database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-30 11:03:19 +03:00
Code Activity

Add strict_word_similarity to pg_trgm module

Browse Source 
strict_word_similarity is similar to existing word_similarity function but
it takes into account word boundaries to compute similarity.

Author: Alexander Korotkov
Review by: David Steele, Liudmila Mantrova, me
Discussion: https://www.postgresql.org/message-id/flat/CY4PR17MB13207ED8310F847CF117EED0D85A0@CY4PR17MB1320.namprd17.prod.outlook.com
This commit is contained in:
Teodor Sigaev
2018-03-21 14:57:42 +03:00
parent f20b328534
commit be8a7a6866
10 changed files with 1461 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
contrib/pg_trgm/sql/pg_strict_word_trgm.sql Normal file
View File

@ -0,0 +1,42 @@
DROP INDEX trgm_idx2;
\copy test_trgm3 from 'data/trgm2.data'
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where 'Baykal' <<% t order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where 'Kabankala' <<% t order by sml desc, t;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where t %>> 'Baykal' order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where t %>> 'Kabankala' order by sml desc, t;
select t <->>> 'Alaikallupoddakulam', t from test_trgm2 order by t <->>> 'Alaikallupoddakulam' limit 7;
create index trgm_idx2 on test_trgm2 using gist (t gist_trgm_ops);
set enable_seqscan=off;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where 'Baykal' <<% t order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where 'Kabankala' <<% t order by sml desc, t;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where t %>> 'Baykal' order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where t %>> 'Kabankala' order by sml desc, t;
explain (costs off)
select t <->>> 'Alaikallupoddakulam', t from test_trgm2 order by t <->>> 'Alaikallupoddakulam' limit 7;
select t <->>> 'Alaikallupoddakulam', t from test_trgm2 order by t <->>> 'Alaikallupoddakulam' limit 7;
drop index trgm_idx2;
create index trgm_idx2 on test_trgm2 using gin (t gin_trgm_ops);
set enable_seqscan=off;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where 'Baykal' <<% t order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where 'Kabankala' <<% t order by sml desc, t;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where t %>> 'Baykal' order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where t %>> 'Kabankala' order by sml desc, t;
set "pg_trgm.strict_word_similarity_threshold" to 0.4;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where 'Baykal' <<% t order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where 'Kabankala' <<% t order by sml desc, t;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where t %>> 'Baykal' order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where t %>> 'Kabankala' order by sml desc, t;
set "pg_trgm.strict_word_similarity_threshold" to 0.2;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where 'Baykal' <<% t order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where 'Kabankala' <<% t order by sml desc, t;
select t,strict_word_similarity('Baykal',t) as sml from test_trgm2 where t %>> 'Baykal' order by sml desc, t;
select t,strict_word_similarity('Kabankala',t) as sml from test_trgm2 where t %>> 'Kabankala' order by sml desc, t;