diff options
Diffstat (limited to 'tests')
-rw-r--r-- | tests/dialects/test_athena.py | 60 | ||||
-rw-r--r-- | tests/dialects/test_bigquery.py | 27 | ||||
-rw-r--r-- | tests/dialects/test_clickhouse.py | 20 | ||||
-rw-r--r-- | tests/dialects/test_databricks.py | 6 | ||||
-rw-r--r-- | tests/dialects/test_dialect.py | 4 | ||||
-rw-r--r-- | tests/dialects/test_duckdb.py | 31 | ||||
-rw-r--r-- | tests/dialects/test_mysql.py | 15 | ||||
-rw-r--r-- | tests/dialects/test_oracle.py | 18 | ||||
-rw-r--r-- | tests/dialects/test_postgres.py | 5 | ||||
-rw-r--r-- | tests/dialects/test_presto.py | 21 | ||||
-rw-r--r-- | tests/dialects/test_redshift.py | 33 | ||||
-rw-r--r-- | tests/dialects/test_snowflake.py | 19 | ||||
-rw-r--r-- | tests/dialects/test_starrocks.py | 6 | ||||
-rw-r--r-- | tests/dialects/test_tsql.py | 7 | ||||
-rw-r--r-- | tests/fixtures/identity.sql | 7 | ||||
-rw-r--r-- | tests/fixtures/optimizer/simplify.sql | 3 | ||||
-rw-r--r-- | tests/fixtures/optimizer/tpc-ds/tpc-ds.sql | 68 | ||||
-rw-r--r-- | tests/test_build.py | 10 | ||||
-rw-r--r-- | tests/test_diff.py | 58 | ||||
-rw-r--r-- | tests/test_expressions.py | 2 | ||||
-rw-r--r-- | tests/test_transpile.py | 1 |
21 files changed, 341 insertions, 80 deletions
diff --git a/tests/dialects/test_athena.py b/tests/dialects/test_athena.py index bf54914..ca91d4a 100644 --- a/tests/dialects/test_athena.py +++ b/tests/dialects/test_athena.py @@ -1,3 +1,4 @@ +from sqlglot import exp from tests.dialects.test_dialect import Validator @@ -68,6 +69,23 @@ class TestAthena(Validator): "CREATE TABLE foo AS WITH foo AS (SELECT a, b FROM bar) SELECT * FROM foo" ) + # ALTER TABLE ADD COLUMN not supported, it needs to be generated as ALTER TABLE ADD COLUMNS + self.validate_identity( + "ALTER TABLE `foo`.`bar` ADD COLUMN `end_ts` BIGINT", + write_sql="ALTER TABLE `foo`.`bar` ADD COLUMNS (`end_ts` BIGINT)", + ) + + def test_dml(self): + self.validate_all( + "SELECT CAST(ds AS VARCHAR) AS ds FROM (VALUES ('2022-01-01')) AS t(ds)", + read={"": "SELECT CAST(ds AS STRING) AS ds FROM (VALUES ('2022-01-01')) AS t(ds)"}, + write={ + "hive": "SELECT CAST(ds AS STRING) AS ds FROM (VALUES ('2022-01-01')) AS t(ds)", + "trino": "SELECT CAST(ds AS VARCHAR) AS ds FROM (VALUES ('2022-01-01')) AS t(ds)", + "athena": "SELECT CAST(ds AS VARCHAR) AS ds FROM (VALUES ('2022-01-01')) AS t(ds)", + }, + ) + def test_ddl_quoting(self): self.validate_identity("CREATE SCHEMA `foo`") self.validate_identity("CREATE SCHEMA foo") @@ -111,6 +129,10 @@ class TestAthena(Validator): 'CREATE VIEW `foo` AS SELECT "id" FROM `tbl`', write_sql='CREATE VIEW "foo" AS SELECT "id" FROM "tbl"', ) + self.validate_identity( + "DROP VIEW IF EXISTS `foo`.`bar`", + write_sql='DROP VIEW IF EXISTS "foo"."bar"', + ) self.validate_identity( 'ALTER TABLE "foo" ADD COLUMNS ("id" STRING)', @@ -128,6 +150,8 @@ class TestAthena(Validator): write_sql='CREATE TABLE "foo" AS WITH "foo" AS (SELECT "a", "b" FROM "bar") SELECT * FROM "foo"', ) + self.validate_identity("DESCRIBE foo.bar", write_sql="DESCRIBE `foo`.`bar`", identify=True) + def test_dml_quoting(self): self.validate_identity("SELECT a AS foo FROM tbl") self.validate_identity('SELECT "a" AS "foo" FROM "tbl"') @@ -167,3 +191,39 @@ class TestAthena(Validator): write_sql='WITH "foo" AS (SELECT "a", "b" FROM "bar") SELECT * FROM "foo"', identify=True, ) + + def test_ctas(self): + # Hive tables use 'external_location' to specify the table location, Iceberg tables use 'location' to specify the table location + # The 'table_type' property is used to determine if it's a Hive or an Iceberg table + # ref: https://docs.aws.amazon.com/athena/latest/ug/create-table-as.html#ctas-table-properties + ctas_hive = exp.Create( + this=exp.to_table("foo.bar"), + kind="TABLE", + properties=exp.Properties( + expressions=[ + exp.FileFormatProperty(this=exp.Literal.string("parquet")), + exp.LocationProperty(this=exp.Literal.string("s3://foo")), + ] + ), + expression=exp.select("1"), + ) + self.assertEqual( + ctas_hive.sql(dialect=self.dialect, identify=True), + "CREATE TABLE \"foo\".\"bar\" WITH (format='parquet', external_location='s3://foo') AS SELECT 1", + ) + + ctas_iceberg = exp.Create( + this=exp.to_table("foo.bar"), + kind="TABLE", + properties=exp.Properties( + expressions=[ + exp.Property(this=exp.var("table_type"), value=exp.Literal.string("iceberg")), + exp.LocationProperty(this=exp.Literal.string("s3://foo")), + ] + ), + expression=exp.select("1"), + ) + self.assertEqual( + ctas_iceberg.sql(dialect=self.dialect, identify=True), + "CREATE TABLE \"foo\".\"bar\" WITH (table_type='iceberg', location='s3://foo') AS SELECT 1", + ) diff --git a/tests/dialects/test_bigquery.py b/tests/dialects/test_bigquery.py index b883896..e2adfea 100644 --- a/tests/dialects/test_bigquery.py +++ b/tests/dialects/test_bigquery.py @@ -22,6 +22,8 @@ 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={ @@ -1502,6 +1504,8 @@ WHERE }, ) + self.validate_identity("SELECT * FROM a-b c", "SELECT * FROM a-b AS c") + def test_errors(self): with self.assertRaises(TokenError): transpile("'\\'", read="bigquery") @@ -1958,3 +1962,26 @@ OPTIONS ( "duckdb": "WITH Races AS (SELECT '800M' AS race) SELECT race, participant FROM Races AS r CROSS JOIN (SELECT UNNEST([{'name': 'Rudisha', 'laps': [23.4, 26.3, 26.4, 26.1]}], max_depth => 2)) AS participant", }, ) + + def test_range_type(self): + for type, value in ( + ("RANGE<DATE>", "'[2020-01-01, 2020-12-31)'"), + ("RANGE<DATE>", "'[UNBOUNDED, 2020-12-31)'"), + ("RANGE<DATETIME>", "'[2020-01-01 12:00:00, 2020-12-31 12:00:00)'"), + ("RANGE<TIMESTAMP>", "'[2020-10-01 12:00:00+08, 2020-12-31 12:00:00+08)'"), + ): + with self.subTest(f"Testing BigQuery's RANGE<T> type: {type} {value}"): + self.validate_identity(f"SELECT {type} {value}", f"SELECT CAST({value} AS {type})") + + self.assertEqual(self.parse_one(type), exp.DataType.build(type, dialect="bigquery")) + + self.validate_identity( + "SELECT RANGE(CAST('2022-12-01' AS DATE), CAST('2022-12-31' AS DATE))" + ) + self.validate_identity("SELECT RANGE(NULL, CAST('2022-12-31' AS DATE))") + self.validate_identity( + "SELECT RANGE(CAST('2022-10-01 14:53:27' AS DATETIME), CAST('2022-10-01 16:00:00' AS DATETIME))" + ) + self.validate_identity( + "SELECT RANGE(CAST('2022-10-01 14:53:27 America/Los_Angeles' AS TIMESTAMP), CAST('2022-10-01 16:00:00 America/Los_Angeles' AS TIMESTAMP))" + ) diff --git a/tests/dialects/test_clickhouse.py b/tests/dialects/test_clickhouse.py index d203141..b4fc587 100644 --- a/tests/dialects/test_clickhouse.py +++ b/tests/dialects/test_clickhouse.py @@ -139,10 +139,10 @@ class TestClickhouse(Validator): "CREATE MATERIALIZED VIEW test_view ON CLUSTER cl1 (id UInt8) ENGINE=AggregatingMergeTree() ORDER BY tuple() AS SELECT * FROM test_data" ) self.validate_identity( - "CREATE MATERIALIZED VIEW test_view ON CLUSTER cl1 (id UInt8) TO table1 AS SELECT * FROM test_data" + "CREATE MATERIALIZED VIEW test_view ON CLUSTER cl1 TO table1 AS SELECT * FROM test_data" ) self.validate_identity( - "CREATE MATERIALIZED VIEW test_view (id UInt8) TO db.table1 AS SELECT * FROM test_data" + "CREATE MATERIALIZED VIEW test_view TO db.table1 (id UInt8) AS SELECT * FROM test_data" ) self.validate_identity( "CREATE TABLE t (foo String CODEC(LZ4HC(9), ZSTD, DELTA), size String ALIAS formatReadableSize(size_bytes), INDEX idx1 a TYPE bloom_filter(0.001) GRANULARITY 1, INDEX idx2 a TYPE set(100) GRANULARITY 2, INDEX idx3 a TYPE minmax GRANULARITY 3)" @@ -519,6 +519,17 @@ class TestClickhouse(Validator): self.validate_identity("SELECT TRIM(LEADING '(' FROM '( Hello, world! )')") self.validate_identity("current_timestamp").assert_is(exp.Column) + self.validate_identity("SELECT * APPLY(sum) FROM columns_transformers") + self.validate_identity("SELECT COLUMNS('[jk]') APPLY(toString) FROM columns_transformers") + self.validate_identity( + "SELECT COLUMNS('[jk]') APPLY(toString) APPLY(length) APPLY(max) FROM columns_transformers" + ) + self.validate_identity("SELECT * APPLY(sum), COLUMNS('col') APPLY(sum) APPLY(avg) FROM t") + self.validate_identity( + "SELECT * FROM ABC WHERE hasAny(COLUMNS('.*field') APPLY(toUInt64) APPLY(to), (SELECT groupUniqArray(toUInt64(field))))" + ) + self.validate_identity("SELECT col apply", "SELECT col AS apply") + def test_clickhouse_values(self): values = exp.select("*").from_( exp.values([exp.tuple_(1, 2, 3)], alias="subq", columns=["a", "b", "c"]) @@ -670,6 +681,7 @@ class TestClickhouse(Validator): "CREATE TABLE foo ENGINE=Memory AS (SELECT * FROM db.other_table) COMMENT 'foo'", ) + self.validate_identity("CREATE MATERIALIZED VIEW a.b TO a.c (c Int32) AS SELECT * FROM a.d") self.validate_identity("""CREATE TABLE ip_data (ip4 IPv4, ip6 IPv6) ENGINE=TinyLog()""") self.validate_identity("""CREATE TABLE dates (dt1 Date32) ENGINE=TinyLog()""") self.validate_identity("CREATE TABLE named_tuples (a Tuple(select String, i Int64))") @@ -1084,3 +1096,7 @@ LIFETIME(MIN 0 MAX 0)""", self.assertEqual( convert(date(2020, 1, 1)).sql(dialect=self.dialect), "toDate('2020-01-01')" ) + + def test_grant(self): + self.validate_identity("GRANT SELECT(x, y) ON db.table TO john WITH GRANT OPTION") + self.validate_identity("GRANT INSERT(x, y) ON db.table TO john") diff --git a/tests/dialects/test_databricks.py b/tests/dialects/test_databricks.py index c2965e8..65e8d5d 100644 --- a/tests/dialects/test_databricks.py +++ b/tests/dialects/test_databricks.py @@ -271,3 +271,9 @@ class TestDatabricks(Validator): self.validate_identity( "CREATE OR REFRESH STREAMING TABLE csv_data (id INT, ts TIMESTAMP, event STRING) AS SELECT * FROM STREAM READ_FILES('s3://bucket/path', format => 'csv', schema => 'id int, ts timestamp, event string')" ) + + def test_grant(self): + self.validate_identity("GRANT CREATE ON SCHEMA my_schema TO `alf@melmak.et`") + 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`") diff --git a/tests/dialects/test_dialect.py b/tests/dialects/test_dialect.py index 19effb3..96ce600 100644 --- a/tests/dialects/test_dialect.py +++ b/tests/dialects/test_dialect.py @@ -2221,9 +2221,9 @@ SELECT self.validate_all( "SUBSTR('123456', 2, 3)", write={ - "bigquery": "SUBSTR('123456', 2, 3)", + "bigquery": "SUBSTRING('123456', 2, 3)", "oracle": "SUBSTR('123456', 2, 3)", - "postgres": "SUBSTR('123456', 2, 3)", + "postgres": "SUBSTRING('123456' FROM 2 FOR 3)", }, ) self.validate_all( diff --git a/tests/dialects/test_duckdb.py b/tests/dialects/test_duckdb.py index 84c82f1..e4788ec 100644 --- a/tests/dialects/test_duckdb.py +++ b/tests/dialects/test_duckdb.py @@ -256,6 +256,7 @@ class TestDuckDB(Validator): parse_one("a // b", read="duckdb").assert_is(exp.IntDiv).sql(dialect="duckdb"), "a // b" ) + self.validate_identity("CREATE TABLE tbl1 (u UNION(num INT, str TEXT))") self.validate_identity("INSERT INTO x BY NAME SELECT 1 AS y") self.validate_identity("SELECT 1 AS x UNION ALL BY NAME SELECT 2 AS x") self.validate_identity("SELECT SUM(x) FILTER (x = 1)", "SELECT SUM(x) FILTER(WHERE x = 1)") @@ -294,6 +295,9 @@ class TestDuckDB(Validator): self.validate_identity("SUMMARIZE tbl").assert_is(exp.Summarize) self.validate_identity("SUMMARIZE SELECT * FROM tbl").assert_is(exp.Summarize) self.validate_identity("CREATE TABLE tbl_summary AS SELECT * FROM (SUMMARIZE tbl)") + self.validate_identity("UNION_VALUE(k1 := 1)").find(exp.PropertyEQ).this.assert_is( + exp.Identifier + ) self.validate_identity( "SELECT species, island, COUNT(*) FROM t GROUP BY GROUPING SETS (species), GROUPING SETS (island)" ) @@ -310,6 +314,13 @@ class TestDuckDB(Validator): "SELECT * FROM x LEFT JOIN UNNEST(y)", "SELECT * FROM x LEFT JOIN UNNEST(y) ON TRUE" ) self.validate_identity( + """SELECT '{ "family": "anatidae", "species": [ "duck", "goose", "swan", null ] }' ->> ['$.family', '$.species']""", + ) + self.validate_identity( + """SELECT JSON_EXTRACT_STRING('{ "family": "anatidae", "species": [ "duck", "goose", "swan", null ] }', ['$.family', '$.species'])""", + """SELECT '{ "family": "anatidae", "species": [ "duck", "goose", "swan", null ] }' ->> ['$.family', '$.species']""", + ) + self.validate_identity( "SELECT col FROM t WHERE JSON_EXTRACT_STRING(col, '$.id') NOT IN ('b')", "SELECT col FROM t WHERE NOT (col ->> '$.id') IN ('b')", ) @@ -524,8 +535,8 @@ class TestDuckDB(Validator): write={ "duckdb": "STR_SPLIT(x, 'a')", "presto": "SPLIT(x, 'a')", - "hive": "SPLIT(x, CONCAT('\\\\Q', 'a'))", - "spark": "SPLIT(x, CONCAT('\\\\Q', 'a'))", + "hive": "SPLIT(x, CONCAT('\\\\Q', 'a', '\\\\E'))", + "spark": "SPLIT(x, CONCAT('\\\\Q', 'a', '\\\\E'))", }, ) self.validate_all( @@ -533,8 +544,8 @@ class TestDuckDB(Validator): write={ "duckdb": "STR_SPLIT(x, 'a')", "presto": "SPLIT(x, 'a')", - "hive": "SPLIT(x, CONCAT('\\\\Q', 'a'))", - "spark": "SPLIT(x, CONCAT('\\\\Q', 'a'))", + "hive": "SPLIT(x, CONCAT('\\\\Q', 'a', '\\\\E'))", + "spark": "SPLIT(x, CONCAT('\\\\Q', 'a', '\\\\E'))", }, ) self.validate_all( @@ -835,6 +846,18 @@ class TestDuckDB(Validator): "SELECT id, STRUCT_PACK(*COLUMNS('m\\d')) AS measurements FROM many_measurements", """SELECT id, {'_0': *COLUMNS('m\\d')} AS measurements FROM many_measurements""", ) + self.validate_identity("SELECT COLUMNS(c -> c LIKE '%num%') FROM numbers") + self.validate_identity( + "SELECT MIN(COLUMNS(* REPLACE (number + id AS number))), COUNT(COLUMNS(* EXCLUDE (number))) FROM numbers" + ) + self.validate_identity("SELECT COLUMNS(*) + COLUMNS(*) FROM numbers") + self.validate_identity("SELECT COLUMNS('(id|numbers?)') FROM numbers") + self.validate_identity( + "SELECT COALESCE(COLUMNS(['a', 'b', 'c'])) AS result FROM (SELECT NULL AS a, 42 AS b, TRUE AS c)" + ) + self.validate_identity( + "SELECT COALESCE(*COLUMNS(['a', 'b', 'c'])) AS result FROM (SELECT NULL AS a, 42 AS b, TRUE AS c)" + ) def test_array_index(self): with self.assertLogs(helper_logger) as cm: diff --git a/tests/dialects/test_mysql.py b/tests/dialects/test_mysql.py index 2f1f7ba..835ee7c 100644 --- a/tests/dialects/test_mysql.py +++ b/tests/dialects/test_mysql.py @@ -1278,3 +1278,18 @@ COMMENT='客户账户表'""" self.validate_identity( f"""SELECT JSON_VALUE({json_doc}, '$.price' RETURNING DECIMAL(4, 2) {on_option} ON EMPTY {on_option} ON ERROR) AS price""" ) + + def test_grant(self): + grant_cmds = [ + "GRANT 'role1', 'role2' TO 'user1'@'localhost', 'user2'@'localhost'", + "GRANT SELECT ON world.* TO 'role3'", + "GRANT SELECT ON db2.invoice TO 'jeffrey'@'localhost'", + "GRANT INSERT ON `d%`.* TO u", + "GRANT ALL ON test.* TO ''@'localhost'", + "GRANT SELECT (col1), INSERT (col1, col2) ON mydb.mytbl TO 'someuser'@'somehost'", + "GRANT SELECT, INSERT, UPDATE ON *.* TO u2", + ] + + for sql in grant_cmds: + with self.subTest(f"Testing MySQL's GRANT command statement: {sql}"): + self.validate_identity(sql, check_command_warning=True) diff --git a/tests/dialects/test_oracle.py b/tests/dialects/test_oracle.py index 28a8da9..8675086 100644 --- a/tests/dialects/test_oracle.py +++ b/tests/dialects/test_oracle.py @@ -546,3 +546,21 @@ WHERE self.validate_identity( f"SELECT * FROM t WHERE JSON_EXISTS(name{format_json}, '$[1].middle'{passing}{on_cond})" ) + + def test_grant(self): + grant_cmds = [ + "GRANT purchases_reader_role TO george, maria", + "GRANT USAGE ON TYPE price TO finance_role", + "GRANT USAGE ON DERBY AGGREGATE types.maxPrice TO sales_role", + ] + + for sql in grant_cmds: + with self.subTest(f"Testing Oracles's GRANT command statement: {sql}"): + self.validate_identity(sql, check_command_warning=True) + + self.validate_identity("GRANT SELECT ON TABLE t TO maria, harry") + self.validate_identity("GRANT SELECT ON TABLE s.v TO PUBLIC") + self.validate_identity("GRANT SELECT ON TABLE t TO purchases_reader_role") + self.validate_identity("GRANT UPDATE, TRIGGER ON TABLE t TO anita, zhi") + self.validate_identity("GRANT EXECUTE ON PROCEDURE p TO george") + self.validate_identity("GRANT USAGE ON SEQUENCE order_id TO sales_role") diff --git a/tests/dialects/test_postgres.py b/tests/dialects/test_postgres.py index ab06683..63266a5 100644 --- a/tests/dialects/test_postgres.py +++ b/tests/dialects/test_postgres.py @@ -797,6 +797,11 @@ class TestPostgres(Validator): self.validate_identity( "MERGE INTO target_table USING source_table AS source ON target.id = source.id WHEN MATCHED THEN DO NOTHING WHEN NOT MATCHED THEN DO NOTHING RETURNING MERGE_ACTION(), *" ) + self.validate_identity( + "SELECT 1 FROM ((VALUES (1)) AS vals(id) LEFT OUTER JOIN tbl ON vals.id = tbl.id)" + ) + self.validate_identity("SELECT OVERLAY(a PLACING b FROM 1)") + self.validate_identity("SELECT OVERLAY(a PLACING b FROM 1 FOR 1)") def test_ddl(self): # Checks that user-defined types are parsed into DataType instead of Identifier diff --git a/tests/dialects/test_presto.py b/tests/dialects/test_presto.py index 9c61f62..3d5fbfe 100644 --- a/tests/dialects/test_presto.py +++ b/tests/dialects/test_presto.py @@ -158,8 +158,8 @@ class TestPresto(Validator): write={ "duckdb": "STR_SPLIT(x, 'a.')", "presto": "SPLIT(x, 'a.')", - "hive": "SPLIT(x, CONCAT('\\\\Q', 'a.'))", - "spark": "SPLIT(x, CONCAT('\\\\Q', 'a.'))", + "hive": "SPLIT(x, CONCAT('\\\\Q', 'a.', '\\\\E'))", + "spark": "SPLIT(x, CONCAT('\\\\Q', 'a.', '\\\\E'))", }, ) self.validate_all( @@ -276,10 +276,19 @@ class TestPresto(Validator): self.validate_all( "DATE_PARSE(SUBSTR(x, 1, 10), '%Y-%m-%d')", write={ - "duckdb": "STRPTIME(SUBSTR(x, 1, 10), '%Y-%m-%d')", - "presto": "DATE_PARSE(SUBSTR(x, 1, 10), '%Y-%m-%d')", - "hive": "CAST(SUBSTR(x, 1, 10) AS TIMESTAMP)", - "spark": "TO_TIMESTAMP(SUBSTR(x, 1, 10), 'yyyy-MM-dd')", + "duckdb": "STRPTIME(SUBSTRING(x, 1, 10), '%Y-%m-%d')", + "presto": "DATE_PARSE(SUBSTRING(x, 1, 10), '%Y-%m-%d')", + "hive": "CAST(SUBSTRING(x, 1, 10) AS TIMESTAMP)", + "spark": "TO_TIMESTAMP(SUBSTRING(x, 1, 10), 'yyyy-MM-dd')", + }, + ) + self.validate_all( + "DATE_PARSE(SUBSTRING(x, 1, 10), '%Y-%m-%d')", + write={ + "duckdb": "STRPTIME(SUBSTRING(x, 1, 10), '%Y-%m-%d')", + "presto": "DATE_PARSE(SUBSTRING(x, 1, 10), '%Y-%m-%d')", + "hive": "CAST(SUBSTRING(x, 1, 10) AS TIMESTAMP)", + "spark": "TO_TIMESTAMP(SUBSTRING(x, 1, 10), 'yyyy-MM-dd')", }, ) self.validate_all( diff --git a/tests/dialects/test_redshift.py b/tests/dialects/test_redshift.py index c13b61a..6f561da 100644 --- a/tests/dialects/test_redshift.py +++ b/tests/dialects/test_redshift.py @@ -626,3 +626,36 @@ FROM ( "TIME_TO_STR(a, '%Y-%m-%d %H:%M:%S.%f')", write={"redshift": "TO_CHAR(a, 'YYYY-MM-DD HH24:MI:SS.US')"}, ) + + def test_grant(self): + grant_cmds = [ + "GRANT SELECT ON ALL TABLES IN SCHEMA qa_tickit TO fred", + "GRANT USAGE ON DATASHARE salesshare TO NAMESPACE '13b8833d-17c6-4f16-8fe4-1a018f5ed00d'", + "GRANT USAGE FOR SCHEMAS IN DATABASE Sales_db TO ROLE Sales", + "GRANT EXECUTE FOR FUNCTIONS IN SCHEMA Sales_schema TO bob", + "GRANT SELECT FOR TABLES IN DATABASE Sales_db TO alice WITH GRANT OPTION", + "GRANT ALL FOR TABLES IN SCHEMA ShareSchema DATABASE ShareDb TO ROLE Sales", + "GRANT ASSUMEROLE ON 'arn:aws:iam::123456789012:role/Redshift-Exfunc' TO reg_user1 FOR EXTERNAL FUNCTION", + "GRANT ROLE sample_role1 TO ROLE sample_role2", + ] + + for sql in grant_cmds: + with self.subTest(f"Testing Redshift's GRANT command statement: {sql}"): + self.validate_identity(sql, check_command_warning=True) + + self.validate_identity("GRANT SELECT ON TABLE sales TO fred") + self.validate_identity("GRANT ALL ON SCHEMA qa_tickit TO GROUP qa_users") + self.validate_identity("GRANT ALL ON TABLE qa_tickit.sales TO GROUP qa_users") + self.validate_identity( + "GRANT ALL ON TABLE qa_tickit.sales TO GROUP qa_users, GROUP ro_users" + ) + self.validate_identity("GRANT ALL ON view_date TO view_user") + self.validate_identity( + "GRANT SELECT(cust_name, cust_phone), UPDATE(cust_contact_preference) ON cust_profile TO GROUP sales_group" + ) + self.validate_identity( + "GRANT ALL(cust_name, cust_phone, cust_contact_preference) ON cust_profile TO GROUP sales_admin" + ) + 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") diff --git a/tests/dialects/test_snowflake.py b/tests/dialects/test_snowflake.py index 40413c8..6cde86b 100644 --- a/tests/dialects/test_snowflake.py +++ b/tests/dialects/test_snowflake.py @@ -755,6 +755,8 @@ WHERE write={ "spark": "SELECT COLLECT_LIST(DISTINCT a)", "snowflake": "SELECT ARRAY_AGG(DISTINCT a)", + "duckdb": "SELECT ARRAY_AGG(DISTINCT a) FILTER(WHERE a IS NOT NULL)", + "presto": "SELECT ARRAY_AGG(DISTINCT a) FILTER(WHERE a IS NOT NULL)", }, ) self.validate_all( @@ -2175,3 +2177,20 @@ SINGLE = TRUE""", """SELECT 1 FROM some_table CHANGES (INFORMATION => APPEND_ONLY) AT (TIMESTAMP => TO_TIMESTAMP_TZ('2024-07-01 00:00:00+00:00')) END (TIMESTAMP => TO_TIMESTAMP_TZ('2024-07-01 14:28:59.999999+00:00'))""", """SELECT 1 FROM some_table CHANGES (INFORMATION => APPEND_ONLY) AT (TIMESTAMP => CAST('2024-07-01 00:00:00+00:00' AS TIMESTAMPTZ)) END (TIMESTAMP => CAST('2024-07-01 14:28:59.999999+00:00' AS TIMESTAMPTZ))""", ) + + def test_grant(self): + grant_cmds = [ + "GRANT SELECT ON FUTURE TABLES IN DATABASE d1 TO ROLE r1", + "GRANT INSERT, DELETE ON FUTURE TABLES IN SCHEMA d1.s1 TO ROLE r2", + "GRANT SELECT ON ALL TABLES IN SCHEMA mydb.myschema to ROLE analyst", + "GRANT SELECT, INSERT ON FUTURE TABLES IN SCHEMA mydb.myschema TO ROLE role1", + "GRANT CREATE MATERIALIZED VIEW ON SCHEMA mydb.myschema TO DATABASE ROLE mydb.dr1", + ] + + for sql in grant_cmds: + with self.subTest(f"Testing Snowflake's GRANT command statement: {sql}"): + self.validate_identity(sql, check_command_warning=True) + + self.validate_identity( + "GRANT ALL PRIVILEGES ON FUNCTION mydb.myschema.ADD5(number) TO ROLE analyst" + ) diff --git a/tests/dialects/test_starrocks.py b/tests/dialects/test_starrocks.py index ee4dc90..44c54a6 100644 --- a/tests/dialects/test_starrocks.py +++ b/tests/dialects/test_starrocks.py @@ -85,8 +85,8 @@ class TestStarrocks(Validator): r"""SELECT id, t.type, t.scores FROM example_table, unnest(split(type, ";"), scores) AS t(type,scores)""", write={ "postgres": "SELECT id, t.type, t.scores FROM example_table, UNNEST(SPLIT(type, ';'), scores) AS t(type, scores)", - "spark": r"""SELECT id, t.type, t.scores FROM example_table LATERAL VIEW INLINE(ARRAYS_ZIP(SPLIT(type, CONCAT('\\Q', ';')), scores)) t AS type, scores""", - "databricks": r"""SELECT id, t.type, t.scores FROM example_table LATERAL VIEW INLINE(ARRAYS_ZIP(SPLIT(type, CONCAT('\\Q', ';')), scores)) t AS type, scores""", + "spark": r"""SELECT id, t.type, t.scores FROM example_table LATERAL VIEW INLINE(ARRAYS_ZIP(SPLIT(type, CONCAT('\\Q', ';', '\\E')), scores)) t AS type, scores""", + "databricks": r"""SELECT id, t.type, t.scores FROM example_table LATERAL VIEW INLINE(ARRAYS_ZIP(SPLIT(type, CONCAT('\\Q', ';', '\\E')), scores)) t AS type, scores""", "starrocks": r"""SELECT id, t.type, t.scores FROM example_table, UNNEST(SPLIT(type, ';'), scores) AS t(type, scores)""", "hive": UnsupportedError, }, @@ -95,7 +95,7 @@ class TestStarrocks(Validator): self.validate_all( r"""SELECT id, t.type, t.scores FROM example_table_2 CROSS JOIN LATERAL unnest(split(type, ";"), scores) AS t(type,scores)""", write={ - "spark": r"""SELECT id, t.type, t.scores FROM example_table_2 LATERAL VIEW INLINE(ARRAYS_ZIP(SPLIT(type, CONCAT('\\Q', ';')), scores)) t AS type, scores""", + "spark": r"""SELECT id, t.type, t.scores FROM example_table_2 LATERAL VIEW INLINE(ARRAYS_ZIP(SPLIT(type, CONCAT('\\Q', ';', '\\E')), scores)) t AS type, scores""", "starrocks": r"""SELECT id, t.type, t.scores FROM example_table_2 CROSS JOIN LATERAL UNNEST(SPLIT(type, ';'), scores) AS t(type, scores)""", "hive": UnsupportedError, }, diff --git a/tests/dialects/test_tsql.py b/tests/dialects/test_tsql.py index 7114750..453cd5a 100644 --- a/tests/dialects/test_tsql.py +++ b/tests/dialects/test_tsql.py @@ -1998,3 +1998,10 @@ FROM OPENJSON(@json) WITH ( "tsql": "SELECT COUNT(1) FROM x", }, ) + + def test_grant(self): + self.validate_identity("GRANT EXECUTE ON TestProc TO User2") + self.validate_identity("GRANT EXECUTE ON TestProc TO TesterRole WITH GRANT OPTION") + self.validate_identity( + "GRANT EXECUTE ON TestProc TO User2 AS TesterRole", check_command_warning=True + ) diff --git a/tests/fixtures/identity.sql b/tests/fixtures/identity.sql index 013eed8..bed2502 100644 --- a/tests/fixtures/identity.sql +++ b/tests/fixtures/identity.sql @@ -131,7 +131,7 @@ x[ORDINAL(1)][SAFE_OFFSET(2)] x GLOB '??-*' x GLOB y ILIKE(x, 'z') -x LIKE SUBSTR('abc', 1, 1) +x LIKE SUBSTRING('abc', 1, 1) x LIKE y x LIKE a.y x LIKE '%y%' @@ -879,3 +879,8 @@ SELECT COUNT(DISTINCT "foo bar") FROM (SELECT 1 AS "foo bar") AS t SELECT vector WITH all AS (SELECT 1 AS count) SELECT all.count FROM all SELECT rename +GRANT SELECT ON TABLE tbl TO user +GRANT SELECT, INSERT ON FUNCTION tbl TO user +GRANT SELECT ON orders TO ROLE PUBLIC +GRANT SELECT ON nation TO alice WITH GRANT OPTION +GRANT DELETE ON SCHEMA finance TO bob
\ No newline at end of file diff --git a/tests/fixtures/optimizer/simplify.sql b/tests/fixtures/optimizer/simplify.sql index 1f60741..fa2dc79 100644 --- a/tests/fixtures/optimizer/simplify.sql +++ b/tests/fixtures/optimizer/simplify.sql @@ -137,6 +137,9 @@ FALSE; TRUE AND TRUE OR TRUE AND FALSE; TRUE; +COALESCE(x, y) <> ALL (SELECT z FROM w); +COALESCE(x, y) <> ALL (SELECT z FROM w); + -------------------------------------- -- Absorption -------------------------------------- diff --git a/tests/fixtures/optimizer/tpc-ds/tpc-ds.sql b/tests/fixtures/optimizer/tpc-ds/tpc-ds.sql index 7bbeb27..290d276 100644 --- a/tests/fixtures/optimizer/tpc-ds/tpc-ds.sql +++ b/tests/fixtures/optimizer/tpc-ds/tpc-ds.sql @@ -991,9 +991,9 @@ FROM store_sales, date_dim, store, (SELECT ca_zip - FROM (SELECT Substr(ca_zip, 1, 5) ca_zip + FROM (SELECT SUBSTRING(ca_zip, 1, 5) ca_zip FROM customer_address - WHERE Substr(ca_zip, 1, 5) IN ( '67436', '26121', '38443', + WHERE SUBSTRING(ca_zip, 1, 5) IN ( '67436', '26121', '38443', '63157', '68856', '19485', '86425', '26741', @@ -1195,7 +1195,7 @@ FROM store_sales, '92564' ) INTERSECT SELECT ca_zip - FROM (SELECT Substr(ca_zip, 1, 5) ca_zip, + FROM (SELECT SUBSTRING(ca_zip, 1, 5) ca_zip, Count(*) cnt FROM customer_address, customer @@ -1207,13 +1207,13 @@ WHERE ss_store_sk = s_store_sk AND ss_sold_date_sk = d_date_sk AND d_qoy = 2 AND d_year = 2000 - AND ( Substr(s_zip, 1, 2) = Substr(V1.ca_zip, 1, 2) ) + AND ( SUBSTRING(s_zip, 1, 2) = SUBSTRING(V1.ca_zip, 1, 2) ) GROUP BY s_store_name ORDER BY s_store_name LIMIT 100; WITH "a1" AS ( SELECT - SUBSTR("customer_address"."ca_zip", 1, 5) AS "ca_zip" + SUBSTRING("customer_address"."ca_zip", 1, 5) AS "ca_zip" FROM "customer_address" AS "customer_address" JOIN "customer" AS "customer" ON "customer"."c_current_addr_sk" = "customer_address"."ca_address_sk" @@ -1224,10 +1224,10 @@ WITH "a1" AS ( COUNT(*) > 10 ), "a2" AS ( SELECT - SUBSTR("customer_address"."ca_zip", 1, 5) AS "ca_zip" + SUBSTRING("customer_address"."ca_zip", 1, 5) AS "ca_zip" FROM "customer_address" AS "customer_address" WHERE - SUBSTR("customer_address"."ca_zip", 1, 5) IN ('67436', '26121', '38443', '63157', '68856', '19485', '86425', '26741', '70991', '60899', '63573', '47556', '56193', '93314', '87827', '62017', '85067', '95390', '48091', '10261', '81845', '41790', '42853', '24675', '12840', '60065', '84430', '57451', '24021', '91735', '75335', '71935', '34482', '56943', '70695', '52147', '56251', '28411', '86653', '23005', '22478', '29031', '34398', '15365', '42460', '33337', '59433', '73943', '72477', '74081', '74430', '64605', '39006', '11226', '49057', '97308', '42663', '18187', '19768', '43454', '32147', '76637', '51975', '11181', '45630', '33129', '45995', '64386', '55522', '26697', '20963', '35154', '64587', '49752', '66386', '30586', '59286', '13177', '66646', '84195', '74316', '36853', '32927', '12469', '11904', '36269', '17724', '55346', '12595', '53988', '65439', '28015', '63268', '73590', '29216', '82575', '69267', '13805', '91678', '79460', '94152', '14961', '15419', '48277', '62588', '55493', '28360', '14152', '55225', '18007', '53705', '56573', '80245', '71769', '57348', '36845', '13039', '17270', '22363', '83474', '25294', '43269', '77666', '15488', '99146', '64441', '43338', '38736', '62754', '48556', '86057', '23090', '38114', '66061', '18910', '84385', '23600', '19975', '27883', '65719', '19933', '32085', '49731', '40473', '27190', '46192', '23949', '44738', '12436', '64794', '68741', '15333', '24282', '49085', '31844', '71156', '48441', '17100', '98207', '44982', '20277', '71496', '96299', '37583', '22206', '89174', '30589', '61924', '53079', '10976', '13104', '42794', '54772', '15809', '56434', '39975', '13874', '30753', '77598', '78229', '59478', '12345', '55547', '57422', '42600', '79444', '29074', '29752', '21676', '32096', '43044', '39383', '37296', '36295', '63077', '16572', '31275', '18701', '40197', '48242', '27219', '49865', '84175', '30446', '25165', '13807', '72142', '70499', '70464', '71429', '18111', '70857', '29545', '36425', '52706', '36194', '42963', '75068', '47921', '74763', '90990', '89456', '62073', '88397', '73963', '75885', '62657', '12530', '81146', '57434', '25099', '41429', '98441', '48713', '52552', '31667', '14072', '13903', '44709', '85429', '58017', '38295', '44875', '73541', '30091', '12707', '23762', '62258', '33247', '78722', '77431', '14510', '35656', '72428', '92082', '35267', '43759', '24354', '90952', '11512', '21242', '22579', '56114', '32339', '52282', '41791', '24484', '95020', '28408', '99710', '11899', '43344', '72915', '27644', '62708', '74479', '17177', '32619', '12351', '91339', '31169', '57081', '53522', '16712', '34419', '71779', '44187', '46206', '96099', '61910', '53664', '12295', '31837', '33096', '10813', '63048', '31732', '79118', '73084', '72783', '84952', '46965', '77956', '39815', '32311', '75329', '48156', '30826', '49661', '13736', '92076', '74865', '88149', '92397', '52777', '68453', '32012', '21222', '52721', '24626', '18210', '42177', '91791', '75251', '82075', '44372', '45542', '20609', '60115', '17362', '22750', '90434', '31852', '54071', '33762', '14705', '40718', '56433', '30996', '40657', '49056', '23585', '66455', '41021', '74736', '72151', '37007', '21729', '60177', '84558', '59027', '93855', '60022', '86443', '19541', '86886', '30532', '39062', '48532', '34713', '52077', '22564', '64638', '15273', '31677', '36138', '62367', '60261', '80213', '42818', '25113', '72378', '69802', '69096', '55443', '28820', '13848', '78258', '37490', '30556', '77380', '28447', '44550', '26791', '70609', '82182', '33306', '43224', '22322', '86959', '68519', '14308', '46501', '81131', '34056', '61991', '19896', '87804', '65774', '92564') + SUBSTRING("customer_address"."ca_zip", 1, 5) IN ('67436', '26121', '38443', '63157', '68856', '19485', '86425', '26741', '70991', '60899', '63573', '47556', '56193', '93314', '87827', '62017', '85067', '95390', '48091', '10261', '81845', '41790', '42853', '24675', '12840', '60065', '84430', '57451', '24021', '91735', '75335', '71935', '34482', '56943', '70695', '52147', '56251', '28411', '86653', '23005', '22478', '29031', '34398', '15365', '42460', '33337', '59433', '73943', '72477', '74081', '74430', '64605', '39006', '11226', '49057', '97308', '42663', '18187', '19768', '43454', '32147', '76637', '51975', '11181', '45630', '33129', '45995', '64386', '55522', '26697', '20963', '35154', '64587', '49752', '66386', '30586', '59286', '13177', '66646', '84195', '74316', '36853', '32927', '12469', '11904', '36269', '17724', '55346', '12595', '53988', '65439', '28015', '63268', '73590', '29216', '82575', '69267', '13805', '91678', '79460', '94152', '14961', '15419', '48277', '62588', '55493', '28360', '14152', '55225', '18007', '53705', '56573', '80245', '71769', '57348', '36845', '13039', '17270', '22363', '83474', '25294', '43269', '77666', '15488', '99146', '64441', '43338', '38736', '62754', '48556', '86057', '23090', '38114', '66061', '18910', '84385', '23600', '19975', '27883', '65719', '19933', '32085', '49731', '40473', '27190', '46192', '23949', '44738', '12436', '64794', '68741', '15333', '24282', '49085', '31844', '71156', '48441', '17100', '98207', '44982', '20277', '71496', '96299', '37583', '22206', '89174', '30589', '61924', '53079', '10976', '13104', '42794', '54772', '15809', '56434', '39975', '13874', '30753', '77598', '78229', '59478', '12345', '55547', '57422', '42600', '79444', '29074', '29752', '21676', '32096', '43044', '39383', '37296', '36295', '63077', '16572', '31275', '18701', '40197', '48242', '27219', '49865', '84175', '30446', '25165', '13807', '72142', '70499', '70464', '71429', '18111', '70857', '29545', '36425', '52706', '36194', '42963', '75068', '47921', '74763', '90990', '89456', '62073', '88397', '73963', '75885', '62657', '12530', '81146', '57434', '25099', '41429', '98441', '48713', '52552', '31667', '14072', '13903', '44709', '85429', '58017', '38295', '44875', '73541', '30091', '12707', '23762', '62258', '33247', '78722', '77431', '14510', '35656', '72428', '92082', '35267', '43759', '24354', '90952', '11512', '21242', '22579', '56114', '32339', '52282', '41791', '24484', '95020', '28408', '99710', '11899', '43344', '72915', '27644', '62708', '74479', '17177', '32619', '12351', '91339', '31169', '57081', '53522', '16712', '34419', '71779', '44187', '46206', '96099', '61910', '53664', '12295', '31837', '33096', '10813', '63048', '31732', '79118', '73084', '72783', '84952', '46965', '77956', '39815', '32311', '75329', '48156', '30826', '49661', '13736', '92076', '74865', '88149', '92397', '52777', '68453', '32012', '21222', '52721', '24626', '18210', '42177', '91791', '75251', '82075', '44372', '45542', '20609', '60115', '17362', '22750', '90434', '31852', '54071', '33762', '14705', '40718', '56433', '30996', '40657', '49056', '23585', '66455', '41021', '74736', '72151', '37007', '21729', '60177', '84558', '59027', '93855', '60022', '86443', '19541', '86886', '30532', '39062', '48532', '34713', '52077', '22564', '64638', '15273', '31677', '36138', '62367', '60261', '80213', '42818', '25113', '72378', '69802', '69096', '55443', '28820', '13848', '78258', '37490', '30556', '77380', '28447', '44550', '26791', '70609', '82182', '33306', '43224', '22322', '86959', '68519', '14308', '46501', '81131', '34056', '61991', '19896', '87804', '65774', '92564') INTERSECT SELECT "a1"."ca_zip" AS "ca_zip" @@ -1244,7 +1244,7 @@ JOIN "date_dim" AS "date_dim" JOIN "store" AS "store" ON "store"."s_store_sk" = "store_sales"."ss_store_sk" JOIN "a2" AS "a2" - ON SUBSTR("a2"."ca_zip", 1, 2) = SUBSTR("store"."s_zip", 1, 2) + ON SUBSTRING("a2"."ca_zip", 1, 2) = SUBSTRING("store"."s_zip", 1, 2) GROUP BY "store"."s_store_name" ORDER BY @@ -2319,7 +2319,7 @@ FROM catalog_sales, date_dim WHERE cs_bill_customer_sk = c_customer_sk AND c_current_addr_sk = ca_address_sk - AND ( Substr(ca_zip, 1, 5) IN ( '85669', '86197', '88274', '83405', + AND ( SUBSTRING(ca_zip, 1, 5) IN ( '85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792' ) OR ca_state IN ( 'CA', 'WA', 'GA' ) @@ -2344,7 +2344,7 @@ JOIN "customer_address" AS "customer_address" ON ( "catalog_sales"."cs_sales_price" > 500 OR "customer_address"."ca_state" IN ('CA', 'WA', 'GA') - OR SUBSTR("customer_address"."ca_zip", 1, 5) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') + OR SUBSTRING("customer_address"."ca_zip", 1, 5) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') ) AND "customer"."c_current_addr_sk" = "customer_address"."ca_address_sk" GROUP BY @@ -2643,7 +2643,7 @@ WHERE d_date_sk = ss_sold_date_sk AND d_year = 1998 AND ss_customer_sk = c_customer_sk AND c_current_addr_sk = ca_address_sk - AND Substr(ca_zip, 1, 5) <> Substr(s_zip, 1, 5) + AND SUBSTRING(ca_zip, 1, 5) <> SUBSTRING(s_zip, 1, 5) AND ss_store_sk = s_store_sk GROUP BY i_brand, i_brand_id, @@ -2672,7 +2672,7 @@ JOIN "customer_address" AS "customer_address" ON "customer"."c_current_addr_sk" = "customer_address"."ca_address_sk" JOIN "store" AS "store" ON "store"."s_store_sk" = "store_sales"."ss_store_sk" - AND SUBSTR("customer_address"."ca_zip", 1, 5) <> SUBSTR("store"."s_zip", 1, 5) + AND SUBSTRING("customer_address"."ca_zip", 1, 5) <> SUBSTRING("store"."s_zip", 1, 5) WHERE "date_dim"."d_moy" = 12 AND "date_dim"."d_year" = 1998 GROUP BY @@ -2895,7 +2895,7 @@ LIMIT 100; -------------------------------------- # execute: true WITH frequent_ss_items - AS (SELECT Substr(i_item_desc, 1, 30) itemdesc, + AS (SELECT SUBSTRING(i_item_desc, 1, 30) itemdesc, i_item_sk item_sk, d_date solddate, Count(*) cnt @@ -2905,7 +2905,7 @@ WITH frequent_ss_items WHERE ss_sold_date_sk = d_date_sk AND ss_item_sk = i_item_sk AND d_year IN ( 1998, 1998 + 1, 1998 + 2, 1998 + 3 ) - GROUP BY Substr(i_item_desc, 1, 30), + GROUP BY SUBSTRING(i_item_desc, 1, 30), i_item_sk, d_date HAVING Count(*) > 4), @@ -2962,7 +2962,7 @@ WITH "frequent_ss_items" AS ( JOIN "item" AS "item" ON "item"."i_item_sk" = "store_sales"."ss_item_sk" GROUP BY - SUBSTR("item"."i_item_desc", 1, 30), + SUBSTRING("item"."i_item_desc", 1, 30), "item"."i_item_sk", "date_dim"."d_date" HAVING @@ -5296,7 +5296,7 @@ FROM web_sales, WHERE ws_bill_customer_sk = c_customer_sk AND c_current_addr_sk = ca_address_sk AND ws_item_sk = i_item_sk - AND ( Substr(ca_zip, 1, 5) IN ( '85669', '86197', '88274', '83405', + AND ( SUBSTRING(ca_zip, 1, 5) IN ( '85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792' ) OR i_item_id IN (SELECT i_item_id @@ -5340,7 +5340,7 @@ JOIN "customer_address" AS "customer_address" ON "customer"."c_current_addr_sk" = "customer_address"."ca_address_sk" WHERE NOT "_u_0"."i_item_id" IS NULL - OR SUBSTR("customer_address"."ca_zip", 1, 5) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') + OR SUBSTRING("customer_address"."ca_zip", 1, 5) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') GROUP BY "customer_address"."ca_zip", "customer_address"."ca_state" @@ -7585,7 +7585,7 @@ LIMIT 100; -- TPC-DS 62 -------------------------------------- # execute: true -SELECT Substr(w_warehouse_name, 1, 20) AS "_col_0", +SELECT SUBSTRING(w_warehouse_name, 1, 20) AS "_col_0", sm_type, web_name, Sum(CASE @@ -7622,15 +7622,15 @@ WHERE d_month_seq BETWEEN 1222 AND 1222 + 11 AND ws_warehouse_sk = w_warehouse_sk AND ws_ship_mode_sk = sm_ship_mode_sk AND ws_web_site_sk = web_site_sk -GROUP BY Substr(w_warehouse_name, 1, 20), +GROUP BY SUBSTRING(w_warehouse_name, 1, 20), sm_type, web_name -ORDER BY Substr(w_warehouse_name, 1, 20), +ORDER BY SUBSTRING(w_warehouse_name, 1, 20), sm_type, web_name LIMIT 100; SELECT - SUBSTR("warehouse"."w_warehouse_name", 1, 20) AS "_col_0", + SUBSTRING("warehouse"."w_warehouse_name", 1, 20) AS "_col_0", "ship_mode"."sm_type" AS "sm_type", "web_site"."web_name" AS "web_name", SUM( @@ -7683,7 +7683,7 @@ JOIN "warehouse" AS "warehouse" JOIN "web_site" AS "web_site" ON "web_sales"."ws_web_site_sk" = "web_site"."web_site_sk" GROUP BY - SUBSTR("warehouse"."w_warehouse_name", 1, 20), + SUBSTRING("warehouse"."w_warehouse_name", 1, 20), "ship_mode"."sm_type", "web_site"."web_name" ORDER BY @@ -10638,7 +10638,7 @@ LIMIT 100; # execute: true SELECT c_last_name, c_first_name, - Substr(s_city, 1, 30) AS "_col_2", + SUBSTRING(s_city, 1, 30) AS "_col_2", ss_ticket_number, amt, profit @@ -10667,7 +10667,7 @@ FROM (SELECT ss_ticket_number, WHERE ss_customer_sk = c_customer_sk ORDER BY c_last_name, c_first_name, - Substr(s_city, 1, 30), + SUBSTRING(s_city, 1, 30), profit LIMIT 100; WITH "ms" AS ( @@ -10701,7 +10701,7 @@ WITH "ms" AS ( SELECT "customer"."c_last_name" AS "c_last_name", "customer"."c_first_name" AS "c_first_name", - SUBSTR("ms"."s_city", 1, 30) AS "_col_2", + SUBSTRING("ms"."s_city", 1, 30) AS "_col_2", "ms"."ss_ticket_number" AS "ss_ticket_number", "ms"."amt" AS "amt", "ms"."profit" AS "profit" @@ -10711,7 +10711,7 @@ JOIN "customer" AS "customer" ORDER BY "c_last_name", "c_first_name", - SUBSTR("ms"."s_city", 1, 30), + SUBSTRING("ms"."s_city", 1, 30), "profit" LIMIT 100; @@ -11371,7 +11371,7 @@ LIMIT 100; -- TPC-DS 85 -------------------------------------- # execute: true -SELECT Substr(r_reason_desc, 1, 20) AS "_col_0", +SELECT SUBSTRING(r_reason_desc, 1, 20) AS "_col_0", Avg(ws_quantity) AS "_col_1", Avg(wr_refunded_cash) AS "_col_2", Avg(wr_fee) AS "_col_3" @@ -11417,13 +11417,13 @@ WHERE ws_web_page_sk = wp_web_page_sk AND ca_state IN ( 'FL', 'WI', 'KS' ) AND ws_net_profit BETWEEN 50 AND 250 ) ) GROUP BY r_reason_desc -ORDER BY Substr(r_reason_desc, 1, 20), +ORDER BY SUBSTRING(r_reason_desc, 1, 20), Avg(ws_quantity), Avg(wr_refunded_cash), Avg(wr_fee) LIMIT 100; SELECT - SUBSTR("reason"."r_reason_desc", 1, 20) AS "_col_0", + SUBSTRING("reason"."r_reason_desc", 1, 20) AS "_col_0", AVG("web_sales"."ws_quantity") AS "_col_1", AVG("web_returns"."wr_refunded_cash") AS "_col_2", AVG("web_returns"."wr_fee") AS "_col_3" @@ -12617,7 +12617,7 @@ ORDER BY -- TPC-DS 99 -------------------------------------- # execute: true -SELECT Substr(w_warehouse_name, 1, 20) AS "_col_0", +SELECT SUBSTRING(w_warehouse_name, 1, 20) AS "_col_0", sm_type, cc_name, Sum(CASE @@ -12654,15 +12654,15 @@ WHERE d_month_seq BETWEEN 1200 AND 1200 + 11 AND cs_warehouse_sk = w_warehouse_sk AND cs_ship_mode_sk = sm_ship_mode_sk AND cs_call_center_sk = cc_call_center_sk -GROUP BY Substr(w_warehouse_name, 1, 20), +GROUP BY SUBSTRING(w_warehouse_name, 1, 20), sm_type, cc_name -ORDER BY Substr(w_warehouse_name, 1, 20), +ORDER BY SUBSTRING(w_warehouse_name, 1, 20), sm_type, cc_name LIMIT 100; SELECT - SUBSTR("warehouse"."w_warehouse_name", 1, 20) AS "_col_0", + SUBSTRING("warehouse"."w_warehouse_name", 1, 20) AS "_col_0", "ship_mode"."sm_type" AS "sm_type", "call_center"."cc_name" AS "cc_name", SUM( @@ -12715,7 +12715,7 @@ JOIN "ship_mode" AS "ship_mode" JOIN "warehouse" AS "warehouse" ON "catalog_sales"."cs_warehouse_sk" = "warehouse"."w_warehouse_sk" GROUP BY - SUBSTR("warehouse"."w_warehouse_name", 1, 20), + SUBSTRING("warehouse"."w_warehouse_name", 1, 20), "ship_mode"."sm_type", "call_center"."cc_name" ORDER BY diff --git a/tests/test_build.py b/tests/test_build.py index d169530..7518b72 100644 --- a/tests/test_build.py +++ b/tests/test_build.py @@ -761,6 +761,16 @@ class TestBuild(unittest.TestCase): ), "MERGE INTO target_table AS target USING source_table AS source ON target.id = source.id WHEN MATCHED THEN UPDATE SET target.name = source.name", ), + ( + lambda: exp.merge( + "WHEN MATCHED THEN UPDATE SET target.name = source.name", + into=exp.table_("target_table").as_("target"), + using=exp.table_("source_table").as_("source"), + on="target.id = source.id", + returning="target.*", + ), + "MERGE INTO target_table AS target USING source_table AS source ON target.id = source.id WHEN MATCHED THEN UPDATE SET target.name = source.name RETURNING target.*", + ), ]: with self.subTest(sql): self.assertEqual(expression().sql(dialect[0] if dialect else None), sql) diff --git a/tests/test_diff.py b/tests/test_diff.py index fa012a8..f83c805 100644 --- a/tests/test_diff.py +++ b/tests/test_diff.py @@ -1,14 +1,18 @@ import unittest from sqlglot import exp, parse_one -from sqlglot.diff import Insert, Keep, Move, Remove, Update, diff +from sqlglot.diff import Insert, Move, Remove, Update, diff from sqlglot.expressions import Join, to_table +def diff_delta_only(source, target, matchings=None, **kwargs): + return diff(source, target, matchings=matchings, delta_only=True, **kwargs) + + class TestDiff(unittest.TestCase): def test_simple(self): self._validate_delta_only( - diff(parse_one("SELECT a + b"), parse_one("SELECT a - b")), + diff_delta_only(parse_one("SELECT a + b"), parse_one("SELECT a - b")), [ Remove(parse_one("a + b")), # the Add node Insert(parse_one("a - b")), # the Sub node @@ -16,21 +20,21 @@ class TestDiff(unittest.TestCase): ) self._validate_delta_only( - diff(parse_one("SELECT a, b, c"), parse_one("SELECT a, c")), + diff_delta_only(parse_one("SELECT a, b, c"), parse_one("SELECT a, c")), [ Remove(parse_one("b")), # the Column node ], ) self._validate_delta_only( - diff(parse_one("SELECT a, b"), parse_one("SELECT a, b, c")), + diff_delta_only(parse_one("SELECT a, b"), parse_one("SELECT a, b, c")), [ Insert(parse_one("c")), # the Column node ], ) self._validate_delta_only( - diff( + diff_delta_only( parse_one("SELECT a FROM table_one"), parse_one("SELECT a FROM table_two"), ), @@ -44,7 +48,9 @@ class TestDiff(unittest.TestCase): def test_lambda(self): self._validate_delta_only( - diff(parse_one("SELECT a, b, c, x(a -> a)"), parse_one("SELECT a, b, c, x(b -> b)")), + diff_delta_only( + parse_one("SELECT a, b, c, x(a -> a)"), parse_one("SELECT a, b, c, x(b -> b)") + ), [ Update( exp.Lambda(this=exp.to_identifier("a"), expressions=[exp.to_identifier("a")]), @@ -55,14 +61,16 @@ class TestDiff(unittest.TestCase): def test_udf(self): self._validate_delta_only( - diff(parse_one('SELECT a, b, "my.udf1"()'), parse_one('SELECT a, b, "my.udf2"()')), + diff_delta_only( + parse_one('SELECT a, b, "my.udf1"()'), parse_one('SELECT a, b, "my.udf2"()') + ), [ Insert(parse_one('"my.udf2"()')), Remove(parse_one('"my.udf1"()')), ], ) self._validate_delta_only( - diff( + diff_delta_only( parse_one('SELECT a, b, "my.udf"(x, y, z)'), parse_one('SELECT a, b, "my.udf"(x, y, w)'), ), @@ -74,28 +82,28 @@ class TestDiff(unittest.TestCase): def test_node_position_changed(self): self._validate_delta_only( - diff(parse_one("SELECT a, b, c"), parse_one("SELECT c, a, b")), + diff_delta_only(parse_one("SELECT a, b, c"), parse_one("SELECT c, a, b")), [ Move(parse_one("c")), # the Column node ], ) self._validate_delta_only( - diff(parse_one("SELECT a + b"), parse_one("SELECT b + a")), + diff_delta_only(parse_one("SELECT a + b"), parse_one("SELECT b + a")), [ Move(parse_one("a")), # the Column node ], ) self._validate_delta_only( - diff(parse_one("SELECT aaaa AND bbbb"), parse_one("SELECT bbbb AND aaaa")), + diff_delta_only(parse_one("SELECT aaaa AND bbbb"), parse_one("SELECT bbbb AND aaaa")), [ Move(parse_one("aaaa")), # the Column node ], ) self._validate_delta_only( - diff( + diff_delta_only( parse_one("SELECT aaaa OR bbbb OR cccc"), parse_one("SELECT cccc OR bbbb OR aaaa"), ), @@ -120,7 +128,7 @@ class TestDiff(unittest.TestCase): """ self._validate_delta_only( - diff(parse_one(expr_src), parse_one(expr_tgt)), + diff_delta_only(parse_one(expr_src), parse_one(expr_tgt)), [ Remove(parse_one("LOWER(c) AS c")), # the Alias node Remove(parse_one("LOWER(c)")), # the Lower node @@ -133,8 +141,7 @@ class TestDiff(unittest.TestCase): expr_src = "SELECT a, b FROM t1 LEFT JOIN t2 ON t1.key = t2.key" expr_tgt = "SELECT a, b FROM t1 RIGHT JOIN t2 ON t1.key = t2.key" - changes = diff(parse_one(expr_src), parse_one(expr_tgt)) - changes = _delta_only(changes) + changes = diff_delta_only(parse_one(expr_src), parse_one(expr_tgt)) self.assertEqual(len(changes), 2) self.assertTrue(isinstance(changes[0], Remove)) @@ -145,10 +152,10 @@ class TestDiff(unittest.TestCase): expr_src = parse_one("SELECT ROW_NUMBER() OVER (PARTITION BY a ORDER BY b)") expr_tgt = parse_one("SELECT RANK() OVER (PARTITION BY a ORDER BY b)") - self._validate_delta_only(diff(expr_src, expr_src), []) + self._validate_delta_only(diff_delta_only(expr_src, expr_src), []) self._validate_delta_only( - diff(expr_src, expr_tgt), + diff_delta_only(expr_src, expr_tgt), [ Remove(parse_one("ROW_NUMBER()")), # the Anonymous node Insert(parse_one("RANK()")), # the Anonymous node @@ -160,7 +167,7 @@ class TestDiff(unittest.TestCase): expr_tgt = parse_one("SELECT 1, 2, 3, 4") self._validate_delta_only( - diff(expr_src, expr_tgt), + diff_delta_only(expr_src, expr_tgt), [ Remove(expr_src), Insert(expr_tgt), @@ -171,7 +178,7 @@ class TestDiff(unittest.TestCase): ) self._validate_delta_only( - diff(expr_src, expr_tgt, matchings=[(expr_src, expr_tgt)]), + diff_delta_only(expr_src, expr_tgt, matchings=[(expr_src, expr_tgt)]), [ Insert(exp.Literal.number(2)), Insert(exp.Literal.number(3)), @@ -180,23 +187,20 @@ class TestDiff(unittest.TestCase): ) with self.assertRaises(ValueError): - diff(expr_src, expr_tgt, matchings=[(expr_src, expr_tgt), (expr_src, expr_tgt)]) + diff_delta_only( + expr_src, expr_tgt, matchings=[(expr_src, expr_tgt), (expr_src, expr_tgt)] + ) def test_identifier(self): expr_src = parse_one("SELECT a FROM tbl") expr_tgt = parse_one("SELECT a, tbl.b from tbl") self._validate_delta_only( - diff(expr_src, expr_tgt), + diff_delta_only(expr_src, expr_tgt), [ Insert(expression=exp.to_column("tbl.b")), ], ) - def _validate_delta_only(self, actual_diff, expected_delta): - actual_delta = _delta_only(actual_diff) + def _validate_delta_only(self, actual_delta, expected_delta): self.assertEqual(set(actual_delta), set(expected_delta)) - - -def _delta_only(changes): - return [d for d in changes if not isinstance(d, Keep)] diff --git a/tests/test_expressions.py b/tests/test_expressions.py index 8e2ac45..e88740b 100644 --- a/tests/test_expressions.py +++ b/tests/test_expressions.py @@ -674,6 +674,8 @@ class TestExpressions(unittest.TestCase): self.assertIsInstance(parse_one("STR_POSITION(a, 'test')"), exp.StrPosition) self.assertIsInstance(parse_one("STR_TO_UNIX(a, 'format')"), exp.StrToUnix) self.assertIsInstance(parse_one("STRUCT_EXTRACT(a, 'test')"), exp.StructExtract) + self.assertIsInstance(parse_one("SUBSTR('a', 1, 1)"), exp.Substring) + self.assertIsInstance(parse_one("SUBSTRING('a', 1, 1)"), exp.Substring) self.assertIsInstance(parse_one("SUM(a)"), exp.Sum) self.assertIsInstance(parse_one("SQRT(a)"), exp.Sqrt) self.assertIsInstance(parse_one("STDDEV(a)"), exp.Stddev) diff --git a/tests/test_transpile.py b/tests/test_transpile.py index 1e0d9b6..07a915d 100644 --- a/tests/test_transpile.py +++ b/tests/test_transpile.py @@ -857,7 +857,6 @@ FROM x""", "CREATE OR REPLACE STAGE", "EXECUTE statement", "EXPLAIN SELECT * FROM x", - "GRANT INSERT ON foo TO bla", "LOAD foo", "OPTIMIZE TABLE y", "PREPARE statement", |