MapReduce之连接模式一：reduce端连接

最新推荐文章于 2023-07-18 16:09:27 发布

老男孩-Leo

最新推荐文章于 2023-07-18 16:09:27 发布

阅读量777

点赞数

分类专栏： Java Hadoop 文章标签： mapreduce

本文链接：https://blog.csdn.net/nihaoxiaocui/article/details/53083557

版权

Java 同时被 2 个专栏收录

11 篇文章 0 订阅

订阅专栏

Hadoop

3 篇文章 0 订阅

订阅专栏

INPUT:表a：userID,user.location;表b：userID,coments.votes
OUTPUT:userID,user.location,coments.votes

joinMapper:
    public static class joinAMapper extends Mapper<Object,Text,Text,Text>{  
            private Text outKey = new Text();
            private Text outValue = new Text();
            public void map(Object key,Text value,Context context){
                    StringTokenizer itr = new StringTokenizer(value.toString());
                    while(itr.hasMoreTokens()){
                    String[] info  = itr.splite(",");
                    outKey.set(info[0]);
                    outValue.set("A"+info[1]);
                    context.write(outKey,outValue);
                    }

            }
    }

    public static class joinBMapper extends Mapper<Object,Text,Text,Text>{  
            private Text outKey = new Text();
            private Text outValue = new Text();
            public void map(Object key,Text value,Context context){
                    StringTokenizer itr = new StringTokenizer(value.toString());
                    while(itr.hasMoreTokens()){
                    String[] info  = itr.splite(",");
                    outKey.set(info[0]);
                    outValue.set("B"+info[1]);
                    context.write(outKey,outValue);
                    }

            }
    }

joinReducer:

    public static class joinReducer extends Reducer<Text,Text,Text,Text>{
            private Text tmp = new Text();
            private ArrayList<Text> listA = new ArrayList<Text>();
            private ArrayList<Text> listB = new ArrayList<Text>();
            public void reduce(Text text,Iterable<Text> values,Context context){
                while(values.hasNext()){
                    tmp = values.next();
                    if(tmp.charAt(0)=='A'){
                        listA.add(tmp.subString(1));
                    }else if(tmp.charAt(0)=='B'){
                        listB.add(tmp.subString(1));
                    }

                }


                execute.JoinLogic(context);
            }

    }