1 /**
  2  *  Licensed under the Apache License, Version 2.0 (the "License");
  3  *  you may not use this file except in compliance with the License.
  4  *  You may obtain a copy of the License at
  5  *
  6  *      http://www.apache.org/licenses/LICENSE-2.0
  7  *
  8  *  Unless required by applicable law or agreed to in writing, software
  9  *  distributed under the License is distributed on an "AS IS" BASIS,
 10  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 11  *  See the License for the specific language governing permissions and
 12  *  limitations under the License.
 13  */
 14
 15
 16 package org.apache.hadoop.examples;
 17
 18 import java.io.IOException;
 19 import java.util.StringTokenizer;
 20
 21 import org.apache.hadoop.conf.Configuration;
 22 import org.apache.hadoop.fs.Path;
 23 import org.apache.hadoop.io.IntWritable;
 24 import org.apache.hadoop.io.Text;
 25 import org.apache.hadoop.fs.FileSystem;
 26 import org.apache.hadoop.mapred.JobConf;
 27 import org.apache.hadoop.mapreduce.Job;
 28 import org.apache.hadoop.mapreduce.Mapper;
 29 import org.apache.hadoop.mapreduce.Reducer;
 30 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
 31 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 32 import org.apache.hadoop.util.GenericOptionsParser;
 33
 34 public class WordCount {
 35
 36   public static class TokenizerMapper
 37        extends Mapper<Object, Text, Text, IntWritable>{
 38
 39     private final static IntWritable one = new IntWritable(1);
 40     private Text word = new Text();
 41
 42     public void map(Object key, Text value, Context context
 43                     ) throws IOException, InterruptedException {
 44       StringTokenizer itr = new StringTokenizer(value.toString());
 45       while (itr.hasMoreTokens()) {
 46         word.set(itr.nextToken());
 47         context.write(word, one);
 48       }
 49     }
 50   }
 51
 52   public static class IntSumReducer
 53        extends Reducer<Text,IntWritable,Text,IntWritable> {
 54     private IntWritable result = new IntWritable();
 55
 56     public void reduce(Text key, Iterable<IntWritable> values,
 57                        Context context
 58                        ) throws IOException, InterruptedException {
 59       int sum = 0;
 60       for (IntWritable val : values) {
 61         sum += val.get();
 62       }
 63       result.set(sum);
 64       context.write(key, result);
 65     }
 66   }
 67
 68   public static void main(String[] args) throws Exception {
 69     Configuration conf = new Configuration();
 70     //JobConf conf=new JobConf();
 71     //
 72     //conf.setJar("org.apache.hadoop.examples.WordCount.jar");
 73    // conf.set("fs.default.name", "hdfs://Master:9000/");
 74     //conf.set("hadoop.job.user","hadoop");
 75     //指定jobtracker的ip和端口号，master在/etc/hosts中可以配置
 76    // conf.set("mapred.job.tracker","Master:9001");
 77
 78     FileSystem hdfs =FileSystem.get(conf);
 79     Path findf=new Path("/eclipse-test5/output");
 80     boolean isExists=hdfs.exists(findf);
 81     System.out.println("/eclipse-test5/output exit?"+isExists);
 82     if(isExists)
 83     {
 84         hdfs.delete(findf, true);
 85         System.out.println("delete /eclipse-test5/output");
 86
 87     }
 88
 89     String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
 90     if (otherArgs.length != 2) {
 91       System.err.println("Usage: wordcount <in> <out>");
 92       System.exit(2);
 93     }
 94     Job job = new Job(conf, "word count");
 95
 96     job.setJarByClass(WordCount.class);
 97     job.setMapperClass(TokenizerMapper.class);
 98     job.setCombinerClass(IntSumReducer.class);
 99     job.setReducerClass(IntSumReducer.class);
100     job.setOutputKeyClass(Text.class);
101     job.setOutputValueClass(IntWritable.class);
102     FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
103     FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
104     System.exit(job.waitForCompletion(true) ? 0 : 1);
105   }
106 }