hadoop MapReduce java示例

Posted 2021-01-11

wordcount工作流程
input-> 拆分Split->映射map->派发Shuffle->缩减reduce->output
hadoop jar /usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.3.jar wordcount 10803060234.txt /output

package wordcount;

import java.io.IOException;

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

public class Test {

public Test() {
    // TODO Auto-generated constructor stub
}

public static void main(String[] args) throws Exception {
    // TODO Auto-generated method stub

    Configuration conf = new Configuration();
    conf.set("fs.defaultFS","hdfs://172.26.19.40:9000");
    conf.set("mapreduce.job.jar", "target/wc.jar");
    conf.set("mapreduce.framework.name", "yarn");
    conf.set("yarn.resourcemanager.hostname", "hmaster");
    conf.set("mapreduce.app-submission.cross-platform", "true");
    Job job = Job.getInstance(conf);
    job.setMapperClass(WordMapper.class);
    job.setReducerClass(WordReducer.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

    FileInputFormat.setInputPaths(job, "");
    FileOutputFormat.setOutputPath(job, new Path(""));

    job.waitForCompletion(true);
}

}

package wordcount;

import java.io.IOException;

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

public class WordMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
        throws IOException, InterruptedException {
    String lineValue = value.toString();
    String[] words = lineValue.split(" ");
    IntWritable cIntWritable = new IntWritable(1);
    for(String word : words) {
        context.write(new Text(word), cIntWritable);
    }
}

}

package wordcount;

import java.io.IOException;

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

public class WordReducer extends Reducer<Text, IntWritable, Text, LongWritable> {

@Override
protected void reduce(Text key, Iterable<IntWritable> values,
        Reducer<Text, IntWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {

     Long tmpCount = 0L;
     for(IntWritable value : values) {
         tmpCount = tmpCount + value.get();
     }

     context.write(key, new LongWritable(tmpCount));

}

}

<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.skcc</groupId>
<artifactId>wordcount</artifactId>
<version>0.0.1-SNAPSHOT</version>
<name>wordcount</name>
<description>count the word</description>

<properties>
    <project.build.sourceencoding>UTF-8</project.build.sourceencoding>
    <hadoop.version>2.7.3</hadoop.version>
</properties>
<dependencies>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.12</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
</dependencies>

</project>