This is an automated email from the ASF dual-hosted git repository.
csy pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/auron.git
The following commit(s) were added to refs/heads/master by this push:
new 61fbac23 [AURON #1867][BUILD] Add scalastyle-maven-plugin (#1868)
61fbac23 is described below
commit 61fbac23baa2105072f0ca78727ca6b57af94d94
Author: yew1eb <[email protected]>
AuthorDate: Mon Jan 19 18:54:12 2026 +0800
[AURON #1867][BUILD] Add scalastyle-maven-plugin (#1868)
# Which issue does this PR close?
Closes #1867
# Rationale for this change
# What changes are included in this PR?
# Are there any user-facing changes?
# How was this patch tested?
---
dev/scalastyle-config.xml | 856 +++++++++++++++++++++
pom.xml | 27 +
.../NativeParquetInsertIntoHiveTableExec.scala | 9 +-
.../auron/plan/NativeShuffleExchangeExec.scala | 6 +-
.../joins/auron/plan/NativeBroadcastJoinExec.scala | 5 +-
.../auron/columnar/AuronArrowColumnVector.scala | 9 +-
.../auron/columnar/AuronColumnarMap.scala | 2 +-
.../shuffle/AuronBlockStoreShuffleReaderBase.scala | 2 +
.../uniffle/AuronUniffleShuffleReader.scala | 3 +-
9 files changed, 906 insertions(+), 13 deletions(-)
diff --git a/dev/scalastyle-config.xml b/dev/scalastyle-config.xml
new file mode 100644
index 00000000..f5b517a0
--- /dev/null
+++ b/dev/scalastyle-config.xml
@@ -0,0 +1,856 @@
+<!--
+ ~ Licensed to the Apache Software Foundation (ASF) under one or more
+ ~ contributor license agreements. See the NOTICE file distributed with
+ ~ this work for additional information regarding copyright ownership.
+ ~ The ASF licenses this file to You under the Apache License, Version 2.0
+ ~ (the "License"); you may not use this file except in compliance with
+ ~ the License. You may obtain a copy of the License at
+ ~
+ ~ http://www.apache.org/licenses/LICENSE-2.0
+ ~
+ ~ Unless required by applicable law or agreed to in writing, software
+ ~ distributed under the License is distributed on an "AS IS" BASIS,
+ ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ ~ See the License for the specific language governing permissions and
+ ~ limitations under the License.
+ -->
+<!--
+
+If you wish to turn off checking for a section of code, you can put a comment
in the source
+before and after the section, with the following syntax:
+
+ // scalastyle:off
+ ... // stuff that breaks the styles
+ // scalastyle:on
+
+You can also disable only one rule, by specifying its rule id, as specified in:
+ http://www.scalastyle.org/rules-0.7.0.html
+
+ // scalastyle:off no.finalize
+ override def finalize(): Unit = ...
+ // scalastyle:on no.finalize
+
+This file is divided into 3 sections:
+ (1) rules that we enforce.
+ (2) rules that we would like to enforce, but haven't cleaned up the codebase
to turn on yet
+ (or we need to make the scalastyle rule more configurable).
+ (3) rules that we don't want to enforce.
+-->
+
+<scalastyle>
+ <name>Scalastyle standard configuration</name>
+
+ <!--
================================================================================
-->
+ <!-- rules we enforce
-->
+ <!--
================================================================================
-->
+
+ <check level="error" class="org.scalastyle.file.FileTabChecker"
enabled="true"></check>
+
+ <check customId="license" level="error"
class="org.scalastyle.file.HeaderMatchesChecker" enabled="true">
+ <parameters>
+ <parameter name="header"><![CDATA[/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */]]></parameter>
+ </parameters>
+ </check>
+
+ <check level="error"
class="org.scalastyle.scalariform.SpacesAfterPlusChecker"
enabled="true"></check>
+
+ <check level="error"
class="org.scalastyle.scalariform.SpacesBeforePlusChecker"
enabled="true"></check>
+
+ <check level="error" class="org.scalastyle.file.WhitespaceEndOfLineChecker"
enabled="true"></check>
+
+ <check level="error" class="org.scalastyle.file.FileLineLengthChecker"
enabled="false">
+ <parameters>
+ <parameter name="maxLineLength"><![CDATA[100]]></parameter>
+ <parameter name="tabSize"><![CDATA[2]]></parameter>
+ <parameter name="ignoreImports">true</parameter>
+ </parameters>
+ </check>
+
+ <check level="error" class="org.scalastyle.scalariform.ClassNamesChecker"
enabled="true">
+ <parameters>
+ <parameter
name="regex"><![CDATA[(sparkver.*|[A-Z][A-Za-z]*)]]></parameter>
+ </parameters>
+ </check>
+
+ <check level="error" class="org.scalastyle.scalariform.ObjectNamesChecker"
enabled="true">
+ <parameters><parameter
name="regex"><![CDATA[(config|sparkver|[A-Z][A-Za-z]*)]]></parameter></parameters>
+ </check>
+
+ <check level="error"
class="org.scalastyle.scalariform.PackageObjectNamesChecker" enabled="true">
+ <parameters><parameter
name="regex"><![CDATA[^[a-z][A-Za-z]*$]]></parameter></parameters>
+ </check>
+
+ <check customId="argcount" level="error"
class="org.scalastyle.scalariform.ParameterNumberChecker" enabled="true">
+ <parameters><parameter
name="maxParameters"><![CDATA[10]]></parameter></parameters>
+ </check>
+
+ <check level="error" class="org.scalastyle.scalariform.NoFinalizeChecker"
enabled="true"></check>
+
+ <check level="error"
class="org.scalastyle.scalariform.CovariantEqualsChecker"
enabled="true"></check>
+
+ <check level="error"
class="org.scalastyle.scalariform.StructuralTypeChecker" enabled="true"></check>
+
+ <check level="error" class="org.scalastyle.scalariform.UppercaseLChecker"
enabled="true"></check>
+
+ <check level="error" class="org.scalastyle.scalariform.IfBraceChecker"
enabled="true">
+ <parameters>
+ <parameter name="singleLineAllowed"><![CDATA[true]]></parameter>
+ <parameter name="doubleLineAllowed"><![CDATA[true]]></parameter>
+ </parameters>
+ </check>
+
+ <check customId="publicmethodtype" level="error"
class="org.scalastyle.scalariform.PublicMethodsHaveTypeChecker"
enabled="true"></check>
+
+ <check level="error" class="org.scalastyle.file.NewLineAtEofChecker"
enabled="true"></check>
+
+ <check customId="nonascii" level="error"
class="org.scalastyle.scalariform.NonASCIICharacterChecker"
enabled="true"></check>
+
+ <check level="error"
class="org.scalastyle.scalariform.SpaceAfterCommentStartChecker"
enabled="true"></check>
+
+ <check level="error"
class="org.scalastyle.scalariform.EnsureSingleSpaceBeforeTokenChecker"
enabled="true">
+ <parameters>
+ <parameter name="tokens">ARROW, EQUALS, ELSE, TRY, CATCH, FINALLY,
LARROW, RARROW</parameter>
+ </parameters>
+ </check>
+
+ <check level="error"
class="org.scalastyle.scalariform.EnsureSingleSpaceAfterTokenChecker"
enabled="true">
+ <parameters>
+ <parameter name="tokens">ARROW, EQUALS, COMMA, COLON, IF, ELSE, DO,
WHILE, FOR, MATCH, TRY, CATCH, FINALLY, LARROW, RARROW</parameter>
+ </parameters>
+ </check>
+
+ <!-- ??? usually shouldn't be checked into the code base. -->
+ <check level="error"
class="org.scalastyle.scalariform.NotImplementedErrorUsage"
enabled="true"></check>
+
+ <!-- As of SPARK-7558, all tests in Spark should extend o.a.s.SparkFunSuite
instead of AnyFunSuite directly -->
+ <check customId="funsuite" level="error"
class="org.scalastyle.scalariform.TokenChecker" enabled="true">
+ <parameters><parameter
name="regex">^AnyFunSuite[A-Za-z]*$</parameter></parameters>
+ <customMessage>Tests must extend org.apache.spark.SparkFunSuite
instead.</customMessage>
+ </check>
+
+ <!-- As of SPARK-7977 all printlns need to be wrapped in '//
scalastyle:off/on println' -->
+ <check customId="println" level="error"
class="org.scalastyle.scalariform.TokenChecker" enabled="true">
+ <parameters><parameter name="regex">^println$</parameter></parameters>
+ <customMessage><![CDATA[Are you sure you want to println? If yes, wrap the
code block with
+ // scalastyle:off println
+ println(...)
+ // scalastyle:on println]]></customMessage>
+ </check>
+
+ <check customId="invalidMDC" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">s".*\$\{MDC\(</parameter></parameters>
+ <customMessage><![CDATA[MDC should be used in string interpolation
log"..." instead of s"..."]]></customMessage>
+ </check>
+
+ <check customId="hadoopconfiguration" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">spark(.sqlContext)?.sparkContext.hadoopConfiguration</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use sparkContext.hadoopConfiguration? In
most cases, you should use
+ spark.sessionState.newHadoopConf() instead, so that the hadoop
configurations specified in Spark session
+ configuration will come into effect.
+ If you must use sparkContext.hadoopConfiguration, wrap the code block
with
+ // scalastyle:off hadoopconfiguration
+ spark.sparkContext.hadoopConfiguration...
+ // scalastyle:on hadoopconfiguration
+ ]]></customMessage>
+ </check>
+
+ <check customId="visiblefortesting" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">@VisibleForTesting</parameter></parameters>
+ <customMessage><![CDATA[
+ @VisibleForTesting causes classpath issues. Please note this in the java
doc instead (SPARK-11615).
+ ]]></customMessage>
+ </check>
+
+ <check customId="runtimeaddshutdownhook" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">Runtime\.getRuntime\.addShutdownHook</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use Runtime.getRuntime.addShutdownHook? In
most cases, you should use
+ ShutdownHookManager.addShutdownHook instead.
+ If you must use Runtime.getRuntime.addShutdownHook, wrap the code block
with
+ // scalastyle:off runtimeaddshutdownhook
+ Runtime.getRuntime.addShutdownHook(...)
+ // scalastyle:on runtimeaddshutdownhook
+ ]]></customMessage>
+ </check>
+
+ <check customId="mutablesynchronizedbuffer" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">mutable\.SynchronizedBuffer</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use mutable.SynchronizedBuffer? In most
cases, you should use
+ java.util.concurrent.ConcurrentLinkedQueue instead.
+ If you must use mutable.SynchronizedBuffer, wrap the code block with
+ // scalastyle:off mutablesynchronizedbuffer
+ mutable.SynchronizedBuffer[...]
+ // scalastyle:on mutablesynchronizedbuffer
+ ]]></customMessage>
+ </check>
+
+ <check customId="classforname" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">Class\.forName</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use Class.forName? In most cases, you
should use Utils.classForName instead.
+ If you must use Class.forName, wrap the code block with
+ // scalastyle:off classforname
+ Class.forName(...)
+ // scalastyle:on classforname
+ ]]></customMessage>
+ </check>
+
+ <check customId="awaitresult" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">Await\.result</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use Await.result? In most cases, you
should use ThreadUtils.awaitResult instead.
+ If you must use Await.result, wrap the code block with
+ // scalastyle:off awaitresult
+ Await.result(...)
+ // scalastyle:on awaitresult
+ ]]></customMessage>
+ </check>
+
+ <check customId="awaitready" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">Await\.ready</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use Await.ready? In most cases, you should
use ThreadUtils.awaitReady instead.
+ If you must use Await.ready, wrap the code block with
+ // scalastyle:off awaitready
+ Await.ready(...)
+ // scalastyle:on awaitready
+ ]]></customMessage>
+ </check>
+
+ <check customId="parvector" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">new.*ParVector</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure you want to create a ParVector? It will not automatically
propagate Spark ThreadLocals or the
+ active SparkSession for the submitted tasks. In most cases, you should
use ThreadUtils.parmap instead.
+ If you must use ParVector, then wrap your creation of the ParVector with
+ // scalastyle:off parvector
+ ...ParVector...
+ // scalastyle:on parvector
+ ]]></customMessage>
+ </check>
+
+ <check customId="caselocale" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">(\.toUpperCase|\.toLowerCase)(?!(\(|\(Locale.ROOT\)))</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use toUpperCase or toLowerCase without the
root locale? In most cases, you
+ should use toUpperCase(Locale.ROOT) or toLowerCase(Locale.ROOT) instead.
+ If you must use toUpperCase or toLowerCase without the root locale, wrap
the code block with
+ // scalastyle:off caselocale
+ .toUpperCase
+ .toLowerCase
+ // scalastyle:on caselocale
+ ]]></customMessage>
+ </check>
+
+ <check customId="throwerror" level="error"
class="org.scalastyle.file.RegexChecker" enabled="false">
+ <parameters><parameter name="regex">throw new
\w+Error\(</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to throw Error? In most cases, you should use
appropriate Exception instead.
+ If you must throw Error, wrap the code block with
+ // scalastyle:off throwerror
+ throw new XXXError(...)
+ // scalastyle:on throwerror
+ ]]></customMessage>
+ </check>
+
+ <!-- As of SPARK-45338 JavaConversions should be replaced with
CollectionConverters -->
+ <check customId="javaconversions" level="error"
class="org.scalastyle.scalariform.TokenChecker" enabled="false">
+ <parameters><parameter
name="regex">JavaConversions</parameter></parameters>
+ <customMessage>Instead of importing implicits in
scala.collection.JavaConversions._, import
+ scala.jdk.CollectionConverters._ and use .asScala / .asJava
methods</customMessage>
+ </check>
+
+ <!-- As of SPARK-45338 JavaConverters should be replaced with
CollectionConverters -->
+ <check customId="javaconverters" level="error"
class="org.scalastyle.scalariform.TokenChecker" enabled="false">
+ <parameters><parameter name="regex">JavaConverters</parameter></parameters>
+ <customMessage>Instead of importing implicits in
scala.collection.JavaConverters._, import
+ scala.jdk.CollectionConverters._ and use .asScala / .asJava
methods</customMessage>
+ </check>
+
+ <check customId="createParentDirs" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.createParentDirs\b</parameter></parameters>
+ <customMessage>Use createParentDirs of SparkFileUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="filesequal" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.equal\b</parameter></parameters>
+ <customMessage>Use contentEquals of SparkFileUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="toByteArray" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.toByteArray\b</parameter></parameters>
+ <customMessage>Use java.nio.file.Files.readAllBytes
instead.</customMessage>
+ </check>
+
+ <check customId="asByteSource" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.asByteSource\b</parameter></parameters>
+ <customMessage>Use java.nio.file.Files.newInputStream
instead.</customMessage>
+ </check>
+
+ <check customId="getTempDirectory" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.getTempDirectory\b</parameter></parameters>
+ <customMessage>Use System.getProperty instead.</customMessage>
+ </check>
+
+ <check customId="readLines" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.readLines\b</parameter></parameters>
+ <customMessage>Use Files.readAllLines instead.</customMessage>
+ </check>
+
+ <check customId="filesreadLines" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.readLines\b</parameter></parameters>
+ <customMessage>Use Files.readAllLines instead.</customMessage>
+ </check>
+
+ <check customId="readFileToString" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.readFileToString\b</parameter></parameters>
+ <customMessage>Use Files.readString instead.</customMessage>
+ </check>
+
+ <check customId="asCharSource" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.asCharSource\b</parameter></parameters>
+ <customMessage>Use Files.readString instead.</customMessage>
+ </check>
+
+ <check customId="write" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.write\b</parameter></parameters>
+ <customMessage>Use Files.writeString instead.</customMessage>
+ </check>
+
+ <check customId="asCharSink" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.asCharSink\b</parameter></parameters>
+ <customMessage>Use Files.writeString instead.</customMessage>
+ </check>
+
+ <check customId="writeLines" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.writeLines\b</parameter></parameters>
+ <customMessage>Use Files.write instead.</customMessage>
+ </check>
+
+ <check customId="cleanDirectory" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.cleanDirectory\b</parameter></parameters>
+ <customMessage>Use cleanDirectory of
JavaUtils/SparkFileUtils/Utils</customMessage>
+ </check>
+
+ <check customId="deleteRecursively" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.deleteDirectory\b</parameter></parameters>
+ <customMessage>Use deleteRecursively of
JavaUtils/SparkFileUtils/Utils</customMessage>
+ </check>
+
+ <check customId="forceDelete" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.forceDelete\b</parameter></parameters>
+ <customMessage>Use deleteRecursively of
JavaUtils/SparkFileUtils/Utils</customMessage>
+ </check>
+
+ <check customId="forceDeleteOnExit" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.forceDeleteOnExit\b</parameter></parameters>
+ <customMessage>Use forceDeleteOnExit of JavaUtils/SparkFileUtils/Utils
instead.</customMessage>
+ </check>
+
+ <check customId="deleteQuietly" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.deleteQuietly\b</parameter></parameters>
+ <customMessage>Use deleteQuietly of
JavaUtils/SparkFileUtils/Utils</customMessage>
+ </check>
+
+ <check customId="readFileToByteArray" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.readFileToByteArray\b</parameter></parameters>
+ <customMessage>Use java.nio.file.Files.readAllBytes</customMessage>
+ </check>
+
+ <check customId="sizeOf" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.sizeOf(Directory)?\b</parameter></parameters>
+ <customMessage>Use sizeOf of JavaUtils or Utils instead.</customMessage>
+ </check>
+
+ <check customId="moveFile" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.moveFile\b</parameter></parameters>
+ <customMessage>Use copyFile of JavaUtils/SparkFileUtils/Utils
instead.</customMessage>
+ </check>
+
+ <check customId="copyURLToFile" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.copyURLToFile\b</parameter></parameters>
+ <customMessage>Use copyURLToFile of JavaUtils instead.</customMessage>
+ </check>
+
+ <check customId="copyFile" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.copyFile\b</parameter></parameters>
+ <customMessage>Use copyFile of SparkFileUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="copyFileToDirectory" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.copyFileToDirectory\b</parameter></parameters>
+ <customMessage>Use copyFileToDirectory of SparkFileUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="copyDirectory" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.copyDirectory\b</parameter></parameters>
+ <customMessage>Use copyDirectory of JavaUtils/SparkFileUtils/Utils
instead.</customMessage>
+ </check>
+
+ <check customId="moveDirectory" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.moveDirectory\b</parameter></parameters>
+ <customMessage>Use copyDirectory of SparkFileUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="contentEquals" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.contentEquals\b</parameter></parameters>
+ <customMessage>Use contentEquals of SparkFileUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="commonslang2" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.lang\.</parameter></parameters>
+ <customMessage>Use Commons Lang 3 classes (package
org.apache.commons.lang3.*) instead
+ of Commons Lang 2 (package org.apache.commons.lang.*)</customMessage>
+ </check>
+
+ <check customId="getFile" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.getFile\b</parameter></parameters>
+ <customMessage>Use getFile of SparkFileUtil or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="touch" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.touch\b</parameter></parameters>
+ <customMessage>Use touch of SparkFileUtil or Utils instead.</customMessage>
+ </check>
+
+ <check customId="filestouch" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFiles\.touch\b</parameter></parameters>
+ <customMessage>Use touch of SparkFileUtil or Utils instead.</customMessage>
+ </check>
+
+ <check customId="writeStringToFile" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.writeStringToFile\b</parameter></parameters>
+ <customMessage>Use java.nio.file.Files.writeString instead.</customMessage>
+ </check>
+
+ <check customId="listFiles" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileUtils\.listFiles\b</parameter></parameters>
+ <customMessage>Use listFiles of SparkFileUtil or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="commonscodecbase64" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.codec\.binary\.Base64\b</parameter></parameters>
+ <customMessage>Use java.util.Base64 instead</customMessage>
+ </check>
+
+ <check customId="commonslang3javaversion" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.lang3\..*JavaVersion</parameter></parameters>
+ <customMessage>Use JEP 223 API (java.lang.Runtime.Version) instead of
+ Commons Lang 3 JavaVersion
(org.apache.commons.lang3.JavaVersion)</customMessage>
+ </check>
+
+ <check customId="commonslang3tuple" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.lang3\.tuple</parameter></parameters>
+ <customMessage>Use org.apache.spark.util.Pair instead</customMessage>
+ </check>
+
+ <check customId="commonslang3tostringbuilder" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.lang3\.builder\.ToStringBuilder</parameter></parameters>
+ <customMessage>Use String concatenation instead</customMessage>
+ </check>
+
+ <check customId="commonslang3pad" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bStringUtils\.(left|right)Pad\b</parameter></parameters>
+ <customMessage>Use (left|right)Pad of SparkStringUtils or Utils
instead</customMessage>
+ </check>
+
+ <check customId="commonslang3split" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bStringUtils\.split\b</parameter></parameters>
+ <customMessage>Use Utils.stringToSeq instead</customMessage>
+ </check>
+
+ <check customId="commonslang3isblankorempty" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bStringUtils\.is(Not)?(Blank|Empty)\b</parameter></parameters>
+ <customMessage>Use Utils.is(Not)?(Blank|Empty) instead</customMessage>
+ </check>
+
+ <check customId="commonslang3getrootcause" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bExceptionUtils\.getRootCause\b</parameter></parameters>
+ <customMessage>Use getRootCause of SparkErrorUtils or Utils
instead</customMessage>
+ </check>
+
+ <check customId="commonslang3getstacktrace" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bExceptionUtils\.getStackTrace\b</parameter></parameters>
+ <customMessage>Use stackTraceToString of JavaUtils/SparkFileUtils/Utils
instead.</customMessage>
+ </check>
+
+ <check customId="commonslang3strings" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.lang3\.Strings\b</parameter></parameters>
+ <customMessage>Use Java String methods instead</customMessage>
+ </check>
+
+ <check customId="commonslang3strip" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bStringUtils\.strip\b</parameter></parameters>
+ <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>
+ </check>
+
+ <check customId="commonslang3stringutils" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.lang3\.StringUtils\b</parameter></parameters>
+ <customMessage>Use Java String or Spark's Utils/JavaUtils methods
instead</customMessage>
+ </check>
+
+ <check customId="commonslang3systemutils" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.lang3\.SystemUtils\b</parameter></parameters>
+ <customMessage>Use SparkSystemUtils or Utils instead</customMessage>
+ </check>
+
+ <check customId="commonstextstringsubstitutor" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.text\.StringSubstitutor\b</parameter></parameters>
+ <customMessage>Use org.apache.spark.StringSubstitutor
instead</customMessage>
+ </check>
+
+ <check customId="commonslang3abbreviate" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bStringUtils\.abbreviate\b</parameter></parameters>
+ <customMessage>Use Utils.abbreviate method instead</customMessage>
+ </check>
+
+ <check customId="commonslang3substring" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bStringUtils\.substring\b</parameter></parameters>
+ <customMessage>Use Java String.substring instead.</customMessage>
+ </check>
+
+ <check customId="uribuilder" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bUriBuilder\.fromUri\b</parameter></parameters>
+ <customMessage>Use Utils.getUriBuilder instead.</customMessage>
+ </check>
+
+ <check customId="executioncontextglobal" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">scala\.concurrent\.ExecutionContext\.Implicits\.global</parameter></parameters>
+ <customMessage> User queries can use global thread pool, causing
starvation and eventual OOM.
+ Thus, Spark-internal APIs should not use this thread pool</customMessage>
+ </check>
+
+ <check customId="FileSystemGet" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bFileSystem\.get\([a-zA-Z_$][a-zA-Z_$0-9]*\)</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that you want to use "FileSystem.get(Configuration conf)"?
If the input
+ configuration is not set properly, a default FileSystem instance will be
returned. It can
+ lead to errors when you deal with multiple file systems. Please consider
using
+ "FileSystem.get(URI uri, Configuration conf)" or
"Path.getFileSystem(Configuration conf)" instead.
+ If you must use the method "FileSystem.get(Configuration conf)", wrap
the code block with
+ // scalastyle:off FileSystemGet
+ FileSystem.get(...)
+ // scalastyle:on FileSystemGet
+ ]]></customMessage>
+ </check>
+
+ <check customId="extractopt" level="error"
class="org.scalastyle.scalariform.TokenChecker" enabled="true">
+ <parameters><parameter name="regex">extractOpt</parameter></parameters>
+ <customMessage>Use jsonOption(x).map(.extract[T]) instead of
.extractOpt[T], as the latter
+ is slower. </customMessage>
+ </check>
+
+ <check level="error" class="org.scalastyle.scalariform.ImportOrderChecker"
enabled="true">
+ <parameters>
+ <parameter name="groups">java,scala,3rdParty,auron</parameter>
+ <parameter name="group.java">javax?\..*</parameter>
+ <parameter name="group.scala">scala\..*</parameter>
+ <parameter
name="group.3rdParty">(?!(javax?\.|scala\.|org\.apache\.auron\.)).*</parameter>
+ <parameter name="group.auron">org\.apache\.auron\..*</parameter>
+ </parameters>
+ </check>
+
+ <check level="error"
class="org.scalastyle.scalariform.DisallowSpaceBeforeTokenChecker"
enabled="true">
+ <parameters>
+ <parameter name="tokens">COMMA</parameter>
+ </parameters>
+ </check>
+
+ <!-- SPARK-3854: Single Space between ')' and '{' -->
+ <check customId="SingleSpaceBetweenRParenAndLCurlyBrace" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">\)\{</parameter></parameters>
+ <customMessage><![CDATA[
+ Single Space between ')' and `{`.
+ ]]></customMessage>
+ </check>
+
+ <check customId="NoScalaDoc" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">(?m)^(\s*)/[*][*].*$(\r|)\n^\1
[*]</parameter></parameters>
+ <customMessage>Use Javadoc style indentation for multiline
comments</customMessage>
+ </check>
+
+ <check customId="OmitBracesInCase" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">case[^\n>]*=>\s*\{</parameter></parameters>
+ <customMessage>Omit braces in case clauses.</customMessage>
+ </check>
+
+ <check level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">new
(java\.lang\.)?(Byte|Integer|Long|Short)\(</parameter></parameters>
+ <customMessage>Use static factory 'valueOf' or 'parseXXX' instead of the
deprecated constructors.</customMessage>
+ </check>
+
+ <!-- SPARK-16877: Avoid Java annotations -->
+ <check level="error" class="org.scalastyle.scalariform.OverrideJavaChecker"
enabled="true"></check>
+
+ <check level="error"
class="org.scalastyle.scalariform.DeprecatedJavaChecker"
enabled="false"></check>
+
+ <check level="error"
class="org.scalastyle.scalariform.IllegalImportsChecker" enabled="true">
+ <parameters><parameter
name="illegalImports"><![CDATA[collection]]></parameter></parameters>
+ <customMessage>Please use scala.collection instead.</customMessage>
+ </check>
+
+ <check level="error"
class="org.scalastyle.scalariform.IllegalImportsChecker" enabled="true">
+ <parameters><parameter
name="illegalImports"><![CDATA[org.apache.log4j]]></parameter></parameters>
+ <customMessage>Please use Apache Log4j 2 instead.</customMessage>
+ </check>
+
+
+ <!--
================================================================================
-->
+ <!-- rules we'd like to enforce, but haven't cleaned up the codebase
yet -->
+ <!--
================================================================================
-->
+
+ <!-- We cannot turn the following two on, because it'd fail a lot of string
interpolation use cases. -->
+ <!-- Ideally the following two rules should be configurable to rule out
string interpolation. -->
+ <check level="error"
class="org.scalastyle.scalariform.NoWhitespaceBeforeLeftBracketChecker"
enabled="false"></check>
+ <check level="error"
class="org.scalastyle.scalariform.NoWhitespaceAfterLeftBracketChecker"
enabled="false"></check>
+
+ <!-- This breaks symbolic method names so we don't turn it on. -->
+ <!-- Maybe we should update it to allow basic symbolic names, and then we
are good to go. -->
+ <check level="error" class="org.scalastyle.scalariform.MethodNamesChecker"
enabled="false">
+ <parameters>
+ <parameter name="regex"><![CDATA[^[a-z][A-Za-z0-9]*$]]></parameter>
+ </parameters>
+ </check>
+
+ <!-- Should turn this on, but we have a few places that need to be fixed
first -->
+ <check level="error"
class="org.scalastyle.scalariform.EqualsHashCodeChecker" enabled="true"></check>
+
+ <!--
================================================================================
-->
+ <!-- rules we don't want
-->
+ <!--
================================================================================
-->
+
+ <check level="error"
class="org.scalastyle.scalariform.IllegalImportsChecker" enabled="false">
+ <parameters><parameter
name="illegalImports"><![CDATA[sun._,java.awt._]]></parameter></parameters>
+ </check>
+
+ <!-- We want the opposite of this: NewLineAtEofChecker -->
+ <check level="error" class="org.scalastyle.file.NoNewLineAtEofChecker"
enabled="false"></check>
+
+ <!-- This one complains about all kinds of random things. Disable. -->
+ <check level="error"
class="org.scalastyle.scalariform.SimplifyBooleanExpressionChecker"
enabled="false"></check>
+
+ <!-- We use return quite a bit for control flows and guards -->
+ <check level="error" class="org.scalastyle.scalariform.ReturnChecker"
enabled="false"></check>
+
+ <!-- We use null a lot in low level code and to interface with 3rd party
code -->
+ <check level="error" class="org.scalastyle.scalariform.NullChecker"
enabled="false"></check>
+
+ <!-- Doesn't seem super big deal here ... -->
+ <check level="error" class="org.scalastyle.scalariform.NoCloneChecker"
enabled="false"></check>
+
+ <!-- Doesn't seem super big deal here ... -->
+ <check level="error" class="org.scalastyle.file.FileLengthChecker"
enabled="false">
+ <parameters><parameter name="maxFileLength">800></parameter></parameters>
+ </check>
+
+ <!-- Doesn't seem super big deal here ... -->
+ <check level="error" class="org.scalastyle.scalariform.NumberOfTypesChecker"
enabled="false">
+ <parameters><parameter name="maxTypes">30</parameter></parameters>
+ </check>
+
+ <!-- Doesn't seem super big deal here ... -->
+ <check level="error"
class="org.scalastyle.scalariform.CyclomaticComplexityChecker" enabled="false">
+ <parameters><parameter name="maximum">10</parameter></parameters>
+ </check>
+
+ <!-- Doesn't seem super big deal here ... -->
+ <check level="error" class="org.scalastyle.scalariform.MethodLengthChecker"
enabled="false">
+ <parameters><parameter name="maxLength">50</parameter></parameters>
+ </check>
+
+ <!-- Not exactly feasible to enforce this right now. -->
+ <!-- It is also infrequent that somebody introduces a new class with a lot
of methods. -->
+ <check level="error"
class="org.scalastyle.scalariform.NumberOfMethodsInTypeChecker" enabled="false">
+ <parameters><parameter
name="maxMethods"><![CDATA[30]]></parameter></parameters>
+ </check>
+
+ <!-- Doesn't seem super big deal here, and we have a lot of magic numbers
... -->
+ <check level="error" class="org.scalastyle.scalariform.MagicNumberChecker"
enabled="false">
+ <parameters><parameter name="ignore">-1,0,1,2,3</parameter></parameters>
+ </check>
+
+ <check customId="byteCountToDisplaySize" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bbyteCountToDisplaySize\b</parameter></parameters>
+ <customMessage>Use Utils.bytesToString instead of byteCountToDisplaySize
for consistency.</customMessage>
+ </check>
+
+ <check customId="pathfromuri" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">new Path\(new
URI\(</parameter></parameters>
+ <customMessage><![CDATA[
+ Are you sure that this string is uri encoded? Please be careful when
converting hadoop Paths
+ and URIs to and from String. If possible, please use SparkPath.
+ ]]></customMessage>
+ </check>
+
+ <check customId="URLConstructor" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter name="regex">new URL\(</parameter></parameters>
+ <customMessage>Use URI.toURL or URL.of instead of URL
constructors.</customMessage>
+ </check>
+
+ <check customId="configName" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">buildConf\("spark.databricks.</parameter></parameters>
+ <customMessage>Use Apache Spark config namespace.</customMessage>
+ </check>
+
+ <check customId="googleStrings" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">com\.google\.common\.base\.Strings\b</parameter></parameters>
+ <customMessage>Use Java built-in methods or SparkStringUtils
instead</customMessage>
+ </check>
+
+ <check customId="hadoopioutils" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.hadoop\.io\.IOUtils\b</parameter></parameters>
+ <customMessage>Use org.apache.spark.util.Utils instead.</customMessage>
+ </check>
+
+ <check customId="defaultCharset" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">Charset\.defaultCharset</parameter></parameters>
+ <customMessage>Use StandardCharsets.UTF_8 instead.</customMessage>
+ </check>
+
+ <check customId="ioutilstobytearray" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bIOUtils\.toByteArray\b</parameter></parameters>
+ <customMessage>Use Java readAllBytes instead.</customMessage>
+ </check>
+
+ <check customId="ioutilsclosequietly" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bIOUtils\.closeQuietly\b</parameter></parameters>
+ <customMessage>Use closeQuietly of SparkErrorUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="ioutilscopy" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bIOUtils\.copy\b</parameter></parameters>
+ <customMessage>Use Java transferTo instead.</customMessage>
+ </check>
+
+ <check customId="ioutilstostring" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bIOUtils\.toString\b</parameter></parameters>
+ <customMessage>Use toString of SparkStreamUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="charstreamstostring" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bCharStreams\.toString\b</parameter></parameters>
+ <customMessage>Use toString of SparkStreamUtils or Utils
instead.</customMessage>
+ </check>
+
+ <check customId="ioutilswrite" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bIOUtils\.write\b</parameter></parameters>
+ <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>
+ </check>
+
+ <check customId="skipFully" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bByteStreams\.skipFully\b</parameter></parameters>
+ <customMessage>Use Java `skipNBytes` instead.</customMessage>
+ </check>
+
+ <check customId="readFully" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bByteStreams\.readFully\b</parameter></parameters>
+ <customMessage>Use readFully of JavaUtils/SparkStreamUtils/Utils
instead.</customMessage>
+ </check>
+
+ <check customId="nullOutputStream" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bByteStreams\.nullOutputStream\b</parameter></parameters>
+ <customMessage>Use OutputStream.nullOutputStream instead.</customMessage>
+ </check>
+
+ <check customId="ImmutableMapcopyOf" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bImmutableMap\.copyOf\b</parameter></parameters>
+ <customMessage>Use Map.copyOf instead.</customMessage>
+ </check>
+
+ <check customId="ImmutableSetof" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bImmutableSet\.of\b</parameter></parameters>
+ <customMessage>Use java.util.Set.of instead.</customMessage>
+ </check>
+
+ <check customId="emptySet" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bCollections\.emptySet\b</parameter></parameters>
+ <customMessage>Use java.util.Set.of() instead.</customMessage>
+ </check>
+
+ <check customId="maputils" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">org\.apache\.commons\.collections4\.MapUtils\b</parameter></parameters>
+ <customMessage>Use org.apache.spark.util.collection.Utils
instead.</customMessage>
+ </check>
+
+ <check customId="googleFiles" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">com\.google\.common\.io\.Files\b</parameter></parameters>
+ <customMessage>Use Java API or Spark's JavaUtils/SparkFileUtils/Utils
instead.</customMessage>
+ </check>
+
+ <check customId="googleObjects" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">com\.google\.common\.base\.Objects\b</parameter></parameters>
+ <customMessage>Use Java APIs (like java.util.Objects)
instead.</customMessage>
+ </check>
+
+ <check customId="googleJoiner" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">com\.google\.common\.base\.Joiner\b</parameter></parameters>
+ <customMessage>Use Java APIs (like String.join/StringJoiner)
instead.</customMessage>
+ </check>
+
+ <check customId="googleBaseEncoding" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">com\.google\.common\.io\.BaseEncoding\b</parameter></parameters>
+ <customMessage>Use Java APIs (like java.util.Base64)
instead.</customMessage>
+ </check>
+
+ <check customId="googleThrowablesGetStackTraceAsString" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bThrowables\.getStackTraceAsString\b</parameter></parameters>
+ <customMessage>Use stackTraceToString of JavaUtils/SparkFileUtils/Utils
instead.</customMessage>
+ </check>
+
+ <check customId="googleThrowablesGetRootCause" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bThrowables\.getRootCause\b</parameter></parameters>
+ <customMessage>Use getRootCause of SparkErrorUtils or Utils
instead</customMessage>
+ </check>
+
+ <check customId="preconditionschecknotnull" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bPreconditions\.checkNotNull\b</parameter></parameters>
+ <customMessage>Use requireNonNull of java.util.Objects
instead.</customMessage>
+ </check>
+
+ <check customId="intscheckedcast" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bInts\.checkedCast\b</parameter></parameters>
+ <customMessage>Use JavaUtils.checkedCast instead.</customMessage>
+ </check>
+
+ <check customId="startsWithK8s" level="error"
class="org.scalastyle.file.RegexChecker" enabled="true">
+ <parameters><parameter
name="regex">\bstartsWith\("k8s\b</parameter></parameters>
+ <customMessage>Use SparkMasterRegex.isK8s instead.</customMessage>
+ </check>
+</scalastyle>
diff --git a/pom.xml b/pom.xml
index 63ebf187..b02819c5 100644
--- a/pom.xml
+++ b/pom.xml
@@ -60,6 +60,7 @@
<maven.version>3.9.12</maven.version>
<maven.plugin.scala.version>4.9.2</maven.plugin.scala.version>
<maven.plugin.scalatest.version>2.2.0</maven.plugin.scalatest.version>
+ <maven.plugin.scalastyle.version>1.0.0</maven.plugin.scalastyle.version>
<maven.plugin.scalatest.exclude.tags />
<maven.plugin.scalatest.include.tags />
<maven.plugin.scalatest.debug.enabled>false</maven.plugin.scalatest.debug.enabled>
@@ -466,6 +467,32 @@
</executions>
</plugin>
+ <plugin>
+ <groupId>org.scalastyle</groupId>
+ <artifactId>scalastyle-maven-plugin</artifactId>
+ <version>${maven.plugin.scalastyle.version}</version>
+ <configuration>
+ <verbose>false</verbose>
+ <failOnViolation>true</failOnViolation>
+ <includeTestSourceDirectory>false</includeTestSourceDirectory>
+ <failOnWarning>false</failOnWarning>
+ <sourceDirectory>${basedir}/src/main/scala</sourceDirectory>
+ <testSourceDirectory>${basedir}/src/test/scala</testSourceDirectory>
+
<configLocation>${maven.multiModuleProjectDirectory}/dev/scalastyle-config.xml</configLocation>
+ <outputFile>${basedir}/target/scalastyle-output.xml</outputFile>
+ <inputEncoding>${project.build.sourceEncoding}</inputEncoding>
+ <outputEncoding>${project.reporting.outputEncoding}</outputEncoding>
+ </configuration>
+ <executions>
+ <execution>
+ <goals>
+ <goal>check</goal>
+ </goals>
+ <phase>validate</phase>
+ </execution>
+ </executions>
+ </plugin>
+
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>flatten-maven-plugin</artifactId>
diff --git
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeParquetInsertIntoHiveTableExec.scala
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeParquetInsertIntoHiveTableExec.scala
index 4d559b32..e19c86e5 100644
---
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeParquetInsertIntoHiveTableExec.scala
+++
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeParquetInsertIntoHiveTableExec.scala
@@ -104,7 +104,8 @@ case class NativeParquetInsertIntoHiveTableExec(
}
@sparkver("3.2 / 3.3")
- override def basicWriteJobStatsTracker(hadoopConf:
org.apache.hadoop.conf.Configuration) = {
+ override def basicWriteJobStatsTracker(hadoopConf:
org.apache.hadoop.conf.Configuration)
+ : org.apache.spark.sql.execution.datasources.BasicWriteJobStatsTracker
= {
import org.apache.spark.sql.catalyst.InternalRow
import
org.apache.spark.sql.execution.datasources.BasicWriteJobStatsTracker
import
org.apache.spark.sql.execution.datasources.BasicWriteTaskStatsTracker
@@ -138,7 +139,8 @@ case class NativeParquetInsertIntoHiveTableExec(
}
@sparkver("3.1")
- override def basicWriteJobStatsTracker(hadoopConf:
org.apache.hadoop.conf.Configuration) = {
+ override def basicWriteJobStatsTracker(hadoopConf:
org.apache.hadoop.conf.Configuration)
+ : org.apache.spark.sql.execution.datasources.BasicWriteJobStatsTracker
= {
import org.apache.spark.sql.catalyst.InternalRow
import
org.apache.spark.sql.execution.datasources.BasicWriteJobStatsTracker
import org.apache.spark.sql.execution.datasources.BasicWriteTaskStats
@@ -187,7 +189,8 @@ case class NativeParquetInsertIntoHiveTableExec(
}
@sparkver("3.0")
- override def basicWriteJobStatsTracker(hadoopConf:
org.apache.hadoop.conf.Configuration) = {
+ override def basicWriteJobStatsTracker(hadoopConf:
org.apache.hadoop.conf.Configuration)
+ : org.apache.spark.sql.execution.datasources.BasicWriteJobStatsTracker
= {
import org.apache.spark.sql.catalyst.InternalRow
import
org.apache.spark.sql.execution.datasources.BasicWriteJobStatsTracker
import org.apache.spark.sql.execution.datasources.BasicWriteTaskStats
diff --git
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeShuffleExchangeExec.scala
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeShuffleExchangeExec.scala
index 37952b20..9d688ad1 100644
---
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeShuffleExchangeExec.scala
+++
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/auron/plan/NativeShuffleExchangeExec.scala
@@ -17,7 +17,6 @@
package org.apache.spark.sql.execution.auron.plan
import scala.collection.mutable
-import scala.concurrent.ExecutionContext.Implicits.global
import scala.concurrent.Future
import org.apache.spark._
@@ -78,6 +77,9 @@ case class NativeShuffleExchangeExec(
// 'mapOutputStatisticsFuture' is only needed when enable AQE.
@transient override lazy val mapOutputStatisticsFuture:
Future[MapOutputStatistics] = {
+ // scalastyle:off executioncontextglobal
+ import scala.concurrent.ExecutionContext.Implicits.global
+ // scalastyle:on executioncontextglobal
if (inputRDD.getNumPartitions == 0) {
Future.successful(null)
} else {
@@ -173,7 +175,7 @@ case class NativeShuffleExchangeExec(
outputPartitioning != SinglePartition
@sparkver("3.1 / 3.2 / 3.3 / 3.4 / 3.5")
- override def shuffleOrigin = {
+ override def shuffleOrigin:
org.apache.spark.sql.execution.exchange.ShuffleOrigin = {
import org.apache.spark.sql.execution.exchange.ShuffleOrigin;
_shuffleOrigin.get.asInstanceOf[ShuffleOrigin]
}
diff --git
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/joins/auron/plan/NativeBroadcastJoinExec.scala
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/joins/auron/plan/NativeBroadcastJoinExec.scala
index fd51bec3..2f04829c 100644
---
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/joins/auron/plan/NativeBroadcastJoinExec.scala
+++
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/execution/joins/auron/plan/NativeBroadcastJoinExec.scala
@@ -62,7 +62,8 @@ case class NativeBroadcastJoinExec(
}
@sparkver("3.1 / 3.2 / 3.3 / 3.4 / 3.5")
- override def requiredChildDistribution = {
+ override def requiredChildDistribution
+ : List[org.apache.spark.sql.catalyst.plans.physical.Distribution] = {
import org.apache.spark.sql.catalyst.plans.physical.BroadcastDistribution
import org.apache.spark.sql.catalyst.plans.physical.UnspecifiedDistribution
import org.apache.spark.sql.execution.joins.HashedRelationBroadcastMode
@@ -83,7 +84,7 @@ case class NativeBroadcastJoinExec(
override def supportCodegen: Boolean = false
@sparkver("3.1 / 3.2 / 3.3 / 3.4 / 3.5")
- override def inputRDDs() = {
+ override def inputRDDs(): Nothing = {
throw new NotImplementedError("NativeBroadcastJoin dose not support
codegen")
}
diff --git
a/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronArrowColumnVector.scala
b/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronArrowColumnVector.scala
index ca5c12cb..d8be57e6 100644
---
a/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronArrowColumnVector.scala
+++
b/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronArrowColumnVector.scala
@@ -190,7 +190,7 @@ object AuronArrowColumnVector {
private class NullAccessor(vector: NullVector)
extends AuronArrowColumnVector.ArrowVectorAccessor(vector) {
- override def isNullAt(rowId: Int) = true
+ override def isNullAt(rowId: Int): Boolean = true
}
private class BooleanAccessor(vector: BitVector)
@@ -215,7 +215,7 @@ object AuronArrowColumnVector {
private class UInt4Accessor(vector: UInt4Vector)
extends AuronArrowColumnVector.ArrowVectorAccessor(vector) {
- final override def getInt(rowId: Int) = vector.get(rowId)
+ final override def getInt(rowId: Int): Int = vector.get(rowId)
}
private class UInt8Accessor(vector: UInt8Vector)
@@ -260,14 +260,15 @@ object AuronArrowColumnVector {
extends AuronArrowColumnVector.ArrowVectorAccessor(vector) {
final private val stringResult = new NullableVarCharHolder
- final override def getUTF8String(rowId: Int) = {
+ final override def getUTF8String(rowId: Int): UTF8String = {
vector.get(rowId, stringResult)
if (stringResult.isSet == 0) null
- else
+ else {
UTF8String.fromAddress(
null,
stringResult.buffer.memoryAddress + stringResult.start,
stringResult.end - stringResult.start)
+ }
}
}
diff --git
a/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronColumnarMap.scala
b/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronColumnarMap.scala
index 2fed6bf1..fc506abd 100644
---
a/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronColumnarMap.scala
+++
b/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/columnar/AuronColumnarMap.scala
@@ -33,5 +33,5 @@ class AuronColumnarMap(
override def valueArray: ArrayData = new AuronColumnarArray(values, offset,
length)
- override def copy = new ArrayBasedMapData(keyArray.copy, valueArray.copy)
+ override def copy: ArrayBasedMapData = new ArrayBasedMapData(keyArray.copy,
valueArray.copy)
}
diff --git
a/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/AuronBlockStoreShuffleReaderBase.scala
b/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/AuronBlockStoreShuffleReaderBase.scala
index b64ad045..477c1b5e 100644
---
a/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/AuronBlockStoreShuffleReaderBase.scala
+++
b/spark-extension/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/AuronBlockStoreShuffleReaderBase.scala
@@ -90,8 +90,10 @@ object AuronBlockStoreShuffleReaderBase extends Logging {
}
private def unwrapInputStream(in: InputStream): InputStream = {
+ // scalastyle:off classforname
val bufferReleasingInputStreamCls =
Class.forName("org.apache.spark.storage.BufferReleasingInputStream")
+ // scalastyle:on classforname
if (in.getClass != bufferReleasingInputStreamCls) {
return in
}
diff --git
a/thirdparty/auron-uniffle/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/uniffle/AuronUniffleShuffleReader.scala
b/thirdparty/auron-uniffle/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/uniffle/AuronUniffleShuffleReader.scala
index 9a786b90..18745f5c 100644
---
a/thirdparty/auron-uniffle/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/uniffle/AuronUniffleShuffleReader.scala
+++
b/thirdparty/auron-uniffle/src/main/scala/org/apache/spark/sql/execution/auron/shuffle/uniffle/AuronUniffleShuffleReader.scala
@@ -250,8 +250,9 @@ class AuronUniffleShuffleReader[K, C](
var readBytes = 0
while (readBytes < len) {
while (byteBuffer == null || !byteBuffer.hasRemaining()) {
- if (!this.toNextBuffer)
+ if (!this.toNextBuffer) {
return if (readBytes > 0) readBytes else -1
+ }
}
val bytesToRead = Math.min(byteBuffer.remaining(), len - readBytes)
byteBuffer.get(arrayBytes, off + readBytes, bytesToRead)
