[
https://issues.apache.org/jira/browse/DRILL-4825?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15408999#comment-15408999
]
ASF GitHub Bot commented on DRILL-4825:
---------------------------------------
Github user amansinha100 commented on a diff in the pull request:
https://github.com/apache/drill/pull/559#discussion_r73649124
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/planner/logical/DirPrunedEnumerableTableScan.java
---
@@ -0,0 +1,73 @@
+/**
+ * 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.
+ */
+
+package org.apache.drill.exec.planner.logical;
+
+import com.google.common.base.Supplier;
+import com.google.common.collect.ImmutableList;
+import org.apache.calcite.adapter.enumerable.EnumerableConvention;
+import org.apache.calcite.adapter.enumerable.EnumerableTableScan;
+import org.apache.calcite.plan.RelOptCluster;
+import org.apache.calcite.plan.RelOptTable;
+import org.apache.calcite.plan.RelTraitSet;
+import org.apache.calcite.rel.RelCollation;
+import org.apache.calcite.rel.RelCollationTraitDef;
+import org.apache.calcite.rel.RelWriter;
+import org.apache.calcite.schema.Table;
+
+import java.util.List;
+
+/**
+ * This class extends from EnumerableTableScan. It puts the file selection
string into it's digest.
+ * When directory-based partition pruning applied, file selection could be
different for the same
+ * table.
+ */
+public class DirPrunedEnumerableTableScan extends EnumerableTableScan {
+ private final String digestFromSelection;
+
+ public DirPrunedEnumerableTableScan(RelOptCluster cluster, RelTraitSet
traitSet,
--- End diff --
Besides the constructor and the create() methods, there's also the copy()
method that I think should be overridden. Several parts of the code make a
copy of EnumerableTableScan and they will not see the digestFromSelection.
> Wrong data with UNION ALL when querying different sub-directories under the
> same table
> --------------------------------------------------------------------------------------
>
> Key: DRILL-4825
> URL: https://issues.apache.org/jira/browse/DRILL-4825
> Project: Apache Drill
> Issue Type: Bug
> Components: Query Planning & Optimization
> Affects Versions: 1.6.0, 1.7.0, 1.8.0
> Reporter: Rahul Challapalli
> Assignee: Jinfeng Ni
> Priority: Critical
> Fix For: 1.8.0
>
> Attachments: l_3level.tgz
>
>
> git.commit.id.abbrev=0700c6b
> The below query returns wrongs results
> {code}
> select count (*) from (
> select l_orderkey, dir0 from l_3level t1 where t1.dir0 = 1 and
> t1.dir1='one' and t1.dir2 = '2015-7-12'
> union all
> select l_orderkey, dir0 from l_3level t2 where t2.dir0 = 1 and
> t2.dir1='two' and t2.dir2 = '2015-8-12') data;
> +---------+
> | EXPR$0 |
> +---------+
> | 20 |
> +---------+
> {code}
> The wrong result is evident from the output of the below queries
> {code}
> 0: jdbc:drill:zk=10.10.100.190:5181> select count (*) from (select
> l_orderkey, dir0 from l_3level t2 where t2.dir0 = 1 and t2.dir1='two' and
> t2.dir2 = '2015-8-12');
> +---------+
> | EXPR$0 |
> +---------+
> | 30 |
> +---------+
> 1 row selected (0.258 seconds)
> 0: jdbc:drill:zk=10.10.100.190:5181> select count (*) from (select
> l_orderkey, dir0 from l_3level t2 where t2.dir0 = 1 and t2.dir1='one' and
> t2.dir2 = '2015-7-12');
> +---------+
> | EXPR$0 |
> +---------+
> | 10 |
> +---------+
> {code}
> I attached the data set. Let me know if you need anything more
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
