增加diff校验

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/v20240718/diff_data_20250319.scala

@@ -50,35 +50,36 @@ object diff_data_20250319 {
 
     val rdd1: JSONObject = odpsData1.first()
     println("rdd1")
+    println(rdd1.getString("logkey"))
     println(rdd1.toString)
 
     val rdd2: JSONObject = odpsData2.first()
-
     println("rdd2")
+    println(rdd2.getString("logkey"))
     println(rdd2.toString)
 
 
-    var result: List[String] = List.empty
-
-    result = result :+ "ad_easyrec_eval_data_v3_sampled size =" + odpsData1.count();
-
-    result = result :+ "alg_recsys_ad_sample_all size =" + odpsData2.count();
+//    var result: List[String] = List.empty
+//
+//    result = result :+ "ad_easyrec_eval_data_v3_sampled size =" + odpsData1.count();
+//
+//    result = result :+ "alg_recsys_ad_sample_all size =" + odpsData2.count();
 
     // 以 logkey 为键进行转换
-    val rdd1Pairs: RDD[(String, JSONObject)] = odpsData1.map(map => (map.getString("logkey"), map))
-    val rdd2Pairs: RDD[(String, JSONObject)] = odpsData2.map(map => (map.getString("logkey"), map))
-
-
-    // 进行 join 操作
-    val joinedRDD: RDD[(String, (JSONObject, JSONObject))] = rdd1Pairs.join(rdd2Pairs)
-
-    val firstElement = joinedRDD.first()
-    firstElement match {
-      case (logkey, (map1, map2)) =>
-        println(logkey)
-        println(map1)
-        println(map2)
-    }
+//    val rdd1Pairs: RDD[(String, JSONObject)] = odpsData1.map(map => (map.getString("logkey"), map))
+//    val rdd2Pairs: RDD[(String, JSONObject)] = odpsData2.map(map => (map.getString("logkey"), map))
+//
+//
+//    // 进行 join 操作
+//    val joinedRDD: RDD[(String, (JSONObject, JSONObject))] = rdd1Pairs.join(rdd2Pairs)
+//
+//    val firstElement = joinedRDD.first()
+//    firstElement match {
+//      case (logkey, (map1, map2)) =>
+//        println(logkey)
+//        println(map1)
+//        println(map2)
+//    }
 
     // 比较相同 logkey 对应的 Map 中相同键的 value
     //    joinedRDD.foreach { case (logkey, (map1, map2)) =>