Github user marmbrus commented on a diff in the pull request:

    https://github.com/apache/spark/pull/14553#discussion_r82297835
  
    --- Diff: 
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/socket.scala 
---
    @@ -92,21 +105,64 @@ class TextSocketSource(host: String, port: Int, 
includeTimestamp: Boolean, sqlCo
       override def schema: StructType = if (includeTimestamp) 
TextSocketSource.SCHEMA_TIMESTAMP
       else TextSocketSource.SCHEMA_REGULAR
     
    -  /** Returns the maximum available offset for this source. */
    +  override def lastCommittedOffset: Option[Offset] = synchronized {
    +    if (lastOffsetCommitted.offset == -1) {
    +      None
    +    } else {
    +      Some(lastOffsetCommitted)
    +    }
    +  }
    +
       override def getOffset: Option[Offset] = synchronized {
    -    if (lines.isEmpty) None else Some(LongOffset(lines.size - 1))
    +    if (currentOffset.offset == -1) {
    +      None
    +    } else {
    +      Some(currentOffset)
    +    }
       }
     
       /** Returns the data that is between the offsets (`start`, `end`]. */
       override def getBatch(start: Option[Offset], end: Offset): DataFrame = 
synchronized {
    -    val startIdx = start.map(_.asInstanceOf[LongOffset].offset.toInt + 
1).getOrElse(0)
    -    val endIdx = end.asInstanceOf[LongOffset].offset.toInt + 1
    -    val data = synchronized { lines.slice(startIdx, endIdx) }
    +    val startOrdinal =
    +      
start.map(_.asInstanceOf[LongOffset]).getOrElse(LongOffset(-1)).offset.toInt + 1
    +    val endOrdinal = end.asInstanceOf[LongOffset].offset.toInt + 1
    +
    +    // Internal buffer only holds the batches after lastOffsetCommitted
    +    val rawList = synchronized {
    +      val sliceStart = startOrdinal - lastOffsetCommitted.offset.toInt - 1
    +      val sliceEnd = endOrdinal - lastOffsetCommitted.offset.toInt - 1
    +      batches.slice(sliceStart, sliceEnd)
    +    }
    +
         import sqlContext.implicits._
    +    val rawBatch = sqlContext.createDataset(rawList)
    +
    +
    +
    --- End diff --
    
    extra lines


---
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

Reply via email to