[SPARK-19387][SPARKR] Tests do not run with SparkR source package in CRAN check

R/pkg/R/install.R

@@ -21,9 +21,9 @@
 #' Download and Install Apache Spark to a Local Directory
 #'
 #' \code{install.spark} downloads and installs Spark to a local directory if
-#' it is not found. The Spark version we use is the same as the SparkR version.
-#' Users can specify a desired Hadoop version, the remote mirror site, and
-#' the directory where the package is installed locally.
+#' it is not found. If SPARK_HOME is set in the environment, and that directory is found, that is
+#' returned. The Spark version we use is the same as the SparkR version. Users can specify a desired
+#' Hadoop version, the remote mirror site, and the directory where the package is installed locally.
 #'
 #' The full url of remote file is inferred from \code{mirrorUrl} and \code{hadoopVersion}.
 #' \code{mirrorUrl} specifies the remote path to a Spark folder. It is followed by a subfolder
@@ -68,6 +68,16 @@
 #'          \href{http://spark.apache.org/downloads.html}{Apache Spark}
 install.spark <- function(hadoopVersion = "2.7", mirrorUrl = NULL,
                           localDir = NULL, overwrite = FALSE) {
+  sparkHome <- Sys.getenv("SPARK_HOME")
+  if (isSparkRShell()) {
+    stopifnot(nchar(sparkHome) > 0)
+    message("Spark is already running in sparkR shell.")
+    return(invisible(sparkHome))
+  } else if (!is.na(file.info(sparkHome)$isdir)) {
+    message("Spark package found in SPARK_HOME: ", sparkHome)
+    return(invisible(sparkHome))
+  }
+
   version <- paste0("spark-", packageVersion("SparkR"))
   hadoopVersion <- tolower(hadoopVersion)
   hadoopVersionName <- hadoopVersionName(hadoopVersion)

R/pkg/R/sparkR.R

@@ -588,13 +588,11 @@ processSparkPackages <- function(packages) {
 sparkCheckInstall <- function(sparkHome, master, deployMode) {
   if (!isSparkRShell()) {
     if (!is.na(file.info(sparkHome)$isdir)) {
-      msg <- paste0("Spark package found in SPARK_HOME: ", sparkHome)
-      message(msg)
+      message("Spark package found in SPARK_HOME: ", sparkHome)
       NULL
     } else {
       if (interactive() || isMasterLocal(master)) {
-        msg <- paste0("Spark not found in SPARK_HOME: ", sparkHome)
-        message(msg)
+        message("Spark not found in SPARK_HOME: ", sparkHome)
         packageLocalDir <- install.spark()
         packageLocalDir
       } else if (isClientMode(master) || deployMode == "client") {

R/pkg/tests/run-all.R

@@ -21,4 +21,7 @@ library(SparkR)
 # Turn all warnings into errors
 options("warn" = 2)
 
+# Setup global test environment
+install.spark()
+
 test_package("SparkR")

R/pkg/vignettes/sparkr-vignettes.Rmd

@@ -27,6 +27,9 @@ library(SparkR)
 
 We use default settings in which it runs in local mode. It auto downloads Spark package in the background if no previous installation is found. For more details about setup, see [Spark Session](#SetupSparkSession).
 
+```{r, include=FALSE}
+install.spark()
+```
 ```{r, message=FALSE, results="hide"}
 sparkR.session()
 ```