Github user HeartSaVioR commented on a diff in the pull request:
https://github.com/apache/spark/pull/21199#discussion_r206357959
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousTextSocketSource.scala
---
@@ -0,0 +1,295 @@
+/*
+ * 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.continuous
+
+import java.io.{BufferedReader, InputStreamReader, IOException}
+import java.net.Socket
+import java.sql.Timestamp
+import java.text.SimpleDateFormat
+import java.util.{Calendar, List => JList, Locale}
+import javax.annotation.concurrent.GuardedBy
+
+import scala.collection.JavaConverters._
+import scala.collection.mutable.ListBuffer
+
+import org.json4s.{DefaultFormats, NoTypeHints}
+import org.json4s.jackson.Serialization
+
+import org.apache.spark.SparkEnv
+import org.apache.spark.internal.Logging
+import org.apache.spark.rpc.RpcEndpointRef
+import org.apache.spark.sql._
+import org.apache.spark.sql.execution.streaming.{ContinuousRecordEndpoint,
ContinuousRecordPartitionOffset, GetRecord}
+import org.apache.spark.sql.sources.v2.DataSourceOptions
+import org.apache.spark.sql.sources.v2.reader.{InputPartition,
InputPartitionReader, SupportsDeprecatedScanRow}
+import
org.apache.spark.sql.sources.v2.reader.streaming.{ContinuousInputPartitionReader,
ContinuousReader, Offset, PartitionOffset}
+import org.apache.spark.sql.types.{StringType, StructField, StructType,
TimestampType}
+import org.apache.spark.util.RpcUtils
+
+
+object TextSocketContinuousReader {
--- End diff --
While the values are good to be placed with companion object, it looks like
redundant to have them in both micro-batch and continuous, so might be better
to have common object to place this.
We may need to find more spots to deduplicate between micro-batch and
continuous for socket.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
