hadoop 單機下運行wordcount

關於單機版的配置，eclipse環境搭建，以後再補充吧

首先是程序

project： wordcunt

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public 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);
        }
    }
}


import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public 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);
    }
}


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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

      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.setCombinerClass(IntSumReducer.class);
            job.setReducerClass(IntSumReducer.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
            FileInputFormat.addInputPath(job, new Path("/tmp/input"));
            FileOutputFormat.setOutputPath(job, new Path("/tmp/output"));
            System.exit(job.waitForCompletion(true) ? 0 : 1);
          }

}

將項目export成爲jar包，注意選擇運行類爲WordCount

在hadoop機器上：

[admin@host WordCount]$ vim input1.txt
Hello, i love china
are you ok?
[admin@host WordCount]$ vim input2.txt
hello, i love word
You are ok

　　在hadoop上新建目錄，和put程序運行所需要的輸入文件:

hadoop fs -mkdir /tmp/input
hadoop fs -mkdir /tmp/output
hadoop fs -put input1.txt /tmp/input/
hadoop fs -put input2.txt /tmp/input/

 

執行：

hadoop jar wordcount.jar WordCount

 

查看效果：

hadoop fs -ls /tmp/output/

hadoop fs -cat /tmp/output/part-r-00000

OK！