project/MimaExcludes.scala

/*
 * 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.
 */

import com.typesafe.tools.mima.core.*

/**
 * Additional excludes for checking of Spark's binary compatibility.
 *
 * This acts as an official audit of cases where we excluded other classes. Please use the narrowest
 * possible exclude here. MIMA will usually tell you what exclude to use, e.g.:
 *
 * ProblemFilters.exclude[MissingMethodProblem]("org.apache.spark.rdd.RDD.take")
 *
 * It is also possible to exclude Spark classes and packages. This should be used sparingly:
 *
 * MimaBuild.excludeSparkClass("graphx.util.collection.GraphXPrimitiveKeyOpenHashMap")
 *
 * For a new Spark version, please update MimaBuild.scala to reflect the previous version.
 */
object MimaExcludes {

  // Exclude rules for 4.1.x from 4.0.0
  lazy val v41excludes = defaultExcludes ++ Seq(
    // [SPARK-51261][ML][CONNECT] Introduce model size estimation to control ml cache
    ProblemFilters.exclude[ReversedMissingMethodProblem]("org.apache.spark.ml.linalg.Vector.getSizeInBytes"),

    // [SPARK-52221][SQL] Refactor SqlScriptingLocalVariableManager into more generic context manager
    ProblemFilters.exclude[DirectMissingMethodProblem]("org.apache.spark.sql.scripting.SqlScriptingExecution.withLocalVariableManager"),

    // [SPARK-53391][CORE] Remove unused PrimitiveKeyOpenHashMap
    ProblemFilters.exclude[MissingClassProblem]("org.apache.spark.util.collection.PrimitiveKeyOpenHashMap*"),

    // [SPARK-54041][SQL] Enable Direct Passthrough Partitioning in the DataFrame API
    ProblemFilters.exclude[ReversedMissingMethodProblem]("org.apache.spark.sql.Dataset.repartitionById")
  )

  // Default exclude rules
  lazy val defaultExcludes = Seq(
    // Spark Internals
    ProblemFilters.exclude[Problem]("org.apache.spark.rpc.*"),
    ProblemFilters.exclude[Problem]("org.spark-project.jetty.*"),
    ProblemFilters.exclude[Problem]("org.spark_project.jetty.*"),
    ProblemFilters.exclude[Problem]("org.sparkproject.jetty.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.internal.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.kafka010.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.unused.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.unsafe.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.memory.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.util.collection.unsafe.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.catalyst.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.execution.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.internal.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.errors.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.classic.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.connect.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.scripting.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.types.variant.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.ui.flamegraph.*"),
    // DSv2 catalog and expression APIs are unstable yet. We should enable this back.
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.connector.catalog.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.connector.expressions.*"),
    // Avro source implementation is internal.
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.v2.avro.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.avro.*"),


    // SPARK-43169: shaded and generated protobuf code
    ProblemFilters.exclude[Problem]("org.sparkproject.spark_core.protobuf.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.status.protobuf.StoreTypes*"),

    // SPARK-44104: shaded protobuf code and Apis with parameters relocated
    ProblemFilters.exclude[Problem]("org.sparkproject.spark_protobuf.protobuf.*"),
    ProblemFilters.exclude[Problem]("org.apache.spark.sql.protobuf.utils.SchemaConverters.*"),

    // SPARK-51267: Match local Spark Connect server logic between Python and Scala
    ProblemFilters.exclude[MissingFieldProblem]("org.apache.spark.launcher.SparkLauncher.SPARK_LOCAL_REMOTE"),

    // SPARK-53138: Split common/utils Java code into a new module common/utils-java
    ProblemFilters.exclude[MissingClassProblem]("org.apache.spark.QueryContext"),
    ProblemFilters.exclude[MissingClassProblem]("org.apache.spark.QueryContextType"),
    ProblemFilters.exclude[MissingClassProblem]("org.apache.spark.api.java.function.*"),
    ProblemFilters.exclude[MissingClassProblem]("org.apache.spark.network.util.ByteUnit"),
    ProblemFilters.exclude[MissingClassProblem]("org.apache.spark.network.util.JavaUtils"),

    (problem: Problem) => problem match {
      case MissingClassProblem(cls) => !cls.fullName.startsWith("org.sparkproject.jpmml") &&
          !cls.fullName.startsWith("org.sparkproject.dmg.pmml")
      case _ => true
    }
  )

  def excludes(version: String): Seq[Problem => Boolean] = version match {
    case v if v.startsWith("4.1") => v41excludes
    case _ => Seq()
  }
}