paleolimbot commented on code in PR #45459:
URL: https://github.com/apache/arrow/pull/45459#discussion_r2059538434
##########
cpp/src/parquet/arrow/arrow_schema_test.cc:
##########
@@ -1090,6 +1094,49 @@ TEST_F(TestConvertParquetSchema,
ParquetSchemaArrowUuidExtension) {
}
}
+TEST_F(TestConvertParquetSchema, ParquetSchemaGeoArrowExtensions) {
+ std::vector<NodePtr> parquet_fields;
+ parquet_fields.push_back(PrimitiveNode::Make("geometry",
Repetition::OPTIONAL,
+ LogicalType::Geometry(),
+ ParquetType::BYTE_ARRAY));
+ parquet_fields.push_back(PrimitiveNode::Make("geography",
Repetition::OPTIONAL,
+ LogicalType::Geography(),
+ ParquetType::BYTE_ARRAY));
+
+ {
+ // Parquet file does not contain Arrow schema.
+ // By default, both fields should be treated as binary() fields in Arrow.
+ auto arrow_schema = ::arrow::schema({::arrow::field("geometry", BINARY,
true),
+ ::arrow::field("geography", BINARY,
true)});
+ std::shared_ptr<KeyValueMetadata> metadata{};
+ ASSERT_OK(ConvertSchema(parquet_fields, metadata));
+ CheckFlatSchema(arrow_schema);
+ }
+
+ {
+ // Parquet file does not contain Arrow schema.
+ // If Arrow extensions are enabled and extensions are registered,
+ // fields will be interpreted as geoarrow_wkb(binary()) extension fields.
+ ::arrow::ExtensionTypeGuard guard(test::geoarrow_wkb());
+
+ ArrowReaderProperties props;
+ props.set_arrow_extensions_enabled(true);
+ auto arrow_schema = ::arrow::schema(
+ {::arrow::field(
+ "geometry",
+ test::geoarrow_wkb(R"({"crs": "OGC:CRS84", "crs_type":
"authority_code"})"),
+ true),
+ ::arrow::field(
+ "geography",
+ test::geoarrow_wkb(
+ R"({"crs": "OGC:CRS84", "crs_type": "authority_code",
"edges": "spherical"})"),
+ true)});
+ std::shared_ptr<KeyValueMetadata> metadata{};
+ ASSERT_OK(ConvertSchema(parquet_fields, metadata, props));
+ CheckFlatSchema(arrow_schema);
+ }
Review Comment:
Done!
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
