Repository: spark Updated Branches: refs/heads/master 7a702d8d5 -> c284c4e1f
[MINOR] Fix a bunch of typos Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/c284c4e1 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/c284c4e1 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/c284c4e1 Branch: refs/heads/master Commit: c284c4e1f6f684ca8db1cc446fdcc43b46e3413c Parents: 7a702d8 Author: Sean Owen <so...@cloudera.com> Authored: Sun Dec 31 17:00:41 2017 -0600 Committer: hyukjinkwon <gurwls...@gmail.com> Committed: Tue Jan 2 07:10:19 2018 +0900 ---------------------------------------------------------------------- bin/find-spark-home | 2 +- .../java/org/apache/spark/util/kvstore/LevelDBIterator.java | 2 +- .../org/apache/spark/network/protocol/MessageWithHeader.java | 4 ++-- .../main/java/org/apache/spark/network/sasl/SaslEncryption.java | 4 ++-- .../org/apache/spark/network/util/TransportFrameDecoder.java | 2 +- .../network/shuffle/ExternalShuffleBlockResolverSuite.java | 2 +- .../src/main/java/org/apache/spark/util/sketch/BloomFilter.java | 2 +- .../java/org/apache/spark/unsafe/array/ByteArrayMethods.java | 2 +- core/src/main/scala/org/apache/spark/SparkContext.scala | 2 +- core/src/main/scala/org/apache/spark/status/storeTypes.scala | 2 +- .../test/scala/org/apache/spark/util/FileAppenderSuite.scala | 2 +- dev/github_jira_sync.py | 2 +- dev/lint-python | 2 +- examples/src/main/python/ml/linearsvc.py | 2 +- .../scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala | 2 +- .../scala/org/apache/spark/sql/kafka010/KafkaTestUtils.scala | 2 +- .../org/apache/spark/streaming/kafka010/JavaKafkaRDDSuite.java | 2 +- .../scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala | 4 ++-- .../main/java/org/apache/spark/launcher/ChildProcAppHandle.java | 2 +- .../main/scala/org/apache/spark/ml/tuning/CrossValidator.scala | 2 +- python/pyspark/ml/image.py | 2 +- .../scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala | 2 +- .../apache/spark/sql/catalyst/expressions/UnsafeArrayData.java | 2 +- .../scala/org/apache/spark/sql/catalyst/analysis/view.scala | 2 +- .../apache/spark/sql/catalyst/expressions/objects/objects.scala | 5 +++-- .../catalyst/expressions/aggregate/CountMinSketchAggSuite.scala | 2 +- .../spark/sql/sources/v2/streaming/MicroBatchWriteSupport.java | 2 +- .../org/apache/spark/sql/execution/ui/static/spark-sql-viz.css | 2 +- .../org/apache/spark/sql/execution/datasources/FileFormat.scala | 2 +- .../spark/sql/execution/datasources/csv/CSVInferSchema.scala | 2 +- .../org/apache/spark/sql/execution/joins/HashedRelation.scala | 2 +- .../execution/streaming/StreamingSymmetricHashJoinHelper.scala | 2 +- .../apache/spark/sql/execution/ui/SQLAppStatusListener.scala | 2 +- .../scala/org/apache/spark/sql/expressions/Aggregator.scala | 2 +- .../main/scala/org/apache/spark/sql/streaming/progress.scala | 2 +- .../src/test/java/test/org/apache/spark/sql/MyDoubleAvg.java | 2 +- .../sql-tests/inputs/typeCoercion/native/implicitTypeCasts.sql | 2 +- .../sql/execution/streaming/CompactibleFileStreamLogSuite.scala | 2 +- .../org/apache/spark/sql/sources/fakeExternalSources.scala | 2 +- .../org/apache/spark/sql/streaming/FileStreamSinkSuite.scala | 2 +- .../src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala | 2 +- .../src/main/scala/org/apache/spark/sql/hive/HiveShim.scala | 2 +- sql/hive/src/test/resources/data/conf/hive-log4j.properties | 2 +- .../scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala | 2 +- .../main/scala/org/apache/spark/streaming/util/StateMap.scala | 2 +- 45 files changed, 50 insertions(+), 49 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/bin/find-spark-home ---------------------------------------------------------------------- diff --git a/bin/find-spark-home b/bin/find-spark-home index fa78407..617dbaa 100755 --- a/bin/find-spark-home +++ b/bin/find-spark-home @@ -21,7 +21,7 @@ FIND_SPARK_HOME_PYTHON_SCRIPT="$(cd "$(dirname "$0")"; pwd)/find_spark_home.py" -# Short cirtuit if the user already has this set. +# Short circuit if the user already has this set. if [ ! -z "${SPARK_HOME}" ]; then exit 0 elif [ ! -f "$FIND_SPARK_HOME_PYTHON_SCRIPT" ]; then http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java ---------------------------------------------------------------------- diff --git a/common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java b/common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java index b3ba76b..f62e85d 100644 --- a/common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java +++ b/common/kvstore/src/main/java/org/apache/spark/util/kvstore/LevelDBIterator.java @@ -86,7 +86,7 @@ class LevelDBIterator<T> implements KVStoreIterator<T> { end = index.start(parent, params.last); } if (it.hasNext()) { - // When descending, the caller may have set up the start of iteration at a non-existant + // When descending, the caller may have set up the start of iteration at a non-existent // entry that is guaranteed to be after the desired entry. For example, if you have a // compound key (a, b) where b is a, integer, you may seek to the end of the elements that // have the same "a" value by specifying Integer.MAX_VALUE for "b", and that value may not http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/common/network-common/src/main/java/org/apache/spark/network/protocol/MessageWithHeader.java ---------------------------------------------------------------------- diff --git a/common/network-common/src/main/java/org/apache/spark/network/protocol/MessageWithHeader.java b/common/network-common/src/main/java/org/apache/spark/network/protocol/MessageWithHeader.java index 897d0f9..a533765 100644 --- a/common/network-common/src/main/java/org/apache/spark/network/protocol/MessageWithHeader.java +++ b/common/network-common/src/main/java/org/apache/spark/network/protocol/MessageWithHeader.java @@ -47,7 +47,7 @@ class MessageWithHeader extends AbstractFileRegion { /** * When the write buffer size is larger than this limit, I/O will be done in chunks of this size. * The size should not be too large as it will waste underlying memory copy. e.g. If network - * avaliable buffer is smaller than this limit, the data cannot be sent within one single write + * available buffer is smaller than this limit, the data cannot be sent within one single write * operation while it still will make memory copy with this size. */ private static final int NIO_BUFFER_LIMIT = 256 * 1024; @@ -100,7 +100,7 @@ class MessageWithHeader extends AbstractFileRegion { * transferTo invocations in order to transfer a single MessageWithHeader to avoid busy waiting. * * The contract is that the caller will ensure position is properly set to the total number - * of bytes transferred so far (i.e. value returned by transfered()). + * of bytes transferred so far (i.e. value returned by transferred()). */ @Override public long transferTo(final WritableByteChannel target, final long position) throws IOException { http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/common/network-common/src/main/java/org/apache/spark/network/sasl/SaslEncryption.java ---------------------------------------------------------------------- diff --git a/common/network-common/src/main/java/org/apache/spark/network/sasl/SaslEncryption.java b/common/network-common/src/main/java/org/apache/spark/network/sasl/SaslEncryption.java index 16ab4ef..3ac9081 100644 --- a/common/network-common/src/main/java/org/apache/spark/network/sasl/SaslEncryption.java +++ b/common/network-common/src/main/java/org/apache/spark/network/sasl/SaslEncryption.java @@ -38,7 +38,7 @@ import org.apache.spark.network.util.ByteArrayWritableChannel; import org.apache.spark.network.util.NettyUtils; /** - * Provides SASL-based encription for transport channels. The single method exposed by this + * Provides SASL-based encryption for transport channels. The single method exposed by this * class installs the needed channel handlers on a connected channel. */ class SaslEncryption { @@ -166,7 +166,7 @@ class SaslEncryption { * This makes assumptions about how netty treats FileRegion instances, because there's no way * to know beforehand what will be the size of the encrypted message. Namely, it assumes * that netty will try to transfer data from this message while - * <code>transfered() < count()</code>. So these two methods return, technically, wrong data, + * <code>transferred() < count()</code>. So these two methods return, technically, wrong data, * but netty doesn't know better. */ @Override http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/common/network-common/src/main/java/org/apache/spark/network/util/TransportFrameDecoder.java ---------------------------------------------------------------------- diff --git a/common/network-common/src/main/java/org/apache/spark/network/util/TransportFrameDecoder.java b/common/network-common/src/main/java/org/apache/spark/network/util/TransportFrameDecoder.java index 50d9651..8e73ab0 100644 --- a/common/network-common/src/main/java/org/apache/spark/network/util/TransportFrameDecoder.java +++ b/common/network-common/src/main/java/org/apache/spark/network/util/TransportFrameDecoder.java @@ -29,7 +29,7 @@ import io.netty.channel.ChannelInboundHandlerAdapter; /** * A customized frame decoder that allows intercepting raw data. * <p> - * This behaves like Netty's frame decoder (with harcoded parameters that match this library's + * This behaves like Netty's frame decoder (with hard coded parameters that match this library's * needs), except it allows an interceptor to be installed to read data directly before it's * framed. * <p> http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/common/network-shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java ---------------------------------------------------------------------- diff --git a/common/network-shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java b/common/network-shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java index 23438a0..6d201b8 100644 --- a/common/network-shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java +++ b/common/network-shuffle/src/test/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolverSuite.java @@ -127,7 +127,7 @@ public class ExternalShuffleBlockResolverSuite { mapper.readValue(shuffleJson, ExecutorShuffleInfo.class); assertEquals(parsedShuffleInfo, shuffleInfo); - // Intentionally keep these hard-coded strings in here, to check backwards-compatability. + // Intentionally keep these hard-coded strings in here, to check backwards-compatibility. // its not legacy yet, but keeping this here in case anybody changes it String legacyAppIdJson = "{\"appId\":\"foo\", \"execId\":\"bar\"}"; assertEquals(appId, mapper.readValue(legacyAppIdJson, AppExecId.class)); http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilter.java ---------------------------------------------------------------------- diff --git a/common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilter.java b/common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilter.java index c0b425e..37803c7 100644 --- a/common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilter.java +++ b/common/sketch/src/main/java/org/apache/spark/util/sketch/BloomFilter.java @@ -34,7 +34,7 @@ import java.io.OutputStream; * <li>{@link String}</li> * </ul> * The false positive probability ({@code FPP}) of a Bloom filter is defined as the probability that - * {@linkplain #mightContain(Object)} will erroneously return {@code true} for an object that hasu + * {@linkplain #mightContain(Object)} will erroneously return {@code true} for an object that has * not actually been put in the {@code BloomFilter}. * * The implementation is largely based on the {@code BloomFilter} class from Guava. http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/common/unsafe/src/main/java/org/apache/spark/unsafe/array/ByteArrayMethods.java ---------------------------------------------------------------------- diff --git a/common/unsafe/src/main/java/org/apache/spark/unsafe/array/ByteArrayMethods.java b/common/unsafe/src/main/java/org/apache/spark/unsafe/array/ByteArrayMethods.java index f121b1c..a6b1f7a 100644 --- a/common/unsafe/src/main/java/org/apache/spark/unsafe/array/ByteArrayMethods.java +++ b/common/unsafe/src/main/java/org/apache/spark/unsafe/array/ByteArrayMethods.java @@ -66,7 +66,7 @@ public class ByteArrayMethods { i += 1; } } - // for architectures that suport unaligned accesses, chew it up 8 bytes at a time + // for architectures that support unaligned accesses, chew it up 8 bytes at a time if (unaligned || (((leftOffset + i) % 8 == 0) && ((rightOffset + i) % 8 == 0))) { while (i <= length - 8) { if (Platform.getLong(leftBase, leftOffset + i) != http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/core/src/main/scala/org/apache/spark/SparkContext.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 1dbb378..31f3cb9 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -2276,7 +2276,7 @@ class SparkContext(config: SparkConf) extends Logging { } /** - * Clean a closure to make it ready to serialized and send to tasks + * Clean a closure to make it ready to be serialized and send to tasks * (removes unreferenced variables in $outer's, updates REPL variables) * If <tt>checkSerializable</tt> is set, <tt>clean</tt> will also proactively * check to see if <tt>f</tt> is serializable and throw a <tt>SparkException</tt> http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/core/src/main/scala/org/apache/spark/status/storeTypes.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/status/storeTypes.scala b/core/src/main/scala/org/apache/spark/status/storeTypes.scala index d9ead00..1cfd30d 100644 --- a/core/src/main/scala/org/apache/spark/status/storeTypes.scala +++ b/core/src/main/scala/org/apache/spark/status/storeTypes.scala @@ -61,7 +61,7 @@ private[spark] class ExecutorSummaryWrapper(val info: ExecutorSummary) { /** * Keep track of the existing stages when the job was submitted, and those that were - * completed during the job's execution. This allows a more accurate acounting of how + * completed during the job's execution. This allows a more accurate accounting of how * many tasks were skipped for the job. */ private[spark] class JobDataWrapper( http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala ---------------------------------------------------------------------- diff --git a/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala b/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala index cd0ed5b..52cd537 100644 --- a/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/FileAppenderSuite.scala @@ -356,7 +356,7 @@ class FileAppenderSuite extends SparkFunSuite with BeforeAndAfter with Logging { generatedFiles } - /** Delete all the generated rolledover files */ + /** Delete all the generated rolled over files */ def cleanup() { testFile.getParentFile.listFiles.filter { file => file.getName.startsWith(testFile.getName) http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/dev/github_jira_sync.py ---------------------------------------------------------------------- diff --git a/dev/github_jira_sync.py b/dev/github_jira_sync.py index acc9aea..7df7b32 100755 --- a/dev/github_jira_sync.py +++ b/dev/github_jira_sync.py @@ -43,7 +43,7 @@ MAX_UPDATES = int(os.environ.get("MAX_UPDATES", "100000")) # "notification overload" when running for the first time. MIN_COMMENT_PR = int(os.environ.get("MIN_COMMENT_PR", "1496")) -# File used as an opitimization to store maximum previously seen PR +# File used as an optimization to store maximum previously seen PR # Used mostly because accessing ASF JIRA is slow, so we want to avoid checking # the state of JIRA's that are tied to PR's we've already looked at. MAX_FILE = ".github-jira-max" http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/dev/lint-python ---------------------------------------------------------------------- diff --git a/dev/lint-python b/dev/lint-python index 07e2606..df8df03 100755 --- a/dev/lint-python +++ b/dev/lint-python @@ -19,7 +19,7 @@ SCRIPT_DIR="$( cd "$( dirname "$0" )" && pwd )" SPARK_ROOT_DIR="$(dirname "$SCRIPT_DIR")" -# Exclude auto-geneated configuration file. +# Exclude auto-generated configuration file. PATHS_TO_CHECK="$( cd "$SPARK_ROOT_DIR" && find . -name "*.py" )" PEP8_REPORT_PATH="$SPARK_ROOT_DIR/dev/pep8-report.txt" PYLINT_REPORT_PATH="$SPARK_ROOT_DIR/dev/pylint-report.txt" http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/examples/src/main/python/ml/linearsvc.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/linearsvc.py b/examples/src/main/python/ml/linearsvc.py index 18cbf87..9b79abb 100644 --- a/examples/src/main/python/ml/linearsvc.py +++ b/examples/src/main/python/ml/linearsvc.py @@ -37,7 +37,7 @@ if __name__ == "__main__": # Fit the model lsvcModel = lsvc.fit(training) - # Print the coefficients and intercept for linearsSVC + # Print the coefficients and intercept for linear SVC print("Coefficients: " + str(lsvcModel.coefficients)) print("Intercept: " + str(lsvcModel.intercept)) http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala ---------------------------------------------------------------------- diff --git a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala b/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala index 9d9e2aa..66b3409 100644 --- a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala +++ b/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceRDD.scala @@ -52,7 +52,7 @@ private[kafka010] case class KafkaSourceRDDPartition( * An RDD that reads data from Kafka based on offset ranges across multiple partitions. * Additionally, it allows preferred locations to be set for each topic + partition, so that * the [[KafkaSource]] can ensure the same executor always reads the same topic + partition - * and cached KafkaConsuemrs (see [[CachedKafkaConsumer]] can be used read data efficiently. + * and cached KafkaConsumers (see [[CachedKafkaConsumer]] can be used read data efficiently. * * @param sc the [[SparkContext]] * @param executorKafkaParams Kafka configuration for creating KafkaConsumer on the executors http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaTestUtils.scala ---------------------------------------------------------------------- diff --git a/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaTestUtils.scala b/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaTestUtils.scala index 08db4d8..7524594 100644 --- a/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaTestUtils.scala +++ b/external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaTestUtils.scala @@ -201,7 +201,7 @@ class KafkaTestUtils(withBrokerProps: Map[String, Object] = Map.empty) extends L verifyTopicDeletionWithRetries(zkUtils, topic, partitions, List(this.server)) } - /** Add new paritions to a Kafka topic */ + /** Add new partitions to a Kafka topic */ def addPartitions(topic: String, partitions: Int): Unit = { AdminUtils.addPartitions(zkUtils, topic, partitions) // wait until metadata is propagated http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/external/kafka-0-10/src/test/java/org/apache/spark/streaming/kafka010/JavaKafkaRDDSuite.java ---------------------------------------------------------------------- diff --git a/external/kafka-0-10/src/test/java/org/apache/spark/streaming/kafka010/JavaKafkaRDDSuite.java b/external/kafka-0-10/src/test/java/org/apache/spark/streaming/kafka010/JavaKafkaRDDSuite.java index 87bfe15..b20fad2 100644 --- a/external/kafka-0-10/src/test/java/org/apache/spark/streaming/kafka010/JavaKafkaRDDSuite.java +++ b/external/kafka-0-10/src/test/java/org/apache/spark/streaming/kafka010/JavaKafkaRDDSuite.java @@ -111,7 +111,7 @@ public class JavaKafkaRDDSuite implements Serializable { LocationStrategies.PreferConsistent() ).map(handler); - // just making sure the java user apis work; the scala tests handle logic corner cases + // just making sure the java user APIs work; the scala tests handle logic corner cases long count1 = rdd1.count(); long count2 = rdd2.count(); Assert.assertTrue(count1 > 0); http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala ---------------------------------------------------------------------- diff --git a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala index 2500460..c60b989 100644 --- a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala +++ b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala @@ -164,7 +164,7 @@ object KinesisUtils { * @param awsSecretKey AWS SecretKey (if null, will use DefaultAWSCredentialsProviderChain) * @param stsAssumeRoleArn ARN of IAM role to assume when using STS sessions to read from * Kinesis stream. - * @param stsSessionName Name to uniquely identify STS sessions if multiple princples assume + * @param stsSessionName Name to uniquely identify STS sessions if multiple principals assume * the same role. * @param stsExternalId External ID that can be used to validate against the assumed IAM role's * trust policy. @@ -434,7 +434,7 @@ object KinesisUtils { * @param awsSecretKey AWS SecretKey (if null, will use DefaultAWSCredentialsProviderChain) * @param stsAssumeRoleArn ARN of IAM role to assume when using STS sessions to read from * Kinesis stream. - * @param stsSessionName Name to uniquely identify STS sessions if multiple princples assume + * @param stsSessionName Name to uniquely identify STS sessions if multiple princpals assume * the same role. * @param stsExternalId External ID that can be used to validate against the assumed IAM role's * trust policy. http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/launcher/src/main/java/org/apache/spark/launcher/ChildProcAppHandle.java ---------------------------------------------------------------------- diff --git a/launcher/src/main/java/org/apache/spark/launcher/ChildProcAppHandle.java b/launcher/src/main/java/org/apache/spark/launcher/ChildProcAppHandle.java index 3bb7e12..8b3f427 100644 --- a/launcher/src/main/java/org/apache/spark/launcher/ChildProcAppHandle.java +++ b/launcher/src/main/java/org/apache/spark/launcher/ChildProcAppHandle.java @@ -71,7 +71,7 @@ class ChildProcAppHandle extends AbstractAppHandle { } /** - * Wait for the child process to exit and update the handle's state if necessary, accoding to + * Wait for the child process to exit and update the handle's state if necessary, according to * the exit code. */ void monitorChild() { http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala b/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala index 0130b3e..095b54c 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala @@ -94,7 +94,7 @@ class CrossValidator @Since("1.2.0") (@Since("1.4.0") override val uid: String) def setSeed(value: Long): this.type = set(seed, value) /** - * Set the mamixum level of parallelism to evaluate models in parallel. + * Set the maximum level of parallelism to evaluate models in parallel. * Default is 1 for serial evaluation * * @group expertSetParam http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/python/pyspark/ml/image.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/image.py b/python/pyspark/ml/image.py index 384599d..c9b8402 100644 --- a/python/pyspark/ml/image.py +++ b/python/pyspark/ml/image.py @@ -212,7 +212,7 @@ class _ImageSchema(object): ImageSchema = _ImageSchema() -# Monkey patch to disallow instantization of this class. +# Monkey patch to disallow instantiation of this class. def _disallow_instance(_): raise RuntimeError("Creating instance of _ImageSchema class is disallowed.") _ImageSchema.__init__ = _disallow_instance http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala ---------------------------------------------------------------------- diff --git a/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala b/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala index ab0005d..061f653 100644 --- a/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala +++ b/resource-managers/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala @@ -95,7 +95,7 @@ class YarnClusterSuite extends BaseYarnClusterSuite { "spark.executor.cores" -> "1", "spark.executor.memory" -> "512m", "spark.executor.instances" -> "2", - // Sending some senstive information, which we'll make sure gets redacted + // Sending some sensitive information, which we'll make sure gets redacted "spark.executorEnv.HADOOP_CREDSTORE_PASSWORD" -> YarnClusterDriver.SECRET_PASSWORD, "spark.yarn.appMasterEnv.HADOOP_CREDSTORE_PASSWORD" -> YarnClusterDriver.SECRET_PASSWORD )) http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java index 64ab01c..d18542b 100644 --- a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java +++ b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java @@ -294,7 +294,7 @@ public final class UnsafeArrayData extends ArrayData { assertIndexIsValid(ordinal); BitSetMethods.set(baseObject, baseOffset + 8, ordinal); - /* we assume the corrresponding column was already 0 or + /* we assume the corresponding column was already 0 or will be set to 0 later by the caller side */ } http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/view.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/view.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/view.scala index 3bbe41c..2021608 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/view.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/view.scala @@ -38,7 +38,7 @@ import org.apache.spark.sql.internal.SQLConf * view resolution, in this way, we are able to get the correct view column ordering and * omit the extra columns that we don't require); * 1.2. Else set the child output attributes to `queryOutput`. - * 2. Map the `queryQutput` to view output by index, if the corresponding attributes don't match, + * 2. Map the `queryOutput` to view output by index, if the corresponding attributes don't match, * try to up cast and alias the attribute in `queryOutput` to the attribute in the view output. * 3. Add a Project over the child, with the new output generated by the previous steps. * If the view output doesn't have the same number of columns neither with the child output, nor http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala index 4af8134..64da9bb 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala @@ -51,7 +51,7 @@ trait InvokeLike extends Expression with NonSQLExpression { * * - generate codes for argument. * - use ctx.splitExpressions() to not exceed 64kb JVM limit while preparing arguments. - * - avoid some of nullabilty checking which are not needed because the expression is not + * - avoid some of nullability checking which are not needed because the expression is not * nullable. * - when needNullCheck == true, short circuit if we found one of arguments is null because * preparing rest of arguments can be skipped in the case. @@ -193,7 +193,8 @@ case class StaticInvoke( * @param targetObject An expression that will return the object to call the method on. * @param functionName The name of the method to call. * @param dataType The expected return type of the function. - * @param arguments An optional list of expressions, whos evaluation will be passed to the function. + * @param arguments An optional list of expressions, whose evaluation will be passed to the + * function. * @param propagateNull When true, and any of the arguments is null, null will be returned instead * of calling the function. * @param returnNullable When false, indicating the invoked method will always return http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAggSuite.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAggSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAggSuite.scala index 1047963..30e3bc9 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAggSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAggSuite.scala @@ -30,7 +30,7 @@ import org.apache.spark.unsafe.types.UTF8String import org.apache.spark.util.sketch.CountMinSketch /** - * Unit test suite for the count-min sketch SQL aggregate funciton [[CountMinSketchAgg]]. + * Unit test suite for the count-min sketch SQL aggregate function [[CountMinSketchAgg]]. */ class CountMinSketchAggSuite extends SparkFunSuite { private val childExpression = BoundReference(0, IntegerType, nullable = true) http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/java/org/apache/spark/sql/sources/v2/streaming/MicroBatchWriteSupport.java ---------------------------------------------------------------------- diff --git a/sql/core/src/main/java/org/apache/spark/sql/sources/v2/streaming/MicroBatchWriteSupport.java b/sql/core/src/main/java/org/apache/spark/sql/sources/v2/streaming/MicroBatchWriteSupport.java index b5e3e44..53ffa95 100644 --- a/sql/core/src/main/java/org/apache/spark/sql/sources/v2/streaming/MicroBatchWriteSupport.java +++ b/sql/core/src/main/java/org/apache/spark/sql/sources/v2/streaming/MicroBatchWriteSupport.java @@ -41,7 +41,7 @@ public interface MicroBatchWriteSupport extends BaseStreamingSink { * @param queryId A unique string for the writing query. It's possible that there are many writing * queries running at the same time, and the returned {@link DataSourceV2Writer} * can use this id to distinguish itself from others. - * @param epochId The uniquenumeric ID of the batch within this writing query. This is an + * @param epochId The unique numeric ID of the batch within this writing query. This is an * incrementing counter representing a consistent set of data; the same batch may * be started multiple times in failure recovery scenarios, but it will always * contain the same records. http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.css ---------------------------------------------------------------------- diff --git a/sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.css b/sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.css index 594e747..b13850c 100644 --- a/sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.css +++ b/sql/core/src/main/resources/org/apache/spark/sql/execution/ui/static/spark-sql-viz.css @@ -32,7 +32,7 @@ stroke-width: 1px; } -/* Hightlight the SparkPlan node name */ +/* Highlight the SparkPlan node name */ #plan-viz-graph svg text :first-child { font-weight: bold; } http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala index d3874b5..023e127 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormat.scala @@ -77,7 +77,7 @@ trait FileFormat { } /** - * Returns whether a file with `path` could be splitted or not. + * Returns whether a file with `path` could be split or not. */ def isSplitable( sparkSession: SparkSession, http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala index b64d71b..a585cbe 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVInferSchema.scala @@ -150,7 +150,7 @@ private[csv] object CSVInferSchema { if ((allCatch opt options.timestampFormat.parse(field)).isDefined) { TimestampType } else if ((allCatch opt DateTimeUtils.stringToTime(field)).isDefined) { - // We keep this for backwords competibility. + // We keep this for backwards compatibility. TimestampType } else { tryParseBoolean(field, options) http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala index d98cf85..1465346 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala @@ -368,7 +368,7 @@ private[execution] final class LongToUnsafeRowMap(val mm: TaskMemoryManager, cap // The minimum key private var minKey = Long.MaxValue - // The maxinum key + // The maximum key private var maxKey = Long.MinValue // The array to store the key and offset of UnsafeRow in the page. http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingSymmetricHashJoinHelper.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingSymmetricHashJoinHelper.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingSymmetricHashJoinHelper.scala index 217e98a..4aba76c 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingSymmetricHashJoinHelper.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingSymmetricHashJoinHelper.scala @@ -203,7 +203,7 @@ object StreamingSymmetricHashJoinHelper extends Logging { /** * A custom RDD that allows partitions to be "zipped" together, while ensuring the tasks' * preferred location is based on which executors have the required join state stores already - * loaded. This is class is a modified verion of [[ZippedPartitionsRDD2]]. + * loaded. This is class is a modified version of [[ZippedPartitionsRDD2]]. */ class StateStoreAwareZipPartitionsRDD[A: ClassTag, B: ClassTag, V: ClassTag]( sc: SparkContext, http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala index 2295b8d..d8adbe7 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala @@ -175,7 +175,7 @@ class SQLAppStatusListener( // Check the execution again for whether the aggregated metrics data has been calculated. // This can happen if the UI is requesting this data, and the onExecutionEnd handler is - // running at the same time. The metrics calculcated for the UI can be innacurate in that + // running at the same time. The metrics calculated for the UI can be innacurate in that // case, since the onExecutionEnd handler will clean up tracked stage metrics. if (exec.metricsValues != null) { exec.metricsValues http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/scala/org/apache/spark/sql/expressions/Aggregator.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/expressions/Aggregator.scala b/sql/core/src/main/scala/org/apache/spark/sql/expressions/Aggregator.scala index 058c38c..1e07620 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/expressions/Aggregator.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/expressions/Aggregator.scala @@ -86,7 +86,7 @@ abstract class Aggregator[-IN, BUF, OUT] extends Serializable { def bufferEncoder: Encoder[BUF] /** - * Specifies the `Encoder` for the final ouput value type. + * Specifies the `Encoder` for the final output value type. * @since 2.0.0 */ def outputEncoder: Encoder[OUT] http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala index cedc1dc..0dcb666 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/streaming/progress.scala @@ -152,7 +152,7 @@ class StreamingQueryProgress private[sql]( * @param endOffset The ending offset for data being read. * @param numInputRows The number of records read from this source. * @param inputRowsPerSecond The rate at which data is arriving from this source. - * @param processedRowsPerSecond The rate at which data from this source is being procressed by + * @param processedRowsPerSecond The rate at which data from this source is being processed by * Spark. * @since 2.1.0 */ http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/test/java/test/org/apache/spark/sql/MyDoubleAvg.java ---------------------------------------------------------------------- diff --git a/sql/core/src/test/java/test/org/apache/spark/sql/MyDoubleAvg.java b/sql/core/src/test/java/test/org/apache/spark/sql/MyDoubleAvg.java index 447a71d..288f5e7 100644 --- a/sql/core/src/test/java/test/org/apache/spark/sql/MyDoubleAvg.java +++ b/sql/core/src/test/java/test/org/apache/spark/sql/MyDoubleAvg.java @@ -47,7 +47,7 @@ public class MyDoubleAvg extends UserDefinedAggregateFunction { _inputDataType = DataTypes.createStructType(inputFields); // The buffer has two values, bufferSum for storing the current sum and - // bufferCount for storing the number of non-null input values that have been contribuetd + // bufferCount for storing the number of non-null input values that have been contributed // to the current sum. List<StructField> bufferFields = new ArrayList<>(); bufferFields.add(DataTypes.createStructField("bufferSum", DataTypes.DoubleType, true)); http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/test/resources/sql-tests/inputs/typeCoercion/native/implicitTypeCasts.sql ---------------------------------------------------------------------- diff --git a/sql/core/src/test/resources/sql-tests/inputs/typeCoercion/native/implicitTypeCasts.sql b/sql/core/src/test/resources/sql-tests/inputs/typeCoercion/native/implicitTypeCasts.sql index 58866f4..6de22b8 100644 --- a/sql/core/src/test/resources/sql-tests/inputs/typeCoercion/native/implicitTypeCasts.sql +++ b/sql/core/src/test/resources/sql-tests/inputs/typeCoercion/native/implicitTypeCasts.sql @@ -32,7 +32,7 @@ SELECT 1.1 - '2.2' FROM t; SELECT 1.1 * '2.2' FROM t; SELECT 4.4 / '2.2' FROM t; --- concatentation +-- concatenation SELECT '$' || cast(1 as smallint) || '$' FROM t; SELECT '$' || 1 || '$' FROM t; SELECT '$' || cast(1 as bigint) || '$' FROM t; http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLogSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLogSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLogSuite.scala index 83018f9..12eaf63 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLogSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/CompactibleFileStreamLogSuite.scala @@ -92,7 +92,7 @@ class CompactibleFileStreamLogSuite extends SparkFunSuite with SharedSQLContext test("deriveCompactInterval") { // latestCompactBatchId(4) + 1 <= default(5) - // then use latestestCompactBatchId + 1 === 5 + // then use latestCompactBatchId + 1 === 5 assert(5 === deriveCompactInterval(5, 4)) // First divisor of 10 greater than 4 === 5 assert(5 === deriveCompactInterval(4, 9)) http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/test/scala/org/apache/spark/sql/sources/fakeExternalSources.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/fakeExternalSources.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/fakeExternalSources.scala index bf43de5..2cb4828 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/sources/fakeExternalSources.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/sources/fakeExternalSources.scala @@ -22,7 +22,7 @@ import org.apache.spark.sql.sources.{BaseRelation, DataSourceRegister, RelationP import org.apache.spark.sql.types._ -// Note that the package name is intendedly mismatched in order to resemble external data sources +// Note that the package name is intentionally mismatched in order to resemble external data sources // and test the detection for them. class FakeExternalSourceOne extends RelationProvider with DataSourceRegister { http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala index 2a25522..8c4e1fd 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala @@ -81,7 +81,7 @@ class FileStreamSinkSuite extends StreamTest { .start(outputDir) try { - // The output is partitoned by "value", so the value will appear in the file path. + // The output is partitioned by "value", so the value will appear in the file path. // This is to test if we handle spaces in the path correctly. inputData.addData("hello world") failAfter(streamingTimeout) { http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala b/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala index b4248b7..904f9f2 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala @@ -113,7 +113,7 @@ private[sql] trait SQLTestUtils extends SparkFunSuite with SQLTestUtilsBase with if (thread.isAlive) { thread.interrupt() // If this interrupt does not work, then this thread is most likely running something that - // is not interruptible. There is not much point to wait for the thread to termniate, and + // is not interruptible. There is not much point to wait for the thread to terminate, and // we rather let the JVM terminate the thread on exit. fail( s"Test '$name' running on o.a.s.util.UninterruptibleThread timed out after" + http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveShim.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveShim.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveShim.scala index 9e98948..11afe1a 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveShim.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveShim.scala @@ -50,7 +50,7 @@ private[hive] object HiveShim { val HIVE_GENERIC_UDF_MACRO_CLS = "org.apache.hadoop.hive.ql.udf.generic.GenericUDFMacro" /* - * This function in hive-0.13 become private, but we have to do this to walkaround hive bug + * This function in hive-0.13 become private, but we have to do this to work around hive bug */ private def appendReadColumnNames(conf: Configuration, cols: Seq[String]) { val old: String = conf.get(ColumnProjectionUtils.READ_COLUMN_NAMES_CONF_STR, "") http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/sql/hive/src/test/resources/data/conf/hive-log4j.properties ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/resources/data/conf/hive-log4j.properties b/sql/hive/src/test/resources/data/conf/hive-log4j.properties index 6a04247..83fd03a 100644 --- a/sql/hive/src/test/resources/data/conf/hive-log4j.properties +++ b/sql/hive/src/test/resources/data/conf/hive-log4j.properties @@ -32,7 +32,7 @@ log4j.threshhold=WARN log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender log4j.appender.DRFA.File=${hive.log.dir}/${hive.log.file} -# Rollver at midnight +# Roll over at midnight log4j.appender.DRFA.DatePattern=.yyyy-MM-dd # 30-day backup http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala ---------------------------------------------------------------------- diff --git a/streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala b/streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala index 15d3c7e..8da5a5f 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/rdd/MapWithStateRDD.scala @@ -162,7 +162,7 @@ private[streaming] class MapWithStateRDD[K: ClassTag, V: ClassTag, S: ClassTag, mappingFunction, batchTime, timeoutThresholdTime, - removeTimedoutData = doFullScan // remove timedout data only when full scan is enabled + removeTimedoutData = doFullScan // remove timed-out data only when full scan is enabled ) Iterator(newRecord) } http://git-wip-us.apache.org/repos/asf/spark/blob/c284c4e1/streaming/src/main/scala/org/apache/spark/streaming/util/StateMap.scala ---------------------------------------------------------------------- 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 3a21cfa..89524cd 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 @@ -364,7 +364,7 @@ private[streaming] object OpenHashMapBasedStateMap { } /** - * Internal class to represent a marker the demarkate the end of all state data in the + * Internal class to represent a marker that demarcates the end of all state data in the * serialized bytes. */ class LimitMarker(val num: Int) extends Serializable --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
