HippoBaro commented on code in PR #11278:
URL: https://github.com/apache/arrow-rs/pull/11278#discussion_r4174717974
##########
parquet/src/arrow/arrow_writer/mod.rs:
##########
@@ -2513,6 +2517,186 @@ mod tests {
roundtrip(batch_fixed_len_byte_array_decimal, Some(SMALL_SIZE / 2));
}
+ fn read_column(file: Vec<u8>) -> ArrayRef {
+ let reader = ParquetRecordBatchReader::try_new(Bytes::from(file),
4096).unwrap();
+ let batches: Vec<RecordBatch> = reader.map(|b| b.unwrap()).collect();
+ let arrays: Vec<&dyn Array> = batches.iter().map(|b|
b.column(0).as_ref()).collect();
+ arrow_select::concat::concat(&arrays).unwrap()
+ }
+
+ fn roundtrip_compatible_column(field: Field, col: ArrayRef) -> ArrayRef {
+ let writer_schema = Arc::new(Schema::new(vec![field]));
+ let batch_schema = Arc::new(Schema::new(vec![Field::new(
+ "c",
+ col.data_type().clone(),
+ col.logical_null_count() != 0,
+ )]));
+ let batch = RecordBatch::try_new(batch_schema, vec![col]).unwrap();
+ let options = ArrowWriterOptions::new().with_skip_arrow_metadata(true);
+ let mut file = vec![];
+ let mut writer =
+ ArrowWriter::try_new_with_options(&mut file, writer_schema,
options).unwrap();
+ writer.write(&batch).unwrap();
+ writer.close().unwrap();
+ read_column(file)
+ }
+
+ #[test]
+ fn arrow_writer_dense_batches_under_nested_wrapper_schemas() {
Review Comment:
Fair thanks for pushing back; it's now split this into ten focused tests.
Failures now identify the specific wrapper or nested-child behavior that broke.
--
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]
