mbutrovich commented on PR #17195: URL: https://github.com/apache/datafusion/pull/17195#issuecomment-3192718767
Tested clickbench q28 which has `regexp_replace` and no regression on the fast-path: main ``` SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25; Query 28 iteration 0 took 5757.7 ms and returned 25 rows Query 28 iteration 1 took 5735.3 ms and returned 25 rows Query 28 iteration 2 took 5750.6 ms and returned 25 rows Query 28 iteration 3 took 5735.3 ms and returned 25 rows Query 28 iteration 4 took 5782.7 ms and returned 25 rows Query 28 avg time: 5752.31 ms ``` PR ``` SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25; Query 28 iteration 0 took 5717.5 ms and returned 25 rows Query 28 iteration 1 took 5735.0 ms and returned 25 rows Query 28 iteration 2 took 5750.9 ms and returned 25 rows Query 28 iteration 3 took 5751.8 ms and returned 25 rows Query 28 iteration 4 took 5739.1 ms and returned 25 rows Query 28 avg time: 5738.83 ms ``` -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org