mr WordCount示例编写

港控/mmm° 2024-04-18 14:31 76阅读 0赞

//map阶段
    package com.mr;
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.LongWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Mapper;
    
    import java.io.IOException;
    //创建一个CountMap类继承Mapper 定义四中类型
    public class CountMap extends Mapper<LongWritable, Text, Text, IntWritable> {
        //重写map方法
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            //拿到一行数据转化为String
            String word = value.toString();
            //将这一行数据按照分隔符进行内容的切割
            //切割成一个数组
            String[] split = word.split(" ");
            //遍历数组，每出现一个单词就标记一个数字1<单词，1>
            for (String w : split) {
                context.write(new Text(w), new IntWritable(1));
            }
        }
    }
    //hadoop自己封装的一套数据类型
    //long----->longwritable
    //String------>Text
    //Interage------->Intwritable
    //null-------->Nullwritable

package com.mr;
    
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Reducer;
    
    import java.io.IOException;
    //定义一个CountReadius继承Reducer
    public class CountReadius  extends Reducer<Text, IntWritable,Text,IntWritable> {
        //重写Reduce方法
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            //定义一个计数器
            Integer count = 0;
            //遍历一组迭代器，把每一个数1加起来
            for (IntWritable v:values){
                count++;
    
            }
            //输出最总结果
            context.write(key, new IntWritable(count));
        }
    }

package com.mr;
    
    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;
    
    import java.io.IOException;
    //运行mr程序的主类
    public class CountDriver {
        public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
            //通过job来封装本次mr的相关信息
            Configuration conf = new Configuration();
            conf.set("mapreduce.framework.name","local");
            conf.set("yarn.resorcemanager.hostname","192.168.72.110");
            conf.set("fs.deafutFS","hdfs://192.168.72.110:9000/");
    
            Job job = Job.getInstance(conf);
            //指定本次mr job jar包运行主类
            job.setJarByClass(CountDriver.class);
            //设置本次job是使用map，reduce类
            job.setMapperClass(CountMap.class);
            job.setReducerClass(CountReadius.class);
            //设置本次map和reduce的输出k,v类型
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
            //设置本次mr最总输出类型
            job.setOutputKeyClass(Text.class);
            job.setOutputKeyClass(IntWritable.class);
            //制定本次job读取源数据时需要用到的组件：我们的源文件在hdfs的文本文件中，用TextInputFormat
            //job.setInputFormatClass(TextInputFormat.class);
            //制定本次job输出数据需要的组件：我们要输出到hdfs文件中，用TextOutputFormat
            //job.setOutputFormatClass(TextOutputFormat.class);
            //设置输入路径
            FileInputFormat.setInputPaths(job,new Path("E:\\hadoop\\wordcount.txt"));
            FileOutputFormat.setOutputPath(job,new Path("E:\\hadoop\\output"));
            //提交任务，客户端返回
            job.submit();//不会追踪
            //提交程序并且监控打印情况
            boolean result = job.waitForCompletion(true);
            System.exit(result ? 0 : 1);
    
    
        }
    
    }