[
https://issues.apache.org/jira/browse/FLINK-2997?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15206118#comment-15206118
]
ASF GitHub Bot commented on FLINK-2997:
---------------------------------------
Github user fhueske commented on a diff in the pull request:
https://github.com/apache/flink/pull/1776#discussion_r56962421
--- Diff:
flink-tests/src/test/java/org/apache/flink/test/javaApiOperators/CustomDistributionITCase.java
---
@@ -0,0 +1,184 @@
+/*
+ * 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.flink.test.javaApiOperators;
+
+import org.apache.flink.api.common.distributions.DataDistribution;
+import org.apache.flink.api.common.functions.MapFunction;
+import org.apache.flink.api.common.functions.RichMapPartitionFunction;
+import org.apache.flink.api.common.typeinfo.BasicTypeInfo;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.java.DataSet;
+import org.apache.flink.api.java.ExecutionEnvironment;
+import org.apache.flink.api.java.io.DiscardingOutputFormat;
+import org.apache.flink.api.java.tuple.Tuple3;
+import org.apache.flink.api.java.utils.DataSetUtils;
+import org.apache.flink.core.memory.DataInputView;
+import org.apache.flink.core.memory.DataOutputView;
+import org.apache.flink.test.javaApiOperators.util.CollectionDataSets;
+import org.apache.flink.util.Collector;
+import org.junit.Test;
+
+
+import java.io.IOException;
+
+import static org.junit.Assert.fail;
+
+
+public class CustomDistributionITCase {
+
+ @Test
+ public void testPartitionWithDistribution1() throws Exception{
+ /*
+ * Test the record partitioned rightly with one field according
to the customized data distribution
+ */
+
+ ExecutionEnvironment env =
ExecutionEnvironment.createLocalEnvironment();
+
+ DataSet<Tuple3<Integer, Long, String>> input1 =
CollectionDataSets.get3TupleDataSet(env);
+ final TestDataDist dist = new TestDataDist(1);
+
+ env.setParallelism(dist.getParallelism());
+
+ DataSet<Boolean> result = DataSetUtils.partitionByRange(input1,
dist, 0).mapPartition(new RichMapPartitionFunction<Tuple3<Integer, Long,
String>, Boolean>() {
+ @Override
+ public void mapPartition(Iterable<Tuple3<Integer, Long,
String>> values, Collector<Boolean> out) throws Exception {
+ int partitionIndex =
getRuntimeContext().getIndexOfThisSubtask();
+
+ for (Tuple3<Integer, Long, String> s : values) {
+ if ((s.f0 - 1) / 7 != partitionIndex) {
+ fail("Record was not correctly
partitioned: " + s.toString());
+ }
+ }
+ }
+ });
+
+ result.output(new DiscardingOutputFormat());
+ env.execute();
+ }
+
+ @Test
+ public void testRangeWithDistribution2() throws Exception{
+ /*
+ * Test the record partitioned rightly with two fields
according to the customized data distribution
+ */
+
+ ExecutionEnvironment env =
ExecutionEnvironment.createLocalEnvironment();
+
+ DataSet<Tuple3<Integer, Long, String>> input1 =
CollectionDataSets.get3TupleDataSet(env);
--- End diff --
I think there is no suitable Collection DataSet to test range partitioning
on a composite key. The easiest data would be two int attributes that are not
correlated, i.e., are not both increasing.
> Support range partition with user customized data distribution.
> ---------------------------------------------------------------
>
> Key: FLINK-2997
> URL: https://issues.apache.org/jira/browse/FLINK-2997
> Project: Flink
> Issue Type: New Feature
> Reporter: Chengxiang Li
>
> This is a followup work of FLINK-7, sometime user have better knowledge of
> the source data, and they can build customized data distribution to do range
> partition more efficiently.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
