add test for writing special character column name

Author: kevinjqliu

tests/integration/test_writes/test_writes.py

@@ -270,6 +270,25 @@ def get_current_snapshot_id(identifier: str) -> int:
     assert tbl.current_snapshot().snapshot_id == get_current_snapshot_id(identifier)  # type: ignore
 
 
+@pytest.mark.integration
+def test_python_writes_special_character_column_with_spark_reads(spark: SparkSession, session_catalog: Catalog) -> None:
+    identifier = "default.python_writes_special_character_column_with_spark_reads"
+    column_name_with_special_character = "letter/abc"
+    TEST_DATA_WITH_SPECIAL_CHARACTER_COLUMN = {
+        column_name_with_special_character: ['a', None, 'z'],
+    }
+    pa_schema = pa.schema([
+        (column_name_with_special_character, pa.string()),
+    ])
+    arrow_table_with_special_character_column = pa.Table.from_pydict(TEST_DATA_WITH_SPECIAL_CHARACTER_COLUMN, schema=pa_schema)
+    tbl = _create_table(session_catalog, identifier, {"format-version": "1"}, schema=pa_schema)
+
+    tbl.overwrite(arrow_table_with_special_character_column)
+    spark_df = spark.sql(f"SELECT * FROM {identifier}").toPandas()
+    pyiceberg_df = tbl.scan().to_pandas()
+    assert spark_df.equals(pyiceberg_df)
+
+
 @pytest.mark.integration
 def test_write_bin_pack_data_files(spark: SparkSession, session_catalog: Catalog, arrow_table_with_null: pa.Table) -> None:
     identifier = "default.write_bin_pack_data_files"

tests/integration/test_writes/utils.py

@@ -15,7 +15,7 @@
 # specific language governing permissions and limitations
 # under the License.
 # pylint:disable=redefined-outer-name
-from typing import List, Optional
+from typing import List, Optional, Union
 
 import pyarrow as pa
 
@@ -65,6 +65,7 @@ def _create_table(
     properties: Properties,
     data: Optional[List[pa.Table]] = None,
     partition_spec: Optional[PartitionSpec] = None,
+    schema: Union[Schema, "pa.Schema"] = TABLE_SCHEMA,
 ) -> Table:
     try:
         session_catalog.drop_table(identifier=identifier)
@@ -73,10 +74,10 @@ def _create_table(
 
     if partition_spec:
         tbl = session_catalog.create_table(
-            identifier=identifier, schema=TABLE_SCHEMA, properties=properties, partition_spec=partition_spec
+            identifier=identifier, schema=schema, properties=properties, partition_spec=partition_spec
         )
     else:
-        tbl = session_catalog.create_table(identifier=identifier, schema=TABLE_SCHEMA, properties=properties)
+        tbl = session_catalog.create_table(identifier=identifier, schema=schema, properties=properties)
 
     if data:
         for d in data: