From 1450b5e095c4dde4eb38d6237e54d6bfa96955e2 Mon Sep 17 00:00:00 2001 From: Brandon Jiang Date: Sat, 22 Aug 2020 06:45:35 +0900 Subject: [PATCH] [MINOR][DOCS] fix typo for docs,log message and comments ### What changes were proposed in this pull request? Fix typo for docs, log messages and comments ### Why are the changes needed? typo fix to increase readability ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? manual test has been performed to test the updated Closes #29443 from brandonJY/spell-fix-doc. Authored-by: Brandon Jiang Signed-off-by: Takeshi Yamamuro --- .../main/java/org/apache/spark/network/util/TransportConf.java | 2 +- .../src/main/java/org/apache/spark/api/plugin/DriverPlugin.java | 2 +- .../apache/spark/resource/ResourceDiscoveryScriptPlugin.scala | 2 +- docs/job-scheduling.md | 2 +- docs/sql-ref-syntax-qry-select-groupby.md | 2 +- docs/sql-ref-syntax-qry-select-hints.md | 2 +- docs/sql-ref.md | 2 +- .../src/main/java/org/apache/spark/launcher/LauncherServer.java | 2 +- sbin/decommission-worker.sh | 2 +- .../org/apache/spark/sql/connector/catalog/TableCatalog.java | 2 +- .../org/apache/spark/sql/catalyst/QueryPlanningTracker.scala | 2 +- .../sql/execution/datasources/v2/ShowTablePropertiesExec.scala | 2 +- 12 files changed, 12 insertions(+), 12 deletions(-) diff --git a/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java b/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java index 6c37f9a382376..646e4278811f4 100644 --- a/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java +++ b/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java @@ -290,7 +290,7 @@ public boolean sharedByteBufAllocators() { } /** - * If enabled then off-heap byte buffers will be prefered for the shared ByteBuf allocators. + * If enabled then off-heap byte buffers will be preferred for the shared ByteBuf allocators. */ public boolean preferDirectBufsForSharedByteBufAllocators() { return conf.getBoolean("spark.network.io.preferDirectBufs", true); diff --git a/core/src/main/java/org/apache/spark/api/plugin/DriverPlugin.java b/core/src/main/java/org/apache/spark/api/plugin/DriverPlugin.java index 0c0d0df8ae682..1d676ff781c70 100644 --- a/core/src/main/java/org/apache/spark/api/plugin/DriverPlugin.java +++ b/core/src/main/java/org/apache/spark/api/plugin/DriverPlugin.java @@ -41,7 +41,7 @@ public interface DriverPlugin { * initialization. *

* It's recommended that plugins be careful about what operations are performed in this call, - * preferrably performing expensive operations in a separate thread, or postponing them until + * preferably performing expensive operations in a separate thread, or postponing them until * the application has fully started. * * @param sc The SparkContext loading the plugin. diff --git a/core/src/main/scala/org/apache/spark/resource/ResourceDiscoveryScriptPlugin.scala b/core/src/main/scala/org/apache/spark/resource/ResourceDiscoveryScriptPlugin.scala index 11a9bb86d3034..d861e91771673 100644 --- a/core/src/main/scala/org/apache/spark/resource/ResourceDiscoveryScriptPlugin.scala +++ b/core/src/main/scala/org/apache/spark/resource/ResourceDiscoveryScriptPlugin.scala @@ -29,7 +29,7 @@ import org.apache.spark.util.Utils.executeAndGetOutput /** * The default plugin that is loaded into a Spark application to control how custom * resources are discovered. This executes the discovery script specified by the user - * and gets the json output back and contructs ResourceInformation objects from that. + * and gets the json output back and constructs ResourceInformation objects from that. * If the user specifies custom plugins, this is the last one to be executed and * throws if the resource isn't discovered. * diff --git a/docs/job-scheduling.md b/docs/job-scheduling.md index 1eed0ff3ee5e8..7c7385b325a7f 100644 --- a/docs/job-scheduling.md +++ b/docs/job-scheduling.md @@ -298,7 +298,7 @@ later. In order to synchronize PVM threads with JVM threads, you should set `PYSPARK_PIN_THREAD` environment variable to `true`. This pinned thread mode allows one PVM thread has one corresponding JVM thread. With this mode, -`pyspark.InheritableThread` is recommanded to use together for a PVM thread to inherit the interitable attributes +`pyspark.InheritableThread` is recommended to use together for a PVM thread to inherit the inheritable attributes such as local properties in a JVM thread. Note that `PYSPARK_PIN_THREAD` is currently experimental and not recommended for use in production. diff --git a/docs/sql-ref-syntax-qry-select-groupby.md b/docs/sql-ref-syntax-qry-select-groupby.md index 6137c0d80f313..934e5f70d4b08 100644 --- a/docs/sql-ref-syntax-qry-select-groupby.md +++ b/docs/sql-ref-syntax-qry-select-groupby.md @@ -58,7 +58,7 @@ aggregate_name ( [ DISTINCT ] expression [ , ... ] ) [ FILTER ( WHERE boolean_ex * **grouping_expression** - Specifies the critieria based on which the rows are grouped together. The grouping of rows is performed based on + Specifies the criteria based on which the rows are grouped together. The grouping of rows is performed based on result values of the grouping expressions. A grouping expression may be a column alias, a column position or an expression. diff --git a/docs/sql-ref-syntax-qry-select-hints.md b/docs/sql-ref-syntax-qry-select-hints.md index 247ce48e79445..5f1cb4c5bed0b 100644 --- a/docs/sql-ref-syntax-qry-select-hints.md +++ b/docs/sql-ref-syntax-qry-select-hints.md @@ -31,7 +31,7 @@ Hints give users a way to suggest how Spark SQL to use specific approaches to ge ### Partitioning Hints -Partitioning hints allow users to suggest a partitioning stragety that Spark should follow. `COALESCE`, `REPARTITION`, +Partitioning hints allow users to suggest a partitioning strategy that Spark should follow. `COALESCE`, `REPARTITION`, and `REPARTITION_BY_RANGE` hints are supported and are equivalent to `coalesce`, `repartition`, and `repartitionByRange` [Dataset APIs](api/scala/org/apache/spark/sql/Dataset.html), respectively. These hints give users a way to tune performance and control the number of output files in Spark SQL. When multiple partitioning hints are diff --git a/docs/sql-ref.md b/docs/sql-ref.md index 8d0c6734c4bd6..6a87166f7133d 100644 --- a/docs/sql-ref.md +++ b/docs/sql-ref.md @@ -32,7 +32,7 @@ Spark SQL is Apache Spark's module for working with structured data. This guide * [Integration with Hive UDFs/UDAFs/UDTFs](sql-ref-functions-udf-hive.html) * [Identifiers](sql-ref-identifier.html) * [Literals](sql-ref-literals.html) - * [Null Semanitics](sql-ref-null-semantics.html) + * [Null Semantics](sql-ref-null-semantics.html) * [SQL Syntax](sql-ref-syntax.html) * [DDL Statements](sql-ref-syntax-ddl.html) * [DML Statements](sql-ref-syntax-dml.html) diff --git a/launcher/src/main/java/org/apache/spark/launcher/LauncherServer.java b/launcher/src/main/java/org/apache/spark/launcher/LauncherServer.java index 3ff77878f68a8..d5a277ba581a0 100644 --- a/launcher/src/main/java/org/apache/spark/launcher/LauncherServer.java +++ b/launcher/src/main/java/org/apache/spark/launcher/LauncherServer.java @@ -364,7 +364,7 @@ public void close() throws IOException { * * This method allows a short period for the above to happen (same amount of time as the * connection timeout, which is configurable). This should be fine for well-behaved - * applications, where they close the connection arond the same time the app handle detects the + * applications, where they close the connection around the same time the app handle detects the * app has finished. * * In case the connection is not closed within the grace period, this method forcefully closes diff --git a/sbin/decommission-worker.sh b/sbin/decommission-worker.sh index cf81a53f395c2..07e1e1771f7c1 100755 --- a/sbin/decommission-worker.sh +++ b/sbin/decommission-worker.sh @@ -46,7 +46,7 @@ else fi # Check if --block-until-exit is set. -# This is done for systems which block on the decomissioning script and on exit +# This is done for systems which block on the decommissioning script and on exit # shut down the entire system (e.g. K8s). if [ "$1" == "--block-until-exit" ]; then shift diff --git a/sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/TableCatalog.java b/sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/TableCatalog.java index 1809b9cdb52e5..b818515adf9c0 100644 --- a/sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/TableCatalog.java +++ b/sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/TableCatalog.java @@ -176,7 +176,7 @@ Table alterTable( * @param newIdent the new table identifier of the table * @throws NoSuchTableException If the table to rename doesn't exist or is a view * @throws TableAlreadyExistsException If the new table name already exists or is a view - * @throws UnsupportedOperationException If the namespaces of old and new identiers do not + * @throws UnsupportedOperationException If the namespaces of old and new identifiers do not * match (optional) */ void renameTable(Identifier oldIdent, Identifier newIdent) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/QueryPlanningTracker.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/QueryPlanningTracker.scala index cd75407c7ee7a..35551d8ba77dc 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/QueryPlanningTracker.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/QueryPlanningTracker.scala @@ -28,7 +28,7 @@ import org.apache.spark.util.BoundedPriorityQueue * There are two separate concepts we track: * * 1. Phases: These are broad scope phases in query planning, as listed below, i.e. analysis, - * optimizationm and physical planning (just planning). + * optimization and physical planning (just planning). * * 2. Rules: These are the individual Catalyst rules that we track. In addition to time, we also * track the number of invocations and effective invocations. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowTablePropertiesExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowTablePropertiesExec.scala index fef63cb8253ca..95715fd1af56e 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowTablePropertiesExec.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ShowTablePropertiesExec.scala @@ -36,7 +36,7 @@ case class ShowTablePropertiesExec( import scala.collection.JavaConverters._ val toRow = RowEncoder(schema).resolveAndBind().createSerializer() - // The reservered properties are accessible through DESCRIBE + // The reserved properties are accessible through DESCRIBE val properties = catalogTable.properties.asScala .filter { case (k, v) => !CatalogV2Util.TABLE_RESERVED_PROPERTIES.contains(k) } propertyKey match {