add partition by 😎 test

Author: kevinjqliu

dev/provision.py

@@ -315,6 +315,27 @@
     """
     )
 
+    # avro sanitization test
+    spark.sql(
+        f"""
+    CREATE TABLE {catalog_name}.default.test_table_metadata_sanitized_character (
+        name STRING NOT NULL,
+        `😎` STRING
+    )
+    USING ICEBERG
+    PARTITIONED BY (`😎`);
+    """
+    )
+
+    spark.sql(
+        f"""
+    INSERT INTO {catalog_name}.default.test_table_metadata_sanitized_character
+    VALUES
+        ('Foo', 'Cool Foo'),
+        ('Bar', 'Cool Bar')
+    """
+    )
+
     spark.sql(
         f"""
     CREATE TABLE {catalog_name}.default.test_table_add_column (

tests/integration/test_reads.py

@@ -760,6 +760,17 @@ def test_sanitize_character(catalog: Catalog) -> None:
     assert arrow_table.schema.names[0] == table_test_table_sanitized_character.schema().fields[0].name
 
 
+@pytest.mark.integration
+@pytest.mark.parametrize("catalog", [pytest.lazy_fixture("session_catalog_hive"), pytest.lazy_fixture("session_catalog")])
+def test_metadata_sanitize_character(catalog: Catalog) -> None:
+    avro_sanitized_character_table = catalog.load_table("default.test_table_metadata_sanitized_character")
+    arrow_table = avro_sanitized_character_table.scan().to_arrow()
+    assert len(arrow_table.schema.names) == 2
+    assert len(avro_sanitized_character_table.inspect.files()) == 2
+    assert [field.name for field in avro_sanitized_character_table.schema().fields] == ["name", "😎"]
+    assert [field.name for field in avro_sanitized_character_table.spec().fields] == ["😎"]
+
+
 @pytest.mark.integration
 @pytest.mark.parametrize("catalog", [pytest.lazy_fixture("session_catalog_hive"), pytest.lazy_fixture("session_catalog")])
 def test_null_list_and_map(catalog: Catalog) -> None: