hadoop之wordcount

布满荆棘的人生 2022-06-10 05:11 211阅读 0赞

1、搭建好一个hadoop程序：

[hadoop完全伪分布式搭建][hadoop]

2、在myeclipse的安装目录下导入hadoop插件：  
![这里写图片描述][SouthEast]

效果：  
![这里写图片描述][SouthEast 1]  
这里我们解压一个hadoop的安装包，箭头指向的位置引入所需依赖包

3、创建一个工程  
![这里写图片描述][SouthEast 2]

4、window–>show view –>Map/Reduce Location  
![这里写图片描述][SouthEast 3]

5、编写WordCount程序：

package com.hadoop.hdfs;
    
    import java.io.IOException;
    
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.io.LongWritable;
    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 WordCount { 
        /** * * @author Howie Lee * 继承Mapper<...>四个泛型分别对应输入的key value 和输出的key value * * BooleanWritable：标准布尔型数值 * ByteWritable：单字节数值 * DoubleWritable：双字节数 * FloatWritable：浮点数 * IntWritable：整型数 * LongWritable：长整型数 * Text：使用UTF8格式存储的文本 * NullWritable：当<key,value>中的key或value为空时使用 * * */
        public static class WCMapper extends Mapper<LongWritable, Text, Text, LongWritable>{ 
    
            protected void map(LongWritable key, Text value, Context context) 
                    throws java.io.IOException ,InterruptedException {
                //分割每行数据
                String line = value.toString();
                String[] words = line.split(" ");
                for(String word : words){
                    context.write(new Text(word), new LongWritable(1));
                }
            };
    
        }
        /** * * @author Howie Lee * 继承Reducer<...>四个泛型分别对应输入的key value 和输出的key value */
        public static class WCReducer extends Reducer<Text, LongWritable, Text, LongWritable>{ 
    
            protected void reduce(Text key, Iterable<LongWritable> values, Context context) 
                    throws java.io.IOException ,InterruptedException {
                Long sum = 0L;
                for(LongWritable value : values ){
                    //这里使用value.get();将LongWritable转换为int类型
                    sum += value.get();
                }
                context.write(key, new LongWritable(sum));
    
            };
        }
    
        public static void main(String[] args) throws IOException, Exception {
    
            Configuration conf = new Configuration();//指定作业执行规范 
            Job job = Job.getInstance(conf);//初始化一个job对象
    
            //传入的class 找到job的jar包(这里只是使用这个类去寻找他的包)
            job.setJarByClass(WordCount.class);
    
            job.setMapperClass(WCMapper.class);//指定map函数 
            job.setReducerClass(WCReducer.class);//指定reducer函数 
            job.setOutputKeyClass(Text.class);//输出key格式(如果一样的话，这句话就可以做到输出map和reducer的格式)
            //如果map/reducer输出不同就单独指定map的
            job.setMapOutputKeyClass(Text.class);//输出map的key格式
            job.setOutputValueClass(LongWritable.class);//输出value格式
            job.setMapOutputValueClass(LongWritable.class);//输出map的value格式
            FileInputFormat.addInputPath(job, new Path("/word/"));//处理文件路径
            FileOutputFormat.setOutputPath(job, new Path("/output/"));//结果输出路径 
            job.waitForCompletion(true);
        }
    }

6、导出为一个jar包（File–>Export–> Jar file）  
![这里写图片描述][SouthEast 4]

7、运行  
![这里写图片描述][SouthEast 5]

8、查看运行结果  
![这里写图片描述][SouthEast 6]

## 完成 ##

[hadoop]: http://blog.csdn.net/mr_leehy/article/details/77067559
[SouthEast]: /images/20220610/0a3b2a0af9394e9680a9ea24180b0776.png
[SouthEast 1]: /images/20220610/11cbff84cee747c284898d27c1b0dfd2.png
[SouthEast 2]: /images/20220610/da13642cf1ee44638575c61fc1e0fe2a.png
[SouthEast 3]: /images/20220610/a4a6f6d2de664135a330d25931e05984.png
[SouthEast 4]: /images/20220610/6cc6bbbf9f164576a9d6fbe9fe5dfd93.png
[SouthEast 5]: /images/20220610/d1e55b0473004cad96a0e638dcdf07c3.png
[SouthEast 6]: /images/20220610/581b1f6c8a1c4c048c73f132ff6304fa.png