Java开发简单Hadoop程序

pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"
>

  <modelVersion>4.0.0</modelVersion>

  <groupId>com.kovansys.test</groupId>
  <version>1.1.0</version>

  <artifactId>hadoop_test</artifactId>

  <packaging>jar</packaging>

  <properties>

    <maven.compiler.source>1.8</maven.compiler.source>
    <maven.compiler.target>1.8</maven.compiler.target>

    <hadoop.version>3.2.0</hadoop.version>
    <java.encoding>UTF-8</java.encoding>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>

  </properties>
  <build>
    <directory>target</directory>
    <plugins>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-compiler-plugin</artifactId>
        <version>3.8.0</version>
      </plugin>
    </plugins>
  </build>

  <dependencies>
    <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-client</artifactId>
      <version>${hadoop.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-mapreduce-client-core</artifactId>
      <version>${hadoop.version}</version>
    </dependency>

  </dependencies>

</project>

 

    WordCountStarter类

package hadoop;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 WordCountStarter {
  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: WordCountStarter <in> <out>");
      System.exit(2);
    }
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCountStarter.class);
    job.setMapperClass(WordCountMapper.class);
    job.setCombinerClass(WordCountReducer.class);
    job.setReducerClass(WordCountReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

 

   WordCountMapper类

package hadoop;

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

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

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

  public void map(Object key, Text value, Mapper<Object, Text, Text, LongWritable>.Context context) throws IOException, InterruptedException {
    StringTokenizer itr = new StringTokenizer(value.toString());
    while (itr.hasMoreTokens()) {
      this.word.set(itr.nextToken());
      context.write(this.word, one);
    }
  }
}

 

    WordCountReducer类

    

package hadoop;

import java.io.IOException;

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

public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
  private LongWritable result = new LongWritable();

  public void reduce(Text key, Iterable<LongWritable> values, Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
    int sum = 0;
    for (LongWritable val : values) {
      sum += val.get();
    }
    this.result.set(sum);
    context.write(key, this.result);
  }
}

 

   #打包

   $mvn clean install

   #将生成的jar包放到服务器上 如/opt/temp/hadoop_test-1.1.0.jar

   #运行mapreducer任务

   bin/hadoop jar /opt/temp/hadoop_test-1.1.0.jar hadoop.WordCountStarter  input output

   #查看结果

   bin/hdfs dfs -cat output/*