WordCount案例实操
WordCount案例实操
环境准备：
配置JDK Hadoop环境变量
WordCount案例：
maven
<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>
log4j.properties
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
Mapper
/**
* map阶段
* LongWritable 输入数据的key
* Text 输入数据的value
* Text 输出数据key的类型
* IntWritable 输出的数据value类型
*/
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 {
// 获取一行
String line = value.toString();
// 根据空格切割单词
String[] words = line.split(" ");
// 循环写出
for (String word:words) {
k.set(word);
context.write(k, v);
}
}
}
Reducer
/**
* reducer阶段
*/
public class WordcountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
IntWritable v = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
// 累加求和
for (IntWritable value: values) {
sum += value.get();
}
v.set(sum);
// 写出
context.write(key, v);
}
}
Driver
public class WordcountDriver {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
// 获取Job对象
Job job = Job.getInstance(conf);
// 设置jar存储位置
job.setJarByClass(WordcountDriver.class);
// 关联Mapper和Reducer类
job.setMapperClass(WordcountMapper.class);
job.setReducerClass(WordcountReducer.class);
// 设置Mapper阶段输出数据的key和value类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// 设置最终数据输出的key和value类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// 设置输入路径和输出路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//job.setInputFormatClass(CombineTextInputFormat.class);
// 虚拟存储切片最大值设置20m
//CombineTextInputFormat.setMaxInputSplitSize(job, 20971520);
//job.setNumReduceTasks(2);
// 提交job
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
案例在集群上运行
1）将程序打包
maven添加打包插件
<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.atguigu.mr.wordcount.WordcountDriver</mainClass>
</manifest>
</archive>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
打包
maven install
2）将打包jar复制到Hadoop服务器
3）运行
$ hadoop jar wordcount.jar com.atguigu.mr.wordcount.WordcountDriver /user/atguigu/input /user/atguigu/output
