Github user marmbrus commented on a diff in the pull request:
https://github.com/apache/spark/pull/13653#discussion_r67023075
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala
---
@@ -0,0 +1,401 @@
+/*
+ * 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.streaming
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.sql.{AnalysisException, DataFrame, Dataset,
ForeachWriter}
+import org.apache.spark.sql.execution.datasources.DataSource
+import org.apache.spark.sql.execution.streaming.{ForeachSink, MemoryPlan,
MemorySink}
+
+/**
+ * :: Experimental ::
+ * Interface used to write a streaming [[Dataset]] to external storage
systems (e.g. file systems,
+ * key-value stores, etc). Use [[Dataset.write]] to access this.
+ *
+ * @since 2.0.0
+ */
+@Experimental
+final class DataStreamWriter[T] private[sql](ds: Dataset[T]) {
+
+ private val df = ds.toDF()
+
+ /**
+ * :: Experimental ::
+ * Specifies how data of a streaming DataFrame/Dataset is written to a
streaming sink.
+ * - `OutputMode.Append()`: only the new rows in the streaming
DataFrame/Dataset will be
+ * written to the sink
+ * - `OutputMode.Complete()`: all the rows in the streaming
DataFrame/Dataset will be written
+ * to the sink every time these is some
updates
+ *
+ * @since 2.0.0
+ */
+ @Experimental
+ def outputMode(outputMode: OutputMode): DataStreamWriter[T] = {
+ this.outputMode = outputMode
+ this
+ }
+
+
+ /**
+ * :: Experimental ::
+ * Specifies how data of a streaming DataFrame/Dataset is written to a
streaming sink.
+ * - `append`: only the new rows in the streaming DataFrame/Dataset
will be written to
+ * the sink
+ * - `complete`: all the rows in the streaming DataFrame/Dataset will
be written to the sink
+ * every time these is some updates
+ *
+ * @since 2.0.0
+ */
+ @Experimental
+ def outputMode(outputMode: String): DataStreamWriter[T] = {
--- End diff --
Again, I'd probably go for consistency unless we think that we will need
save modes in streaming (i'm not really sure how that would work).
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
