gatorsmile commented on a change in pull request #27368: [SPARK-30651][SQL] Add detailed information for Aggregate operators in EXPLAIN FORMATTED URL: https://github.com/apache/spark/pull/27368#discussion_r376694900
########## File path: sql/core/src/test/resources/sql-tests/results/explain.sql.out ########## @@ -786,6 +870,144 @@ Output: [] (4) Project +-- !query +EXPLAIN FORMATTED + SELECT + COUNT(val) + SUM(key) as TOTAL, + COUNT(key) FILTER (WHERE val > 1) + FROM explain_temp1 +-- !query schema +struct<plan:string> +-- !query output +== Physical Plan == +* HashAggregate (5) ++- Exchange (4) + +- HashAggregate (3) + +- * ColumnarToRow (2) + +- Scan parquet default.explain_temp1 (1) + + +(1) Scan parquet default.explain_temp1 +Output: [key#x, val#x] +Batched: true +Location [not included in comparison]/{warehouse_dir}/explain_temp1] +ReadSchema: struct<key:int,val:int> + +(2) ColumnarToRow [codegen id : 1] +Input: [key#x, val#x] + +(3) HashAggregate +Input: [key#x, val#x] +Keys: [] +Functions: [partial_count(val#x), partial_sum(cast(key#x as bigint)), partial_count(key#x) FILTER (WHERE (val#x > 1))] +Aggregate Attributes: [count#xL, sum#xL, count#xL] +Results: [count#xL, sum#xL, count#xL] + +(4) Exchange +Input: [count#xL, sum#xL, count#xL] + +(5) HashAggregate [codegen id : 2] +Input: [count#xL, sum#xL, count#xL] +Keys: [] +Functions: [count(val#x), sum(cast(key#x as bigint)), count(key#x)] +Aggregate Attributes: [count(val#x)#xL, sum(cast(key#x as bigint))#xL, count(key#x)#xL] +Results: [(count(val#x)#xL + sum(cast(key#x as bigint))#xL) AS TOTAL#xL, count(key#x)#xL AS count(key) FILTER (WHERE (val > 1))#xL] + + +-- !query +EXPLAIN FORMATTED + SELECT key, sort_array(collect_set(val))[0] + FROM explain_temp4 + GROUP BY key +-- !query schema +struct<plan:string> +-- !query output +== Physical Plan == +ObjectHashAggregate (5) ++- Exchange (4) + +- ObjectHashAggregate (3) + +- * ColumnarToRow (2) + +- Scan parquet default.explain_temp4 (1) + + +(1) Scan parquet default.explain_temp4 +Output: [key#x, val#x] +Batched: true +Location [not included in comparison]/{warehouse_dir}/explain_temp4] +ReadSchema: struct<key:int,val:string> + +(2) ColumnarToRow [codegen id : 1] +Input: [key#x, val#x] + +(3) ObjectHashAggregate +Input: [key#x, val#x] +Keys: [key#x] +Functions: [partial_collect_set(val#x, 0, 0)] +Aggregate Attributes: [buf#x] +Results: [key#x, buf#x] + +(4) Exchange +Input: [key#x, buf#x] + +(5) ObjectHashAggregate +Input: [key#x, buf#x] +Keys: [key#x] +Functions: [collect_set(val#x, 0, 0)] +Aggregate Attributes: [collect_set(val#x, 0, 0)#x] +Results: [key#x, sort_array(collect_set(val#x, 0, 0)#x, true)[0] AS sort_array(collect_set(val), true)[0]#x] Review comment: This can be a separate PR if this is a general issue for all the other operator. We should make all of them consistent. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org