Github user tengpeng commented on a diff in the pull request:
https://github.com/apache/spark/pull/20933#discussion_r198456106
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FilePartitionUtil.scala
---
@@ -0,0 +1,225 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.spark.sql.execution.datasources
+
+import java.io.{FileNotFoundException, IOException}
+
+import scala.collection.mutable
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.spark.TaskContext
+import org.apache.spark.deploy.SparkHadoopUtil
+import org.apache.spark.internal.Logging
+import org.apache.spark.rdd.InputFileBlockHolder
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.vectorized.ColumnarBatch
+import org.apache.spark.util.NextIterator
+
+object FilePartitionUtil extends Logging {
+
+ def getFilePartitions(
+ sparkSession: SparkSession,
+ partitionedFiles: Seq[PartitionedFile],
+ maxSplitBytes: Long): Seq[FilePartition] = {
+ val partitions = new ArrayBuffer[FilePartition]
+ val currentFiles = new ArrayBuffer[PartitionedFile]
+ var currentSize = 0L
+
+ /** Close the current partition and move to the next. */
+ def closePartition(): Unit = {
+ if (currentFiles.nonEmpty) {
+ val newPartition =
+ FilePartition(
+ partitions.size,
+ currentFiles.toArray.toSeq) // Copy to a new Array.
+ partitions += newPartition
+ }
+ currentFiles.clear()
+ currentSize = 0
+ }
+
+ val openCostInBytes =
sparkSession.sessionState.conf.filesOpenCostInBytes
+ // Assign files to partitions using "Next Fit Decreasing"
+ partitionedFiles.foreach { file =>
+ if (currentSize + file.length > maxSplitBytes) {
+ closePartition()
+ }
+ // Add the given file to the current partition.
+ currentSize += file.length + openCostInBytes
+ currentFiles += file
+ }
+ closePartition()
+ partitions
+ }
+
+ def compute(
--- End diff --
Reasonable concern. Is it because the author followed the convention in RDD
in which `compute` is used?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
