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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
|
--
-- COPY
--
-- directory paths are passed to us in environment variables
\getenv abs_srcdir PG_ABS_SRCDIR
\getenv abs_builddir PG_ABS_BUILDDIR
--- test copying in CSV mode with various styles
--- of embedded line ending characters
create temp table copytest (
style text,
test text,
filler int);
insert into copytest values('DOS',E'abc\r\ndef',1);
insert into copytest values('Unix',E'abc\ndef',2);
insert into copytest values('Mac',E'abc\rdef',3);
insert into copytest values(E'esc\\ape',E'a\\r\\\r\\\n\\nb',4);
\set filename :abs_builddir '/results/copytest.csv'
copy copytest to :'filename' csv;
create temp table copytest2 (like copytest);
copy copytest2 from :'filename' csv;
select * from copytest except select * from copytest2;
truncate copytest2;
--- same test but with an escape char different from quote char
copy copytest to :'filename' csv quote '''' escape E'\\';
copy copytest2 from :'filename' csv quote '''' escape E'\\';
select * from copytest except select * from copytest2;
--- test unquoted \. as data inside CSV
-- do not use copy out to export the data, as it would quote \.
\o :filename
\qecho line1
\qecho '\\.'
\qecho line2
\o
-- get the data back in with copy
truncate copytest2;
copy copytest2(test) from :'filename' csv;
select test from copytest2 order by test collate "C";
-- in text mode, \. must be alone on its line
truncate copytest2;
copy copytest2(test) from stdin;
line1
line2
foo\.
line3
\.
copy copytest2(test) from stdin;
line4
line5
\.foo
line6
\.
select test from copytest2;
-- test header line feature
create temp table copytest3 (
c1 int,
"col with , comma" text,
"col with "" quote" int);
copy copytest3 from stdin csv header;
this is just a line full of junk that would error out if parsed
1,a,1
2,b,2
\.
copy copytest3 to stdout csv header;
create temp table copytest4 (
c1 int,
"colname with tab: " text);
copy copytest4 from stdin (header);
this is just a line full of junk that would error out if parsed
1 a
2 b
\.
copy copytest4 to stdout (header);
-- test copy from with a partitioned table
create table parted_copytest (
a int,
b int,
c text
) partition by list (b);
create table parted_copytest_a1 (c text, b int, a int);
create table parted_copytest_a2 (a int, c text, b int);
alter table parted_copytest attach partition parted_copytest_a1 for values in(1);
alter table parted_copytest attach partition parted_copytest_a2 for values in(2);
-- We must insert enough rows to trigger multi-inserts. These are only
-- enabled adaptively when there are few enough partition changes.
insert into parted_copytest select x,1,'One' from generate_series(1,1000) x;
insert into parted_copytest select x,2,'Two' from generate_series(1001,1010) x;
insert into parted_copytest select x,1,'One' from generate_series(1011,1020) x;
\set filename :abs_builddir '/results/parted_copytest.csv'
copy (select * from parted_copytest order by a) to :'filename';
truncate parted_copytest;
copy parted_copytest from :'filename';
-- Ensure COPY FREEZE errors for partitioned tables.
begin;
truncate parted_copytest;
copy parted_copytest from :'filename' (freeze);
rollback;
select tableoid::regclass,count(*),sum(a) from parted_copytest
group by tableoid order by tableoid::regclass::name;
truncate parted_copytest;
-- create before insert row trigger on parted_copytest_a2
create function part_ins_func() returns trigger language plpgsql as $$
begin
return new;
end;
$$;
create trigger part_ins_trig
before insert on parted_copytest_a2
for each row
execute procedure part_ins_func();
copy parted_copytest from :'filename';
select tableoid::regclass,count(*),sum(a) from parted_copytest
group by tableoid order by tableoid::regclass::name;
truncate table parted_copytest;
create index on parted_copytest (b);
drop trigger part_ins_trig on parted_copytest_a2;
copy parted_copytest from stdin;
1 1 str1
2 2 str2
\.
-- Ensure index entries were properly added during the copy.
select * from parted_copytest where b = 1;
select * from parted_copytest where b = 2;
drop table parted_copytest;
--
-- Progress reporting for COPY
--
create table tab_progress_reporting (
name text,
age int4,
location point,
salary int4,
manager name
);
-- Add a trigger to catch and print the contents of the catalog view
-- pg_stat_progress_copy during data insertion. This allows to test
-- the validation of some progress reports for COPY FROM where the trigger
-- would fire.
create function notice_after_tab_progress_reporting() returns trigger AS
$$
declare report record;
begin
-- The fields ignored here are the ones that may not remain
-- consistent across multiple runs. The sizes reported may differ
-- across platforms, so just check if these are strictly positive.
with progress_data as (
select
relid::regclass::text as relname,
command,
type,
bytes_processed > 0 as has_bytes_processed,
bytes_total > 0 as has_bytes_total,
tuples_processed,
tuples_excluded,
tuples_skipped
from pg_stat_progress_copy
where pid = pg_backend_pid())
select into report (to_jsonb(r)) as value
from progress_data r;
raise info 'progress: %', report.value::text;
return new;
end;
$$ language plpgsql;
create trigger check_after_tab_progress_reporting
after insert on tab_progress_reporting
for each statement
execute function notice_after_tab_progress_reporting();
-- Generate COPY FROM report with PIPE.
copy tab_progress_reporting from stdin;
sharon 25 (15,12) 1000 sam
sam 30 (10,5) 2000 bill
bill 20 (11,10) 1000 sharon
\.
-- Generate COPY FROM report with FILE, with some excluded tuples.
truncate tab_progress_reporting;
\set filename :abs_srcdir '/data/emp.data'
copy tab_progress_reporting from :'filename'
where (salary < 2000);
-- Generate COPY FROM report with PIPE, with some skipped tuples.
copy tab_progress_reporting from stdin(on_error ignore);
sharon x (15,12) x sam
sharon 25 (15,12) 1000 sam
sharon y (15,12) x sam
\.
drop trigger check_after_tab_progress_reporting on tab_progress_reporting;
drop function notice_after_tab_progress_reporting();
drop table tab_progress_reporting;
-- Test header matching feature
create table header_copytest (
a int,
b int,
c text
);
-- Make sure it works with dropped columns
alter table header_copytest drop column c;
alter table header_copytest add column c text;
copy header_copytest to stdout with (header match);
copy header_copytest from stdin with (header wrong_choice);
-- works
copy header_copytest from stdin with (header match);
a b c
1 2 foo
\.
copy header_copytest (c, a, b) from stdin with (header match);
c a b
bar 3 4
\.
copy header_copytest from stdin with (header match, format csv);
a,b,c
5,6,baz
\.
-- errors
copy header_copytest (c, b, a) from stdin with (header match);
a b c
1 2 foo
\.
copy header_copytest from stdin with (header match);
a b \N
1 2 foo
\.
copy header_copytest from stdin with (header match);
a b
1 2
\.
copy header_copytest from stdin with (header match);
a b c d
1 2 foo bar
\.
copy header_copytest from stdin with (header match);
a b d
1 2 foo
\.
SELECT * FROM header_copytest ORDER BY a;
-- Drop an extra column, in the middle of the existing set.
alter table header_copytest drop column b;
-- works
copy header_copytest (c, a) from stdin with (header match);
c a
foo 7
\.
copy header_copytest (a, c) from stdin with (header match);
a c
8 foo
\.
-- errors
copy header_copytest from stdin with (header match);
a ........pg.dropped.2........ c
1 2 foo
\.
copy header_copytest (a, c) from stdin with (header match);
a c b
1 foo 2
\.
SELECT * FROM header_copytest ORDER BY a;
drop table header_copytest;
-- test COPY with overlong column defaults
create temp table oversized_column_default (
col1 varchar(5) DEFAULT 'more than 5 chars',
col2 varchar(5));
-- normal COPY should work
copy oversized_column_default from stdin;
\.
-- error if the column is excluded
copy oversized_column_default (col2) from stdin;
\.
-- error if the DEFAULT option is given
copy oversized_column_default from stdin (default '');
\.
drop table oversized_column_default;
--
-- Create partitioned table that does not allow bulk insertions, to test bugs
-- related to the reuse of BulkInsertState across partitions (only done when
-- not using bulk insert). Switching between partitions often makes it more
-- likely to encounter these bugs, so we just switch on roughly every insert
-- by having an even/odd number partition and inserting evenly distributed
-- data.
--
CREATE TABLE parted_si (
id int not null,
data text not null,
-- prevent use of bulk insert by having a volatile function
rand float8 not null default random()
)
PARTITION BY LIST((id % 2));
CREATE TABLE parted_si_p_even PARTITION OF parted_si FOR VALUES IN (0);
CREATE TABLE parted_si_p_odd PARTITION OF parted_si FOR VALUES IN (1);
-- Test that bulk relation extension handles reusing a single BulkInsertState
-- across partitions. Without the fix applied, this reliably reproduces
-- #18130 unless shared_buffers is extremely small (preventing any use of bulk
-- relation extension). See
-- https://postgr.es/m/18130-7a86a7356a75209d%40postgresql.org
-- https://postgr.es/m/257696.1695670946%40sss.pgh.pa.us
\set filename :abs_srcdir '/data/desc.data'
COPY parted_si(id, data) FROM :'filename';
-- An earlier bug (see commit b1ecb9b3fcf) could end up using a buffer from
-- the wrong partition. This test is *not* guaranteed to trigger that bug, but
-- does so when shared_buffers is small enough. To test if we encountered the
-- bug, check that the partition condition isn't violated.
SELECT tableoid::regclass, id % 2 = 0 is_even, count(*) from parted_si GROUP BY 1, 2 ORDER BY 1;
DROP TABLE parted_si;
-- ensure COPY FREEZE errors for foreign tables
begin;
create foreign data wrapper copytest_wrapper;
create server copytest_server foreign data wrapper copytest_wrapper;
create foreign table copytest_foreign_table (a int) server copytest_server;
copy copytest_foreign_table from stdin (freeze);
1
\.
rollback;
-- Tests for COPY TO with materialized views.
-- COPY TO should fail for an unpopulated materialized view
-- but succeed for a populated one.
CREATE MATERIALIZED VIEW copytest_mv AS SELECT 1 AS id WITH NO DATA;
COPY copytest_mv(id) TO stdout WITH (header);
REFRESH MATERIALIZED VIEW copytest_mv;
COPY copytest_mv(id) TO stdout WITH (header);
DROP MATERIALIZED VIEW copytest_mv;
|