dbcli/sqlglot
1
0
Fork 0
Code Issues Activity

Merging upstream version 17.7.0.

Browse source 
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-02-13 20:46:55 +01:00
parent 87252470ef
commit 137902868c
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
93 changed files with 41580 additions and 39040 deletions
Download patch file Download diff file Expand all files Collapse all files

76
tests/dialects/test_spark.py
View file

@ -224,6 +224,9 @@ TBLPROPERTIES (
)
def test_spark(self):
self.validate_identity("SELECT TRANSFORM(ARRAY(1, 2, 3), x -> x + 1)")
self.validate_identity("SELECT TRANSFORM(ARRAY(1, 2, 3), (x, i) -> x + i)")
self.validate_identity("REFRESH table a.b.c")
self.validate_identity("INTERVAL -86 days")
self.validate_identity("SELECT UNIX_TIMESTAMP()")
self.validate_identity("TRIM(' SparkSQL ')")
@ -232,6 +235,61 @@ TBLPROPERTIES (
self.validate_identity("TRIM(TRAILING 'SL' FROM 'SSparkSQLS')")
self.validate_identity("SPLIT(str, pattern, lim)")
self.validate_all(
"SELECT DATEDIFF(month, CAST('1996-10-30' AS TIMESTAMP), CAST('1997-02-28 10:30:00' AS TIMESTAMP))",
read={
"duckdb": "SELECT DATEDIFF('month', CAST('1996-10-30' AS TIMESTAMP), CAST('1997-02-28 10:30:00' AS TIMESTAMP))",
},
write={
"spark": "SELECT DATEDIFF(month, TO_DATE(CAST('1996-10-30' AS TIMESTAMP)), TO_DATE(CAST('1997-02-28 10:30:00' AS TIMESTAMP)))",
"spark2": "SELECT MONTHS_BETWEEN(TO_DATE(CAST('1997-02-28 10:30:00' AS TIMESTAMP)), TO_DATE(CAST('1996-10-30' AS TIMESTAMP)))",
},
)
self.validate_all(
"SELECT MONTHS_BETWEEN('1997-02-28 10:30:00', '1996-10-30')",
write={
"duckdb": "SELECT DATEDIFF('month', CAST('1996-10-30' AS TIMESTAMP), CAST('1997-02-28 10:30:00' AS TIMESTAMP))",
"hive": "SELECT MONTHS_BETWEEN('1997-02-28 10:30:00', '1996-10-30')",
"spark": "SELECT MONTHS_BETWEEN('1997-02-28 10:30:00', '1996-10-30')",
},
)
self.validate_all(
"SELECT MONTHS_BETWEEN('1997-02-28 10:30:00', '1996-10-30', FALSE)",
write={
"duckdb": "SELECT DATEDIFF('month', CAST('1996-10-30' AS TIMESTAMP), CAST('1997-02-28 10:30:00' AS TIMESTAMP))",
"hive": "SELECT MONTHS_BETWEEN('1997-02-28 10:30:00', '1996-10-30')",
"spark": "SELECT MONTHS_BETWEEN('1997-02-28 10:30:00', '1996-10-30', FALSE)",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP('2016-12-31 00:12:00')",
write={
"": "SELECT CAST('2016-12-31 00:12:00' AS TIMESTAMP)",
"duckdb": "SELECT CAST('2016-12-31 00:12:00' AS TIMESTAMP)",
"spark": "SELECT CAST('2016-12-31 00:12:00' AS TIMESTAMP)",
},
)
self.validate_all(
"SELECT TO_TIMESTAMP('2016-12-31', 'yyyy-MM-dd')",
read={
"duckdb": "SELECT STRPTIME('2016-12-31', '%Y-%m-%d')",
},
write={
"": "SELECT STR_TO_TIME('2016-12-31', '%Y-%m-%d')",
"duckdb": "SELECT STRPTIME('2016-12-31', '%Y-%m-%d')",
"spark": "SELECT TO_TIMESTAMP('2016-12-31', 'yyyy-MM-dd')",
},
)
self.validate_all(
"SELECT RLIKE('John Doe', 'John.*')",
write={
"bigquery": "SELECT REGEXP_CONTAINS('John Doe', 'John.*')",
"hive": "SELECT 'John Doe' RLIKE 'John.*'",
"postgres": "SELECT 'John Doe' ~ 'John.*'",
"snowflake": "SELECT REGEXP_LIKE('John Doe', 'John.*')",
"spark": "SELECT 'John Doe' RLIKE 'John.*'",
},
)
self.validate_all(
"UNHEX(MD5(x))",
write={
@ -446,3 +504,21 @@ TBLPROPERTIES (
"CURRENT_USER()",
write={"spark": "CURRENT_USER()"},
)
def test_transform_query(self):
self.validate_identity("SELECT TRANSFORM(x) USING 'x' AS (x INT) FROM t")
self.validate_identity(
"SELECT TRANSFORM(zip_code, name, age) USING 'cat' AS (a, b, c) FROM person WHERE zip_code > 94511"
)
self.validate_identity(
"SELECT TRANSFORM(zip_code, name, age) USING 'cat' AS (a STRING, b STRING, c STRING) FROM person WHERE zip_code > 94511"
)
self.validate_identity(
"SELECT TRANSFORM(name, age) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' LINES TERMINATED BY '\n' NULL DEFINED AS 'NULL' USING 'cat' AS (name_age STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '@' LINES TERMINATED BY '\n' NULL DEFINED AS 'NULL' FROM person"
)
self.validate_identity(
"SELECT TRANSFORM(zip_code, name, age) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' WITH SERDEPROPERTIES ('field.delim'='\t') USING 'cat' AS (a STRING, b STRING, c STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' WITH SERDEPROPERTIES ('field.delim'='\t') FROM person WHERE zip_code > 94511"
)
self.validate_identity(
"SELECT TRANSFORM(zip_code, name, age) USING 'cat' FROM person WHERE zip_code > 94500"
)