WordLines.java Source code

Introduction

Here is the source code for WordLines.java

Source

/**
 *  * 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.hadoop.examples;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

public class WordLines {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, Text> {

        private Text word = new Text();
        String fileName = new String();
        Text output = new Text();
        String wordSearch;

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            String lineVal = itr.nextToken();
            fileName = ((FileSplit) context.getInputSplit()).getPath().getName();
            Configuration conf = context.getConfiguration();
            wordSearch = conf.get("searchWord");
            //      String [] values = {lineVal,fileName};
            output.set(lineVal + "," + fileName);
            while (itr.hasMoreTokens()) {
                String val = itr.nextToken();
                if (val.equals(wordSearch)) {
                    word.set(val);
                    context.write(word, output);
                    break;
                }
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text, Text, Text, Text> {
        //    private IntWritable result = new IntWritable(); 
        public void reduce(Text key, Iterable<String[]> values, Context context)
                throws IOException, InterruptedException {
            for (String[] val : values) {
                Text resultLines = new Text(val[0] + "," + val[1]);
                context.write(key, resultLines);
                //        sum += val.get();

            }
            //      result.set(sum);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 3) {
            System.err.println("Usage: wordlines <in> [<in>...] <SearchTerm> <out>");
            System.exit(2);
        }
        conf.set("searchWord", otherArgs[otherArgs.length - 2]);
        Job job = new Job(conf, "word lines");
        job.setJarByClass(WordLines.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        for (int i = 0; i < otherArgs.length - 2; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}