WordCount

pom WordCountMapper.java WordCountReducer.java WordCountDriver.java

POM

<properties>
	<hadoop.version>2.6.0</hadoop.version>
</properties>

<dependencies>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-mapreduce-client-core</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-mapreduce-client-common</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-mapreduce-client-jobclient</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-common</artifactId>
		<version>${hadoop.version}</version>
	</dependency>
	<dependency>
		<groupId>org.apache.hadoop</groupId>
		<artifactId>hadoop-hdfs</artifactId>
		<version>${hadoop.version}</version>
	</dependency>

	<!-- https://mvnrepository.com/artifact/org.apache.mrunit/mrunit -->
	<dependency>
		<groupId>org.apache.mrunit</groupId>
		<artifactId>mrunit</artifactId>
		<version>1.1.0</version>
		<!--<scope>test</scope>-->
		<!--不加导包可能失败-->
		<classifier>hadoop2</classifier>
	</dependency>

</dependencies>

 

---

 

WordCountMapper.java

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;

/**
 * KEYIN：默认情况下，是mr框架所读到的一行文本的起始偏移量，Long; 在hadoop中有自己的更精简的序列化接口，所以不直接用Long，而是用LongWritable
 * VALUEIN：默认情况下，是mr框架所读到的一行文本内容，String;此处用Text
 *
 * KEYOUT：是用户自定义逻辑处理完成之后输出数据中的key,在此处是单词，String；此处用Text
 * VALUEOUT：是用户自定义逻辑处理完成之后输出数据中的value，在此处是单词次数，Integer，此处用IntWritable
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
    /**
     * map阶段的业务逻辑就写在自定义的map()方法中
     * maptask会对每一行输入数据调用一次我们自定义的map()方法
     */
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 1 将maptask传给我们的文本内容先转换成String
        String line = value.toString();

        // 2 根据空格将这一行切分成单词
        String[] words = line.split(" ");

        // 3 将单词输出为<单词，1>
        for(String word:words){
            // 将单词作为key，将次数1作为value,以便于后续的数据分发，可以根据单词分发，以便于相同单词会到相同的reducetask中
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

WordCountReducer.java

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

/**
 * KEYIN , VALUEIN 对应mapper输出的KEYOUT, VALUEOUT类型
 *
 * KEYOUT，VALUEOUT 对应自定义reduce逻辑处理结果的输出数据类型 KEYOUT是单词 VALUEOUT是总次数
 */
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
	/**
	 * key，是一组相同单词kv对的key
	 */
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
		int count = 0;

		// 1 汇总各个key的个数
		for(IntWritable value:values){
			count +=value.get();
		}

		// 2输出该key的总次数
		context.write(key, new IntWritable(count));
	}
}

WordCountDriver.java

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;

//        Java类型   <--->   Hadoop Writable类型
//        boolean            BooleanWritable
//        byte               ByteWritable
//        int                IntWritable
//        float	             FloatWritable
//        long	             LongWritable
//        double	         DoubleWritable
//        string	         Text
//        map	             MapWritable
//        array	             ArrayWritable

/**
 * 驱动主程序
 */
public class WordCountDriver {

	public static void main(String[] args) throws Exception {
        // 1 获取配置信息，或者job对象实例
        Configuration configuration = new Configuration();
        // 即使没有下面这行,也可以本地运行。因\hadoop-mapreduce-client-core.jar!\mapred-default.xml 中默认的参数就是 local
        configuration.set("mapreduce.framework.name","local");

        Job job = Job.getInstance(configuration);

        // 2 指定本次mr job jar包运行主类
        job.setJarByClass(WordCountDriver.class);

        // 3 指定本业务job要使用的mapper/Reducer业务类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 指定mapper输出数据的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 指定最终输出的数据的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 指定job的输入原始文件所在目录，输入目录下可放多个文件，eg：data1.txt  data2.txt ......
        FileInputFormat.setInputPaths(job, new Path("C:\\Users\\Administrator\\Desktop\\input"));
        // 7 指定文件输出目录，注意：输出目录output在程序执行之前并不存在，存在则报错
        FileOutputFormat.setOutputPath(job, new Path("C:\\Users\\Administrator\\Desktop\\output"));

        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);
	}

}

 

---

 

若报错：

Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z

请在windows下配置hadoop环境后重启。 hadoop的windows压缩包

 

代码见GitHub：https://github.com/666wg/mapreduce