Dandandan commented on PR #9659: URL: https://github.com/apache/arrow-rs/pull/9659#issuecomment-4286556596
@sdf-jkl I was also thinking: instead of adding heuristics as we try to do here we could avoid "fragmented" selections. We could "unfragment" the selection instead by only call `skip` whenever this chunk is all false, but just decode and post-filter based on a boolean selection in other cases. That would avoid the nasty interleaving of skip / read but still benefit from more filters that are effective on part of the row filter. -- 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]
