diff options
author | Dongjoon Hyun <dongjoon@apache.org> | 2016-06-20 11:30:26 -0700 |
---|---|---|
committer | Shivaram Venkataraman <shivaram@cs.berkeley.edu> | 2016-06-20 11:30:26 -0700 |
commit | c44bf137c7ca649e0c504229eb3e6ff7955e9a53 (patch) | |
tree | fa7fade42068841c8fb8403b0c7434eefc874e55 /R/pkg/inst/tests/testthat/test_sparkSQL.R | |
parent | 36e812d4b695566437c6bac991ef06a0f81fb1c5 (diff) | |
download | spark-c44bf137c7ca649e0c504229eb3e6ff7955e9a53.tar.gz spark-c44bf137c7ca649e0c504229eb3e6ff7955e9a53.tar.bz2 spark-c44bf137c7ca649e0c504229eb3e6ff7955e9a53.zip |
[SPARK-16051][R] Add `read.orc/write.orc` to SparkR
## What changes were proposed in this pull request?
This issue adds `read.orc/write.orc` to SparkR for API parity.
## How was this patch tested?
Pass the Jenkins tests (with new testcases).
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes #13763 from dongjoon-hyun/SPARK-16051.
Diffstat (limited to 'R/pkg/inst/tests/testthat/test_sparkSQL.R')
-rw-r--r-- | R/pkg/inst/tests/testthat/test_sparkSQL.R | 21 |
1 files changed, 21 insertions, 0 deletions
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R index ceba0d138e..114fec6e36 100644 --- a/R/pkg/inst/tests/testthat/test_sparkSQL.R +++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R @@ -68,6 +68,7 @@ mockLines <- c("{\"name\":\"Michael\"}", "{\"name\":\"Justin\", \"age\":19}") jsonPath <- tempfile(pattern = "sparkr-test", fileext = ".tmp") parquetPath <- tempfile(pattern = "sparkr-test", fileext = ".parquet") +orcPath <- tempfile(pattern = "sparkr-test", fileext = ".orc") writeLines(mockLines, jsonPath) # For test nafunctions, like dropna(), fillna(),... @@ -1667,6 +1668,25 @@ test_that("mutate(), transform(), rename() and names()", { detach(airquality) }) +test_that("read/write ORC files", { + df <- read.df(jsonPath, "json") + + # Test write.df and read.df + write.df(df, orcPath, "orc", mode = "overwrite") + df2 <- read.df(orcPath, "orc") + expect_is(df2, "SparkDataFrame") + expect_equal(count(df), count(df2)) + + # Test write.orc and read.orc + orcPath2 <- tempfile(pattern = "orcPath2", fileext = ".orc") + write.orc(df, orcPath2) + orcDF <- read.orc(orcPath2) + expect_is(orcDF, "SparkDataFrame") + expect_equal(count(orcDF), count(df)) + + unlink(orcPath2) +}) + test_that("read/write Parquet files", { df <- read.df(jsonPath, "json") # Test write.df and read.df @@ -2351,5 +2371,6 @@ test_that("enableHiveSupport on SparkSession", { }) unlink(parquetPath) +unlink(orcPath) unlink(jsonPath) unlink(jsonPathNa) |