48.Spark大型电商项目-用户访问session分析-top10热门品类之进行二次排序

目录

代码

UserVisitSessionAnalyzeSpark.java

---

本篇文章记录用户访问session分析-top10热门品类之进行二次排序。

代码

UserVisitSessionAnalyzeSpark.java

 /**
         * 第五步：将数据映射成<CategorySortKey,info>格式的RDD，然后进行二次排序（降序）
         */
        JavaPairRDD<CategorySortKey,String> sortKey2countRDD = categoryid2countRDD.mapToPair(
                new PairFunction<Tuple2<Long, String>, CategorySortKey, String>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Tuple2<CategorySortKey, String> call(Tuple2<Long, String> tuple) throws Exception {
                        String countInfo = tuple._2;
                        long clickCount = Long.valueOf(StringUtils.getFieldFromConcatString(countInfo,"\\\\|",Constants.FIELD_CLICK_COUNT));
                        long orderCount = Long.valueOf(StringUtils.getFieldFromConcatString(countInfo,"\\\\|",Constants.FIELD_ORDER_COUNT));
                        long payCount = Long.valueOf(StringUtils.getFieldFromConcatString(countInfo,"\\\\|",Constants.FIELD_PAY_COUNT));
                        CategorySortKey categorySortKey = new CategorySortKey(clickCount,orderCount,payCount);

                        return new Tuple2<CategorySortKey,String>(categorySortKey,countInfo);
                    }
                }
        );

        JavaPairRDD<CategorySortKey,String> sortedCategoryCountRDD = sortKey2countRDD.sortByKey(false);