mrunit测试在使用multipleoutputs写入hdfs时出现nullpointer异常

euoag5mw  于 2021-05-29  发布在  Hadoop
关注(0)|答案(1)|浏览(401)

我目前有一个mapreduce程序,它用不同的文件名将数据发送到hdfs。因此,在我的reducer中,我使用multipleoutput来写入hdfs中的不同文件(下面是完整的reducer代码)。
我想用mrunit测试我的代码,下面是我的测试方法。

@Test
public void reducerMRUnit() throws IOException{

    String output="";
    ArrayList<Text> list = new ArrayList<Text>(0);
    list.add(new Text(""));

    reduceDriver.withInput(new Text(""), list);

    reduceDriver.withPathOutput(new Text(output),NullWritable.get(),"");

    reduceDriver.runTest();
}

但是,当我做这个测试的时候,它给了我npe。

java.lang.NullPointerException
at org.apache.hadoop.fs.Path.<init>(Path.java:104)
at org.apache.hadoop.fs.Path.<init>(Path.java:93)
at org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.getDefaultWorkFile(FileOutputFormat.java:286)
at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:129)
at org.apache.hadoop.mapreduce.lib.output.MultipleOutputs.getRecordWriter(MultipleOutputs.java:476)
at org.apache.hadoop.mapreduce.lib.output.MultipleOutputs.write(MultipleOutputs.java:456)
at org.clinical3PO.learn.fasta.ArffToFastAReducer.reduce(ArffToFastAReducer.java:127)
at org.clinical3PO.learn.fasta.ArffToFastAReducer.reduce(ArffToFastAReducer.java:1)
at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:171)
at org.apache.hadoop.mrunit.mapreduce.ReduceDriver.run(ReduceDriver.java:265)
at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:640)
at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:627)
at org.clinical3PO.learn.fasta.MRUnitTest.ArffToFastAReducerMRUnitTest.reducerMRUnit(ArffToFastAReducerMRUnitTest.java:63)
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:44)
at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15)
at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:41)
at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:20)
at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:28)
at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:76)
at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50)
at org.junit.runners.ParentRunner$3.run(ParentRunner.java:193)
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:52)
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:191)
at org.junit.runners.ParentRunner.access$000(ParentRunner.java:42)
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:184)
at org.junit.runners.ParentRunner.run(ParentRunner.java:236)
at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50)
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:675)
at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:382)
at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:192)

减速机代码:

import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;

public class AReducer extends Reducer<Text, Text, Text, NullWritable>{
    private MultipleOutputs<Text, NullWritable> mos = null;

    @Override
    public void setup(Context context) throws IOException {
        mos = new MultipleOutputs<Text, NullWritable>(context);
    }

    @Override
    public void reduce(Text key, Iterable<Text> values, Context context)
            throws IOException, InterruptedException {
        mos = new MultipleOutputs<Text, NullWritable>(context);
        mos.write(key, value, "filename");
    }

    @Override
    public void cleanup(Context context) throws IOException, InterruptedException {
        mos.close();
    }
}

有什么建议吗?

hvvq6cgz

hvvq6cgz1#

mrunit目前有一个已知的问题,没有很好的文档记录,那就是测试 MultipleOutputs 需要使用运行测试 PowerMockRunner 和一个 PrepareForTest 应用于模拟reducer类的注解。jira问题mrunit-13和mrunit-213对此进行了详细讨论。mrunit-213仍未解决/未修复。
将powermock添加到项目中之后,在排列mockito和powermock的正确兼容版本时会引发一些进一步的挑战。有关将powermock与mockito结合使用的文档介绍了哪些版本是兼容的。
我试过对你的样品做些改动。那已经过去了 NullPointerException ,但后来我遇到了最后一个问题。测试中声明的预期路径输出与 "filename" 减速器代码使用的路径。我更改了预期的路径输出,以使测试完全通过。
这是我的最终结果:一个完全工作的项目与您的样本测试。好好享受!

pom.xml文件

<?xml version="1.0" encoding="UTF-8"?>
<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/maven-v4_0_0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>test</groupId>
    <artifactId>test-mrunit</artifactId>
    <packaging>jar</packaging>
    <version>0.0.1-SNAPSHOT</version>
    <name>Test MRUnit</name>
    <description>Test MRUnit</description>
    <properties>
        <hadoop.version>2.7.1</hadoop.version>
        <powermock.version>1.6.4</powermock.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>${hadoop.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.mockito</groupId>
            <artifactId>mockito-all</artifactId>
            <version>1.10.19</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.powermock</groupId>
            <artifactId>powermock-core</artifactId>
            <version>${powermock.version}</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.powermock</groupId>
            <artifactId>powermock-module-junit4</artifactId>
            <version>${powermock.version}</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.powermock</groupId>
            <artifactId>powermock-api-mockito</artifactId>
            <version>${powermock.version}</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.mrunit</groupId>
            <artifactId>mrunit</artifactId>
            <version>1.1.0</version>
            <classifier>hadoop2</classifier>
            <scope>test</scope>
        </dependency>
    </dependencies>
</project>

src/main/java/areducer.java

import java.io.IOException;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;

public class AReducer extends Reducer<Text, Text, Text, NullWritable>{
    private MultipleOutputs<Text, NullWritable> mos = null;

    @Override
    public void setup(Context context) throws IOException {
        mos = new MultipleOutputs<Text, NullWritable>(context);
    }

    @Override
    public void reduce(Text key, Iterable<Text> values, Context context)
            throws IOException, InterruptedException {
        mos.write(key, NullWritable.get(), "filename");
    }

    @Override
    public void cleanup(Context context) throws IOException, InterruptedException {
        mos.close();
    }
}

src/test/java/testaducer.java

import java.io.IOException;
import java.util.ArrayList;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mrunit.mapreduce.ReduceDriver;
import org.junit.Test;
import org.junit.runner.RunWith;
import org.powermock.core.classloader.annotations.PrepareForTest;
import org.powermock.modules.junit4.PowerMockRunner;

@RunWith(PowerMockRunner.class)
@PrepareForTest(AReducer.class)
public class TestAReducer {

    @Test
    public void reducerMRUnit() throws IOException{
        ReduceDriver reduceDriver = new ReduceDriver(new AReducer());
        String output = "";
        ArrayList<Text> list = new ArrayList<Text>(0);
        list.add(new Text(""));
        reduceDriver.withInput(new Text(""), list);
        reduceDriver.withPathOutput(new Text(output), NullWritable.get(), "filename");
        reduceDriver.runTest();
    }
}

相关问题