Skip to content

Commit 157d137

Browse files
author
Artur Zakirov
committed
Added features and fix bugs:
- use index scan with order by without where clause. - added RumKey structure. - fix indentation. - fix tests.
1 parent 209619e commit 157d137

23 files changed

+1723
-1314
lines changed

‎.gitignore

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
.deps
22
*.o
33
*.so
4-
results
4+
results

‎README.md

+11-5
Original file line numberDiff line numberDiff line change
@@ -32,9 +32,9 @@ The **rum** module provides the access method **rum** and the operator class
3232

3333
The module provides new operators.
3434

35-
| Operator | Returns | Description
36-
| ------------------- | ------- | ----------------------------------------------
37-
| tsvector >< tsquery | float4 | Returns distance between tsvector and tsquery.
35+
| Operator | Returns | Description
36+
| -------------------- | ------- | ----------------------------------------------
37+
| tsvector <-> tsquery | float4 | Returns distance between tsvector and tsquery.
3838

3939
## Examples
4040

@@ -67,15 +67,21 @@ CREATE INDEX rumidx ON test_rum USING rum (a rum_tsvector_ops);
6767
And we can execute the following queries:
6868

6969
```sql
70-
=# SELECT t, a >< to_tsquery('english', 'beautiful | place') AS rank FROM test_rum WHERE a @@ to_tsquery('english', 'beautiful | place') order by a >< to_tsquery('english', 'beautiful | place');
70+
=# SELECT t, a <-> to_tsquery('english', 'beautiful | place') AS rank
71+
FROM test_rum
72+
WHERE a @@ to_tsquery('english', 'beautiful | place')
73+
ORDER BY a <-> to_tsquery('english', 'beautiful | place');
7174
t | rank
7275
---------------------------------+-----------
7376
The situation is most beautiful | 0.0303964
7477
It is a beautiful | 0.0303964
7578
It looks like a beautiful place | 0.0607927
7679
(3 rows)
7780

78-
=# SELECT t, a >< to_tsquery('english', 'place | situation') AS rank FROM test_rum WHERE a @@ to_tsquery('english', 'place | situation') order by a >< to_tsquery('english', 'place | situation');
81+
=# SELECT t, a <-> to_tsquery('english', 'place | situation') AS rank
82+
FROM test_rum
83+
WHERE a @@ to_tsquery('english', 'place | situation')
84+
ORDER BY a <-> to_tsquery('english', 'place | situation');
7985
t | rank
8086
---------------------------------+-----------
8187
The situation is most beautiful | 0.0303964

‎expected/orderby.out

+19-4
Original file line numberDiff line numberDiff line change
@@ -184,7 +184,22 @@ SELECT id, d, d |-> '2016-05-16 14:21:25' FROM tsts WHERE t @@ 'wr&qh' ORDER BY
184184
457 | Fri May 20 20:21:22.326724 2016 | 367197.326724
185185
(5 rows)
186186

187-
--to be fixed
188-
--EXPLAIN (costs off)
189-
--SELECT id, d, d <-> '2016-05-16 14:21:25' FROM tsts ORDER BY d <-> '2016-05-16 14:21:25' LIMIT 5;
190-
--SELECT id, d, d <-> '2016-05-16 14:21:25' FROM tsts ORDER BY d <-> '2016-05-16 14:21:25' LIMIT 5;
187+
EXPLAIN (costs off)
188+
SELECT id, d, d <-> '2016-05-16 14:21:25' FROM tsts ORDER BY d <-> '2016-05-16 14:21:25' LIMIT 5;
189+
QUERY PLAN
190+
-----------------------------------------------------------------------------------
191+
Limit
192+
-> Index Scan using tsts_idx on tsts
193+
Order By: (d <-> 'Mon May 16 14:21:25 2016'::timestamp without time zone)
194+
(3 rows)
195+
196+
SELECT id, d, d <-> '2016-05-16 14:21:25' FROM tsts ORDER BY d <-> '2016-05-16 14:21:25' LIMIT 5;
197+
id | d | ?column?
198+
-----+---------------------------------+-------------
199+
355 | Mon May 16 14:21:22.326724 2016 | 2.673276
200+
356 | Mon May 16 15:21:22.326724 2016 | 3597.326724
201+
354 | Mon May 16 13:21:22.326724 2016 | 3602.673276
202+
357 | Mon May 16 16:21:22.326724 2016 | 7197.326724
203+
353 | Mon May 16 12:21:22.326724 2016 | 7202.673276
204+
(5 rows)
205+

‎expected/rum.out

+19-13
Original file line numberDiff line numberDiff line change
@@ -96,10 +96,10 @@ SELECT rum_ts_distance(a, to_tsquery('pg_catalog.english', 'way')), *
9696
ORDER BY a <-> to_tsquery('pg_catalog.english', 'way');
9797
rum_ts_distance | t | a
9898
-----------------+--------------------------------------------------------------------------+---------------------------------------------------------------
99-
0.0607927 | my appreciation of you in a more complimentary way than by sending this | 'appreci':2 'complimentari':8 'send':12 'way':9
100-
0.0607927 | itself. Put on your “specs” and look at the castle, half way up the | 'castl':10 'half':11 'look':7 'put':2 'spec':5 'way':12
101-
0.0607927 | so well that only a fragment, as it were, gave way. It still hangs as if | 'fragment':6 'gave':10 'hang':14 'still':13 'way':11 'well':2
102-
0.0607927 | thinking--“to go or not to go?” We are this far on the way. Reached | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
99+
16.4493 | my appreciation of you in a more complimentary way than by sending this | 'appreci':2 'complimentari':8 'send':12 'way':9
100+
16.4493 | itself. Put on your “specs” and look at the castle, half way up the | 'castl':10 'half':11 'look':7 'put':2 'spec':5 'way':12
101+
16.4493 | so well that only a fragment, as it were, gave way. It still hangs as if | 'fragment':6 'gave':10 'hang':14 'still':13 'way':11 'well':2
102+
16.4493 | thinking--“to go or not to go?” We are this far on the way. Reached | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
103103
(4 rows)
104104

105105
SELECT rum_ts_distance(a, to_tsquery('pg_catalog.english', 'way & (go | half)')), *
@@ -108,10 +108,23 @@ SELECT rum_ts_distance(a, to_tsquery('pg_catalog.english', 'way & (go | half)'))
108108
ORDER BY a <-> to_tsquery('pg_catalog.english', 'way & (go | half)');
109109
rum_ts_distance | t | a
110110
-----------------+---------------------------------------------------------------------+---------------------------------------------------------
111-
0.103556 | thinking--“to go or not to go?” We are this far on the way. Reached | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
112-
0.0991032 | itself. Put on your “specs” and look at the castle, half way up the | 'castl':10 'half':11 'look':7 'put':2 'spec':5 'way':12
111+
9.65659 | thinking--“to go or not to go?” We are this far on the way. Reached | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
112+
10.0905 | itself. Put on your “specs” and look at the castle, half way up the | 'castl':10 'half':11 'look':7 'put':2 'spec':5 'way':12
113113
(2 rows)
114114

115+
SELECT
116+
a <-> to_tsquery('pg_catalog.english', 'way & (go | half)'),
117+
rum_ts_distance(a, to_tsquery('pg_catalog.english', 'way & (go | half)')),
118+
*
119+
FROM test_rum
120+
ORDER BY a <-> to_tsquery('pg_catalog.english', 'way & (go | half)') limit 3;
121+
?column? | rum_ts_distance | t | a
122+
----------+-----------------+-------------------------------------------------------------------------+---------------------------------------------------------
123+
9.65659 | 9.65659 | thinking--“to go or not to go?” We are this far on the way. Reached | 'far':11 'go':3,7 'reach':15 'think':1 'way':14
124+
10.0905 | 10.0905 | itself. Put on your “specs” and look at the castle, half way up the | 'castl':10 'half':11 'look':7 'put':2 'spec':5 'way':12
125+
1e+20 | 1e+20 | my appreciation of you in a more complimentary way than by sending this | 'appreci':2 'complimentari':8 'send':12 'way':9
126+
(3 rows)
127+
115128
INSERT INTO test_rum (t) VALUES ('foo bar foo the over foo qq bar');
116129
INSERT INTO test_rum (t) VALUES ('345 qwerty copyright');
117130
INSERT INTO test_rum (t) VALUES ('345 qwerty');
@@ -146,13 +159,6 @@ SELECT a FROM test_rum WHERE a @@ to_tsquery('pg_catalog.english', 'bar') ORDER
146159
'bar':2,8 'foo':1,3,6 'qq':7
147160
(1 row)
148161

149-
DELETE FROM test_rum;
150-
SELECT count(*) from test_rum;
151-
count
152-
-------
153-
0
154-
(1 row)
155-
156162
CREATE TABLE tst (i int4, t tsvector);
157163
INSERT INTO tst SELECT i%10, to_tsvector('simple', substr(md5(i::text), 1, 1)) FROM generate_series(1,100000) i;
158164
CREATE INDEX tstidx ON tst USING rum (t rum_tsvector_ops);

0 commit comments

Comments
 (0)