Merging upstream version 25.29.0.
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
parent
de8c8a17d0
commit
1e53504dfc
GPG key ID:
FBB4F0E80A80222F
97 changed files with 64720 additions and 61752 deletions
|
|
@ -9,7 +9,6 @@ from sqlglot import (
|
|||
UnsupportedError,
|
||||
exp,
|
||||
parse,
|
||||
parse_one,
|
||||
transpile,
|
||||
)
|
||||
from sqlglot.helper import logger as helper_logger
|
||||
|
|
@ -85,12 +84,21 @@ LANGUAGE js AS
|
|||
"PARSE_TIMESTAMP('%Y-%m-%dT%H:%M:%E*S%z', x)",
|
||||
)
|
||||
|
||||
table = parse_one("x-0._y.z", dialect="bigquery", into=exp.Table)
|
||||
for prefix in ("c.db.", "db.", ""):
|
||||
with self.subTest(f"Parsing {prefix}INFORMATION_SCHEMA.X into a Table"):
|
||||
table = self.parse_one(f"`{prefix}INFORMATION_SCHEMA.X`", into=exp.Table)
|
||||
this = table.this
|
||||
|
||||
self.assertIsInstance(this, exp.Identifier)
|
||||
self.assertTrue(this.quoted)
|
||||
self.assertEqual(this.name, "INFORMATION_SCHEMA.X")
|
||||
|
||||
table = self.parse_one("x-0._y.z", into=exp.Table)
|
||||
self.assertEqual(table.catalog, "x-0")
|
||||
self.assertEqual(table.db, "_y")
|
||||
self.assertEqual(table.name, "z")
|
||||
|
||||
table = parse_one("x-0._y", dialect="bigquery", into=exp.Table)
|
||||
table = self.parse_one("x-0._y", into=exp.Table)
|
||||
self.assertEqual(table.db, "x-0")
|
||||
self.assertEqual(table.name, "_y")
|
||||
|
||||
|
|
@ -165,6 +173,7 @@ LANGUAGE js AS
|
|||
self.validate_identity("SELECT * FROM foo.bar.25ab c", "SELECT * FROM foo.bar.`25ab` AS c")
|
||||
self.validate_identity("x <> ''")
|
||||
self.validate_identity("DATE_TRUNC(col, WEEK(MONDAY))")
|
||||
self.validate_identity("DATE_TRUNC(col, MONTH, 'UTC+8')")
|
||||
self.validate_identity("SELECT b'abc'")
|
||||
self.validate_identity("SELECT AS STRUCT 1 AS a, 2 AS b")
|
||||
self.validate_identity("SELECT DISTINCT AS STRUCT 1 AS a, 2 AS b")
|
||||
|
|
@ -182,7 +191,6 @@ LANGUAGE js AS
|
|||
self.validate_identity("SELECT y + 1 FROM x GROUP BY y + 1 ORDER BY 1")
|
||||
self.validate_identity("SELECT TIMESTAMP_SECONDS(2) AS t")
|
||||
self.validate_identity("SELECT TIMESTAMP_MILLIS(2) AS t")
|
||||
self.validate_identity("""SELECT JSON_EXTRACT_SCALAR('{"a": 5}', '$.a')""")
|
||||
self.validate_identity("UPDATE x SET y = NULL")
|
||||
self.validate_identity("LOG(n, b)")
|
||||
self.validate_identity("SELECT COUNT(x RESPECT NULLS)")
|
||||
|
|
@ -194,11 +202,11 @@ LANGUAGE js AS
|
|||
self.validate_identity("CAST(x AS NVARCHAR)", "CAST(x AS STRING)")
|
||||
self.validate_identity("CAST(x AS TIMESTAMPTZ)", "CAST(x AS TIMESTAMP)")
|
||||
self.validate_identity("CAST(x AS RECORD)", "CAST(x AS STRUCT)")
|
||||
self.validate_identity(
|
||||
"MERGE INTO dataset.NewArrivals USING (SELECT * FROM UNNEST([('microwave', 10, 'warehouse #1'), ('dryer', 30, 'warehouse #1'), ('oven', 20, 'warehouse #2')])) ON FALSE WHEN NOT MATCHED THEN INSERT ROW WHEN NOT MATCHED BY SOURCE THEN DELETE"
|
||||
self.validate_identity("EDIT_DISTANCE('a', 'a', max_distance => 2)").assert_is(
|
||||
exp.Levenshtein
|
||||
)
|
||||
self.validate_identity(
|
||||
"SELECT * FROM `SOME_PROJECT_ID.SOME_DATASET_ID.INFORMATION_SCHEMA.SOME_VIEW`"
|
||||
"MERGE INTO dataset.NewArrivals USING (SELECT * FROM UNNEST([('microwave', 10, 'warehouse #1'), ('dryer', 30, 'warehouse #1'), ('oven', 20, 'warehouse #2')])) ON FALSE WHEN NOT MATCHED THEN INSERT ROW WHEN NOT MATCHED BY SOURCE THEN DELETE"
|
||||
)
|
||||
self.validate_identity(
|
||||
"SELECT * FROM test QUALIFY a IS DISTINCT FROM b WINDOW c AS (PARTITION BY d)"
|
||||
|
|
@ -228,10 +236,23 @@ LANGUAGE js AS
|
|||
"SELECT LAST_VALUE(a IGNORE NULLS) OVER y FROM x WINDOW y AS (PARTITION BY CATEGORY)",
|
||||
)
|
||||
self.validate_identity(
|
||||
"""SELECT JSON_EXTRACT_SCALAR('5')""", """SELECT JSON_EXTRACT_SCALAR('5', '$')"""
|
||||
"CREATE OR REPLACE VIEW test (tenant_id OPTIONS (description='Test description on table creation')) AS SELECT 1 AS tenant_id, 1 AS customer_id",
|
||||
)
|
||||
self.validate_identity(
|
||||
"CREATE OR REPLACE VIEW test (tenant_id OPTIONS (description='Test description on table creation')) AS SELECT 1 AS tenant_id, 1 AS customer_id",
|
||||
"SELECT * FROM `proj.dataset.INFORMATION_SCHEMA.SOME_VIEW`",
|
||||
"SELECT * FROM `proj.dataset.INFORMATION_SCHEMA.SOME_VIEW` AS `proj.dataset.INFORMATION_SCHEMA.SOME_VIEW`",
|
||||
)
|
||||
self.validate_identity(
|
||||
"SELECT * FROM region_or_dataset.INFORMATION_SCHEMA.TABLES",
|
||||
"SELECT * FROM region_or_dataset.`INFORMATION_SCHEMA.TABLES` AS TABLES",
|
||||
)
|
||||
self.validate_identity(
|
||||
"SELECT * FROM region_or_dataset.INFORMATION_SCHEMA.TABLES AS some_name",
|
||||
"SELECT * FROM region_or_dataset.`INFORMATION_SCHEMA.TABLES` AS some_name",
|
||||
)
|
||||
self.validate_identity(
|
||||
"SELECT * FROM proj.region_or_dataset.INFORMATION_SCHEMA.TABLES",
|
||||
"SELECT * FROM proj.region_or_dataset.`INFORMATION_SCHEMA.TABLES` AS TABLES",
|
||||
)
|
||||
self.validate_identity(
|
||||
"CREATE VIEW `d.v` OPTIONS (expiration_timestamp=TIMESTAMP '2020-01-02T04:05:06.007Z') AS SELECT 1 AS c",
|
||||
|
|
@ -302,6 +323,13 @@ LANGUAGE js AS
|
|||
"SELECT CAST(1 AS INT64)",
|
||||
)
|
||||
|
||||
self.validate_all(
|
||||
"EDIT_DISTANCE(a, b)",
|
||||
write={
|
||||
"bigquery": "EDIT_DISTANCE(a, b)",
|
||||
"duckdb": "LEVENSHTEIN(a, b)",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"SAFE_CAST(some_date AS DATE FORMAT 'DD MONTH YYYY')",
|
||||
write={
|
||||
|
|
@ -361,9 +389,18 @@ LANGUAGE js AS
|
|||
write={
|
||||
"bigquery": "TIMESTAMP(x)",
|
||||
"duckdb": "CAST(x AS TIMESTAMPTZ)",
|
||||
"snowflake": "CAST(x AS TIMESTAMPTZ)",
|
||||
"presto": "CAST(x AS TIMESTAMP WITH TIME ZONE)",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"SELECT TIMESTAMP('2008-12-25 15:30:00', 'America/Los_Angeles')",
|
||||
write={
|
||||
"bigquery": "SELECT TIMESTAMP('2008-12-25 15:30:00', 'America/Los_Angeles')",
|
||||
"duckdb": "SELECT CAST('2008-12-25 15:30:00' AS TIMESTAMP) AT TIME ZONE 'America/Los_Angeles'",
|
||||
"snowflake": "SELECT CONVERT_TIMEZONE('America/Los_Angeles', CAST('2008-12-25 15:30:00' AS TIMESTAMP))",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"SELECT SUM(x IGNORE NULLS) AS x",
|
||||
read={
|
||||
|
|
@ -629,6 +666,7 @@ LANGUAGE js AS
|
|||
write={
|
||||
"bigquery": "SELECT DATETIME_DIFF('2023-01-01T00:00:00', '2023-01-01T05:00:00', MILLISECOND)",
|
||||
"databricks": "SELECT TIMESTAMPDIFF(MILLISECOND, '2023-01-01T05:00:00', '2023-01-01T00:00:00')",
|
||||
"snowflake": "SELECT TIMESTAMPDIFF(MILLISECOND, '2023-01-01T05:00:00', '2023-01-01T00:00:00')",
|
||||
},
|
||||
),
|
||||
)
|
||||
|
|
@ -639,6 +677,7 @@ LANGUAGE js AS
|
|||
"bigquery": "SELECT DATETIME_ADD('2023-01-01T00:00:00', INTERVAL '1' MILLISECOND)",
|
||||
"databricks": "SELECT TIMESTAMPADD(MILLISECOND, '1', '2023-01-01T00:00:00')",
|
||||
"duckdb": "SELECT CAST('2023-01-01T00:00:00' AS DATETIME) + INTERVAL '1' MILLISECOND",
|
||||
"snowflake": "SELECT TIMESTAMPADD(MILLISECOND, '1', '2023-01-01T00:00:00')",
|
||||
},
|
||||
),
|
||||
)
|
||||
|
|
@ -670,6 +709,7 @@ LANGUAGE js AS
|
|||
"databricks": "SELECT DATE_ADD(MINUTE, '10', CAST('2008-12-25 15:30:00+00' AS TIMESTAMP))",
|
||||
"mysql": "SELECT DATE_ADD(TIMESTAMP('2008-12-25 15:30:00+00'), INTERVAL '10' MINUTE)",
|
||||
"spark": "SELECT DATE_ADD(MINUTE, '10', CAST('2008-12-25 15:30:00+00' AS TIMESTAMP))",
|
||||
"snowflake": "SELECT TIMESTAMPADD(MINUTE, '10', CAST('2008-12-25 15:30:00+00' AS TIMESTAMPTZ))",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
|
|
@ -677,6 +717,14 @@ LANGUAGE js AS
|
|||
write={
|
||||
"bigquery": "SELECT TIMESTAMP_SUB(CAST('2008-12-25 15:30:00+00' AS TIMESTAMP), INTERVAL '10' MINUTE)",
|
||||
"mysql": "SELECT DATE_SUB(TIMESTAMP('2008-12-25 15:30:00+00'), INTERVAL '10' MINUTE)",
|
||||
"snowflake": "SELECT TIMESTAMPADD(MINUTE, '10' * -1, CAST('2008-12-25 15:30:00+00' AS TIMESTAMPTZ))",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
'SELECT TIMESTAMP_SUB(TIMESTAMP "2008-12-25 15:30:00+00", INTERVAL col MINUTE)',
|
||||
write={
|
||||
"bigquery": "SELECT TIMESTAMP_SUB(CAST('2008-12-25 15:30:00+00' AS TIMESTAMP), INTERVAL col MINUTE)",
|
||||
"snowflake": "SELECT TIMESTAMPADD(MINUTE, col * -1, CAST('2008-12-25 15:30:00+00' AS TIMESTAMPTZ))",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
|
|
@ -1113,7 +1161,8 @@ LANGUAGE js AS
|
|||
write={
|
||||
"bigquery": "CURRENT_TIME()",
|
||||
"duckdb": "CURRENT_TIME",
|
||||
"presto": "CURRENT_TIME()",
|
||||
"presto": "CURRENT_TIME",
|
||||
"trino": "CURRENT_TIME",
|
||||
"hive": "CURRENT_TIME()",
|
||||
"spark": "CURRENT_TIME()",
|
||||
},
|
||||
|
|
@ -1490,6 +1539,14 @@ WHERE
|
|||
"duckdb": "SELECT CAST(STRPTIME('Thursday Dec 25 2008', '%A %b %-d %Y') AS DATE)",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"SELECT PARSE_DATE('%Y%m%d', '20081225')",
|
||||
write={
|
||||
"bigquery": "SELECT PARSE_DATE('%Y%m%d', '20081225')",
|
||||
"duckdb": "SELECT CAST(STRPTIME('20081225', '%Y%m%d') AS DATE)",
|
||||
"snowflake": "SELECT DATE('20081225', 'yyyymmDD')",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"SELECT ARRAY_TO_STRING(['cake', 'pie', NULL], '--') AS text",
|
||||
write={
|
||||
|
|
@ -1504,9 +1561,48 @@ WHERE
|
|||
"duckdb": "SELECT ARRAY_TO_STRING(LIST_TRANSFORM(['cake', 'pie', NULL], x -> COALESCE(x, 'MISSING')), '--') AS text",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"STRING(a)",
|
||||
write={
|
||||
"bigquery": "STRING(a)",
|
||||
"snowflake": "CAST(a AS VARCHAR)",
|
||||
"duckdb": "CAST(a AS TEXT)",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"STRING('2008-12-25 15:30:00', 'America/New_York')",
|
||||
write={
|
||||
"bigquery": "STRING('2008-12-25 15:30:00', 'America/New_York')",
|
||||
"snowflake": "CAST(CONVERT_TIMEZONE('UTC', 'America/New_York', '2008-12-25 15:30:00') AS VARCHAR)",
|
||||
"duckdb": "CAST(CAST('2008-12-25 15:30:00' AS TIMESTAMP) AT TIME ZONE 'UTC' AT TIME ZONE 'America/New_York' AS TEXT)",
|
||||
},
|
||||
)
|
||||
|
||||
self.validate_identity("SELECT * FROM a-b c", "SELECT * FROM a-b AS c")
|
||||
|
||||
self.validate_all(
|
||||
"SAFE_DIVIDE(x, y)",
|
||||
write={
|
||||
"bigquery": "SAFE_DIVIDE(x, y)",
|
||||
"duckdb": "IF((y) <> 0, (x) / (y), NULL)",
|
||||
"presto": "IF((y) <> 0, (x) / (y), NULL)",
|
||||
"trino": "IF((y) <> 0, (x) / (y), NULL)",
|
||||
"hive": "IF((y) <> 0, (x) / (y), NULL)",
|
||||
"spark2": "IF((y) <> 0, (x) / (y), NULL)",
|
||||
"spark": "IF((y) <> 0, (x) / (y), NULL)",
|
||||
"databricks": "IF((y) <> 0, (x) / (y), NULL)",
|
||||
"snowflake": "IFF((y) <> 0, (x) / (y), NULL)",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"""SELECT JSON_QUERY('{"class": {"students": []}}', '$.class')""",
|
||||
write={
|
||||
"bigquery": """SELECT JSON_QUERY('{"class": {"students": []}}', '$.class')""",
|
||||
"duckdb": """SELECT '{"class": {"students": []}}' -> '$.class'""",
|
||||
"snowflake": """SELECT GET_PATH(PARSE_JSON('{"class": {"students": []}}'), 'class')""",
|
||||
},
|
||||
)
|
||||
|
||||
def test_errors(self):
|
||||
with self.assertRaises(TokenError):
|
||||
transpile("'\\'", read="bigquery")
|
||||
|
|
@ -2000,3 +2096,23 @@ OPTIONS (
|
|||
"bigquery": f"SELECT color, ARRAY_AGG(id ORDER BY id {sort_order}) AS ids FROM colors GROUP BY 1",
|
||||
},
|
||||
)
|
||||
|
||||
def test_json_extract_scalar(self):
|
||||
for func in ("JSON_EXTRACT_SCALAR", "JSON_VALUE"):
|
||||
with self.subTest(f"Testing BigQuery's {func}"):
|
||||
self.validate_all(
|
||||
f"SELECT {func}('5')",
|
||||
write={
|
||||
"bigquery": f"SELECT {func}('5', '$')",
|
||||
"duckdb": """SELECT '5' ->> '$'""",
|
||||
},
|
||||
)
|
||||
|
||||
self.validate_all(
|
||||
f"""SELECT {func}('{{"name": "Jakob", "age": "6"}}', '$.age')""",
|
||||
write={
|
||||
"bigquery": f"""SELECT {func}('{{"name": "Jakob", "age": "6"}}', '$.age')""",
|
||||
"duckdb": """SELECT '{"name": "Jakob", "age": "6"}' ->> '$.age'""",
|
||||
"snowflake": """SELECT JSON_EXTRACT_PATH_TEXT('{"name": "Jakob", "age": "6"}', 'age')""",
|
||||
},
|
||||
)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue