Github user jose-torres commented on a diff in the pull request:

    https://github.com/apache/spark/pull/20382#discussion_r163612181
  
    --- Diff: 
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/TextSocketStreamSourceV2.scala
 ---
    @@ -0,0 +1,247 @@
    +/*
    + * 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.sources
    +
    +import java.io.{BufferedReader, InputStreamReader, IOException}
    +import java.net.Socket
    +import java.sql.Timestamp
    +import java.text.SimpleDateFormat
    +import java.util._
    +import java.util.{List => JList}
    +import java.util.concurrent.atomic.AtomicLong
    +import javax.annotation.concurrent.GuardedBy
    +
    +import scala.collection.JavaConverters._
    +import scala.collection.mutable.ListBuffer
    +import scala.util.{Failure, Success, Try}
    +
    +import org.apache.spark.internal.Logging
    +import org.apache.spark.sql.{AnalysisException, Row}
    +import org.apache.spark.sql.sources.DataSourceRegister
    +import org.apache.spark.sql.sources.v2.{DataSourceV2, DataSourceV2Options}
    +import org.apache.spark.sql.sources.v2.reader.{DataReader, ReadTask}
    +import org.apache.spark.sql.sources.v2.streaming.MicroBatchReadSupport
    +import org.apache.spark.sql.sources.v2.streaming.reader.{MicroBatchReader, 
Offset}
    +import org.apache.spark.sql.types.{StringType, StructField, StructType, 
TimestampType}
    +
    +
    +object TextSocketSourceProviderV2 {
    +  val HOST = "host"
    +  val PORT = "port"
    +  val INCLUDE_TIMESTAMP = "includeTimestamp"
    +  val NUM_PARTITIONS = "numPartitions"
    +  val SCHEMA_REGULAR = StructType(StructField("value", StringType) :: Nil)
    +  val SCHEMA_TIMESTAMP = StructType(StructField("value", StringType) ::
    +    StructField("timestamp", TimestampType) :: Nil)
    +  val DATE_FORMAT = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss", Locale.US)
    +}
    +
    +class TextSocketSourceProviderV2 extends DataSourceV2
    +    with MicroBatchReadSupport with DataSourceRegister with Logging {
    --- End diff --
    
    The intent is for the V2 and V1 source to live in the same register, so 
existing queries can start using the V2 source with no change needed. This also 
allows the V2 implementation to be validated by passing all the old tests.


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to