diff options
author | hyukjinkwon <gurwls223@gmail.com> | 2016-10-07 11:34:49 -0700 |
---|---|---|
committer | Felix Cheung <felixcheung@apache.org> | 2016-10-07 11:34:49 -0700 |
commit | 9d8ae853ecc5600f5c2f69565b96d5c46a8c0048 (patch) | |
tree | c3f57c9401be83b54eaa96f3fa4018fa527da3d5 /R/pkg/inst/tests/testthat/test_sparkSQL.R | |
parent | bb1aaf28eca6d9ae9af664ac3ad35cafdfc01a3b (diff) | |
download | spark-9d8ae853ecc5600f5c2f69565b96d5c46a8c0048.tar.gz spark-9d8ae853ecc5600f5c2f69565b96d5c46a8c0048.tar.bz2 spark-9d8ae853ecc5600f5c2f69565b96d5c46a8c0048.zip |
[SPARK-17665][SPARKR] Support options/mode all for read/write APIs and options in other types
## What changes were proposed in this pull request?
This PR includes the changes below:
- Support `mode`/`options` in `read.parquet`, `write.parquet`, `read.orc`, `write.orc`, `read.text`, `write.text`, `read.json` and `write.json` APIs
- Support other types (logical, numeric and string) as options for `write.df`, `read.df`, `read.parquet`, `write.parquet`, `read.orc`, `write.orc`, `read.text`, `write.text`, `read.json` and `write.json`
## How was this patch tested?
Unit tests in `test_sparkSQL.R`/ `utils.R`.
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #15239 from HyukjinKwon/SPARK-17665.
Diffstat (limited to 'R/pkg/inst/tests/testthat/test_sparkSQL.R')
-rw-r--r-- | R/pkg/inst/tests/testthat/test_sparkSQL.R | 75 |
1 files changed, 75 insertions, 0 deletions
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R index f5ab601f27..6d8cfad5c1 100644 --- a/R/pkg/inst/tests/testthat/test_sparkSQL.R +++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R @@ -256,6 +256,23 @@ test_that("read/write csv as DataFrame", { unlink(csvPath2) }) +test_that("Support other types for options", { + csvPath <- tempfile(pattern = "sparkr-test", fileext = ".csv") + mockLinesCsv <- c("year,make,model,comment,blank", + "\"2012\",\"Tesla\",\"S\",\"No comment\",", + "1997,Ford,E350,\"Go get one now they are going fast\",", + "2015,Chevy,Volt", + "NA,Dummy,Placeholder") + writeLines(mockLinesCsv, csvPath) + + csvDf <- read.df(csvPath, "csv", header = "true", inferSchema = "true") + expected <- read.df(csvPath, "csv", header = TRUE, inferSchema = TRUE) + expect_equal(collect(csvDf), collect(expected)) + + expect_error(read.df(csvPath, "csv", header = TRUE, maxColumns = 3)) + unlink(csvPath) +}) + test_that("convert NAs to null type in DataFrames", { rdd <- parallelize(sc, list(list(1L, 2L), list(NA, 4L))) df <- createDataFrame(rdd, list("a", "b")) @@ -497,6 +514,19 @@ test_that("read/write json files", { unlink(jsonPath3) }) +test_that("read/write json files - compression option", { + df <- read.df(jsonPath, "json") + + jsonPath <- tempfile(pattern = "jsonPath", fileext = ".json") + write.json(df, jsonPath, compression = "gzip") + jsonDF <- read.json(jsonPath) + expect_is(jsonDF, "SparkDataFrame") + expect_equal(count(jsonDF), count(df)) + expect_true(length(list.files(jsonPath, pattern = ".gz")) > 0) + + unlink(jsonPath) +}) + test_that("jsonRDD() on a RDD with json string", { sqlContext <- suppressWarnings(sparkRSQL.init(sc)) rdd <- parallelize(sc, mockLines) @@ -1786,6 +1816,21 @@ test_that("read/write ORC files", { unsetHiveContext() }) +test_that("read/write ORC files - compression option", { + setHiveContext(sc) + df <- read.df(jsonPath, "json") + + orcPath2 <- tempfile(pattern = "orcPath2", fileext = ".orc") + write.orc(df, orcPath2, compression = "ZLIB") + orcDF <- read.orc(orcPath2) + expect_is(orcDF, "SparkDataFrame") + expect_equal(count(orcDF), count(df)) + expect_true(length(list.files(orcPath2, pattern = ".zlib.orc")) > 0) + + unlink(orcPath2) + unsetHiveContext() +}) + test_that("read/write Parquet files", { df <- read.df(jsonPath, "json") # Test write.df and read.df @@ -1817,6 +1862,23 @@ test_that("read/write Parquet files", { unlink(parquetPath4) }) +test_that("read/write Parquet files - compression option/mode", { + df <- read.df(jsonPath, "json") + tempPath <- tempfile(pattern = "tempPath", fileext = ".parquet") + + # Test write.df and read.df + write.parquet(df, tempPath, compression = "GZIP") + df2 <- read.parquet(tempPath) + expect_is(df2, "SparkDataFrame") + expect_equal(count(df2), 3) + expect_true(length(list.files(tempPath, pattern = ".gz.parquet")) > 0) + + write.parquet(df, tempPath, mode = "overwrite") + df3 <- read.parquet(tempPath) + expect_is(df3, "SparkDataFrame") + expect_equal(count(df3), 3) +}) + test_that("read/write text files", { # Test write.df and read.df df <- read.df(jsonPath, "text") @@ -1838,6 +1900,19 @@ test_that("read/write text files", { unlink(textPath2) }) +test_that("read/write text files - compression option", { + df <- read.df(jsonPath, "text") + + textPath <- tempfile(pattern = "textPath", fileext = ".txt") + write.text(df, textPath, compression = "GZIP") + textDF <- read.text(textPath) + expect_is(textDF, "SparkDataFrame") + expect_equal(count(textDF), count(df)) + expect_true(length(list.files(textPath, pattern = ".gz")) > 0) + + unlink(textPath) +}) + test_that("describe() and summarize() on a DataFrame", { df <- read.json(jsonPath) stats <- describe(df, "age") |