[SPARK-23268][SQL][FOLLOWUP] Reorganize packages in data source V2

cloud-fan · cloud-fan · commit a75f92717363 · 2018-02-08T19:20:11.000+08:00
## What changes were proposed in this pull request? This is a followup of #20435. While reorganizing the packages for streaming data source v2, the top level stream read/write support interfaces should not be in the reader/writer package, but should be in the `sources.v2` package, to follow the `ReadSupport`, `WriteSupport`, etc. ## How was this patch tested? N/A Author: Wenchen Fan <wenchen@databricks.com> Closes #20509 from cloud-fan/followup.
diff --git a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala b/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala
@@ -30,9 +30,7 @@ import org.apache.spark.internal.Logging
 import org.apache.spark.sql.{AnalysisException, DataFrame, SaveMode, SparkSession, SQLContext}
 import org.apache.spark.sql.execution.streaming.{Sink, Source}
 import org.apache.spark.sql.sources._
-import org.apache.spark.sql.sources.v2.DataSourceOptions
-import org.apache.spark.sql.sources.v2.reader.ContinuousReadSupport
-import org.apache.spark.sql.sources.v2.writer.StreamWriteSupport
+import org.apache.spark.sql.sources.v2.{ContinuousReadSupport, DataSourceOptions, StreamWriteSupport}
 import org.apache.spark.sql.sources.v2.writer.streaming.StreamWriter
 import org.apache.spark.sql.streaming.OutputMode
 import org.apache.spark.sql.types.StructType
diff --git a/sql/core/src/main/java/org/apache/spark/sql/sources/v2/ContinuousReadSupport.java b/sql/core/src/main/java/org/apache/spark/sql/sources/v2/ContinuousReadSupport.java
@@ -15,13 +15,11 @@
  * limitations under the License.
  */
 
-package org.apache.spark.sql.sources.v2.reader;
+package org.apache.spark.sql.sources.v2;
 
 import java.util.Optional;
 
 import org.apache.spark.annotation.InterfaceStability;
-import org.apache.spark.sql.sources.v2.DataSourceV2;
-import org.apache.spark.sql.sources.v2.DataSourceOptions;
 import org.apache.spark.sql.sources.v2.reader.streaming.ContinuousReader;
 import org.apache.spark.sql.types.StructType;
 
diff --git a/sql/core/src/main/java/org/apache/spark/sql/sources/v2/MicroBatchReadSupport.java b/sql/core/src/main/java/org/apache/spark/sql/sources/v2/MicroBatchReadSupport.java
@@ -15,13 +15,11 @@
  * limitations under the License.
  */
 
-package org.apache.spark.sql.sources.v2.reader;
+package org.apache.spark.sql.sources.v2;
 
 import java.util.Optional;
 
 import org.apache.spark.annotation.InterfaceStability;
-import org.apache.spark.sql.sources.v2.DataSourceOptions;
-import org.apache.spark.sql.sources.v2.DataSourceV2;
 import org.apache.spark.sql.sources.v2.reader.streaming.MicroBatchReader;
 import org.apache.spark.sql.types.StructType;
 
diff --git a/sql/core/src/main/java/org/apache/spark/sql/sources/v2/StreamWriteSupport.java b/sql/core/src/main/java/org/apache/spark/sql/sources/v2/StreamWriteSupport.java
@@ -15,12 +15,11 @@
  * limitations under the License.
  */
 
-package org.apache.spark.sql.sources.v2.writer;
+package org.apache.spark.sql.sources.v2;
 
 import org.apache.spark.annotation.InterfaceStability;
 import org.apache.spark.sql.execution.streaming.BaseStreamingSink;
-import org.apache.spark.sql.sources.v2.DataSourceOptions;
-import org.apache.spark.sql.sources.v2.DataSourceV2;
+import org.apache.spark.sql.sources.v2.writer.DataSourceWriter;
 import org.apache.spark.sql.sources.v2.writer.streaming.StreamWriter;
 import org.apache.spark.sql.streaming.OutputMode;
 import org.apache.spark.sql.types.StructType;
diff --git a/sql/core/src/main/java/org/apache/spark/sql/sources/v2/writer/DataSourceWriter.java b/sql/core/src/main/java/org/apache/spark/sql/sources/v2/writer/DataSourceWriter.java
@@ -21,6 +21,7 @@
 import org.apache.spark.sql.Row;
 import org.apache.spark.sql.SaveMode;
 import org.apache.spark.sql.sources.v2.DataSourceOptions;
+import org.apache.spark.sql.sources.v2.StreamWriteSupport;
 import org.apache.spark.sql.sources.v2.WriteSupport;
 import org.apache.spark.sql.streaming.OutputMode;
 import org.apache.spark.sql.types.StructType;
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/MicroBatchExecution.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/MicroBatchExecution.scala
@@ -29,10 +29,9 @@ import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan}
 import org.apache.spark.sql.execution.SQLExecution
 import org.apache.spark.sql.execution.datasources.v2.{StreamingDataSourceV2Relation, WriteToDataSourceV2}
 import org.apache.spark.sql.execution.streaming.sources.{InternalRowMicroBatchWriter, MicroBatchWriter}
-import org.apache.spark.sql.sources.v2.DataSourceOptions
-import org.apache.spark.sql.sources.v2.reader.MicroBatchReadSupport
+import org.apache.spark.sql.sources.v2.{DataSourceOptions, MicroBatchReadSupport, StreamWriteSupport}
 import org.apache.spark.sql.sources.v2.reader.streaming.{MicroBatchReader, Offset => OffsetV2}
-import org.apache.spark.sql.sources.v2.writer.{StreamWriteSupport, SupportsWriteInternalRow}
+import org.apache.spark.sql.sources.v2.writer.SupportsWriteInternalRow
 import org.apache.spark.sql.streaming.{OutputMode, ProcessingTime, Trigger}
 import org.apache.spark.util.{Clock, Utils}
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/RateSourceProvider.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/RateSourceProvider.scala
@@ -32,7 +32,6 @@ import org.apache.spark.sql.catalyst.util.{CaseInsensitiveMap, DateTimeUtils}
 import org.apache.spark.sql.execution.streaming.continuous.RateStreamContinuousReader
 import org.apache.spark.sql.sources.{DataSourceRegister, StreamSourceProvider}
 import org.apache.spark.sql.sources.v2._
-import org.apache.spark.sql.sources.v2.reader.ContinuousReadSupport
 import org.apache.spark.sql.sources.v2.reader.streaming.ContinuousReader
 import org.apache.spark.sql.types._
 import org.apache.spark.util.{ManualClock, SystemClock}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingRelation.scala
@@ -25,8 +25,7 @@ import org.apache.spark.sql.catalyst.plans.logical.LeafNode
 import org.apache.spark.sql.catalyst.plans.logical.Statistics
 import org.apache.spark.sql.execution.LeafExecNode
 import org.apache.spark.sql.execution.datasources.DataSource
-import org.apache.spark.sql.sources.v2.DataSourceV2
-import org.apache.spark.sql.sources.v2.reader.ContinuousReadSupport
+import org.apache.spark.sql.sources.v2.{ContinuousReadSupport, DataSourceV2}
 
 object StreamingRelation {
   def apply(dataSource: DataSource): StreamingRelation = {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/console.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/console.scala
@@ -20,8 +20,7 @@ package org.apache.spark.sql.execution.streaming
 import org.apache.spark.sql._
 import org.apache.spark.sql.execution.streaming.sources.ConsoleWriter
 import org.apache.spark.sql.sources.{BaseRelation, CreatableRelationProvider, DataSourceRegister}
-import org.apache.spark.sql.sources.v2.{DataSourceOptions, DataSourceV2}
-import org.apache.spark.sql.sources.v2.writer.StreamWriteSupport
+import org.apache.spark.sql.sources.v2.{DataSourceOptions, DataSourceV2, StreamWriteSupport}
 import org.apache.spark.sql.sources.v2.writer.streaming.StreamWriter
 import org.apache.spark.sql.streaming.OutputMode
 import org.apache.spark.sql.types.StructType
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousExecution.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousExecution.scala
@@ -31,10 +31,8 @@ import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.execution.SQLExecution
 import org.apache.spark.sql.execution.datasources.v2.{DataSourceV2Relation, StreamingDataSourceV2Relation, WriteToDataSourceV2}
 import org.apache.spark.sql.execution.streaming.{ContinuousExecutionRelation, StreamingRelationV2, _}
-import org.apache.spark.sql.sources.v2.DataSourceOptions
-import org.apache.spark.sql.sources.v2.reader.ContinuousReadSupport
+import org.apache.spark.sql.sources.v2.{ContinuousReadSupport, DataSourceOptions, StreamWriteSupport}
 import org.apache.spark.sql.sources.v2.reader.streaming.{ContinuousReader, PartitionOffset}
-import org.apache.spark.sql.sources.v2.writer.StreamWriteSupport
 import org.apache.spark.sql.streaming.{OutputMode, ProcessingTime, Trigger}
 import org.apache.spark.sql.types.StructType
 import org.apache.spark.util.{Clock, Utils}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/RateStreamSourceV2.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/RateStreamSourceV2.scala
@@ -29,7 +29,7 @@ import org.apache.spark.sql.Row
 import org.apache.spark.sql.catalyst.util.DateTimeUtils
 import org.apache.spark.sql.execution.streaming.{RateStreamOffset, ValueRunTimeMsPair}
 import org.apache.spark.sql.sources.DataSourceRegister
-import org.apache.spark.sql.sources.v2.{DataSourceOptions, DataSourceV2}
+import org.apache.spark.sql.sources.v2.{DataSourceOptions, DataSourceV2, MicroBatchReadSupport}
 import org.apache.spark.sql.sources.v2.reader._
 import org.apache.spark.sql.sources.v2.reader.streaming.{MicroBatchReader, Offset}
 import org.apache.spark.sql.types.{LongType, StructField, StructType, TimestampType}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/memoryV2.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/memoryV2.scala
@@ -29,7 +29,7 @@ import org.apache.spark.sql.catalyst.expressions.Attribute
 import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, Statistics}
 import org.apache.spark.sql.catalyst.streaming.InternalOutputModes.{Append, Complete, Update}
 import org.apache.spark.sql.execution.streaming.Sink
-import org.apache.spark.sql.sources.v2.{DataSourceOptions, DataSourceV2}
+import org.apache.spark.sql.sources.v2.{DataSourceOptions, DataSourceV2, StreamWriteSupport}
 import org.apache.spark.sql.sources.v2.writer._
 import org.apache.spark.sql.sources.v2.writer.streaming.StreamWriter
 import org.apache.spark.sql.streaming.OutputMode
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala
@@ -28,8 +28,7 @@ import org.apache.spark.sql.execution.command.DDLUtils
 import org.apache.spark.sql.execution.datasources.DataSource
 import org.apache.spark.sql.execution.streaming.{StreamingRelation, StreamingRelationV2}
 import org.apache.spark.sql.sources.StreamSourceProvider
-import org.apache.spark.sql.sources.v2.DataSourceOptions
-import org.apache.spark.sql.sources.v2.reader.{ContinuousReadSupport, MicroBatchReadSupport}
+import org.apache.spark.sql.sources.v2.{ContinuousReadSupport, DataSourceOptions, MicroBatchReadSupport}
 import org.apache.spark.sql.types.StructType
 import org.apache.spark.util.Utils
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala
@@ -29,7 +29,7 @@ import org.apache.spark.sql.execution.datasources.DataSource
 import org.apache.spark.sql.execution.streaming._
 import org.apache.spark.sql.execution.streaming.continuous.ContinuousTrigger
 import org.apache.spark.sql.execution.streaming.sources.{MemoryPlanV2, MemorySinkV2}
-import org.apache.spark.sql.sources.v2.writer.StreamWriteSupport
+import org.apache.spark.sql.sources.v2.StreamWriteSupport
 
 /**
  * Interface used to write a streaming `Dataset` to external storage systems (e.g. file systems,
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/StreamingQueryManager.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/StreamingQueryManager.scala
@@ -32,7 +32,7 @@ import org.apache.spark.sql.execution.streaming._
 import org.apache.spark.sql.execution.streaming.continuous.{ContinuousExecution, ContinuousTrigger}
 import org.apache.spark.sql.execution.streaming.state.StateStoreCoordinatorRef
 import org.apache.spark.sql.internal.SQLConf
-import org.apache.spark.sql.sources.v2.writer.StreamWriteSupport
+import org.apache.spark.sql.sources.v2.StreamWriteSupport
 import org.apache.spark.util.{Clock, SystemClock, Utils}
 
 /**
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/RateSourceV2Suite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/RateSourceV2Suite.scala
@@ -26,8 +26,8 @@ import org.apache.spark.sql.Row
 import org.apache.spark.sql.execution.datasources.DataSource
 import org.apache.spark.sql.execution.streaming.continuous._
 import org.apache.spark.sql.execution.streaming.sources.{RateStreamBatchTask, RateStreamMicroBatchReader, RateStreamSourceV2}
+import org.apache.spark.sql.sources.v2.{ContinuousReadSupport, MicroBatchReadSupport}
 import org.apache.spark.sql.sources.v2.DataSourceOptions
-import org.apache.spark.sql.sources.v2.reader.{ContinuousReadSupport, MicroBatchReadSupport}
 import org.apache.spark.sql.streaming.StreamTest
 import org.apache.spark.util.ManualClock
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/sources/StreamingDataSourceV2Suite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/sources/StreamingDataSourceV2Suite.scala
@@ -25,10 +25,9 @@ import org.apache.spark.sql.execution.streaming.{RateStreamOffset, Sink, Streami
 import org.apache.spark.sql.execution.streaming.continuous.ContinuousTrigger
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.sources.{DataSourceRegister, StreamSinkProvider}
-import org.apache.spark.sql.sources.v2.DataSourceOptions
-import org.apache.spark.sql.sources.v2.reader.{ContinuousReadSupport, DataReaderFactory, MicroBatchReadSupport}
+import org.apache.spark.sql.sources.v2.{ContinuousReadSupport, DataSourceOptions, MicroBatchReadSupport, StreamWriteSupport}
+import org.apache.spark.sql.sources.v2.reader.DataReaderFactory
 import org.apache.spark.sql.sources.v2.reader.streaming.{ContinuousReader, MicroBatchReader, Offset, PartitionOffset}
-import org.apache.spark.sql.sources.v2.writer.StreamWriteSupport
 import org.apache.spark.sql.sources.v2.writer.streaming.StreamWriter
 import org.apache.spark.sql.streaming.{OutputMode, StreamTest, Trigger}
 import org.apache.spark.sql.types.StructType
