From 6b41195bca65de6236168d96758f93b85f1dd7ca Mon Sep 17 00:00:00 2001
From: hyukjinkwon <gurwls223@gmail.com>
Date: Wed, 7 Sep 2016 19:24:03 +0900
Subject: [PATCH] [SPARK-17339][SPARKR][CORE] Fix some R tests and use
Path.toUri in SparkContext for Windows paths in SparkR
## What changes were proposed in this pull request?
This PR fixes the Windows path issues in several APIs. Please refer https://issues.apache.org/jira/browse/SPARK-17339 for more details.
## How was this patch tested?
Tests via AppVeyor CI - https://ci.appveyor.com/project/HyukjinKwon/spark/build/82-SPARK-17339-fix-r
Also, manually,
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #14960 from HyukjinKwon/SPARK-17339.
---
R/pkg/inst/tests/testthat/test_mllib.R | 14 ++++++++++----
.../main/scala/org/apache/spark/SparkContext.scala | 4 ++--
2 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/R/pkg/inst/tests/testthat/test_mllib.R b/R/pkg/inst/tests/testthat/test_mllib.R
index ca25f2c7e8..ac896cfbcf 100644
--- a/R/pkg/inst/tests/testthat/test_mllib.R
+++ b/R/pkg/inst/tests/testthat/test_mllib.R
@@ -22,6 +22,11 @@ context("MLlib functions")
# Tests for MLlib functions in SparkR
sparkSession <- sparkR.session(enableHiveSupport = FALSE)
+absoluteSparkPath <- function(x) {
+ sparkHome <- sparkR.conf("spark.home")
+ file.path(sparkHome, x)
+}
+
test_that("formula of spark.glm", {
training <- suppressWarnings(createDataFrame(iris))
# directly calling the spark API
@@ -354,7 +359,8 @@ test_that("spark.kmeans", {
})
test_that("spark.mlp", {
- df <- read.df("data/mllib/sample_multiclass_classification_data.txt", source = "libsvm")
+ df <- read.df(absoluteSparkPath("data/mllib/sample_multiclass_classification_data.txt"),
+ source = "libsvm")
model <- spark.mlp(df, blockSize = 128, layers = c(4, 5, 4, 3), solver = "l-bfgs", maxIter = 100,
tol = 0.5, stepSize = 1, seed = 1)
@@ -616,7 +622,7 @@ test_that("spark.gaussianMixture", {
})
test_that("spark.lda with libsvm", {
- text <- read.df("data/mllib/sample_lda_libsvm_data.txt", source = "libsvm")
+ text <- read.df(absoluteSparkPath("data/mllib/sample_lda_libsvm_data.txt"), source = "libsvm")
model <- spark.lda(text, optimizer = "em")
stats <- summary(model, 10)
@@ -652,7 +658,7 @@ test_that("spark.lda with libsvm", {
})
test_that("spark.lda with text input", {
- text <- read.text("data/mllib/sample_lda_data.txt")
+ text <- read.text(absoluteSparkPath("data/mllib/sample_lda_data.txt"))
model <- spark.lda(text, optimizer = "online", features = "value")
stats <- summary(model)
@@ -688,7 +694,7 @@ test_that("spark.lda with text input", {
})
test_that("spark.posterior and spark.perplexity", {
- text <- read.text("data/mllib/sample_lda_data.txt")
+ text <- read.text(absoluteSparkPath("data/mllib/sample_lda_data.txt"))
model <- spark.lda(text, features = "value", k = 3)
# Assert perplexities are equal
diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
index 744d5d0f7a..4aa795a58a 100644
--- a/core/src/main/scala/org/apache/spark/SparkContext.scala
+++ b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -992,7 +992,7 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
// This is a hack to enforce loading hdfs-site.xml.
// See SPARK-11227 for details.
- FileSystem.get(new URI(path), hadoopConfiguration)
+ FileSystem.getLocal(hadoopConfiguration)
// A Hadoop configuration can be about 10 KB, which is pretty big, so broadcast it.
val confBroadcast = broadcast(new SerializableConfiguration(hadoopConfiguration))
@@ -1081,7 +1081,7 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
// This is a hack to enforce loading hdfs-site.xml.
// See SPARK-11227 for details.
- FileSystem.get(new URI(path), hadoopConfiguration)
+ FileSystem.getLocal(hadoopConfiguration)
// The call to NewHadoopJob automatically adds security credentials to conf,
// so we don't need to explicitly add them ourselves
--
GitLab