | baz');
|
|
|
|
SELECT to_tsvector('bar baz') @@
|
|
|
|
ts_rewrite(tsquery_phrase('foo', 'foo'), 'foo', 'bar | baz');
|
|
|
|
|
2007-08-21 03:11:32 +02:00
|
|
|
RESET enable_seqscan;
|
|
|
|
|
|
|
|
--test GUC
|
2007-08-21 17:41:13 +02:00
|
|
|
SET default_text_search_config=simple;
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT to_tsvector('SKIES My booKs');
|
|
|
|
SELECT plainto_tsquery('SKIES My booKs');
|
|
|
|
SELECT to_tsquery('SKIES & My | booKs');
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SET default_text_search_config=english;
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT to_tsvector('SKIES My booKs');
|
|
|
|
SELECT plainto_tsquery('SKIES My booKs');
|
|
|
|
SELECT to_tsquery('SKIES & My | booKs');
|
2007-08-21 03:11:32 +02:00
|
|
|
|
|
|
|
--trigger
|
|
|
|
CREATE TRIGGER tsvectorupdate
|
|
|
|
BEFORE UPDATE OR INSERT ON test_tsvector
|
|
|
|
FOR EACH ROW EXECUTE PROCEDURE tsvector_update_trigger(a, 'pg_catalog.english', t);
|
|
|
|
|
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ to_tsquery('345&qwerty');
|
|
|
|
INSERT INTO test_tsvector (t) VALUES ('345 qwerty');
|
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ to_tsquery('345&qwerty');
|
|
|
|
UPDATE test_tsvector SET t = null WHERE t = '345 qwerty';
|
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ to_tsquery('345&qwerty');
|
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
INSERT INTO test_tsvector (t) VALUES ('345 qwerty');
|
2007-08-21 03:11:32 +02:00
|
|
|
|
2007-08-21 17:41:13 +02:00
|
|
|
SELECT count(*) FROM test_tsvector WHERE a @@ to_tsquery('345&qwerty');
|
2009-05-19 04:48:26 +02:00
|
|
|
|
|
|
|
-- test finding items in GIN's pending list
|
|
|
|
create temp table pendtest (ts tsvector);
|
|
|
|
create index pendtest_idx on pendtest using gin(ts);
|
|
|
|
insert into pendtest values (to_tsvector('Lore ipsam'));
|
|
|
|
insert into pendtest values (to_tsvector('Lore ipsum'));
|
|
|
|
select * from pendtest where 'ipsu:*'::tsquery @@ ts;
|
|
|
|
select * from pendtest where 'ipsa:*'::tsquery @@ ts;
|
|
|
|
select * from pendtest where 'ips:*'::tsquery @@ ts;
|
|
|
|
select * from pendtest where 'ipt:*'::tsquery @@ ts;
|
|
|
|
select * from pendtest where 'ipi:*'::tsquery @@ ts;
|
2016-04-07 17:44:18 +02:00
|
|
|
|
|
|
|
--check OP_PHRASE on index
|
|
|
|
create temp table phrase_index_test(fts tsvector);
|
2016-06-27 19:47:32 +02:00
|
|
|
insert into phrase_index_test values ('A fat cat has just eaten a rat.');
|
|
|
|
insert into phrase_index_test values (to_tsvector('english', 'A fat cat has just eaten a rat.'));
|
2016-04-07 17:44:18 +02:00
|
|
|
create index phrase_index_test_idx on phrase_index_test using gin(fts);
|
|
|
|
set enable_seqscan = off;
|
2016-04-07 18:28:31 +02:00
|
|
|
select * from phrase_index_test where fts @@ phraseto_tsquery('english', 'fat cat');
|
2016-04-07 17:44:18 +02:00
|
|
|
set enable_seqscan = on;
|