Hadoop学习之idea开发wordcount实例

在使用idea开发wordcount实例中，首先构建一个maven工程，需要引入的依赖有：

<repositories>
    <repository>
        <id>apache</id>
        <url>http://maven.apache.org</url>
    </repository>
</repositories>

<dependencies>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.7.3</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>2.7.3</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>2.7.3</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.7.3</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>3.8.1</version>
        <scope>test</scope>
    </dependency>
</dependencies>
<build>
    <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-dependency-plugin</artifactId>
            <configuration>
                <excludeTransitive>false</excludeTransitive>
                <stripVersion>true</stripVersion>
                <outputDirectory>./lib</outputDirectory>
            </configuration>

        </plugin>
    </plugins>
</build>

在引入各个依赖后，点击自己创建的项目，选择open module setting如下所示; 

    

 之后，引入Hadoop的包，如下图所示：

选择自己Hadoop的路径，之后选择以下所示的文件夹，选中引入即可。

之后点击配置，配置本项目的文件输入路径和输出路径，在program arguments中前一个为文件输入路径，后一个为输出路径，当然，此时的路径均为hdfs集群路径，应该将创建的文件夹上传到hdfs集群中，然后把该路径写入，否则会报找不到文件路径的错误，出错解决办法参考我上一篇博客。

配置完成后，将core-site.xml配置文件引入，如下图所示：

在一切配置准备完成后，便可以进行编码了，首先创建一个java类名为WordCount，具体代码如下所示：

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;


import java.io.IOException;
import java.util.StringTokenizer;

public class WordCount {
//编写TokenizerMapper类继承Mapper类
    public static class TokenizerMapper extends Mapper<Object,Text,Text,IntWritable>{
        //定义变量one值设置为1，为每个单词定义value为1
        public static final IntWritable one=new IntWritable(1);
        private Text word=new Text();
        //编写map函数，其中输入参数为value（即为单词），输出参数为context
        public void map(Object key,Text values,Context context) throws IOException, InterruptedException {
            StringTokenizer str=new StringTokenizer(values.toString());
            while(str.hasMoreTokens()){
                word.set(str.nextToken());
                context.write(word,one);
            }
        }
    }
    //定义IntSumReducer继承Reducer
    public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable>{
        private IntWritable result=new IntWritable();
        //定义reduce方法
        public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
            //遍历，将统计各个单词的总个数
            int sum=0;
            for (IntWritable val:values) {
                sum+=val.get();
            }
            result.set(sum);
            context.write(key,result);
        }
    }
    //编写主函数
    public static void main(String[] args) throws Exception{
        Configuration conf=new Configuration();

        Job job=Job.getInstance(conf,"wordCount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //添加文件的输入路径
        FileInputFormat.addInputPath(job, new Path(args[0]));
        //添加文件的输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }
}

一切就绪后，点击运行便可运行出结果。当然在运行之前要开启hadoop集群。