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

Jump to bottom

[SPARK-12198] [SparkR] SparkR support read.parquet and deprecate parquetFile #10191

Closed
wants to merge 2 commits into from
Closed

[SPARK-12198] [SparkR] SparkR support read.parquet and deprecate parquetFile #10191

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e507c31
SparkR support read.parquet and deprecate parquetFile
yanboliang Dec 8, 2015
9e0fd63
reorder namespace
yanboliang Dec 9, 2015
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
1 change: 1 addition & 0 deletions R/pkg/NAMESPACE
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,6 +270,7 @@ export("as.DataFrame",
"loadDF",
"parquetFile",
"read.df",
"read.parquet",
"sql",
"table",
"tableNames",
Expand Down
16 changes: 14 additions & 2 deletions R/pkg/R/SQLContext.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,18 +256,30 @@ jsonRDD <- function(sqlContext, rdd, schema = NULL, samplingRatio = 1.0) {
}
}


#' Create a DataFrame from a Parquet file.
#'
#' Loads a Parquet file, returning the result as a DataFrame.
#'
#' @param sqlContext SQLContext to use
#' @param ... Path(s) of parquet file(s) to read.
#' @param path Path of file to read. A vector of multiple paths is allowed.
#' @return DataFrame
#' @rdname read.parquet
#' @name read.parquet
#' @export
read.parquet <- function(sqlContext, path) {
# Allow the user to have a more flexible definiton of the text file path
paths <- as.list(suppressWarnings(normalizePath(path)))
read <- callJMethod(sqlContext, "read")
sdf <- callJMethod(read, "parquet", paths)
dataFrame(sdf)
}

#' @rdname read.parquet
#' @name parquetFile
#' @export
# TODO: Implement saveasParquetFile and write examples for both
parquetFile <- function(sqlContext, ...) {
.Deprecated("read.parquet")
# Allow the user to have a more flexible definiton of the text file path
paths <- lapply(list(...), function(x) suppressWarnings(normalizePath(x)))
sdf <- callJMethod(sqlContext, "parquetFile", paths)
Expand Down
11 changes: 7 additions & 4 deletions R/pkg/inst/tests/testthat/test_sparkSQL.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1420,22 +1420,25 @@ test_that("mutate(), transform(), rename() and names()", {
detach(airquality)
})

test_that("write.df() on DataFrame and works with parquetFile", {
test_that("write.df() on DataFrame and works with read.parquet", {
df <- jsonFile(sqlContext, jsonPath)
write.df(df, parquetPath, "parquet", mode="overwrite")
parquetDF <- parquetFile(sqlContext, parquetPath)
parquetDF <- read.parquet(sqlContext, parquetPath)
expect_is(parquetDF, "DataFrame")
expect_equal(count(df), count(parquetDF))
})

test_that("parquetFile works with multiple input paths", {
test_that("read.parquet()/parquetFile() works with multiple input paths", {
df <- jsonFile(sqlContext, jsonPath)
write.df(df, parquetPath, "parquet", mode="overwrite")
parquetPath2 <- tempfile(pattern = "parquetPath2", fileext = ".parquet")
write.df(df, parquetPath2, "parquet", mode="overwrite")
parquetDF <- parquetFile(sqlContext, parquetPath, parquetPath2)
parquetDF <- read.parquet(sqlContext, c(parquetPath, parquetPath2))
expect_is(parquetDF, "DataFrame")
expect_equal(count(parquetDF), count(df) * 2)
parquetDF2 <- suppressWarnings(parquetFile(sqlContext, parquetPath, parquetPath2))
expect_is(parquetDF2, "DataFrame")
expect_equal(count(parquetDF2), count(df) * 2)

# Test if varargs works with variables
saveMode <- "overwrite"
Expand Down