tustvold commented on a change in pull request #1180:
URL: https://github.com/apache/arrow-rs/pull/1180#discussion_r788690328
##########
File path: parquet/src/arrow/arrow_reader.rs
##########
@@ -470,9 +454,78 @@ mod tests {
2,
ConvertedType::UTF8,
Some(ArrowDataType::LargeUtf8),
- &converter,
+ &large_utf8_converter,
encodings,
);
+
+ let small_key_types = [ArrowDataType::Int8, ArrowDataType::UInt8];
+ for key in &small_key_types {
+ for encoding in encodings {
+ let mut opts = TestOptions::new(2, 20,
15).with_null_percent(50);
+ opts.encoding = *encoding;
+
+ // Cannot run full test suite as keys overflow, run small test
instead
+ single_column_reader_test::<
+ ByteArrayType,
+ StringArray,
+ Utf8ArrayConverter,
+ RandUtf8Gen,
+ >(
+ opts,
+ 2,
+ ConvertedType::UTF8,
+ Some(ArrowDataType::Dictionary(
+ Box::new(key.clone()),
+ Box::new(ArrowDataType::Utf8),
+ )),
+ &utf8_converter,
+ );
+ }
+ }
+
+ let key_types = [
+ ArrowDataType::Int16,
+ ArrowDataType::UInt16,
+ ArrowDataType::Int32,
+ ArrowDataType::UInt32,
+ ArrowDataType::Int64,
+ ArrowDataType::UInt64,
+ ];
+
+ for key in &key_types {
Review comment:
Yeah... Tbh there may be value in splitting it out as an actual fuzz
testing suite in its own right...
--
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]
