etseidl commented on code in PR #6730:
URL: https://github.com/apache/arrow-rs/pull/6730#discussion_r1844492304
##########
parquet/src/arrow/arrow_reader/mod.rs:
##########
@@ -4065,4 +4065,72 @@ mod tests {
}
}
}
+
+ #[test]
+ fn test_map_no_value() {
+ let schema = "
+ message spark_schema {
+ REQUIRED group my_map (MAP) {
+ REPEATED group key_value {
+ REQUIRED INT32 key;
+ }
+ }
+ REQUIRED group my_list (LIST) {
+ REPEATED group list {
+ REQUIRED INT32 element;
+ }
+ }
+ }
+ ";
+ let schema = Arc::new(parse_message_type(schema).unwrap());
+
+ // Write Parquet file to buffer
+ let mut buffer: Vec<u8> = Vec::new();
+ let mut file_writer =
+ SerializedFileWriter::new(&mut buffer, schema,
Default::default()).unwrap();
+ let mut row_group_writer = file_writer.next_row_group().unwrap();
+
+ // Write column my_map.key_value.key
+ let mut column_writer =
row_group_writer.next_column().unwrap().unwrap();
+ column_writer
+ .typed::<Int32Type>()
+ .write_batch(
+ &[1, 2, 3, 4, 5, 6, 7, 8, 9],
+ Some(&[1, 1, 1, 1, 1, 1, 1, 1, 1]),
+ Some(&[0, 1, 1, 0, 1, 1, 0, 1, 1]),
+ )
+ .unwrap();
+ column_writer.close().unwrap();
+
+ // Write column my_list.list.element
+ let mut column_writer =
row_group_writer.next_column().unwrap().unwrap();
+ column_writer
+ .typed::<Int32Type>()
+ .write_batch(
+ &[1, 2, 3, 4, 5, 6, 7, 8, 9],
+ Some(&[1, 1, 1, 1, 1, 1, 1, 1, 1]),
+ Some(&[0, 1, 1, 0, 1, 1, 0, 1, 1]),
+ )
+ .unwrap();
+ column_writer.close().unwrap();
+
+ // Finalize Parquet file
+ row_group_writer.close().unwrap();
+ file_writer.close().unwrap();
+ assert_eq!(&buffer[0..4], b"PAR1");
+
+ // Read Parquet file from buffer
+ let mut reader =
ParquetRecordBatchReaderBuilder::try_new(Bytes::from(buffer))
+ .unwrap()
+ .build()
+ .unwrap();
+ let out = reader.next().unwrap().unwrap();
+ assert_eq!(out.num_rows(), 3);
+ assert_eq!(out.num_columns(), 2);
+ // map and list columns should now be equivalent
Review Comment:
Yes, because an arrow map must have non-null values IIUC.
--
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]
