jayzhan211 commented on code in PR #11299: URL: https://github.com/apache/datafusion/pull/11299#discussion_r1667496202
########## datafusion/sqllogictest/test_files/aggregate.slt: ########## @@ -1753,31 +1753,12 @@ NULL 4 29 1.260869565217 123 -117 23 NULL 5 -194 -13.857142857143 118 -101 14 NULL NULL 781 7.81 125 -117 100 -# TODO: array_agg_distinct output is non-deterministic -- rewrite with array_sort(list_sort) -# unnest is also not available, so manually unnesting via CROSS JOIN -# additional count(1) forces array_agg_distinct instead of array_agg over aggregated by c2 data -# +# select with count to forces array_agg_distinct function, since single distinct expression is converted to group by by optimizer # csv_query_array_agg_distinct -query III -WITH indices AS ( - SELECT 1 AS idx UNION ALL - SELECT 2 AS idx UNION ALL - SELECT 3 AS idx UNION ALL - SELECT 4 AS idx UNION ALL - SELECT 5 AS idx -) -SELECT data.arr[indices.idx] as element, array_length(data.arr) as array_len, dummy -FROM ( - SELECT array_agg(distinct c2) as arr, count(1) as dummy FROM aggregate_test_100 -) data - CROSS JOIN indices -ORDER BY 1 ----- -1 5 100 -2 5 100 -3 5 100 -4 5 100 -5 5 100 Review Comment: I rewrite it to the simpler one! -- 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]
