Fix(clickhouse): add missing type mappings for string types (#2183)

* Fix(clickhouse): add missing type mappings for string types * pr feedback * add mediumint test
tobymao · Sep 8, 2023 · 451439c · 451439c
1 parent 5e2042a
commit 451439c
Show file tree

Hide file tree

Showing 3 changed files with 47 additions and 30 deletions.
diff --git a/sqlglot/dialects/clickhouse.py b/sqlglot/dialects/clickhouse.py
@@ -333,6 +333,7 @@ class Generator(generator.Generator):
             exp.DataType.Type.FIXEDSTRING: "FixedString",
             exp.DataType.Type.FLOAT: "Float32",
             exp.DataType.Type.INT: "Int32",
+            exp.DataType.Type.MEDIUMINT: "Int32",
             exp.DataType.Type.INT128: "Int128",
             exp.DataType.Type.INT256: "Int256",
             exp.DataType.Type.LOWCARDINALITY: "LowCardinality",

diff --git a/sqlglot/tokens.py b/sqlglot/tokens.py
@@ -677,6 +677,7 @@ class Tokenizer(metaclass=_Tokenizer):
         "BOOL": TokenType.BOOLEAN,
         "BOOLEAN": TokenType.BOOLEAN,
         "BYTE": TokenType.TINYINT,
+        "MEDIUMINT": TokenType.MEDIUMINT,
         "TINYINT": TokenType.TINYINT,
         "SHORT": TokenType.SMALLINT,
         "SMALLINT": TokenType.SMALLINT,
@@ -714,12 +715,16 @@ class Tokenizer(metaclass=_Tokenizer):
         "STR": TokenType.TEXT,
         "STRING": TokenType.TEXT,
         "TEXT": TokenType.TEXT,
-        "TINYTEXT": TokenType.TEXT,
+        "LONGTEXT": TokenType.LONGTEXT,
+        "MEDIUMTEXT": TokenType.MEDIUMTEXT,
+        "TINYTEXT": TokenType.TINYTEXT,
         "CLOB": TokenType.TEXT,
         "LONGVARCHAR": TokenType.TEXT,
         "BINARY": TokenType.BINARY,
         "BLOB": TokenType.VARBINARY,
-        "TINYBLOB": TokenType.VARBINARY,
+        "LONGBLOB": TokenType.LONGBLOB,
+        "MEDIUMBLOB": TokenType.MEDIUMBLOB,
+        "TINYBLOB": TokenType.TINYBLOB,
         "BYTEA": TokenType.VARBINARY,
         "VARBINARY": TokenType.VARBINARY,
         "TIME": TokenType.TIME,

diff --git a/tests/dialects/test_clickhouse.py b/tests/dialects/test_clickhouse.py
@@ -6,30 +6,19 @@ class TestClickhouse(Validator):
     dialect = "clickhouse"
 
     def test_clickhouse(self):
-        self.validate_all(
-            "DATE_ADD('day', 1, x)",
-            read={
-                "clickhouse": "dateAdd(day, 1, x)",
-                "presto": "DATE_ADD('day', 1, x)",
-            },
-            write={
-                "clickhouse": "DATE_ADD('day', 1, x)",
-                "presto": "DATE_ADD('day', 1, x)",
-                "": "DATE_ADD(x, 1, 'day')",
-            },
-        )
-        self.validate_all(
-            "DATE_DIFF('day', a, b)",
-            read={
-                "clickhouse": "dateDiff('day', a, b)",
-                "presto": "DATE_DIFF('day', a, b)",
-            },
-            write={
-                "clickhouse": "DATE_DIFF('day', a, b)",
-                "presto": "DATE_DIFF('day', a, b)",
-                "": "DATEDIFF(b, a, day)",
-            },
-        )
+        string_types = [
+            "BLOB",
+            "LONGBLOB",
+            "LONGTEXT",
+            "MEDIUMBLOB",
+            "MEDIUMTEXT",
+            "TINYBLOB",
+            "TINYTEXT",
+            "VARCHAR(255)",
+        ]
+
+        for string_type in string_types:
+            self.validate_identity(f"CAST(x AS {string_type})", "CAST(x AS String)")
 
         expr = parse_one("count(x)")
         self.assertEqual(expr.sql(dialect="clickhouse"), "COUNT(x)")
@@ -72,10 +61,8 @@ def test_clickhouse(self):
         self.validate_identity("position(haystack, needle)")
         self.validate_identity("position(haystack, needle, position)")
         self.validate_identity("CAST(x AS DATETIME)")
-        self.validate_identity("CAST(x AS VARCHAR(255))", "CAST(x AS String)")
-        self.validate_identity("CAST(x AS BLOB)", "CAST(x AS String)")
-        self.validate_identity("CAST(x AS TINYBLOB)", "CAST(x AS String)")
-        self.validate_identity("CAST(x AS TINYTEXT)", "CAST(x AS String)")
+        self.validate_identity("CAST(x as MEDIUMINT)", "CAST(x AS Int32)")
+
         self.validate_identity(
             'SELECT CAST(tuple(1 AS "a", 2 AS "b", 3.0 AS "c").2 AS Nullable(String))'
         )
@@ -95,6 +82,30 @@ def test_clickhouse(self):
             "CREATE MATERIALIZED VIEW test_view (id UInt8) TO db.table1 AS SELECT * FROM test_data"
         )
 
+        self.validate_all(
+            "DATE_ADD('day', 1, x)",
+            read={
+                "clickhouse": "dateAdd(day, 1, x)",
+                "presto": "DATE_ADD('day', 1, x)",
+            },
+            write={
+                "clickhouse": "DATE_ADD('day', 1, x)",
+                "presto": "DATE_ADD('day', 1, x)",
+                "": "DATE_ADD(x, 1, 'day')",
+            },
+        )
+        self.validate_all(
+            "DATE_DIFF('day', a, b)",
+            read={
+                "clickhouse": "dateDiff('day', a, b)",
+                "presto": "DATE_DIFF('day', a, b)",
+            },
+            write={
+                "clickhouse": "DATE_DIFF('day', a, b)",
+                "presto": "DATE_DIFF('day', a, b)",
+                "": "DATEDIFF(b, a, day)",
+            },
+        )
         self.validate_all(
             "SELECT xor(1, 0)",
             read={