diff options
author | hyukjinkwon <gurwls223@gmail.com> | 2016-04-16 14:56:23 +0100 |
---|---|---|
committer | Sean Owen <sowen@cloudera.com> | 2016-04-16 14:56:23 +0100 |
commit | 9f678e97549b19d6d979b22fa4079094ce9fb2c0 (patch) | |
tree | 978e18e46d294ba336f4657c6d627d146680f915 /sql | |
parent | 527c780bb0d6cb074128448da00cb330e9049385 (diff) | |
download | spark-9f678e97549b19d6d979b22fa4079094ce9fb2c0.tar.gz spark-9f678e97549b19d6d979b22fa4079094ce9fb2c0.tar.bz2 spark-9f678e97549b19d6d979b22fa4079094ce9fb2c0.zip |
[MINOR] Remove inappropriate type notation and extra anonymous closure within functional transformations
## What changes were proposed in this pull request?
This PR removes
- Inappropriate type notations
For example, from
```scala
words.foreachRDD { (rdd: RDD[String], time: Time) =>
...
```
to
```scala
words.foreachRDD { (rdd, time) =>
...
```
- Extra anonymous closure within functional transformations.
For example,
```scala
.map(item => {
...
})
```
which can be just simply as below:
```scala
.map { item =>
...
}
```
and corrects some obvious style nits.
## How was this patch tested?
This was tested after adding rules in `scalastyle-config.xml`, which ended up with not finding all perfectly.
The rules applied were below:
- For the first correction,
```xml
<check customId="NoExtraClosure" level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter name="regex">(?m)\.[a-zA-Z_][a-zA-Z0-9]*\(\s*[^,]+s*=>\s*\{[^\}]+\}\s*\)</parameter></parameters>
</check>
```
```xml
<check customId="NoExtraClosure" level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter name="regex">\.[a-zA-Z_][a-zA-Z0-9]*\s*[\{|\(]([^\n>,]+=>)?\s*\{([^()]|(?R))*\}^[,]</parameter></parameters>
</check>
```
- For the second correction
```xml
<check customId="TypeNotation" level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter name="regex">\.[a-zA-Z_][a-zA-Z0-9]*\s*[\{|\(]\s*\([^):]*:R))*\}^[,]</parameter></parameters>
</check>
```
**Those rules were not added**
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #12413 from HyukjinKwon/SPARK-style.
Diffstat (limited to 'sql')
6 files changed, 13 insertions, 21 deletions
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 37ff6ab6f6..6591559426 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 @@ -172,8 +172,8 @@ class Analyzer( private def assignAliases(exprs: Seq[NamedExpression]) = { exprs.zipWithIndex.map { case (expr, i) => - expr transformUp { - case u @ UnresolvedAlias(child, optionalAliasName) => child match { + expr.transformUp { case u @ UnresolvedAlias(child, optionalAliasName) => + child match { case ne: NamedExpression => ne case e if !e.resolved => u case g: Generator => MultiAlias(g, Nil) @@ -215,7 +215,7 @@ class Analyzer( * represented as the bit masks. */ def bitmasks(r: Rollup): Seq[Int] = { - Seq.tabulate(r.groupByExprs.length + 1)(idx => {(1 << idx) - 1}) + Seq.tabulate(r.groupByExprs.length + 1)(idx => (1 << idx) - 1) } /* diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala index 354311c5e7..27ad8e4cf2 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Projection.scala @@ -168,9 +168,7 @@ object FromUnsafeProjection { * Returns an UnsafeProjection for given Array of DataTypes. */ def apply(fields: Seq[DataType]): Projection = { - create(fields.zipWithIndex.map(x => { - new BoundReference(x._2, x._1, true) - })) + create(fields.zipWithIndex.map(x => new BoundReference(x._2, x._1, true))) } /** diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala index 6c8f8f40dd..c46bdfb2b5 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala @@ -314,11 +314,9 @@ object SetOperationPushDown extends Rule[LogicalPlan] with PredicateHelper { assert(children.nonEmpty) val (deterministic, nondeterministic) = partitionByDeterministic(condition) val newFirstChild = Filter(deterministic, children.head) - val newOtherChildren = children.tail.map { - child => { - val rewrites = buildRewrites(children.head, child) - Filter(pushToRight(deterministic, rewrites), child) - } + val newOtherChildren = children.tail.map { child => + val rewrites = buildRewrites(children.head, child) + Filter(pushToRight(deterministic, rewrites), child) } Filter(nondeterministic, Union(newFirstChild +: newOtherChildren)) @@ -360,7 +358,7 @@ object ColumnPruning extends Rule[LogicalPlan] { case a @ Project(_, e @ Expand(_, _, grandChild)) if (e.outputSet -- a.references).nonEmpty => val newOutput = e.output.filter(a.references.contains(_)) val newProjects = e.projections.map { proj => - proj.zip(e.output).filter { case (e, a) => + proj.zip(e.output).filter { case (_, a) => newOutput.contains(a) }.unzip._1 } diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoin.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoin.scala index 0c3e3c3fc1..f021f3758c 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoin.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoin.scala @@ -60,9 +60,7 @@ case class ShuffledHashJoin( val context = TaskContext.get() val relation = HashedRelation(iter, buildKeys, taskMemoryManager = context.taskMemoryManager()) // This relation is usually used until the end of task. - context.addTaskCompletionListener((t: TaskContext) => - relation.close() - ) + context.addTaskCompletionListener(_ => relation.close()) relation } diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala index d603f63a08..9afbd0e994 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/stat/StatFunctions.scala @@ -431,7 +431,7 @@ private[sql] object StatFunctions extends Logging { s"exceed 1e4. Currently $columnSize") val table = counts.groupBy(_.get(0)).map { case (col1Item, rows) => val countsRow = new GenericMutableRow(columnSize + 1) - rows.foreach { (row: Row) => + rows.foreach { row => // row.get(0) is column 1 // row.get(1) is column 2 // row.get(2) is the frequency diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala index 784b018353..5aab4132bc 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala @@ -82,7 +82,7 @@ private[hive] case class HiveSimpleUDF( // TODO: Finish input output types. override def eval(input: InternalRow): Any = { - val inputs = wrap(children.map(c => c.eval(input)), arguments, cached, inputDataTypes) + val inputs = wrap(children.map(_.eval(input)), arguments, cached, inputDataTypes) val ret = FunctionRegistry.invoke( method, function, @@ -152,10 +152,8 @@ private[hive] case class HiveGenericUDF( var i = 0 while (i < children.length) { val idx = i - deferredObjects(i).asInstanceOf[DeferredObjectAdapter].set( - () => { - children(idx).eval(input) - }) + deferredObjects(i).asInstanceOf[DeferredObjectAdapter] + .set(() => children(idx).eval(input)) i += 1 } unwrap(function.evaluate(deferredObjects), returnInspector) |