Repository: spark Updated Branches: refs/heads/branch-2.0 6dae027a6 -> 7076b3707
[SPARK-15645][STREAMING] Fix some typos of Streaming module ## What changes were proposed in this pull request? No code change, just some typo fixing. ## How was this patch tested? Manually run project build with testing, and build is successful. Author: Xin Ren <iamsh...@126.com> Closes #13385 from keypointt/codeWalkThroughStreaming. (cherry picked from commit 5728aa558e44f056f3e5a7f8726ab174d3830103) Signed-off-by: Sean Owen <so...@cloudera.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/7076b370 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/7076b370 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/7076b370 Branch: refs/heads/branch-2.0 Commit: 7076b3707b530e19a8e8353dd8a4fd42dd148eab Parents: 6dae027 Author: Xin Ren <iamsh...@126.com> Authored: Mon May 30 08:40:03 2016 -0500 Committer: Sean Owen <so...@cloudera.com> Committed: Mon May 30 08:40:15 2016 -0500 ---------------------------------------------------------------------- .../scala/org/apache/spark/rdd/ParallelCollectionRDD.scala | 4 ++-- .../org/apache/spark/examples/streaming/CustomReceiver.scala | 2 +- .../org/apache/spark/examples/streaming/QueueStream.scala | 2 +- .../scala/org/apache/spark/streaming/dstream/DStream.scala | 2 +- .../org/apache/spark/streaming/receiver/BlockGenerator.scala | 6 +++--- .../scala/org/apache/spark/streaming/receiver/Receiver.scala | 6 +++--- .../org/apache/spark/streaming/scheduler/JobGenerator.scala | 3 +-- .../org/apache/spark/streaming/scheduler/ReceiverTracker.scala | 2 +- 8 files changed, 13 insertions(+), 14 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/core/src/main/scala/org/apache/spark/rdd/ParallelCollectionRDD.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/rdd/ParallelCollectionRDD.scala b/core/src/main/scala/org/apache/spark/rdd/ParallelCollectionRDD.scala index 34a1c11..e909273 100644 --- a/core/src/main/scala/org/apache/spark/rdd/ParallelCollectionRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/ParallelCollectionRDD.scala @@ -32,8 +32,8 @@ import org.apache.spark.util.Utils private[spark] class ParallelCollectionPartition[T: ClassTag]( var rddId: Long, var slice: Int, - var values: Seq[T]) - extends Partition with Serializable { + var values: Seq[T] + ) extends Partition with Serializable { def iterator: Iterator[T] = values.iterator http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala index f70975e..43044d0 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala @@ -29,7 +29,7 @@ import org.apache.spark.streaming.{Seconds, StreamingContext} import org.apache.spark.streaming.receiver.Receiver /** - * Custom Receiver that receives data over a socket. Received bytes is interpreted as + * Custom Receiver that receives data over a socket. Received bytes are interpreted as * text and \n delimited lines are considered as records. They are then counted and printed. * * To run this on your local machine, you need to first run a Netcat server http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/examples/src/main/scala/org/apache/spark/examples/streaming/QueueStream.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/QueueStream.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/QueueStream.scala index 5455aed..19bacd4 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/QueueStream.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/QueueStream.scala @@ -43,7 +43,7 @@ object QueueStream { reducedStream.print() ssc.start() - // Create and push some RDDs into + // Create and push some RDDs into rddQueue for (i <- 1 to 30) { rddQueue.synchronized { rddQueue += ssc.sparkContext.makeRDD(1 to 1000, 10) http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala ---------------------------------------------------------------------- diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala index 01dcfcf..147e8c1 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/DStream.scala @@ -52,7 +52,7 @@ import org.apache.spark.util.{CallSite, Utils} * `join`. These operations are automatically available on any DStream of pairs * (e.g., DStream[(Int, Int)] through implicit conversions. * - * DStreams internally is characterized by a few basic properties: + * A DStream internally is characterized by a few basic properties: * - A list of other DStreams that the DStream depends on * - A time interval at which the DStream generates an RDD * - A function that is used to generate an RDD after each time interval http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala ---------------------------------------------------------------------- diff --git a/streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala b/streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala index 4592e01..90309c0 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/receiver/BlockGenerator.scala @@ -86,13 +86,13 @@ private[streaming] class BlockGenerator( /** * The BlockGenerator can be in 5 possible states, in the order as follows. * - * - Initialized: Nothing has been started + * - Initialized: Nothing has been started. * - Active: start() has been called, and it is generating blocks on added data. * - StoppedAddingData: stop() has been called, the adding of data has been stopped, * but blocks are still being generated and pushed. * - StoppedGeneratingBlocks: Generating of blocks has been stopped, but * they are still being pushed. - * - StoppedAll: Everything has stopped, and the BlockGenerator object can be GCed. + * - StoppedAll: Everything has been stopped, and the BlockGenerator object can be GCed. */ private object GeneratorState extends Enumeration { type GeneratorState = Value @@ -148,7 +148,7 @@ private[streaming] class BlockGenerator( blockIntervalTimer.stop(interruptTimer = false) synchronized { state = StoppedGeneratingBlocks } - // Wait for the queue to drain and mark generated as stopped + // Wait for the queue to drain and mark state as StoppedAll logInfo("Waiting for block pushing thread to terminate") blockPushingThread.join() synchronized { state = StoppedAll } http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/streaming/src/main/scala/org/apache/spark/streaming/receiver/Receiver.scala ---------------------------------------------------------------------- diff --git a/streaming/src/main/scala/org/apache/spark/streaming/receiver/Receiver.scala b/streaming/src/main/scala/org/apache/spark/streaming/receiver/Receiver.scala index 5157ca6..d91a64d 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/receiver/Receiver.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/receiver/Receiver.scala @@ -32,7 +32,7 @@ import org.apache.spark.storage.StorageLevel * should define the setup steps necessary to start receiving data, * and `onStop()` should define the cleanup steps necessary to stop receiving data. * Exceptions while receiving can be handled either by restarting the receiver with `restart(...)` - * or stopped completely by `stop(...)` or + * or stopped completely by `stop(...)`. * * A custom receiver in Scala would look like this. * @@ -45,7 +45,7 @@ import org.apache.spark.storage.StorageLevel * // Call store(...) in those threads to store received data into Spark's memory. * * // Call stop(...), restart(...) or reportError(...) on any thread based on how - * // different errors needs to be handled. + * // different errors need to be handled. * * // See corresponding method documentation for more details * } @@ -71,7 +71,7 @@ import org.apache.spark.storage.StorageLevel * // Call store(...) in those threads to store received data into Spark's memory. * * // Call stop(...), restart(...) or reportError(...) on any thread based on how - * // different errors needs to be handled. + * // different errors need to be handled. * * // See corresponding method documentation for more details * } http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala ---------------------------------------------------------------------- diff --git a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala index 8f9421f..19c88f1 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/JobGenerator.scala @@ -19,7 +19,6 @@ package org.apache.spark.streaming.scheduler import scala.util.{Failure, Success, Try} -import org.apache.spark.SparkEnv import org.apache.spark.internal.Logging import org.apache.spark.rdd.RDD import org.apache.spark.streaming.{Checkpoint, CheckpointWriter, Time} @@ -239,7 +238,7 @@ class JobGenerator(jobScheduler: JobScheduler) extends Logging { logInfo("Restarted JobGenerator at " + restartTime) } - /** Generate jobs and perform checkpoint for the given `time`. */ + /** Generate jobs and perform checkpointing for the given `time`. */ private def generateJobs(time: Time) { // Checkpoint all RDDs marked for checkpointing to ensure their lineages are // truncated periodically. Otherwise, we may run into stack overflows (SPARK-6847). http://git-wip-us.apache.org/repos/asf/spark/blob/7076b370/streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceiverTracker.scala ---------------------------------------------------------------------- diff --git a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceiverTracker.scala b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceiverTracker.scala index 9aa2f0b..b9d898a 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceiverTracker.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/scheduler/ReceiverTracker.scala @@ -20,7 +20,7 @@ package org.apache.spark.streaming.scheduler import java.util.concurrent.{CountDownLatch, TimeUnit} import scala.collection.mutable.HashMap -import scala.concurrent.{ExecutionContext, Future} +import scala.concurrent.ExecutionContext import scala.language.existentials import scala.util.{Failure, Success} --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
