1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
|
#
# 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.
#
context("test functions in sparkR.R")
test_that("Check masked functions", {
# Check that we are not masking any new function from base, stats, testthat unexpectedly
masked <- conflicts(detail = TRUE)$`package:SparkR`
expect_true("describe" %in% masked) # only when with testthat..
func <- lapply(masked, function(x) { capture.output(showMethods(x))[[1]] })
funcSparkROrEmpty <- grepl("\\(package SparkR\\)$|^$", func)
maskedBySparkR <- masked[funcSparkROrEmpty]
namesOfMasked <- c("describe", "cov", "filter", "lag", "na.omit", "predict", "sd", "var",
"colnames", "colnames<-", "intersect", "rank", "rbind", "sample", "subset",
"summary", "transform", "drop", "window")
expect_equal(length(maskedBySparkR), length(namesOfMasked))
expect_equal(sort(maskedBySparkR), sort(namesOfMasked))
# above are those reported as masked when `library(SparkR)`
# note that many of these methods are still callable without base:: or stats:: prefix
# there should be a test for each of these, except followings, which are currently "broken"
funcHasAny <- unlist(lapply(masked, function(x) {
any(grepl("=\"ANY\"", capture.output(showMethods(x)[-1])))
}))
maskedCompletely <- masked[!funcHasAny]
namesOfMaskedCompletely <- c("cov", "filter", "sample")
expect_equal(length(maskedCompletely), length(namesOfMaskedCompletely))
expect_equal(sort(maskedCompletely), sort(namesOfMaskedCompletely))
})
test_that("repeatedly starting and stopping SparkR", {
for (i in 1:4) {
sc <- sparkR.init()
rdd <- parallelize(sc, 1:20, 2L)
expect_equal(count(rdd), 20)
sparkR.stop()
}
})
test_that("repeatedly starting and stopping SparkR SQL", {
for (i in 1:4) {
sc <- sparkR.init()
sqlContext <- sparkRSQL.init(sc)
df <- createDataFrame(sqlContext, data.frame(a = 1:20))
expect_equal(count(df), 20)
sparkR.stop()
}
})
test_that("rdd GC across sparkR.stop", {
sparkR.stop()
sc <- sparkR.init() # 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.stop()
sc <- sparkR.init() # sc should get id 0 again
# GC rdd1 before creating rdd3 and rdd2 after
rm(rdd1)
gc()
rdd3 <- parallelize(sc, 1:20, 2L) # rdd3 should get id 1 now
rdd4 <- parallelize(sc, 1:10, 2L) # rdd4 should get id 2 now
rm(rdd2)
gc()
count(rdd3)
count(rdd4)
})
test_that("job group functions can be called", {
sc <- sparkR.init()
setJobGroup(sc, "groupId", "job description", TRUE)
cancelJobGroup(sc, "groupId")
clearJobGroup(sc)
})
test_that("getClientModeSparkSubmitOpts() returns spark-submit args from whitelist", {
e <- new.env()
e[["spark.driver.memory"]] <- "512m"
ops <- getClientModeSparkSubmitOpts("sparkrmain", e)
expect_equal("--driver-memory \"512m\" sparkrmain", ops)
e[["spark.driver.memory"]] <- "5g"
e[["spark.driver.extraClassPath"]] <- "/opt/class_path" # nolint
e[["spark.driver.extraJavaOptions"]] <- "-XX:+UseCompressedOops -XX:+UseCompressedStrings"
e[["spark.driver.extraLibraryPath"]] <- "/usr/local/hadoop/lib" # nolint
e[["random"]] <- "skipthis"
ops2 <- getClientModeSparkSubmitOpts("sparkr-shell", e)
# nolint start
expect_equal(ops2, paste0("--driver-class-path \"/opt/class_path\" --driver-java-options \"",
"-XX:+UseCompressedOops -XX:+UseCompressedStrings\" --driver-library-path \"",
"/usr/local/hadoop/lib\" --driver-memory \"5g\" sparkr-shell"))
# nolint end
e[["spark.driver.extraClassPath"]] <- "/" # too short
ops3 <- getClientModeSparkSubmitOpts("--driver-memory 4g sparkr-shell2", e)
# nolint start
expect_equal(ops3, paste0("--driver-java-options \"-XX:+UseCompressedOops ",
"-XX:+UseCompressedStrings\" --driver-library-path \"/usr/local/hadoop/lib\"",
" --driver-memory 4g sparkr-shell2"))
# nolint end
})
test_that("sparkJars sparkPackages as comma-separated strings", {
expect_warning(processSparkJars(" a, b "))
jars <- suppressWarnings(processSparkJars(" a, b "))
expect_equal(jars, c("a", "b"))
jars <- suppressWarnings(processSparkJars(" abc ,, def "))
expect_equal(jars, c("abc", "def"))
jars <- suppressWarnings(processSparkJars(c(" abc ,, def ", "", "xyz", " ", "a,b")))
expect_equal(jars, c("abc", "def", "xyz", "a", "b"))
p <- processSparkPackages(c("ghi", "lmn"))
expect_equal(p, c("ghi", "lmn"))
# check normalizePath
f <- dir()[[1]]
expect_that(processSparkJars(f), not(gives_warning()))
expect_match(processSparkJars(f), f)
})
|
