chaohParse.searchWord.java Source code

Introduction

Here is the source code for chaohParse.searchWord.java

Source

/**
 *  Licensed 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 chaohParse;

import java.io.IOException;

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;

public class searchWord {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            //System.out.println("begin mapper");
            String[] indexString = value.toString().split("\t");// get the work and passage

            String searchString = "hello world";
            String[] searchSplit = searchString.split(" ");

            for (String val : searchSplit) {
                if (val == indexString[0]) {
                    String[] passageSplit = indexString[1].split("$");
                    int i = passageSplit.length - 1;
                    while (i >= 0) {
                        context.write(new Text(passageSplit[i]), one);
                        i--;
                    }
                }
            }
        }
    }

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

        private IntWritable result = new IntWritable();

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

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }
        Job job = new Job(conf, "word count");
        job.setJarByClass(wordcount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Integer.class);

        job.setReducerClass(IntSumReducer.class);

        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(Text.class);

        job.setInputFormatClass(FileInputFormat.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}