1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
|
CREATE EXTENSION pg_trgm;
-- Check whether any of our opclasses fail amvalidate
SELECT amname, opcname
FROM pg_opclass opc LEFT JOIN pg_am am ON am.oid = opcmethod
WHERE opc.oid >= 16384 AND NOT amvalidate(opc.oid);
--backslash is used in tests below, installcheck will fail if
--standard_conforming_string is off
set standard_conforming_strings=on;
select show_trgm('');
select show_trgm('(*&^$@%@');
select show_trgm('a b c');
select show_trgm(' a b c ');
select show_trgm('aA bB cC');
select show_trgm(' aA bB cC ');
select show_trgm('a b C0*%^');
select similarity('wow','WOWa ');
select similarity('wow',' WOW ');
select similarity('---', '####---');
CREATE TABLE test_trgm(t text COLLATE "C");
\copy test_trgm from 'data/trgm.data'
select t,similarity(t,'qwertyu0988') as sml from test_trgm where t % 'qwertyu0988' order by sml desc, t;
select t,similarity(t,'gwertyu0988') as sml from test_trgm where t % 'gwertyu0988' order by sml desc, t;
select t,similarity(t,'gwertyu1988') as sml from test_trgm where t % 'gwertyu1988' order by sml desc, t;
select t <-> 'q0987wertyu0988', t from test_trgm order by t <-> 'q0987wertyu0988' limit 2;
select count(*) from test_trgm where t ~ '[qwerty]{2}-?[qwerty]{2}';
create index trgm_idx on test_trgm using gist (t gist_trgm_ops);
set enable_seqscan=off;
select t,similarity(t,'qwertyu0988') as sml from test_trgm where t % 'qwertyu0988' order by sml desc, t;
select t,similarity(t,'gwertyu0988') as sml from test_trgm where t % 'gwertyu0988' order by sml desc, t;
select t,similarity(t,'gwertyu1988') as sml from test_trgm where t % 'gwertyu1988' order by sml desc, t;
explain (costs off)
select t <-> 'q0987wertyu0988', t from test_trgm order by t <-> 'q0987wertyu0988' limit 2;
select t <-> 'q0987wertyu0988', t from test_trgm order by t <-> 'q0987wertyu0988' limit 2;
select count(*) from test_trgm where t ~ '[qwerty]{2}-?[qwerty]{2}';
drop index trgm_idx;
create index trgm_idx on test_trgm using gin (t gin_trgm_ops);
set enable_seqscan=off;
select t,similarity(t,'qwertyu0988') as sml from test_trgm where t % 'qwertyu0988' order by sml desc, t;
select t,similarity(t,'gwertyu0988') as sml from test_trgm where t % 'gwertyu0988' order by sml desc, t;
select t,similarity(t,'gwertyu1988') as sml from test_trgm where t % 'gwertyu1988' order by sml desc, t;
select count(*) from test_trgm where t ~ '[qwerty]{2}-?[qwerty]{2}';
create table test2(t text COLLATE "C");
insert into test2 values ('abcdef');
insert into test2 values ('quark');
insert into test2 values (' z foo bar');
insert into test2 values ('/123/-45/');
create index test2_idx_gin on test2 using gin (t gin_trgm_ops);
set enable_seqscan=off;
explain (costs off)
select * from test2 where t like '%BCD%';
explain (costs off)
select * from test2 where t ilike '%BCD%';
select * from test2 where t like '%BCD%';
select * from test2 where t like '%bcd%';
select * from test2 where t like E'%\\bcd%';
select * from test2 where t ilike '%BCD%';
select * from test2 where t ilike 'qua%';
select * from test2 where t like '%z foo bar%';
select * from test2 where t like ' z foo%';
explain (costs off)
select * from test2 where t ~ '[abc]{3}';
explain (costs off)
select * from test2 where t ~* 'DEF';
select * from test2 where t ~ '[abc]{3}';
select * from test2 where t ~ 'a[bc]+d';
select * from test2 where t ~ '(abc)*$';
select * from test2 where t ~* 'DEF';
select * from test2 where t ~ 'dEf';
select * from test2 where t ~* '^q';
select * from test2 where t ~* '[abc]{3}[def]{3}';
select * from test2 where t ~* 'ab[a-z]{3}';
select * from test2 where t ~* '(^| )qua';
select * from test2 where t ~ 'q.*rk$';
select * from test2 where t ~ 'q';
select * from test2 where t ~ '[a-z]{3}';
select * from test2 where t ~* '(a{10}|b{10}|c{10}){10}';
select * from test2 where t ~ 'z foo bar';
select * from test2 where t ~ ' z foo bar';
select * from test2 where t ~ ' z foo bar';
select * from test2 where t ~ ' z foo';
select * from test2 where t ~ 'qua(?!foo)';
select * from test2 where t ~ '/\d+/-\d';
drop index test2_idx_gin;
create index test2_idx_gist on test2 using gist (t gist_trgm_ops);
set enable_seqscan=off;
explain (costs off)
select * from test2 where t like '%BCD%';
explain (costs off)
select * from test2 where t ilike '%BCD%';
select * from test2 where t like '%BCD%';
select * from test2 where t like '%bcd%';
select * from test2 where t like E'%\\bcd%';
select * from test2 where t ilike '%BCD%';
select * from test2 where t ilike 'qua%';
select * from test2 where t like '%z foo bar%';
select * from test2 where t like ' z foo%';
explain (costs off)
select * from test2 where t ~ '[abc]{3}';
explain (costs off)
select * from test2 where t ~* 'DEF';
select * from test2 where t ~ '[abc]{3}';
select * from test2 where t ~ 'a[bc]+d';
select * from test2 where t ~ '(abc)*$';
select * from test2 where t ~* 'DEF';
select * from test2 where t ~ 'dEf';
select * from test2 where t ~* '^q';
select * from test2 where t ~* '[abc]{3}[def]{3}';
select * from test2 where t ~* 'ab[a-z]{3}';
select * from test2 where t ~* '(^| )qua';
select * from test2 where t ~ 'q.*rk$';
select * from test2 where t ~ 'q';
select * from test2 where t ~ '[a-z]{3}';
select * from test2 where t ~* '(a{10}|b{10}|c{10}){10}';
select * from test2 where t ~ 'z foo bar';
select * from test2 where t ~ ' z foo bar';
select * from test2 where t ~ ' z foo bar';
select * from test2 where t ~ ' z foo';
select * from test2 where t ~ 'qua(?!foo)';
select * from test2 where t ~ '/\d+/-\d';
-- Check similarity threshold (bug #14202)
CREATE TEMP TABLE restaurants (city text);
INSERT INTO restaurants SELECT 'Warsaw' FROM generate_series(1, 10000);
INSERT INTO restaurants SELECT 'Szczecin' FROM generate_series(1, 10000);
CREATE INDEX ON restaurants USING gist(city gist_trgm_ops);
-- Similarity of the two names (for reference).
SELECT similarity('Szczecin', 'Warsaw');
-- Should get only 'Warsaw' for either setting of set_limit.
EXPLAIN (COSTS OFF)
SELECT DISTINCT city, similarity(city, 'Warsaw'), show_limit()
FROM restaurants WHERE city % 'Warsaw';
SELECT set_limit(0.3);
SELECT DISTINCT city, similarity(city, 'Warsaw'), show_limit()
FROM restaurants WHERE city % 'Warsaw';
SELECT set_limit(0.5);
SELECT DISTINCT city, similarity(city, 'Warsaw'), show_limit()
FROM restaurants WHERE city % 'Warsaw';
|
