summaryrefslogtreecommitdiffstats
path: root/contrib/pg_trgm/sql/pg_trgm.sql
blob: 6a9da24d5a72b3c9928deedd9d74540fe7fa35fb (plain)
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
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;

-- reduce noise
set extra_float_digits = 0;

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 gist (t gist_trgm_ops(siglen=0));
create index trgm_idx on test_trgm using gist (t gist_trgm_ops(siglen=2025));
create index trgm_idx on test_trgm using gist (t gist_trgm_ops(siglen=2024));
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}';

-- check handling of indexquals that generate no searchable conditions
explain (costs off)
select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
explain (costs off)
select count(*) from test_trgm where t like '%99%' and t like '%qw%';
select count(*) from test_trgm where t like '%99%' and t like '%qw%';
-- ensure that pending-list items are handled correctly, too
create temp table t_test_trgm(t text COLLATE "C");
create index t_trgm_idx on t_test_trgm using gin (t gin_trgm_ops);
insert into t_test_trgm values ('qwerty99'), ('qwerty01');
explain (costs off)
select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
explain (costs off)
select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';

-- run the same queries with sequential scan to check the results
set enable_bitmapscan=off;
set enable_seqscan=on;
select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
select count(*) from test_trgm where t like '%99%' and t like '%qw%';
select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
reset enable_bitmapscan;

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/');
insert into test2 values ('line 1');
insert into test2 values ('%line 2');
insert into test2 values ('line 3%');
insert into test2 values ('%line 4%');
insert into test2 values ('%li%ne 5%');
insert into test2 values ('li_e 6');
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';
-- test = operator
explain (costs off)
  select * from test2 where t = 'abcdef';
select * from test2 where t = 'abcdef';
explain (costs off)
  select * from test2 where t = '%line%';
select * from test2 where t = '%line%';
select * from test2 where t = 'li_e 1';
select * from test2 where t = '%line 2';
select * from test2 where t = 'line 3%';
select * from test2 where t = '%line 3%';
select * from test2 where t = '%line 4%';
select * from test2 where t = '%line 5%';
select * from test2 where t = '%li_ne 5%';
select * from test2 where t = '%li%ne 5%';
select * from test2 where t = 'line 6';
select * from test2 where t = 'li_e 6';
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';
-- test = operator
explain (costs off)
  select * from test2 where t = 'abcdef';
select * from test2 where t = 'abcdef';
explain (costs off)
  select * from test2 where t = '%line%';
select * from test2 where t = '%line%';
select * from test2 where t = 'li_e 1';
select * from test2 where t = '%line 2';
select * from test2 where t = 'line 3%';
select * from test2 where t = '%line 3%';
select * from test2 where t = '%line 4%';
select * from test2 where t = '%line 5%';
select * from test2 where t = '%li_ne 5%';
select * from test2 where t = '%li%ne 5%';
select * from test2 where t = 'line 6';
select * from test2 where t = 'li_e 6';

-- 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';