tustvold commented on code in PR #5630:
URL: https://github.com/apache/arrow-rs/pull/5630#discussion_r1580849931
##########
parquet/src/arrow/arrow_reader/mod.rs:
##########
@@ -1436,6 +1436,35 @@ mod tests {
assert_eq!(row_count, 300);
}
+ #[test]
+ fn test_read_incorrect_map_schema_file() {
+ let testdata = arrow::util::test_util::parquet_test_data();
+ // see https://github.com/apache/parquet-testing/pull/47
+ let path = format!("{testdata}/incorrect_map_schema.parquet");
+ let file = File::open(path).unwrap();
+ let mut record_reader = ParquetRecordBatchReader::try_new(file,
32).unwrap();
+
+ let batch = record_reader.next().unwrap().unwrap();
+ assert_eq!(batch.num_rows(), 1);
+
+ let expected_schema = Schema::new(Fields::from(vec![Field::new(
+ "my_map",
+ ArrowDataType::Map(
+ Arc::new(Field::new(
+ "key_value",
+ ArrowDataType::Struct(Fields::from(vec![
+ Field::new("key", ArrowDataType::Utf8, false),
+ Field::new("value", ArrowDataType::Utf8, true),
+ ])),
+ false,
+ )),
+ false.into(),
+ ),
+ true,
+ )]));
+ assert_eq!(batch.schema().as_ref(), &expected_schema);
Review Comment:
Could we perhaps check that the data is what we expect to be encoded in this
file?
--
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]
