alamb commented on code in PR #9695: URL: https://github.com/apache/arrow-datafusion/pull/9695#discussion_r1530424694
########## datafusion/sqllogictest/test_files/array_query.slt: ########## @@ -0,0 +1,160 @@ +# 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. + +## Tests for basic array queries + +# Make a table with multiple input partitions +statement ok +CREATE TABLE data AS + SELECT * FROM (VALUES + ([1,2,3], [4,5], 1) + ) + UNION ALL + SELECT * FROM (VALUES + ([2,3], [2,3], 1), + ([1,2,3], NULL, 1) + ) +; + +query ??I rowsort +SELECT * FROM data; +---- +[1, 2, 3] NULL 1 +[1, 2, 3] [4, 5] 1 +[2, 3] [2, 3] 1 + +########### +# Filtering +########### + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) == List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 = [1,2,3]; + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) == List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 = column2 + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) != List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 != [1,2,3]; + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) != List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 != column2 + +########### +# Aggregates +########### + +query error Internal error: Min/Max accumulator not implemented for type List Review Comment: We should probably make this at least a nicer error ("Not supported" rather than "internal error") ########## datafusion/sqllogictest/test_files/array_query.slt: ########## @@ -0,0 +1,160 @@ +# 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. + +## Tests for basic array queries + +# Make a table with multiple input partitions +statement ok +CREATE TABLE data AS + SELECT * FROM (VALUES + ([1,2,3], [4,5], 1) + ) + UNION ALL + SELECT * FROM (VALUES + ([2,3], [2,3], 1), + ([1,2,3], NULL, 1) + ) +; + +query ??I rowsort +SELECT * FROM data; +---- +[1, 2, 3] NULL 1 +[1, 2, 3] [4, 5] 1 +[2, 3] [2, 3] 1 + +########### +# Filtering +########### + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) == List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) Review Comment: I was actually surprised I couldn't write a basic filter for `ARRAY`s -- do you know if this is tracked by any ticket @jayzhan211 ? ########## datafusion/sqllogictest/test_files/array_query.slt: ########## @@ -0,0 +1,160 @@ +# 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. + +## Tests for basic array queries + +# Make a table with multiple input partitions +statement ok +CREATE TABLE data AS + SELECT * FROM (VALUES + ([1,2,3], [4,5], 1) + ) + UNION ALL + SELECT * FROM (VALUES + ([2,3], [2,3], 1), + ([1,2,3], NULL, 1) + ) +; + +query ??I rowsort +SELECT * FROM data; +---- +[1, 2, 3] NULL 1 +[1, 2, 3] [4, 5] 1 +[2, 3] [2, 3] 1 + +########### +# Filtering +########### + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) == List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 = [1,2,3]; + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) == List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 = column2 + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) != List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 != [1,2,3]; + +query error DataFusion error: Arrow error: Invalid argument error: Invalid comparison operation: List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) != List\(Field \{ name: "item", data_type: Int64, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: \{\} \}\) +SELECT * FROM data WHERE column1 != column2 + +########### +# Aggregates +########### + +query error Internal error: Min/Max accumulator not implemented for type List +SELECT min(column1) FROM data; + +query error Internal error: Min/Max accumulator not implemented for type List +SELECT max(column1) FROM data; + +query I +SELECT count(column1) FROM data; +---- +3 + +# note single count distincts are rewritten to use a group by +query I +SELECT count(distinct column1) FROM data; +---- +2 + +query I +SELECT count(distinct column2) FROM data; +---- +2 + + +# note multiple count distincts are not rewritten +query II +SELECT count(distinct column1), count(distinct column2) FROM data; +---- +2 2 + + +########### +# GROUP BY +########### + + +query I +SELECT count(column1) FROM data GROUP BY column3; +---- +3 + +# note single count distincts are rewritten to use a group by +query I +SELECT count(distinct column1) FROM data GROUP BY column3; +---- +2 + +query I +SELECT count(distinct column2) FROM data GROUP BY column3; +---- +2 + +# note multiple count distincts are not rewritten +query II +SELECT count(distinct column1), count(distinct column2) FROM data GROUP BY column3; +---- +1 1 Review Comment: This answer is actually incorrect (same root cause as https://github.com/apache/arrow-datafusion/issues/9586) and the answer will be correct (2,2) after https://github.com/apache/arrow-datafusion/pull/9679 is merged -- 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]
