spark git commit: [SPARK-20090][PYTHON] Add StructType.fieldNames in PySpark
Repository: spark Updated Branches: refs/heads/master 0ef9fe64e -> b56f79cc3 [SPARK-20090][PYTHON] Add StructType.fieldNames in PySpark ## What changes were proposed in this pull request? This PR proposes `StructType.fieldNames` that returns a copy of a field name list rather than a (undocumented) `StructType.names`. There are two points here: - API consistency with Scala/Java - Provide a safe way to get the field names. Manipulating these might cause unexpected behaviour as below: ```python from pyspark.sql.types import * struct = StructType([StructField("f1", StringType(), True)]) names = struct.names del names[0] spark.createDataFrame([{"f1": 1}], struct).show() ``` ``` ... java.lang.IllegalStateException: Input row doesn't have expected number of values required by the schema. 1 fields are required while 0 values are provided. at org.apache.spark.sql.execution.python.EvaluatePython$.fromJava(EvaluatePython.scala:138) at org.apache.spark.sql.SparkSession$$anonfun$6.apply(SparkSession.scala:741) at org.apache.spark.sql.SparkSession$$anonfun$6.apply(SparkSession.scala:741) ... ``` ## How was this patch tested? Added tests in `python/pyspark/sql/tests.py`. Author: hyukjinkwonCloses #18618 from HyukjinKwon/SPARK-20090. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/b56f79cc Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/b56f79cc Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/b56f79cc Branch: refs/heads/master Commit: b56f79cc359d093d757af83171175cfd933162d1 Parents: 0ef9fe6 Author: hyukjinkwon Authored: Fri Jul 28 20:59:32 2017 -0700 Committer: Holden Karau Committed: Fri Jul 28 20:59:32 2017 -0700 -- python/pyspark/sql/tests.py | 16 python/pyspark/sql/types.py | 15 ++- 2 files changed, 22 insertions(+), 9 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/b56f79cc/python/pyspark/sql/tests.py -- diff --git a/python/pyspark/sql/tests.py b/python/pyspark/sql/tests.py index 54756ed..cfd9c55 100644 --- a/python/pyspark/sql/tests.py +++ b/python/pyspark/sql/tests.py @@ -1241,26 +1241,29 @@ class SQLTests(ReusedPySparkTestCase): struct1 = StructType().add("f1", StringType(), True).add("f2", StringType(), True, None) struct2 = StructType([StructField("f1", StringType(), True), StructField("f2", StringType(), True, None)]) +self.assertEqual(struct1.fieldNames(), struct2.names) self.assertEqual(struct1, struct2) struct1 = StructType().add("f1", StringType(), True).add("f2", StringType(), True, None) struct2 = StructType([StructField("f1", StringType(), True)]) +self.assertNotEqual(struct1.fieldNames(), struct2.names) self.assertNotEqual(struct1, struct2) struct1 = (StructType().add(StructField("f1", StringType(), True)) .add(StructField("f2", StringType(), True, None))) struct2 = StructType([StructField("f1", StringType(), True), StructField("f2", StringType(), True, None)]) +self.assertEqual(struct1.fieldNames(), struct2.names) self.assertEqual(struct1, struct2) struct1 = (StructType().add(StructField("f1", StringType(), True)) .add(StructField("f2", StringType(), True, None))) struct2 = StructType([StructField("f1", StringType(), True)]) +self.assertNotEqual(struct1.fieldNames(), struct2.names) self.assertNotEqual(struct1, struct2) # Catch exception raised during improper construction -with self.assertRaises(ValueError): -struct1 = StructType().add("name") +self.assertRaises(ValueError, lambda: StructType().add("name")) struct1 = StructType().add("f1", StringType(), True).add("f2", StringType(), True, None) for field in struct1: @@ -1273,12 +1276,9 @@ class SQLTests(ReusedPySparkTestCase): self.assertIs(struct1["f1"], struct1.fields[0]) self.assertIs(struct1[0], struct1.fields[0]) self.assertEqual(struct1[0:1], StructType(struct1.fields[0:1])) -with self.assertRaises(KeyError): -not_a_field = struct1["f9"] -with self.assertRaises(IndexError): -not_a_field = struct1[9] -with self.assertRaises(TypeError): -not_a_field = struct1[9.9] +self.assertRaises(KeyError, lambda: struct1["f9"]) +self.assertRaises(IndexError, lambda: struct1[9]) +self.assertRaises(TypeError, lambda: struct1[9.9]) def
spark git commit: Typo in comment
Repository: spark Updated Branches: refs/heads/master 69ab0e4bd -> 0ef9fe64e Typo in comment - Author: Johan GrandeCloses #18738 from nahoj/patch-1. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/0ef9fe64 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/0ef9fe64 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/0ef9fe64 Branch: refs/heads/master Commit: 0ef9fe64e2d59bdf98c0f4729e5017d258f7c07d Parents: 69ab0e4 Author: Johan Grande Authored: Fri Jul 28 16:51:18 2017 +0100 Committer: Sean Owen Committed: Fri Jul 28 16:51:18 2017 +0100 -- core/src/main/scala/org/apache/spark/rdd/RDD.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/0ef9fe64/core/src/main/scala/org/apache/spark/rdd/RDD.scala -- diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index 2985c90..5435f59 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -55,7 +55,7 @@ import org.apache.spark.util.random.{BernoulliCellSampler, BernoulliSampler, Poi * Doubles; and * [[org.apache.spark.rdd.SequenceFileRDDFunctions]] contains operations available on RDDs that * can be saved as SequenceFiles. - * All operations are automatically available on any RDD of the right type (e.g. RDD[(Int, Int)] + * All operations are automatically available on any RDD of the right type (e.g. RDD[(Int, Int)]) * through implicit. * * Internally, each RDD is characterized by five main properties: - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-21541][YARN] Spark Logs show incorrect job status for a job that does not create SparkContext
Repository: spark Updated Branches: refs/heads/master 784680903 -> 69ab0e4bd [SPARK-21541][YARN] Spark Logs show incorrect job status for a job that does not create SparkContext If you run a spark job without creating the SparkSession or SparkContext, the spark job logs says it succeeded but yarn says it fails and retries 3 times. Also, since, Application Master unregisters with Resource Manager and exits successfully, it deletes the spark staging directory, so when yarn makes subsequent retries, it fails to find the staging directory and thus, the retries fail. Added a flag to check whether user has initialized SparkContext. If it is true, we let Application Master unregister with Resource Manager else, we do not let AM unregister with RM. ## How was this patch tested? Manually tested the fix. Before: https://user-images.githubusercontent.com/8190/28647214-69bf81e2-722b-11e7-9ed0-d416d2bf23be.png;> After: https://user-images.githubusercontent.com/8190/28647220-70f9eea2-722b-11e7-85c6-e56276b15614.png;> Please review http://spark.apache.org/contributing.html before opening a pull request. Author: pgandhiAuthor: pgandhi999 Closes #18741 from pgandhi999/SPARK-21541. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/69ab0e4b Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/69ab0e4b Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/69ab0e4b Branch: refs/heads/master Commit: 69ab0e4bddccb461f960fcb48a390a1517e504dd Parents: 7846809 Author: pgandhi Authored: Fri Jul 28 09:23:08 2017 -0500 Committer: Tom Graves Committed: Fri Jul 28 09:23:08 2017 -0500 -- .../spark/deploy/yarn/ApplicationMaster.scala | 21 +--- 1 file changed, 14 insertions(+), 7 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/69ab0e4b/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala -- diff --git a/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala b/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala index fc92502..ca6a3ef 100644 --- a/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala +++ b/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala @@ -90,6 +90,9 @@ private[spark] class ApplicationMaster( @volatile private var reporterThread: Thread = _ @volatile private var allocator: YarnAllocator = _ + // A flag to check whether user has initialized spark context + @volatile private var registered = false + private val userClassLoader = { val classpath = Client.getUserClasspath(sparkConf) val urls = classpath.map { entry => @@ -319,7 +322,7 @@ private[spark] class ApplicationMaster( */ final def unregister(status: FinalApplicationStatus, diagnostics: String = null): Unit = { synchronized { - if (!unregistered) { + if (registered && !unregistered) { logInfo(s"Unregistering ApplicationMaster with $status" + Option(diagnostics).map(msg => s" (diag message: $msg)").getOrElse("")) unregistered = true @@ -332,10 +335,15 @@ private[spark] class ApplicationMaster( synchronized { if (!finished) { val inShutdown = ShutdownHookManager.inShutdown() -logInfo(s"Final app status: $status, exitCode: $code" + +if (registered) { + exitCode = code + finalStatus = status +} else { + finalStatus = FinalApplicationStatus.FAILED + exitCode = ApplicationMaster.EXIT_SC_NOT_INITED +} +logInfo(s"Final app status: $finalStatus, exitCode: $exitCode" + Option(msg).map(msg => s", (reason: $msg)").getOrElse("")) -exitCode = code -finalStatus = status finalMsg = msg finished = true if (!inShutdown && Thread.currentThread() != reporterThread && reporterThread != null) { @@ -439,12 +447,11 @@ private[spark] class ApplicationMaster( sc.getConf.get("spark.driver.port"), isClusterMode = true) registerAM(sc.getConf, rpcEnv, driverRef, sc.ui.map(_.webUrl), securityMgr) +registered = true } else { // Sanity check; should never happen in normal operation, since sc should only be null // if the user app did not create a SparkContext. -if (!finished) { - throw new IllegalStateException("SparkContext is null but app is still running!") -} +throw new IllegalStateException("User did not initialize spark context!")
spark git commit: [SPARK-21553][SPARK SHELL] Add the description of the default value of master parameter in the spark-shell
Repository: spark Updated Branches: refs/heads/master 63d168cbb -> 784680903 [SPARK-21553][SPARK SHELL] Add the description of the default value of master parameter in the spark-shell When I type spark-shell --help, I find that the default value description for the master parameter is missing. The user does not know what the default value is when the master parameter is not included, so we need to add the master parameter default description to the help information. [https://issues.apache.org/jira/browse/SPARK-21553](https://issues.apache.org/jira/browse/SPARK-21553) Author: davidxdhAuthor: Donghui Xu Closes #18755 from davidxdh/dev_0728. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/78468090 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/78468090 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/78468090 Branch: refs/heads/master Commit: 784680903cdf003ac965b2d97b3f793324909bd3 Parents: 63d168c Author: davidxdh Authored: Fri Jul 28 15:21:45 2017 +0100 Committer: Sean Owen Committed: Fri Jul 28 15:21:45 2017 +0100 -- .../main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/78468090/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala -- diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala index fd15211..3721b98 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala @@ -514,7 +514,8 @@ private[deploy] class SparkSubmitArguments(args: Seq[String], env: Map[String, S outStream.println( s""" |Options: -| --master MASTER_URL spark://host:port, mesos://host:port, yarn, or local. +| --master MASTER_URL spark://host:port, mesos://host:port, yarn, or local +| (Default: local[*]). | --deploy-mode DEPLOY_MODE Whether to launch the driver program locally ("client") or | on one of the worker machines inside the cluster ("cluster") | (Default: client). - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: Revert "[SPARK-21306][ML] OneVsRest should support setWeightCol"
Repository: spark Updated Branches: refs/heads/branch-2.1 8520d7c6d -> 258ca40cf Revert "[SPARK-21306][ML] OneVsRest should support setWeightCol" This reverts commit 8520d7c6d5e880dea3c1a8a874148c07222b4b4b. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/258ca40c Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/258ca40c Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/258ca40c Branch: refs/heads/branch-2.1 Commit: 258ca40cf43eedae59b014a41fc6197df9bde299 Parents: 8520d7c Author: Yanbo LiangAuthored: Fri Jul 28 20:24:54 2017 +0800 Committer: Yanbo Liang Committed: Fri Jul 28 20:24:54 2017 +0800 -- .../spark/ml/classification/OneVsRest.scala | 39 ++-- .../ml/classification/OneVsRestSuite.scala | 10 - python/pyspark/ml/classification.py | 27 +++--- python/pyspark/ml/tests.py | 14 --- 4 files changed, 9 insertions(+), 81 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/258ca40c/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala -- diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala index c4a8f1f..e58b30d 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala @@ -34,7 +34,6 @@ import org.apache.spark.ml._ import org.apache.spark.ml.attribute._ import org.apache.spark.ml.linalg.Vector import org.apache.spark.ml.param.{Param, ParamMap, ParamPair, Params} -import org.apache.spark.ml.param.shared.HasWeightCol import org.apache.spark.ml.util._ import org.apache.spark.sql.{DataFrame, Dataset, Row} import org.apache.spark.sql.functions._ @@ -54,8 +53,7 @@ private[ml] trait ClassifierTypeTrait { /** * Params for [[OneVsRest]]. */ -private[ml] trait OneVsRestParams extends PredictorParams - with ClassifierTypeTrait with HasWeightCol { +private[ml] trait OneVsRestParams extends PredictorParams with ClassifierTypeTrait { /** * param for the base binary classifier that we reduce multiclass classification into. @@ -301,18 +299,6 @@ final class OneVsRest @Since("1.4.0") ( @Since("1.5.0") def setPredictionCol(value: String): this.type = set(predictionCol, value) - /** - * Sets the value of param [[weightCol]]. - * - * This is ignored if weight is not supported by [[classifier]]. - * If this is not set or empty, we treat all instance weights as 1.0. - * Default is not set, so all instances have weight one. - * - * @group setParam - */ - @Since("2.3.0") - def setWeightCol(value: String): this.type = set(weightCol, value) - @Since("1.4.0") override def transformSchema(schema: StructType): StructType = { validateAndTransformSchema(schema, fitting = true, getClassifier.featuresDataType) @@ -331,20 +317,7 @@ final class OneVsRest @Since("1.4.0") ( } val numClasses = MetadataUtils.getNumClasses(labelSchema).fold(computeNumClasses())(identity) -val weightColIsUsed = isDefined(weightCol) && $(weightCol).nonEmpty && { - getClassifier match { -case _: HasWeightCol => true -case c => - logWarning(s"weightCol is ignored, as it is not supported by $c now.") - false - } -} - -val multiclassLabeled = if (weightColIsUsed) { - dataset.select($(labelCol), $(featuresCol), $(weightCol)) -} else { - dataset.select($(labelCol), $(featuresCol)) -} +val multiclassLabeled = dataset.select($(labelCol), $(featuresCol)) // persist if underlying dataset is not persistent. val handlePersistence = dataset.rdd.getStorageLevel == StorageLevel.NONE @@ -364,13 +337,7 @@ final class OneVsRest @Since("1.4.0") ( paramMap.put(classifier.labelCol -> labelColName) paramMap.put(classifier.featuresCol -> getFeaturesCol) paramMap.put(classifier.predictionCol -> getPredictionCol) - if (weightColIsUsed) { -val classifier_ = classifier.asInstanceOf[ClassifierType with HasWeightCol] -paramMap.put(classifier_.weightCol -> getWeightCol) -classifier_.fit(trainingDataset, paramMap) - } else { -classifier.fit(trainingDataset, paramMap) - } + classifier.fit(trainingDataset, paramMap) }.toArray[ClassificationModel[_, _]] if (handlePersistence) { http://git-wip-us.apache.org/repos/asf/spark/blob/258ca40c/mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala -- diff --git
spark git commit: Revert "[SPARK-21306][ML] OneVsRest should support setWeightCol"
Repository: spark Updated Branches: refs/heads/branch-2.0 ccb827224 -> f8ae2bdd2 Revert "[SPARK-21306][ML] OneVsRest should support setWeightCol" This reverts commit ccb82722450c20c9cdea2b2c68783943213a5aa1. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f8ae2bdd Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f8ae2bdd Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f8ae2bdd Branch: refs/heads/branch-2.0 Commit: f8ae2bdd2112780ec2b1104119bac2b718a55413 Parents: ccb8272 Author: Yanbo LiangAuthored: Fri Jul 28 19:45:14 2017 +0800 Committer: Yanbo Liang Committed: Fri Jul 28 19:45:14 2017 +0800 -- .../spark/ml/classification/OneVsRest.scala | 39 ++-- .../ml/classification/OneVsRestSuite.scala | 10 - python/pyspark/ml/classification.py | 27 +++--- python/pyspark/ml/tests.py | 14 --- 4 files changed, 9 insertions(+), 81 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/f8ae2bdd/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala -- diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala index 770d5db..f4ab0a0 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala @@ -34,7 +34,6 @@ import org.apache.spark.ml._ import org.apache.spark.ml.attribute._ import org.apache.spark.ml.linalg.Vector import org.apache.spark.ml.param.{Param, ParamMap, ParamPair, Params} -import org.apache.spark.ml.param.shared.HasWeightCol import org.apache.spark.ml.util._ import org.apache.spark.sql.{DataFrame, Dataset, Row} import org.apache.spark.sql.functions._ @@ -54,8 +53,7 @@ private[ml] trait ClassifierTypeTrait { /** * Params for [[OneVsRest]]. */ -private[ml] trait OneVsRestParams extends PredictorParams - with ClassifierTypeTrait with HasWeightCol { +private[ml] trait OneVsRestParams extends PredictorParams with ClassifierTypeTrait { /** * param for the base binary classifier that we reduce multiclass classification into. @@ -292,18 +290,6 @@ final class OneVsRest @Since("1.4.0") ( @Since("1.5.0") def setPredictionCol(value: String): this.type = set(predictionCol, value) - /** - * Sets the value of param [[weightCol]]. - * - * This is ignored if weight is not supported by [[classifier]]. - * If this is not set or empty, we treat all instance weights as 1.0. - * Default is not set, so all instances have weight one. - * - * @group setParam - */ - @Since("2.3.0") - def setWeightCol(value: String): this.type = set(weightCol, value) - @Since("1.4.0") override def transformSchema(schema: StructType): StructType = { validateAndTransformSchema(schema, fitting = true, getClassifier.featuresDataType) @@ -322,20 +308,7 @@ final class OneVsRest @Since("1.4.0") ( } val numClasses = MetadataUtils.getNumClasses(labelSchema).fold(computeNumClasses())(identity) -val weightColIsUsed = isDefined(weightCol) && $(weightCol).nonEmpty && { - getClassifier match { -case _: HasWeightCol => true -case c => - logWarning(s"weightCol is ignored, as it is not supported by $c now.") - false - } -} - -val multiclassLabeled = if (weightColIsUsed) { - dataset.select($(labelCol), $(featuresCol), $(weightCol)) -} else { - dataset.select($(labelCol), $(featuresCol)) -} +val multiclassLabeled = dataset.select($(labelCol), $(featuresCol)) // persist if underlying dataset is not persistent. val handlePersistence = dataset.rdd.getStorageLevel == StorageLevel.NONE @@ -355,13 +328,7 @@ final class OneVsRest @Since("1.4.0") ( paramMap.put(classifier.labelCol -> labelColName) paramMap.put(classifier.featuresCol -> getFeaturesCol) paramMap.put(classifier.predictionCol -> getPredictionCol) - if (weightColIsUsed) { -val classifier_ = classifier.asInstanceOf[ClassifierType with HasWeightCol] -paramMap.put(classifier_.weightCol -> getWeightCol) -classifier_.fit(trainingDataset, paramMap) - } else { -classifier.fit(trainingDataset, paramMap) - } + classifier.fit(trainingDataset, paramMap) }.toArray[ClassificationModel[_, _]] if (handlePersistence) { http://git-wip-us.apache.org/repos/asf/spark/blob/f8ae2bdd/mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala -- diff --git
spark git commit: [MINOR][BUILD] Fix current lint-java failures
Repository: spark Updated Branches: refs/heads/master a5a318997 -> 63d168cbb [MINOR][BUILD] Fix current lint-java failures ## What changes were proposed in this pull request? Fixes current failures in dev/lint-java ## How was this patch tested? Existing linter, tests. Author: Sean OwenCloses #18757 from srowen/LintJava. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/63d168cb Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/63d168cb Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/63d168cb Branch: refs/heads/master Commit: 63d168cbb8ebe80bfcf91a4d5070f1d9f3ec7aca Parents: a5a3189 Author: Sean Owen Authored: Fri Jul 28 11:31:40 2017 +0100 Committer: Sean Owen Committed: Fri Jul 28 11:31:40 2017 +0100 -- .../org/apache/spark/network/TransportRequestHandlerSuite.java | 6 -- .../org/apache/spark/shuffle/sort/ShuffleExternalSorter.java | 6 -- .../spark/sql/execution/vectorized/ArrowColumnVector.java | 2 +- 3 files changed, 9 insertions(+), 5 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/63d168cb/common/network-common/src/test/java/org/apache/spark/network/TransportRequestHandlerSuite.java -- diff --git a/common/network-common/src/test/java/org/apache/spark/network/TransportRequestHandlerSuite.java b/common/network-common/src/test/java/org/apache/spark/network/TransportRequestHandlerSuite.java index 1fb987a..1ed5711 100644 --- a/common/network-common/src/test/java/org/apache/spark/network/TransportRequestHandlerSuite.java +++ b/common/network-common/src/test/java/org/apache/spark/network/TransportRequestHandlerSuite.java @@ -105,7 +105,7 @@ public class TransportRequestHandlerSuite { private List listeners = new ArrayList<>(); private boolean success; -public ExtendedChannelPromise(Channel channel) { +ExtendedChannelPromise(Channel channel) { super(channel); success = false; } @@ -127,7 +127,9 @@ public class TransportRequestHandlerSuite { listeners.forEach(listener -> { try { listener.operationComplete(this); -} catch (Exception e) { } +} catch (Exception e) { + // do nothing +} }); } } http://git-wip-us.apache.org/repos/asf/spark/blob/63d168cb/core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java -- diff --git a/core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java b/core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java index 338faaa..da6c55d 100644 --- a/core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java +++ b/core/src/main/java/org/apache/spark/shuffle/sort/ShuffleExternalSorter.java @@ -120,14 +120,16 @@ final class ShuffleExternalSorter extends MemoryConsumer { this.taskContext = taskContext; this.numPartitions = numPartitions; // Use getSizeAsKb (not bytes) to maintain backwards compatibility if no units are provided -this.fileBufferSizeBytes = (int) (long) conf.get(package$.MODULE$.SHUFFLE_FILE_BUFFER_SIZE()) * 1024; +this.fileBufferSizeBytes = +(int) (long) conf.get(package$.MODULE$.SHUFFLE_FILE_BUFFER_SIZE()) * 1024; this.numElementsForSpillThreshold = conf.getLong("spark.shuffle.spill.numElementsForceSpillThreshold", 1024 * 1024 * 1024); this.writeMetrics = writeMetrics; this.inMemSorter = new ShuffleInMemorySorter( this, initialSize, conf.getBoolean("spark.shuffle.sort.useRadixSort", true)); this.peakMemoryUsedBytes = getMemoryUsage(); -this.diskWriteBufferSize = (int) (long) conf.get(package$.MODULE$.SHUFFLE_DISK_WRITE_BUFFER_SIZE()); +this.diskWriteBufferSize = +(int) (long) conf.get(package$.MODULE$.SHUFFLE_DISK_WRITE_BUFFER_SIZE()); } /** http://git-wip-us.apache.org/repos/asf/spark/blob/63d168cb/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ArrowColumnVector.java -- diff --git a/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ArrowColumnVector.java b/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ArrowColumnVector.java index 31dea6a..59d66c5 100644 --- a/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ArrowColumnVector.java +++ b/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ArrowColumnVector.java @@ -322,7 +322,7 @@ public final class ArrowColumnVector extends ReadOnlyColumnVector { anyNullsSet = numNulls > 0; } - private static abstract class
spark-website git commit: Update committer page
Repository: spark-website Updated Branches: refs/heads/asf-site 6ff5039f3 -> 0e09b2f58 Update committer page Project: http://git-wip-us.apache.org/repos/asf/spark-website/repo Commit: http://git-wip-us.apache.org/repos/asf/spark-website/commit/0e09b2f5 Tree: http://git-wip-us.apache.org/repos/asf/spark-website/tree/0e09b2f5 Diff: http://git-wip-us.apache.org/repos/asf/spark-website/diff/0e09b2f5 Branch: refs/heads/asf-site Commit: 0e09b2f580b32e16a6eef81e520e909174ebdb4d Parents: 6ff5039 Author: hyukjinkwonAuthored: Fri Jul 28 10:22:44 2017 +0900 Committer: hyukjinkwon Committed: Fri Jul 28 10:30:43 2017 +0900 -- committers.md| 1 + site/committers.html | 4 2 files changed, 5 insertions(+) -- http://git-wip-us.apache.org/repos/asf/spark-website/blob/0e09b2f5/committers.md -- diff --git a/committers.md b/committers.md index e850f8b..a4965cb 100644 --- a/committers.md +++ b/committers.md @@ -30,6 +30,7 @@ navigation: |Shane Huang|Intel| |Holden Karau|IBM| |Andy Konwinski|Databricks| +|Hyukjin Kwon|Mobigen| |Ryan LeCompte|Quantifind| |Haoyuan Li|Alluxio, UC Berkeley| |Xiao Li|Databricks| http://git-wip-us.apache.org/repos/asf/spark-website/blob/0e09b2f5/site/committers.html -- diff --git a/site/committers.html b/site/committers.html index b3137ca..f69529d 100644 --- a/site/committers.html +++ b/site/committers.html @@ -285,6 +285,10 @@ Databricks + Hyukjin Kwon + Mobigen + + Ryan LeCompte Quantifind - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org