[
https://issues.apache.org/jira/browse/FLINK-2997?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15197405#comment-15197405
]
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_r56344082
--- Diff:
flink-tests/src/test/java/org/apache/flink/test/javaApiOperators/CustomDistributionITCase.java
---
@@ -0,0 +1,161 @@
+/*
+ * 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.functions.MapFunction;
+import org.apache.flink.api.common.functions.RichMapPartitionFunction;
+import org.apache.flink.api.java.tuple.Tuple2;
+import org.apache.flink.test.distribution.CustomDistribution;
+import org.apache.flink.api.java.DataSet;
+import org.apache.flink.api.java.ExecutionEnvironment;
+import org.apache.flink.api.java.tuple.Tuple3;
+import org.apache.flink.api.java.utils.DataSetUtils;
+import org.apache.flink.types.IntValue;
+import org.apache.flink.util.Collector;
+import org.junit.Test;
+
+
+import java.util.List;
+
+import static org.junit.Assert.assertTrue;
+
+
+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, Integer, String>> input1 =
env.fromElements(
+ new Tuple3<>(1, 1, "Hi"),
+ new Tuple3<>(1, 2, "Hello"),
+ new Tuple3<>(1, 3, "Hello world"),
+ new Tuple3<>(2, 4, "how are you?"),
+ new Tuple3<>(2, 5, "I am fine."),
+ new Tuple3<>(3, 6, "Luke Skywalker"),
+ new Tuple3<>(4, 7, "Comment#1"),
+ new Tuple3<>(4, 8, "Comment#2"),
+ new Tuple3<>(4, 9, "Comment#3"),
+ new Tuple3<>(5, 10, "Comment#4"));
+
+ final IntValue[] keys = new IntValue[3];
+
+ for (int i = 0; i < 3; i++) {
+ keys[i] = new IntValue((i + 1) * 2);
+ }
+
+ final CustomDistribution cd = new CustomDistribution(keys);
--- End diff --
I think we do not need the `CustomDistribution` class. It is quite heavy
and hard to read for a test class.
IMO, a static `DataDistribution` class like the following would be
sufficient for these tests:
```
public static final class TestDataDist implements DataDistribution {
@Override
public Object[] getBucketBoundary(int bucketNum, int totalNumBuckets) {
return new Integer[]{(bucketNum+1)*2};
}
@Override
public int getNumberOfFields() {
return 1;
}
@Override
public void write(DataOutputView out) throws IOException { }
@Override
public void read(DataInputView in) throws IOException { }
}
```
> 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)
