This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 800d3729c9c2 [SPARK-53035][CORE][SQL][K8S][MLLIB] Use `String.repeat`
instead of Scala string multiplication
800d3729c9c2 is described below
commit 800d3729c9c2c1b1bf2d4c326d1ade610a7f2ada
Author: Dongjoon Hyun <dongj...@apache.org>
AuthorDate: Thu Jul 31 03:42:49 2025 -0700
[SPARK-53035][CORE][SQL][K8S][MLLIB] Use `String.repeat` instead of Scala
string multiplication
### What changes were proposed in this pull request?
This PR aims to use `String.repeat` (Java 11+) instead of Scala string
multiplication with `*`. The focus of change is `main` source code.
**BEFORE**
```
$ git grep '" \* ' | grep main | wc -l
21
```
**AFTER**
```
$ git grep '" \* ' | grep main | wc -l
0
```
### Why are the changes needed?
`String.repeat` is **significantly faster** than Scala implementation.
```scala
scala> spark.time((" " * 500_000_000).length)
Time taken: 1408 ms
val res0: Int = 500000000
scala> spark.time((" ".repeat(500_000_000)).length)
Time taken: 22 ms
val res1: Int = 500000000
```
### Does this PR introduce _any_ user-facing change?
No behavior change.
### How was this patch tested?
Pass the existing CIs because this is the replacement.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #51740 from dongjoon-hyun/SPARK-53035.
Authored-by: Dongjoon Hyun <dongj...@apache.org>
Signed-off-by: Dongjoon Hyun <dongj...@apache.org>
---
.../main/scala/org/apache/spark/util/SparkStringUtils.scala | 2 +-
.../apache/spark/deploy/history/HistoryServerArguments.scala | 2 +-
.../scala/org/apache/spark/deploy/worker/DriverRunner.scala | 2 +-
.../scala/org/apache/spark/deploy/worker/ExecutorRunner.scala | 2 +-
core/src/main/scala/org/apache/spark/rdd/RDD.scala | 4 ++--
.../main/scala/org/apache/spark/ui/ConsoleProgressBar.scala | 2 +-
mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala | 4 ++--
.../main/scala/org/apache/spark/mllib/tree/model/Node.scala | 2 +-
.../scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala | 2 +-
.../spark/sql/catalyst/expressions/codegen/CodeFormatter.scala | 4 ++--
.../org/apache/spark/sql/catalyst/util/ToNumberParser.scala | 10 +++++-----
.../src/main/scala/org/apache/spark/sql/classic/Dataset.scala | 2 +-
.../spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala | 2 +-
.../main/scala/org/apache/spark/streaming/util/StateMap.scala | 2 +-
14 files changed, 21 insertions(+), 21 deletions(-)
diff --git
a/common/utils/src/main/scala/org/apache/spark/util/SparkStringUtils.scala
b/common/utils/src/main/scala/org/apache/spark/util/SparkStringUtils.scala
index dbe7d78937e9..12622b13d21f 100644
--- a/common/utils/src/main/scala/org/apache/spark/util/SparkStringUtils.scala
+++ b/common/utils/src/main/scala/org/apache/spark/util/SparkStringUtils.scala
@@ -60,7 +60,7 @@ private[spark] trait SparkStringUtils {
val rightPadded = right ++ Seq.fill(math.max(left.size - right.size,
0))("")
leftPadded.zip(rightPadded).map { case (l, r) =>
- (if (l == r) " " else "!") + l + (" " * ((maxLeftSize - l.length) + 3))
+ r
+ (if (l == r) " " else "!") + l + " ".repeat((maxLeftSize - l.length) +
3) + r
}
}
diff --git
a/core/src/main/scala/org/apache/spark/deploy/history/HistoryServerArguments.scala
b/core/src/main/scala/org/apache/spark/deploy/history/HistoryServerArguments.scala
index f1343a055138..14d6e4a0381a 100644
---
a/core/src/main/scala/org/apache/spark/deploy/history/HistoryServerArguments.scala
+++
b/core/src/main/scala/org/apache/spark/deploy/history/HistoryServerArguments.scala
@@ -83,7 +83,7 @@ private[history] class HistoryServerArguments(conf:
SparkConf, args: Array[Strin
configs.sortBy(_.key).foreach { conf =>
sb.append(" ").append(conf.key.padTo(maxConfigLength, ' '))
var currentDocLen = 0
- val intention = "\n" + " " * (maxConfigLength + 2)
+ val intention = "\n" + " ".repeat(maxConfigLength + 2)
conf.doc.split("\\s+").foreach { word =>
if (currentDocLen + word.length > 60) {
sb.append(intention).append(" ").append(word)
diff --git
a/core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala
b/core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala
index 22e4c83440f6..e52bb3ae6d22 100644
--- a/core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/worker/DriverRunner.scala
@@ -215,7 +215,7 @@ private[deploy] class DriverRunner(
val stderr = new File(baseDir, "stderr")
val redactedCommand = Utils.redactCommandLineArgs(conf,
builder.command.asScala.toSeq)
.mkString("\"", "\" \"", "\"")
- val header = "Launch Command: %s\n%s\n\n".format(redactedCommand, "=" *
40)
+ val header = "Launch Command: %s\n%s\n\n".format(redactedCommand,
"=".repeat(40))
Files.asCharSink(stderr, StandardCharsets.UTF_8,
FileWriteMode.APPEND).write(header)
CommandUtils.redirectStream(process.getErrorStream, stderr)
}
diff --git
a/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala
b/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala
index d21904dd16ea..1476bdd5c016 100644
--- a/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala
@@ -184,7 +184,7 @@ private[deploy] class ExecutorRunner(
process = builder.start()
val header = "Spark Executor Command: %s\n%s\n\n".format(
- redactedCommand, "=" * 40)
+ redactedCommand, "=".repeat(40))
// Redirect its stdout and stderr to files
val stdout = new File(executorDir, "stdout")
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 80db818b77e4..b3d412ed0494 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -2016,7 +2016,7 @@ abstract class RDD[T: ClassTag](
def firstDebugString(rdd: RDD[_]): Seq[String] = {
val partitionStr = "(" + rdd.partitions.length + ")"
val leftOffset = (partitionStr.length - 1) / 2
- val nextPrefix = (" " * leftOffset) + "|" + (" " * (partitionStr.length
- leftOffset))
+ val nextPrefix = " ".repeat(leftOffset) + "|" + "
".repeat(partitionStr.length - leftOffset)
debugSelf(rdd).zipWithIndex.map{
case (desc: String, 0) => s"$partitionStr $desc"
@@ -2030,7 +2030,7 @@ abstract class RDD[T: ClassTag](
val nextPrefix = (
thisPrefix
+ (if (isLastChild) " " else "| ")
- + (" " * leftOffset) + "|" + (" " * (partitionStr.length -
leftOffset)))
+ + (" ".repeat(leftOffset)) + "|" + (" ".repeat(partitionStr.length -
leftOffset)))
debugSelf(rdd).zipWithIndex.map{
case (desc: String, 0) => s"$thisPrefix+-$partitionStr $desc"
diff --git a/core/src/main/scala/org/apache/spark/ui/ConsoleProgressBar.scala
b/core/src/main/scala/org/apache/spark/ui/ConsoleProgressBar.scala
index 980cd6e541a2..0ce0f69b2070 100644
--- a/core/src/main/scala/org/apache/spark/ui/ConsoleProgressBar.scala
+++ b/core/src/main/scala/org/apache/spark/ui/ConsoleProgressBar.scala
@@ -105,7 +105,7 @@ private[spark] class ConsoleProgressBar(sc: SparkContext)
extends Logging {
*/
private def clear(): Unit = {
if (!lastProgressBar.isEmpty) {
- console.printf(s"$CR${" " * TerminalWidth}$CR")
+ console.printf(s"$CR${" ".repeat(TerminalWidth)}$CR")
lastProgressBar = ""
}
}
diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala
b/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala
index 697d98953839..b68a5e079dc4 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala
@@ -134,7 +134,7 @@ class LeafNode private[ml] (
override private[tree] def numDescendants: Int = 0
override private[tree] def subtreeToString(indentFactor: Int = 0): String = {
- val prefix: String = " " * indentFactor
+ val prefix: String = " ".repeat(indentFactor)
prefix + s"Predict: $prediction\n"
}
@@ -212,7 +212,7 @@ class InternalNode private[ml] (
}
override private[tree] def subtreeToString(indentFactor: Int = 0): String = {
- val prefix: String = " " * indentFactor
+ val prefix: String = " ".repeat(indentFactor)
prefix + s"If (${InternalNode.splitToString(split, left = true)})\n" +
leftChild.subtreeToString(indentFactor + 1) +
prefix + s"Else (${InternalNode.splitToString(split, left = false)})\n" +
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
index bac36ce6937b..a0eec8b2afb9 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala
@@ -137,7 +137,7 @@ class Node @Since("1.2.0") (
}
}
}
- val prefix: String = " " * indentFactor
+ val prefix: String = " ".repeat(indentFactor)
if (isLeaf) {
prefix + s"Predict: ${predict.predict}\n"
} else {
diff --git
a/resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala
b/resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala
index c2fcfe179bbe..7f8bdb38b893 100644
---
a/resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala
+++
b/resource-managers/kubernetes/core/src/main/scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala
@@ -146,7 +146,7 @@ object KubernetesUtils extends Logging {
@Since("3.0.0")
def formatPairsBundle(pairs: Seq[(String, String)], indent: Int = 1) :
String = {
// Use more loggable format if value is null or empty
- val indentStr = "\t" * indent
+ val indentStr = "\t".repeat(indent)
pairs.map {
case (k, v) => s"\n$indentStr $k:
${Option(v).filter(_.nonEmpty).getOrElse("N/A")}"
}.mkString("")
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeFormatter.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeFormatter.scala
index 2ec31458270f..4fb180a72012 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeFormatter.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeFormatter.scala
@@ -144,7 +144,7 @@ private class CodeFormatter {
// Lines starting with '}' should be de-indented even if they contain '{'
after;
// in addition, lines ending with ':' are typically labels
val thisLineIndent = if (line.startsWith("}") || line.startsWith(")") ||
line.endsWith(":")) {
- " " * (indentSize * (indentLevel - 1))
+ " ".repeat(indentSize * (indentLevel - 1))
} else {
indentString
}
@@ -157,7 +157,7 @@ private class CodeFormatter {
}
code.append("\n")
indentLevel = newIndentLevel
- indentString = " " * (indentSize * newIndentLevel)
+ indentString = " ".repeat(indentSize * newIndentLevel)
currentLine += 1
}
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala
index b66658467c1b..ea2f48fafc0d 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ToNumberParser.scala
@@ -619,7 +619,7 @@ class ToNumberParser(numberFormat: String, errorOnFail:
Boolean) extends Seriali
// digits as the scale. This is necessary because we must determine the
scale from the format
// string alone but each input string may include a variable number of
digits after the decimal
// point.
- val extraZeros = "0" * (scale - parsedAfterDecimalPoint.length)
+ val extraZeros = "0".repeat(scale - parsedAfterDecimalPoint.length)
val afterDecimalPadded = parsedAfterDecimalPoint.toString + extraZeros
val prefix = if (negateResult) "-" else ""
val suffix = if (afterDecimalPadded.nonEmpty) "." + afterDecimalPadded
else ""
@@ -763,11 +763,11 @@ class ToNumberParser(numberFormat: String, errorOnFail:
Boolean) extends Seriali
// than specified in the format string, this is an overflow.
if (numFormatDigitsBeforeDecimalPoint < beforeDecimalPoint.length ||
numFormatDigitsAfterDecimalPoint < afterDecimalPoint.length) {
- beforeDecimalPoint = "#" * numFormatDigitsBeforeDecimalPoint
- afterDecimalPoint = "#" * numFormatDigitsAfterDecimalPoint
+ beforeDecimalPoint = "#".repeat(numFormatDigitsBeforeDecimalPoint)
+ afterDecimalPoint = "#".repeat(numFormatDigitsAfterDecimalPoint)
}
- val leadingSpaces = " " * (numFormatDigitsBeforeDecimalPoint -
beforeDecimalPoint.length)
- val trailingZeros = "0" * (numFormatDigitsAfterDecimalPoint -
afterDecimalPoint.length)
+ val leadingSpaces = " ".repeat(numFormatDigitsBeforeDecimalPoint -
beforeDecimalPoint.length)
+ val trailingZeros = "0".repeat(numFormatDigitsAfterDecimalPoint -
afterDecimalPoint.length)
(leadingSpaces + beforeDecimalPoint, afterDecimalPoint + trailingZeros)
}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala
b/sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala
index 8327d8181619..940517617425 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/classic/Dataset.scala
@@ -404,7 +404,7 @@ class Dataset[T] private[sql](
}
// Create SeparateLine
- val sep: String = colWidths.map("-" * _).addString(sb, "+", "+",
"+\n").toString()
+ val sep: String = colWidths.map("-".repeat(_)).addString(sb, "+", "+",
"+\n").toString()
// column names
paddedRows.head.addString(sb, "|", "|", "|\n")
diff --git
a/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala
b/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala
index 9354f03297c5..00376670956d 100644
---
a/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala
+++
b/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala
@@ -488,7 +488,7 @@ case class AdaptiveSparkPlanExec(
maxFields: Int,
printNodeId: Boolean,
printOutputColumns: Boolean): Unit = {
- append(" " * depth)
+ append(" ".repeat(depth))
append(s"+- == $header ==\n")
plan.generateTreeString(
0,
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 c125bd13cd35..674a53b1cdf5 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
@@ -202,7 +202,7 @@ private[streaming] class OpenHashMapBasedStateMap[K, S](
/** Get all the data of this map as string formatted as a tree based on the
delta depth */
override def toDebugString(): String = {
val tabs = if (deltaChainLength > 0) {
- (" " * (deltaChainLength - 1)) + "+--- "
+ (" ".repeat(deltaChainLength - 1)) + "+--- "
} else ""
parentStateMap.toDebugString() + "\n" + deltaMap.iterator.mkString(tabs,
"\n" + tabs, "")
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
