com.mycompany.keywordsearch.KeywordSearch.java Source code

Introduction

Here is the source code for com.mycompany.keywordsearch.KeywordSearch.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package com.mycompany.keywordsearch;

/**
 *
 * @author ril
 */
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

public class KeywordSearch {
    public static class TokenizerMapper extends Mapper<Text, Text, Text, IntWritable> {
        private final static IntWritable num = new IntWritable();
        private String keyword;

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            keyword = context.getConfiguration().get(KEYWORD);
        }

        @Override
        public void map(Text key, Text value, Context context) throws IOException, InterruptedException {
            if (keyword == null) {
                return;
            }
            int index = value.find(keyword), counter = 0;
            while (index < value.getLength() && index != -1) {
                ++counter;
                index = value.find(keyword, index + keyword.length());
            }

            num.set(counter);
            context.write(key, num);
        }
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private final IntWritable result = new IntWritable();

        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            if (sum < 3)
                return;
            result.set(sum);
            context.write(key, result);
        }
    }

    private static void clearOutput(Configuration conf, Path path) throws IOException {
        FileSystem fs = FileSystem.get(conf);
        if (fs.exists(path)) {
            fs.delete(path, true);
        }
    }

    private static final String KEYWORD = "course.keyword";

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        conf.set(FileInputFormat.INPUT_DIR_RECURSIVE, String.valueOf(true));
        Path input = new Path(args[0]);
        Path output = new Path(args[1]);
        BufferedReader in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
        System.out.print("Keyword:\t");
        conf.set(KEYWORD, in.readLine());
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(KeywordSearch.class);
        job.setInputFormatClass(TextInputFormatV2.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        clearOutput(conf, output);
        FileInputFormat.addInputPath(job, input);
        FileOutputFormat.setOutputPath(job, output);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}