Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SPARK-30645][SPARKR][TESTS][WINDOWS] Move Unicode test data to external file #27362

Closed
wants to merge 1 commit into from
Closed

[SPARK-30645][SPARKR][TESTS][WINDOWS] Move Unicode test data to external file #27362

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions R/pkg/tests/fulltests/data/test_utils_utf.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
{"name": "안녕하세요"}
{"name": "您好", "age": 30}
{"name": "こんにちは", "age": 19}
{"name": "Xin chào"}
29 changes: 18 additions & 11 deletions R/pkg/tests/fulltests/test_sparkSQL.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -848,24 +848,31 @@ test_that("collect() and take() on a DataFrame return the same number of rows an
})

test_that("collect() support Unicode characters", {
lines <- c("{\"name\":\"안녕하세요\"}",
"{\"name\":\"您好\", \"age\":30}",
"{\"name\":\"こんにちは\", \"age\":19}",
"{\"name\":\"Xin chào\"}")
jsonPath <- file.path(
Sys.getenv("SPARK_HOME"),
"R", "pkg", "tests", "fulltests", "data",
"test_utils_utf.json"
)

lines <- readLines(jsonPath, encoding = "UTF-8")

jsonPath <- tempfile(pattern = "sparkr-test", fileext = ".tmp")
writeLines(lines, jsonPath)
expected <- regmatches(lines, gregexpr('(?<="name": ").*?(?=")', lines, perl = TRUE))

df <- read.df(jsonPath, "json")
rdf <- collect(df)
expect_true(is.data.frame(rdf))
expect_equal(rdf$name[1], markUtf8("안녕하세요"))
expect_equal(rdf$name[2], markUtf8("您好"))
expect_equal(rdf$name[3], markUtf8("こんにちは"))
expect_equal(rdf$name[4], markUtf8("Xin chào"))
expect_equal(rdf$name[1], expected[[1]])
expect_equal(rdf$name[2], expected[[2]])
expect_equal(rdf$name[3], expected[[3]])
expect_equal(rdf$name[4], expected[[4]])

df1 <- createDataFrame(rdf)
expect_equal(collect(where(df1, df1$name == markUtf8("您好")))$name, markUtf8("您好"))
expect_equal(
collect(
where(df1, df1$name == expected[[2]])
)$name,
expected[[2]]
)
})

test_that("multiple pipeline transformations result in an RDD with the correct values", {
Expand Down