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
|
from sqlglot import UnsupportedError
from tests.dialects.test_dialect import Validator
class TestSnowflake(Validator):
dialect = "snowflake"
def test_snowflake(self):
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 STR_TO_TIME('2013-04-05 01:02:03', '%Y-%m-%d %H:%M:%S')",
"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 STR_TO_TIME('04/05/2013 01:02:03', '%m/%d/%Y %H:%M:%S')",
"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 STR_TO_TIME('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')",
"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(
"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 $ '",
},
)
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_timestamps(self):
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_identity("SELECT EXTRACT(month FROM a)")
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 FROM a::DATETIME)",
write={
"snowflake": "SELECT EXTRACT(month FROM CAST(a AS DATETIME))",
},
)
|
