[GitHub] [spark] cloud-fan commented on a diff in pull request #38468: [SPARK-41005][CONNECT][PYTHON] Arrow-based collect

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

cloud-fan commented on code in PR #38468:
URL: https://github.com/apache/spark/pull/38468#discussion_r1019090389


##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamHandler.scala:
##########
@@ -114,10 +120,93 @@ class SparkConnectStreamHandler(responseObserver: StreamObserver[Response]) exte
       responseObserver.onNext(response.build())
     }
 
-    responseObserver.onNext(sendMetricsToResponse(clientId, rows))
+    responseObserver.onNext(sendMetricsToResponse(clientId, dataframe))
     responseObserver.onCompleted()
   }
 
+  def processAsArrowBatches(clientId: String, dataframe: DataFrame): Unit = {
+    val spark = dataframe.sparkSession
+    val schema = dataframe.schema
+    // TODO: control the batch size instead of max records
+    val maxRecordsPerBatch = spark.sessionState.conf.arrowMaxRecordsPerBatch
+    val timeZoneId = spark.sessionState.conf.sessionLocalTimeZone
+
+    SQLExecution.withNewExecutionId(dataframe.queryExecution, Some("collectArrow")) {
+      val rows = dataframe.queryExecution.executedPlan.execute()
+      val numPartitions = rows.getNumPartitions
+      var numSent = 0
+
+      if (numPartitions > 0) {
+        type Batch = (Array[Byte], Long)
+
+        val batches = rows.mapPartitionsInternal { iter =>
+          ArrowConverters
+            .toArrowBatchIterator(iter, schema, maxRecordsPerBatch, timeZoneId)
+        }
+
+        val signal = new Object
+        val partitions = collection.mutable.Map.empty[Int, Array[Batch]]

Review Comment:
   do we really need a map? We know the number of partitions and we can just create an array.



-- 
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.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


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