diff options
Diffstat (limited to 'streaming/src')
14 files changed, 17 insertions, 17 deletions
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala b/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala index 11a4c7dfd0..16c575bcc1 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala @@ -205,7 +205,7 @@ class CheckpointWriter( // also use the latest checkpoint time as the file name, so that we can recovery from the // latest checkpoint file. // - // Note: there is only one thread writting the checkpoint files, so we don't need to worry + // Note: there is only one thread writing the checkpoint files, so we don't need to worry // about thread-safety. val checkpointFile = Checkpoint.checkpointFile(checkpointDir, latestCheckpointTime) val backupFile = Checkpoint.checkpointBackupFile(checkpointDir, latestCheckpointTime) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala b/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala index 25e61578a1..e7f3a213d4 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala @@ -299,7 +299,7 @@ class StreamingContext private[streaming] ( /** * Create a input stream from TCP source hostname:port. Data is received using - * a TCP socket and the receive bytes it interepreted as object using the given + * a TCP socket and the receive bytes it interpreted as object using the given * converter. * @param hostname Hostname to connect to for receiving data * @param port Port to connect to for receiving data diff --git a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala index aad9a12c15..2a80cf4466 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaPairDStream.scala @@ -155,7 +155,7 @@ class JavaPairDStream[K, V](val dstream: DStream[(K, V)])( /** * Return a new DStream by applying `reduceByKey` to each RDD. The values for each key are * merged using the supplied reduce function. org.apache.spark.Partitioner is used to control - * thepartitioning of each RDD. + * the partitioning of each RDD. */ def reduceByKey(func: JFunction2[V, V, V], partitioner: Partitioner): JavaPairDStream[K, V] = { dstream.reduceByKey(func, partitioner) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala index 860b802725..05f4da6fac 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala @@ -530,7 +530,7 @@ class JavaStreamingContext(val ssc: StreamingContext) extends Closeable { * Return the current state of the context. The context can be in three possible states - * <ul> * <li> - * StreamingContextState.INTIALIZED - The context has been created, but not been started yet. + * StreamingContextState.INITIALIZED - The context has been created, but not been started yet. * Input DStreams, transformations and output operations can be created on the context. * </li> * <li> diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala index 1dcdb64e28..d6ff96e1fc 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala @@ -446,7 +446,7 @@ class PairDStreamFunctions[K, V](self: DStream[(K, V)]) * remember the partitioner despite the key being changed. * @param partitioner Partitioner for controlling the partitioning of each RDD in the new * DStream - * @param rememberPartitioner Whether to remember the paritioner object in the generated RDDs. + * @param rememberPartitioner Whether to remember the partitioner object in the generated RDDs. * @tparam S State type */ def updateStateByKey[S: ClassTag]( @@ -490,7 +490,7 @@ class PairDStreamFunctions[K, V](self: DStream[(K, V)]) * remember the partitioner despite the key being changed. * @param partitioner Partitioner for controlling the partitioning of each RDD in the new * DStream - * @param rememberPartitioner Whether to remember the paritioner object in the generated RDDs. + * @param rememberPartitioner Whether to remember the partitioner object in the generated RDDs. * @param initialRDD initial state value of each key. * @tparam S State type */ diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala index 080bc873fa..47eb9b806f 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/TransformedDStream.scala @@ -55,7 +55,7 @@ class TransformedDStream[U: ClassTag] ( /** * Wrap a body of code such that the call site and operation scope * information are passed to the RDDs created in this body properly. - * This has been overriden to make sure that `displayInnerRDDOps` is always `true`, that is, + * This has been overridden to make sure that `displayInnerRDDOps` is always `true`, that is, * the inner scopes and callsites of RDDs generated in `DStream.transform` are always * displayed in the UI. */ diff --git a/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingJobProgressListener.scala b/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingJobProgressListener.scala index 430f35a400..d6fcc582b9 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingJobProgressListener.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/ui/StreamingJobProgressListener.scala @@ -257,7 +257,7 @@ private[streaming] class StreamingJobProgressListener(ssc: StreamingContext) } batchUIData.foreach { _batchUIData => // We use an Iterable rather than explicitly converting to a seq so that updates - // will propegate + // will propagate val outputOpIdToSparkJobIds: Iterable[OutputOpIdAndSparkJobId] = Option(batchTimeToOutputOpIdSparkJobIdPair.get(batchTime).asScala) .getOrElse(Seq.empty) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala b/streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala index 2be1d6df86..3a21cfae5a 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala @@ -177,7 +177,7 @@ private[streaming] class OpenHashMapBasedStateMap[K, S]( new OpenHashMapBasedStateMap[K, S](this, deltaChainThreshold = deltaChainThreshold) } - /** Whether the delta chain lenght is long enough that it should be compacted */ + /** Whether the delta chain length is long enough that it should be compacted */ def shouldCompact: Boolean = { deltaChainLength >= deltaChainThreshold } diff --git a/streaming/src/test/scala/org/apache/spark/streaming/MapWithStateSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/MapWithStateSuite.scala index 403400904b..3b662ec183 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/MapWithStateSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/MapWithStateSuite.scala @@ -518,7 +518,7 @@ class MapWithStateSuite extends SparkFunSuite val mapWithStateStream = dstream.map { _ -> 1 }.mapWithState( StateSpec.function(runningCount)) - // Set internval make sure there is one RDD checkpointing + // Set interval make sure there is one RDD checkpointing mapWithStateStream.checkpoint(checkpointDuration) mapWithStateStream.stateSnapshots() } diff --git a/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala index 45424f9bac..95c1609d8e 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/ReceivedBlockHandlerSuite.scala @@ -202,13 +202,13 @@ class ReceivedBlockHandlerSuite blockManager = createBlockManager(12000, sparkConf) // there is not enough space to store this block in MEMORY, - // But BlockManager will be able to sereliaze this block to WAL + // But BlockManager will be able to serialize this block to WAL // and hence count returns correct value. testRecordcount(false, StorageLevel.MEMORY_ONLY, IteratorBlock((List.fill(70)(new Array[Byte](100))).iterator), blockManager, Some(70)) // there is not enough space to store this block in MEMORY, - // But BlockManager will be able to sereliaze this block to DISK + // But BlockManager will be able to serialize this block to DISK // and hence count returns correct value. testRecordcount(true, StorageLevel.MEMORY_AND_DISK, IteratorBlock((List.fill(70)(new Array[Byte](100))).iterator), blockManager, Some(70)) @@ -272,7 +272,7 @@ class ReceivedBlockHandlerSuite } /** - * Test storing of data using different types of Handler, StorageLevle and ReceivedBlocks + * Test storing of data using different types of Handler, StorageLevel and ReceivedBlocks * and verify the correct record count */ private def testRecordcount(isBlockManagedBasedBlockHandler: Boolean, diff --git a/streaming/src/test/scala/org/apache/spark/streaming/ReceiverInputDStreamSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/ReceiverInputDStreamSuite.scala index a4871b460e..6763ac64da 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/ReceiverInputDStreamSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/ReceiverInputDStreamSuite.scala @@ -97,7 +97,7 @@ class ReceiverInputDStreamSuite extends TestSuiteBase with BeforeAndAfterAll { assert(blockRDD.walRecordHandles.toSeq === blockInfos.map { _.walRecordHandleOption.get }) } - testWithWAL("createBlockRDD creates BlockRDD when some block info dont have WAL info") { + testWithWAL("createBlockRDD creates BlockRDD when some block info don't have WAL info") { receiverStream => val blockInfos1 = Seq.fill(2) { createBlockInfo(withWALInfo = true) } val blockInfos2 = Seq.fill(3) { createBlockInfo(withWALInfo = false) } diff --git a/streaming/src/test/scala/org/apache/spark/streaming/StateMapSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/StateMapSuite.scala index 7a76cafc9a..484f3733e8 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/StateMapSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/StateMapSuite.scala @@ -182,7 +182,7 @@ class StateMapSuite extends SparkFunSuite { * * - These operations are done on a test map in "sets". After each set, the map is "copied" * to create a new map, and the next set of operations are done on the new one. This tests - * whether the map data persistes correctly across copies. + * whether the map data persist correctly across copies. * * - Within each set, there are a number of operations to test whether the map correctly * updates and removes data without affecting the parent state map. diff --git a/streaming/src/test/scala/org/apache/spark/streaming/StreamingContextSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/StreamingContextSuite.scala index 197b3d1439..2159edce2b 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/StreamingContextSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/StreamingContextSuite.scala @@ -147,7 +147,7 @@ class StreamingContextSuite extends SparkFunSuite with BeforeAndAfter with Timeo } } - test("start with non-seriazable DStream checkpoints") { + test("start with non-serializable DStream checkpoints") { val checkpointDir = Utils.createTempDir() ssc = new StreamingContext(conf, batchDuration) ssc.checkpoint(checkpointDir.getAbsolutePath) diff --git a/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala b/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala index 82cd63bcaf..8269963edf 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/TestSuiteBase.scala @@ -56,7 +56,7 @@ private[streaming] class DummyInputDStream(ssc: StreamingContext) extends InputD /** * This is a input stream just for the testsuites. This is equivalent to a checkpointable, * replayable, reliable message queue like Kafka. It requires a sequence as input, and - * returns the i_th element at the i_th batch unde manual clock. + * returns the i_th element at the i_th batch under manual clock. */ class TestInputStream[T: ClassTag](_ssc: StreamingContext, input: Seq[Seq[T]], numPartitions: Int) extends InputDStream[T](_ssc) { |