rok commented on code in PR #13901:
URL: https://github.com/apache/arrow/pull/13901#discussion_r1737572395
##########
cpp/src/parquet/arrow/arrow_schema_test.cc:
##########
@@ -724,6 +727,85 @@ TEST_F(TestConvertParquetSchema,
ParquetRepeatedNestedSchema) {
ASSERT_NO_FATAL_FAILURE(CheckFlatSchema(arrow_schema));
}
+TEST_F(TestConvertParquetSchema, ParquetSchemaArrowExtensions) {
+ std::vector<NodePtr> parquet_fields;
+ parquet_fields.push_back(PrimitiveNode::Make(
+ "json_1", Repetition::OPTIONAL, ParquetType::BYTE_ARRAY,
ConvertedType::JSON));
+ parquet_fields.push_back(PrimitiveNode::Make(
+ "json_2", Repetition::OPTIONAL, ParquetType::BYTE_ARRAY,
ConvertedType::JSON));
+
+ {
+ // Parquet file does not contain Arrow schema.
+ // By default, both fields should be treated as utf8() fields in Arrow.
+ auto arrow_schema = ::arrow::schema(
+ {::arrow::field("json_1", UTF8, true), ::arrow::field("json_2", UTF8,
true)});
+ std::shared_ptr<KeyValueMetadata> metadata =
::arrow::key_value_metadata({}, {});
Review Comment:
Do you mean the test in general or the way metadata is generated? This was
changed to use a helper now.
##########
cpp/src/parquet/arrow/arrow_schema_test.cc:
##########
@@ -724,6 +727,85 @@ TEST_F(TestConvertParquetSchema,
ParquetRepeatedNestedSchema) {
ASSERT_NO_FATAL_FAILURE(CheckFlatSchema(arrow_schema));
}
+TEST_F(TestConvertParquetSchema, ParquetSchemaArrowExtensions) {
+ std::vector<NodePtr> parquet_fields;
+ parquet_fields.push_back(PrimitiveNode::Make(
+ "json_1", Repetition::OPTIONAL, ParquetType::BYTE_ARRAY,
ConvertedType::JSON));
+ parquet_fields.push_back(PrimitiveNode::Make(
+ "json_2", Repetition::OPTIONAL, ParquetType::BYTE_ARRAY,
ConvertedType::JSON));
+
+ {
+ // Parquet file does not contain Arrow schema.
+ // By default, both fields should be treated as utf8() fields in Arrow.
+ auto arrow_schema = ::arrow::schema(
+ {::arrow::field("json_1", UTF8, true), ::arrow::field("json_2", UTF8,
true)});
+ std::shared_ptr<KeyValueMetadata> metadata =
::arrow::key_value_metadata({}, {});
+ ASSERT_OK(ConvertSchema(parquet_fields, metadata));
+ CheckFlatSchema(arrow_schema);
+ }
+
+ {
+ // Parquet file does not contain Arrow schema.
+ // If Arrow extensions are enabled, both fields should be treated as
json() extension
+ // fields.
+ ArrowReaderProperties props;
+ props.set_arrow_extensions_enabled();
+ auto arrow_schema =
+ ::arrow::schema({::arrow::field("json_1", ::arrow::extension::json(),
true),
+ ::arrow::field("json_2", ::arrow::extension::json(),
true)});
+ std::shared_ptr<KeyValueMetadata> metadata =
::arrow::key_value_metadata({}, {});
Review Comment:
Same as above.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
