From 41f1f5740d2140bfd3b2a282ca1087a4b576679a Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Mon, 15 Apr 2024 07:02:18 +0200 Subject: Merging upstream version 23.10.0. Signed-off-by: Daniel Baumann --- tests/dialects/test_clickhouse.py | 3 ++ tests/dialects/test_databricks.py | 5 +++ tests/dialects/test_dialect.py | 11 ++++- tests/dialects/test_duckdb.py | 1 + tests/dialects/test_mysql.py | 2 +- tests/dialects/test_postgres.py | 7 +++ tests/dialects/test_presto.py | 10 +++++ tests/dialects/test_prql.py | 61 +++++++++++++++++++++++---- tests/dialects/test_snowflake.py | 41 ++++++++++-------- tests/dialects/test_spark.py | 36 +++++++++++++--- tests/dialects/test_teradata.py | 89 +++++++++++++++++++++++++++++++++++++++ 11 files changed, 231 insertions(+), 35 deletions(-) (limited to 'tests/dialects') diff --git a/tests/dialects/test_clickhouse.py b/tests/dialects/test_clickhouse.py index c5f9847..df3caaf 100644 --- a/tests/dialects/test_clickhouse.py +++ b/tests/dialects/test_clickhouse.py @@ -810,3 +810,6 @@ LIFETIME(MIN 0 MAX 0)""", }, pretty=True, ) + self.validate_identity( + "CREATE TABLE t1 (a String EPHEMERAL, b String EPHEMERAL func(), c String MATERIALIZED func(), d String ALIAS func()) ENGINE=TinyLog()" + ) diff --git a/tests/dialects/test_databricks.py b/tests/dialects/test_databricks.py index 94f2dc2..c15cf09 100644 --- a/tests/dialects/test_databricks.py +++ b/tests/dialects/test_databricks.py @@ -7,6 +7,8 @@ class TestDatabricks(Validator): dialect = "databricks" def test_databricks(self): + self.validate_identity("DESCRIBE HISTORY a.b") + self.validate_identity("DESCRIBE history.tbl") self.validate_identity("CREATE TABLE t (c STRUCT)") self.validate_identity("CREATE TABLE my_table TBLPROPERTIES (a.b=15)") self.validate_identity("CREATE TABLE my_table TBLPROPERTIES ('a.b'=15)") @@ -23,6 +25,9 @@ class TestDatabricks(Validator): self.validate_identity("CREATE FUNCTION a AS b") self.validate_identity("SELECT ${x} FROM ${y} WHERE ${z} > 1") self.validate_identity("CREATE TABLE foo (x DATE GENERATED ALWAYS AS (CAST(y AS DATE)))") + self.validate_identity( + "SELECT DATE_FORMAT(CAST(FROM_UTC_TIMESTAMP(CAST(foo AS TIMESTAMP), 'America/Los_Angeles') AS TIMESTAMP), 'yyyy-MM-dd HH:mm:ss') AS foo FROM t" + ) self.validate_identity( "SELECT * FROM sales UNPIVOT INCLUDE NULLS (sales FOR quarter IN (q1 AS `Jan-Mar`))" ) diff --git a/tests/dialects/test_dialect.py b/tests/dialects/test_dialect.py index 76ab94b..691beb9 100644 --- a/tests/dialects/test_dialect.py +++ b/tests/dialects/test_dialect.py @@ -1332,6 +1332,15 @@ class TestDialect(Validator): ) def test_set_operators(self): + self.validate_all( + "SELECT * FROM a UNION SELECT * FROM b ORDER BY x LIMIT 1", + write={ + "": "SELECT * FROM a UNION SELECT * FROM b ORDER BY x LIMIT 1", + "clickhouse": "SELECT * FROM (SELECT * FROM a UNION DISTINCT SELECT * FROM b) AS _l_0 ORDER BY x NULLS FIRST LIMIT 1", + "tsql": "SELECT TOP 1 * FROM (SELECT * FROM a UNION SELECT * FROM b) AS _l_0 ORDER BY x", + }, + ) + self.validate_all( "SELECT * FROM a UNION SELECT * FROM b", read={ @@ -1667,7 +1676,7 @@ class TestDialect(Validator): "presto": "CAST(a AS DOUBLE) / b", "redshift": "CAST(a AS DOUBLE PRECISION) / b", "sqlite": "CAST(a AS REAL) / b", - "teradata": "CAST(a AS DOUBLE) / b", + "teradata": "CAST(a AS DOUBLE PRECISION) / b", "trino": "CAST(a AS DOUBLE) / b", "tsql": "CAST(a AS FLOAT) / b", }, diff --git a/tests/dialects/test_duckdb.py b/tests/dialects/test_duckdb.py index 5a7e93e..0b13a70 100644 --- a/tests/dialects/test_duckdb.py +++ b/tests/dialects/test_duckdb.py @@ -240,6 +240,7 @@ class TestDuckDB(Validator): self.validate_identity("SELECT MAP(['key1', 'key2', 'key3'], [10, 20, 30])") self.validate_identity("SELECT MAP {'x': 1}") + self.validate_identity("SELECT (MAP {'x': 1})['x']") self.validate_identity("SELECT df1.*, df2.* FROM df1 POSITIONAL JOIN df2") self.validate_identity("MAKE_TIMESTAMP(1992, 9, 20, 13, 34, 27.123456)") self.validate_identity("MAKE_TIMESTAMP(1667810584123456)") diff --git a/tests/dialects/test_mysql.py b/tests/dialects/test_mysql.py index 7a9d6bf..6558c97 100644 --- a/tests/dialects/test_mysql.py +++ b/tests/dialects/test_mysql.py @@ -1103,7 +1103,7 @@ COMMENT='客户账户表'""" "presto": "CAST(a AS DOUBLE) / NULLIF(b, 0)", "redshift": "CAST(a AS DOUBLE PRECISION) / NULLIF(b, 0)", "sqlite": "CAST(a AS REAL) / b", - "teradata": "CAST(a AS DOUBLE) / NULLIF(b, 0)", + "teradata": "CAST(a AS DOUBLE PRECISION) / NULLIF(b, 0)", "trino": "CAST(a AS DOUBLE) / NULLIF(b, 0)", "tsql": "CAST(a AS FLOAT) / NULLIF(b, 0)", }, diff --git a/tests/dialects/test_postgres.py b/tests/dialects/test_postgres.py index 7a41cef..5a55a7d 100644 --- a/tests/dialects/test_postgres.py +++ b/tests/dialects/test_postgres.py @@ -50,6 +50,7 @@ class TestPostgres(Validator): self.validate_identity("STRING_AGG(DISTINCT x, ',' ORDER BY y DESC)") self.validate_identity("SELECT CASE WHEN SUBSTRING('abcdefg') IN ('ab') THEN 1 ELSE 0 END") self.validate_identity("COMMENT ON TABLE mytable IS 'this'") + self.validate_identity("COMMENT ON MATERIALIZED VIEW my_view IS 'this'") self.validate_identity("SELECT e'\\xDEADBEEF'") self.validate_identity("SELECT CAST(e'\\176' AS BYTEA)") self.validate_identity("SELECT * FROM x WHERE SUBSTRING('Thomas' FROM '...$') IN ('mas')") @@ -466,6 +467,12 @@ class TestPostgres(Validator): "tsql": "SELECT (CAST('2016-01-10' AS DATE), CAST('2016-02-01' AS DATE)) OVERLAPS (CAST('2016-01-20' AS DATE), CAST('2016-02-10' AS DATE))", }, ) + self.validate_all( + "SELECT DATE_PART('epoch', CAST('2023-01-04 04:05:06.789' AS TIMESTAMP))", + read={ + "": "SELECT TIME_TO_UNIX(TIMESTAMP '2023-01-04 04:05:06.789')", + }, + ) self.validate_all( "x ^ y", write={ diff --git a/tests/dialects/test_presto.py b/tests/dialects/test_presto.py index 2162499..e1d8c06 100644 --- a/tests/dialects/test_presto.py +++ b/tests/dialects/test_presto.py @@ -7,6 +7,7 @@ class TestPresto(Validator): dialect = "presto" def test_cast(self): + self.validate_identity("SELECT * FROM x qualify", "SELECT * FROM x AS qualify") self.validate_identity("CAST(x AS IPADDRESS)") self.validate_identity("CAST(x AS IPPREFIX)") @@ -611,6 +612,15 @@ class TestPresto(Validator): self.validate_identity( "SELECT * FROM example.testdb.customer_orders FOR TIMESTAMP AS OF CAST('2022-03-23 09:59:29.803 Europe/Vienna' AS TIMESTAMP)" ) + self.validate_identity( + "SELECT origin_state, destination_state, origin_zip, SUM(package_weight) FROM shipping GROUP BY ALL CUBE (origin_state, destination_state), ROLLUP (origin_state, origin_zip)" + ) + self.validate_identity( + "SELECT origin_state, destination_state, origin_zip, SUM(package_weight) FROM shipping GROUP BY DISTINCT CUBE (origin_state, destination_state), ROLLUP (origin_state, origin_zip)" + ) + self.validate_identity( + "SELECT JSON_EXTRACT_SCALAR(CAST(extra AS JSON), '$.value_b'), COUNT(*) FROM table_a GROUP BY DISTINCT (JSON_EXTRACT_SCALAR(CAST(extra AS JSON), '$.value_b'))" + ) self.validate_all( "SELECT LAST_DAY_OF_MONTH(CAST('2008-11-25' AS DATE))", diff --git a/tests/dialects/test_prql.py b/tests/dialects/test_prql.py index 9a42d0c..69e2e28 100644 --- a/tests/dialects/test_prql.py +++ b/tests/dialects/test_prql.py @@ -5,13 +5,56 @@ class TestPRQL(Validator): dialect = "prql" def test_prql(self): - self.validate_identity("FROM x", "SELECT * FROM x") - self.validate_identity("FROM x DERIVE a + 1", "SELECT *, a + 1 FROM x") - self.validate_identity("FROM x DERIVE x = a + 1", "SELECT *, a + 1 AS x FROM x") - self.validate_identity("FROM x DERIVE {a + 1}", "SELECT *, a + 1 FROM x") - self.validate_identity("FROM x DERIVE {x = a + 1, b}", "SELECT *, a + 1 AS x, b FROM x") - self.validate_identity("FROM x TAKE 10", "SELECT * FROM x LIMIT 10") - self.validate_identity("FROM x TAKE 10 TAKE 5", "SELECT * FROM x LIMIT 5") - self.validate_identity( - "FROM x DERIVE {x = a + 1, b} SELECT {y = x, 2}", "SELECT a + 1 AS y, 2 FROM x" + self.validate_identity("from x", "SELECT * FROM x") + self.validate_identity("from x derive a + 1", "SELECT *, a + 1 FROM x") + self.validate_identity("from x derive x = a + 1", "SELECT *, a + 1 AS x FROM x") + self.validate_identity("from x derive {a + 1}", "SELECT *, a + 1 FROM x") + self.validate_identity("from x derive {x = a + 1, b}", "SELECT *, a + 1 AS x, b FROM x") + self.validate_identity( + "from x derive {x = a + 1, b} select {y = x, 2}", "SELECT a + 1 AS y, 2 FROM x" + ) + self.validate_identity("from x take 10", "SELECT * FROM x LIMIT 10") + self.validate_identity("from x take 10 take 5", "SELECT * FROM x LIMIT 5") + self.validate_identity("from x filter age > 25", "SELECT * FROM x WHERE age > 25") + self.validate_identity( + "from x derive {x = a + 1, b} filter age > 25", + "SELECT *, a + 1 AS x, b FROM x WHERE age > 25", + ) + self.validate_identity("from x filter dept != 'IT'", "SELECT * FROM x WHERE dept <> 'IT'") + self.validate_identity( + "from x filter p == 'product' select { a, b }", "SELECT a, b FROM x WHERE p = 'product'" + ) + self.validate_identity( + "from x filter age > 25 filter age < 27", "SELECT * FROM x WHERE age > 25 AND age < 27" + ) + self.validate_identity( + "from x filter (age > 25 && age < 27)", "SELECT * FROM x WHERE (age > 25 AND age < 27)" + ) + self.validate_identity( + "from x filter (age > 25 || age < 27)", "SELECT * FROM x WHERE (age > 25 OR age < 27)" + ) + self.validate_identity( + "from x filter (age > 25 || age < 22) filter age > 26 filter age < 27", + "SELECT * FROM x WHERE ((age > 25 OR age < 22) AND age > 26) AND age < 27", + ) + self.validate_identity( + "from x sort age", + "SELECT * FROM x ORDER BY age", + ) + self.validate_identity( + "from x sort {-age}", + "SELECT * FROM x ORDER BY age DESC", + ) + self.validate_identity( + "from x sort {age, name}", + "SELECT * FROM x ORDER BY age, name", + ) + self.validate_identity( + "from x sort {-age, +name}", + "SELECT * FROM x ORDER BY age DESC, name", + ) + self.validate_identity("from x append y", "SELECT * FROM x UNION ALL SELECT * FROM y") + self.validate_identity("from x remove y", "SELECT * FROM x EXCEPT ALL SELECT * FROM y") + self.validate_identity( + "from x intersect y", "SELECT * FROM x INTERSECT ALL SELECT * FROM y" ) diff --git a/tests/dialects/test_snowflake.py b/tests/dialects/test_snowflake.py index a41d35a..b652541 100644 --- a/tests/dialects/test_snowflake.py +++ b/tests/dialects/test_snowflake.py @@ -66,6 +66,7 @@ WHERE self.validate_identity("SELECT DAYOFYEAR(CURRENT_TIMESTAMP())") self.validate_identity("LISTAGG(data['some_field'], ',')") self.validate_identity("WEEKOFYEAR(tstamp)") + self.validate_identity("SELECT QUARTER(CURRENT_TIMESTAMP())") self.validate_identity("SELECT SUM(amount) FROM mytable GROUP BY ALL") self.validate_identity("WITH x AS (SELECT 1 AS foo) SELECT foo FROM IDENTIFIER('x')") self.validate_identity("WITH x AS (SELECT 1 AS foo) SELECT IDENTIFIER('foo') FROM x") @@ -1575,22 +1576,26 @@ FROM persons AS p, LATERAL FLATTEN(input => p.c, path => 'contact') AS _flattene ) def test_match_recognize(self): - for row in ( - "ONE ROW PER MATCH", - "ALL ROWS PER MATCH", - "ALL ROWS PER MATCH SHOW EMPTY MATCHES", - "ALL ROWS PER MATCH OMIT EMPTY MATCHES", - "ALL ROWS PER MATCH WITH UNMATCHED ROWS", - ): - for after in ( - "AFTER MATCH SKIP", - "AFTER MATCH SKIP PAST LAST ROW", - "AFTER MATCH SKIP TO NEXT ROW", - "AFTER MATCH SKIP TO FIRST x", - "AFTER MATCH SKIP TO LAST x", + for window_frame in ("", "FINAL ", "RUNNING "): + for row in ( + "ONE ROW PER MATCH", + "ALL ROWS PER MATCH", + "ALL ROWS PER MATCH SHOW EMPTY MATCHES", + "ALL ROWS PER MATCH OMIT EMPTY MATCHES", + "ALL ROWS PER MATCH WITH UNMATCHED ROWS", ): - self.validate_identity( - f"""SELECT + for after in ( + "AFTER MATCH SKIP", + "AFTER MATCH SKIP PAST LAST ROW", + "AFTER MATCH SKIP TO NEXT ROW", + "AFTER MATCH SKIP TO FIRST x", + "AFTER MATCH SKIP TO LAST x", + ): + with self.subTest( + f"MATCH_RECOGNIZE with window frame {window_frame}, rows {row}, after {after}: " + ): + self.validate_identity( + f"""SELECT * FROM x MATCH_RECOGNIZE ( @@ -1598,15 +1603,15 @@ MATCH_RECOGNIZE ( ORDER BY x DESC MEASURES - y AS b + {window_frame}y AS b {row} {after} PATTERN (^ S1 S2*? ( {{- S3 -}} S4 )+ | PERMUTE(S1, S2){{1,2}} $) DEFINE x AS y )""", - pretty=True, - ) + pretty=True, + ) def test_show_users(self): self.validate_identity("SHOW USERS") diff --git a/tests/dialects/test_spark.py b/tests/dialects/test_spark.py index 18f1fb7..d2285e0 100644 --- a/tests/dialects/test_spark.py +++ b/tests/dialects/test_spark.py @@ -2,6 +2,7 @@ from unittest import mock from sqlglot import exp, parse_one from sqlglot.dialects.dialect import Dialects +from sqlglot.helper import logger as helper_logger from tests.dialects.test_dialect import Validator @@ -223,17 +224,16 @@ TBLPROPERTIES ( ) def test_spark(self): - self.validate_identity("any_value(col, true)", "ANY_VALUE(col) IGNORE NULLS") - self.validate_identity("first(col, true)", "FIRST(col) IGNORE NULLS") - self.validate_identity("first_value(col, true)", "FIRST_VALUE(col) IGNORE NULLS") - self.validate_identity("last(col, true)", "LAST(col) IGNORE NULLS") - self.validate_identity("last_value(col, true)", "LAST_VALUE(col) IGNORE NULLS") - self.assertEqual( parse_one("REFRESH TABLE t", read="spark").assert_is(exp.Refresh).sql(dialect="spark"), "REFRESH TABLE t", ) + self.validate_identity("any_value(col, true)", "ANY_VALUE(col) IGNORE NULLS") + self.validate_identity("first(col, true)", "FIRST(col) IGNORE NULLS") + self.validate_identity("first_value(col, true)", "FIRST_VALUE(col) IGNORE NULLS") + self.validate_identity("last(col, true)", "LAST(col) IGNORE NULLS") + self.validate_identity("last_value(col, true)", "LAST_VALUE(col) IGNORE NULLS") self.validate_identity("DESCRIBE EXTENDED db.table") self.validate_identity("SELECT * FROM test TABLESAMPLE (50 PERCENT)") self.validate_identity("SELECT * FROM test TABLESAMPLE (5 ROWS)") @@ -284,6 +284,30 @@ TBLPROPERTIES ( "SELECT STR_TO_MAP('a:1,b:2,c:3', ',', ':')", ) + with self.assertLogs(helper_logger): + self.validate_all( + "SELECT TRY_ELEMENT_AT(ARRAY(1, 2, 3), 2)", + read={ + "databricks": "SELECT TRY_ELEMENT_AT(ARRAY(1, 2, 3), 2)", + }, + write={ + "databricks": "SELECT TRY_ELEMENT_AT(ARRAY(1, 2, 3), 2)", + "duckdb": "SELECT ([1, 2, 3])[3]", + "spark": "SELECT TRY_ELEMENT_AT(ARRAY(1, 2, 3), 2)", + }, + ) + + self.validate_all( + "SELECT TRY_ELEMENT_AT(MAP(1, 'a', 2, 'b'), 2)", + read={ + "databricks": "SELECT TRY_ELEMENT_AT(MAP(1, 'a', 2, 'b'), 2)", + }, + write={ + "databricks": "SELECT TRY_ELEMENT_AT(MAP(1, 'a', 2, 'b'), 2)", + "duckdb": "SELECT (MAP([1, 2], ['a', 'b'])[2])[1]", + "spark": "SELECT TRY_ELEMENT_AT(MAP(1, 'a', 2, 'b'), 2)", + }, + ) self.validate_all( "SELECT SPLIT('123|789', '\\\\|')", read={ diff --git a/tests/dialects/test_teradata.py b/tests/dialects/test_teradata.py index a85ca8c..010b683 100644 --- a/tests/dialects/test_teradata.py +++ b/tests/dialects/test_teradata.py @@ -210,3 +210,92 @@ class TestTeradata(Validator): "teradata": "TRYCAST('-2.5' AS DECIMAL(5, 2))", }, ) + + def test_time(self): + self.validate_all( + "CURRENT_TIMESTAMP", + read={ + "teradata": "CURRENT_TIMESTAMP", + "snowflake": "CURRENT_TIMESTAMP()", + }, + ) + + self.validate_all( + "SELECT '2023-01-01' + INTERVAL '5' YEAR", + read={ + "teradata": "SELECT '2023-01-01' + INTERVAL '5' YEAR", + "snowflake": "SELECT DATEADD(YEAR, 5, '2023-01-01')", + }, + ) + self.validate_all( + "SELECT '2023-01-01' - INTERVAL '5' YEAR", + read={ + "teradata": "SELECT '2023-01-01' - INTERVAL '5' YEAR", + "snowflake": "SELECT DATEADD(YEAR, -5, '2023-01-01')", + }, + ) + self.validate_all( + "SELECT '2023-01-01' - INTERVAL '5' YEAR", + read={ + "teradata": "SELECT '2023-01-01' - INTERVAL '5' YEAR", + "sqlite": "SELECT DATE_SUB('2023-01-01', 5, YEAR)", + }, + ) + self.validate_all( + "SELECT '2023-01-01' + INTERVAL '5' YEAR", + read={ + "teradata": "SELECT '2023-01-01' + INTERVAL '5' YEAR", + "sqlite": "SELECT DATE_SUB('2023-01-01', -5, YEAR)", + }, + ) + self.validate_all( + "SELECT (90 * INTERVAL '1' DAY)", + read={ + "teradata": "SELECT (90 * INTERVAL '1' DAY)", + "snowflake": "SELECT INTERVAL '1' QUARTER", + }, + ) + self.validate_all( + "SELECT (7 * INTERVAL '1' DAY)", + read={ + "teradata": "SELECT (7 * INTERVAL '1' DAY)", + "snowflake": "SELECT INTERVAL '1' WEEK", + }, + ) + self.validate_all( + "SELECT '2023-01-01' + (90 * INTERVAL '5' DAY)", + read={ + "teradata": "SELECT '2023-01-01' + (90 * INTERVAL '5' DAY)", + "snowflake": "SELECT DATEADD(QUARTER, 5, '2023-01-01')", + }, + ) + self.validate_all( + "SELECT '2023-01-01' + (7 * INTERVAL '5' DAY)", + read={ + "teradata": "SELECT '2023-01-01' + (7 * INTERVAL '5' DAY)", + "snowflake": "SELECT DATEADD(WEEK, 5, '2023-01-01')", + }, + ) + self.validate_all( + "CAST(TO_CHAR(x, 'Q') AS INT)", + read={ + "teradata": "CAST(TO_CHAR(x, 'Q') AS INT)", + "snowflake": "DATE_PART(QUARTER, x)", + "bigquery": "EXTRACT(QUARTER FROM x)", + }, + ) + self.validate_all( + "EXTRACT(MONTH FROM x)", + read={ + "teradata": "EXTRACT(MONTH FROM x)", + "snowflake": "DATE_PART(MONTH, x)", + "bigquery": "EXTRACT(MONTH FROM x)", + }, + ) + self.validate_all( + "CAST(TO_CHAR(x, 'Q') AS INT)", + read={ + "snowflake": "quarter(x)", + "teradata": "CAST(TO_CHAR(x, 'Q') AS INT)", + }, + ) -- cgit v1.2.3