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 8eaad0069e3f [SPARK-53195][CORE] Use Java `InputStream.readNBytes`
instead of `ByteStreams.read`
8eaad0069e3f is described below
commit 8eaad0069e3f26264be849600ee224b9ca9bafc8
Author: Dongjoon Hyun <dongj...@apache.org>
AuthorDate: Fri Aug 8 06:35:12 2025 -0700
[SPARK-53195][CORE] Use Java `InputStream.readNBytes` instead of
`ByteStreams.read`
### What changes were proposed in this pull request?
This PR aims to use Java 9+ `InputStream.readNBytes` API instead of
`ByteStreams.read`.
### Why are the changes needed?
To simplify the code by using native Java API.
```scala
- var numBytes = ByteStreams.read(gzInputStream, buf, 0, bufSize)
+ var numBytes = gzInputStream.readNBytes(buf, 0, bufSize)
```
### Does this PR introduce _any_ user-facing change?
No behavior change.
### How was this patch tested?
Pass the CIs.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #51923 from dongjoon-hyun/SPARK-53195.
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 | 6 +++---
scalastyle-config.xml | 5 +++++
2 files changed, 8 insertions(+), 3 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 57f70489a860..4f2d5fe8f820 100644
--- a/core/src/main/scala/org/apache/spark/util/Utils.scala
+++ b/core/src/main/scala/org/apache/spark/util/Utils.scala
@@ -46,7 +46,7 @@ import scala.util.matching.Regex
import _root_.io.netty.channel.unix.Errors.NativeIoException
import com.google.common.cache.{CacheBuilder, CacheLoader, LoadingCache}
import com.google.common.collect.Interners
-import com.google.common.io.{ByteStreams, Files => GFiles}
+import com.google.common.io.{Files => GFiles}
import com.google.common.net.InetAddresses
import jakarta.ws.rs.core.UriBuilder
import org.apache.commons.codec.binary.Hex
@@ -1558,10 +1558,10 @@ private[spark] object Utils
gzInputStream = new GZIPInputStream(new FileInputStream(file))
val bufSize = 1024
val buf = new Array[Byte](bufSize)
- var numBytes = ByteStreams.read(gzInputStream, buf, 0, bufSize)
+ var numBytes = gzInputStream.readNBytes(buf, 0, bufSize)
while (numBytes > 0) {
fileSize += numBytes
- numBytes = ByteStreams.read(gzInputStream, buf, 0, bufSize)
+ numBytes = gzInputStream.readNBytes(buf, 0, bufSize)
}
fileSize
} catch {
diff --git a/scalastyle-config.xml b/scalastyle-config.xml
index e6d0007cae48..42e3913f10d6 100644
--- a/scalastyle-config.xml
+++ b/scalastyle-config.xml
@@ -732,6 +732,11 @@ This file is divided into 3 sections:
<customMessage>Use Java `write` instead.</customMessage>
</check>
+ <check customId="bytestreamsread" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bByteStreams\.read\b</parameter></parameters>
+ <customMessage>Use Java readNBytes instead.</customMessage>
+ </check>
+
<check customId="bytestreamscopy" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter
name="regex">\bByteStreams\.copy\b</parameter></parameters>
<customMessage>Use Java transferTo instead.</customMessage>
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
