database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-06-26 12:21:12 +03:00
Code Activity

Fix behavior of ~> (cube, int) operator

Browse Source 
~> (cube, int) operator was especially designed for knn-gist search.
However, it appears that knn-gist search can't work correctly with current
behavior of this operator when dataset contains cubes of variable
dimensionality. In this case, the same value of second operator argument
can point to different dimension depending on dimensionality of particular cube.
Such behavior is incompatible with gist indexing of cubes, and knn-gist doesn't
work correctly for it.

This patch changes behavior of ~> (cube, int) operator by introducing dimension
numbering where value of second argument unambiguously identifies number of
dimension. With new behavior, this operator can be correctly supported by
knn-gist. Relevant changes to cube operator class are also included.

Backpatch to v9.6 where operator was introduced.

Since behavior of ~> (cube, int) operator is changed, depending entities
must be refreshed after upgrade. Such as, expression indexes using this
operator must be reindexed, materialized views must be rebuilt, stored
procedures and client code must be revised to correctly use new behavior.
That should be mentioned in release notes.

Noticed by: Tomas Vondra
Author: Alexander Korotkov
Reviewed by: Tomas Vondra, Andrey Borodin
Discussion: https://www.postgresql.org/message-id/flat/a9657f6a-b497-36ff-e56-482a2c7e3292@2ndquadrant.com
This commit is contained in:
Teodor Sigaev
2018-01-11 14:43:13 +03:00
parent 1226051948
commit bda5281fdc
7 changed files with 901 additions and 527 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
contrib/cube/sql/cube.sql
View File

@ -372,20 +372,29 @@ SELECT * FROM test_cube WHERE c && '(3000,1000),(0,0)' ORDER BY c;
-- Test sorting
SELECT * FROM test_cube WHERE c && '(3000,1000),(0,0)' GROUP BY c ORDER BY c;
-- kNN with index
-- Test kNN
INSERT INTO test_cube VALUES ('(1,1)'), ('(100000)'), ('(0, 100000)'); -- Some corner cases
SET enable_seqscan = false;
-- Test different metrics
SELECT *, c <-> '(100, 100),(500, 500)'::cube as dist FROM test_cube ORDER BY c <-> '(100, 100),(500, 500)'::cube LIMIT 5;
SELECT *, c <=> '(100, 100),(500, 500)'::cube as dist FROM test_cube ORDER BY c <=> '(100, 100),(500, 500)'::cube LIMIT 5;
SELECT *, c <#> '(100, 100),(500, 500)'::cube as dist FROM test_cube ORDER BY c <#> '(100, 100),(500, 500)'::cube LIMIT 5;
-- kNN-based sorting
SELECT * FROM test_cube ORDER BY c~>1 LIMIT 15; -- ascending by 1st coordinate of lower left corner
SELECT * FROM test_cube ORDER BY c~>4 LIMIT 15; -- ascending by 2nd coordinate or upper right corner
SELECT * FROM test_cube ORDER BY c~>1 DESC LIMIT 15; -- descending by 1st coordinate of lower left corner
SELECT * FROM test_cube ORDER BY c~>4 DESC LIMIT 15; -- descending by 2nd coordinate or upper right corner
-- Test sorting by coordinates
SELECT c~>1, c FROM test_cube ORDER BY c~>1 LIMIT 15; -- ascending by left bound
SELECT c~>2, c FROM test_cube ORDER BY c~>2 LIMIT 15; -- ascending by right bound
SELECT c~>3, c FROM test_cube ORDER BY c~>3 LIMIT 15; -- ascending by lower bound
SELECT c~>4, c FROM test_cube ORDER BY c~>4 LIMIT 15; -- ascending by upper bound
-- same thing for index with points
CREATE TABLE test_point(c cube);
INSERT INTO test_point(SELECT cube(array[c->1,c->2,c->3,c->4]) FROM test_cube);
CREATE INDEX ON test_point USING gist(c);
SELECT * FROM test_point ORDER BY c~>1, c~>2 LIMIT 15; -- ascending by 1st then by 2nd coordinate
SELECT * FROM test_point ORDER BY c~>4 DESC LIMIT 15; -- descending by 1st coordinate
-- Same queries with sequential scan (should give the same results as above)
RESET enable_seqscan;
SET enable_indexscan = OFF;
SELECT *, c <-> '(100, 100),(500, 500)'::cube as dist FROM test_cube ORDER BY c <-> '(100, 100),(500, 500)'::cube LIMIT 5;
SELECT *, c <=> '(100, 100),(500, 500)'::cube as dist FROM test_cube ORDER BY c <=> '(100, 100),(500, 500)'::cube LIMIT 5;
SELECT *, c <#> '(100, 100),(500, 500)'::cube as dist FROM test_cube ORDER BY c <#> '(100, 100),(500, 500)'::cube LIMIT 5;
SELECT c~>1, c FROM test_cube ORDER BY c~>1 LIMIT 15; -- ascending by left bound
SELECT c~>2, c FROM test_cube ORDER BY c~>2 LIMIT 15; -- ascending by right bound
SELECT c~>3, c FROM test_cube ORDER BY c~>3 LIMIT 15; -- ascending by lower bound
SELECT c~>4, c FROM test_cube ORDER BY c~>4 LIMIT 15; -- ascending by upper bound
RESET enable_indexscan;