MapRaduse应用

(1) 首先启动hadoop

 

 

 

(2) 配置两个文本文件Txte1.txt、Txte2.txt并分别输入内容

 

 

 

 

（3）在hdfs下创建文件、并把两个文本内容加载上去

 

 

 

 

 

（4）在IDEA软件中配置pom文件

 

（5）重新创建一个类WordconutText在hdfstest包下面,并配置内容

 

 

 

（6）运行程序可以在虚拟机中查看到内容

 

 

 

相关代码：

pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0
https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>hadoop</groupId>
    <artifactId>hdfstest</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.2.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.2.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.2.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>3.2.1</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>

        <dependency>
            <groupId>org.apache.zookeeper</groupId>
            <artifactId>zookeeper</artifactId>
            <version>3.5.6</version>
        </dependency>
</project>

 

WordCountTest类

package hdfstest;
        import java.io.IOException;
        import java.util.StringTokenizer;
        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.Mapper;
        import org.apache.hadoop.mapreduce.Reducer;
        import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
        import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCountTest {
    public static class TokenizerMapper extends Mapper<Object, Text,
            Text, IntWritable> { // 继承Mapper类并重写map()方法
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            StringTokenizer itr = new
                    StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text,
            IntWritable, Text, IntWritable> { // 继承Reducer并重写reduce()方法
        private IntWritable result = new IntWritable();


        public void reduce(Text key, Iterable<IntWritable> values,
                           Context context)
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCountTest.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
// 设定hdfs下输入输出路径
        FileInputFormat.addInputPath(job, new
                Path("hdfs://192.168.233.10:8020/lixianhui/"));
        FileOutputFormat.setOutputPath(job, new
                Path("hdfs://192.168.233.10:8020/lixianhui/output/"));
/*
* 设置本地文件系统输入和输出路径
* final Path inputpath = new Path("D:\\a.txt");
* final Path outpath = new Path("D:\\demo");
FileInputFormat.setInputPaths(job,inputpath);
FileOutputFormat.setOutputPath(job,outpath);
*
*/
        System.exit(job.waitForCompletion(true) ? 0 : 1);
        System.out.println("done!");
    }
}