[
https://issues.apache.org/jira/browse/FLINK-1512?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14376976#comment-14376976
]
ASF GitHub Bot commented on FLINK-1512:
---------------------------------------
Github user fhueske commented on a diff in the pull request:
https://github.com/apache/flink/pull/426#discussion_r26994167
--- Diff:
flink-tests/src/test/java/org/apache/flink/test/io/CsvReaderWithPOJOITCase.java
---
@@ -0,0 +1,132 @@
+/*
+ * 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.io;
+
+import com.google.common.base.Charsets;
+import com.google.common.io.Files;
+import org.apache.flink.api.common.functions.MapFunction;
+import org.apache.flink.api.java.DataSet;
+import org.apache.flink.api.java.ExecutionEnvironment;
+import org.apache.flink.api.java.tuple.Tuple2;
+import org.apache.flink.test.util.MultipleProgramsTestBase;
+import org.junit.After;
+import org.junit.Before;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+import org.junit.runner.RunWith;
+import org.junit.runners.Parameterized;
+
+import java.io.File;
+
+@RunWith(Parameterized.class)
+public class CsvReaderWithPOJOITCase extends MultipleProgramsTestBase {
+ private String resultPath;
+ private String expected;
+
+ @Rule
+ public TemporaryFolder tempFolder = new TemporaryFolder();
+
+ public CsvReaderWithPOJOITCase(ExecutionMode mode) {
+ super(mode);
+ }
+
+ @Before
+ public void before() throws Exception {
+ resultPath = tempFolder.newFile("result").toURI().toString();
+ }
+
+ @After
+ public void after() throws Exception {
+ compareResultsByLinesInMemory(expected, resultPath);
+ }
+
+ private String createInputData(String data) throws Exception {
+ File file = tempFolder.newFile("input");
+ Files.write(data, file, Charsets.UTF_8);
+
+ return file.toURI().toString();
+ }
+
+ @Test
+ public void testPOJOType() throws Exception {
+ final String dataPath =
createInputData("ABC,2.20,3\nDEF,5.1,5\nDEF,3.30,1\nGHI,3.30,10");
+ final ExecutionEnvironment env =
ExecutionEnvironment.getExecutionEnvironment();
+
+ DataSet<POJOItem> data =
env.readCsvFile(dataPath).pojoType(POJOItem.class, new String[]{"f1", "f3",
"f2"});
+ DataSet<Tuple2<String, Integer>> result = data.map(new
POJOToTupleMapper()).groupBy(0).sum(1);
--- End diff --
I would remove the `POJOToTupleMapper` and the aggregation and instead
directly emit the POJO data with `writeAsText()`. This will use the
`toString()` method of the POJO to write the data.
Simplifies the test and restricts it to the essential part.
> Add CsvReader for reading into POJOs.
> -------------------------------------
>
> Key: FLINK-1512
> URL: https://issues.apache.org/jira/browse/FLINK-1512
> Project: Flink
> Issue Type: New Feature
> Components: Java API, Scala API
> Reporter: Robert Metzger
> Assignee: Chiwan Park
> Priority: Minor
> Labels: starter
>
> Currently, the {{CsvReader}} supports only TupleXX types.
> It would be nice if users were also able to read into POJOs.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
