WordCount单词计数

课程链接：Hadoop大数据平台架构与实践--基础篇

计算文件中出现每个单词的频数，输入结果按照字母顺序进行排序

Map过程（切分，中间结果：Key-Value）

Reduce过程（合并、归约后经过Hash,所有单词放在同一个结点）

步骤：

1. 编写WordCount.java，包含Mapper类和Reduce类
2. 编译WordCount.java,javac -classpath
3. 打包jar -cvf WordCount.jar classes/*
4. 作业提交 hadoop jar WordCount.jar WordCount input output

 WordCount.java

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.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class WordCount {
    public static class WordCountMap extends
            Mapper<LongWritable, Text, Text, IntWritable> {
        private final IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer token = new StringTokenizer(line);
            while (token.hasMoreTokens()) {
                word.set(token.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class WordCountReduce extends
            Reducer<Text, IntWritable, Text, IntWritable> {
        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = new Job(conf);
        job.setJarByClass(WordCount.class);
        job.setJobName("wordcount");
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setMapperClass(WordCountMap.class);
        job.setReducerClass(WordCountReduce.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}

案例：利用MapReduce进行排序

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

public class Sort {
    public static class Map extends
            Mapper<Object, Text, IntWritable, IntWritable> {
        private static IntWritable data = new IntWritable();
        
        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            String line = value.toString();
            data.set(Integer.parseInt(line));
            context.write(data, new IntWritable(1));
        }
    }

    public static class Reduce extends
            Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {
        private static IntWritable linenum = new IntWritable(1);
        public void reduce(IntWritable key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            for (IntWritable val : values) {
                context.write(linenum, key);
                linenum = new IntWritable(linenum.get() + 1);
            }
        }
    }

    public static class Partition extends Partitioner<IntWritable, IntWritable> {

        @Override
        public int getPartition(IntWritable key, IntWritable value,
                int numPartitions) {
            int MaxNumber = 65223;
            int bound = MaxNumber / numPartitions + 1;
            int keynumber = key.get();
            for (int i = 0; i < numPartitions; i++) {
                if (keynumber < bound * i && keynumber >= bound * (i - 1))
                    return i - 1;
            }
            return 0;
        }
    }

    /**
     * @param args
     */

    public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args)
                .getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage WordCount <int> <out>");
            System.exit(2);
        }
        Job job = new Job(conf, "Sort");
        job.setJarByClass(Sort.class);
        job.setMapperClass(Map.class);
        job.setPartitionerClass(Partition.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

}