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
|
--
-- SELECT_DISTINCT
--
--
-- awk '{print $3;}' onek.data | sort -n | uniq
--
SELECT DISTINCT two FROM onek ORDER BY 1;
--
-- awk '{print $5;}' onek.data | sort -n | uniq
--
SELECT DISTINCT ten FROM onek ORDER BY 1;
--
-- awk '{print $16;}' onek.data | sort -d | uniq
--
SELECT DISTINCT string4 FROM onek ORDER BY 1;
--
-- awk '{print $3,$16,$5;}' onek.data | sort -d | uniq |
-- sort +0n -1 +1d -2 +2n -3
--
SELECT DISTINCT two, string4, ten
FROM onek
ORDER BY two using <, string4 using <, ten using <;
--
-- awk '{print $2;}' person.data |
-- awk '{if(NF!=1){print $2;}else{print;}}' - emp.data |
-- awk '{if(NF!=1){print $2;}else{print;}}' - student.data |
-- awk 'BEGIN{FS=" ";}{if(NF!=1){print $5;}else{print;}}' - stud_emp.data |
-- sort -n -r | uniq
--
SELECT DISTINCT p.age FROM person* p ORDER BY age using >;
--
-- Check mentioning same column more than once
--
EXPLAIN (VERBOSE, COSTS OFF)
SELECT count(*) FROM
(SELECT DISTINCT two, four, two FROM tenk1) ss;
SELECT count(*) FROM
(SELECT DISTINCT two, four, two FROM tenk1) ss;
--
-- Compare results between plans using sorting and plans using hash
-- aggregation. Force spilling in both cases by setting work_mem low.
--
SET work_mem='64kB';
-- Produce results with sorting.
SET enable_hashagg=FALSE;
SET jit_above_cost=0;
EXPLAIN (costs off)
SELECT DISTINCT g%1000 FROM generate_series(0,9999) g;
CREATE TABLE distinct_group_1 AS
SELECT DISTINCT g%1000 FROM generate_series(0,9999) g;
SET jit_above_cost TO DEFAULT;
CREATE TABLE distinct_group_2 AS
SELECT DISTINCT (g%1000)::text FROM generate_series(0,9999) g;
SET enable_hashagg=TRUE;
-- Produce results with hash aggregation.
SET enable_sort=FALSE;
SET jit_above_cost=0;
EXPLAIN (costs off)
SELECT DISTINCT g%1000 FROM generate_series(0,9999) g;
CREATE TABLE distinct_hash_1 AS
SELECT DISTINCT g%1000 FROM generate_series(0,9999) g;
SET jit_above_cost TO DEFAULT;
CREATE TABLE distinct_hash_2 AS
SELECT DISTINCT (g%1000)::text FROM generate_series(0,9999) g;
SET enable_sort=TRUE;
SET work_mem TO DEFAULT;
-- Compare results
(SELECT * FROM distinct_hash_1 EXCEPT SELECT * FROM distinct_group_1)
UNION ALL
(SELECT * FROM distinct_group_1 EXCEPT SELECT * FROM distinct_hash_1);
(SELECT * FROM distinct_hash_1 EXCEPT SELECT * FROM distinct_group_1)
UNION ALL
(SELECT * FROM distinct_group_1 EXCEPT SELECT * FROM distinct_hash_1);
DROP TABLE distinct_hash_1;
DROP TABLE distinct_hash_2;
DROP TABLE distinct_group_1;
DROP TABLE distinct_group_2;
-- Test parallel DISTINCT
SET parallel_tuple_cost=0;
SET parallel_setup_cost=0;
SET min_parallel_table_scan_size=0;
SET max_parallel_workers_per_gather=2;
-- Ensure we get a parallel plan
EXPLAIN (costs off)
SELECT DISTINCT four FROM tenk1;
-- Ensure the parallel plan produces the correct results
SELECT DISTINCT four FROM tenk1;
CREATE OR REPLACE FUNCTION distinct_func(a INT) RETURNS INT AS $$
BEGIN
RETURN a;
END;
$$ LANGUAGE plpgsql PARALLEL UNSAFE;
-- Ensure we don't do parallel distinct with a parallel unsafe function
EXPLAIN (COSTS OFF)
SELECT DISTINCT distinct_func(1) FROM tenk1;
-- make the function parallel safe
CREATE OR REPLACE FUNCTION distinct_func(a INT) RETURNS INT AS $$
BEGIN
RETURN a;
END;
$$ LANGUAGE plpgsql PARALLEL SAFE;
-- Ensure we do parallel distinct now that the function is parallel safe
EXPLAIN (COSTS OFF)
SELECT DISTINCT distinct_func(1) FROM tenk1;
RESET max_parallel_workers_per_gather;
RESET min_parallel_table_scan_size;
RESET parallel_setup_cost;
RESET parallel_tuple_cost;
--
-- Also, some tests of IS DISTINCT FROM, which doesn't quite deserve its
-- very own regression file.
--
CREATE TEMP TABLE disttable (f1 integer);
INSERT INTO DISTTABLE VALUES(1);
INSERT INTO DISTTABLE VALUES(2);
INSERT INTO DISTTABLE VALUES(3);
INSERT INTO DISTTABLE VALUES(NULL);
-- basic cases
SELECT f1, f1 IS DISTINCT FROM 2 as "not 2" FROM disttable;
SELECT f1, f1 IS DISTINCT FROM NULL as "not null" FROM disttable;
SELECT f1, f1 IS DISTINCT FROM f1 as "false" FROM disttable;
SELECT f1, f1 IS DISTINCT FROM f1+1 as "not null" FROM disttable;
-- check that optimizer constant-folds it properly
SELECT 1 IS DISTINCT FROM 2 as "yes";
SELECT 2 IS DISTINCT FROM 2 as "no";
SELECT 2 IS DISTINCT FROM null as "yes";
SELECT null IS DISTINCT FROM null as "no";
-- negated form
SELECT 1 IS NOT DISTINCT FROM 2 as "no";
SELECT 2 IS NOT DISTINCT FROM 2 as "yes";
SELECT 2 IS NOT DISTINCT FROM null as "no";
SELECT null IS NOT DISTINCT FROM null as "yes";
|
