WordCount案例实操
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(test.txt)
(2)期望输出数据
flume 2
hadoop 2
hive 1
html 1
java 1
php 2
spark 1
2)需求分析
按照MapReduce编程规范,分别编写Mapper,Reducer,Driver。
3)环境准备
(1)创建maven工程
(2)在pom.xml文件中添加如下依赖
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>2.12.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>3.1.3</version>
</dependency>
</dependencies>
(2)在项目的src/main/resources目录下,新建一个文件,命名为"log4j2.xml",在文件中填入。
<?xml version="1.0" encoding="UTF-8"?>
<Configuration status="error" strict="true" name="XMLConfig">
<Appenders>
<!-- 类型名为Console,名称为必须属性 -->
<Appender type="Console" name="STDOUT">
<!-- 布局为PatternLayout的方式,
输出样式为[INFO] [2020-01-01 00:00:00][org.test.Console]I'm here -->
<Layout type="PatternLayout"
pattern="[%p] [%d{yyyy-MM-dd HH:mm:ss}][%c{10}]%m%n" />
</Appender>
</Appenders>
<Loggers>
<!-- 可加性为false -->
<Logger name="test" level="info" additivity="false">
<AppenderRef ref="STDOUT" />
</Logger>
<!-- root loggerConfig设置 -->
<Root level="info">
<AppenderRef ref="STDOUT" />
</Root>
</Loggers>
</Configuration>
4)编写程序
(1)编写Mapper类
package com.qinjl.mapreduce.wordcount;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* KEYIN, map阶段输入K的类型 LongWritalbe
* VALUEIN, map阶段输入V的类型 Text
* KEYOUT, map阶段输出K的类型 Text
* VALUEOUT,map阶段输出V的类型 intwritable
*/
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private Text outK = new Text();
private IntWritable outV = new IntWritable(1);
//参数解读 1、偏移量 2、输入的一行数据 3、上下文对象
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//1 获取一行数据,并转换成字符串
String line = value.toString();
//2 切割一行数据,按空格切割
String[] words = line.split(" ");
//3 遍历words数组
for (String word : words) {
//封装outK,outV
outK.set(word);
//输出
context.write(outK, outV);
}
}
}
(2)编写Reducer类
package com.qinjl.mapreduce.wordcount;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* KEYIN, reduce阶段输入K的类型 Text
* VALUEIN, reduce阶段输入V的类型 IntWritable
* KEYOUT, reduce阶段输出K的类型 Text
* VALUEOUT,reduce阶段输出V的类型 intwritable
*/
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable outV = new IntWritable();
//参数解读 1.单词 2.相同单词的一组数据 3 上下文对象
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
//遍历相同单词的一组数据 说白了就是一个个的1 (1,1)
for (IntWritable value : values) {
int i = value.get();
sum += i;
}
//封装outK outV
outV.set(sum);
//写出
context.write(key,outV);
}
}
(3)编写Driver驱动类
package com.qinjl.mapreduce.wordcount;
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;
import java.io.IOException;
public class WordCountDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
//1 获取job对象
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//2 设置本Driver程序的类
job.setJarByClass(WordCountDriver.class);
//3 关联mapper和reducer
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
//4 设置map端输出的KV类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
//5 设置mr程序的最终输出KV类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//6 设置程序的输入输出路径
FileInputFormat.setInputPaths(job, new Path("D:\\hadoop\\inputword"));
FileOutputFormat.setOutputPath(job, new Path("D:\\hadoop\\output"));
//7 提交job
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
5)本地测试
(1)需要首先配置好HADOOP_HOME变量以及Windows运行依赖
(2)在IDEA上运行程序
6)集群上测试
(0)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>3.6.1</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>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
- 注意:如果工程上显示红叉。在项目上右键->maven->Reimport即可。
(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
[qinjl@hadoop102 software]$ hadoop jar wc.jar
com.qinjl.wordcount.WordcountDriver /user/qinjl/input /user/qinjl/output
7)在Windows上向集群提交任务
(1)添加必要配置信息
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();
//设置HDFS NameNode的地址
configuration.set("fs.defaultFS", "hdfs://hadoop102:9820");
// 指定MapReduce运行在Yarn上
configuration.set("mapreduce.framework.name","yarn");
// 指定mapreduce可以在远程集群运行
configuration.set("mapreduce.app-submission.cross-platform","true");
//指定Yarn resourcemanager的位置
configuration.set("yarn.resourcemanager.hostname","hadoop103");
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);
}
}
(2)编辑任务配置
1)检查第一个参数 Main class是不是我们要运行的类的全类名,如果不是的话一定要修改!
2)在VM options后面加上 :-DHADOOP\_USER\_NAME=qinjl
3)在Program arguments后面加上两个参数分别代表输入输出路径,两个参数之间用空格隔开。
- 如:
hdfs://hadoop102:9820/input
hdfs://hadoop102:9820/output
(3)打包,并将Jar包设置到Driver中
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();
configuration.set("fs.defaultFS", "hdfs://hadoop102:9820");
configuration.set("mapreduce.framework.name","yarn");
configuration.set("mapreduce.app-submission.cross-platform","true");
configuration.set("yarn.resourcemanager.hostname","hadoop103");
Job job = Job.getInstance(configuration);
// 2 设置jar加载路径
//job.setJarByClass(WordCountDriver.class);
job.setJar("E:\IdeaProjects\mapreduce\target\mapreduce-1.0-SNAPSHOT.jar");
// 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);
}
}
(4)提交并查看结果