santosh-d3vpl3x commented on code in PR #37526:
URL: https://github.com/apache/spark/pull/37526#discussion_r946754596
##########
R/pkg/R/DataFrame.R:
##########
@@ -3577,40 +3577,90 @@ setMethod("str",
#' This is a no-op if schema doesn't contain column name(s).
#'
#' @param x a SparkDataFrame.
-#' @param col a character vector of column names or a Column.
-#' @param ... further arguments to be passed to or from other methods.
-#' @return A SparkDataFrame.
+#' @param col a list of columns or single Column or name.
+#' @param ... additional column(s) if only one column is specified in
\code{col}.
+#' If more than one column is assigned in \code{col}, \code{...}
+#' should be left empty.
+#' @return A new SparkDataFrame with selected columns.
#'
#' @family SparkDataFrame functions
#' @rdname drop
#' @name drop
-#' @aliases drop,SparkDataFrame-method
+#' @aliases drop,SparkDataFrame,character-method
+#' @family subsetting functions
#' @examples
-#'\dontrun{
-#' sparkR.session()
-#' path <- "path/to/file.json"
-#' df <- read.json(path)
-#' drop(df, "col1")
-#' drop(df, c("col1", "col2"))
-#' drop(df, df$col1)
+#' \dontrun{
+#' drop(df, "*")
+#' drop(df, "col1", "col2")
+#' drop(df, df$name, df$age + 1)
+#' drop(df, c("col1", "col2"))
+#' drop(df, list(df$name, df$age + 1))
#' }
-#' @note drop since 2.0.0
-setMethod("drop",
- signature(x = "SparkDataFrame"),
- function(x, col) {
- stopifnot(class(col) == "character" || class(col) == "Column")
+#' @note drop(SparkDataFrame, character) since 2.0.0
+setMethod("drop", signature(x = "SparkDataFrame", col = "character"),
+ function(x, col, ...) {
+ if (length(col) > 1) {
+ if (length(list(...)) > 0) {
+ stop("To drop multiple columns, use a character vector or list
for col")
+ }
- if (class(col) == "Column") {
- sdf <- callJMethod(x@sdf, "drop", col@jc)
+ drop(x, as.list(col))
} else {
- sdf <- callJMethod(x@sdf, "drop", as.list(col))
+ sdf <- callJMethod(x@sdf, "drop", list(col, ...))
+ dataFrame(sdf)
}
+ })
+
+#' @rdname drop
+#' @aliases drop,SparkDataFrame,Column-method
+#' @note drop(SparkDataFrame, Column) since 2.0.0
+setMethod("drop", signature(x = "SparkDataFrame", col = "Column"),
+ function(x, col, ...) {
+ jcols <- lapply(list(col, ...), function(c) {
+ c@jc
+ })
+ sdf <- callJMethod(x@sdf, "drop", jcols[[1]], jcols[-1])
dataFrame(sdf)
})
-# Expose base::drop
-#' @name drop
#' @rdname drop
+#' @aliases drop,SparkDataFrame,list-method
+#' @note drop(SparkDataFrame, list) since 3.4.0
+setMethod("drop",
+ signature(x = "SparkDataFrame", col = "list"),
+ function(x, col) {
+ cols <- lapply(col, function(c) {
+ if (class(c) == "Column") {
+ c@jc
+ } else {
+ col(c)@jc
+ }
+ })
+ sdf <- callJMethod(x@sdf, "drop", cols[[1]], cols[-1])
+ dataFrame(sdf)
+ })
+
+#' Expose base::drop which deletes the dimensions of an array which have only
one level.
Review Comment:
Now [Run / Linters, licenses, dependencies and documentation
generation](https://github.com/santosh-d3vpl3x/spark/runs/7857027573?check_suite_focus=true#logs)
errors out with following:
```
-- Building function reference
-------------------------------------------------
Error in check_missing_topics(rows, pkg) :
All topics must be included in reference index
✖ Missing topics: drop,ANY,ANY-method
ℹ Either add to _pkgdown.yml or use @keyword internal
Error:
! error in callr subprocess
Caused by error in `check_missing_topics(rows, pkg)`:
! All topics must be included in reference index
✖ Missing topics: drop,ANY,ANY-method
ℹ Either add to _pkgdown.yml or use @keyword internal
```
@HyukjinKwon would you know what is the best way to deal with this?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
