使用命令行编译、打包、运行WordCount--不用eclipse

  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 import java.io.IOException;
 17 import java.util.StringTokenizer;
 18 
 19 import org.apache.hadoop.conf.Configuration;
 20 import org.apache.hadoop.fs.Path;
 21 import org.apache.hadoop.io.IntWritable;
 22 import org.apache.hadoop.io.Text;
 23 import org.apache.hadoop.fs.FileSystem;
 24 import org.apache.hadoop.mapred.JobConf;
 25 import org.apache.hadoop.mapreduce.Job;
 26 import org.apache.hadoop.mapreduce.Mapper;
 27 import org.apache.hadoop.mapreduce.Reducer;
 28 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
 29 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 30 import org.apache.hadoop.util.GenericOptionsParser;
 31 
 32 public class WordCount {
 33 
 34   public static class TokenizerMapper 
 35        extends Mapper<Object, Text, Text, IntWritable>{
 36     
 37     private final static IntWritable one = new IntWritable(1);
 38     private Text word = new Text();
 39       
 40     public void map(Object key, Text value, Context context
 41                     ) throws IOException, InterruptedException {
 42       StringTokenizer itr = new StringTokenizer(value.toString());
 43       while (itr.hasMoreTokens()) {
 44         word.set(itr.nextToken());
 45         context.write(word, one);
 46       }
 47     }
 48   }
 49   
 50   public static class IntSumReducer 
 51        extends Reducer<Text,IntWritable,Text,IntWritable> {
 52     private IntWritable result = new IntWritable();
 53 
 54     public void reduce(Text key, Iterable<IntWritable> values, 
 55                        Context context
 56                        ) throws IOException, InterruptedException {
 57       int sum = 0;
 58       for (IntWritable val : values) {
 59         sum += val.get();
 60       }
 61       result.set(sum);
 62       context.write(key, result);
 63     }
 64   }
 65 
 66   public static void main(String[] args) throws Exception {
 67     Configuration conf = new Configuration(); 
 68     //JobConf conf=new JobConf();
 69     //
 70     //conf.setJar("org.apache.hadoop.examples.WordCount.jar");
 71    // conf.set("fs.default.name", "hdfs://Master:9000/");  
 72     //conf.set("hadoop.job.user","hadoop");    
 73     //指定jobtracker的ip和端口号，master在/etc/hosts中可以配置  
 74    // conf.set("mapred.job.tracker","Master:9001"); 
 75    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
 76     if (otherArgs.length != 2) {
 77       System.err.println("Usage: wordcount <in> <out>");
 78       System.exit(2);
 79     }
 80 
 81     FileSystem hdfs =FileSystem.get(conf);
 82     Path findf=new Path(otherArgs[1]);
 83     boolean isExists=hdfs.exists(findf);
 84     System.out.println("exit?"+isExists);
 85     if(isExists)
 86     {
 87         hdfs.delete(findf, true);
 88         System.out.println("delete output");
 89         
 90     }
 91   
 92 
 93     Job job = new Job(conf, "word count");
 94     
 95     job.setJarByClass(WordCount.class);
 96     job.setMapperClass(TokenizerMapper.class);
 97     job.setCombinerClass(IntSumReducer.class);
 98     job.setReducerClass(IntSumReducer.class);
 99     job.setOutputKeyClass(Text.class);
100     job.setOutputValueClass(IntWritable.class);
101     FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
102     FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
103     System.exit(job.waitForCompletion(true) ? 0 : 1);
104   }
105 }

FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

 FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));