Spark的wordcount

小鱼儿 2022-02-05 13:21 256阅读 0赞

private static void wordCount() {
            //设置这次任务的名字和设置本地跑spark程序
            SparkConf conf = new SparkConf().setAppName("hzy").setMaster("local");
            JavaSparkContext sparkContext = new JavaSparkContext(conf);
            //读取文件地址
            JavaRDD<String> lines = sparkContext.textFile("E:\\hzyFtp\\aa\\words.txt");
            //List<hello,word,hello>
            JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
                @Override
                public Iterator<String> call(String s) throws Exception {
                    String[] arr = s.split(" ");
                    List<String> list = Arrays.asList(arr);
                    return list.iterator();
                }
            });
            //Map(<hello,1>,<word,1>,<hello,1>)
            JavaPairRDD<String,Integer> tuples =words.mapToPair(new PairFunction<String, String, Integer>() {
                @Override
                public Tuple2<String, Integer> call(String s) throws Exception {
                    return new Tuple2<>(s, 1);
                }
            });
            //聚合Map(<hello,2>,<word,1>)
            JavaPairRDD<String,Integer> reduced = tuples.reduceByKey(new Function2<Integer, Integer, Integer>() {
                @Override
                public Integer call(Integer v1, Integer v2) throws Exception {
                    return v1+v2;
                }
            });
    
            //单词和它出现的次数做一个颠倒，交换
            JavaPairRDD<Integer,String> swaped = reduced.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
                @Override
                public Tuple2<Integer, String> call(Tuple2<String, Integer> tup) throws Exception {
                    return tup.swap();
                }
            });
    
            //排序
            JavaPairRDD<Integer,String> sorted =swaped.sortByKey();
    
            //数据的一个位置交换
            JavaPairRDD<String,Integer> res = sorted.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
                @Override
                public Tuple2<String, Integer> call(Tuple2<Integer, String> tup) throws Exception {
                    return tup.swap();
                }
            });
    
    		//把结果写出去，一半情况下我们选择写到hdfs中
            res.saveAsTextFile("D:\\ceshi\\out");
            sparkContext.stop();
    
        }