westonpace commented on pull request #9810: URL: https://github.com/apache/arrow/pull/9810#issuecomment-819134918
> I mostly agree with this, but my assumption is that Project selects which columns are produced? I don't know the implementation details, but I hope that something else actually determines which columns are read from the source (since a filter may be applied to a column not in the projection)? @drin Yes, the columns read from the disk will be the based on the columns needed for the projection expression and the columns needed for the filter expression. -- 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. For queries about this service, please contact Infrastructure at: [email protected]
