nevi-me commented on a change in pull request #511:
URL: https://github.com/apache/arrow-rs/pull/511#discussion_r663325539
##########
File path: parquet/src/arrow/arrow_writer.rs
##########
@@ -712,6 +711,47 @@ mod tests {
writer.close().unwrap();
}
+ #[test]
+ fn arrow_writer_list_non_null() {
+ // define schema
+ let schema = Schema::new(vec![Field::new(
+ "a",
+ DataType::List(Box::new(Field::new("item", DataType::Int32,
false))),
+ false,
+ )]);
+
+ // create some data
+ let a_values = Int32Array::from(vec![1, 2, 3, 4, 5, 6, 7, 8, 9, 10]);
+
+ // Construct a buffer for value offsets, for the nested array:
+ // [[1], [2, 3], [], [4, 5, 6], [7, 8, 9, 10]]
+ let a_value_offsets =
+ arrow::buffer::Buffer::from(&[0, 1, 3, 3, 6, 10].to_byte_slice());
+
+ // Construct a list array from the above two
+ let a_list_data =
ArrayData::builder(DataType::List(Box::new(Field::new(
+ "item",
+ DataType::Int32,
+ false,
+ ))))
+ .len(5)
+ .add_buffer(a_value_offsets)
+ .add_child_data(a_values.data().clone())
+ .build();
+ let a = ListArray::from(a_list_data);
+
+ // build a record batch
+ let batch =
+ RecordBatch::try_new(Arc::new(schema.clone()),
vec![Arc::new(a)]).unwrap();
+
+ assert_eq!(batch.column(0).data().null_count(), 0);
+
+ let file = get_temp_file("test_arrow_writer_list_non_null.parquet",
&[]);
+ let mut writer = ArrowWriter::try_new(file, Arc::new(schema),
None).unwrap();
+ writer.write(&batch).unwrap();
+ writer.close().unwrap();
Review comment:
@alamb it's because `fn roundtrip` was added after these tests existed
(and I think the reader was lagging behind the writer), so we never expanded it
to them. I've now done so, removing quite a bit of duplication.
--
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]
