2010YOUY01 commented on code in PR #22607: URL: https://github.com/apache/datafusion/pull/22607#discussion_r3480381992
########## datafusion/sqllogictest/test_files/range_partitioning.slt: ########## @@ -0,0 +1,134 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +# The sqllogictest harness registers range_partitioned(range_key, non_range_key, value) +# as an in-memory source with four physical source partitions: +# +# partition 0: range_key in [..., 10), rows (1, 1, 10), (5, 2, 50) +# partition 1: range_key in [10, 20), rows (10, 1, 100), (15, 2, 150) +# partition 2: range_key in [20, 30), rows (20, 1, 200), (25, 2, 250) +# partition 3: range_key in [30, ...), rows (30, 1, 300), (35, 2, 350) + +statement ok +set datafusion.explain.physical_plan_only = true; + +########## +# TEST 1: Aggregate on Range Partition Column +# Scanning range_key preserves source Range partitioning metadata. +# Planning still inserts Hash repartitioning today; later optimizer PRs can +# use this baseline to show when the repartition is removed. +########## + +query TT +EXPLAIN SELECT range_key, SUM(value) FROM range_partitioned GROUP BY range_key; +---- +physical_plan +01)AggregateExec: mode=FinalPartitioned, gby=[range_key@0 as range_key], aggr=[sum(range_partitioned.value)] +02)--RepartitionExec: partitioning=Hash([range_key@0], 4), input_partitions=4 +03)----AggregateExec: mode=Partial, gby=[range_key@0 as range_key], aggr=[sum(range_partitioned.value)] +04)------DataSourceExec: partitions=4, partition_sizes=[1, 1, 1, 1], output_partitioning=Range([range_key@0 ASC], [(10), (20), (30)], 4) + +query II +SELECT range_key, SUM(value) FROM range_partitioned GROUP BY range_key ORDER BY range_key; +---- +1 10 +5 50 +10 100 +15 150 +20 200 +25 250 +30 300 +35 350 + + +########## +# TEST 2: Aggregate on Non-Range Column +# Projecting away range_key means the scan output no longer contains the +# expression needed to describe range partitioning, so it reports +# UnknownPartitioning with the same partition count. +########## + +query TT +EXPLAIN SELECT non_range_key, SUM(value) FROM range_partitioned GROUP BY non_range_key; +---- +physical_plan +01)AggregateExec: mode=FinalPartitioned, gby=[non_range_key@0 as non_range_key], aggr=[sum(range_partitioned.value)] +02)--RepartitionExec: partitioning=Hash([non_range_key@0], 4), input_partitions=4 +03)----AggregateExec: mode=Partial, gby=[non_range_key@0 as non_range_key], aggr=[sum(range_partitioned.value)] +04)------DataSourceExec: partitions=4, partition_sizes=[1, 1, 1, 1], output_partitioning=UnknownPartitioning(4) + +query II +SELECT non_range_key, SUM(value) FROM range_partitioned GROUP BY non_range_key ORDER BY non_range_key; +---- +1 610 +2 800 + + +########## +# TEST 3: Join on Range Partition Column +# Both inputs expose Range partitioning on range_key. Join planning currently +# reaches the unsupported Range output-partitioning path; later optimizer PRs +# can replace this baseline with a successful plan and result test. +########## + +query error This feature is not implemented: Join output partitioning with range partitioning is not implemented Review Comment: Okay, please ignore my previous comment, it's already being fixed in: - https://github.com/apache/datafusion/pull/23184/changes#diff-c02cbf8b6d5fd94c0b49666836e9e182e0e9f86054aab1c14843c577af659c7f -- 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]
