Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[jvm-packages] update scala style configuration (#10836)

Browse Source
This commit is contained in:
Bobby Wang 2024-09-24 17:39:44 +08:00 committed by GitHub
parent 2a03685bff
commit f3df0d0eb4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
8 changed files with 112 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

119
jvm-packages/scalastyle-config.xml
View File

@ -82,19 +82,27 @@ This file is divided into 3 sections:
</check>
<check level="error" class="org.scalastyle.scalariform.ClassNamesChecker" enabled="true">
<parameters><parameter name="regex"><![CDATA[[A-Z][A-Za-z]*]]></parameter></parameters>
<parameters>
<parameter name="regex"><![CDATA[[A-Z][A-Za-z]*]]></parameter>
</parameters>
</check>
<check level="error" class="org.scalastyle.scalariform.ObjectNamesChecker" enabled="true">
<parameters><parameter name="regex"><![CDATA[[A-Z][A-Za-z]*]]></parameter></parameters>
<parameters>
<parameter name="regex"><![CDATA[[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]*$]]></parameter></parameters>
<parameters>
<parameter name="regex"><![CDATA[^[a-z][A-Za-z]*$]]></parameter>
</parameters>
</check>
<check level="error" class="org.scalastyle.scalariform.ParameterNumberChecker" enabled="true">
<parameters><parameter name="maxParameters"><![CDATA[10]]></parameter></parameters>
<parameters>
<parameter name="maxParameters"><![CDATA[10]]></parameter>
</parameters>
</check>
<check level="error" class="org.scalastyle.scalariform.NoFinalizeChecker" enabled="false"></check>
@ -121,14 +129,16 @@ This file is divided into 3 sections:
<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>
<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>
<parameter name="tokens">ARROW, EQUALS, COMMA, COLON, IF, ELSE, DO, WHILE, FOR, MATCH, TRY, CATCH, FINALLY,
LARROW, RARROW
</parameter>
</parameters>
</check>
@ -136,14 +146,18 @@ This file is divided into 3 sections:
<check level="error" class="org.scalastyle.scalariform.NotImplementedErrorUsage" enabled="true"></check>
<check customId="visiblefortesting" level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter name="regex">@VisibleForTesting</parameter></parameters>
<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>
<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.
@ -155,7 +169,9 @@ This file is divided into 3 sections:
</check>
<check customId="mutablesynchronizedbuffer" level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter name="regex">mutable\.SynchronizedBuffer</parameter></parameters>
<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.
@ -167,7 +183,9 @@ This file is divided into 3 sections:
</check>
<check customId="classforname" level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters><parameter name="regex">Class\.forName</parameter></parameters>
<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
@ -179,17 +197,20 @@ This file is divided into 3 sections:
<!-- As of SPARK-9613 JavaConversions should be replaced with JavaConverters -->
<check customId="javaconversions" level="error" class="org.scalastyle.scalariform.TokenChecker" enabled="true">
<parameters><parameter name="regex">JavaConversions</parameter></parameters>
<parameters>
<parameter name="regex">JavaConversions</parameter>
</parameters>
<customMessage>Instead of importing implicits in scala.collection.JavaConversions._, import
scala.collection.JavaConverters._ and use .asScala / .asJava methods</customMessage>
scala.collection.JavaConverters._ and use .asScala / .asJava methods
</customMessage>
</check>
<check level="error" class="org.scalastyle.scalariform.ImportOrderChecker" enabled="true">
<parameters>
<parameter name="groups">java,scala,3rdParty,spark</parameter>
<parameter name="groups">java,scala,3rdParty,dmlc</parameter>
<parameter name="group.java">javax?\..*</parameter>
<parameter name="group.scala">scala\..*</parameter>
<parameter name="group.3rdParty">(?!ml\.dmlc\.xgboost4j\.).*</parameter>
<parameter name="group.3rdParty">(?!ml\.dmlc\.xgboost4j).*</parameter>
<parameter name="group.dmlc">ml.dmlc.xgboost4j.*</parameter>
</parameters>
</check>
@ -213,7 +234,7 @@ This file is divided into 3 sections:
<!-- 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]*$]]></parameter>
<parameter name="regex"><![CDATA[^[a-z][A-Za-z0-9]*$]]></parameter>
</parameters>
</check>
@ -225,7 +246,9 @@ This file is divided into 3 sections:
<!-- ================================================================================ -->
<check level="error" class="org.scalastyle.scalariform.IllegalImportsChecker" enabled="false">
<parameters><parameter name="illegalImports"><![CDATA[sun._,java.awt._]]></parameter></parameters>
<parameters>
<parameter name="illegalImports"><![CDATA[sun._,java.awt._]]></parameter>
</parameters>
</check>
<!-- We want the opposite of this: NewLineAtEofChecker -->
@ -245,33 +268,81 @@ This file is divided into 3 sections:
<!-- Doesn't seem super big deal here ... -->
<check level="error" class="org.scalastyle.file.FileLengthChecker" enabled="false">
<parameters><parameter name="maxFileLength">800></parameter></parameters>
<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>
<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>
<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>
<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>
<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>
<parameters>
<parameter name="ignore">-1,0,1,2,3</parameter>
</parameters>
</check>
<check level="error" class="org.scalastyle.scalariform.IllegalImportsChecker" enabled="true">
<parameters>
<parameter name="illegalImports"><![CDATA[scala.collection.Seq,scala.collection.IndexedSeq]]></parameter>
</parameters>
<customMessage><![CDATA[
Don't import scala.collection.Seq and scala.collection.IndexedSeq as it may cause issues with cross-build between Scala 2.12 and 2.13.
Please refer below page to see the details of changes around Seq / IndexedSeq.
https://docs.scala-lang.org/overviews/core/collections-migration-213.html
If you really need to use scala.collection.Seq or scala.collection.IndexedSeq, please use the fully-qualified name instead.
]]></customMessage>
</check>
<check level="error" class="org.scalastyle.scalariform.ProcedureDeclarationChecker" enabled="true">
<customMessage>procedure syntax is deprecated in Scala 2.13: add return type `: Unit` and `=`</customMessage>
</check>
<check level="error" class="org.scalastyle.file.RegexChecker" enabled="true">
<parameters>
<parameter name="regex">ArrayBuilder.make\[(.+)\]\(\)</parameter>
<parameter name="line">false</parameter>
</parameters>
<customMessage>ArrayBuilder.make does not accept parens anymore in Scala 2.13</customMessage>
</check>
<check level="warning" class="org.scalastyle.file.RegexChecker" enabled="false">
<parameters>
<parameter name="regex">(: |\[)(Indexed)?Seq\[[A-Za-z0-9_]+\]</parameter>
<parameter name="line">false</parameter>
</parameters>
<customMessage><![CDATA[NOTE: Scala 2.12 defaults scala.(Indexed)Seq to scala.collection.(Indexed)Seq while Scala 2.13 defaults
scala.(Indexed)Seq to scala.collection.immutable.(Indexed)Seq
Please refer below page to see the details of changes around Seq / IndexedSeq.
https://docs.scala-lang.org/overviews/core/collections-migration-213.html
]]></customMessage>
</check>
</scalastyle>

4
jvm-packages/xgboost4j-spark-gpu/src/main/scala/ml/dmlc/xgboost4j/scala/QuantileDMatrix.scala
View File

@ -16,10 +16,10 @@
package ml.dmlc.xgboost4j.scala
import ml.dmlc.xgboost4j.java.{Column, ColumnBatch, XGBoostError, QuantileDMatrix => JQuantileDMatrix}
import scala.collection.JavaConverters._
import ml.dmlc.xgboost4j.java.{Column, ColumnBatch, QuantileDMatrix => JQuantileDMatrix, XGBoostError}
class QuantileDMatrix private[scala](
private[scala] override val jDMatrix: JQuantileDMatrix) extends DMatrix(jDMatrix) {

1
jvm-packages/xgboost4j-spark-gpu/src/test/resources/log4j.properties Normal file
View File

@ -0,0 +1 @@
log4j.logger.org.apache.spark=INFO

3
jvm-packages/xgboost4j-spark-gpu/src/test/scala/ml/dmlc/xgboost4j/scala/spark/GpuTestSuite.scala
View File

@ -17,13 +17,12 @@
package ml.dmlc.xgboost4j.scala.rapids.spark
import java.nio.file.{Files, Path}
import java.sql.{Date, Timestamp}
import java.util.{Locale, TimeZone}
import org.apache.spark.{GpuTestUtils, SparkConf}
import org.apache.spark.internal.Logging
import org.apache.spark.network.util.JavaUtils
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.SparkSession
import org.scalatest.BeforeAndAfterAll
import org.scalatest.funsuite.AnyFunSuite

14
jvm-packages/xgboost4j-spark-gpu/src/test/scala/ml/dmlc/xgboost4j/scala/spark/GpuXGBoostPluginSuite.scala
View File

@ -16,18 +16,20 @@
package ml.dmlc.xgboost4j.scala.spark
import java.io.File
import scala.collection.mutable.ArrayBuffer
import ai.rapids.cudf.{OrderByArg, Table}
import org.apache.spark.SparkConf
import org.apache.spark.ml.linalg.DenseVector
import org.apache.spark.sql.{Dataset, Row, SparkSession}
import ml.dmlc.xgboost4j.java.CudfColumnBatch
import ml.dmlc.xgboost4j.scala.{DMatrix, QuantileDMatrix, XGBoost => ScalaXGBoost}
import ml.dmlc.xgboost4j.scala.rapids.spark.GpuTestSuite
import ml.dmlc.xgboost4j.scala.rapids.spark.SparkSessionHolder.withSparkSession
import ml.dmlc.xgboost4j.scala.spark.Utils.withResource
import org.apache.spark.ml.linalg.DenseVector
import org.apache.spark.sql.{Dataset, Row, SparkSession}
import org.apache.spark.SparkConf
import java.io.File
import scala.collection.mutable.ArrayBuffer
class GpuXGBoostPluginSuite extends GpuTestSuite {

3
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostRanker.scala
View File

@ -22,11 +22,12 @@ import org.apache.spark.ml.param.ParamMap
import org.apache.spark.ml.util.{DefaultParamsReadable, Identifiable, MLReadable, MLReader}
import org.apache.spark.ml.xgboost.SparkUtils
import org.apache.spark.sql.Dataset
import org.apache.spark.sql.types.{DataType, DoubleType, StructType}
import ml.dmlc.xgboost4j.scala.Booster
import ml.dmlc.xgboost4j.scala.spark.XGBoostRanker._uid
import ml.dmlc.xgboost4j.scala.spark.params.HasGroupCol
import ml.dmlc.xgboost4j.scala.spark.params.LearningTaskParams.RANKER_OBJS
import org.apache.spark.sql.types.{DataType, DoubleType, StructType}
class XGBoostRanker(override val uid: String,
private val xgboostParams: Map[String, Any])

2
jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostRegressor.scala
View File

@ -22,11 +22,11 @@ import org.apache.spark.ml.param.ParamMap
import org.apache.spark.ml.util.{DefaultParamsReadable, Identifiable, MLReadable, MLReader}
import org.apache.spark.ml.xgboost.SparkUtils
import org.apache.spark.sql.Dataset
import org.apache.spark.sql.types.{DataType, DoubleType, StructType}
import ml.dmlc.xgboost4j.scala.Booster
import ml.dmlc.xgboost4j.scala.spark.XGBoostRegressor._uid
import ml.dmlc.xgboost4j.scala.spark.params.LearningTaskParams.REGRESSION_OBJS
import org.apache.spark.sql.types.{DataType, DoubleType, StructType}
class XGBoostRegressor(override val uid: String,
private val xgboostParams: Map[String, Any])

3
jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostEstimatorSuite.scala
View File

@ -18,10 +18,11 @@ package ml.dmlc.xgboost4j.scala.spark
import java.io.File
import java.util.Arrays
import scala.collection.mutable.ArrayBuffer
import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vectors}
import org.apache.spark.SparkException
import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vectors}
import org.json4s.{DefaultFormats, Formats}
import org.json4s.jackson.parseJson
import org.scalatest.funsuite.AnyFunSuite