mrunit的问题

来源：互联网发布：上海知而行编辑：程序博客网时间：2024/06/03 19:37

3. MRUnit 单元测试

3.1 MRUnit jar下载

搜索下载时注意，一定要下载hadoop2.x版本的，不然会报兼容错误。

报错信息：

java.lang.IncompatibleClassChangeError: Found interface org.apache.hadoop.mapreduce.TaskInputOutputContext, but class was expectedat org.apache.hadoop.mrunit.internal.mapreduce.AbstractMockContextWrapper.createCommon(AbstractMockContextWrapper.java:59)at org.apache.hadoop.mrunit.internal.mapreduce.MockMapContextWrapper.create(MockMapContextWrapper.java:77)at org.apache.hadoop.mrunit.internal.mapreduce.MockMapContextWrapper.<init>(MockMapContextWrapper.java:68)at org.apache.hadoop.mrunit.mapreduce.MapDriver.getContextWrapper(MapDriver.java:167)at org.apache.hadoop.mrunit.mapreduce.MapDriver.run(MapDriver.java:144)at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:640)at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:627)at com.demo.sort.MaxTemperatureMapperTest.processValidRecord(MaxTemperatureMapperTest.java:35)at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)at java.lang.reflect.Method.invoke(Method.java:497)at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47)at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44)at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:271)at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:70)at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50)at org.junit.runners.ParentRunner$3.run(ParentRunner.java:238)at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:63)at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:236)at org.junit.runners.ParentRunner.access$000(ParentRunner.java:53)at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:229)at org.junit.runners.ParentRunner.run(ParentRunner.java:309)at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:86)at org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:459)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:678)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:382)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:192)

我是从这里下载的：http://download.csdn.net/download/fkbush/9522361#comment

3.2 写UnitTest代码

单元测试函数的上面加上 @Test 注入标签。示例代码如下：

MaxTemperatureMapperTest.java

package com.demo.sort;import java.io.IOException;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mrunit.mapreduce.MapDriver;import org.junit.Test;public final class MaxTemperatureMapperTest {@Testpublic void processValidRecord() throws IOException {final Text value = new Text("123456798676231190101234567986762311901012345679867623119010123456798676231190101234561+00121534567890356"/* * + * "\r\n123456798676231190101234567986762311901012345679867623119010123456798676231190101234562+01122934567890456" * + * "\r\n123456798676231190201234567986762311901012345679867623119010123456798676231190101234562+02120234567893456" * + * "\r\n123456798676231190401234567986762311901012345679867623119010123456798676231190101234561+00321234567803456" * + * "\r\n123456798676231190101234567986762311902012345679867623119010123456798676231190101234561+00429234567903456" * + * "\r\n123456798676231190501234567986762311902012345679867623119010123456798676231190101234561+01021134568903456" * + * "\r\n123456798676231190201234567986762311902012345679867623119010123456798676231190101234561+01124234578903456" * + * "\r\n123456798676231190301234567986762311905012345679867623119010123456798676231190101234561+04121234678903456" * + * "\r\n123456798676231190301234567986762311905012345679867623119010123456798676231190101234561+0082123567" */);new MapDriver<LongWritable, Text, Text, IntWritable>().withMapper(new MaxTemperatureMapper()).withInput(new LongWritable(110000), value).withOutput(new Text("1901"), new IntWritable(11)).runTest();}}

MaxTemperatureMapper.java

/*** 页面描述* @author Henry* Created at 2017年7月23日*/package com.demo.sort;import java.io.IOException;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Mapper;// 获得每年的温度值。// 输入：一串文本。// 输出：年份(字符范围：15-19)和温度（字符范围：87-2位，有可能有加号），当没有温度数据时，用-999代替。public class MaxTemperatureMapper extends Mapper<LongWritable, Text, Text, IntWritable> {int MISSED = 999;@Overrideprotected void map(final LongWritable key, final Text value, final Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {final String line = value.toString();final String year = line.substring(15, 19);final char symbol = line.charAt(87);int airTemplate = -999;if (symbol == '+') {airTemplate = Integer.parseInt(line.substring(88, 92));} else {airTemplate = Integer.parseInt(line.substring(87, 92));}final String quality = line.substring(92, 93); // 空气质量指数if (airTemplate == MISSED && quality.matches("[01459]")) {context.write(new Text(year), new IntWritable(airTemplate));}}}

3.3 运行结果

运行报错了！！可能是发布jar的作者缺少发布一个类了？有知道的朋友么？

java.lang.NoClassDefFoundError: org/powermock/api/mockito/PowerMockitoat org.apache.hadoop.mrunit.mapreduce.MapDriver.run(MapDriver.java:147)at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:640)at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:627)at com.demo.sort.MaxTemperatureMapperTest.processValidRecord(MaxTemperatureMapperTest.java:35)at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)at java.lang.reflect.Method.invoke(Method.java:497)at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47)at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44)at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:271)at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:70)at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50)at org.junit.runners.ParentRunner$3.run(ParentRunner.java:238)at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:63)at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:236)at org.junit.runners.ParentRunner.access$000(ParentRunner.java:53)at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:229)at org.junit.runners.ParentRunner.run(ParentRunner.java:309)at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:86)at org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:459)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:678)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:382)at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:192)Caused by: java.lang.ClassNotFoundException: org.powermock.api.mockito.PowerMockitoat java.net.URLClassLoader.findClass(URLClassLoader.java:381)at java.lang.ClassLoader.loadClass(ClassLoader.java:424)at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:331)at java.lang.ClassLoader.loadClass(ClassLoader.java:357)... 27 more

3.4 报错解决过程后续

为了避免繁琐的jar依赖关系，我决定采用Maven插件来管理jar。

项目结构如下：

pom.xml：

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"><modelVersion>4.0.0</modelVersion><groupId>practice.hadoop</groupId><artifactId>simple-examples</artifactId><version>0.0.1-SNAPSHOT</version><packaging>jar</packaging><name>simple-examples</name><url>http://maven.apache.org</url><properties><project.build.sourceEncoding>UTF-8</project.build.sourceEncoding></properties><dependencies><dependency><groupId>junit</groupId><artifactId>junit</artifactId><version>4.12</version><scope>test</scope></dependency><!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common --><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-common</artifactId><version>2.8.0</version></dependency><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-hdfs</artifactId><version>2.8.0</version></dependency><!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-client --><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-client</artifactId><version>2.8.0</version></dependency><dependency><groupId>org.apache.mrunit</groupId><artifactId>mrunit</artifactId><version>1.1.0</version><classifier>hadoop2</classifier><scope>test</scope></dependency><!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-core --><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-mapreduce-client-core</artifactId><version>2.8.0</version></dependency><!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-yarn-api --><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-yarn-api</artifactId><version>2.8.0</version></dependency><!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-auth --><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-auth</artifactId><version>2.8.0</version></dependency><dependency><groupId>jdk.tools</groupId><artifactId>jdk.tools</artifactId><version>1.8</version><scope>system</scope><systemPath>${JAVA_HOME}/lib/tools.jar</systemPath></dependency><!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-minicluster --><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-minicluster</artifactId><version>2.8.0</version><scope>test</scope></dependency><!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-jobclient --><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-mapreduce-client-jobclient</artifactId><version>2.8.0</version><scope>provided</scope></dependency></dependencies></project>