采用反编译工具反编译源码,发现WordCount案例有Map类、Reduce类和驱动类。且数据的类型是Hadoop自身封装的序列化类型。
atguigu atguigu
ss ss
cls cls
jiao
banzhang
xue
hadoop
2)期望输出数据
atguigu 2
banzhang 1
cls 2
hadoop 1
jiao 1
ss 2
xue 1
<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
package com.until.mapreduce;
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;
import java.nio.MappedByteBuffer;
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.until.mapreduce;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.junit.Test;
import java.io.IOException;
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.until.mapreduce;
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 {
static {
try {
System.load("C:/mine/software/hadoop-2.7.2/bin/hadoop.dll");
} catch (UnsatisfiedLinkError e) {
System.err.println("Native code library failed to load.\n" + e);
System.exit(1);
}
}
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));
}
}
d:/input/hello.txt d:/output1
然后直接运行
可能会遇到错误:
org.apache.hadoop.io.nativeio.NativeIO$Windows.createDirectoryWithMode0(Ljava/lang/String;I)V错误解决方案
<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.until.mapreduce.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 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
[root@hadoop200 software]# hadoop jar wc.jar com.until.mapreduce.WordcountDriver /user/hadoop/input /user/hadoop/output