MapReduce Old API - Passing Command Line Argument to Map

Question

I am coding a MapReduce job for finding the occurrence of a search string (passed through Command Line argument) in an input file stored in HDFS using old API.

Below is my Driver class -

public class StringSearchDriver
{

    public static void main(String[] args) throws IOException
    {
        JobConf jc = new JobConf(StringSearchDriver.class);
        jc.set("SearchWord", args[2]);
        jc.setJobName("String Search");
        FileInputFormat.addInputPath(jc, new Path(args[0]));
        FileOutputFormat.setOutputPath(jc, new Path(args[1]));
        jc.setMapperClass(StringSearchMap.class);
        jc.setReducerClass(StringSearchReduce.class);
        jc.setOutputKeyClass(Text.class);
        jc.setOutputValueClass(IntWritable.class);
        JobClient.runJob(jc);
    }
}

Below is my Mapper Class -

public class StringSearchMap extends MapReduceBase implements
        Mapper<LongWritable, Text, Text, IntWritable>
{
    String searchWord;

    public void configure(JobConf jc)
    {
        searchWord = jc.get("SearchWord");

    }



    @Override
    public void map(LongWritable key, Text value,  
            OutputCollector<Text, IntWritable> out, Reporter reporter)
            throws IOException
    {
        String[] input = value.toString().split("");

        for(String word:input)
        {
            if (word.equalsIgnoreCase(searchWord))
                out.collect(new Text(word), new IntWritable(1));
        }
    }

}

On running the job (command line string passed is "hi"), I am getting the below error -

14/09/21 22:35:41 INFO mapred.JobClient: Task Id : attempt_201409212134_0005_m_000001_2, Status : FAILED
java.lang.ClassCastException: interface javax.xml.soap.Text
    at java.lang.Class.asSubclass(Class.java:3129)
    at org.apache.hadoop.mapred.JobConf.getOutputKeyComparator(JobConf.java:795)
    at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.<init>(MapTask.java:964)
    at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:422)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:366)
    at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:416)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1190)
    at org.apache.hadoop.mapred.Child.main(Child.java:249)

Please suggest.

Answer 1

You auto imported the wrong import. Instead of import org.apache.hadoop.io.Text you import javax.xml.soap.Text

You can find a sample wrong import in this blog .

One point , It is better to adopt New API

EDIT

I used New Api

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * @author Unmesha sreeveni
 * @Date 23 sep 2014
 */
public class StringSearchDriver extends Configured implements Tool {
    public static class Map extends
    Mapper<LongWritable, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            Configuration conf = context.getConfiguration();
            String line = value.toString();
            String searchString = conf.get("word");
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                String token = tokenizer.nextToken();
                if(token.equals(searchString)){
                    word.set(token);
                    context.write(word, one);
                }

            }
        }
    }

    public static class Reduce extends
    Reducer<Text, IntWritable, Text, IntWritable> {

        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {

            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        int res = ToolRunner.run(conf, new StringSearchDriver(), args);
        System.exit(res);

    }
    @Override
    public int run(String[] args) throws Exception {
        // TODO Auto-generated method stub
        if (args.length != 3) {
            System.out
            .printf("Usage: Search String <input dir> <output dir> <search word> \n");
            System.exit(-1);
        }

        String source = args[0];
        String dest = args[1];
        String searchword = args[2];
        Configuration conf = new Configuration();
        conf.set("word", searchword);
        Job job = new Job(conf, "Search String");
        job.setJarByClass(StringSearchDriver.class);
        FileSystem fs = FileSystem.get(conf);

        Path in =new Path(source);
        Path out =new Path(dest);
        if (fs.exists(out)) {
            fs.delete(out, true);
        }

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        boolean sucess = job.waitForCompletion(true);
        return (sucess ? 0 : 1);
    }
}

This works.

Answer 2

For Text; required hadoop package is org.apache.hadoop.io. . Check your packages

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;