Hadoop实例学习(四)Mapreduce词频统计

---

创建maven项目

pom.xml添加依赖

<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.1.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.1.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>3.1.4</version>
        </dependency>
</dependencies>

添加log文件

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

编写类

编写Mapper类

package mapper;
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;
/**
 * @author 公羽
 * @time : 2020/10/22 20:20
 * @File : Mapper.java
 */
class WcMapper 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);
        }
    }
}

编写Reducer类

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

/**
 * @author 公羽
 * @time : 2020/10/22 20:23
 * @File : Reducer.java
 */
class WcReducer 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);
    }
}

编写Driver驱动

package mapper;
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;
/**
 * @author 公羽
 * @time : 2020/10/22 20:24
 * @File : Driver.java
 */
public class WcDriver {

    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(WcDriver.class);

        // 3 设置map和reduce类
        job.setMapperClass(WcMapper.class);
        job.setReducerClass(WcReducer.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);
    }
}

!!!不能直接运行因为还没设置输入和输出路径

运行结果

!会遇见的问题

常见错误

Hadoop启动报错org.apache.hadoop.io.nativeio.NativeIO$POSIX.stat(Ljava/lang/String；)Lorg/apache/hadoop/io

产生原因及解决方法

原因是hadoop.dll文件版本的问题，版本对应不上，我的hadoop是3.1.4的，但是用的是hadoop3.0.0的hadoop.dll文件版本对应不上，换成hadoop3.1.x以上的hadoop.dll文件就行

hadoop3.1.1版本的hadoo.dll