From 81c99a5b953802129b36d48c965cbb0bb97501b3 Mon Sep 17 00:00:00 2001
From: xuanyuanking <xyliyuanjian@gmail.com>
Date: Wed, 19 Jul 2017 10:27:42 +0800
Subject: [PATCH] [SPARK-21435][SQL] Empty files should be skipped while write
to file
## What changes were proposed in this pull request?
Add EmptyDirectoryWriteTask for empty task while writing files. Fix the empty result for parquet format by leaving the first partition for meta writing.
## How was this patch tested?
Add new test in `FileFormatWriterSuite `
Author: xuanyuanking <xyliyuanjian@gmail.com>
Closes #18654 from xuanyuanking/SPARK-21435.
---
.../datasources/FileFormatWriter.scala | 19 ++++++++++-
.../datasources/FileFormatWriterSuite.scala | 33 +++++++++++++++++++
2 files changed, 51 insertions(+), 1 deletion(-)
create mode 100644 sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileFormatWriterSuite.scala
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala
index 9eb9eae699..073e8788af 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala
@@ -236,7 +236,10 @@ object FileFormatWriter extends Logging {
committer.setupTask(taskAttemptContext)
val writeTask =
- if (description.partitionColumns.isEmpty && description.bucketIdExpression.isEmpty) {
+ if (sparkPartitionId != 0 && !iterator.hasNext) {
+ // In case of empty job, leave first partition to save meta for file format like parquet.
+ new EmptyDirectoryWriteTask
+ } else if (description.partitionColumns.isEmpty && description.bucketIdExpression.isEmpty) {
new SingleDirectoryWriteTask(description, taskAttemptContext, committer)
} else {
new DynamicPartitionWriteTask(description, taskAttemptContext, committer)
@@ -301,6 +304,20 @@ object FileFormatWriter extends Logging {
}
}
+ /** ExecuteWriteTask for empty partitions */
+ private class EmptyDirectoryWriteTask extends ExecuteWriteTask {
+
+ override def execute(iter: Iterator[InternalRow]): ExecutedWriteSummary = {
+ ExecutedWriteSummary(
+ updatedPartitions = Set.empty,
+ numOutputFile = 0,
+ numOutputBytes = 0,
+ numOutputRows = 0)
+ }
+
+ override def releaseResources(): Unit = {}
+ }
+
/** Writes data to a single directory (used for non-dynamic-partition writes). */
private class SingleDirectoryWriteTask(
description: WriteJobDescription,
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileFormatWriterSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileFormatWriterSuite.scala
new file mode 100644
index 0000000000..a0c1ea63d3
--- /dev/null
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileFormatWriterSuite.scala
@@ -0,0 +1,33 @@
+/*
+ * 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 org.apache.spark.sql.QueryTest
+import org.apache.spark.sql.test.SharedSQLContext
+
+class FileFormatWriterSuite extends QueryTest with SharedSQLContext {
+
+ test("empty file should be skipped while write to file") {
+ withTempPath { path =>
+ spark.range(100).repartition(10).where("id = 50").write.parquet(path.toString)
+ val partFiles = path.listFiles()
+ .filter(f => f.isFile && !f.getName.startsWith(".") && !f.getName.startsWith("_"))
+ assert(partFiles.length === 2)
+ }
+ }
+}
--
GitLab