[SPARK-16508][SPARKR] Fix CRAN undocumented/duplicated arguments warnings.

This PR tries to fix all the remaining "undocumented/duplicated arguments" warnings given by CRAN-check.

One left is doc for R `stats::glm` exported in SparkR. To mute that warning, we have to also provide document for all arguments of that non-SparkR function.

Some previous conversation is in #14558.

R unit test and `check-cran.sh` script (with no-test).

Author: Junyang Qian <[email protected]>

Closes #14705 from junyangq/SPARK-16508-master.

(cherry picked from commit 01401e9)
Signed-off-by: Shivaram Venkataraman <[email protected]>

Author: junyangq

R/pkg/R/DataFrame.R

@@ -165,9 +165,9 @@ getDefaultSqlSource <- function() {
 #'
 #' Converts R data.frame or list into SparkDataFrame.
 #'
-#' @param data An RDD or list or data.frame
-#' @param schema a list of column names or named list (StructType), optional
-#' @return a SparkDataFrame
+#' @param data an RDD or list or data.frame.
+#' @param schema a list of column names or named list (StructType), optional.
+#' @return A SparkDataFrame.
 #' @rdname createDataFrame
 #' @export
 #' @examples
@@ -257,23 +257,25 @@ createDataFrame.default <- function(data, schema = NULL, samplingRatio = 1.0) {
 }
 
 createDataFrame <- function(x, ...) {
-  dispatchFunc("createDataFrame(data, schema = NULL, samplingRatio = 1.0)", x, ...)
+  dispatchFunc("createDataFrame(data, schema = NULL)", x, ...)
 }
 
+#' @param samplingRatio Currently not used.
 #' @rdname createDataFrame
 #' @aliases createDataFrame
 #' @export
 #' @method as.DataFrame default
 #' @note as.DataFrame since 1.6.0
 as.DataFrame.default <- function(data, schema = NULL, samplingRatio = 1.0) {
-  createDataFrame(data, schema, samplingRatio)
+  createDataFrame(data, schema)
 }
 
+#' @param ... additional argument(s).
 #' @rdname createDataFrame
 #' @aliases as.DataFrame
 #' @export
-as.DataFrame <- function(x, ...) {
-  dispatchFunc("as.DataFrame(data, schema = NULL, samplingRatio = 1.0)", x, ...)
+as.DataFrame <- function(data, ...) {
+  dispatchFunc("as.DataFrame(data, schema = NULL)", data, ...)
 }
 
 #' toDF
@@ -398,7 +400,7 @@ read.orc <- function(path) {
 #'
 #' Loads a Parquet file, returning the result as a SparkDataFrame.
 #'
-#' @param path Path of file to read. A vector of multiple paths is allowed.
+#' @param path path of file to read. A vector of multiple paths is allowed.
 #' @return SparkDataFrame
 #' @rdname read.parquet
 #' @export
@@ -418,6 +420,7 @@ read.parquet <- function(x, ...) {
   dispatchFunc("read.parquet(...)", x, ...)
 }
 
+#' @param ... argument(s) passed to the method.
 #' @rdname read.parquet
 #' @name parquetFile
 #' @export
@@ -727,6 +730,7 @@ dropTempView <- function(viewName) {
 #' @param source The name of external data source
 #' @param schema The data schema defined in structType
 #' @param na.strings Default string value for NA when source is "csv"
+#' @param ... additional external data source specific named properties.
 #' @return SparkDataFrame
 #' @rdname read.df
 #' @name read.df
@@ -791,10 +795,11 @@ loadDF <- function(x, ...) {
 #' If `source` is not specified, the default data source configured by
 #' "spark.sql.sources.default" will be used.
 #'
-#' @param tableName A name of the table
-#' @param path The path of files to load
-#' @param source the name of external data source
-#' @return SparkDataFrame
+#' @param tableName a name of the table.
+#' @param path the path of files to load.
+#' @param source the name of external data source.
+#' @param ... additional argument(s) passed to the method.
+#' @return A SparkDataFrame.
 #' @rdname createExternalTable
 #' @export
 #' @examples
@@ -840,6 +845,7 @@ createExternalTable <- function(x, ...) {
 #'                      clause expressions used to split the column `partitionColumn` evenly.
 #'                      This defaults to SparkContext.defaultParallelism when unset.
 #' @param predicates a list of conditions in the where clause; each one defines one partition
+#' @param ... additional JDBC database connection named propertie(s).
 #' @return SparkDataFrame
 #' @rdname read.jdbc
 #' @name read.jdbc

R/pkg/R/SQLContext.R

@@ -54,8 +54,10 @@ setMethod("show", "WindowSpec",
 #'
 #' Defines the partitioning columns in a WindowSpec.
 #'
-#' @param x a WindowSpec
-#' @return a WindowSpec
+#' @param x a WindowSpec.
+#' @param col a column to partition on (desribed by the name or Column).
+#' @param ... additional column(s) to partition on.
+#' @return A WindowSpec.
 #' @rdname partitionBy
 #' @name partitionBy
 #' @aliases partitionBy,WindowSpec-method
@@ -86,7 +88,7 @@ setMethod("partitionBy",
 #'
 #' Defines the ordering columns in a WindowSpec.
 #' @param x a WindowSpec
-#' @param col a character or Column object indicating an ordering column
+#' @param col a character or Column indicating an ordering column
 #' @param ... additional sorting fields
 #' @return A WindowSpec.
 #' @name orderBy
@@ -192,6 +194,9 @@ setMethod("rangeBetween",
 #'
 #' Define a windowing column.
 #'
+#' @param x a Column, usually one returned by window function(s).
+#' @param window a WindowSpec object. Can be created by `windowPartitionBy` or
+#'        `windowOrderBy` and configured by other WindowSpec methods.
 #' @rdname over
 #' @name over
 #' @aliases over,Column,WindowSpec-method

R/pkg/R/WindowSpec.R

@@ -163,8 +163,9 @@ setMethod("alias",
 #' @family colum_func
 #' @aliases substr,Column-method
 #'
-#' @param start starting position
-#' @param stop ending position
+#' @param x a Column.
+#' @param start starting position.
+#' @param stop ending position.
 #' @note substr since 1.4.0
 setMethod("substr", signature(x = "Column"),
           function(x, start, stop) {
@@ -219,6 +220,7 @@ setMethod("endsWith", signature(x = "Column"),
 #' @family colum_func
 #' @aliases between,Column-method
 #'
+#' @param x a Column
 #' @param bounds lower and upper bounds
 #' @note between since 1.5.0
 setMethod("between", signature(x = "Column"),
@@ -233,6 +235,11 @@ setMethod("between", signature(x = "Column"),
 
 #' Casts the column to a different data type.
 #'
+#' @param x a Column.
+#' @param dataType a character object describing the target data type.
+#'        See
+#'        \href{https://spark.apache.org/docs/latest/sparkr.html#data-type-mapping-between-r-and-spark}{
+#'        Spark Data Types} for available data types.
 #' @rdname cast
 #' @name cast
 #' @family colum_func
@@ -254,10 +261,12 @@ setMethod("cast",
 
 #' Match a column with given values.
 #'
+#' @param x a Column.
+#' @param table a collection of values (coercible to list) to compare with.
 #' @rdname match
 #' @name %in%
 #' @aliases %in%,Column-method
-#' @return a matched values as a result of comparing with given values.
+#' @return A matched values as a result of comparing with given values.
 #' @export
 #' @examples
 #' \dontrun{
@@ -277,6 +286,9 @@ setMethod("%in%",
 #' If values in the specified column are null, returns the value.
 #' Can be used in conjunction with `when` to specify a default value for expressions.
 #'
+#' @param x a Column.
+#' @param value value to replace when the corresponding entry in \code{x} is NA.
+#'              Can be a single value or a Column.
 #' @rdname otherwise
 #' @name otherwise
 #' @family colum_func