[SNAPPYDATA] fixed doc references in R, build changes

- updated build to use common top-level sources/doc packaging methods if available
- build changes for the switch from maven to maven-publish
- fixed failure in an R test

Author: Sumedh Wale

R/pkg/R/context.R

@@ -303,7 +303,7 @@ setCheckpointDir <- function(sc, dirName) {
 #'
 #' A directory can be given if the recursive option is set to true.
 #' Currently directories are only supported for Hadoop-supported filesystems.
-#' Refer Hadoop-supported filesystems at \url{https://wiki.apache.org/hadoop/HCFS}.
+#' Refer Hadoop-supported filesystems at \url{https://cwiki.apache.org/confluence/display/HADOOP2/HCFS}.
 #'
 #' @rdname spark.addFile
 #' @param path The path of the file to be added

R/pkg/vignettes/sparkr-vignettes.Rmd

@@ -317,7 +317,7 @@ A common flow of grouping and aggregation is
 
 2. Feed the `GroupedData` object to `agg` or `summarize` functions, with some provided aggregation functions to compute a number within each group.
 
-A number of widely used functions are supported to aggregate data after grouping, including `avg`, `countDistinct`, `count`, `first`, `kurtosis`, `last`, `max`, `mean`, `min`, `sd`, `skewness`, `stddev_pop`, `stddev_samp`, `sumDistinct`, `sum`, `var_pop`, `var_samp`, `var`. See the [API doc for `mean`](http://spark.apache.org/docs/latest/api/R/mean.html) and other `agg_funcs` linked there.
+A number of widely used functions are supported to aggregate data after grouping, including `avg`, `countDistinct`, `count`, `first`, `kurtosis`, `last`, `max`, `mean`, `min`, `sd`, `skewness`, `stddev_pop`, `stddev_samp`, `sumDistinct`, `sum`, `var_pop`, `var_samp`, `var`. See the [API doc for `mean`](https://spark.apache.org/docs/2.1.3/api/R/mean.html) and other `agg_funcs` linked there.
 
 For example we can compute a histogram of the number of cylinders in the `mtcars` dataset as shown below.
 

build.gradle

@@ -312,7 +312,7 @@ task cleanSparkJUnit { doLast {
 
 subprojects {
   apply plugin: 'scala'
-  apply plugin: 'maven'
+  apply plugin: 'maven-publish'
   apply plugin: 'scalaStyle'
 
   int maxWorkers = project.hasProperty('org.gradle.workers.max') ?
@@ -352,6 +352,10 @@ subprojects {
       archiveClassifier.set('sources')
       from sourceSets.main.allSource
     }
+    task packageScalaDocs(type: Jar, dependsOn: scaladoc) {
+      archiveClassifier.set('javadoc')
+      from scaladoc
+    }
 
     configurations {
       testOutput {
@@ -369,15 +373,6 @@ subprojects {
       testOutput packageTests
     }
   }
-  task packageScalaDocs(type: Jar, dependsOn: scaladoc) {
-    archiveClassifier.set('javadoc')
-    from scaladoc
-  }
-  if (rootProject.hasProperty('enablePublish')) {
-    artifacts {
-      archives packageScalaDocs, packageSources
-    }
-  }
 
   // fix scala+java mix to all use compileScala which use correct dependency order
   sourceSets.main.scala.srcDir 'src/main/java'

core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala

@@ -14,6 +14,24 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+/*
+ * Changes for TIBCO Project SnappyData data platform.
+ *
+ * Portions Copyright (c) 2017-2022 TIBCO Software Inc. All rights reserved.
+ *
+ * Licensed 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. See accompanying
+ * LICENSE file.
+ */
 
 package org.apache.spark.deploy
 
@@ -427,9 +445,10 @@ class SparkSubmitSuite
     // Check if the SparkR package is installed
     assume(RUtils.isSparkRInstalled, "SparkR is not installed in this build.")
     val main = MavenCoordinate("my.great.lib", "mylib", "0.1")
-    val sparkHome = sys.props.getOrElse("spark.test.home", fail("spark.test.home is not set!"))
-    val rScriptDir = Seq(
-      sparkHome, "R", "pkg", "tests", "fulltests", "packageInAJarTest.R").mkString(File.separator)
+    val sparkProjectHome = sys.props.getOrElse("spark.project.home",
+      sys.props.getOrElse("spark.test.home", fail("spark.test.home is not set!")))
+    val rScriptDir = Seq(sparkProjectHome,
+      "R", "pkg", "tests", "fulltests", "packageInAJarTest.R").mkString(File.separator)
     assert(new File(rScriptDir).exists)
     IvyTestUtils.withRepository(main, None, None, withR = true) { repo =>
       val args = Seq(
@@ -446,11 +465,12 @@ class SparkSubmitSuite
 
   test("include an external JAR in SparkR") {
     assume(RUtils.isRInstalled, "R isn't installed on this machine.")
-    val sparkHome = sys.props.getOrElse("spark.test.home", fail("spark.test.home is not set!"))
+    val sparkProjectHome = sys.props.getOrElse("spark.project.home",
+      sys.props.getOrElse("spark.test.home", fail("spark.test.home is not set!")))
     // Check if the SparkR package is installed
     assume(RUtils.isSparkRInstalled, "SparkR is not installed in this build.")
-    val rScriptDir =
-      Seq(sparkHome, "R", "pkg", "tests", "fulltests", "jarTest.R").mkString(File.separator)
+    val rScriptDir = Seq(sparkProjectHome,
+      "R", "pkg", "tests", "fulltests", "jarTest.R").mkString(File.separator)
     assert(new File(rScriptDir).exists)
 
     // compile a small jar containing a class that will be called from R code.