Hadoop Day 2

example 1 word count:
/**
 * 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;

public class WordCount {

  public static class TokenizerMapper                         //继承Mapper类实现map方法
       extends Mapper<Object, Text, Text, IntWritable>{
    
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
      
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
    
  public static class IntSumReducer                           //继承并Reducer类并实现reduce方法
       extends Reducer<Text,IntWritable,Text,IntWritable> {  
    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(key, result);
    }
  }

  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> [<in>...] <out>");
      System.exit(2);
    }
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

example 2 :对电话清单进行整理
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.StringTokenizer;
import javax.sound.midi.SysexMessage;


//import javax.tools.Tool;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.mapred.TextOutputFormat;
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.util.ToolRunner;

import com.sun.org.apache.xml.internal.serialize.OutputFormat;

public class Test_2 extends Configured implements Tool{
    enum Counter
    {
        LINESKIP, //出错的行数
    }
    public static class Map extends Mapper<LongWritable, Text, Text, Text>{
        @Override
        public void map(LongWritable key, Text value,
                Mapper<LongWritable, Text, Text, Text>.Context context)
                throws IOException, InterruptedException{
            // TODO Auto-generated method stub
            try {
                String line = value.toString();
                String[] linesplit = line.split(" ");
                String anum = linesplit[0];
                String bnum = linesplit[1];
                context.write(new Text(bnum), new Text(anum));
            } catch (java.lang.ArrayIndexOutOfBoundsException e) {
                // TODO: handle exception
                context.getCounter(Counter.LINESKIP).increment(1);
                return;
            }       
        }
    }
    public static class Reduce extends Reducer<Text, Text, Text, Text>{
        public void reduce(Text key,Iterable<Text> values,Context context) throws IOException, InterruptedException
        {
            String valueString;
            String out="";
            for (Text value:values) {
                valueString = value.toString();
                out += valueString+"|"; 
            }
            context.write(key, new Text(out));
        }
    }
    
    public int run(String[] args) throws Exception {
        Configuration conf = getConf();
        Job job = new Job(conf, "Test_2");
        job.setJarByClass(Test_2.class);
        for (int i = 0; i < args.length-1; i++) {
            FileInputFormat.setInputPaths(job, new Path(args[i]));
        }
        FileOutputFormat.setOutputPath(job, new Path(args[args.length-1]));
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
//      job.setOutputFormatClass(TextOutputFormat.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        job.waitForCompletion(true);
        return job.isSuccessful()?0:1;
    };
    public static void main(String[] args) throws Exception {
        System.out.println(args.length);
        int res = ToolRunner.run(new Configuration(),new Test_2(),args);
        System.exit(res);
    }
}