cast to pyarrow schema

Author: kevinjqliu

pyiceberg/table/__init__.py

@@ -1126,6 +1126,8 @@ def overwrite(self, df: pa.Table, overwrite_filter: BooleanExpression = ALWAYS_T
         except ModuleNotFoundError as e:
             raise ModuleNotFoundError("For writes PyArrow needs to be installed") from e
 
+        from pyiceberg.io.pyarrow import schema_to_pyarrow
+
         if not isinstance(df, pa.Table):
             raise ValueError(f"Expected PyArrow table, got: {df}")
 
@@ -1136,6 +1138,9 @@ def overwrite(self, df: pa.Table, overwrite_filter: BooleanExpression = ALWAYS_T
             raise ValueError("Cannot write to partitioned tables")
 
         _check_schema(self.schema(), other_schema=df.schema)
+        # safe to cast
+        pyarrow_schema = schema_to_pyarrow(self.schema())
+        df = df.cast(pyarrow_schema)
 
         with self.transaction() as txn:
             with txn.update_snapshot().overwrite() as update_snapshot:

tests/catalog/test_sql.py

@@ -193,6 +193,39 @@ def test_create_table_with_pyarrow_schema(
     catalog.drop_table(random_identifier)
 
 
+@pytest.mark.parametrize(
+    'catalog',
+    [
+        lazy_fixture('catalog_memory'),
+        # lazy_fixture('catalog_sqlite'),
+    ],
+)
+def test_write_pyarrow_schema(catalog: SqlCatalog, random_identifier: Identifier) -> None:
+    import pyarrow as pa
+
+    pyarrow_table = pa.Table.from_arrays(
+        [
+            pa.array([None, "A", "B", "C"]),  # 'foo' column
+            pa.array([1, 2, 3, 4]),  # 'bar' column
+            pa.array([True, None, False, True]),  # 'baz' column
+            pa.array([None, "A", "B", "C"]),  # 'large' column
+        ],
+        schema=pa.schema([
+            pa.field('foo', pa.string(), nullable=True),
+            pa.field('bar', pa.int32(), nullable=False),
+            pa.field('baz', pa.bool_(), nullable=True),
+            pa.field('large', pa.large_string(), nullable=True),
+        ]),
+    )
+    database_name, _table_name = random_identifier
+    catalog.create_namespace(database_name)
+    table = catalog.create_table(random_identifier, pyarrow_table.schema)
+    print(pyarrow_table.schema)
+    print(table.schema().as_struct())
+    print()
+    table.overwrite(pyarrow_table)
+
+
 @pytest.mark.parametrize(
     'catalog',
     [