Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/11897#discussion_r57086874
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSink.scala
---
@@ -0,0 +1,79 @@
+/*
+ * 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.streaming
+
+import java.util.UUID
+
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.{DataFrame, SQLContext}
+import org.apache.spark.sql.sources.FileFormat
+
+object FileStreamSink {
+ // The name of the subdirectory that is used to store metadata about
which files are valid.
+ val metadataDir = "_spark_metadata"
+}
+
+/**
+ * A sink that writes out results to parquet files. Each batch is written
out to a unique
+ * directory. After all of the files in a batch have been succesfully
written, the list of
+ * file paths is appended to the log atomically. In the case of partial
failures, some duplicate
+ * data may be present in the target directory, but only one copy of each
file will be present
+ * in the log.
+ */
+class FileStreamSink(
+ sqlContext: SQLContext,
+ path: String,
+ fileFormat: FileFormat) extends Sink with Logging {
+
+ val basePath = new Path(path)
+ val logPath = new Path(basePath, FileStreamSink.metadataDir)
+ val fileLog = new HDFSMetadataLog[Seq[String]](sqlContext,
logPath.toUri.toString)
--- End diff --
nit: private
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
