mrunit execute test method error HADOOP_HOME or hadoop.home.dir are not set

2.6k views Asked by At

I want to test hadoop2 mapreduce code,use mrunit but have a error.local machine don't install hadoop in windows. pom.xml below:

 <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-core</artifactId>
                <version>2.6.0-mr1-cdh5.4.2</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-common</artifactId>
                <version>2.6.0-cdh5.4.2</version>
            </dependency>
            <dependency>
                <groupId>org.apache.mrunit</groupId>
                <artifactId>mrunit</artifactId>
                <version>1.1.0</version>
                <classifier>hadoop2</classifier>
                <scope>test</scope>
            </dependency>
            <dependency>
                <groupId>org.mockito</groupId>
                <artifactId>mockito-all</artifactId>
                <version>1.9.5</version>
                <scope>test</scope>
            </dependency>

map code belows :

package com.hadoop;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/**
 * Created by zhu on 2015/6/3.
 */
public class SMSCDRMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    private Text status = new Text();
    private final static IntWritable addOne = new IntWritable(1);

    /**
     * Returns the SMS status code and its count
     */
    protected void map(LongWritable key, Text value, Context context)
            throws java.io.IOException, InterruptedException {

        //655209;1;796764372490213;804422938115889;6 is the Sample record format
        String[] line = value.toString().split(";");
        // If record is of SMS CDR
        if (Integer.parseInt(line[1]) == 1) {
            status.set(line[4]);
            context.write(status, addOne);
        }
    }
}

reduce code belows:

package com.hadoop;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

/**
 * Created by zhu on 2015/6/3.
 */
public class SMSCDRReducer extends
        Reducer<Text, IntWritable, Text, IntWritable> {

    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws java.io.IOException, InterruptedException {
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        context.write(key, new IntWritable(sum));
    }
}

Mrunit code test belows:

 package com.hadoop;

/**
 * Created by zhu on 2015/6/3.
 */
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
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.apache.hadoop.mrunit.mapreduce.MapReduceDriver;
import org.apache.hadoop.mrunit.mapreduce.ReduceDriver;
import org.junit.Before;
import org.junit.Test;

public class SMSCDRMapperReducerTest {
    MapDriver<LongWritable, Text, Text, IntWritable> mapDriver;
    ReduceDriver<Text, IntWritable, Text, IntWritable> reduceDriver;
    MapReduceDriver<LongWritable, Text, Text, IntWritable, Text, IntWritable> mapReduceDriver;
    Configuration conf = new Configuration();

    @Before
    public void setUp() {
        SMSCDRMapper mapper = new SMSCDRMapper();
        SMSCDRReducer reducer = new SMSCDRReducer();
        mapDriver = MapDriver.newMapDriver(mapper);
        reduceDriver = ReduceDriver.newReduceDriver(reducer);
        mapReduceDriver = MapReduceDriver.newMapReduceDriver(mapper, reducer);
        mapDriver.setConfiguration(conf);
        conf.set("myParameter1", "20");
        conf.set("myParameter2", "23");
    }

    @Test
    public void testMapper() {
        mapDriver.withInput(new LongWritable(), new Text(
                "655209;1;796764372490213;804422938115889;6"));
        mapDriver.withOutput(new Text("6"), new IntWritable(1));
        try {
            mapDriver.runTest();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Test
    public void testReducer() throws IOException {
        List<IntWritable> values = new ArrayList<IntWritable>();
        values.add(new IntWritable(1));
        values.add(new IntWritable(1));
        reduceDriver.withInput(new Text("6"), values);
        reduceDriver.withOutput(new Text("6"), new IntWritable(2));
        reduceDriver.runTest();
    }

    @Test
    public void testMapReduce() throws IOException {
        mapReduceDriver.withInput(new LongWritable(), new Text(
                "655209;1;796764372490213;804422938115889;6"));
        List<IntWritable> values = new ArrayList<IntWritable>();
        values.add(new IntWritable(1));
        values.add(new IntWritable(1));
        mapReduceDriver.withOutput(new Text("6"), new IntWritable(2));
        mapReduceDriver.runTest();
    }
}

execute test method have error.use mrunit must install hadoop in local machine?

16:03:40,383 DEBUG Shell - Failed to detect a valid hadoop home directory
java.io.IOException: HADOOP_HOME or hadoop.home.dir are not set.
    at org.apache.hadoop.util.Shell.checkHadoopHome(Shell.java:302)
    at org.apache.hadoop.util.Shell.<clinit>(Shell.java:327)
    at org.apache.hadoop.util.StringUtils.<clinit>(StringUtils.java:79)
    at org.apache.hadoop.conf.Configuration.getStrings(Configuration.java:1767)
    at org.apache.hadoop.io.serializer.SerializationFactory.<init>(SerializationFactory.java:58)
    at org.apache.hadoop.mrunit.internal.io.Serialization.<init>(Serialization.java:39)
    at org.apache.hadoop.mrunit.TestDriver.getSerialization(TestDriver.java:530)
    at org.apache.hadoop.mrunit.TestDriver.copy(TestDriver.java:675)
    at org.apache.hadoop.mrunit.TestDriver.copyPair(TestDriver.java:679)
    at org.apache.hadoop.mrunit.MapReduceDriverBase.addInput(MapReduceDriverBase.java:66)
    at org.apache.hadoop.mrunit.MapReduceDriverBase.withInput(MapReduceDriverBase.java:119)
    at com.hadoop.SMSCDRMapperReducerTest.testMapReduce(SMSCDRMapperReducerTest.java:62)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:601)
    at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:45)
    at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15)
    at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:42)
    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.ParentRunner.runLeaf(ParentRunner.java:263)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:68)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:47)
    at org.junit.runners.ParentRunner$3.run(ParentRunner.java:231)
    at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:60)
    at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:229)
    at org.junit.runners.ParentRunner.access$000(ParentRunner.java:50)
    at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:222)
    at org.junit.runners.ParentRunner.run(ParentRunner.java:300)
    at org.junit.runner.JUnitCore.run(JUnitCore.java:157)
    at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:78)
    at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:212)
    at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:68)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:601)
    at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
16:03:40,406 ERROR Shell - Failed to locate the winutils binary in the hadoop binary path
java.io.IOException: Could not locate executable null\bin\winutils.exe in the Hadoop binaries.
    at org.apache.hadoop.util.Shell.getQualifiedBinPath(Shell.java:355)
    at org.apache.hadoop.util.Shell.getWinUtilsPath(Shell.java:370)
    at org.apache.hadoop.util.Shell.<clinit>(Shell.java:363)
    at org.apache.hadoop.util.StringUtils.<clinit>(StringUtils.java:79)
    at org.apache.hadoop.conf.Configuration.getStrings(Configuration.java:1767)
    at org.apache.hadoop.io.serializer.SerializationFactory.<init>(SerializationFactory.java:58)
    at org.apache.hadoop.mrunit.internal.io.Serialization.<init>(Serialization.java:39)
    at org.apache.hadoop.mrunit.TestDriver.getSerialization(TestDriver.java:530)
    at org.apache.hadoop.mrunit.TestDriver.copy(TestDriver.java:675)
    at org.apache.hadoop.mrunit.TestDriver.copyPair(TestDriver.java:679)
    at org.apache.hadoop.mrunit.MapReduceDriverBase.addInput(MapReduceDriverBase.java:66)
    at org.apache.hadoop.mrunit.MapReduceDriverBase.withInput(MapReduceDriverBase.java:119)
    at com.hadoop.SMSCDRMapperReducerTest.testMapReduce(SMSCDRMapperReducerTest.java:62)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:601)
    at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:45)
    at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15)
    at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:42)
    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.ParentRunner.runLeaf(ParentRunner.java:263)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:68)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:47)
    at org.junit.runners.ParentRunner$3.run(ParentRunner.java:231)
    at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:60)
    at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:229)
    at org.junit.runners.ParentRunner.access$000(ParentRunner.java:50)
    at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:222)
    at org.junit.runners.ParentRunner.run(ParentRunner.java:300)
    at org.junit.runner.JUnitCore.run(JUnitCore.java:157)
    at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:78)
    at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:212)
    at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:68)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:601)
    at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
16:03:40,447 DEBUG MapReduceDriver - Starting map phase with mapper: com.hadoop.SMSCDRMapper@1a74d2a
16:03:40,970 DEBUG MapReduceDriver - Starting reduce phase with reducer: com.hadoop.SMSCDRReducer@1b18eb3
16:03:41,010 DEBUG ReducePhaseRunner - Reducing input ((6, 1))
16:03:41,103 ERROR TestDriver - Missing expected output (6, 2) at position 0, got (6, 1).

java.lang.AssertionError: 1 Error(s): (Missing expected output (6, 2) at position 0, got (6, 1).)
    at org.junit.Assert.fail(Assert.java:93)
    at org.apache.hadoop.mrunit.internal.util.Errors.assertNone(Errors.java:73)
    at org.apache.hadoop.mrunit.TestDriver.validate(TestDriver.java:768)
    at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:641)
    at org.apache.hadoop.mrunit.TestDriver.runTest(TestDriver.java:627)
    at com.hadoop.SMSCDRMapperReducerTest.testMapReduce(SMSCDRMapperReducerTest.java:68)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:45)
    at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15)
    at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:42)
    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.ParentRunner.runLeaf(ParentRunner.java:263)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:68)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:47)
    at org.junit.runners.ParentRunner$3.run(ParentRunner.java:231)
    at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:60)
    at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:229)
    at org.junit.runners.ParentRunner.access$000(ParentRunner.java:50)
    at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:222)
    at org.junit.runners.ParentRunner.run(ParentRunner.java:300)
    at org.junit.runner.JUnitCore.run(JUnitCore.java:157)
    at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:78)
    at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:212)
    at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:68)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)

how to solve the problem ?

2

There are 2 answers

0
Yunhui Zhu On BEST ANSWER

Finally, mrunit's use for hadoop2 still have a error.mrunit's use for hadoop1 is ok.below is change maven:

<dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.0.0-mr1-cdh4.4.0</version>
            <scope>provided</scope>
            <exclusions>
                <exclusion>
                    <artifactId>mockito-all</artifactId>
                    <groupId>org.mockito</groupId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.0.0-cdh4.4.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.mrunit</groupId>
            <artifactId>mrunit</artifactId>
            <version>1.1.0</version>
            <classifier>hadoop2</classifier>
            <!--<scope>test</scope>-->
        </dependency>
        <dependency>
            <groupId>org.mockito</groupId>
            <artifactId>mockito-all</artifactId>
            <version>1.9.5</version>
            <scope>test</scope>
        </dependency>
1
user1516083 On

I too had the simmilar problem and got it solved by replacing dependency "hadoop-common" with "hadoop-yarn-common". Hope that helps you too.

Also I am sceptical about the dependency "hadoop-core" with version "2.6.0-mr1-cdh5.4.2" mentioned in you question, this i believe is for mapreduce1(and not mapreduce2) compatibility.