pitrou opened a new pull request #11828:
URL: https://github.com/apache/arrow/pull/11828


   Some CSV files may have long cells (values), for example if containing 
arbitrary texts or even things like timestamps.
   We can speed up parsing such CSV files by filtering multiple bytes at once 
for state-changing characters such as delimiters.
   
   This PR adds two kinds of bulk filters:
   - a very simple heuristic Bloom filter
   - a precise filter using SSE4.2 packed compare
   
   Given that negative filter matches have a non-trivial cost, the bulk filters 
are enabled only if the average cell length exceeds a given threshold.


-- 
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]


Reply via email to