/*
 * 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 groovy.json.JsonOutput

plugins { id 'org.apache.beam.module' }
applyJavaNature(
  automaticModuleName: 'org.apache.beam.runners.spark',
  enableChecker: false,
  ignoreRawtypeErrors: true)

description = "Apache Beam :: Runners :: Spark"

/*
 * We need to rely on manually specifying these evaluationDependsOn to ensure that
 * the following projects are evaluated before we evaluate this project. This is because
 * we are attempting to reference the "sourceSets.test.output" directly.
 */
evaluationDependsOn(":sdks:java:core")
evaluationDependsOn(":sdks:java:io:hadoop-format")
evaluationDependsOn(":runners:core-java")

configurations {
  validatesRunner
}

test {
  systemProperty "beam.spark.test.reuseSparkContext", "true"
  systemProperty "spark.sql.shuffle.partitions", "4"
  systemProperty "spark.ui.enabled", "false"
  systemProperty "spark.ui.showConsoleProgress", "false"
  systemProperty "beamTestPipelineOptions", """[
                    "--runner=TestSparkRunner",
                    "--streaming=false",
                    "--enableSparkMetricSinks=true"
                  ]"""
  // Only one SparkContext may be running in a JVM (SPARK-2243)
  forkEvery 1
  maxParallelForks 4
  useJUnit {
    excludeCategories "org.apache.beam.runners.spark.StreamingTest"
    excludeCategories "org.apache.beam.runners.spark.UsesCheckpointRecovery"
  }
}

dependencies {
  compile project(path: ":model:pipeline", configuration: "shadow")
  compile project(path: ":sdks:java:core", configuration: "shadow")
  compile project(":runners:core-construction-java")
  compile project(":runners:core-java")
  compile project(":runners:java-fn-execution")
  compile project(":runners:java-job-service")
  compile project(":sdks:java:extensions:google-cloud-platform-core")
  compile library.java.jackson_annotations
  compile library.java.slf4j_api
  compile library.java.joda_time
  compile library.java.args4j
  provided library.java.spark_core
  provided library.java.spark_sql
  provided library.java.spark_streaming
  provided library.java.spark_network_common
  provided library.java.hadoop_common
  provided library.java.commons_io
  provided library.java.hamcrest_core
  provided library.java.hamcrest_library
  provided "com.esotericsoftware.kryo:kryo:2.21"
  runtimeOnly library.java.jackson_module_scala
  runtimeOnly "org.scala-lang:scala-library:2.11.8"
  testCompile project(":sdks:java:io:kafka")
  testCompile project(path: ":sdks:java:core", configuration: "shadowTest")
  // SparkStateInternalsTest extends abstract StateInternalsTest
  testCompile project(path: ":runners:core-java", configuration: "testRuntime")
  testCompile project(":sdks:java:harness")
  testCompile library.java.avro
  testCompile library.java.kafka
  testCompile library.java.kafka_clients
  testCompile library.java.junit
  testCompile library.java.mockito_core
  testCompile library.java.jackson_dataformat_yaml
  testCompile "org.apache.zookeeper:zookeeper:3.4.11"
  validatesRunner project(path: ":sdks:java:core", configuration: "shadowTest")
  validatesRunner project(path: ":runners:core-java", configuration: "testRuntime")
  validatesRunner project(":sdks:java:io:hadoop-format")
  validatesRunner project(":sdks:java:io:hadoop-format").sourceSets.test.output
  validatesRunner project(path: ":examples:java", configuration: "testRuntime")
  validatesRunner project(path: project.path, configuration: "testRuntime")
  validatesRunner project(project.path)
  validatesRunner project(path: project.path, configuration: "provided")
}

configurations.testRuntimeClasspath {
  // Testing the Spark runner causes a StackOverflowError if slf4j-jdk14 is on the classpath
  exclude group: "org.slf4j", module: "slf4j-jdk14"
}

configurations.validatesRunner {
  // Testing the Spark runner causes a StackOverflowError if slf4j-jdk14 is on the classpath
  exclude group: "org.slf4j", module: "slf4j-jdk14"
}

task validatesRunnerBatch(type: Test) {
  group = "Verification"
  def pipelineOptions = JsonOutput.toJson([
          "--runner=TestSparkRunner",
          "--streaming=false",
          "--enableSparkMetricSinks=false",
  ])
  systemProperty "beamTestPipelineOptions", pipelineOptions
  systemProperty "beam.spark.test.reuseSparkContext", "true"
  systemProperty "spark.ui.enabled", "false"
  systemProperty "spark.ui.showConsoleProgress", "false"

  classpath = configurations.validatesRunner
  testClassesDirs = files(
            project(":sdks:java:core").sourceSets.test.output.classesDirs,
            project(":runners:core-java").sourceSets.test.output.classesDirs,
        )
  testClassesDirs += files(project.sourceSets.test.output.classesDirs)


          // Only one SparkContext may be running in a JVM (SPARK-2243)
  forkEvery 1
  maxParallelForks 4
  useJUnit {
    includeCategories 'org.apache.beam.sdk.testing.ValidatesRunner'
    includeCategories 'org.apache.beam.runners.spark.UsesCheckpointRecovery'
    excludeCategories 'org.apache.beam.sdk.testing.UsesCustomWindowMerging'
    excludeCategories 'org.apache.beam.sdk.testing.UsesTimerMap'
    excludeCategories 'org.apache.beam.sdk.testing.UsesKeyInParDo'
    excludeCategories 'org.apache.beam.sdk.testing.UsesOnWindowExpiration'
    excludeCategories 'org.apache.beam.sdk.testing.UsesStrictTimerOrdering'
    // Unbounded
    excludeCategories 'org.apache.beam.sdk.testing.UsesUnboundedPCollections'
    excludeCategories 'org.apache.beam.sdk.testing.UsesTestStream'
    // Metrics
    excludeCategories 'org.apache.beam.sdk.testing.UsesCommittedMetrics'
    excludeCategories 'org.apache.beam.sdk.testing.UsesSystemMetrics'
    // SDF
    excludeCategories 'org.apache.beam.sdk.testing.UsesUnboundedSplittableParDo'
    // Portability
    excludeCategories 'org.apache.beam.sdk.testing.UsesImpulse'
    excludeCategories 'org.apache.beam.sdk.testing.UsesCrossLanguageTransforms'
    excludeCategories 'org.apache.beam.sdk.testing.UsesBundleFinalizer'
  }
  jvmArgs '-Xmx3g'
}

task validatesRunnerStreaming(type: Test) {
  group = "Verification"
  def pipelineOptions = JsonOutput.toJson([
          "--runner=TestSparkRunner",
          "--forceStreaming=true",
          "--enableSparkMetricSinks=true",
  ])
  systemProperty "beamTestPipelineOptions", pipelineOptions

  classpath = configurations.validatesRunner
  testClassesDirs += files(project.sourceSets.test.output.classesDirs)

  // Only one SparkContext may be running in a JVM (SPARK-2243)
  forkEvery 1
  maxParallelForks 4
  useJUnit {
    includeCategories 'org.apache.beam.runners.spark.StreamingTest'
  }
}

task validatesStructuredStreamingRunnerBatch(type: Test) {
  group = "Verification"
  def pipelineOptions = JsonOutput.toJson([
          "--runner=SparkStructuredStreamingRunner",
          "--testMode=true",
          "--streaming=false",
  ])
  systemProperty "beamTestPipelineOptions", pipelineOptions
  systemProperty "spark.sql.shuffle.partitions", "4"
  systemProperty "spark.ui.enabled", "false"
  systemProperty "spark.ui.showConsoleProgress", "false"

  classpath = configurations.validatesRunner
  testClassesDirs = files(
          project(":sdks:java:core").sourceSets.test.output.classesDirs,
          project(":runners:core-java").sourceSets.test.output.classesDirs,
  )
  testClassesDirs += files(project.sourceSets.test.output.classesDirs)

  // Only one SparkContext may be running in a JVM (SPARK-2243)
  forkEvery 1
  maxParallelForks 4
  useJUnit {
    includeCategories 'org.apache.beam.sdk.testing.ValidatesRunner'
    // Unbounded
    excludeCategories 'org.apache.beam.sdk.testing.UsesUnboundedPCollections'
    excludeCategories 'org.apache.beam.sdk.testing.UsesTestStream'
    // State and Timers
    excludeCategories 'org.apache.beam.sdk.testing.UsesStatefulParDo'
    excludeCategories 'org.apache.beam.sdk.testing.UsesMapState'
    excludeCategories 'org.apache.beam.sdk.testing.UsesSetState'
    excludeCategories 'org.apache.beam.sdk.testing.UsesTimersInParDo'
    excludeCategories 'org.apache.beam.sdk.testing.UsesTimerMap'
    excludeCategories 'org.apache.beam.sdk.testing.UsesKeyInParDo'
    excludeCategories 'org.apache.beam.sdk.testing.UsesOnWindowExpiration'
    // Metrics
    excludeCategories 'org.apache.beam.sdk.testing.UsesCommittedMetrics'
    excludeCategories 'org.apache.beam.sdk.testing.UsesSystemMetrics'
    // SDF
    excludeCategories 'org.apache.beam.sdk.testing.UsesUnboundedSplittableParDo'
    // Portability
    excludeCategories 'org.apache.beam.sdk.testing.UsesImpulse'
    excludeCategories 'org.apache.beam.sdk.testing.UsesCrossLanguageTransforms'
    excludeCategories 'org.apache.beam.sdk.testing.FlattenWithHeterogeneousCoders'
    excludeCategories 'org.apache.beam.sdk.testing.UsesBundleFinalizer'
  }
  filter {
    // Combine with context not implemented
    excludeTestsMatching 'org.apache.beam.sdk.transforms.CombineFnsTest.testComposedCombineWithContext'
    excludeTestsMatching 'org.apache.beam.sdk.transforms.CombineTest$CombineWithContextTests.testSimpleCombineWithContext'
    excludeTestsMatching 'org.apache.beam.sdk.transforms.CombineTest$CombineWithContextTests.testSimpleCombineWithContextEmpty'
    excludeTestsMatching 'org.apache.beam.sdk.transforms.CombineTest$WindowingTests.testFixedWindowsCombineWithContext'
    excludeTestsMatching 'org.apache.beam.sdk.transforms.CombineTest$WindowingTests.testSessionsCombineWithContext'
    excludeTestsMatching 'org.apache.beam.sdk.transforms.CombineTest$WindowingTests.testSlidingWindowsCombineWithContext'
    // multiple coders bug BEAM-8894
    excludeTestsMatching 'org.apache.beam.sdk.transforms.FlattenTest.testFlattenMultipleCoders'
    //SDF
    excludeTestsMatching 'org.apache.beam.sdk.transforms.SplittableDoFnTest.testLifecycleMethodsBounded'
    excludeTestsMatching 'org.apache.beam.sdk.transforms.SplittableDoFnTest.testPairWithIndexWindowedTimestampedBounded'
  }
}

task validatesRunner {
  group = "Verification"
  description "Validates Spark runner"
  dependsOn validatesRunnerBatch
  dependsOn validatesRunnerStreaming
  // It should be uncommented once all "validatesStructuredStreamingRunnerBatch" tests will pass.
  // Otherwise, it breaks Spark runner ValidatesRunner tests.
  //dependsOn validatesStructuredStreamingRunnerBatch
}

// Generates :runners:spark:runQuickstartJavaSpark
createJavaExamplesArchetypeValidationTask(type: 'Quickstart', runner: 'Spark')