dbcli/sqlglot
1
0
Fork 0
Code Issues Activity

Merging upstream version 26.2.1.

Browse source 
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-02-13 22:00:08 +01:00
parent a5399bd16b
commit 4d0635d636
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
85 changed files with 57142 additions and 52288 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/dialects/test_databricks.py
View file

@ -291,3 +291,15 @@ class TestDatabricks(Validator):
self.validate_identity("GRANT SELECT ON TABLE sample_data TO `alf@melmak.et`")
self.validate_identity("GRANT ALL PRIVILEGES ON TABLE forecasts TO finance")
self.validate_identity("GRANT SELECT ON TABLE t TO `fab9e00e-ca35-11ec-9d64-0242ac120002`")
def test_analyze(self):
self.validate_identity("ANALYZE TABLE tbl COMPUTE DELTA STATISTICS NOSCAN")
self.validate_identity("ANALYZE TABLE tbl COMPUTE DELTA STATISTICS FOR ALL COLUMNS")
self.validate_identity("ANALYZE TABLE tbl COMPUTE DELTA STATISTICS FOR COLUMNS foo, bar")
self.validate_identity("ANALYZE TABLE ctlg.db.tbl COMPUTE DELTA STATISTICS NOSCAN")
self.validate_identity("ANALYZE TABLES COMPUTE STATISTICS NOSCAN")
self.validate_identity("ANALYZE TABLES FROM db COMPUTE STATISTICS")
self.validate_identity("ANALYZE TABLES IN db COMPUTE STATISTICS")
self.validate_identity(
"ANALYZE TABLE ctlg.db.tbl PARTITION(foo = 'foo', bar = 'bar') COMPUTE STATISTICS NOSCAN"
)

22
tests/dialects/test_dialect.py
View file

@ -528,7 +528,7 @@ class TestDialect(Validator):
"sqlite": "SELECT (NOT x GLOB CAST(x'2a5b5e012d7f5d2a' AS TEXT))",
"mysql": "SELECT REGEXP_LIKE(x, '^[[:ascii:]]*$')",
"postgres": "SELECT (x ~ '^[[:ascii:]]*$')",
"tsql": "SELECT (PATINDEX('%[^' + CHAR(0x00) + '-' + CHAR(0x7f) + ']%' COLLATE Latin1_General_BIN, x) = 0)",
"tsql": "SELECT (PATINDEX(CONVERT(VARCHAR(MAX), 0x255b5e002d7f5d25) COLLATE Latin1_General_BIN, x) = 0)",
"oracle": "SELECT NVL(REGEXP_LIKE(x, '^[' || CHR(1) || '-' || CHR(127) || ']*$'), TRUE)",
},
)
@ -1686,7 +1686,7 @@ class TestDialect(Validator):
write={
"drill": "STRPOS(haystack, needle)",
"duckdb": "STRPOS(haystack, needle)",
"postgres": "POSITION(needle IN haystack)",
"postgres": "STRPOS(haystack, needle)",
"presto": "STRPOS(haystack, needle)",
"spark": "LOCATE(needle, haystack)",
"clickhouse": "position(haystack, needle)",
@ -1699,7 +1699,7 @@ class TestDialect(Validator):
write={
"drill": "STRPOS(haystack, needle)",
"duckdb": "STRPOS(haystack, needle)",
"postgres": "POSITION(needle IN haystack)",
"postgres": "STRPOS(haystack, needle)",
"presto": "STRPOS(haystack, needle)",
"bigquery": "STRPOS(haystack, needle)",
"spark": "LOCATE(needle, haystack)",
@ -1711,8 +1711,9 @@ class TestDialect(Validator):
self.validate_all(
"POSITION(needle, haystack, pos)",
write={
"drill": "STRPOS(SUBSTR(haystack, pos), needle) + pos - 1",
"presto": "STRPOS(SUBSTR(haystack, pos), needle) + pos - 1",
"drill": "`IF`(STRPOS(SUBSTR(haystack, pos), needle) = 0, 0, STRPOS(SUBSTR(haystack, pos), needle) + pos - 1)",
"presto": "IF(STRPOS(SUBSTR(haystack, pos), needle) = 0, 0, STRPOS(SUBSTR(haystack, pos), needle) + pos - 1)",
"postgres": "CASE WHEN STRPOS(SUBSTR(haystack, pos), needle) = 0 THEN 0 ELSE STRPOS(SUBSTR(haystack, pos), needle) + pos - 1 END",
"spark": "LOCATE(needle, haystack, pos)",
"clickhouse": "position(haystack, needle, pos)",
"snowflake": "POSITION(needle, haystack, pos)",
@ -2335,6 +2336,17 @@ SELECT
},
)
# needs to preserve the target alias in then WHEN condition and function but not in the THEN clause
self.validate_all(
"""MERGE INTO foo AS target USING (SELECT a, b FROM tbl) AS src ON src.a = target.a
WHEN MATCHED THEN UPDATE SET target.b = COALESCE(src.b, target.b)
WHEN NOT MATCHED THEN INSERT (target.a, target.b) VALUES (src.a, src.b)""",
write={
"trino": """MERGE INTO foo AS target USING (SELECT a, b FROM tbl) AS src ON src.a = target.a WHEN MATCHED THEN UPDATE SET b = COALESCE(src.b, target.b) WHEN NOT MATCHED THEN INSERT (a, b) VALUES (src.a, src.b)""",
"postgres": """MERGE INTO foo AS target USING (SELECT a, b FROM tbl) AS src ON src.a = target.a WHEN MATCHED THEN UPDATE SET b = COALESCE(src.b, target.b) WHEN NOT MATCHED THEN INSERT (a, b) VALUES (src.a, src.b)""",
},
)
def test_substring(self):
self.validate_all(
"SUBSTR('123456', 2, 3)",

5
tests/dialects/test_doris.py
View file

@ -100,3 +100,8 @@ class TestDoris(Validator):
"doris": "SELECT REGEXP(abc, '%foo%')",
},
)
def test_analyze(self):
self.validate_identity("ANALYZE TABLE tbl")
self.validate_identity("ANALYZE DATABASE db")
self.validate_identity("ANALYZE TABLE TBL(c1, c2)")

4
tests/dialects/test_drill.py
View file

@ -19,3 +19,7 @@ class TestDrill(Validator):
"mysql": "SELECT '2021-01-01' + INTERVAL '1' MONTH",
},
)
def test_analyze(self):
self.validate_identity("ANALYZE TABLE tbl COMPUTE STATISTICS")
self.validate_identity("ANALYZE TABLE tbl COMPUTE STATISTICS SAMPLE 5 PERCENT")

21
tests/dialects/test_druid.py Normal file
View file

@ -0,0 +1,21 @@
from sqlglot.dialects.dialect import Dialects
from tests.dialects.test_dialect import Validator
class TestDruid(Validator):
dialect = "druid"
def test_druid(self):
self.validate_identity("SELECT CEIL(__time TO WEEK) FROM t")
self.validate_identity("SELECT CEIL(col) FROM t")
self.validate_identity("SELECT CEIL(price, 2) AS rounded_price FROM t")
self.validate_identity("SELECT FLOOR(__time TO WEEK) FROM t")
self.validate_identity("SELECT FLOOR(col) FROM t")
self.validate_identity("SELECT FLOOR(price, 2) AS rounded_price FROM t")
# validate across all dialects
write = {dialect.value: "FLOOR(__time TO WEEK)" for dialect in Dialects}
self.validate_all(
"FLOOR(__time TO WEEK)",
write=write,
)

3
tests/dialects/test_duckdb.py
View file

@ -1448,3 +1448,6 @@ class TestDuckDB(Validator):
"WITH t1 AS (FROM (FROM t2 SELECT foo1, foo2)) FROM t1",
"WITH t1 AS (SELECT * FROM (SELECT foo1, foo2 FROM t2)) SELECT * FROM t1",
)
def test_analyze(self):
self.validate_identity("ANALYZE")

4
tests/dialects/test_hive.py
View file

@ -588,8 +588,8 @@ class TestHive(Validator):
self.validate_all(
"LOCATE('a', x, 3)",
write={
"duckdb": "STRPOS(SUBSTR(x, 3), 'a') + 3 - 1",
"presto": "STRPOS(SUBSTR(x, 3), 'a') + 3 - 1",
"duckdb": "CASE WHEN STRPOS(SUBSTR(x, 3), 'a') = 0 THEN 0 ELSE STRPOS(SUBSTR(x, 3), 'a') + 3 - 1 END",
"presto": "IF(STRPOS(SUBSTR(x, 3), 'a') = 0, 0, STRPOS(SUBSTR(x, 3), 'a') + 3 - 1)",
"hive": "LOCATE('a', x, 3)",
"spark": "LOCATE('a', x, 3)",
},

10
tests/dialects/test_mysql.py
View file

@ -1378,3 +1378,13 @@ COMMENT='客户账户表'"""
"mysql": "SELECT FORMAT(12332.2, 2, 'de_DE')",
},
)
def test_analyze(self):
self.validate_identity("ANALYZE LOCAL TABLE tbl")
self.validate_identity("ANALYZE NO_WRITE_TO_BINLOG TABLE tbl")
self.validate_identity("ANALYZE tbl UPDATE HISTOGRAM ON col1")
self.validate_identity("ANALYZE tbl UPDATE HISTOGRAM ON col1 USING DATA 'json_data'")
self.validate_identity("ANALYZE tbl UPDATE HISTOGRAM ON col1 WITH 5 BUCKETS")
self.validate_identity("ANALYZE tbl UPDATE HISTOGRAM ON col1 WITH 5 BUCKETS AUTO UPDATE")
self.validate_identity("ANALYZE tbl UPDATE HISTOGRAM ON col1 WITH 5 BUCKETS MANUAL UPDATE")
self.validate_identity("ANALYZE tbl DROP HISTOGRAM ON col1")

24
tests/dialects/test_oracle.py
View file

@ -654,3 +654,27 @@ WHERE
"'W'",
):
self.validate_identity(f"TRUNC(x, {unit})")
def test_analyze(self):
self.validate_identity("ANALYZE TABLE tbl")
self.validate_identity("ANALYZE INDEX ndx")
self.validate_identity("ANALYZE TABLE db.tbl PARTITION(foo = 'foo', bar = 'bar')")
self.validate_identity("ANALYZE TABLE db.tbl SUBPARTITION(foo = 'foo', bar = 'bar')")
self.validate_identity("ANALYZE INDEX db.ndx PARTITION(foo = 'foo', bar = 'bar')")
self.validate_identity("ANALYZE INDEX db.ndx PARTITION(part1)")
self.validate_identity("ANALYZE CLUSTER db.cluster")
self.validate_identity("ANALYZE TABLE tbl VALIDATE REF UPDATE")
self.validate_identity("ANALYZE LIST CHAINED ROWS")
self.validate_identity("ANALYZE LIST CHAINED ROWS INTO tbl")
self.validate_identity("ANALYZE DELETE STATISTICS")
self.validate_identity("ANALYZE DELETE SYSTEM STATISTICS")
self.validate_identity("ANALYZE VALIDATE REF UPDATE")
self.validate_identity("ANALYZE VALIDATE REF UPDATE SET DANGLING TO NULL")
self.validate_identity("ANALYZE VALIDATE STRUCTURE")
self.validate_identity("ANALYZE VALIDATE STRUCTURE CASCADE FAST")
self.validate_identity(
"ANALYZE TABLE tbl VALIDATE STRUCTURE CASCADE COMPLETE ONLINE INTO db.tbl"
)
self.validate_identity(
"ANALYZE TABLE tbl VALIDATE STRUCTURE CASCADE COMPLETE OFFLINE INTO db.tbl"
)

6
tests/dialects/test_postgres.py
View file

@ -1316,3 +1316,9 @@ CROSS JOIN JSON_ARRAY_ELEMENTS(CAST(JSON_EXTRACT_PATH(tbox, 'boxes') AS JSON)) A
self.validate_identity(
"SELECT XMLELEMENT(NAME foo, XMLATTRIBUTES('xyz' AS bar), XMLELEMENT(NAME abc), XMLCOMMENT('test'), XMLELEMENT(NAME xyz))"
)
def test_analyze(self):
self.validate_identity("ANALYZE TBL")
self.validate_identity("ANALYZE TBL(col1, col2)")
self.validate_identity("ANALYZE VERBOSE SKIP_LOCKED TBL(col1, col2)")
self.validate_identity("ANALYZE BUFFER_USAGE_LIMIT 1337 TBL")

4
tests/dialects/test_presto.py
View file

@ -1296,3 +1296,7 @@ MATCH_RECOGNIZE (
# If the setting is overriden to False, then generate ROW access (dot notation)
self.assertEqual(s.sql(dialect_row_access_setting), 'SELECT col.x.y."special string"')
def test_analyze(self):
self.validate_identity("ANALYZE tbl")
self.validate_identity("ANALYZE tbl WITH (prop1=val1, prop2=val2)")

6
tests/dialects/test_redshift.py
View file

@ -666,3 +666,9 @@ FROM (
self.validate_identity("GRANT USAGE ON DATABASE sales_db TO Bob")
self.validate_identity("GRANT USAGE ON SCHEMA sales_schema TO ROLE Analyst_role")
self.validate_identity("GRANT SELECT ON sales_db.sales_schema.tickit_sales_redshift TO Bob")
def test_analyze(self):
self.validate_identity("ANALYZE TBL(col1, col2)")
self.validate_identity("ANALYZE VERBOSE TBL")
self.validate_identity("ANALYZE TBL PREDICATE COLUMNS")
self.validate_identity("ANALYZE TBL ALL COLUMNS")

12
tests/dialects/test_snowflake.py
View file

@ -77,6 +77,7 @@ class TestSnowflake(Validator):
self.validate_identity("SELECT MATCH_CONDITION")
self.validate_identity("SELECT * REPLACE (CAST(col AS TEXT) AS scol) FROM t")
self.validate_identity("1 /* /* */")
self.validate_identity("TO_TIMESTAMP(col, fmt)")
self.validate_identity(
"SELECT * FROM table AT (TIMESTAMP => '2024-07-24') UNPIVOT(a FOR b IN (c)) AS pivot_table"
)
@ -104,7 +105,14 @@ class TestSnowflake(Validator):
self.validate_identity(
"SELECT * FROM DATA AS DATA_L ASOF JOIN DATA AS DATA_R MATCH_CONDITION (DATA_L.VAL > DATA_R.VAL) ON DATA_L.ID = DATA_R.ID"
)
self.validate_identity("TO_TIMESTAMP(col, fmt)")
self.validate_identity(
"WITH t (SELECT 1 AS c) SELECT c FROM t",
"WITH t AS (SELECT 1 AS c) SELECT c FROM t",
)
self.validate_identity(
"GET_PATH(json_data, '$id')",
"""GET_PATH(json_data, '["$id"]')""",
)
self.validate_identity(
"CAST(x AS GEOGRAPHY)",
"TO_GEOGRAPHY(x)",
@ -481,6 +489,7 @@ class TestSnowflake(Validator):
write={
"": "SELECT LOGICAL_OR(c1), LOGICAL_OR(c2) FROM test",
"duckdb": "SELECT BOOL_OR(c1), BOOL_OR(c2) FROM test",
"oracle": "SELECT MAX(c1), MAX(c2) FROM test",
"postgres": "SELECT BOOL_OR(c1), BOOL_OR(c2) FROM test",
"snowflake": "SELECT BOOLOR_AGG(c1), BOOLOR_AGG(c2) FROM test",
"spark": "SELECT BOOL_OR(c1), BOOL_OR(c2) FROM test",
@ -492,6 +501,7 @@ class TestSnowflake(Validator):
write={
"": "SELECT LOGICAL_AND(c1), LOGICAL_AND(c2) FROM test",
"duckdb": "SELECT BOOL_AND(c1), BOOL_AND(c2) FROM test",
"oracle": "SELECT MIN(c1), MIN(c2) FROM test",
"postgres": "SELECT BOOL_AND(c1), BOOL_AND(c2) FROM test",
"snowflake": "SELECT BOOLAND_AGG(c1), BOOLAND_AGG(c2) FROM test",
"spark": "SELECT BOOL_AND(c1), BOOL_AND(c2) FROM test",

20
tests/dialects/test_spark.py
View file

@ -263,6 +263,14 @@ TBLPROPERTIES (
self.validate_identity("TRIM(LEADING 'SL' FROM 'SSparkSQLS')")
self.validate_identity("TRIM(TRAILING 'SL' FROM 'SSparkSQLS')")
self.validate_identity("SPLIT(str, pattern, lim)")
self.validate_identity(
"SELECT 1 limit",
"SELECT 1 AS limit",
)
self.validate_identity(
"SELECT 1 offset",
"SELECT 1 AS offset",
)
self.validate_identity(
"SELECT UNIX_TIMESTAMP()",
"SELECT UNIX_TIMESTAMP(CURRENT_TIMESTAMP())",
@ -918,3 +926,15 @@ TBLPROPERTIES (
with self.subTest(f"Testing STRING() for {dialect}"):
query = parse_one("STRING(a)", dialect=dialect)
self.assertEqual(query.sql(dialect), "CAST(a AS STRING)")
def test_analyze(self):
self.validate_identity("ANALYZE TABLE tbl COMPUTE STATISTICS NOSCAN")
self.validate_identity("ANALYZE TABLE tbl COMPUTE STATISTICS FOR ALL COLUMNS")
self.validate_identity("ANALYZE TABLE tbl COMPUTE STATISTICS FOR COLUMNS foo, bar")
self.validate_identity("ANALYZE TABLE ctlg.db.tbl COMPUTE STATISTICS NOSCAN")
self.validate_identity("ANALYZE TABLES COMPUTE STATISTICS NOSCAN")
self.validate_identity("ANALYZE TABLES FROM db COMPUTE STATISTICS")
self.validate_identity("ANALYZE TABLES IN db COMPUTE STATISTICS")
self.validate_identity(
"ANALYZE TABLE ctlg.db.tbl PARTITION(foo = 'foo', bar = 'bar') COMPUTE STATISTICS NOSCAN"
)

4
tests/dialects/test_sqlite.py
View file

@ -237,3 +237,7 @@ class TestSQLite(Validator):
self.validate_identity(
"CREATE TABLE store (store_id INTEGER PRIMARY KEY AUTOINCREMENT, mgr_id INTEGER NOT NULL UNIQUE REFERENCES staff ON UPDATE CASCADE)"
)
def test_analyze(self):
self.validate_identity("ANALYZE tbl")
self.validate_identity("ANALYZE schma.tbl")

21
tests/dialects/test_starrocks.py
View file

@ -126,3 +126,24 @@ class TestStarrocks(Validator):
"spark": "SELECT id, t.col FROM tbl LATERAL VIEW EXPLODE(scores) t AS col",
},
)
def test_analyze(self):
self.validate_identity("ANALYZE TABLE TBL(c1, c2) PROPERTIES ('prop1'=val1)")
self.validate_identity("ANALYZE FULL TABLE TBL(c1, c2) PROPERTIES ('prop1'=val1)")
self.validate_identity("ANALYZE SAMPLE TABLE TBL(c1, c2) PROPERTIES ('prop1'=val1)")
self.validate_identity("ANALYZE TABLE TBL(c1, c2) WITH SYNC MODE PROPERTIES ('prop1'=val1)")
self.validate_identity(
"ANALYZE TABLE TBL(c1, c2) WITH ASYNC MODE PROPERTIES ('prop1'=val1)"
)
self.validate_identity(
"ANALYZE TABLE TBL UPDATE HISTOGRAM ON c1, c2 PROPERTIES ('prop1'=val1)"
)
self.validate_identity(
"ANALYZE TABLE TBL UPDATE HISTOGRAM ON c1, c2 WITH 5 BUCKETS PROPERTIES ('prop1'=val1)"
)
self.validate_identity(
"ANALYZE TABLE TBL UPDATE HISTOGRAM ON c1, c2 WITH SYNC MODE WITH 5 BUCKETS PROPERTIES ('prop1'=val1)"
)
self.validate_identity(
"ANALYZE TABLE TBL UPDATE HISTOGRAM ON c1, c2 WITH ASYNC MODE WITH 5 BUCKETS PROPERTIES ('prop1'=val1)"
)

4
tests/dialects/test_trino.py
View file

@ -78,3 +78,7 @@ class TestTrino(Validator):
self.validate_identity(
"ALTER VIEW people SET AUTHORIZATION alice", check_command_warning=True
)
def test_analyze(self):
self.validate_identity("ANALYZE tbl")
self.validate_identity("ANALYZE tbl WITH (prop1=val1, prop2=val2)")

4
tests/fixtures/identity.sql vendored
View file

@ -882,4 +882,6 @@ GRANT SELECT ON orders TO ROLE PUBLIC
GRANT SELECT ON nation TO alice WITH GRANT OPTION
GRANT DELETE ON SCHEMA finance TO bob
SELECT attach
SELECT detach
SELECT detach
SELECT 1 OFFSET 1
SELECT 1 LIMIT 1

4
tests/fixtures/optimizer/qualify_columns.sql vendored
View file

@ -277,6 +277,10 @@ SELECT x.a AS a FROM x AS x UNION SELECT x.a AS a FROM x AS x UNION SELECT x.a A
SELECT a FROM (SELECT a FROM x UNION SELECT a FROM x) ORDER BY a;
SELECT _q_0.a AS a FROM (SELECT x.a AS a FROM x AS x UNION SELECT x.a AS a FROM x AS x) AS _q_0 ORDER BY a;
# title: nested subqueries in union
((select a from x where a < 1)) UNION ((select a from x where a > 2));
((SELECT x.a AS a FROM x AS x WHERE x.a < 1)) UNION ((SELECT x.a AS a FROM x AS x WHERE x.a > 2));
--------------------------------------
-- Subqueries
--------------------------------------

16
tests/test_build.py
View file

@ -822,6 +822,22 @@ class TestBuild(unittest.TestCase):
lambda: exp.union("SELECT 1", "SELECT 2", "SELECT 3", "SELECT 4"),
"SELECT 1 UNION SELECT 2 UNION SELECT 3 UNION SELECT 4",
),
(
lambda: select("x")
.with_("var1", as_=select("x").from_("tbl2").subquery(), scalar=True)
.from_("tbl")
.where("x > var1"),
"WITH (SELECT x FROM tbl2) AS var1 SELECT x FROM tbl WHERE x > var1",
"clickhouse",
),
(
lambda: select("x")
.with_("var1", as_=select("x").from_("tbl2"), scalar=True)
.from_("tbl")
.where("x > var1"),
"WITH (SELECT x FROM tbl2) AS var1 SELECT x FROM tbl WHERE x > var1",
"clickhouse",
),
]:
with self.subTest(sql):
self.assertEqual(expression().sql(dialect[0] if dialect else None), sql)

1
tests/test_transpile.py
View file

@ -880,7 +880,6 @@ FROM tbl1""",
"ALTER TABLE table1 RENAME COLUMN c1 c2",
"ALTER TYPE electronic_mail RENAME TO email",
"ALTER schema doo",
"ANALYZE a.y",
"CALL catalog.system.iceberg_procedure_name(named_arg_1 => 'arg_1', named_arg_2 => 'arg_2')",
"COMMENT ON ACCESS METHOD gin IS 'GIN index access method'",
"CREATE OR REPLACE STAGE",