Kristofferjoha commented on code in PR #26669: URL: https://github.com/apache/datafusion/pull/26669#discussion_r4367231235
########## datafusion/sqllogictest/test_files/cte.slt: ########## @@ -1727,3 +1727,107 @@ order by 1, 2; statement ok drop table test; + +# Dynamic filters produced by a recursive term must be reset between +# iterations. Otherwise the second execution of this uncorrelated aggregate +# reuses the first iteration's MAX bound and scans no rows. +statement ok +COPY (SELECT CAST(value AS DOUBLE) AS r FROM generate_series(0, 128)) TO 'test_files/scratch/cte/dynamic_filter_recursive.parquet' STORED AS PARQUET; + +statement ok +CREATE EXTERNAL TABLE dynamic_filter_recursive STORED AS PARQUET LOCATION 'test_files/scratch/cte/dynamic_filter_recursive.parquet'; + +query IR rowsort +WITH RECURSIVE w(n, m) AS ( + SELECT 0, CAST(NULL AS DOUBLE) + UNION ALL + SELECT w.n + 1, x.m + FROM w CROSS JOIN ( + SELECT MAX(r) AS m + FROM dynamic_filter_recursive + WHERE r % 2 = 0 + ) x + WHERE w.n < 3 +) +SELECT n, m FROM w; +---- +0 NULL +1 128 +2 128 +3 128 + +statement ok +DROP TABLE dynamic_filter_recursive; + +# Hash join dynamic filters must remain shared with the probe scan across +# recursive iterations (#26641). Each iteration looks up a different key, so +# retaining a stale bound would also truncate the recursive result. Review Comment: Good catch, updated the comment -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
