hadoop之重写word count案例

目录

1．需求

2、建立maven工程编写代码

1.配置在pom.xml文件中添加如下依赖

编写程序

（1）编写Mapper类

（2）编写Reducer类

（3）编写Driver驱动类

3．本地测试

4、集群上测试

---

1．需求

在给定的文本文件中统计输出每一个单词出现的总次数

（1）输入数据
ss ss
cls cls
jiao shi wangwu cls
banzhang
xue
hadoop

（2）期望输出数据

banzhang 1

cls   3

hadoop   1

jiao  1

ss    2

xue  1

 shi   1

wangwu   1

2、建立maven工程编写代码

1.配置在pom.xml文件中添加如下依赖

<dependencies>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>RELEASE</version>
		</dependency>
		<dependency>
			<groupId>org.apache.logging.log4j</groupId>
			<artifactId>log4j-core</artifactId>
			<version>2.8.2</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-common</artifactId>
			<version>2.7.2</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-client</artifactId>
			<version>2.7.2</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-hdfs</artifactId>
			<version>2.7.2</version>
		</dependency>
</dependencies>

2.在项目的src/main/resources目录下，新建一个文件，命名为“log4j.properties”，在文件中填入。

log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

编写程序

（1）编写Mapper类

package com.caigua.mapreduce;
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 WordcountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	
	Text k = new Text();
	IntWritable v = new IntWritable(1);
	
	@Override
	protected void map(LongWritable key, Text value, Context context)	throws IOException, InterruptedException {
		
		// 1 获取一行
		String line = value.toString();
		
		// 2 切割
		String[] words = line.split(" ");
		
		// 3 输出
		for (String word : words) {
			
			k.set(word);
			context.write(k, v);
		}
	}
}

（2）编写Reducer类

package com.caigua.mapreduce.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordcountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

int sum;
IntWritable v = new IntWritable();

	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
		
		// 1 累加求和
		sum = 0;
		for (IntWritable count : values) {
			sum += count.get();
		}
		
		// 2 输出
       v.set(sum);
		context.write(key,v);
	}
}

（3）编写Driver驱动类

package com.caigua.mapreduce.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.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 WordcountDriver {

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

		// 1 获取配置信息以及封装任务
		Configuration configuration = new Configuration();
		Job job = Job.getInstance(configuration);

		// 2 设置jar加载路径
		job.setJarByClass(WordcountDriver.class);

		// 3 设置map和reduce类
		job.setMapperClass(WordcountMapper.class);
		job.setReducerClass(WordcountReducer.class);

		// 4 设置map输出
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);

		// 5 设置最终输出kv类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		// 6 设置输入和输出路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		// 7 提交
		boolean result = job.waitForCompletion(true);

		System.exit(result ? 0 : 1);
	}
}

3．本地测试

（1）如果电脑系统是win7的就将win7的hadoop jar包解压到非中文路径，并在Windows环境上配置HADOOP_HOME环境变量。如果是电脑win10操作系统，就解压win10的hadoop jar包，并配置HADOOP_HOME环境变量。（具体的本地环境配置就不再过多阐述）

集群上测试

4、集群上测试

用maven打jar包，需要添加的打包插件依赖

<build>
		<plugins>
			<plugin>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>2.3.2</version>
				<configuration>
					<source>1.8</source>
					<target>1.8</target>
				</configuration>
			</plugin>
			<plugin>
				<artifactId>maven-assembly-plugin </artifactId>
				<configuration>
					<descriptorRefs>
						<descriptorRef>jar-with-dependencies</descriptorRef>
					</descriptorRefs>
					<archive>
						<manifest>
							<mainClass>com.caigua.mr.WordcountDriver</mainClass>
						</manifest>
					</archive>
				</configuration>
				<executions>
					<execution>
						<id>make-assembly</id>
						<phase>package</phase>
						<goals>
							<goal>single</goal>
						</goals>
					</execution>
				</executions>
			</plugin>
		</plugins>
	</build>

（1）将程序打成jar包，然后拷贝到Hadoop集群中

步骤详情：右键->Run as->maven install。等待编译完成就会在项目的target文件夹中生成jar包。如果看不到。在项目上右键-》Refresh，即可看到。修改不带依赖的jar包名称为wc.jar，并拷贝该jar包到Hadoop集群。

（2）启动Hadoop集群

（3）执行WordCount程序

[atguigu@hadoop102 software]$ hadoop jar  wc.jar com.caigua.wordcount.WordcountDriver /user/atguigu/input /user/atguigu/output