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 423bca63dec4 [SPARK-53214][CORE][SQL][K8S] Use Java `HexFormat`
instead of `Hex.encodeHexString`
423bca63dec4 is described below
commit 423bca63dec4772d96a2dbf293318cd5c428a598
Author: Dongjoon Hyun <dongj...@apache.org>
AuthorDate: Sat Aug 9 17:42:16 2025 -0700
[SPARK-53214][CORE][SQL][K8S] Use Java `HexFormat` instead of
`Hex.encodeHexString`
### What changes were proposed in this pull request?
This PR aims to use Java 17+ `HexFormat` instead of Apache Commons Codec
`Hex.encodeHexString`.
### Why are the changes needed?
Java native method is ***roughly 2x*** faster than Apache Commons Codec API.
```scala
scala> val a = new Array[Byte](1_000_000_000)
scala> spark.time(org.apache.commons.codec.binary.Hex.encodeHexString(a,
false).length)
Time taken: 1559 ms
val res0: Int = 2000000000
scala>
spark.time(java.util.HexFormat.of().withUpperCase().formatHex(a).length)
Time taken: 672 ms
val res1: Int = 2000000000
```
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Pass the CIs.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #51939 from dongjoon-hyun/SPARK-53214.
Authored-by: Dongjoon Hyun <dongj...@apache.org>
Signed-off-by: Dongjoon Hyun <dongj...@apache.org>
---
core/src/main/scala/org/apache/spark/util/Utils.scala | 5 ++---
.../main/scala/org/apache/spark/deploy/k8s/KubernetesUtils.scala | 5 ++---
scalastyle-config.xml | 5 +++++
.../scala/org/apache/spark/sql/catalyst/expressions/literals.scala | 7 +++----
.../org/apache/spark/sql/connector/expressions/expressions.scala | 4 ++--
.../src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala | 5 ++---
6 files changed, 16 insertions(+), 15 deletions(-)
diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala
b/core/src/main/scala/org/apache/spark/util/Utils.scala
index a9ceadc208dd..3b525cd69430 100644
--- a/core/src/main/scala/org/apache/spark/util/Utils.scala
+++ b/core/src/main/scala/org/apache/spark/util/Utils.scala
@@ -28,7 +28,7 @@ import java.nio.channels.Channels
import java.nio.charset.StandardCharsets
import java.nio.file.Files
import java.security.SecureRandom
-import java.util.{Locale, Properties, Random, UUID}
+import java.util.{HexFormat, Locale, Properties, Random, UUID}
import java.util.concurrent._
import java.util.concurrent.TimeUnit.NANOSECONDS
import java.util.zip.{GZIPInputStream, ZipInputStream}
@@ -48,7 +48,6 @@ import com.google.common.cache.{CacheBuilder, CacheLoader,
LoadingCache}
import com.google.common.collect.Interners
import com.google.common.net.InetAddresses
import jakarta.ws.rs.core.UriBuilder
-import org.apache.commons.codec.binary.Hex
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, FileUtil, Path}
import org.apache.hadoop.fs.audit.CommonAuditContext.currentAuditContext
@@ -2919,7 +2918,7 @@ private[spark] object Utils
val rnd = new SecureRandom()
val secretBytes = new Array[Byte](bits / JByte.SIZE)
rnd.nextBytes(secretBytes)
- Hex.encodeHexString(secretBytes)
+ HexFormat.of().formatHex(secretBytes)
}
/**
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 5f79c894c232..a6eb0fcc98b9 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
@@ -19,13 +19,12 @@ package org.apache.spark.deploy.k8s
import java.io.{File, IOException}
import java.net.URI
import java.security.SecureRandom
-import java.util.{Collections, UUID}
+import java.util.{Collections, HexFormat, UUID}
import scala.jdk.CollectionConverters._
import io.fabric8.kubernetes.api.model.{Container, ContainerBuilder,
ContainerStateRunning, ContainerStateTerminated, ContainerStateWaiting,
ContainerStatus, EnvVar, EnvVarBuilder, EnvVarSourceBuilder, HasMetadata,
OwnerReferenceBuilder, Pod, PodBuilder, Quantity}
import io.fabric8.kubernetes.client.KubernetesClient
-import org.apache.commons.codec.binary.Hex
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.spark.{SparkConf, SparkException}
@@ -241,7 +240,7 @@ object KubernetesUtils extends Logging {
}
val time = java.lang.Long.toHexString(clock.getTimeMillis() &
0xFFFFFFFFFFL)
- Hex.encodeHexString(random) + time
+ HexFormat.of().formatHex(random) + time
}
/**
diff --git a/scalastyle-config.xml b/scalastyle-config.xml
index bc28bfe295a8..48362ca6f9a2 100644
--- a/scalastyle-config.xml
+++ b/scalastyle-config.xml
@@ -499,6 +499,11 @@ This file is divided into 3 sections:
<customMessage>Use Utils.strip method instead</customMessage>
</check>
+ <check customId="encodeHexString" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bHex\.encodeHexString\b</parameter></parameters>
+ <customMessage>Use java.util.HexFormat instead</customMessage>
+ </check>
+
<check customId="commonsiofileutils" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter
name="regex">org\.apache\.commons\.io\.FileUtils\b</parameter></parameters>
<customMessage>Use Java API or Spark's JavaUtils/SparkSystemUtils/Utils
instead</customMessage>
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
index b1d8c636118d..c799415dfc70 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/literals.scala
@@ -30,14 +30,13 @@ import java.nio.charset.StandardCharsets
import java.sql.{Date, Timestamp}
import java.time.{Duration, Instant, LocalDate, LocalDateTime, LocalTime,
Period, ZoneOffset}
import java.util
-import java.util.Objects
+import java.util.{HexFormat, Objects}
import scala.collection.{immutable, mutable}
import scala.math.{BigDecimal, BigInt}
import scala.reflect.runtime.universe.TypeTag
import scala.util.Try
-import org.apache.commons.codec.binary.{Hex => ApacheHex}
import org.json4s.JsonAST._
import org.apache.spark.sql.catalyst.{CatalystTypeConverters,
FunctionIdentifier, InternalRow, ScalaReflection}
@@ -432,7 +431,7 @@ case class Literal (value: Any, dataType: DataType) extends
LeafExpression {
override def toString: String = value match {
case null => "null"
- case binary: Array[Byte] => "0x" + ApacheHex.encodeHexString(binary, false)
+ case binary: Array[Byte] => "0x" +
HexFormat.of().withUpperCase().formatHex(binary)
case d: ArrayBasedMapData => s"map(${d.toString})"
case other =>
dataType match {
@@ -578,7 +577,7 @@ case class Literal (value: Any, dataType: DataType) extends
LeafExpression {
s"TIMESTAMP_NTZ '$toString'"
case (i: CalendarInterval, CalendarIntervalType) =>
s"INTERVAL '${i.toString}'"
- case (v: Array[Byte], BinaryType) => s"X'${ApacheHex.encodeHexString(v,
false)}'"
+ case (v: Array[Byte], BinaryType) =>
s"X'${HexFormat.of().withUpperCase().formatHex(v)}'"
case (i: Long, DayTimeIntervalType(startField, endField)) =>
toDayTimeIntervalString(i, ANSI_STYLE, startField, endField)
case (i: Int, YearMonthIntervalType(startField, endField)) =>
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/connector/expressions/expressions.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/connector/expressions/expressions.scala
index d9d91e187e8a..18d94969aa27 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/connector/expressions/expressions.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/connector/expressions/expressions.scala
@@ -17,7 +17,7 @@
package org.apache.spark.sql.connector.expressions
-import org.apache.commons.codec.binary.Hex
+import java.util.HexFormat
import org.apache.spark.SparkException
import org.apache.spark.sql.catalyst
@@ -393,7 +393,7 @@ private[sql] final case class LiteralValue[T](value: T,
dataType: DataType) exte
case BinaryType =>
assert(value.isInstanceOf[Array[Byte]])
val bytes = value.asInstanceOf[Array[Byte]]
- "0x" + Hex.encodeHexString(bytes, false)
+ "0x" + HexFormat.of().withUpperCase().formatHex(bytes)
case _ => s"$value"
}
}
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
index d19585a3b8f2..c6a48d98fa98 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCV2Suite.scala
@@ -18,11 +18,10 @@
package org.apache.spark.sql.jdbc
import java.sql.{Connection, DriverManager}
-import java.util.Properties
+import java.util.{HexFormat, Properties}
import scala.util.control.NonFatal
-import org.apache.commons.codec.binary.Hex
import
test.org.apache.spark.sql.connector.catalog.functions.JavaStrLen.JavaStrLenStaticMagic
import org.apache.spark.{SparkConf, SparkException,
SparkIllegalArgumentException}
@@ -3103,7 +3102,7 @@ class JDBCV2Suite extends QueryTest with
SharedSparkSession with ExplainSuiteHel
}
test("SPARK-50792: Format binary data as a binary literal in JDBC.") {
- val hexBinary = Hex.encodeHexString(testBytes, false)
+ val hexBinary = HexFormat.of().withUpperCase().formatHex(testBytes)
val binary = "X'" + hexBinary + "'"
val df = sql(s"SELECT * FROM h2.test.binary_tab WHERE b = $binary")
checkFiltersRemoved(df)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
