emkornfield commented on code in PR #34054:
URL: https://github.com/apache/arrow/pull/34054#discussion_r1132715248
##########
cpp/src/parquet/arrow/arrow_reader_writer_test.cc:
##########
@@ -5146,5 +5158,96 @@ TEST(TestArrowReadWrite, FuzzReader) {
}
}
+TEST(TestArrowReadWrite, WriteReadPageIndexRoundTrip) {
+ // Enable page index to the writer.
+ auto writer_properties = WriterProperties::Builder()
+ .enable_write_page_index()
+ ->max_row_group_length(4)
+ ->build();
+ auto arrow_writer_properties = default_arrow_writer_properties();
+ auto pool = ::arrow::default_memory_pool();
+ auto sink = CreateOutputStream();
+ auto schema = ::arrow::schema(
+ {::arrow::field("c0", ::arrow::int64()), ::arrow::field("c1",
::arrow::utf8())});
+ std::shared_ptr<SchemaDescriptor> parquet_schema;
+ ASSERT_OK_NO_THROW(ToParquetSchema(schema.get(), *writer_properties,
+ *arrow_writer_properties,
&parquet_schema));
+ auto schema_node =
std::static_pointer_cast<GroupNode>(parquet_schema->schema_root());
+
+ // Prepare data and each row group contains 4 rows.
+ auto record_batch = ::arrow::RecordBatchFromJSON(schema, R"([
+ [1, "a"],
+ [2, "b"],
+ [3, "c"],
+ [null, "d"],
+ [5, null],
+ [6, "f"]
Review Comment:
it would be nice to verify a repeated column also.
--
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]
