Merging upstream version 25.30.0.
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
parent
4816f3663d
commit
ebf5336f85
GPG key ID:
FBB4F0E80A80222F
69 changed files with 48139 additions and 46098 deletions
|
|
@ -10,6 +10,7 @@ from sqlglot import (
|
|||
exp,
|
||||
parse,
|
||||
transpile,
|
||||
parse_one,
|
||||
)
|
||||
from sqlglot.helper import logger as helper_logger
|
||||
from sqlglot.parser import logger as parser_logger
|
||||
|
|
@ -21,8 +22,6 @@ class TestBigQuery(Validator):
|
|||
maxDiff = None
|
||||
|
||||
def test_bigquery(self):
|
||||
self.validate_identity("REGEXP_EXTRACT(x, '(?<)')")
|
||||
|
||||
self.validate_all(
|
||||
"EXTRACT(HOUR FROM DATETIME(2008, 12, 25, 15, 30, 00))",
|
||||
write={
|
||||
|
|
@ -182,7 +181,6 @@ LANGUAGE js AS
|
|||
self.validate_identity("""CREATE TABLE x (a STRUCT<values ARRAY<INT64>>)""")
|
||||
self.validate_identity("""CREATE TABLE x (a STRUCT<b STRING OPTIONS (description='b')>)""")
|
||||
self.validate_identity("CAST(x AS TIMESTAMP)")
|
||||
self.validate_identity("REGEXP_EXTRACT(`foo`, 'bar: (.+?)', 1, 1)")
|
||||
self.validate_identity("BEGIN DECLARE y INT64", check_command_warning=True)
|
||||
self.validate_identity("BEGIN TRANSACTION")
|
||||
self.validate_identity("COMMIT TRANSACTION")
|
||||
|
|
@ -202,9 +200,24 @@ 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("EDIT_DISTANCE('a', 'a', max_distance => 2)").assert_is(
|
||||
exp.Levenshtein
|
||||
self.validate_all(
|
||||
"EDIT_DISTANCE(col1, col2, max_distance => 3)",
|
||||
write={
|
||||
"bigquery": "EDIT_DISTANCE(col1, col2, max_distance => 3)",
|
||||
"clickhouse": UnsupportedError,
|
||||
"databricks": UnsupportedError,
|
||||
"drill": UnsupportedError,
|
||||
"duckdb": UnsupportedError,
|
||||
"hive": UnsupportedError,
|
||||
"postgres": "LEVENSHTEIN_LESS_EQUAL(col1, col2, 3)",
|
||||
"presto": UnsupportedError,
|
||||
"snowflake": "EDITDISTANCE(col1, col2, 3)",
|
||||
"spark": UnsupportedError,
|
||||
"spark2": UnsupportedError,
|
||||
"sqlite": UnsupportedError,
|
||||
},
|
||||
)
|
||||
|
||||
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"
|
||||
)
|
||||
|
|
@ -314,10 +327,6 @@ LANGUAGE js AS
|
|||
"SELECT * FROM (SELECT a, b, c FROM test) PIVOT(SUM(b) d, COUNT(*) e FOR c IN ('x', 'y'))",
|
||||
"SELECT * FROM (SELECT a, b, c FROM test) PIVOT(SUM(b) AS d, COUNT(*) AS e FOR c IN ('x', 'y'))",
|
||||
)
|
||||
self.validate_identity(
|
||||
r"REGEXP_EXTRACT(svc_plugin_output, r'\\\((.*)')",
|
||||
r"REGEXP_EXTRACT(svc_plugin_output, '\\\\\\((.*)')",
|
||||
)
|
||||
self.validate_identity(
|
||||
"SELECT CAST(1 AS BYTEINT)",
|
||||
"SELECT CAST(1 AS INT64)",
|
||||
|
|
@ -1378,14 +1387,6 @@ LANGUAGE js AS
|
|||
"postgres": "SELECT * FROM (VALUES (1)) AS t1(id) CROSS JOIN (VALUES (1)) AS t2(id)",
|
||||
},
|
||||
)
|
||||
|
||||
self.validate_all(
|
||||
"SELECT REGEXP_EXTRACT(abc, 'pattern(group)') FROM table",
|
||||
write={
|
||||
"bigquery": "SELECT REGEXP_EXTRACT(abc, 'pattern(group)') FROM table",
|
||||
"duckdb": '''SELECT REGEXP_EXTRACT(abc, 'pattern(group)', 1) FROM "table"''',
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"SELECT * FROM UNNEST([1]) WITH OFFSET",
|
||||
write={"bigquery": "SELECT * FROM UNNEST([1]) WITH OFFSET AS offset"},
|
||||
|
|
@ -1602,6 +1603,14 @@ WHERE
|
|||
"snowflake": """SELECT GET_PATH(PARSE_JSON('{"class": {"students": []}}'), 'class')""",
|
||||
},
|
||||
)
|
||||
self.validate_all(
|
||||
"""SELECT JSON_VALUE_ARRAY('{"arr": [1, "a"]}', '$.arr')""",
|
||||
write={
|
||||
"bigquery": """SELECT JSON_VALUE_ARRAY('{"arr": [1, "a"]}', '$.arr')""",
|
||||
"duckdb": """SELECT CAST('{"arr": [1, "a"]}' -> '$.arr' AS TEXT[])""",
|
||||
"snowflake": """SELECT TRANSFORM(GET_PATH(PARSE_JSON('{"arr": [1, "a"]}'), 'arr'), x -> CAST(x AS VARCHAR))""",
|
||||
},
|
||||
)
|
||||
|
||||
def test_errors(self):
|
||||
with self.assertRaises(TokenError):
|
||||
|
|
@ -2116,3 +2125,91 @@ OPTIONS (
|
|||
"snowflake": """SELECT JSON_EXTRACT_PATH_TEXT('{"name": "Jakob", "age": "6"}', 'age')""",
|
||||
},
|
||||
)
|
||||
|
||||
def test_json_extract_array(self):
|
||||
for func in ("JSON_QUERY_ARRAY", "JSON_EXTRACT_ARRAY"):
|
||||
with self.subTest(f"Testing BigQuery's {func}"):
|
||||
self.validate_all(
|
||||
f"""SELECT {func}('{{"fruits": [1, "oranges"]}}', '$.fruits')""",
|
||||
write={
|
||||
"bigquery": f"""SELECT {func}('{{"fruits": [1, "oranges"]}}', '$.fruits')""",
|
||||
"duckdb": """SELECT CAST('{"fruits": [1, "oranges"]}' -> '$.fruits' AS JSON[])""",
|
||||
"snowflake": """SELECT TRANSFORM(GET_PATH(PARSE_JSON('{"fruits": [1, "oranges"]}'), 'fruits'), x -> PARSE_JSON(TO_JSON(x)))""",
|
||||
},
|
||||
)
|
||||
|
||||
def test_unix_seconds(self):
|
||||
self.validate_all(
|
||||
"SELECT UNIX_SECONDS('2008-12-25 15:30:00+00')",
|
||||
read={
|
||||
"bigquery": "SELECT UNIX_SECONDS('2008-12-25 15:30:00+00')",
|
||||
"spark": "SELECT UNIX_SECONDS('2008-12-25 15:30:00+00')",
|
||||
"databricks": "SELECT UNIX_SECONDS('2008-12-25 15:30:00+00')",
|
||||
},
|
||||
write={
|
||||
"spark": "SELECT UNIX_SECONDS('2008-12-25 15:30:00+00')",
|
||||
"databricks": "SELECT UNIX_SECONDS('2008-12-25 15:30:00+00')",
|
||||
"duckdb": "SELECT DATE_DIFF('SECONDS', CAST('1970-01-01 00:00:00+00' AS TIMESTAMPTZ), '2008-12-25 15:30:00+00')",
|
||||
"snowflake": "SELECT TIMESTAMPDIFF(SECONDS, CAST('1970-01-01 00:00:00+00' AS TIMESTAMPTZ), '2008-12-25 15:30:00+00')",
|
||||
},
|
||||
)
|
||||
|
||||
for dialect in ("bigquery", "spark", "databricks"):
|
||||
parse_one("UNIX_SECONDS(col)", dialect=dialect).assert_is(exp.UnixSeconds)
|
||||
|
||||
def test_regexp_extract(self):
|
||||
self.validate_identity("REGEXP_EXTRACT(x, '(?<)')")
|
||||
self.validate_identity("REGEXP_EXTRACT(`foo`, 'bar: (.+?)', 1, 1)")
|
||||
self.validate_identity(
|
||||
r"REGEXP_EXTRACT(svc_plugin_output, r'\\\((.*)')",
|
||||
r"REGEXP_EXTRACT(svc_plugin_output, '\\\\\\((.*)')",
|
||||
)
|
||||
self.validate_identity(
|
||||
r"REGEXP_SUBSTR(value, pattern, position, occurence)",
|
||||
r"REGEXP_EXTRACT(value, pattern, position, occurence)",
|
||||
)
|
||||
|
||||
self.validate_all(
|
||||
"SELECT REGEXP_EXTRACT(abc, 'pattern(group)') FROM table",
|
||||
write={
|
||||
"bigquery": "SELECT REGEXP_EXTRACT(abc, 'pattern(group)') FROM table",
|
||||
"duckdb": '''SELECT REGEXP_EXTRACT(abc, 'pattern(group)', 1) FROM "table"''',
|
||||
},
|
||||
)
|
||||
|
||||
# The pattern does not capture a group (entire regular expression is extracted)
|
||||
self.validate_all(
|
||||
"REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
read={
|
||||
"bigquery": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"trino": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"presto": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"snowflake": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"duckdb": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]', 0)",
|
||||
"spark": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]', 0)",
|
||||
"databricks": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]', 0)",
|
||||
},
|
||||
write={
|
||||
"bigquery": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"trino": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"presto": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"snowflake": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]')",
|
||||
"duckdb": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]', 0)",
|
||||
"spark": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]', 0)",
|
||||
"databricks": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', 'a[0-9]', 0)",
|
||||
},
|
||||
)
|
||||
|
||||
# The pattern does capture >=1 group (the default is to extract the first instance)
|
||||
self.validate_all(
|
||||
"REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]')",
|
||||
write={
|
||||
"bigquery": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]')",
|
||||
"trino": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]', 1)",
|
||||
"presto": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]', 1)",
|
||||
"snowflake": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]', 1, 1, 'c', 1)",
|
||||
"duckdb": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]', 1)",
|
||||
"spark": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]')",
|
||||
"databricks": "REGEXP_EXTRACT_ALL('a1_a2a3_a4A5a6', '(a)[0-9]')",
|
||||
},
|
||||
)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue