Hadoop MapReduce实现单词计数(Word Count)

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 {
        //每次处理一行，一个mapper里的value为一行,key为该行在文件中的偏移量
        StringTokenizer iter = new StringTokenizer(value.toString());
        while (iter.hasMoreTokens()) {
            word.set(iter.nextToken());
            // 向context中写入<word, 1>
            context.write(word, one);
            System.out.println(word);
        }
    }
}

 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);
        }
    }

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.FileSystem;
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;
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 {
        //每次处理一行，一个mapper里的value为一行,key为该行在文件中的偏移量
            StringTokenizer iter = new StringTokenizer(value.toString());
            while (iter.hasMoreTokens()) {
                word.set(iter.nextToken());
                // 向context中写入<word, 1>
                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();
        Job job = Job.getInstance(conf, "word_count");

        job.setJarByClass(WordCount.class);

        job.setMapperClass(TokenizerMapper.class);
        //此处的Combine操作意为即第每个mapper工作完了先局部reduce一下，最后再全局reduce
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //第0个参数是输入目录，第1个参数是输出目录
        //先判断output path是否存在，如果存在则删除
        Path path = new Path(args[1]);// 
        FileSystem fileSystem = path.getFileSystem(conf);
        if (fileSystem.exists(path)) {
            fileSystem.delete(path, true);
        }

        //设置输入目录和输出目录
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }
}

    ...
  <!-- 集中定义版本号 -->
  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>17</maven.compiler.source>
    <maven.compiler.target>17</maven.compiler.target>
    <hadoop.version>3.3.1</hadoop.version>
  </properties>
  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.11</version>
      <scope>test</scope>
    </dependency>
    <!-- 导入hadoop依赖环境 -->
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-mapreduce-client-core</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-yarn-api</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
  </dependencies>
  ...
</project>

...
"args": [
    "input",
    "output"
],
...