Hadoop WordCount代码

来源：互联网发布：内容管理系统cms 开源编辑：程序博客网时间：2024/05/01 15:57
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        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        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 = Job.getInstance(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);  }}
0 0