[GitHub] [spark] ConeyLiu commented on a change in pull request #23086: [SPARK-25528][SQL] data source v2 API refactor (batch read)

[GitBox <gi...@apache.org>]

ConeyLiu commented on a change in pull request #23086: [SPARK-25528][SQL] data source v2 API refactor (batch read)
URL: https://github.com/apache/spark/pull/23086#discussion_r267719800
 
 

 ##########
 File path: sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
 ##########
 @@ -194,20 +194,26 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging {
     }
 
     val cls = DataSource.lookupDataSource(source, sparkSession.sessionState.conf)
-    if (classOf[DataSourceV2].isAssignableFrom(cls)) {
-      val ds = cls.getConstructor().newInstance().asInstanceOf[DataSourceV2]
-      if (ds.isInstanceOf[BatchReadSupportProvider]) {
-        val sessionOptions = DataSourceV2Utils.extractSessionConfigs(
-          ds = ds, conf = sparkSession.sessionState.conf)
-        val pathsOption = {
-          val objectMapper = new ObjectMapper()
-          DataSourceOptions.PATHS_KEY -> objectMapper.writeValueAsString(paths.toArray)
-        }
-        Dataset.ofRows(sparkSession, DataSourceV2Relation.create(
-          ds, sessionOptions ++ extraOptions.toMap + pathsOption,
-          userSpecifiedSchema = userSpecifiedSchema))
-      } else {
-        loadV1Source(paths: _*)
+    if (classOf[TableProvider].isAssignableFrom(cls)) {
+      val provider = cls.getConstructor().newInstance().asInstanceOf[TableProvider]
+      val sessionOptions = DataSourceV2Utils.extractSessionConfigs(
+        ds = provider, conf = sparkSession.sessionState.conf)
+      val pathsOption = {
+        val objectMapper = new ObjectMapper()
+        DataSourceOptions.PATHS_KEY -> objectMapper.writeValueAsString(paths.toArray)
+      }
+      val finalOptions = sessionOptions ++ extraOptions.toMap + pathsOption
+      val dsOptions = new DataSourceOptions(finalOptions.asJava)
+      val table = userSpecifiedSchema match {
+        case Some(schema) => provider.getTable(dsOptions, schema)
+        case _ => provider.getTable(dsOptions)
+      }
+      table match {
+        case s: SupportsBatchRead =>
+          Dataset.ofRows(sparkSession, DataSourceV2Relation.create(
+            provider, s, finalOptions, userSpecifiedSchema = userSpecifiedSchema))
+
+        case _ => loadV1Source(paths: _*)
 
 Review comment:
   Hi @cloud-fan. I have a minor question here how we load the data that just extend the `SupportsRead`.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org