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
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
|
from sqlglot import UnsupportedError, exp, parse_one
from tests.dialects.test_dialect import Validator
class TestSnowflake(Validator):
dialect = "snowflake"
def test_snowflake(self):
self.validate_identity("$x")
self.validate_identity("SELECT REGEXP_LIKE(a, b, c)")
self.validate_identity("PUT file:///dir/tmp.csv @%table")
self.validate_identity("CREATE TABLE foo (bar FLOAT AUTOINCREMENT START 0 INCREMENT 1)")
self.validate_identity("ALTER TABLE IF EXISTS foo SET TAG a = 'a', b = 'b', c = 'c'")
self.validate_identity("ALTER TABLE foo UNSET TAG a, b, c")
self.validate_identity(
'COPY INTO NEW_TABLE ("foo", "bar") FROM (SELECT $1, $2, $3, $4 FROM @%old_table)'
)
self.validate_identity("COMMENT IF EXISTS ON TABLE foo IS 'bar'")
self.validate_all(
"TO_CHAR(x, y)",
read={
"": "TO_CHAR(x, y)",
"snowflake": "TO_VARCHAR(x, y)",
},
write={
"": "CAST(x AS TEXT)",
"databricks": "TO_CHAR(x, y)",
"drill": "TO_CHAR(x, y)",
"oracle": "TO_CHAR(x, y)",
"postgres": "TO_CHAR(x, y)",
"snowflake": "TO_CHAR(x, y)",
"teradata": "TO_CHAR(x, y)",
},
)
self.validate_all(
"SQUARE(x)",
write={
"bigquery": "POWER(x, 2)",
"clickhouse": "POWER(x, 2)",
"databricks": "POWER(x, 2)",
"drill": "POW(x, 2)",
"duckdb": "POWER(x, 2)",
"hive": "POWER(x, 2)",
"mysql": "POWER(x, 2)",
"oracle": "POWER(x, 2)",
"postgres": "x ^ 2",
"presto": "POWER(x, 2)",
"redshift": "POWER(x, 2)",
"snowflake": "POWER(x, 2)",
"spark": "POWER(x, 2)",
"sqlite": "POWER(x, 2)",
"starrocks": "POWER(x, 2)",
"trino": "POWER(x, 2)",
"tsql": "POWER(x, 2)",
},
)
self.validate_all(
"POWER(x, 2)",
read={
"oracle": "SQUARE(x)",
"snowflake": "SQUARE(x)",
"tsql": "SQUARE(x)",
},
)
self.validate_all(
"DIV0(foo, bar)",
write={
"snowflake": "IFF(bar = 0, 0, foo / bar)",
"sqlite": "CASE WHEN bar = 0 THEN 0 ELSE foo / bar END",
"presto": "IF(bar = 0, 0, foo / bar)",
"spark": "IF(bar = 0, 0, foo / bar)",
"hive": "IF(bar = 0, 0, foo / bar)",
"duckdb": "CASE WHEN bar = 0 THEN 0 ELSE foo / bar END",
},
)
self.validate_all(
"ZEROIFNULL(foo)",
write={
"snowflake": "IFF(foo IS NULL, 0, foo)",
"sqlite": "CASE WHEN foo IS NULL THEN 0 ELSE foo END",
"presto": "IF(foo IS NULL, 0, foo)",
"spark": "IF(foo IS NULL, 0, foo)",
"hive": "IF(foo IS NULL, 0, foo)",
"duckdb": "CASE WHEN foo IS NULL THEN 0 ELSE foo END",
},
)
self.validate_all(
"NULLIFZERO(foo)",
write={
"snowflake": "IFF(foo = 0, NULL, foo)",
"sqlite": "CASE WHEN foo = 0 THEN NULL ELSE foo END",
"presto": "IF(foo = 0, NULL, foo)",
"spark": "IF(foo = 0, NULL, foo)",
"hive": "IF(foo = 0, NULL, foo)",
"duckdb": "CASE WHEN foo = 0 THEN NULL ELSE foo END",
},
)
self.validate_all(
"CREATE OR REPLACE TEMPORARY TABLE x (y NUMBER IDENTITY(0, 1))",
write={
"snowflake": "CREATE OR REPLACE TEMPORARY TABLE x (y DECIMAL AUTOINCREMENT START 0 INCREMENT 1)",
},
)
self.validate_all(
"CREATE TEMPORARY TABLE x (y NUMBER AUTOINCREMENT(0, 1))",
write={
"snowflake": "CREATE TEMPORARY TABLE x (y DECIMAL AUTOINCREMENT START 0 INCREMENT 1)",
},
)
self.validate_all(
"CREATE TABLE x (y NUMBER IDENTITY START 0 INCREMENT 1)",
write={
"snowflake": "CREATE TABLE x (y DECIMAL AUTOINCREMENT START 0 INCREMENT 1)",
},
)
self.validate_all(
"ALTER TABLE foo ADD COLUMN id INT identity(1, 1)",
write={
"snowflake": "ALTER TABLE foo ADD COLUMN id INT AUTOINCREMENT START 1 INCREMENT 1",
},
)
self.validate_all(
"SELECT DAYOFWEEK('2016-01-02T23:39:20.123-07:00'::TIMESTAMP)",
write={
"snowflake": "SELECT DAYOFWEEK(CAST('2016-01-02T23:39:20.123-07:00' AS TIMESTAMPNTZ))",
},
)
self.validate_all(
"SELECT * FROM xxx WHERE col ilike '%Don''t%'",
write={
"snowflake": "SELECT * FROM xxx WHERE col ILIKE '%Don\\'t%'",
},
)
self.validate_all(
"SELECT * EXCLUDE a, b FROM xxx",
write={
"snowflake": "SELECT * EXCLUDE (a, b) FROM xxx",
},
)
self.validate_all(
"SELECT * RENAME a AS b, c AS d FROM xxx",
write={
"snowflake": "SELECT * RENAME (a AS b, c AS d) FROM xxx",
},
)
self.validate_all(
"SELECT * EXCLUDE (a, b) RENAME (c AS d, E AS F) FROM xxx",
read={
"duckdb": "SELECT * EXCLUDE (a, b) REPLACE (c AS d, E AS F) FROM xxx",
},
write={
"snowflake": "SELECT * EXCLUDE (a, b) RENAME (c AS d, E AS F) FROM xxx",
"duckdb": "SELECT * EXCLUDE (a, b) REPLACE (c AS d, E AS F) FROM xxx",
},
)
self.validate_all(
'x:a:"b c"',
write={
"duckdb": "x['a']['b c']",
"hive": "x['a']['b c']",
"presto": "x['a']['b c']",
"snowflake": "x['a']['b c']",
"spark": "x['a']['b c']",
},
)
self.validate_all(
"SELECT a FROM test WHERE a = 1 GROUP BY a HAVING a = 2 QUALIFY z ORDER BY a LIMIT 10",
write={
"bigquery": "SELECT a FROM test WHERE a = 1 GROUP BY a HAVING a = 2 QUALIFY z ORDER BY a NULLS LAST LIMIT 10",
"snowflake": "SELECT a FROM test WHERE a = 1 GROUP BY a HAVING a = 2 QUALIFY z ORDER BY a LIMIT 10",
},
)
self.validate_all(
"SELECT a FROM test AS t QUALIFY ROW_NUMBER() OVER (PARTITION BY a ORDER BY Z) = 1",
write={
"bigquery": "SELECT a FROM test AS t QUALIFY ROW_NUMBER() OVER (PARTITION BY a ORDER BY Z NULLS LAST) = 1",
"snowflake": "SELECT a FROM test AS t QUALIFY ROW_NUMBER() OVER (PARTITION BY a ORDER BY Z) = 1",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP(1659981729)",
write={
"bigquery": "SELECT UNIX_TO_TIME(1659981729)",
"snowflake": "SELECT TO_TIMESTAMP(1659981729)",
"spark": "SELECT FROM_UNIXTIME(1659981729)",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP(1659981729000, 3)",
write={
"bigquery": "SELECT UNIX_TO_TIME(1659981729000, 'millis')",
"snowflake": "SELECT TO_TIMESTAMP(1659981729000, 3)",
"spark": "SELECT TIMESTAMP_MILLIS(1659981729000)",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP('1659981729')",
write={
"bigquery": "SELECT UNIX_TO_TIME('1659981729')",
"snowflake": "SELECT TO_TIMESTAMP('1659981729')",
"spark": "SELECT FROM_UNIXTIME('1659981729')",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP(1659981729000000000, 9)",
write={
"bigquery": "SELECT UNIX_TO_TIME(1659981729000000000, 'micros')",
"snowflake": "SELECT TO_TIMESTAMP(1659981729000000000, 9)",
"spark": "SELECT TIMESTAMP_MICROS(1659981729000000000)",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP('2013-04-05 01:02:03')",
write={
"bigquery": "SELECT PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', '2013-04-05 01:02:03')",
"snowflake": "SELECT TO_TIMESTAMP('2013-04-05 01:02:03', 'yyyy-mm-dd hh24:mi:ss')",
"spark": "SELECT TO_TIMESTAMP('2013-04-05 01:02:03', 'yyyy-MM-dd HH:mm:ss')",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP('04/05/2013 01:02:03', 'mm/dd/yyyy hh24:mi:ss')",
read={
"bigquery": "SELECT PARSE_TIMESTAMP('%m/%d/%Y %H:%M:%S', '04/05/2013 01:02:03')",
"duckdb": "SELECT STRPTIME('04/05/2013 01:02:03', '%m/%d/%Y %H:%M:%S')",
"snowflake": "SELECT TO_TIMESTAMP('04/05/2013 01:02:03', 'mm/dd/yyyy hh24:mi:ss')",
},
write={
"bigquery": "SELECT PARSE_TIMESTAMP('%m/%d/%Y %H:%M:%S', '04/05/2013 01:02:03')",
"snowflake": "SELECT TO_TIMESTAMP('04/05/2013 01:02:03', 'mm/dd/yyyy hh24:mi:ss')",
"spark": "SELECT TO_TIMESTAMP('04/05/2013 01:02:03', 'MM/dd/yyyy HH:mm:ss')",
},
)
self.validate_all(
"SELECT IFF(TRUE, 'true', 'false')",
write={
"snowflake": "SELECT IFF(TRUE, 'true', 'false')",
},
)
self.validate_all(
"SELECT fname, lname, age FROM person ORDER BY age DESC NULLS FIRST, fname ASC NULLS LAST, lname",
write={
"duckdb": "SELECT fname, lname, age FROM person ORDER BY age DESC NULLS FIRST, fname NULLS LAST, lname NULLS LAST",
"postgres": "SELECT fname, lname, age FROM person ORDER BY age DESC, fname, lname",
"presto": "SELECT fname, lname, age FROM person ORDER BY age DESC NULLS FIRST, fname, lname",
"hive": "SELECT fname, lname, age FROM person ORDER BY age DESC NULLS FIRST, fname NULLS LAST, lname NULLS LAST",
"spark": "SELECT fname, lname, age FROM person ORDER BY age DESC NULLS FIRST, fname NULLS LAST, lname NULLS LAST",
"snowflake": "SELECT fname, lname, age FROM person ORDER BY age DESC, fname, lname",
},
)
self.validate_all(
"SELECT ARRAY_AGG(DISTINCT a)",
write={
"spark": "SELECT COLLECT_LIST(DISTINCT a)",
"snowflake": "SELECT ARRAY_AGG(DISTINCT a)",
},
)
self.validate_all(
"ARRAY_TO_STRING(x, '')",
write={
"spark": "ARRAY_JOIN(x, '')",
"snowflake": "ARRAY_TO_STRING(x, '')",
},
)
self.validate_all(
"TO_ARRAY(x)",
write={
"spark": "ARRAY(x)",
"snowflake": "[x]",
},
)
self.validate_all(
"SELECT * FROM a INTERSECT ALL SELECT * FROM b",
write={
"snowflake": UnsupportedError,
},
)
self.validate_all(
"SELECT * FROM a EXCEPT ALL SELECT * FROM b",
write={
"snowflake": UnsupportedError,
},
)
self.validate_all(
"SELECT ARRAY_UNION_AGG(a)",
write={
"snowflake": "SELECT ARRAY_UNION_AGG(a)",
},
)
self.validate_all(
"SELECT NVL2(a, b, c)",
write={
"snowflake": "SELECT NVL2(a, b, c)",
},
)
self.validate_all(
"SELECT $$a$$",
write={
"snowflake": "SELECT 'a'",
},
)
self.validate_all(
r"SELECT $$a ' \ \t \x21 z $ $$",
write={
"snowflake": r"SELECT 'a \' \ \t \x21 z $ '",
},
)
self.validate_identity("REGEXP_REPLACE('target', 'pattern', '\n')")
self.validate_all(
"SELECT RLIKE(a, b)",
write={
"snowflake": "SELECT REGEXP_LIKE(a, b)",
},
)
self.validate_all(
"SELECT a FROM test pivot",
write={
"snowflake": "SELECT a FROM test AS pivot",
},
)
self.validate_all(
"SELECT a FROM test unpivot",
write={
"snowflake": "SELECT a FROM test AS unpivot",
},
)
self.validate_all(
"trim(date_column, 'UTC')",
write={
"bigquery": "TRIM(date_column, 'UTC')",
"snowflake": "TRIM(date_column, 'UTC')",
"postgres": "TRIM('UTC' FROM date_column)",
},
)
self.validate_all(
"trim(date_column)",
write={
"snowflake": "TRIM(date_column)",
"bigquery": "TRIM(date_column)",
},
)
self.validate_all(
"DECODE(x, a, b, c, d)",
read={
"": "MATCHES(x, a, b, c, d)",
},
write={
"": "MATCHES(x, a, b, c, d)",
"oracle": "DECODE(x, a, b, c, d)",
"snowflake": "DECODE(x, a, b, c, d)",
},
)
def test_null_treatment(self):
self.validate_all(
r"SELECT FIRST_VALUE(TABLE1.COLUMN1) OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1",
write={
"snowflake": r"SELECT FIRST_VALUE(TABLE1.COLUMN1) OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1"
},
)
self.validate_all(
r"SELECT FIRST_VALUE(TABLE1.COLUMN1 RESPECT NULLS) OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1",
write={
"snowflake": r"SELECT FIRST_VALUE(TABLE1.COLUMN1) OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1"
},
)
self.validate_all(
r"SELECT FIRST_VALUE(TABLE1.COLUMN1) RESPECT NULLS OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1",
write={
"snowflake": r"SELECT FIRST_VALUE(TABLE1.COLUMN1) RESPECT NULLS OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1"
},
)
self.validate_all(
r"SELECT FIRST_VALUE(TABLE1.COLUMN1 IGNORE NULLS) OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1",
write={
"snowflake": r"SELECT FIRST_VALUE(TABLE1.COLUMN1 IGNORE NULLS) OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1"
},
)
self.validate_all(
r"SELECT FIRST_VALUE(TABLE1.COLUMN1) IGNORE NULLS OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1",
write={
"snowflake": r"SELECT FIRST_VALUE(TABLE1.COLUMN1) IGNORE NULLS OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1"
},
)
def test_sample(self):
self.validate_identity("SELECT * FROM testtable TABLESAMPLE BERNOULLI (20.3)")
self.validate_identity("SELECT * FROM testtable TABLESAMPLE (100)")
self.validate_identity(
"SELECT i, j FROM table1 AS t1 INNER JOIN table2 AS t2 TABLESAMPLE (50) WHERE t2.j = t1.i"
)
self.validate_identity(
"SELECT * FROM (SELECT * FROM t1 JOIN t2 ON t1.a = t2.c) TABLESAMPLE (1)"
)
self.validate_identity("SELECT * FROM testtable TABLESAMPLE SYSTEM (3) SEED (82)")
self.validate_identity("SELECT * FROM testtable TABLESAMPLE (10 ROWS)")
self.validate_all(
"SELECT * FROM testtable SAMPLE (10)",
write={"snowflake": "SELECT * FROM testtable TABLESAMPLE (10)"},
)
self.validate_all(
"SELECT * FROM testtable SAMPLE ROW (0)",
write={"snowflake": "SELECT * FROM testtable TABLESAMPLE ROW (0)"},
)
self.validate_all(
"SELECT a FROM test SAMPLE BLOCK (0.5) SEED (42)",
write={
"snowflake": "SELECT a FROM test TABLESAMPLE BLOCK (0.5) SEED (42)",
},
)
self.validate_all(
"""
SELECT i, j
FROM
table1 AS t1 SAMPLE (25) -- 25% of rows in table1
INNER JOIN
table2 AS t2 SAMPLE (50) -- 50% of rows in table2
WHERE t2.j = t1.i""",
write={
"snowflake": "SELECT i, j FROM table1 AS t1 TABLESAMPLE (25) /* 25% of rows in table1 */ INNER JOIN table2 AS t2 TABLESAMPLE (50) /* 50% of rows in table2 */ WHERE t2.j = t1.i",
},
)
self.validate_all(
"SELECT * FROM testtable SAMPLE BLOCK (0.012) REPEATABLE (99992)",
write={
"snowflake": "SELECT * FROM testtable TABLESAMPLE BLOCK (0.012) SEED (99992)",
},
)
def test_timestamps(self):
self.validate_identity("SELECT EXTRACT(month FROM a)")
self.validate_all(
"SELECT CAST(a AS TIMESTAMP)",
write={
"snowflake": "SELECT CAST(a AS TIMESTAMPNTZ)",
},
)
self.validate_all(
"SELECT a::TIMESTAMP_LTZ(9)",
write={
"snowflake": "SELECT CAST(a AS TIMESTAMPLTZ(9))",
},
)
self.validate_all(
"SELECT a::TIMESTAMPLTZ",
write={
"snowflake": "SELECT CAST(a AS TIMESTAMPLTZ)",
},
)
self.validate_all(
"SELECT a::TIMESTAMP WITH LOCAL TIME ZONE",
write={
"snowflake": "SELECT CAST(a AS TIMESTAMPLTZ)",
},
)
self.validate_all(
"SELECT EXTRACT('month', a)",
write={
"snowflake": "SELECT EXTRACT('month' FROM a)",
},
)
self.validate_all(
"SELECT DATE_PART('month', a)",
write={
"snowflake": "SELECT EXTRACT('month' FROM a)",
},
)
self.validate_all(
"SELECT DATE_PART(month, a::DATETIME)",
write={
"snowflake": "SELECT EXTRACT(month FROM CAST(a AS DATETIME))",
},
)
self.validate_all(
"SELECT DATE_PART(epoch_second, foo) as ddate from table_name",
write={
"snowflake": "SELECT EXTRACT(epoch_second FROM CAST(foo AS TIMESTAMPNTZ)) AS ddate FROM table_name",
"presto": "SELECT TO_UNIXTIME(CAST(foo AS TIMESTAMP)) AS ddate FROM table_name",
},
)
self.validate_all(
"SELECT DATE_PART(epoch_milliseconds, foo) as ddate from table_name",
write={
"snowflake": "SELECT EXTRACT(epoch_second FROM CAST(foo AS TIMESTAMPNTZ)) * 1000 AS ddate FROM table_name",
"presto": "SELECT TO_UNIXTIME(CAST(foo AS TIMESTAMP)) * 1000 AS ddate FROM table_name",
},
)
self.validate_all(
"DATEADD(DAY, 5, CAST('2008-12-25' AS DATE))",
write={
"bigquery": "DATE_ADD(CAST('2008-12-25' AS DATE), INTERVAL 5 DAY)",
"snowflake": "DATEADD(DAY, 5, CAST('2008-12-25' AS DATE))",
},
)
def test_semi_structured_types(self):
self.validate_identity("SELECT CAST(a AS VARIANT)")
self.validate_identity("SELECT CAST(a AS ARRAY)")
self.validate_all(
"SELECT a::VARIANT",
write={
"snowflake": "SELECT CAST(a AS VARIANT)",
"tsql": "SELECT CAST(a AS SQL_VARIANT)",
},
)
self.validate_all(
"ARRAY_CONSTRUCT(0, 1, 2)",
write={
"snowflake": "[0, 1, 2]",
"bigquery": "[0, 1, 2]",
"duckdb": "LIST_VALUE(0, 1, 2)",
"presto": "ARRAY[0, 1, 2]",
"spark": "ARRAY(0, 1, 2)",
},
)
self.validate_all(
"SELECT a::OBJECT",
write={
"snowflake": "SELECT CAST(a AS OBJECT)",
},
)
def test_ddl(self):
self.validate_identity(
"CREATE TABLE a (x DATE, y BIGINT) WITH (PARTITION BY (x), integration='q', auto_refresh=TRUE, file_format=(type = parquet))"
)
self.validate_identity("CREATE MATERIALIZED VIEW a COMMENT='...' AS SELECT 1 FROM x")
self.validate_all(
"CREATE OR REPLACE TRANSIENT TABLE a (id INT)",
read={
"postgres": "CREATE OR REPLACE TRANSIENT TABLE a (id INT)",
"snowflake": "CREATE OR REPLACE TRANSIENT TABLE a (id INT)",
},
write={
"postgres": "CREATE OR REPLACE TABLE a (id INT)",
"mysql": "CREATE OR REPLACE TABLE a (id INT)",
"snowflake": "CREATE OR REPLACE TRANSIENT TABLE a (id INT)",
},
)
self.validate_all(
"CREATE TABLE a (b INT)",
read={"teradata": "CREATE MULTISET TABLE a (b INT)"},
write={"snowflake": "CREATE TABLE a (b INT)"},
)
def test_user_defined_functions(self):
self.validate_all(
"CREATE FUNCTION a(x DATE, y BIGINT) RETURNS ARRAY LANGUAGE JAVASCRIPT AS $$ SELECT 1 $$",
write={
"snowflake": "CREATE FUNCTION a(x DATE, y BIGINT) RETURNS ARRAY LANGUAGE JAVASCRIPT AS ' SELECT 1 '",
},
)
self.validate_all(
"CREATE FUNCTION a() RETURNS TABLE (b INT) AS 'SELECT 1'",
write={
"snowflake": "CREATE FUNCTION a() RETURNS TABLE (b INT) AS 'SELECT 1'",
"bigquery": "CREATE TABLE FUNCTION a() RETURNS TABLE <b INT64> AS SELECT 1",
},
)
self.validate_all(
"CREATE FUNCTION a() RETURNS INT IMMUTABLE AS 'SELECT 1'",
write={
"snowflake": "CREATE FUNCTION a() RETURNS INT IMMUTABLE AS 'SELECT 1'",
},
)
def test_stored_procedures(self):
self.validate_identity("CALL a.b.c(x, y)")
self.validate_identity(
"CREATE PROCEDURE a.b.c(x INT, y VARIANT) RETURNS OBJECT EXECUTE AS CALLER AS 'BEGIN SELECT 1; END;'"
)
def test_table_literal(self):
# All examples from https://docs.snowflake.com/en/sql-reference/literals-table.html
self.validate_all(
r"""SELECT * FROM TABLE('MYTABLE')""",
write={"snowflake": r"""SELECT * FROM TABLE('MYTABLE')"""},
)
self.validate_all(
r"""SELECT * FROM TABLE('MYDB."MYSCHEMA"."MYTABLE"')""",
write={"snowflake": r"""SELECT * FROM TABLE('MYDB."MYSCHEMA"."MYTABLE"')"""},
)
# Per Snowflake documentation at https://docs.snowflake.com/en/sql-reference/literals-table.html
# one can use either a " ' " or " $$ " to enclose the object identifier.
# Capturing the single tokens seems like lot of work. Hence adjusting tests to use these interchangeably,
self.validate_all(
r"""SELECT * FROM TABLE($$MYDB. "MYSCHEMA"."MYTABLE"$$)""",
write={"snowflake": r"""SELECT * FROM TABLE('MYDB. "MYSCHEMA"."MYTABLE"')"""},
)
self.validate_all(
r"""SELECT * FROM TABLE($MYVAR)""",
write={"snowflake": r"""SELECT * FROM TABLE($MYVAR)"""},
)
self.validate_all(
r"""SELECT * FROM TABLE(?)""",
write={"snowflake": r"""SELECT * FROM TABLE(?)"""},
)
self.validate_all(
r"""SELECT * FROM TABLE(:BINDING)""",
write={"snowflake": r"""SELECT * FROM TABLE(:BINDING)"""},
)
self.validate_all(
r"""SELECT * FROM TABLE($MYVAR) WHERE COL1 = 10""",
write={"snowflake": r"""SELECT * FROM TABLE($MYVAR) WHERE COL1 = 10"""},
)
def test_flatten(self):
self.validate_all(
"""
select
dag_report.acct_id,
dag_report.report_date,
dag_report.report_uuid,
dag_report.airflow_name,
dag_report.dag_id,
f.value::varchar as operator
from cs.telescope.dag_report,
table(flatten(input=>split(operators, ','))) f
""",
write={
"snowflake": """SELECT
dag_report.acct_id,
dag_report.report_date,
dag_report.report_uuid,
dag_report.airflow_name,
dag_report.dag_id,
CAST(f.value AS VARCHAR) AS operator
FROM cs.telescope.dag_report, TABLE(FLATTEN(input => SPLIT(operators, ','))) AS f"""
},
pretty=True,
)
# All examples from https://docs.snowflake.com/en/sql-reference/functions/flatten.html#syntax
self.validate_all(
"SELECT * FROM TABLE(FLATTEN(input => parse_json('[1, ,77]'))) f",
write={
"snowflake": "SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('[1, ,77]'))) AS f"
},
)
self.validate_all(
"""SELECT * FROM TABLE(FLATTEN(input => parse_json('{"a":1, "b":[77,88]}'), outer => true)) f""",
write={
"snowflake": """SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('{"a":1, "b":[77,88]}'), outer => TRUE)) AS f"""
},
)
self.validate_all(
"""SELECT * FROM TABLE(FLATTEN(input => parse_json('{"a":1, "b":[77,88]}'), path => 'b')) f""",
write={
"snowflake": """SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('{"a":1, "b":[77,88]}'), path => 'b')) AS f"""
},
)
self.validate_all(
"""SELECT * FROM TABLE(FLATTEN(input => parse_json('[]'))) f""",
write={"snowflake": """SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('[]'))) AS f"""},
)
self.validate_all(
"""SELECT * FROM TABLE(FLATTEN(input => parse_json('[]'), outer => true)) f""",
write={
"snowflake": """SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('[]'), outer => TRUE)) AS f"""
},
)
self.validate_all(
"""SELECT * FROM TABLE(FLATTEN(input => parse_json('{"a":1, "b":[77,88], "c": {"d":"X"}}'))) f""",
write={
"snowflake": """SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('{"a":1, "b":[77,88], "c": {"d":"X"}}'))) AS f"""
},
)
self.validate_all(
"""SELECT * FROM TABLE(FLATTEN(input => parse_json('{"a":1, "b":[77,88], "c": {"d":"X"}}'), recursive => true)) f""",
write={
"snowflake": """SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('{"a":1, "b":[77,88], "c": {"d":"X"}}'), recursive => TRUE)) AS f"""
},
)
self.validate_all(
"""SELECT * FROM TABLE(FLATTEN(input => parse_json('{"a":1, "b":[77,88], "c": {"d":"X"}}'), recursive => true, mode => 'object')) f""",
write={
"snowflake": """SELECT * FROM TABLE(FLATTEN(input => PARSE_JSON('{"a":1, "b":[77,88], "c": {"d":"X"}}'), recursive => TRUE, mode => 'object')) AS f"""
},
)
self.validate_all(
"""
SELECT id as "ID",
f.value AS "Contact",
f1.value:type AS "Type",
f1.value:content AS "Details"
FROM persons p,
lateral flatten(input => p.c, path => 'contact') f,
lateral flatten(input => f.value:business) f1
""",
write={
"snowflake": """SELECT
id AS "ID",
f.value AS "Contact",
f1.value['type'] AS "Type",
f1.value['content'] AS "Details"
FROM persons AS p, LATERAL FLATTEN(input => p.c, path => 'contact') AS f, LATERAL FLATTEN(input => f.value['business']) AS f1""",
},
pretty=True,
)
def test_minus(self):
self.validate_all(
"SELECT 1 EXCEPT SELECT 1",
read={
"oracle": "SELECT 1 MINUS SELECT 1",
"snowflake": "SELECT 1 MINUS SELECT 1",
},
)
def test_values(self):
self.validate_all(
'SELECT c0, c1 FROM (VALUES (1, 2), (3, 4)) AS "t0"(c0, c1)',
read={
"spark": "SELECT `c0`, `c1` FROM (VALUES (1, 2), (3, 4)) AS `t0`(`c0`, `c1`)",
},
)
self.validate_all(
"""SELECT $1 AS "_1" FROM VALUES ('a'), ('b')""",
write={
"snowflake": """SELECT $1 AS "_1" FROM (VALUES ('a'), ('b'))""",
"spark": """SELECT @1 AS `_1` FROM VALUES ('a'), ('b')""",
},
)
def test_describe_table(self):
self.validate_all(
"DESCRIBE TABLE db.table",
write={
"snowflake": "DESCRIBE TABLE db.table",
"spark": "DESCRIBE db.table",
},
)
self.validate_all(
"DESCRIBE db.table",
write={
"snowflake": "DESCRIBE TABLE db.table",
"spark": "DESCRIBE db.table",
},
)
self.validate_all(
"DESC TABLE db.table",
write={
"snowflake": "DESCRIBE TABLE db.table",
"spark": "DESCRIBE db.table",
},
)
self.validate_all(
"DESC VIEW db.table",
write={
"snowflake": "DESCRIBE VIEW db.table",
"spark": "DESCRIBE db.table",
},
)
def test_parse_like_any(self):
like = parse_one("a LIKE ANY fun('foo')", read="snowflake")
ilike = parse_one("a ILIKE ANY fun('foo')", read="snowflake")
self.assertIsInstance(like, exp.LikeAny)
self.assertIsInstance(ilike, exp.ILikeAny)
def test_match_recognize(self):
for row in (
"ONE ROW PER MATCH",
"ALL ROWS PER MATCH",
"ALL ROWS PER MATCH SHOW EMPTY MATCHES",
"ALL ROWS PER MATCH OMIT EMPTY MATCHES",
"ALL ROWS PER MATCH WITH UNMATCHED ROWS",
):
for after in (
"AFTER MATCH SKIP",
"AFTER MATCH SKIP PAST LAST ROW",
"AFTER MATCH SKIP TO NEXT ROW",
"AFTER MATCH SKIP TO FIRST x",
"AFTER MATCH SKIP TO LAST x",
):
self.validate_identity(
f"""SELECT
*
FROM x
MATCH_RECOGNIZE (
PARTITION BY a, b
ORDER BY
x DESC
MEASURES y AS b
{row}
{after}
PATTERN (^ S1 S2*? ( {{- S3 -}} S4 )+ | PERMUTE(S1, S2){{1,2}} $)
DEFINE x AS y
)""",
pretty=True,
)
|