summaryrefslogtreecommitdiffstats
path: root/tests/dialects/test_bigquery.py
blob: 241f496ffa3ee0519b360d083bc637a8890273c3 (plain)
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
from sqlglot import ErrorLevel, ParseError, UnsupportedError, transpile
from tests.dialects.test_dialect import Validator


class TestBigQuery(Validator):
    dialect = "bigquery"

    def test_bigquery(self):
        self.validate_identity("SELECT STRUCT<ARRAY<STRING>>(['2023-01-17'])")
        self.validate_identity("SELECT * FROM q UNPIVOT(values FOR quarter IN (b, c))")
        self.validate_all(
            "REGEXP_CONTAINS('foo', '.*')",
            read={"bigquery": "REGEXP_CONTAINS('foo', '.*')"},
            write={"mysql": "REGEXP_LIKE('foo', '.*')"},
        ),
        self.validate_all(
            '"""x"""',
            write={
                "bigquery": "'x'",
                "duckdb": "'x'",
                "presto": "'x'",
                "hive": "'x'",
                "spark": "'x'",
            },
        )
        self.validate_all(
            '"""x\'"""',
            write={
                "bigquery": "'x\\''",
                "duckdb": "'x'''",
                "presto": "'x'''",
                "hive": "'x\\''",
                "spark": "'x\\''",
            },
        )
        self.validate_all(
            r'r"""/\*.*\*/"""',
            write={
                "bigquery": r"'/\\*.*\\*/'",
                "duckdb": r"'/\*.*\*/'",
                "presto": r"'/\*.*\*/'",
                "hive": r"'/\\*.*\\*/'",
                "spark": r"'/\\*.*\\*/'",
            },
        )
        self.validate_all(
            r"'\\'",
            write={
                "bigquery": r"'\\'",
                "duckdb": r"'\'",
                "presto": r"'\'",
                "hive": r"'\\'",
            },
        )
        self.validate_all(
            R'R"""/\*.*\*/"""',
            write={
                "bigquery": R"'/\\*.*\\*/'",
                "duckdb": R"'/\*.*\*/'",
                "presto": R"'/\*.*\*/'",
                "hive": R"'/\\*.*\\*/'",
                "spark": R"'/\\*.*\\*/'",
            },
        )
        self.validate_all(
            "CAST(a AS INT64)",
            write={
                "bigquery": "CAST(a AS INT64)",
                "duckdb": "CAST(a AS BIGINT)",
                "presto": "CAST(a AS BIGINT)",
                "hive": "CAST(a AS BIGINT)",
                "spark": "CAST(a AS LONG)",
            },
        )
        self.validate_all(
            "CAST(a AS NUMERIC)",
            write={
                "bigquery": "CAST(a AS NUMERIC)",
                "duckdb": "CAST(a AS DECIMAL)",
                "presto": "CAST(a AS DECIMAL)",
                "hive": "CAST(a AS DECIMAL)",
                "spark": "CAST(a AS DECIMAL)",
            },
        )
        self.validate_all(
            "[1, 2, 3]",
            read={
                "duckdb": "LIST_VALUE(1, 2, 3)",
                "presto": "ARRAY[1, 2, 3]",
                "hive": "ARRAY(1, 2, 3)",
                "spark": "ARRAY(1, 2, 3)",
            },
            write={
                "bigquery": "[1, 2, 3]",
                "duckdb": "LIST_VALUE(1, 2, 3)",
                "presto": "ARRAY[1, 2, 3]",
                "hive": "ARRAY(1, 2, 3)",
                "spark": "ARRAY(1, 2, 3)",
            },
        )
        self.validate_all(
            "SELECT * FROM UNNEST(['7', '14']) AS x",
            read={
                "spark": "SELECT * FROM UNNEST(ARRAY('7', '14')) AS (x)",
            },
            write={
                "bigquery": "SELECT * FROM UNNEST(['7', '14']) AS x",
                "presto": "SELECT * FROM UNNEST(ARRAY['7', '14']) AS (x)",
                "hive": "SELECT * FROM UNNEST(ARRAY('7', '14')) AS (x)",
                "spark": "SELECT * FROM UNNEST(ARRAY('7', '14')) AS (x)",
            },
        )
        self.validate_all(
            "SELECT ARRAY(SELECT x FROM UNNEST([0, 1]) AS x)",
            write={"bigquery": "SELECT ARRAY(SELECT x FROM UNNEST([0, 1]) AS x)"},
        )
        self.validate_all(
            "SELECT ARRAY(SELECT DISTINCT x FROM UNNEST(some_numbers) AS x) AS unique_numbers",
            write={
                "bigquery": "SELECT ARRAY(SELECT DISTINCT x FROM UNNEST(some_numbers) AS x) AS unique_numbers"
            },
        )
        self.validate_all(
            "SELECT ARRAY(SELECT * FROM foo JOIN bla ON x = y)",
            write={"bigquery": "SELECT ARRAY(SELECT * FROM foo JOIN bla ON x = y)"},
        )

        self.validate_all(
            "x IS unknown",
            write={
                "bigquery": "x IS NULL",
                "duckdb": "x IS NULL",
                "presto": "x IS NULL",
                "hive": "x IS NULL",
                "spark": "x IS NULL",
            },
        )
        self.validate_all(
            "CURRENT_TIMESTAMP()",
            read={
                "tsql": "GETDATE()",
            },
            write={
                "tsql": "GETDATE()",
            },
        )
        self.validate_all(
            "current_datetime",
            write={
                "bigquery": "CURRENT_DATETIME()",
                "duckdb": "CURRENT_DATETIME()",
                "presto": "CURRENT_DATETIME()",
                "hive": "CURRENT_DATETIME()",
                "spark": "CURRENT_DATETIME()",
            },
        )
        self.validate_all(
            "current_time",
            write={
                "bigquery": "CURRENT_TIME()",
                "duckdb": "CURRENT_TIME()",
                "presto": "CURRENT_TIME()",
                "hive": "CURRENT_TIME()",
                "spark": "CURRENT_TIME()",
            },
        )
        self.validate_all(
            "current_timestamp",
            write={
                "bigquery": "CURRENT_TIMESTAMP()",
                "duckdb": "CURRENT_TIMESTAMP()",
                "postgres": "CURRENT_TIMESTAMP",
                "presto": "CURRENT_TIMESTAMP",
                "hive": "CURRENT_TIMESTAMP()",
                "spark": "CURRENT_TIMESTAMP()",
            },
        )
        self.validate_all(
            "current_timestamp()",
            write={
                "bigquery": "CURRENT_TIMESTAMP()",
                "duckdb": "CURRENT_TIMESTAMP()",
                "postgres": "CURRENT_TIMESTAMP",
                "presto": "CURRENT_TIMESTAMP",
                "hive": "CURRENT_TIMESTAMP()",
                "spark": "CURRENT_TIMESTAMP()",
            },
        )

        self.validate_all(
            "DIV(x, y)",
            write={
                "bigquery": "DIV(x, y)",
                "duckdb": "CAST(x / y AS INT)",
            },
        )

        self.validate_identity(
            "SELECT ROW() OVER (y ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING) FROM x WINDOW y AS (PARTITION BY CATEGORY)"
        )

        self.validate_identity(
            "SELECT item, purchases, LAST_VALUE(item) OVER (item_window ROWS BETWEEN 2 PRECEDING AND 2 FOLLOWING) AS most_popular FROM Produce WINDOW item_window AS (ORDER BY purchases)"
        )

        self.validate_identity(
            "SELECT LAST_VALUE(a IGNORE NULLS) OVER y FROM x WINDOW y AS (PARTITION BY CATEGORY)",
        )

        self.validate_all(
            "CREATE TABLE db.example_table (col_a struct<struct_col_a:int, struct_col_b:string>)",
            write={
                "bigquery": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT64, struct_col_b STRING>)",
                "duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a INT, struct_col_b TEXT))",
                "presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a INTEGER, struct_col_b VARCHAR))",
                "hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT, struct_col_b STRING>)",
                "spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: INT, struct_col_b: STRING>)",
            },
        )
        self.validate_all(
            "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT64, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
            write={
                "bigquery": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a INT64, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
                "duckdb": "CREATE TABLE db.example_table (col_a STRUCT(struct_col_a BIGINT, struct_col_b STRUCT(nested_col_a TEXT, nested_col_b TEXT)))",
                "presto": "CREATE TABLE db.example_table (col_a ROW(struct_col_a BIGINT, struct_col_b ROW(nested_col_a VARCHAR, nested_col_b VARCHAR)))",
                "hive": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a BIGINT, struct_col_b STRUCT<nested_col_a STRING, nested_col_b STRING>>)",
                "spark": "CREATE TABLE db.example_table (col_a STRUCT<struct_col_a: LONG, struct_col_b: STRUCT<nested_col_a: STRING, nested_col_b: STRING>>)",
            },
        )
        self.validate_all(
            "SELECT * FROM a WHERE b IN UNNEST([1, 2, 3])",
            write={
                "bigquery": "SELECT * FROM a WHERE b IN UNNEST([1, 2, 3])",
                "mysql": "SELECT * FROM a WHERE b IN (SELECT UNNEST(ARRAY(1, 2, 3)))",
                "presto": "SELECT * FROM a WHERE b IN (SELECT UNNEST(ARRAY[1, 2, 3]))",
                "hive": "SELECT * FROM a WHERE b IN (SELECT UNNEST(ARRAY(1, 2, 3)))",
                "spark": "SELECT * FROM a WHERE b IN (SELECT UNNEST(ARRAY(1, 2, 3)))",
            },
        )

        # Reference: https://cloud.google.com/bigquery/docs/reference/standard-sql/query-syntax#set_operators
        with self.assertRaises(UnsupportedError):
            transpile(
                "SELECT * FROM a INTERSECT ALL SELECT * FROM b",
                write="bigquery",
                unsupported_level=ErrorLevel.RAISE,
            )

        with self.assertRaises(UnsupportedError):
            transpile(
                "SELECT * FROM a EXCEPT ALL SELECT * FROM b",
                write="bigquery",
                unsupported_level=ErrorLevel.RAISE,
            )

        with self.assertRaises(ParseError):
            transpile("SELECT * FROM UNNEST(x) AS x(y)", read="bigquery")

        self.validate_all(
            "DATE_SUB(CURRENT_DATE(), INTERVAL 1 DAY)",
            write={
                "postgres": "CURRENT_DATE - INTERVAL '1' DAY",
            },
        )
        self.validate_all(
            "DATE_ADD(CURRENT_DATE(), INTERVAL 1 DAY)",
            write={
                "bigquery": "DATE_ADD(CURRENT_DATE, INTERVAL 1 DAY)",
                "duckdb": "CURRENT_DATE + INTERVAL 1 DAY",
                "mysql": "DATE_ADD(CURRENT_DATE, INTERVAL 1 DAY)",
                "postgres": "CURRENT_DATE + INTERVAL '1' DAY",
                "presto": "DATE_ADD(DAY, 1, CURRENT_DATE)",
                "hive": "DATE_ADD(CURRENT_DATE, 1)",
                "spark": "DATE_ADD(CURRENT_DATE, 1)",
            },
        )
        self.validate_all(
            "DATE_DIFF(DATE '2010-07-07', DATE '2008-12-25', DAY)",
            write={
                "bigquery": "DATE_DIFF(CAST('2010-07-07' AS DATE), CAST('2008-12-25' AS DATE), DAY)",
                "mysql": "DATEDIFF(CAST('2010-07-07' AS DATE), CAST('2008-12-25' AS DATE))",
            },
        )
        self.validate_all(
            "DATE_DIFF(DATE '2010-07-07', DATE '2008-12-25', MINUTE)",
            write={
                "bigquery": "DATE_DIFF(CAST('2010-07-07' AS DATE), CAST('2008-12-25' AS DATE), MINUTE)",
                "mysql": "DATEDIFF(CAST('2010-07-07' AS DATE), CAST('2008-12-25' AS DATE))",
            },
        )
        self.validate_all(
            "CURRENT_DATE('UTC')",
            write={
                "mysql": "CURRENT_DATE AT TIME ZONE 'UTC'",
                "postgres": "CURRENT_DATE AT TIME ZONE 'UTC'",
            },
        )
        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 LIMIT 10",
                "snowflake": "SELECT a FROM test WHERE a = 1 GROUP BY a HAVING a = 2 QUALIFY z ORDER BY a NULLS FIRST LIMIT 10",
            },
        )
        self.validate_all(
            "SELECT cola, colb FROM (VALUES (1, 'test')) AS tab(cola, colb)",
            write={
                "spark": "SELECT cola, colb FROM VALUES (1, 'test') AS tab(cola, colb)",
                "bigquery": "SELECT cola, colb FROM UNNEST([STRUCT(1 AS cola, 'test' AS colb)])",
                "snowflake": "SELECT cola, colb FROM (VALUES (1, 'test')) AS tab(cola, colb)",
            },
        )
        self.validate_all(
            "SELECT cola, colb, colc FROM (VALUES (1, 'test', NULL)) AS tab(cola, colb, colc)",
            write={
                "spark": "SELECT cola, colb, colc FROM VALUES (1, 'test', NULL) AS tab(cola, colb, colc)",
                "bigquery": "SELECT cola, colb, colc FROM UNNEST([STRUCT(1 AS cola, 'test' AS colb, NULL AS colc)])",
                "snowflake": "SELECT cola, colb, colc FROM (VALUES (1, 'test', NULL)) AS tab(cola, colb, colc)",
            },
        )
        self.validate_all(
            "SELECT * FROM (SELECT a, b, c FROM test) PIVOT(SUM(b) d, COUNT(*) e FOR c IN ('x', 'y'))",
            write={
                "bigquery": "SELECT * FROM (SELECT a, b, c FROM test) PIVOT(SUM(b) AS d, COUNT(*) AS e FOR c IN ('x', 'y'))",
            },
        )
        self.validate_identity("BEGIN A B C D E F")
        self.validate_identity("BEGIN TRANSACTION")
        self.validate_identity("COMMIT TRANSACTION")
        self.validate_identity("ROLLBACK TRANSACTION")

    def test_user_defined_functions(self):
        self.validate_identity(
            "CREATE TEMPORARY FUNCTION a(x FLOAT64, y FLOAT64) RETURNS FLOAT64 NOT DETERMINISTIC LANGUAGE js AS 'return x*y;'"
        )
        self.validate_identity("CREATE TEMPORARY FUNCTION a(x FLOAT64, y FLOAT64) AS ((x + 4) / y)")
        self.validate_identity(
            "CREATE TABLE FUNCTION a(x INT64) RETURNS TABLE <q STRING, r INT64> AS SELECT s, t"
        )

    def test_group_concat(self):
        self.validate_all(
            "SELECT a, GROUP_CONCAT(b) FROM table GROUP BY a",
            write={"bigquery": "SELECT a, STRING_AGG(b) FROM table GROUP BY a"},
        )

    def test_remove_precision_parameterized_types(self):
        self.validate_all(
            "SELECT CAST(1 AS NUMERIC(10, 2))",
            write={
                "bigquery": "SELECT CAST(1 AS NUMERIC)",
            },
        )
        self.validate_all(
            "CREATE TABLE test (a NUMERIC(10, 2))",
            write={
                "bigquery": "CREATE TABLE test (a NUMERIC(10, 2))",
            },
        )
        self.validate_all(
            "SELECT CAST('1' AS STRING(10)) UNION ALL SELECT CAST('2' AS STRING(10))",
            write={
                "bigquery": "SELECT CAST('1' AS STRING) UNION ALL SELECT CAST('2' AS STRING)",
            },
        )
        self.validate_all(
            "SELECT cola FROM (SELECT CAST('1' AS STRING(10)) AS cola UNION ALL SELECT CAST('2' AS STRING(10)) AS cola)",
            write={
                "bigquery": "SELECT cola FROM (SELECT CAST('1' AS STRING) AS cola UNION ALL SELECT CAST('2' AS STRING) AS cola)",
            },
        )
        self.validate_all(
            "INSERT INTO test (cola, colb) VALUES (CAST(7 AS STRING(10)), CAST(14 AS STRING(10)))",
            write={
                "bigquery": "INSERT INTO test (cola, colb) VALUES (CAST(7 AS STRING), CAST(14 AS STRING))",
            },
        )