Hadoop学习笔记——WordCount
Posted tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Hadoop学习笔记——WordCount相关的知识，希望对你有一定的参考价值。
1.在IDEA下新建工程,选择from Mevan
GroupId:WordCount
ArtifactId:com.hadoop.1st
Project name:WordCount
2.pom.xml文件
<?xml version="1.0" encoding="UTF-8"?>
<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>WordCount</groupId>
<artifactId>com.hadoop.1st</artifactId>
<version>1.0-SNAPSHOT</version>
<repositories>
<repository>
<id>apache</id>
<url>http://maven.apache.org</url>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>1.2.1</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.1</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<artifactId>maven-dependency-plugin</artifactId>
<configuration>
<excludeTransitive>false</excludeTransitive>
<stripVersion>true</stripVersion>
<outputDirectory>./lib</outputDirectory>
</configuration>
</plugin>
</plugins>
</build>
</project>
3.main/java目录下新建WordCount.java文件
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;
import java.io.IOException;
import java.util.StringTokenizer;
/**
* Created by common on 17-3-26.
*/
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);
}
}
4.在src同级目录下新建input目录,以及下面的test.segmented文件
test.segmented文件内容
aa bb cc dd aa cc ee ff ff gg hh aa
4.在run configuration下设置运行方式为Application
5.运行java文件,将会生成output目录,part-r-00000为运行的结果,下次运行必须删除output目录,否则会报错
以上是关于Hadoop学习笔记——WordCount的主要内容，如果未能解决你的问题，请参考以下文章
hadoop学习笔记：运行wordcount对文件字符串进行统计案例