From 888b84abe8d3fd36c5c2226aeb9e202029936f94 Mon Sep 17 00:00:00 2001
From: Felix Cheung <felixcheung_m@hotmail.com>
Date: Thu, 11 May 2017 23:10:04 -0700
Subject: [PATCH] [SPARK-20704][SPARKR] change CRAN test to run single thread
## What changes were proposed in this pull request?
- [x] need to test by running R CMD check --as-cran
- [x] sanity check vignettes
## How was this patch tested?
Jenkins
Author: Felix Cheung <felixcheung_m@hotmail.com>
Closes #17945 from felixcheung/rchangesforpackage.
---
R/pkg/inst/tests/testthat/jarTest.R | 2 +-
R/pkg/inst/tests/testthat/packageInAJarTest.R | 2 +-
R/pkg/inst/tests/testthat/test_Serde.R | 2 +-
R/pkg/inst/tests/testthat/test_binaryFile.R | 2 +-
R/pkg/inst/tests/testthat/test_binary_function.R | 2 +-
R/pkg/inst/tests/testthat/test_broadcast.R | 2 +-
R/pkg/inst/tests/testthat/test_context.R | 16 ++++++++--------
R/pkg/inst/tests/testthat/test_includePackage.R | 2 +-
R/pkg/inst/tests/testthat/test_jvm_api.R | 2 +-
.../tests/testthat/test_mllib_classification.R | 2 +-
.../inst/tests/testthat/test_mllib_clustering.R | 2 +-
R/pkg/inst/tests/testthat/test_mllib_fpm.R | 2 +-
.../tests/testthat/test_mllib_recommendation.R | 2 +-
.../inst/tests/testthat/test_mllib_regression.R | 2 +-
R/pkg/inst/tests/testthat/test_mllib_stat.R | 2 +-
R/pkg/inst/tests/testthat/test_mllib_tree.R | 2 +-
.../tests/testthat/test_parallelize_collect.R | 2 +-
R/pkg/inst/tests/testthat/test_rdd.R | 2 +-
R/pkg/inst/tests/testthat/test_shuffle.R | 2 +-
R/pkg/inst/tests/testthat/test_sparkSQL.R | 2 +-
R/pkg/inst/tests/testthat/test_streaming.R | 2 +-
R/pkg/inst/tests/testthat/test_take.R | 2 +-
R/pkg/inst/tests/testthat/test_textFile.R | 2 +-
R/pkg/inst/tests/testthat/test_utils.R | 2 +-
R/pkg/tests/run-all.R | 5 +++++
R/pkg/vignettes/sparkr-vignettes.Rmd | 3 ++-
26 files changed, 38 insertions(+), 32 deletions(-)
diff --git a/R/pkg/inst/tests/testthat/jarTest.R b/R/pkg/inst/tests/testthat/jarTest.R
index c9615c8d4f..e2241e03b5 100644
--- a/R/pkg/inst/tests/testthat/jarTest.R
+++ b/R/pkg/inst/tests/testthat/jarTest.R
@@ -16,7 +16,7 @@
#
library(SparkR)
-sc <- sparkR.session()
+sc <- sparkR.session(master = "local[1]")
helloTest <- SparkR:::callJStatic("sparkrtest.DummyClass",
"helloWorld",
diff --git a/R/pkg/inst/tests/testthat/packageInAJarTest.R b/R/pkg/inst/tests/testthat/packageInAJarTest.R
index 4bc935c79e..ac70626199 100644
--- a/R/pkg/inst/tests/testthat/packageInAJarTest.R
+++ b/R/pkg/inst/tests/testthat/packageInAJarTest.R
@@ -17,7 +17,7 @@
library(SparkR)
library(sparkPackageTest)
-sparkR.session()
+sparkR.session(master = "local[1]")
run1 <- myfunc(5L)
diff --git a/R/pkg/inst/tests/testthat/test_Serde.R b/R/pkg/inst/tests/testthat/test_Serde.R
index 518fb7bd94..6e160fae1a 100644
--- a/R/pkg/inst/tests/testthat/test_Serde.R
+++ b/R/pkg/inst/tests/testthat/test_Serde.R
@@ -17,7 +17,7 @@
context("SerDe functionality")
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
test_that("SerDe of primitive types", {
skip_on_cran()
diff --git a/R/pkg/inst/tests/testthat/test_binaryFile.R b/R/pkg/inst/tests/testthat/test_binaryFile.R
index 63f54e1af0..00954fa31b 100644
--- a/R/pkg/inst/tests/testthat/test_binaryFile.R
+++ b/R/pkg/inst/tests/testthat/test_binaryFile.R
@@ -18,7 +18,7 @@
context("functions on binary files")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
mockFile <- c("Spark is pretty.", "Spark is awesome.")
diff --git a/R/pkg/inst/tests/testthat/test_binary_function.R b/R/pkg/inst/tests/testthat/test_binary_function.R
index 25bb2b8426..236cb38854 100644
--- a/R/pkg/inst/tests/testthat/test_binary_function.R
+++ b/R/pkg/inst/tests/testthat/test_binary_function.R
@@ -18,7 +18,7 @@
context("binary functions")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
# Data
diff --git a/R/pkg/inst/tests/testthat/test_broadcast.R b/R/pkg/inst/tests/testthat/test_broadcast.R
index 504ded4fc8..254f8f522a 100644
--- a/R/pkg/inst/tests/testthat/test_broadcast.R
+++ b/R/pkg/inst/tests/testthat/test_broadcast.R
@@ -18,7 +18,7 @@
context("broadcast variables")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
# Partitioned data
diff --git a/R/pkg/inst/tests/testthat/test_context.R b/R/pkg/inst/tests/testthat/test_context.R
index 632a90d681..f6d9f5423d 100644
--- a/R/pkg/inst/tests/testthat/test_context.R
+++ b/R/pkg/inst/tests/testthat/test_context.R
@@ -60,7 +60,7 @@ test_that("repeatedly starting and stopping SparkR", {
skip_on_cran()
for (i in 1:4) {
- sc <- suppressWarnings(sparkR.init())
+ sc <- suppressWarnings(sparkR.init(master = sparkRTestMaster))
rdd <- parallelize(sc, 1:20, 2L)
expect_equal(countRDD(rdd), 20)
suppressWarnings(sparkR.stop())
@@ -69,7 +69,7 @@ test_that("repeatedly starting and stopping SparkR", {
test_that("repeatedly starting and stopping SparkSession", {
for (i in 1:4) {
- sparkR.session(enableHiveSupport = FALSE)
+ sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
df <- createDataFrame(data.frame(dummy = 1:i))
expect_equal(count(df), i)
sparkR.session.stop()
@@ -79,12 +79,12 @@ test_that("repeatedly starting and stopping SparkSession", {
test_that("rdd GC across sparkR.stop", {
skip_on_cran()
- sc <- sparkR.sparkContext() # sc should get id 0
+ sc <- sparkR.sparkContext(master = sparkRTestMaster) # sc should get id 0
rdd1 <- parallelize(sc, 1:20, 2L) # rdd1 should get id 1
rdd2 <- parallelize(sc, 1:10, 2L) # rdd2 should get id 2
sparkR.session.stop()
- sc <- sparkR.sparkContext() # sc should get id 0 again
+ sc <- sparkR.sparkContext(master = sparkRTestMaster) # sc should get id 0 again
# GC rdd1 before creating rdd3 and rdd2 after
rm(rdd1)
@@ -104,7 +104,7 @@ test_that("rdd GC across sparkR.stop", {
test_that("job group functions can be called", {
skip_on_cran()
- sc <- sparkR.sparkContext()
+ sc <- sparkR.sparkContext(master = sparkRTestMaster)
setJobGroup("groupId", "job description", TRUE)
cancelJobGroup("groupId")
clearJobGroup()
@@ -118,7 +118,7 @@ test_that("job group functions can be called", {
test_that("utility function can be called", {
skip_on_cran()
- sparkR.sparkContext()
+ sparkR.sparkContext(master = sparkRTestMaster)
setLogLevel("ERROR")
sparkR.session.stop()
})
@@ -175,7 +175,7 @@ test_that("sparkJars sparkPackages as comma-separated strings", {
})
test_that("spark.lapply should perform simple transforms", {
- sparkR.sparkContext()
+ sparkR.sparkContext(master = sparkRTestMaster)
doubled <- spark.lapply(1:10, function(x) { 2 * x })
expect_equal(doubled, as.list(2 * 1:10))
sparkR.session.stop()
@@ -184,7 +184,7 @@ test_that("spark.lapply should perform simple transforms", {
test_that("add and get file to be downloaded with Spark job on every node", {
skip_on_cran()
- sparkR.sparkContext()
+ sparkR.sparkContext(master = sparkRTestMaster)
# Test add file.
path <- tempfile(pattern = "hello", fileext = ".txt")
filename <- basename(path)
diff --git a/R/pkg/inst/tests/testthat/test_includePackage.R b/R/pkg/inst/tests/testthat/test_includePackage.R
index f823ad8e9c..d7d9eeed15 100644
--- a/R/pkg/inst/tests/testthat/test_includePackage.R
+++ b/R/pkg/inst/tests/testthat/test_includePackage.R
@@ -18,7 +18,7 @@
context("include R packages")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
# Partitioned data
diff --git a/R/pkg/inst/tests/testthat/test_jvm_api.R b/R/pkg/inst/tests/testthat/test_jvm_api.R
index 7348c893d0..8b3b4f73de 100644
--- a/R/pkg/inst/tests/testthat/test_jvm_api.R
+++ b/R/pkg/inst/tests/testthat/test_jvm_api.R
@@ -17,7 +17,7 @@
context("JVM API")
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
test_that("Create and call methods on object", {
jarr <- sparkR.newJObject("java.util.ArrayList")
diff --git a/R/pkg/inst/tests/testthat/test_mllib_classification.R b/R/pkg/inst/tests/testthat/test_mllib_classification.R
index cbc7087182..f3eaeb381a 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_classification.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_classification.R
@@ -20,7 +20,7 @@ library(testthat)
context("MLlib classification algorithms, except for tree-based algorithms")
# Tests for MLlib classification algorithms in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
absoluteSparkPath <- function(x) {
sparkHome <- sparkR.conf("spark.home")
diff --git a/R/pkg/inst/tests/testthat/test_mllib_clustering.R b/R/pkg/inst/tests/testthat/test_mllib_clustering.R
index 478012e882..df8e5968b2 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_clustering.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_clustering.R
@@ -20,7 +20,7 @@ library(testthat)
context("MLlib clustering algorithms")
# Tests for MLlib clustering algorithms in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
absoluteSparkPath <- function(x) {
sparkHome <- sparkR.conf("spark.home")
diff --git a/R/pkg/inst/tests/testthat/test_mllib_fpm.R b/R/pkg/inst/tests/testthat/test_mllib_fpm.R
index c38f113389..1fa5375f9d 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_fpm.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_fpm.R
@@ -20,7 +20,7 @@ library(testthat)
context("MLlib frequent pattern mining")
# Tests for MLlib frequent pattern mining algorithms in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
test_that("spark.fpGrowth", {
data <- selectExpr(createDataFrame(data.frame(items = c(
diff --git a/R/pkg/inst/tests/testthat/test_mllib_recommendation.R b/R/pkg/inst/tests/testthat/test_mllib_recommendation.R
index 6b1040db93..e3e2b15c71 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_recommendation.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_recommendation.R
@@ -20,7 +20,7 @@ library(testthat)
context("MLlib recommendation algorithms")
# Tests for MLlib recommendation algorithms in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
test_that("spark.als", {
data <- list(list(0, 0, 4.0), list(0, 1, 2.0), list(1, 1, 3.0), list(1, 2, 4.0),
diff --git a/R/pkg/inst/tests/testthat/test_mllib_regression.R b/R/pkg/inst/tests/testthat/test_mllib_regression.R
index 58924f952c..44c98be906 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_regression.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_regression.R
@@ -20,7 +20,7 @@ library(testthat)
context("MLlib regression algorithms, except for tree-based algorithms")
# Tests for MLlib regression algorithms in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
test_that("formula of spark.glm", {
skip_on_cran()
diff --git a/R/pkg/inst/tests/testthat/test_mllib_stat.R b/R/pkg/inst/tests/testthat/test_mllib_stat.R
index beb148e770..1600833a5d 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_stat.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_stat.R
@@ -20,7 +20,7 @@ library(testthat)
context("MLlib statistics algorithms")
# Tests for MLlib statistics algorithms in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
test_that("spark.kstest", {
data <- data.frame(test = c(0.1, 0.15, 0.2, 0.3, 0.25, -1, -0.5))
diff --git a/R/pkg/inst/tests/testthat/test_mllib_tree.R b/R/pkg/inst/tests/testthat/test_mllib_tree.R
index e0802a9b02..146bc2878e 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_tree.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_tree.R
@@ -20,7 +20,7 @@ library(testthat)
context("MLlib tree-based algorithms")
# Tests for MLlib tree-based algorithms in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
absoluteSparkPath <- function(x) {
sparkHome <- sparkR.conf("spark.home")
diff --git a/R/pkg/inst/tests/testthat/test_parallelize_collect.R b/R/pkg/inst/tests/testthat/test_parallelize_collect.R
index 1f7f387de0..52d4c93ed9 100644
--- a/R/pkg/inst/tests/testthat/test_parallelize_collect.R
+++ b/R/pkg/inst/tests/testthat/test_parallelize_collect.R
@@ -33,7 +33,7 @@ numPairs <- list(list(1, 1), list(1, 2), list(2, 2), list(2, 3))
strPairs <- list(list(strList, strList), list(strList, strList))
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
jsc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
# Tests
diff --git a/R/pkg/inst/tests/testthat/test_rdd.R b/R/pkg/inst/tests/testthat/test_rdd.R
index a3b1631e1d..fb244e1d49 100644
--- a/R/pkg/inst/tests/testthat/test_rdd.R
+++ b/R/pkg/inst/tests/testthat/test_rdd.R
@@ -18,7 +18,7 @@
context("basic RDD functions")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
# Data
diff --git a/R/pkg/inst/tests/testthat/test_shuffle.R b/R/pkg/inst/tests/testthat/test_shuffle.R
index cedf4f100c..18320ea44b 100644
--- a/R/pkg/inst/tests/testthat/test_shuffle.R
+++ b/R/pkg/inst/tests/testthat/test_shuffle.R
@@ -18,7 +18,7 @@
context("partitionBy, groupByKey, reduceByKey etc.")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
# Data
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R
index 19aa61e9a5..0ff2e02e75 100644
--- a/R/pkg/inst/tests/testthat/test_sparkSQL.R
+++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R
@@ -61,7 +61,7 @@ unsetHiveContext <- function() {
# Tests for SparkSQL functions in SparkR
filesBefore <- list.files(path = sparkRDir, all.files = TRUE)
-sparkSession <- sparkR.session()
+sparkSession <- sparkR.session(master = sparkRTestMaster)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
mockLines <- c("{\"name\":\"Michael\"}",
diff --git a/R/pkg/inst/tests/testthat/test_streaming.R b/R/pkg/inst/tests/testthat/test_streaming.R
index 91df7ac6f9..b20b4312fb 100644
--- a/R/pkg/inst/tests/testthat/test_streaming.R
+++ b/R/pkg/inst/tests/testthat/test_streaming.R
@@ -21,7 +21,7 @@ context("Structured Streaming")
# Tests for Structured Streaming functions in SparkR
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
jsonSubDir <- file.path("sparkr-test", "json", "")
if (.Platform$OS.type == "windows") {
diff --git a/R/pkg/inst/tests/testthat/test_take.R b/R/pkg/inst/tests/testthat/test_take.R
index e2130eaac7..c00723ba31 100644
--- a/R/pkg/inst/tests/testthat/test_take.R
+++ b/R/pkg/inst/tests/testthat/test_take.R
@@ -30,7 +30,7 @@ strList <- list("Dexter Morgan: Blood. Sometimes it sets my teeth on edge, ",
"raising me. But they're both dead now. I didn't kill them. Honest.")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
test_that("take() gives back the original elements in correct count and order", {
diff --git a/R/pkg/inst/tests/testthat/test_textFile.R b/R/pkg/inst/tests/testthat/test_textFile.R
index 28b7e8e318..e8a961cb3e 100644
--- a/R/pkg/inst/tests/testthat/test_textFile.R
+++ b/R/pkg/inst/tests/testthat/test_textFile.R
@@ -18,7 +18,7 @@
context("the textFile() function")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
mockFile <- c("Spark is pretty.", "Spark is awesome.")
diff --git a/R/pkg/inst/tests/testthat/test_utils.R b/R/pkg/inst/tests/testthat/test_utils.R
index 4a01e87540..2fc6530d63 100644
--- a/R/pkg/inst/tests/testthat/test_utils.R
+++ b/R/pkg/inst/tests/testthat/test_utils.R
@@ -18,7 +18,7 @@
context("functions in utils.R")
# JavaSparkContext handle
-sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
test_that("convertJListToRList() gives back (deserializes) the original JLists
diff --git a/R/pkg/tests/run-all.R b/R/pkg/tests/run-all.R
index 29812f872c..9c6cba535d 100644
--- a/R/pkg/tests/run-all.R
+++ b/R/pkg/tests/run-all.R
@@ -31,4 +31,9 @@ sparkRWhitelistSQLDirs <- c("spark-warehouse", "metastore_db")
invisible(lapply(sparkRWhitelistSQLDirs,
function(x) { unlink(file.path(sparkRDir, x), recursive = TRUE, force = TRUE)}))
+sparkRTestMaster <- "local[1]"
+if (identical(Sys.getenv("NOT_CRAN"), "true")) {
+ sparkRTestMaster <- ""
+}
+
test_package("SparkR")
diff --git a/R/pkg/vignettes/sparkr-vignettes.Rmd b/R/pkg/vignettes/sparkr-vignettes.Rmd
index 49f4ab8f14..13a399165c 100644
--- a/R/pkg/vignettes/sparkr-vignettes.Rmd
+++ b/R/pkg/vignettes/sparkr-vignettes.Rmd
@@ -46,8 +46,9 @@ We use default settings in which it runs in local mode. It auto downloads Spark
```{r, include=FALSE}
install.spark()
+sparkR.session(master = "local[1]")
```
-```{r, message=FALSE, results="hide"}
+```{r, eval=FALSE}
sparkR.session()
```
--
GitLab