hadoop WordCount

最新推荐文章于 2024-11-19 22:39:34 发布

自由自在梦在何方

最新推荐文章于 2024-11-19 22:39:34 发布

阅读量158

点赞数

CC 4.0 BY-SA版权

分类专栏：大数据 python及shell

本文链接：https://blog.youkuaiyun.com/lifestxx/article/details/81590294

python及shell 同时被 2 个专栏收录

84 篇文章

订阅专栏

大数据

39 篇文章

订阅专栏

本文介绍如何使用Hadoop实现WordCount程序，包括配置依赖、编写MapReduce任务代码及运行程序的具体步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1 pom.xml

<dependencies>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>2.7.4</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>2.7.4</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-mapreduce-client-core</artifactId>
        <version>2.7.4</version>
    </dependency>
</dependencies>

2 见hadoop自带源码

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;

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


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);
    }
}

mvn package

3 执行

hdfs dfs -mkdir -p /user/data/input

hdfs dfs -mkdir -p /user/data/output

hdfs dfs -ls /user/data/input/

hdfs dfs -put ./file.txt /user/data/input/

hdfs dfs -cat /user/data/input/file.txt

hadoop jar MapRed-1.0-SNAPSHOT.jar WordCount /user/data/input/ /user/data/output

hdfs dfs -cat /user/data/output/part-r-00000