Repository: spark Updated Branches: refs/heads/branch-2.3 6facc7fb2 -> 566ef93a6
[MINOR] Typo fixes ## What changes were proposed in this pull request? Typo fixes ## How was this patch tested? Local build / Doc-only changes Author: Jacek Laskowski <ja...@japila.pl> Closes #20344 from jaceklaskowski/typo-fixes. (cherry picked from commit 76b8b840ddc951ee6203f9cccd2c2b9671c1b5e8) Signed-off-by: Sean Owen <so...@cloudera.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/566ef93a Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/566ef93a Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/566ef93a Branch: refs/heads/branch-2.3 Commit: 566ef93a672aea1803d6977883204780c2f6982d Parents: 6facc7f Author: Jacek Laskowski <ja...@japila.pl> Authored: Mon Jan 22 13:55:14 2018 -0600 Committer: Sean Owen <so...@cloudera.com> Committed: Mon Jan 22 13:55:22 2018 -0600 ---------------------------------------------------------------------- core/src/main/scala/org/apache/spark/SparkContext.scala | 2 +- .../apache/spark/sql/kafka010/KafkaSourceProvider.scala | 4 ++-- .../org/apache/spark/sql/kafka010/KafkaWriteTask.scala | 2 +- .../java/org/apache/spark/sql/streaming/OutputMode.java | 2 +- .../apache/spark/sql/catalyst/analysis/Analyzer.scala | 8 ++++---- .../apache/spark/sql/catalyst/analysis/unresolved.scala | 2 +- .../sql/catalyst/expressions/aggregate/interfaces.scala | 12 +++++------- .../sql/catalyst/plans/logical/LogicalPlanVisitor.scala | 2 +- .../logical/statsEstimation/BasicStatsPlanVisitor.scala | 2 +- .../SizeInBytesOnlyStatsPlanVisitor.scala | 4 ++-- .../scala/org/apache/spark/sql/internal/SQLConf.scala | 2 +- .../org/apache/spark/sql/catalyst/plans/PlanTest.scala | 2 +- .../scala/org/apache/spark/sql/DataFrameWriter.scala | 2 +- .../org/apache/spark/sql/execution/SparkSqlParser.scala | 2 +- .../spark/sql/execution/WholeStageCodegenExec.scala | 2 +- .../apache/spark/sql/execution/command/SetCommand.scala | 4 ++-- .../apache/spark/sql/execution/datasources/rules.scala | 2 +- .../spark/sql/execution/streaming/HDFSMetadataLog.scala | 2 +- .../spark/sql/execution/streaming/OffsetSeq.scala | 2 +- .../spark/sql/execution/streaming/OffsetSeqLog.scala | 2 +- .../sql/execution/streaming/StreamingQueryWrapper.scala | 2 +- .../sql/execution/streaming/state/StateStore.scala | 2 +- .../apache/spark/sql/execution/ui/ExecutionPage.scala | 2 +- .../spark/sql/expressions/UserDefinedFunction.scala | 4 ++-- .../spark/sql/internal/BaseSessionStateBuilder.scala | 4 ++-- .../apache/spark/sql/streaming/DataStreamReader.scala | 6 +++--- .../sql-tests/results/columnresolution-negative.sql.out | 2 +- .../sql-tests/results/columnresolution-views.sql.out | 2 +- .../sql-tests/results/columnresolution.sql.out | 6 +++--- .../test/scala/org/apache/spark/sql/SQLQuerySuite.scala | 4 ++-- .../org/apache/spark/sql/execution/SQLViewSuite.scala | 2 +- .../org/apache/spark/sql/hive/HiveExternalCatalog.scala | 4 ++-- 32 files changed, 50 insertions(+), 52 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/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 31f3cb9..3828d4f 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 be serialized and send to tasks + * Clean a closure to make it ready to be serialized and sent to tasks * (removes unreferenced variables in $outer's, updates REPL variables) * If <tt>checkSerializable</tt> is set, <tt>clean</tt> will also proactively * check to see if <tt>f</tt> is serializable and throw a <tt>SparkException</tt> http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala ---------------------------------------------------------------------- diff --git a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala b/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala index 3914370..62a998f 100644 --- a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala +++ b/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaSourceProvider.scala @@ -307,7 +307,7 @@ private[kafka010] class KafkaSourceProvider extends DataSourceRegister if (caseInsensitiveParams.contains(s"kafka.${ConsumerConfig.GROUP_ID_CONFIG}")) { throw new IllegalArgumentException( s"Kafka option '${ConsumerConfig.GROUP_ID_CONFIG}' is not supported as " + - s"user-specified consumer groups is not used to track offsets.") + s"user-specified consumer groups are not used to track offsets.") } if (caseInsensitiveParams.contains(s"kafka.${ConsumerConfig.AUTO_OFFSET_RESET_CONFIG}")) { @@ -335,7 +335,7 @@ private[kafka010] class KafkaSourceProvider extends DataSourceRegister { throw new IllegalArgumentException( s"Kafka option '${ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG}' is not supported as " - + "value are deserialized as byte arrays with ByteArrayDeserializer. Use DataFrame " + + "values are deserialized as byte arrays with ByteArrayDeserializer. Use DataFrame " + "operations to explicitly deserialize the values.") } http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriteTask.scala ---------------------------------------------------------------------- diff --git a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriteTask.scala b/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriteTask.scala index baa60fe..d90630a 100644 --- a/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriteTask.scala +++ b/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriteTask.scala @@ -26,7 +26,7 @@ import org.apache.spark.sql.catalyst.expressions.{Attribute, Cast, Literal, Unsa import org.apache.spark.sql.types.{BinaryType, StringType} /** - * A simple trait for writing out data in a single Spark task, without any concerns about how + * Writes out data in a single Spark task, without any concerns about how * to commit or abort tasks. Exceptions thrown by the implementation of this class will * automatically trigger task aborts. */ http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/java/org/apache/spark/sql/streaming/OutputMode.java ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/java/org/apache/spark/sql/streaming/OutputMode.java b/sql/catalyst/src/main/java/org/apache/spark/sql/streaming/OutputMode.java index 2800b30..470c128 100644 --- a/sql/catalyst/src/main/java/org/apache/spark/sql/streaming/OutputMode.java +++ b/sql/catalyst/src/main/java/org/apache/spark/sql/streaming/OutputMode.java @@ -21,7 +21,7 @@ import org.apache.spark.annotation.InterfaceStability; import org.apache.spark.sql.catalyst.streaming.InternalOutputModes; /** - * OutputMode is used to what data will be written to a streaming sink when there is + * OutputMode describes what data will be written to a streaming sink when there is * new data available in a streaming DataFrame/Dataset. * * @since 2.0.0 http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala index 35b3511..2b14c82 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala @@ -611,8 +611,8 @@ class Analyzer( if (AnalysisContext.get.nestedViewDepth > conf.maxNestedViewDepth) { view.failAnalysis(s"The depth of view ${view.desc.identifier} exceeds the maximum " + s"view resolution depth (${conf.maxNestedViewDepth}). Analysis is aborted to " + - "avoid errors. Increase the value of spark.sql.view.maxNestedViewDepth to work " + - "aroud this.") + s"avoid errors. Increase the value of ${SQLConf.MAX_NESTED_VIEW_DEPTH.key} to work " + + "around this.") } executeSameContext(child) } @@ -653,7 +653,7 @@ class Analyzer( // Note that if the database is not defined, it is possible we are looking up a temp view. case e: NoSuchDatabaseException => u.failAnalysis(s"Table or view not found: ${tableIdentWithDb.unquotedString}, the " + - s"database ${e.db} doesn't exsits.") + s"database ${e.db} doesn't exist.") } } @@ -1524,7 +1524,7 @@ class Analyzer( } /** - * Extracts [[Generator]] from the projectList of a [[Project]] operator and create [[Generate]] + * Extracts [[Generator]] from the projectList of a [[Project]] operator and creates [[Generate]] * operator under [[Project]]. * * This rule will throw [[AnalysisException]] for following cases: http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala index d336f80..a65f58f 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/unresolved.scala @@ -294,7 +294,7 @@ case class UnresolvedStar(target: Option[Seq[String]]) extends Star with Unevalu } else { val from = input.inputSet.map(_.name).mkString(", ") val targetString = target.get.mkString(".") - throw new AnalysisException(s"cannot resolve '$targetString.*' give input columns '$from'") + throw new AnalysisException(s"cannot resolve '$targetString.*' given input columns '$from'") } } http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala index 19abce0..e1d16a2 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/interfaces.scala @@ -190,17 +190,15 @@ abstract class AggregateFunction extends Expression { def defaultResult: Option[Literal] = None /** - * Wraps this [[AggregateFunction]] in an [[AggregateExpression]] because - * [[AggregateExpression]] is the container of an [[AggregateFunction]], aggregation mode, - * and the flag indicating if this aggregation is distinct aggregation or not. - * An [[AggregateFunction]] should not be used without being wrapped in - * an [[AggregateExpression]]. + * Creates [[AggregateExpression]] with `isDistinct` flag disabled. + * + * @see `toAggregateExpression(isDistinct: Boolean)` for detailed description */ def toAggregateExpression(): AggregateExpression = toAggregateExpression(isDistinct = false) /** - * Wraps this [[AggregateFunction]] in an [[AggregateExpression]] and set isDistinct - * field of the [[AggregateExpression]] to the given value because + * Wraps this [[AggregateFunction]] in an [[AggregateExpression]] and sets `isDistinct` + * flag of the [[AggregateExpression]] to the given value because * [[AggregateExpression]] is the container of an [[AggregateFunction]], aggregation mode, * and the flag indicating if this aggregation is distinct aggregation or not. * An [[AggregateFunction]] should not be used without being wrapped in http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlanVisitor.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlanVisitor.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlanVisitor.scala index e074804..2c248d7 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlanVisitor.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlanVisitor.scala @@ -18,7 +18,7 @@ package org.apache.spark.sql.catalyst.plans.logical /** - * A visitor pattern for traversing a [[LogicalPlan]] tree and compute some properties. + * A visitor pattern for traversing a [[LogicalPlan]] tree and computing some properties. */ trait LogicalPlanVisitor[T] { http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/BasicStatsPlanVisitor.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/BasicStatsPlanVisitor.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/BasicStatsPlanVisitor.scala index ca0775a..b6c1607 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/BasicStatsPlanVisitor.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/BasicStatsPlanVisitor.scala @@ -20,7 +20,7 @@ package org.apache.spark.sql.catalyst.plans.logical.statsEstimation import org.apache.spark.sql.catalyst.plans.logical._ /** - * An [[LogicalPlanVisitor]] that computes a the statistics used in a cost-based optimizer. + * A [[LogicalPlanVisitor]] that computes the statistics for the cost-based optimizer. */ object BasicStatsPlanVisitor extends LogicalPlanVisitor[Statistics] { http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala index 5e1c4e0..85f67c7 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala @@ -48,8 +48,8 @@ object SizeInBytesOnlyStatsPlanVisitor extends LogicalPlanVisitor[Statistics] { } /** - * For leaf nodes, use its computeStats. For other nodes, we assume the size in bytes is the - * sum of all of the children's. + * For leaf nodes, use its `computeStats`. For other nodes, we assume the size in bytes is the + * product of all of the children's `computeStats`. */ override def default(p: LogicalPlan): Statistics = p match { case p: LeafNode => p.computeStats() http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala index cc4f4bf..1cef09a 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala @@ -894,7 +894,7 @@ object SQLConf { .internal() .doc("The number of bins when generating histograms.") .intConf - .checkValue(num => num > 1, "The number of bins must be large than 1.") + .checkValue(num => num > 1, "The number of bins must be larger than 1.") .createWithDefault(254) val PERCENTILE_ACCURACY = http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala index 82c5307..6241d5c 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/plans/PlanTest.scala @@ -154,7 +154,7 @@ trait PlanTestBase extends PredicateHelper { self: Suite => } /** - * Sets all SQL configurations specified in `pairs`, calls `f`, and then restore all SQL + * Sets all SQL configurations specified in `pairs`, calls `f`, and then restores all SQL * configurations. */ protected def withSQLConf(pairs: (String, String)*)(f: => Unit): Unit = { http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala index 97f12ff..5f3d444 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala @@ -311,7 +311,7 @@ final class DataFrameWriter[T] private[sql](ds: Dataset[T]) { if (partitioningColumns.isDefined) { throw new AnalysisException( "insertInto() can't be used together with partitionBy(). " + - "Partition columns have already be defined for the table. " + + "Partition columns have already been defined for the table. " + "It is not necessary to use partitionBy()." ) } http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala index d3cfd2a..4828fa6 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala @@ -327,7 +327,7 @@ class SparkSqlAstBuilder(conf: SQLConf) extends AstBuilder(conf) { } /** - * Create a [[DescribeTableCommand]] logical plan. + * Create a [[DescribeColumnCommand]] or [[DescribeTableCommand]] logical commands. */ override def visitDescribeTable(ctx: DescribeTableContext): LogicalPlan = withOrigin(ctx) { val isExtended = ctx.EXTENDED != null || ctx.FORMATTED != null http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala index 0659545..6102937 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala @@ -58,7 +58,7 @@ trait CodegenSupport extends SparkPlan { } /** - * Whether this SparkPlan support whole stage codegen or not. + * Whether this SparkPlan supports whole stage codegen or not. */ def supportCodegen: Boolean = true http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/SetCommand.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/SetCommand.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/SetCommand.scala index 7477d02..3c900be 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/SetCommand.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/SetCommand.scala @@ -91,8 +91,8 @@ case class SetCommand(kv: Option[(String, Option[String])]) extends RunnableComm if (sparkSession.conf.get(CATALOG_IMPLEMENTATION.key).equals("hive") && key.startsWith("hive.")) { logWarning(s"'SET $key=$value' might not work, since Spark doesn't support changing " + - "the Hive config dynamically. Please passing the Hive-specific config by adding the " + - s"prefix spark.hadoop (e.g., spark.hadoop.$key) when starting a Spark application. " + + "the Hive config dynamically. Please pass the Hive-specific config by adding the " + + s"prefix spark.hadoop (e.g. spark.hadoop.$key) when starting a Spark application. " + "For details, see the link: https://spark.apache.org/docs/latest/configuration.html#" + "dynamically-loading-spark-properties.") } http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala index f64e079..5dbcf4a 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala @@ -32,7 +32,7 @@ import org.apache.spark.sql.types.{AtomicType, StructType} import org.apache.spark.sql.util.SchemaUtils /** - * Try to replaces [[UnresolvedRelation]]s if the plan is for direct query on files. + * Replaces [[UnresolvedRelation]]s if the plan is for direct query on files. */ class ResolveSQLOnFile(sparkSession: SparkSession) extends Rule[LogicalPlan] { private def maybeSQLFile(u: UnresolvedRelation): Boolean = { http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala index 6e8154d..00bc215 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala @@ -330,7 +330,7 @@ object HDFSMetadataLog { /** A simple trait to abstract out the file management operations needed by HDFSMetadataLog. */ trait FileManager { - /** List the files in a path that matches a filter. */ + /** List the files in a path that match a filter. */ def list(path: Path, filter: PathFilter): Array[FileStatus] /** Make directory at the give path and all its parent directories as needed. */ http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeq.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeq.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeq.scala index a1b63a6..73945b3 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeq.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeq.scala @@ -32,7 +32,7 @@ import org.apache.spark.sql.internal.SQLConf.{SHUFFLE_PARTITIONS, STATE_STORE_PR case class OffsetSeq(offsets: Seq[Option[Offset]], metadata: Option[OffsetSeqMetadata] = None) { /** - * Unpacks an offset into [[StreamProgress]] by associating each offset with the order list of + * Unpacks an offset into [[StreamProgress]] by associating each offset with the ordered list of * sources. * * This method is typically used to associate a serialized offset with actual sources (which http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeqLog.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeqLog.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeqLog.scala index e3f4abc..2c8d7c7 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeqLog.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/OffsetSeqLog.scala @@ -28,7 +28,7 @@ import org.apache.spark.sql.SparkSession /** * This class is used to log offsets to persistent files in HDFS. * Each file corresponds to a specific batch of offsets. The file - * format contain a version string in the first line, followed + * format contains a version string in the first line, followed * by a the JSON string representation of the offsets separated * by a newline character. If a source offset is missing, then * that line will contain a string value defined in the http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingQueryWrapper.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingQueryWrapper.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingQueryWrapper.scala index 020c9cb..3f2cdad 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingQueryWrapper.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingQueryWrapper.scala @@ -22,7 +22,7 @@ import org.apache.spark.sql.SparkSession import org.apache.spark.sql.streaming.{StreamingQuery, StreamingQueryException, StreamingQueryProgress, StreamingQueryStatus} /** - * Wrap non-serializable StreamExecution to make the query serializable as it's easy to for it to + * Wrap non-serializable StreamExecution to make the query serializable as it's easy for it to * get captured with normal usage. It's safe to capture the query but not use it in executors. * However, if the user tries to call its methods, it will throw `IllegalStateException`. */ http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala index 6fe632f..d1d9f95 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala @@ -94,7 +94,7 @@ trait StateStore { def abort(): Unit /** - * Return an iterator containing all the key-value pairs in the SateStore. Implementations must + * Return an iterator containing all the key-value pairs in the StateStore. Implementations must * ensure that updates (puts, removes) can be made while iterating over this iterator. */ def iterator(): Iterator[UnsafeRowPair] http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala index f29e135..e0554f0 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/ui/ExecutionPage.scala @@ -80,7 +80,7 @@ class ExecutionPage(parent: SQLTab) extends WebUIPage("execution") with Logging planVisualization(metrics, graph) ++ physicalPlanDescription(executionUIData.physicalPlanDescription) }.getOrElse { - <div>No information to display for Plan {executionId}</div> + <div>No information to display for query {executionId}</div> } UIUtils.headerSparkPage(s"Details for Query $executionId", content, parent, Some(5000)) http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/expressions/UserDefinedFunction.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/expressions/UserDefinedFunction.scala b/sql/core/src/main/scala/org/apache/spark/sql/expressions/UserDefinedFunction.scala index 40a058d..bdc4bb4 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/expressions/UserDefinedFunction.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/expressions/UserDefinedFunction.scala @@ -27,8 +27,8 @@ import org.apache.spark.sql.types.DataType * * As an example: * {{{ - * // Defined a UDF that returns true or false based on some numeric score. - * val predict = udf((score: Double) => if (score > 0.5) true else false) + * // Define a UDF that returns true or false based on some numeric score. + * val predict = udf((score: Double) => score > 0.5) * * // Projects a column that adds a prediction column based on the score column. * df.select( predict(df("score")) ) http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala index 2867b4c..007f876 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala @@ -206,7 +206,7 @@ abstract class BaseSessionStateBuilder( /** * Logical query plan optimizer. * - * Note: this depends on the `conf`, `catalog` and `experimentalMethods` fields. + * Note: this depends on `catalog` and `experimentalMethods` fields. */ protected def optimizer: Optimizer = { new SparkOptimizer(catalog, experimentalMethods) { @@ -263,7 +263,7 @@ abstract class BaseSessionStateBuilder( * An interface to register custom [[org.apache.spark.sql.util.QueryExecutionListener]]s * that listen for execution metrics. * - * This gets cloned from parent if available, otherwise is a new instance is created. + * This gets cloned from parent if available, otherwise a new instance is created. */ protected def listenerManager: ExecutionListenerManager = { parentState.map(_.listenerManager.clone()).getOrElse( http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala index 52f2e26..9f5ca9f 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala @@ -118,7 +118,7 @@ final class DataStreamReader private[sql](sparkSession: SparkSession) extends Lo * You can set the following option(s): * <ul> * <li>`timeZone` (default session local timezone): sets the string that indicates a timezone - * to be used to parse timestamps in the JSON/CSV datasources or partition values.</li> + * to be used to parse timestamps in the JSON/CSV data sources or partition values.</li> * </ul> * * @since 2.0.0 @@ -129,12 +129,12 @@ final class DataStreamReader private[sql](sparkSession: SparkSession) extends Lo } /** - * Adds input options for the underlying data source. + * (Java-specific) Adds input options for the underlying data source. * * You can set the following option(s): * <ul> * <li>`timeZone` (default session local timezone): sets the string that indicates a timezone - * to be used to parse timestamps in the JSON/CSV datasources or partition values.</li> + * to be used to parse timestamps in the JSON/CSV data sources or partition values.</li> * </ul> * * @since 2.0.0 http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/test/resources/sql-tests/results/columnresolution-negative.sql.out ---------------------------------------------------------------------- diff --git a/sql/core/src/test/resources/sql-tests/results/columnresolution-negative.sql.out b/sql/core/src/test/resources/sql-tests/results/columnresolution-negative.sql.out index b5a4f5c..539f673 100644 --- a/sql/core/src/test/resources/sql-tests/results/columnresolution-negative.sql.out +++ b/sql/core/src/test/resources/sql-tests/results/columnresolution-negative.sql.out @@ -195,7 +195,7 @@ SELECT t1.x.y.* FROM t1 struct<> -- !query 22 output org.apache.spark.sql.AnalysisException -cannot resolve 't1.x.y.*' give input columns 'i1'; +cannot resolve 't1.x.y.*' given input columns 'i1'; -- !query 23 http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/test/resources/sql-tests/results/columnresolution-views.sql.out ---------------------------------------------------------------------- diff --git a/sql/core/src/test/resources/sql-tests/results/columnresolution-views.sql.out b/sql/core/src/test/resources/sql-tests/results/columnresolution-views.sql.out index 7c451c2..2092119 100644 --- a/sql/core/src/test/resources/sql-tests/results/columnresolution-views.sql.out +++ b/sql/core/src/test/resources/sql-tests/results/columnresolution-views.sql.out @@ -88,7 +88,7 @@ SELECT global_temp.view1.* FROM global_temp.view1 struct<> -- !query 10 output org.apache.spark.sql.AnalysisException -cannot resolve 'global_temp.view1.*' give input columns 'i1'; +cannot resolve 'global_temp.view1.*' given input columns 'i1'; -- !query 11 http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/test/resources/sql-tests/results/columnresolution.sql.out ---------------------------------------------------------------------- diff --git a/sql/core/src/test/resources/sql-tests/results/columnresolution.sql.out b/sql/core/src/test/resources/sql-tests/results/columnresolution.sql.out index d3ca444..e10f516 100644 --- a/sql/core/src/test/resources/sql-tests/results/columnresolution.sql.out +++ b/sql/core/src/test/resources/sql-tests/results/columnresolution.sql.out @@ -179,7 +179,7 @@ SELECT mydb1.t1.* FROM mydb1.t1 struct<> -- !query 21 output org.apache.spark.sql.AnalysisException -cannot resolve 'mydb1.t1.*' give input columns 'i1'; +cannot resolve 'mydb1.t1.*' given input columns 'i1'; -- !query 22 @@ -212,7 +212,7 @@ SELECT mydb1.t1.* FROM mydb1.t1 struct<> -- !query 25 output org.apache.spark.sql.AnalysisException -cannot resolve 'mydb1.t1.*' give input columns 'i1'; +cannot resolve 'mydb1.t1.*' given input columns 'i1'; -- !query 26 @@ -420,7 +420,7 @@ SELECT mydb1.t5.* FROM mydb1.t5 struct<> -- !query 50 output org.apache.spark.sql.AnalysisException -cannot resolve 'mydb1.t5.*' give input columns 'i1, t5'; +cannot resolve 'mydb1.t5.*' given input columns 'i1, t5'; -- !query 51 http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala ---------------------------------------------------------------------- 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 083a0c0..a79ab47 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 @@ -1896,12 +1896,12 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext { var e = intercept[AnalysisException] { sql("SELECT a.* FROM temp_table_no_cols a") }.getMessage - assert(e.contains("cannot resolve 'a.*' give input columns ''")) + assert(e.contains("cannot resolve 'a.*' given input columns ''")) e = intercept[AnalysisException] { dfNoCols.select($"b.*") }.getMessage - assert(e.contains("cannot resolve 'b.*' give input columns ''")) + assert(e.contains("cannot resolve 'b.*' given input columns ''")) } } http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala index 1408219..ce8fde2 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala @@ -663,7 +663,7 @@ abstract class SQLViewSuite extends QueryTest with SQLTestUtils { }.getMessage assert(e.contains("The depth of view `default`.`view0` exceeds the maximum view " + "resolution depth (10). Analysis is aborted to avoid errors. Increase the value " + - "of spark.sql.view.maxNestedViewDepth to work aroud this.")) + "of spark.sql.view.maxNestedViewDepth to work around this.")) } val e = intercept[IllegalArgumentException] { http://git-wip-us.apache.org/repos/asf/spark/blob/566ef93a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala index 632e3e0..3b8a8ca 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala @@ -109,8 +109,8 @@ private[spark] class HiveExternalCatalog(conf: SparkConf, hadoopConf: Configurat } /** - * Get the raw table metadata from hive metastore directly. The raw table metadata may contains - * special data source properties and should not be exposed outside of `HiveExternalCatalog`. We + * Get the raw table metadata from hive metastore directly. The raw table metadata may contain + * special data source properties that should not be exposed outside of `HiveExternalCatalog`. We * should interpret these special data source properties and restore the original table metadata * before returning it. */ --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org