• mapreduce 依赖组合


    mport 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.jobcontrol.ControlledJob;
    import org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl;
    import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
    import org.apache.hadoop.util.GenericOptionsParser;

    public class Driver {

        public static class TokenizerMapper extends
                Mapper<Object, Text, Text, IntWritable> {
            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> {
            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 class DependenceMapper extends
                Mapper<Object, Text, Text, Text> {
            private Text word = new Text();
            public void map(Object key, Text value, Context context)
                    throws IOException, InterruptedException {
                String []sep=value.toString().split(" ");
                word.set(sep[1]+" "+sep[0]);
                System.out.println(value.toString());
                context.write(word,new Text(""));
            }
        }

        public static class DependenceReducer extends
                Reducer<Text,Text,Text,Text> {
            public void reduce(Text key, Iterable<Text> values,
                    Context context) throws IOException, InterruptedException {
                String[] sep = key.toString().split(" ");
                System.out.println( sep[0]+"++++++++="+ sep[1]);
                context.write(key,new Text(""));
            }
        }

        public static void main(String[] args) throws Exception {
            Configuration conf = new Configuration();
            String[] otherArgs = new GenericOptionsParser(conf, args)
                    .getRemainingArgs();
            if (otherArgs.length < 2) {
                System.err.println("Usage: wordcount <in> <out>");
                System.exit(2);
            }
            Job job = new Job(conf, "word count");
            //加入控制容器
            ControlledJob ctrljob1=new  ControlledJob(conf);
            ctrljob1.setJob(job);
            job.setJarByClass(Driver.class);
            job.setMapperClass(TokenizerMapper.class);
            job.setCombinerClass(IntSumReducer.class);
            job.setReducerClass(IntSumReducer.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
            FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
            FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    //        job.waitForCompletion(true);

            Configuration conf2 = new Configuration();
            Job job2 = new Job(conf2, "word count1");
             ControlledJob ctrljob2=new ControlledJob(conf);
                ctrljob2.setJob(job2);
                ctrljob2.addDependingJob(ctrljob1);
            job2.setJarByClass(Driver.class);
            job2.setMapperClass(DependenceMapper.class);
            job2.setReducerClass(DependenceReducer.class);
            job2.setOutputKeyClass(Text.class);
            job2.setOutputValueClass(Text.class);
            FileInputFormat.addInputPath(job2, new Path(otherArgs[1]));
            FileOutputFormat.setOutputPath(job2, new Path(otherArgs[2]));
        //    job2.waitForCompletion(true);
              JobControl jobCtrl=new JobControl("myctrl");
              
                //添加到总的JobControl里,进行控制
                jobCtrl.addJob(ctrljob1);
                jobCtrl.addJob(ctrljob2);
                jobCtrl.run();
                
        }
    }

  • 相关阅读:
    oo——第三单元总结
    oo第三单元总结
    【BUAA软工】提问回顾与个人总结
    【BUAA软工】HTTP协议前后端实现及实战北航云盘爬取
    【BUAA软工】软件案例分析
    【BUAA软工】结对编程作业
    【BUAA 软工个人项目作业】玩转平面几何
    【BUAA 软工博客作业】个人博客作业
    【BUAA 软工热身作业】继往开来,勇攀高峰
    BUAA-OO-第四单元总结——终章
  • 原文地址:https://www.cnblogs.com/1130136248wlxk/p/5011142.html
Copyright © 2020-2023  润新知