mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-08-16 13:23:22 +02:00
6cfaffc0dd
regexport.c thought it could just ignore LACON arcs, but the correct
behavior is to treat them as satisfiable while consuming zero input
(rather reminiscently of commit 9f1e642d5). Otherwise, the emitted
simplified-NFA representation may contain no paths leading from initial
to final state, which unsurprisingly confuses pg_trgm, as seen in
bug #14623 from Jeff Janes.
Since regexport's output representation has no concept of an arc that
consumes zero input, recurse internally to find the next normal arc(s)
after any LACON transitions. We'd be forced into changing that
representation if a LACON could be the last arc reaching the final
state, but fortunately the regex library never builds NFAs with such
a configuration, so there always is a next normal arc.
Back-patch to 9.3 where this logic was introduced.
Discussion: https://postgr.es/m/20170413180503.25948.94871@wrigleys.postgresql.org
148 lines
6.0 KiB
SQL
148 lines
6.0 KiB
SQL
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);
|
|
|
|
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');
|
|
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$';
|
|
select * from test2 where t ~ 'q';
|
|
select * from test2 where t ~ '[a-z]{3}';
|
|
select * from test2 where t ~* '(a{10}|b{10}|c{10}){10}';
|
|
select * from test2 where t ~ 'z foo bar';
|
|
select * from test2 where t ~ ' z foo bar';
|
|
select * from test2 where t ~ ' z foo bar';
|
|
select * from test2 where t ~ ' z foo';
|
|
select * from test2 where t ~ 'qua(?!foo)';
|
|
drop index test2_idx_gin;
|
|
|
|
create index test2_idx_gist on test2 using gist (t gist_trgm_ops);
|
|
set enable_seqscan=off;
|
|
explain (costs off)
|
|
select * from test2 where t like '%BCD%';
|
|
explain (costs off)
|
|
select * from test2 where t ilike '%BCD%';
|
|
select * from test2 where t like '%BCD%';
|
|
select * from test2 where t like '%bcd%';
|
|
select * from test2 where t like E'%\\bcd%';
|
|
select * from test2 where t ilike '%BCD%';
|
|
select * from test2 where t ilike 'qua%';
|
|
select * from test2 where t like '%z foo bar%';
|
|
select * from test2 where t like ' z foo%';
|
|
explain (costs off)
|
|
select * from test2 where t ~ '[abc]{3}';
|
|
explain (costs off)
|
|
select * from test2 where t ~* 'DEF';
|
|
select * from test2 where t ~ '[abc]{3}';
|
|
select * from test2 where t ~ 'a[bc]+d';
|
|
select * from test2 where t ~ '(abc)*$';
|
|
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)';
|
|
|
|
-- 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';
|