diff options
107 files changed, 135 insertions, 135 deletions
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala index 13e18a56c8..0d3a5237d9 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala @@ -66,7 +66,7 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) */ def unpersist(blocking: Boolean): JavaDoubleRDD = fromRDD(srdd.unpersist(blocking)) - // first() has to be overriden here in order for its return type to be Double instead of Object. + // first() has to be overridden here in order for its return type to be Double instead of Object. override def first(): JDouble = srdd.first() // Transformations (return a new RDD) diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala index f1aebbcd39..d362c40b7a 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala @@ -351,7 +351,7 @@ class JavaSparkContext(val sc: SparkContext) } /** - * Get an RDD for a Hadoop-readable dataset from a Hadooop JobConf giving its InputFormat and any + * Get an RDD for a Hadoop-readable dataset from a Hadoop JobConf giving its InputFormat and any * other necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable, * etc). * @@ -383,7 +383,7 @@ class JavaSparkContext(val sc: SparkContext) } /** - * Get an RDD for a Hadoop-readable dataset from a Hadooop JobConf giving its InputFormat and any + * Get an RDD for a Hadoop-readable dataset from a Hadoop JobConf giving its InputFormat and any * other necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable, * * @param conf JobConf for setting up the dataset. Note: This will be put into a Broadcast. diff --git a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala index 550e1ba6d3..8091aa8062 100644 --- a/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala +++ b/core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala @@ -74,7 +74,7 @@ private[spark] class TorrentBroadcast[T: ClassTag](obj: T, id: Long) } else { None } - // Note: use getSizeAsKb (not bytes) to maintain compatiblity if no units are provided + // Note: use getSizeAsKb (not bytes) to maintain compatibility if no units are provided blockSize = conf.getSizeAsKb("spark.broadcast.blockSize", "4m").toInt * 1024 } setConf(SparkEnv.get.conf) diff --git a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala index e2fda29044..000f7e8e1e 100644 --- a/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala +++ b/core/src/main/scala/org/apache/spark/deploy/history/ApplicationCache.scala @@ -87,7 +87,7 @@ private[history] class ApplicationCache( /** * The cache of applications. * - * Tagged as `protected` so as to allow subclasses in tests to accesss it directly + * Tagged as `protected` so as to allow subclasses in tests to access it directly */ protected val appCache: LoadingCache[CacheKey, CacheEntry] = { CacheBuilder.newBuilder() @@ -447,7 +447,7 @@ private[history] class CacheMetrics(prefix: String) extends Source { private[history] trait ApplicationCacheOperations { /** - * Get the application UI and the probe neededed to see if it has been updated. + * Get the application UI and the probe needed to see if it has been updated. * @param appId application ID * @param attemptId attempt ID * @return If found, the Spark UI and any history information to be used in the cache @@ -590,7 +590,7 @@ private[history] object ApplicationCacheCheckFilterRelay extends Logging { // name of the attempt ID entry in the filter configuration. Optional. val ATTEMPT_ID = "attemptId" - // namer of the filter to register + // name of the filter to register val FILTER_NAME = "org.apache.spark.deploy.history.ApplicationCacheCheckFilter" /** the application cache to relay requests to */ diff --git a/core/src/main/scala/org/apache/spark/executor/Executor.scala b/core/src/main/scala/org/apache/spark/executor/Executor.scala index 07e3c12bc9..48372d70d5 100644 --- a/core/src/main/scala/org/apache/spark/executor/Executor.scala +++ b/core/src/main/scala/org/apache/spark/executor/Executor.scala @@ -124,7 +124,7 @@ private[spark] class Executor( private val HEARTBEAT_MAX_FAILURES = conf.getInt("spark.executor.heartbeat.maxFailures", 60) /** - * Count the failure times of heartbeat. It should only be acessed in the heartbeat thread. Each + * Count the failure times of heartbeat. It should only be accessed in the heartbeat thread. Each * successful heartbeat will reset it to 0. */ private var heartbeatFailures = 0 diff --git a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala index c9606600ed..0f579cfe42 100644 --- a/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/DoubleRDDFunctions.scala @@ -141,7 +141,7 @@ class DoubleRDDFunctions(self: RDD[Double]) extends Logging with Serializable { * And on the input of 1 and 50 we would have a histogram of 1, 0, 1 * * Note: if your histogram is evenly spaced (e.g. [0, 10, 20, 30]) this can be switched - * from an O(log n) inseration to O(1) per element. (where n = # buckets) if you set evenBuckets + * from an O(log n) insertion to O(1) per element. (where n = # buckets) if you set evenBuckets * to true. * buckets must be sorted and not contain any duplicates. * buckets array must be at least two elements diff --git a/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala b/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala index def0aac720..dfcdd113df 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/InputFormatInfo.scala @@ -157,7 +157,7 @@ object InputFormatInfo { b) Decrement the currently allocated containers on that host. c) Compute rack info for each host and update rack -> count map based on (b). d) Allocate nodes based on (c) - e) On the allocation result, ensure that we dont allocate "too many" jobs on a single node + e) On the allocation result, ensure that we don't allocate "too many" jobs on a single node (even if data locality on that is very high) : this is to prevent fragility of job if a single (or small set of) hosts go down. diff --git a/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala b/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala index 1ce83485f0..6e9337bb90 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala @@ -45,7 +45,7 @@ class SplitInfo( hashCode } - // This is practically useless since most of the Split impl's dont seem to implement equals :-( + // This is practically useless since most of the Split impl's don't seem to implement equals :-( // So unless there is identity equality between underlyingSplits, it will always fail even if it // is pointing to same block. override def equals(other: Any): Boolean = other match { diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala index bcf65e9d7e..996c1f5d9e 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala @@ -1057,7 +1057,7 @@ private[spark] class BlockManager( failures += 1 replicationFailed = true peersFailedToReplicateTo += peer - if (failures > maxReplicationFailures) { // too many failures in replcating to peers + if (failures > maxReplicationFailures) { // too many failures in replicating to peers done = true } } diff --git a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala index 478a928acd..b19c30e2ff 100644 --- a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala +++ b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala @@ -70,7 +70,7 @@ final class ShuffleBlockFetcherIterator( private[this] var numBlocksToFetch = 0 /** - * The number of blocks proccessed by the caller. The iterator is exhausted when + * The number of blocks processed by the caller. The iterator is exhausted when * [[numBlocksProcessed]] == [[numBlocksToFetch]]. */ private[this] var numBlocksProcessed = 0 diff --git a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala index 5a8c291431..094953f2f5 100644 --- a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala +++ b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala @@ -102,7 +102,7 @@ private[spark] object UIWorkloadGenerator { try { setProperties(desc) job() - println("Job funished: " + desc) + println("Job finished: " + desc) } catch { case e: Exception => println("Job Failed: " + desc) diff --git a/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala b/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala index 73d126ff62..c9b7493fcd 100644 --- a/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala +++ b/core/src/main/scala/org/apache/spark/util/ParentClassLoader.scala @@ -18,7 +18,7 @@ package org.apache.spark.util /** - * A class loader which makes some protected methods in ClassLoader accesible. + * A class loader which makes some protected methods in ClassLoader accessible. */ private[spark] class ParentClassLoader(parent: ClassLoader) extends ClassLoader(parent) { diff --git a/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala b/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala index 83ded92609..a06db9a4fc 100644 --- a/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala +++ b/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala @@ -253,7 +253,7 @@ object SizeEstimator extends Logging { } else { // Estimate the size of a large array by sampling elements without replacement. // To exclude the shared objects that the array elements may link, sample twice - // and use the min one to caculate array size. + // and use the min one to calculate array size. val rand = new Random(42) val drawn = new OpenHashSet[Int](2 * ARRAY_SAMPLE_SIZE) val s1 = sampleArray(array, state, rand, drawn, length) diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index b5a98ce569..37c6c9bf90 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -1530,7 +1530,7 @@ private[spark] object Utils extends Logging { rawMod + (if (rawMod < 0) mod else 0) } - // Handles idiosyncracies with hash (add more as required) + // Handles idiosyncrasies with hash (add more as required) // This method should be kept in sync with // org.apache.spark.network.util.JavaUtils#nonNegativeHash(). def nonNegativeHash(obj: AnyRef): Int = { @@ -1600,7 +1600,7 @@ private[spark] object Utils extends Logging { * @param f function to be executed. If prepare is not None, the running time of each call to f * must be an order of magnitude longer than one millisecond for accurate timing. * @param prepare function to be executed before each call to f. Its running time doesn't count. - * @return the total time across all iterations (not couting preparation time) + * @return the total time across all iterations (not counting preparation time) */ def timeIt(numIters: Int)(f: => Unit, prepare: Option[() => Unit] = None): Long = { if (prepare.isEmpty) { diff --git a/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala b/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala index 1314217023..3c61528ab5 100644 --- a/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala +++ b/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala @@ -54,7 +54,7 @@ object RandomSampler { /** * Default maximum gap-sampling fraction. * For sampling fractions <= this value, the gap sampling optimization will be applied. - * Above this value, it is assumed that "tradtional" Bernoulli sampling is faster. The + * Above this value, it is assumed that "traditional" Bernoulli sampling is faster. The * optimal value for this will depend on the RNG. More expensive RNGs will tend to make * the optimal value higher. The most reliable way to determine this value for a new RNG * is to experiment. When tuning for a new RNG, I would expect a value of 0.5 to be close @@ -319,7 +319,7 @@ class GapSamplingReplacementIterator[T: ClassTag]( /** * Skip elements with replication factor zero (i.e. elements that won't be sampled). * Samples 'k' from geometric distribution P(k) = (1-q)(q)^k, where q = e^(-f), that is - * q is the probabililty of Poisson(0; f) + * q is the probability of Poisson(0; f) */ private def advance(): Unit = { val u = math.max(rng.nextDouble(), epsilon) diff --git a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala index 91fef772d1..bb2adff57e 100644 --- a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala @@ -34,7 +34,7 @@ import org.apache.spark.deploy.SparkSubmitUtils.MavenCoordinate import org.apache.spark.util.{ResetSystemProperties, Utils} // Note: this suite mixes in ResetSystemProperties because SparkSubmit.main() sets a bunch -// of properties that neeed to be cleared after tests. +// of properties that needed to be cleared after tests. class SparkSubmitSuite extends SparkFunSuite with Matchers diff --git a/core/src/test/scala/org/apache/spark/deploy/StandaloneDynamicAllocationSuite.scala b/core/src/test/scala/org/apache/spark/deploy/StandaloneDynamicAllocationSuite.scala index b7ff5c9e8c..d2e24912b5 100644 --- a/core/src/test/scala/org/apache/spark/deploy/StandaloneDynamicAllocationSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/StandaloneDynamicAllocationSuite.scala @@ -501,7 +501,7 @@ class StandaloneDynamicAllocationSuite master.self.askWithRetry[MasterStateResponse](RequestMasterState) } - /** Get the applictions that are active from Master */ + /** Get the applications that are active from Master */ private def getApplications(): Seq[ApplicationInfo] = { getMasterState.activeApps } diff --git a/core/src/test/scala/org/apache/spark/deploy/client/AppClientSuite.scala b/core/src/test/scala/org/apache/spark/deploy/client/AppClientSuite.scala index 379c038c55..7017296bd1 100644 --- a/core/src/test/scala/org/apache/spark/deploy/client/AppClientSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/client/AppClientSuite.scala @@ -159,7 +159,7 @@ class AppClientSuite extends SparkFunSuite with LocalSparkContext with BeforeAnd master.self.askWithRetry[MasterStateResponse](RequestMasterState) } - /** Get the applictions that are active from Master */ + /** Get the applications that are active from Master */ private def getApplications(): Seq[ApplicationInfo] = { getMasterState.activeApps } diff --git a/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala b/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala index e24188781f..c874b95b09 100644 --- a/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/history/ApplicationCacheSuite.scala @@ -219,7 +219,7 @@ class ApplicationCacheSuite extends SparkFunSuite with Logging with MockitoSugar val cacheEntry = cache.lookupCacheEntry(app1, None) assert(1 === cacheEntry.probeTime) assert(cacheEntry.completed) - // assert about queries made of the opereations + // assert about queries made of the operations assert(1 === operations.getAppUICount, "getAppUICount") assert(1 === operations.attachCount, "attachCount") @@ -338,7 +338,7 @@ class ApplicationCacheSuite extends SparkFunSuite with Logging with MockitoSugar } /** - * Look up the cache entry and assert that it maches in the expected value. + * Look up the cache entry and assert that it matches in the expected value. * This assertion works if the two CacheEntries are different -it looks at the fields. * UI are compared on object equality; the timestamp and completed flags directly. * @param appId application ID @@ -384,7 +384,7 @@ class ApplicationCacheSuite extends SparkFunSuite with Logging with MockitoSugar val operations = new StubCacheOperations() val clock = new ManualClock(0) val size = 5 - // only two entries are retained, so we expect evictions to occurr on lookups + // only two entries are retained, so we expect evictions to occur on lookups implicit val cache: ApplicationCache = new TestApplicationCache(operations, retainedApplications = size, clock = clock) diff --git a/core/src/test/scala/org/apache/spark/metrics/InputOutputMetricsSuite.scala b/core/src/test/scala/org/apache/spark/metrics/InputOutputMetricsSuite.scala index e5a448298a..056e5463a0 100644 --- a/core/src/test/scala/org/apache/spark/metrics/InputOutputMetricsSuite.scala +++ b/core/src/test/scala/org/apache/spark/metrics/InputOutputMetricsSuite.scala @@ -98,14 +98,14 @@ class InputOutputMetricsSuite extends SparkFunSuite with SharedSparkContext rdd.coalesce(4).count() } - // for count and coelesce, the same bytes should be read. + // for count and coalesce, the same bytes should be read. assert(bytesRead != 0) assert(bytesRead2 == bytesRead) } /** * This checks the situation where we have interleaved reads from - * different sources. Currently, we only accumulate fron the first + * different sources. Currently, we only accumulate from the first * read method we find in the task. This test uses cartesian to create * the interleaved reads. * @@ -183,7 +183,7 @@ class InputOutputMetricsSuite extends SparkFunSuite with SharedSparkContext assert(records == numRecords) } - test("input metrics on recordsd read with cache") { + test("input metrics on records read with cache") { // prime the cache manager val rdd = sc.textFile(tmpFilePath, 4).cache() rdd.collect() diff --git a/core/src/test/scala/org/apache/spark/rdd/DoubleRDDSuite.scala b/core/src/test/scala/org/apache/spark/rdd/DoubleRDDSuite.scala index 76451788d2..864adddad3 100644 --- a/core/src/test/scala/org/apache/spark/rdd/DoubleRDDSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/DoubleRDDSuite.scala @@ -164,8 +164,8 @@ class DoubleRDDSuite extends SparkFunSuite with SharedSparkContext { val expectedHistogramResults = Array(4, 2, 1, 2, 3) assert(histogramResults === expectedHistogramResults) } - // Make sure this works with a NaN end bucket and an inifity - test("WorksMixedRangeWithUnevenBucketsAndNaNAndNaNRangeAndInfity") { + // Make sure this works with a NaN end bucket and an infinity + test("WorksMixedRangeWithUnevenBucketsAndNaNAndNaNRangeAndInfinity") { // Make sure that it works with two unequally spaced buckets and elements in each val rdd = sc.parallelize(Seq(-0.01, 0.0, 1, 2, 3, 5, 6, 11.01, 12.0, 199.0, 200.0, 200.1, 1.0/0.0, -1.0/0.0, Double.NaN)) diff --git a/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala b/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala index 7d51538d92..b0d69de6e2 100644 --- a/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala @@ -182,7 +182,7 @@ class PairRDDFunctionsSuite extends SparkFunSuite with SharedSparkContext { assert(sums(2) === 1) } - test("reduceByKey with many output partitons") { + test("reduceByKey with many output partitions") { val pairs = sc.parallelize(Array((1, 1), (1, 2), (1, 3), (1, 1), (2, 1))) val sums = pairs.reduceByKey(_ + _, 10).collect() assert(sums.toSet === Set((1, 7), (2, 1))) diff --git a/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala index d8849d5948..d1c7143abf 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala @@ -663,7 +663,7 @@ class DAGSchedulerSuite extends SparkFunSuite with LocalSparkContext with Timeou completeShuffleMapStageSuccessfully(0, 1, numShufflePartitions = parts) completeNextResultStageWithSuccess(1, 1) - // Confirm job finished succesfully + // Confirm job finished successfully sc.listenerBus.waitUntilEmpty(1000) assert(ended === true) assert(results === (0 until parts).map { idx => idx -> 42 }.toMap) diff --git a/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala index 2c99dd5afb..d35ca411f4 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/TaskSetManagerSuite.scala @@ -396,7 +396,7 @@ class TaskSetManagerSuite extends SparkFunSuite with LocalSparkContext with Logg val rescheduleDelay = 300L val conf = new SparkConf(). set("spark.scheduler.executorTaskBlacklistTime", rescheduleDelay.toString). - // dont wait to jump locality levels in this test + // don't wait to jump locality levels in this test set("spark.locality.wait", "0") sc = new SparkContext("local", "test", conf) diff --git a/core/src/test/scala/org/apache/spark/serializer/SerializationDebuggerSuite.scala b/core/src/test/scala/org/apache/spark/serializer/SerializationDebuggerSuite.scala index 683aaa3aab..bdee889cdc 100644 --- a/core/src/test/scala/org/apache/spark/serializer/SerializationDebuggerSuite.scala +++ b/core/src/test/scala/org/apache/spark/serializer/SerializationDebuggerSuite.scala @@ -191,7 +191,7 @@ class SerializationDebuggerSuite extends SparkFunSuite with BeforeAndAfterEach { } val originalException = new NotSerializableException("someClass") - // verify thaht original exception is returned on failure + // verify that original exception is returned on failure assert(SerializationDebugger.improveException(o, originalException).eq(originalException)) } } diff --git a/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala b/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala index 853503bbc2..83eba3690e 100644 --- a/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/random/XORShiftRandomSuite.scala @@ -53,7 +53,7 @@ class XORShiftRandomSuite extends SparkFunSuite with Matchers { * Perform the chi square test on the 5 rows of randomly generated numbers evenly divided into * 10 bins. chiSquareTest returns true iff the null hypothesis (that the classifications * represented by the counts in the columns of the input 2-way table are independent of the - * rows) can be rejected with 100 * (1 - alpha) percent confidence, where alpha is prespeficied + * rows) can be rejected with 100 * (1 - alpha) percent confidence, where alpha is prespecified * as 0.05 */ val chiTest = new ChiSquareTest diff --git a/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala b/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala index 7796f362bb..d498af9c39 100644 --- a/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala +++ b/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala @@ -38,7 +38,7 @@ object SkewedGroupByTest { val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p => val ranGen = new Random - // map output sizes lineraly increase from the 1st to the last + // map output sizes linearly increase from the 1st to the last numKVPairs = (1.0 * (p + 1) / numMappers * numKVPairs).toInt var arr1 = new Array[(Int, Array[Byte])](numKVPairs) diff --git a/external/flume-sink/src/main/scala/org/apache/spark/streaming/flume/sink/Logging.scala b/external/flume-sink/src/main/scala/org/apache/spark/streaming/flume/sink/Logging.scala index aa530a7121..09d3fe91e4 100644 --- a/external/flume-sink/src/main/scala/org/apache/spark/streaming/flume/sink/Logging.scala +++ b/external/flume-sink/src/main/scala/org/apache/spark/streaming/flume/sink/Logging.scala @@ -101,7 +101,7 @@ private[sink] trait Logging { private def initializeLogging() { Logging.initialized = true - // Force a call into slf4j to initialize it. Avoids this happening from mutliple threads + // Force a call into slf4j to initialize it. Avoids this happening from multiple threads // and triggering this: http://mailman.qos.ch/pipermail/slf4j-dev/2010-April/002956.html log } diff --git a/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeBatchFetcher.scala b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeBatchFetcher.scala index b9d4e762ca..3555fa68b6 100644 --- a/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeBatchFetcher.scala +++ b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeBatchFetcher.scala @@ -77,7 +77,7 @@ private[flume] class FlumeBatchFetcher(receiver: FlumePollingReceiver) extends R /** * Gets a batch of events from the specified client. This method does not handle any exceptions - * which will be propogated to the caller. + * which will be propagated to the caller. * @param client Client to get events from * @return [[Some]] which contains the event batch if Flume sent any events back, else [[None]] */ @@ -96,8 +96,8 @@ private[flume] class FlumeBatchFetcher(receiver: FlumePollingReceiver) extends R } /** - * Store the events in the buffer to Spark. This method will not propogate any exceptions, - * but will propogate any other errors. + * Store the events in the buffer to Spark. This method will not propagate any exceptions, + * but will propagate any other errors. * @param buffer The buffer to store * @return true if the data was stored without any exception being thrown, else false */ diff --git a/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaCluster.scala b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaCluster.scala index 8a66621a31..726b5d8ec3 100644 --- a/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaCluster.scala +++ b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaCluster.scala @@ -167,7 +167,7 @@ class KafkaCluster(val kafkaParams: Map[String, String]) extends Serializable { ): Either[Err, Map[TopicAndPartition, LeaderOffset]] = { getLeaderOffsets(topicAndPartitions, before, 1).right.map { r => r.map { kv => - // mapValues isnt serializable, see SI-7005 + // mapValues isn't serializable, see SI-7005 kv._1 -> kv._2.head } } diff --git a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala index b5b76cb92d..23b74da642 100644 --- a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala +++ b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala @@ -132,7 +132,7 @@ private[kinesis] object KinesisRecordProcessor extends Logging { * Retry the given amount of times with a random backoff time (millis) less than the * given maxBackOffMillis * - * @param expression expression to evalute + * @param expression expression to evaluate * @param numRetriesLeft number of retries left * @param maxBackOffMillis: max millis between retries * diff --git a/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDDSuite.scala b/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDDSuite.scala index 2555332d22..905c33834d 100644 --- a/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDDSuite.scala +++ b/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDDSuite.scala @@ -122,7 +122,7 @@ abstract class KinesisBackedBlockRDDTests(aggregateTestData: Boolean) testIsBlockValid = true) } - testIfEnabled("Test whether RDD is valid after removing blocks from block anager") { + testIfEnabled("Test whether RDD is valid after removing blocks from block manager") { testRDD(numPartitions = 2, numPartitionsInBM = 2, numPartitionsInKinesis = 2, testBlockRemove = true) } diff --git a/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisReceiverSuite.scala b/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisReceiverSuite.scala index fd15b6ccdc..deac9090e2 100644 --- a/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisReceiverSuite.scala +++ b/external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisReceiverSuite.scala @@ -194,7 +194,7 @@ class KinesisReceiverSuite extends TestSuiteBase with Matchers with BeforeAndAft verify(checkpointerMock, times(1)).checkpoint() } - test("retry failed after exhausing all retries") { + test("retry failed after exhausting all retries") { val expectedErrorMessage = "final try error message" when(checkpointerMock.checkpoint()) .thenThrow(new ThrottlingException("error message")) diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala index fe884d0022..5485e30f5a 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala @@ -297,7 +297,7 @@ abstract class Graph[VD: ClassTag, ED: ClassTag] protected () extends Serializab /** * Restricts the graph to only the vertices and edges satisfying the predicates. The resulting - * subgraph satisifies + * subgraph satisfies * * {{{ * V' = {v : for all v in V where vpred(v)} diff --git a/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala b/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala index d537b6141c..fcb1b5999f 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala @@ -236,11 +236,11 @@ class GraphOps[VD: ClassTag, ED: ClassTag](graph: Graph[VD, ED]) extends Seriali * @param preprocess a function to compute new vertex and edge data before filtering * @param epred edge pred to filter on after preprocess, see more details under * [[org.apache.spark.graphx.Graph#subgraph]] - * @param vpred vertex pred to filter on after prerocess, see more details under + * @param vpred vertex pred to filter on after preprocess, see more details under * [[org.apache.spark.graphx.Graph#subgraph]] * @tparam VD2 vertex type the vpred operates on * @tparam ED2 edge type the epred operates on - * @return a subgraph of the orginal graph, with its data unchanged + * @return a subgraph of the original graph, with its data unchanged * * @example This function can be used to filter the graph based on some property, without * changing the vertex and edge values in your program. For example, we could remove the vertices diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala index 6dab465fb9..a4e293d74a 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala @@ -49,7 +49,7 @@ object ShippableVertexPartition { /** * Construct a `ShippableVertexPartition` from the given vertices with the specified routing * table, filling in missing vertices mentioned in the routing table using `defaultVal`, - * and merging duplicate vertex atrribute with mergeFunc. + * and merging duplicate vertex attribute with mergeFunc. */ def apply[VD: ClassTag]( iter: Iterator[(VertexId, VD)], routingTable: RoutingTablePartition, defaultVal: VD, diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala b/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala index 46faad2e68..00ba358a9b 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala @@ -54,7 +54,7 @@ import org.apache.spark.graphx._ * }}} * * `alpha` is the random reset probability (typically 0.15), `inNbrs[i]` is the set of - * neighbors whick link to `i` and `outDeg[j]` is the out degree of vertex `j`. + * neighbors which link to `i` and `outDeg[j]` is the out degree of vertex `j`. * * Note that this is not the "normalized" PageRank and as a consequence pages that have no * inlinks will have a PageRank of alpha. @@ -209,7 +209,7 @@ object PageRank extends Logging { } // Set the weight on the edges based on the degree .mapTriplets( e => 1.0 / e.srcAttr ) - // Set the vertex attributes to (initalPR, delta = 0) + // Set the vertex attributes to (initialPR, delta = 0) .mapVertices { (id, attr) => if (id == src) (resetProb, Double.NegativeInfinity) else (0.0, 0.0) } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/package.scala b/graphx/src/main/scala/org/apache/spark/graphx/package.scala index 6aab28ff05..dde25b9659 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/package.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/package.scala @@ -30,7 +30,7 @@ package object graphx { */ type VertexId = Long - /** Integer identifer of a graph partition. Must be less than 2^30. */ + /** Integer identifier of a graph partition. Must be less than 2^30. */ // TODO: Consider using Char. type PartitionID = Int diff --git a/graphx/src/main/scala/org/apache/spark/graphx/util/BytecodeUtils.scala b/graphx/src/main/scala/org/apache/spark/graphx/util/BytecodeUtils.scala index a6d0cb6409..d76e84ed8c 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/util/BytecodeUtils.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/util/BytecodeUtils.scala @@ -92,7 +92,7 @@ private[graphx] object BytecodeUtils { /** * Given the class name, return whether we should look into the class or not. This is used to - * skip examing a large quantity of Java or Scala classes that we know for sure wouldn't access + * skip examining a large quantity of Java or Scala classes that we know for sure wouldn't access * the closures. Note that the class name is expected in ASM style (i.e. use "/" instead of "."). */ private def skipClass(className: String): Boolean = { diff --git a/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala index f497e001df..cb981797d3 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala @@ -229,7 +229,7 @@ class GraphSuite extends SparkFunSuite with LocalSparkContext { test("subgraph") { withSpark { sc => - // Create a star graph of 10 veritces. + // Create a star graph of 10 vertices. val n = 10 val star = starGraph(sc, n) // Take only vertices whose vids are even diff --git a/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala b/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala index f21b623e93..2cd94fa8f5 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala @@ -523,7 +523,7 @@ private[ml] object FeedForwardTopology { /** * Creates a multi-layer perceptron * @param layerSizes sizes of layers including input and output size - * @param softmax wether to use SoftMax or Sigmoid function for an output layer. + * @param softmax whether to use SoftMax or Sigmoid function for an output layer. * Softmax is default * @return multilayer perceptron topology */ diff --git a/mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala b/mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala index 521d209a8f..27554acdf3 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/attribute/attributes.scala @@ -481,7 +481,7 @@ object NominalAttribute extends AttributeFactory { * A binary attribute. * @param name optional name * @param index optional index - * @param values optionla values. If set, its size must be 2. + * @param values optional values. If set, its size must be 2. */ @DeveloperApi class BinaryAttribute private[ml] ( diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala index f8de4e2220..c8ec0c1685 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/RankingMetrics.scala @@ -83,7 +83,7 @@ class RankingMetrics[T: ClassTag](predictionAndLabels: RDD[(Array[T], Array[T])] /** * Returns the mean average precision (MAP) of all the queries. * If a query has an empty ground truth set, the average precision will be zero and a log - * warining is generated. + * warning is generated. */ lazy val meanAveragePrecision: Double = { predictionAndLabels.map { case (pred, lab) => diff --git a/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala b/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala index 07eb750b06..790d6b101e 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala @@ -58,7 +58,7 @@ class AssociationRules private[fpm] ( /** * Computes the association rules with confidence above [[minConfidence]]. * @param freqItemsets frequent itemset model obtained from [[FPGrowth]] - * @return a [[Set[Rule[Item]]] containing the assocation rules. + * @return a [[Set[Rule[Item]]] containing the association rules. * */ @Since("1.5.0") diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala index 240781bcd3..58fd010e49 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala @@ -158,7 +158,7 @@ object LinearDataGenerator { /** * Generate an RDD containing sample data for Linear Regression models - including Ridge, Lasso, - * and uregularized variants. + * and unregularized variants. * * @param sc SparkContext to be used for generating the RDD. * @param nexamples Number of examples that will be contained in the RDD. diff --git a/mllib/src/test/scala/org/apache/spark/ml/source/libsvm/LibSVMRelationSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/source/libsvm/LibSVMRelationSuite.scala index 71f4926290..114a238462 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/source/libsvm/LibSVMRelationSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/source/libsvm/LibSVMRelationSuite.scala @@ -88,7 +88,7 @@ class LibSVMRelationSuite extends SparkFunSuite with MLlibTestSparkContext { val df = sqlContext.read.format("libsvm").load(path) val tempDir2 = Utils.createTempDir() val writepath = tempDir2.toURI.toString - // TODO: Remove requirement to coalesce by supporting mutiple reads. + // TODO: Remove requirement to coalesce by supporting multiple reads. df.coalesce(1).write.format("libsvm").mode(SaveMode.Overwrite).save(writepath) val df2 = sqlContext.read.format("libsvm").load(writepath) diff --git a/mllib/src/test/scala/org/apache/spark/mllib/classification/LogisticRegressionSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/classification/LogisticRegressionSuite.scala index cea0adc55c..28fada7053 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/classification/LogisticRegressionSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/classification/LogisticRegressionSuite.scala @@ -496,7 +496,7 @@ class LogisticRegressionSuite extends SparkFunSuite with MLlibTestSparkContext w * features = as.matrix(data.frame(data$V2, data$V3, data$V4, data$V5)) * weights = coef(glmnet(features,label, family="multinomial", alpha = 0, lambda = 0)) * - * The model weights of mutinomial logstic regression in R have `K` set of linear predictors + * The model weights of multinomial logistic regression in R have `K` set of linear predictors * for `K` classes classification problem; however, only `K-1` set is required if the first * outcome is chosen as a "pivot", and the other `K-1` outcomes are separately regressed against * the pivot outcome. This can be done by subtracting the first weights from those `K-1` set diff --git a/mllib/src/test/scala/org/apache/spark/mllib/stat/HypothesisTestSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/stat/HypothesisTestSuite.scala index 142b90e764..46fcebe132 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/stat/HypothesisTestSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/stat/HypothesisTestSuite.scala @@ -144,7 +144,7 @@ class HypothesisTestSuite extends SparkFunSuite with MLlibTestSparkContext { assert(chi.size === numCols) assert(chi(1000) != null) // SPARK-3087 - // Detect continous features or labels + // Detect continuous features or labels val random = new Random(11L) val continuousLabel = Seq.fill(100000)(LabeledPoint(random.nextDouble(), Vectors.dense(random.nextInt(2)))) diff --git a/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala index dca8ea815a..5518bdf527 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/tree/DecisionTreeSuite.scala @@ -1075,7 +1075,7 @@ object DecisionTreeSuite extends SparkFunSuite { assert(a.isLeaf === b.isLeaf) assert(a.split === b.split) (a.stats, b.stats) match { - // TODO: Check other fields besides the infomation gain. + // TODO: Check other fields besides the information gain. case (Some(aStats), Some(bStats)) => assert(aStats.gain === bStats.gain) case (None, None) => case _ => throw new AssertionError( diff --git a/project/MimaExcludes.scala b/project/MimaExcludes.scala index c4c8d8870f..faa52bf18c 100644 --- a/project/MimaExcludes.scala +++ b/project/MimaExcludes.scala @@ -334,7 +334,7 @@ object MimaExcludes { excludePackage("org.apache.spark.sql.columnar"), // The shuffle package is considered private. excludePackage("org.apache.spark.shuffle"), - // The collections utlities are considered pricate. + // The collections utilities are considered private. excludePackage("org.apache.spark.util.collection") ) ++ MimaBuild.excludeSparkClass("streaming.flume.FlumeTestUtils") ++ @@ -639,7 +639,7 @@ object MimaExcludes { Seq( MimaBuild.excludeSparkPackage("deploy"), MimaBuild.excludeSparkPackage("ml"), - // SPARK-7910 Adding a method to get the partioner to JavaRDD, + // SPARK-7910 Adding a method to get the partitioner to JavaRDD, ProblemFilters.exclude[MissingMethodProblem]("org.apache.spark.api.java.JavaRDDLike.partitioner"), // SPARK-5922 Adding a generalized diff(other: RDD[(VertexId, VD)]) to VertexRDD ProblemFilters.exclude[MissingMethodProblem]("org.apache.spark.graphx.VertexRDD.diff"), @@ -657,7 +657,7 @@ object MimaExcludes { ProblemFilters.exclude[MissingClassProblem]( "org.apache.spark.scheduler.OutputCommitCoordinator$OutputCommitCoordinatorEndpoint") ) ++ Seq( - // SPARK-4655 - Making Stage an Abstract class broke binary compatility even though + // SPARK-4655 - Making Stage an Abstract class broke binary compatibility even though // the stage class is defined as private[spark] ProblemFilters.exclude[AbstractClassProblem]("org.apache.spark.scheduler.Stage") ) ++ Seq( diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala index f108264861..1219d4d453 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala @@ -305,7 +305,7 @@ trait Row extends Serializable { * @throws ClassCastException when data type does not match. */ def getStruct(i: Int): Row = { - // Product and Row both are recoginized as StructType in a Row + // Product and Row both are recognized as StructType in a Row val t = get(i) if (t.isInstanceOf[Product]) { Row.fromTuple(t.asInstanceOf[Product]) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala index c12b5c20ea..bf07f4557a 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala @@ -29,7 +29,7 @@ import org.apache.spark.util.Utils */ object ScalaReflection extends ScalaReflection { val universe: scala.reflect.runtime.universe.type = scala.reflect.runtime.universe - // Since we are creating a runtime mirror usign the class loader of current thread, + // Since we are creating a runtime mirror using the class loader of current thread, // we need to use def at here. So, every time we call mirror, it is using the // class loader of the current thread. // SPARK-13640: Synchronize this because universe.runtimeMirror is not thread-safe in Scala 2.10. diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala index ad56c98649..9c38dd2ee4 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala @@ -155,7 +155,7 @@ object DecimalPrecision extends Rule[LogicalPlan] { * * Note that technically this is an "optimization" and should go into the optimizer. However, * by the time the optimizer runs, these comparison expressions would be pretty hard to pattern - * match because there are multuple (at least 2) levels of casts involved. + * match because there are multiple (at least 2) levels of casts involved. * * There are a lot more possible rules we can implement, but we don't do them * because we are not sure how common they are. diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala index 38c1641f73..2e30d83a60 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala @@ -96,7 +96,7 @@ import org.apache.spark.sql.types.IntegerType * This rule duplicates the input data by two or more times (# distinct groups + an optional * non-distinct group). This will put quite a bit of memory pressure of the used aggregate and * exchange operators. Keeping the number of distinct groups as low a possible should be priority, - * we could improve this in the current rule by applying more advanced expression cannocalization + * we could improve this in the current rule by applying more advanced expression canonicalization * techniques. */ object DistinctAggregationRewriter extends Rule[LogicalPlan] { diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala index 57bdb164e1..0f85f44ffa 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercion.scala @@ -307,7 +307,7 @@ object HiveTypeCoercion { case p @ Equality(left @ TimestampType(), right @ StringType()) => p.makeCopy(Array(left, Cast(right, TimestampType))) - // We should cast all relative timestamp/date/string comparison into string comparisions + // We should cast all relative timestamp/date/string comparison into string comparisons // This behaves as a user would expect because timestamp strings sort lexicographically. // i.e. TimeStamp(2013-01-01 00:00 ...) < "2014" = true case p @ BinaryComparison(left @ StringType(), right @ DateType()) => diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala index 3831535574..8bdf9b29c9 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala @@ -53,7 +53,7 @@ object AttributeSet { * cosmetically (e.g., the names have different capitalizations). * * Note that we do not override equality for Attribute references as it is really weird when - * `AttributeReference("a"...) == AttrributeReference("b", ...)`. This tactic leads to broken tests, + * `AttributeReference("a"...) == AttributeReference("b", ...)`. This tactic leads to broken tests, * and also makes doing transformations hard (we always try keep older trees instead of new ones * when the transformation was a no-op). */ diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSet.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSet.scala index acea049adc..644a5b28a2 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSet.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSet.scala @@ -36,7 +36,7 @@ object ExpressionSet { * Internally this set uses the canonical representation, but keeps also track of the original * expressions to ease debugging. Since different expressions can share the same canonical * representation, this means that operations that extract expressions from this set are only - * guranteed to see at least one such expression. For example: + * guaranteed to see at least one such expression. For example: * * {{{ * val set = AttributeSet(a + 1, 1 + a) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDF.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDF.scala index 22184f1ddf..500ff447a9 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDF.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDF.scala @@ -973,7 +973,7 @@ case class ScalaUDF( // scalastyle:on line.size.limit - // Generate codes used to convert the arguments to Scala type for user-defined funtions + // Generate codes used to convert the arguments to Scala type for user-defined functions private[this] def genCodeForConverter(ctx: CodegenContext, index: Int): String = { val converterClassName = classOf[Any => Any].getName val typeConvertersClassName = CatalystTypeConverters.getClass.getName + ".MODULE$" diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala index c4265a7539..3dbe634898 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala @@ -126,7 +126,7 @@ class CodegenContext { * For expressions that appear more than once, generate additional code to prevent * recomputing the value. * - * For example, consider two exprsesion generated from this SQL statement: + * For example, consider two expression generated from this SQL statement: * SELECT (col1 + col2), (col1 + col2) / col3. * * equivalentExpressions will match the tree containing `col1 + col2` and it will only @@ -140,7 +140,7 @@ class CodegenContext { // Foreach expression that is participating in subexpression elimination, the state to use. val subExprEliminationExprs = mutable.HashMap.empty[Expression, SubExprEliminationState] - // The collection of sub-exression result resetting methods that need to be called on each row. + // The collection of sub-expression result resetting methods that need to be called on each row. val subexprFunctions = mutable.ArrayBuffer.empty[String] def declareAddedFunctions(): String = { diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/conditionalExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/conditionalExpressions.scala index 5ceb36513f..103ab365e3 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/conditionalExpressions.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/conditionalExpressions.scala @@ -214,7 +214,7 @@ case class CaseWhen(branches: Seq[(Expression, Expression)], elseValue: Option[E /** Factory methods for CaseWhen. */ object CaseWhen { - // The maxium number of switches supported with codegen. + // The maximum number of switches supported with codegen. val MAX_NUM_CASES_FOR_CODEGEN = 20 def apply(branches: Seq[(Expression, Expression)], elseValue: Expression): CaseWhen = { diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala index b95c5dd892..7eba617fcd 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala @@ -364,7 +364,7 @@ object MapObjects { * used as input for the `lambdaFunction`. It also carries the element type info. * @param lambdaFunction A function that take the `loopVar` as input, and used as lambda function * to handle collection elements. - * @param inputData An expression that when evaluted returns a collection object. + * @param inputData An expression that when evaluated returns a collection object. */ case class MapObjects private( loopVar: LambdaVariable, diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala index e4417e0955..da90ddbd63 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/NumberConverter.scala @@ -66,7 +66,7 @@ object NumberConverter { * negative digit is found, ignore the suffix starting there. * * @param radix must be between MIN_RADIX and MAX_RADIX - * @param fromPos is the first element that should be conisdered + * @param fromPos is the first element that should be considered * @return the result should be treated as an unsigned 64-bit integer. */ private def encode(radix: Int, fromPos: Int): Long = { diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala index de9a56dc9c..4e7bbc38d6 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala @@ -276,7 +276,7 @@ class AnalysisErrorSuite extends AnalysisTest { test("SPARK-6452 regression test") { // CheckAnalysis should throw AnalysisException when Aggregate contains missing attribute(s) - // Since we manually construct the logical plan at here and Sum only accetp + // Since we manually construct the logical plan at here and Sum only accept // LongType, DoubleType, and DecimalType. We use LongType as the type of a. val plan = Aggregate( diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisSuite.scala index aa1d2b0861..8b568b6dd6 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisSuite.scala @@ -250,7 +250,7 @@ class AnalysisSuite extends AnalysisTest { assertAnalysisSuccess(plan) } - test("SPARK-8654: different types in inlist but can be converted to a commmon type") { + test("SPARK-8654: different types in inlist but can be converted to a common type") { val plan = Project(Alias(In(Literal(null), Seq(Literal(1), Literal(1.2345))), "a")() :: Nil, LocalRelation() ) diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercionSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercionSuite.scala index c30434a006..6f289dcc47 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercionSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/HiveTypeCoercionSuite.scala @@ -205,7 +205,7 @@ class HiveTypeCoercionSuite extends PlanTest { Project(Seq(Alias(transformed, "a")()), testRelation)) } - test("cast NullType for expresions that implement ExpectsInputTypes") { + test("cast NullType for expressions that implement ExpectsInputTypes") { import HiveTypeCoercionSuite._ ruleTest(HiveTypeCoercion.ImplicitTypeCasts, diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSetSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSetSuite.scala index ce42e5784c..0b350c6a98 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSetSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSetSuite.scala @@ -70,7 +70,7 @@ class ExpressionSetSuite extends SparkFunSuite { // Not commutative setTest(2, aUpper - bUpper, bUpper - aUpper) - // Reversable + // Reversible setTest(1, aUpper > bUpper, bUpper < aUpper) setTest(1, aUpper >= bUpper, bUpper <= aUpper) diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlusSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlusSuite.scala index 0dbfb01e88..f5374229ca 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlusSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlusSuite.scala @@ -131,7 +131,7 @@ class HyperLogLogPlusPlusSuite extends SparkFunSuite { i += 1 } - // Merge the lower and upper halfs. + // Merge the lower and upper halves. hll.merge(buffer1a, buffer1b) // Create the other buffer in reverse diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala index f7ba61d2b8..1751720a7d 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala @@ -78,7 +78,7 @@ class TypedColumn[-T, U]( * * {{{ * df("columnName") // On a specific DataFrame. - * col("columnName") // A generic column no yet associcated with a DataFrame. + * col("columnName") // A generic column no yet associated with a DataFrame. * col("columnName.field") // Extracting a struct field * col("`a.column.with.dots`") // Escape `.` in column names. * $"columnName" // Scala short hand for a named column. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/GroupedDataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/GroupedDataset.scala index 472ae716f1..a8700de135 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/GroupedDataset.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/GroupedDataset.scala @@ -223,7 +223,7 @@ class GroupedDataset[K, V] private[sql]( * Internal helper function for building typed aggregations that return tuples. For simplicity * and code reuse, we do this without the help of the type system and then use helper functions * that cast appropriately for the user facing interface. - * TODO: does not handle aggrecations that return nonflat results, + * TODO: does not handle aggregations that return nonflat results, */ protected def aggUntyped(columns: TypedColumn[_, _]*): Dataset[_] = { val encoders = columns.map(_.encoder) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala index 3be4cce045..a92c99e06f 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlan.scala @@ -52,7 +52,7 @@ abstract class SparkPlan extends QueryPlan[SparkPlan] with Logging with Serializ protected def sparkContext = sqlContext.sparkContext // sqlContext will be null when we are being deserialized on the slaves. In this instance - // the value of subexpressionEliminationEnabled will be set by the desserializer after the + // the value of subexpressionEliminationEnabled will be set by the deserializer after the // constructor has run. val subexpressionEliminationEnabled: Boolean = if (sqlContext != null) { sqlContext.conf.subexpressionEliminationEnabled @@ -65,7 +65,7 @@ abstract class SparkPlan extends QueryPlan[SparkPlan] with Logging with Serializ */ private val prepareCalled = new AtomicBoolean(false) - /** Overridden make copy also propogates sqlContext to copied plan. */ + /** Overridden make copy also propagates sqlContext to copied plan. */ override def makeCopy(newArgs: Array[AnyRef]): SparkPlan = { SQLContext.setActive(sqlContext) super.makeCopy(newArgs) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala index 3ec01185c4..f9d606e37e 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/ColumnType.scala @@ -40,7 +40,7 @@ import org.apache.spark.unsafe.types.UTF8String * so we do not have helper methods for them. * * - * WARNNING: This only works with HeapByteBuffer + * WARNING: This only works with HeapByteBuffer */ private[columnar] object ByteBufferHelper { def getInt(buffer: ByteBuffer): Int = { diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala index c3f8d7f75a..18a460fc85 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala @@ -88,7 +88,7 @@ private[sql] object PartitioningUtils { }.unzip // We create pairs of (path -> path's partition value) here - // If the corresponding partition value is None, the pair will be skiped + // If the corresponding partition value is None, the pair will be skipped val pathsWithPartitionValues = paths.zip(partitionValues).flatMap(x => x._2.map(x._1 -> _)) if (pathsWithPartitionValues.isEmpty) { diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala index e295722cac..64a820c6d7 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/JdbcUtils.scala @@ -70,7 +70,7 @@ object JdbcUtils extends Logging { // Somewhat hacky, but there isn't a good way to identify whether a table exists for all // SQL database systems using JDBC meta data calls, considering "table" could also include - // the database name. Query used to find table exists can be overriden by the dialects. + // the database name. Query used to find table exists can be overridden by the dialects. Try { val statement = conn.prepareStatement(dialect.getTableExistsQuery(table)) try { diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/python/BatchPythonEvaluation.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/python/BatchPythonEvaluation.scala index c65a7bcff8..79e4491026 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/python/BatchPythonEvaluation.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/python/BatchPythonEvaluation.scala @@ -31,7 +31,7 @@ import org.apache.spark.sql.types.{StructField, StructType} /** - * A physical plan that evalutes a [[PythonUDF]], one partition of tuples at a time. + * A physical plan that evaluates a [[PythonUDF]], one partition of tuples at a time. * * Python evaluation works by sending the necessary (projected) input data via a socket to an * external Python process, and combine the result from the Python process with the original row. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala index 1bd71b6b02..e3b2d2f67e 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala @@ -38,7 +38,7 @@ trait Sink { * Accepts a new batch of data as well as a [[Offset]] that denotes how far in the input * data computation has progressed to. When computation restarts after a failure, it is important * that a [[Sink]] returns the same [[Offset]] as the most recent batch of data that - * has been persisted durrably. Note that this does not necessarily have to be the + * has been persisted durably. Note that this does not necessarily have to be the * [[Offset]] for the most recent batch of data that was given to the sink. For example, * it is valid to buffer data before persisting, as long as the [[Offset]] is stored * transactionally as data is eventually persisted. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala index 096477ce0e..d7ff44afad 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/memory.scala @@ -100,7 +100,7 @@ case class MemoryStream[A : Encoder](id: Int, sqlContext: SQLContext) /** * A sink that stores the results in memory. This [[Sink]] is primarily intended for use in unit - * tests and does not provide durablility. + * tests and does not provide durability. */ class MemorySink(schema: StructType) extends Sink with Logging { /** An order list of batches that have been written to this [[Sink]]. */ diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala index 384102e5ea..59429d254e 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala @@ -441,7 +441,7 @@ object SQLConf { // NOTE: // // 1. Instead of SQLConf, this option *must be set in Hadoop Configuration*. - // 2. This option can be overriden by "spark.sql.parquet.output.committer.class". + // 2. This option can be overridden by "spark.sql.parquet.output.committer.class". val OUTPUT_COMMITTER_CLASS = stringConf("spark.sql.sources.outputCommitterClass", isPublic = false) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala index e865dbe6b5..a7a826bc7a 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameStatSuite.scala @@ -80,7 +80,7 @@ class DataFrameStatSuite extends QueryTest with SharedSQLContext { // Verify that the splits span the entire dataset assert(splits.flatMap(_.collect()).toSet == data.collect().toSet) - // Verify that the splits don't overalap + // Verify that the splits don't overlap assert(splits(0).intersect(splits(1)).collect().isEmpty) // Verify that the results are deterministic across multiple runs diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala index 9f32c8bf95..d7fa23651b 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala @@ -46,7 +46,7 @@ class DatasetSuite extends QueryTest with SharedSQLContext { 1, 1, 1) } - test("SPARK-12404: Datatype Helper Serializablity") { + test("SPARK-12404: Datatype Helper Serializability") { val ds = sparkContext.parallelize(( new Timestamp(0), new Date(0), diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala index 182f287dd0..98d0008489 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala @@ -986,7 +986,7 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext { test("SET commands with illegal or inappropriate argument") { sqlContext.conf.clear() - // Set negative mapred.reduce.tasks for automatically determing + // Set negative mapred.reduce.tasks for automatically determining // the number of reducers is not supported intercept[IllegalArgumentException](sql(s"SET mapred.reduce.tasks=-1")) intercept[IllegalArgumentException](sql(s"SET mapred.reduce.tasks=-01")) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala b/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala index 7a5b639115..81078dc6a0 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/StreamTest.scala @@ -80,7 +80,7 @@ trait StreamTest extends QueryTest with Timeouts { trait StreamMustBeRunning /** - * Adds the given data to the stream. Subsuquent check answers will block until this data has + * Adds the given data to the stream. Subsequent check answers will block until this data has * been processed. */ object AddData { @@ -109,7 +109,7 @@ trait StreamTest extends QueryTest with Timeouts { /** * Checks to make sure that the current data stored in the sink matches the `expectedAnswer`. - * This operation automatically blocks untill all added data has been processed. + * This operation automatically blocks until all added data has been processed. */ object CheckAnswer { def apply[A : Encoder](data: A*): CheckAnswerRows = { diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchemaSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchemaSuite.scala index 7af3f94aef..3a7cb25b4f 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchemaSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchemaSuite.scala @@ -80,7 +80,7 @@ class InferSchemaSuite extends SparkFunSuite { assert(CSVInferSchema.inferField(BooleanType, "\\N", "\\N") == BooleanType) } - test("Merging Nulltypes should yeild Nulltype.") { + test("Merging Nulltypes should yield Nulltype.") { val mergedNullTypes = CSVInferSchema.mergeRowTypes(Array(NullType), Array(NullType)) assert(mergedNullTypes.deep == Array(NullType).deep) } diff --git a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala index 1ef517324d..f66deea065 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala @@ -359,7 +359,7 @@ class JDBCSuite extends SparkFunSuite .collect().length === 3) } - test("Partioning on column that might have null values.") { + test("Partitioning on column that might have null values.") { assert( sqlContext.read.jdbc(urlWithUserAndPass, "TEST.EMP", "theid", 0, 4, 3, new Properties) .collect().length === 4) @@ -372,7 +372,7 @@ class JDBCSuite extends SparkFunSuite .collect().length === 4) } - test("SELECT * on partitioned table with a nullable partioncolumn") { + test("SELECT * on partitioned table with a nullable partition column") { assert(sql("SELECT * FROM nullparts").collect().size == 4) } diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala index 26c1ff5204..99f1661ad0 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/sources/TableScanSuite.scala @@ -339,7 +339,7 @@ class TableScanSuite extends DataSourceTest with SharedSQLContext { test("exceptions") { // Make sure we do throw correct exception when users use a relation provider that - // only implements the RelationProvier or the SchemaRelationProvider. + // only implements the RelationProvider or the SchemaRelationProvider. val schemaNotAllowed = intercept[Exception] { sql( """ diff --git a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala index 54fffb971d..694bd97515 100644 --- a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala +++ b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala @@ -68,7 +68,7 @@ class CliSuite extends SparkFunSuite with BeforeAndAfterAll with Logging { * with one of these strings is found, fail the test immediately. * The default value is `Seq("Error:")` * - * @param queriesAndExpectedAnswers one or more tupes of query + answer + * @param queriesAndExpectedAnswers one or more tuples of query + answer */ def runCliWithin( timeout: FiniteDuration, diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index 56acb87c80..739fbaf444 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -245,7 +245,7 @@ private[hive] class HiveQl(conf: ParserConf) extends SparkQl(conf) with Logging val tableName = tableNameParts.map { case Token(p, Nil) => p }.mkString(".") DropTable(tableName, ifExists.nonEmpty) - // Support "ANALYZE TABLE tableNmae COMPUTE STATISTICS noscan" + // Support "ANALYZE TABLE tableName COMPUTE STATISTICS noscan" case Token("TOK_ANALYZE", Token("TOK_TAB", Token("TOK_TABNAME", tableNameParts) :: partitionSpec) :: isNoscan) => // Reference: @@ -535,7 +535,7 @@ private[hive] class HiveQl(conf: ParserConf) extends SparkQl(conf) with Logging case Token("TOK_STORAGEHANDLER", _) => throw new AnalysisException( "CREATE TABLE AS SELECT cannot be used for a non-native table") - case _ => // Unsupport features + case _ => // Unsupported features } CreateTableAsSelect(tableDesc, nodeToPlan(query), allowExisting.isDefined) diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala index 059ad8b1f7..8240f2f222 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileOperator.scala @@ -89,7 +89,7 @@ private[orc] object OrcFileOperator extends Logging { } def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path] = { - // TODO: Check if the paths comming in are already qualified and simplify. + // TODO: Check if the paths coming in are already qualified and simplify. val origPath = new Path(pathStr) val fs = origPath.getFileSystem(conf) val path = origPath.makeQualified(fs.getUri, fs.getWorkingDirectory) diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala index 1053246fc2..5e452d107d 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveComparisonTest.scala @@ -143,7 +143,7 @@ abstract class HiveComparisonTest 0D } - s"""SQLBuiler statistics: + s"""SQLBuilder statistics: |- Total query number: $numTotalQueries |- Number of convertible queries: $numConvertibleQueries |- Percentage of convertible queries: $percentage% diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index 1002487447..d905f0cd68 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -602,7 +602,7 @@ class HiveQuerySuite extends HiveComparisonTest with BeforeAndAfter { |select * where key = 4 """.stripMargin) - // test get_json_object again Hive, because the HiveCompatabilitySuite cannot handle result + // test get_json_object again Hive, because the HiveCompatibilitySuite cannot handle result // with newline in it. createQueryTest("get_json_object #1", "SELECT get_json_object(src_json.json, '$') FROM src_json") 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) { diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/AMDelegationTokenRenewer.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/AMDelegationTokenRenewer.scala index 6e95bb9710..498471b23b 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/AMDelegationTokenRenewer.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/AMDelegationTokenRenewer.scala @@ -115,7 +115,7 @@ private[yarn] class AMDelegationTokenRenewer( } } // Schedule update of credentials. This handles the case of updating the tokens right now - // as well, since the renenwal interval will be 0, and the thread will get scheduled + // as well, since the renewal interval will be 0, and the thread will get scheduled // immediately. scheduleRenewal(driverTokenRenewerRunnable) } diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala index 9f91d182eb..9cdbd6da62 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala @@ -186,9 +186,9 @@ private[yarn] class ExecutorRunnable( else { // If no java_opts specified, default to using -XX:+CMSIncrementalMode // It might be possible that other modes/config is being done in - // spark.executor.extraJavaOptions, so we dont want to mess with it. - // In our expts, using (default) throughput collector has severe perf ramnifications in - // multi-tennent machines + // spark.executor.extraJavaOptions, so we don't want to mess with it. + // In our expts, using (default) throughput collector has severe perf ramifications in + // multi-tenant machines // The options are based on // http://www.oracle.com/technetwork/java/gc-tuning-5-138395.html#0.0.0.%20When%20to%20Use // %20the%20Concurrent%20Low%20Pause%20Collector|outline diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala index ed56d4bd44..2915e664be 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala @@ -65,7 +65,7 @@ class YarnSparkHadoopUtil extends SparkHadoopUtil { override def isYarnMode(): Boolean = { true } // Return an appropriate (subclass) of Configuration. Creating a config initializes some Hadoop - // subsystems. Always create a new config, dont reuse yarnConf. + // subsystems. Always create a new config, don't reuse yarnConf. override def newConfiguration(conf: SparkConf): Configuration = new YarnConfiguration(super.newConfiguration(conf)) @@ -217,7 +217,7 @@ class YarnSparkHadoopUtil extends SparkHadoopUtil { // the hive configuration class is a subclass of Hadoop Configuration, so can be cast down // to a Configuration and used without reflection val hiveConfClass = mirror.classLoader.loadClass("org.apache.hadoop.hive.conf.HiveConf") - // using the (Configuration, Class) constructor allows the current configuratin to be included + // using the (Configuration, Class) constructor allows the current configuration to be included // in the hive config. val ctor = hiveConfClass.getDeclaredConstructor(classOf[Configuration], classOf[Object].getClass) @@ -502,7 +502,7 @@ object YarnSparkHadoopUtil { /** * Getting the initial target number of executors depends on whether dynamic allocation is * enabled. - * If not using dynamic allocation it gets the number of executors reqeusted by the user. + * If not using dynamic allocation it gets the number of executors requested by the user. */ def getInitialTargetExecutorNumber( conf: SparkConf, diff --git a/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnShuffleIntegrationSuite.scala b/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnShuffleIntegrationSuite.scala index 1538ff75be..05c1e1613d 100644 --- a/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnShuffleIntegrationSuite.scala +++ b/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnShuffleIntegrationSuite.scala @@ -78,7 +78,7 @@ private object YarnExternalShuffleDriver extends Logging with Matchers { s""" |Invalid command line: ${args.mkString(" ")} | - |Usage: ExternalShuffleDriver [result file] [registed exec file] + |Usage: ExternalShuffleDriver [result file] [registered exec file] """.stripMargin) // scalastyle:on println System.exit(1) |