add GetPortrait

eda/feededa/src/main/scala/com/gmei/EsmmData.scala

@@ -226,7 +226,6 @@ object EsmmData {
 
 
 
-
 object EsmmPredData {
 
   Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
@@ -425,6 +424,77 @@ object EsmmPredData {
 
 
 
+      sc.stop()
+
+    }
+  }
+
+}
+
+
+object GetPortrait {
+
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev",
+                    date: String = GmeiConfig.getMinusNDate(1)
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("EsmmData")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    opt[String]("date")
+      .text(s"the date you used")
+      .action((x,c) => c.copy(date = x))
+    note(
+      """
+        |For example, the following command runs this app on a tidb dataset:
+        |
+        | spark-submit --class com.gmei.EsmmData ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod",tableName = "data_feed_click")
+
+      val diary_tag = sc.sql(
+        s"""
+           |select d.diary_id,
+           |(case when d.tag_type = '1' then d.level1_ids else "" end) level1_ids,
+           |(case when d.tag_type = '2' then d.level2_ids else "" end) level2_ids,
+           |(case when d.tag_type = '3' then d.level3_ids else "" end) level3_ids from
+           |	(select c.diary_id,c.tag_type,
+           |		group_concat(c.level1_id) as level1_ids
+           |		group_concat(c.level2_id) as level2_ids
+           |		group_concat(c.level3_id) as level3_ids from
+           |	(select a.diary_id,a.tag_id,b.tag_type,b.level1_id,b.level2_id,b.level3_id
+           |		from tl_hdfs_diary_tags_view a
+           |		left join bl_tag_hierarchy_detail b
+           |		on a.tag_id = b.id
+           |		where a.partition_date = '20181218'
+           |		and b.partition_date = '20181218') c
+           |	group by c.diary_id,c.tag_type) d
+           |group by d.diary_id
+         """.stripMargin
+      )
+      diary_tag.show()
+
+
       sc.stop()
 
     }