modified: pkg/R/RDD.R

Author: hqzizania

pkg/NAMESPACE

@@ -6,6 +6,7 @@ exportMethods(
               "checkpoint",
               "cogroup",
               "collect",
+              "collectAsMap",
               "collectPartition",
               "combineByKey",
               "count",

pkg/R/RDD.R

@@ -358,6 +358,7 @@ setMethod("collect",
             convertJListToRList(collected, flatten)
           })
 
+
 #' @rdname collect-methods
 #' @export
 #' @description
@@ -382,6 +383,29 @@ setMethod("collectPartition",
             convertJListToRList(jList, flatten = TRUE)
           })
 
+#' @rdname collect-methods
+#' @export
+#' @description
+#' \code{collectAsMap} returns a named list as a map that contains all of the elements
+#' in a key-value pair RDD. 
+#' @examples
+#'\dontrun{
+#' sc <- sparkR.init()
+#' rdd <- parallelize(sc, list(list(1, 2),list(3, 4)), 2L)
+#' collectAsMap(rdd) # list(`1` = 2, `3` = 4)
+#'}
+setGeneric("collectAsMap", function(rdd) { standardGeneric("collectAsMap") })
+
+#' @rdname collect-methods
+#' @aliases collectAsMap,RDD-method
+setMethod("collectAsMap",
+          signature(rdd = "RDD"),
+          function(rdd) {
+            pairList <- collect(rdd)
+            map <- new.env()
+            lapply(pairList, function(x) { assign(as.character(x[[1]]), x[[2]], envir = map) })
+            as.list(map)
+          })
 
 #' Look up elements of a key in an RDD
 #'

pkg/man/collect-methods.Rd

@@ -1,8 +1,11 @@
-% Generated by roxygen2 (4.0.2): do not edit by hand
+% Generated by roxygen2 (4.1.0): do not edit by hand
+% Please edit documentation in R/RDD.R
 \docType{methods}
 \name{collect}
 \alias{collect}
 \alias{collect,RDD-method}
+\alias{collectAsMap}
+\alias{collectAsMap,RDD-method}
 \alias{collectPartition}
 \alias{collectPartition,RDD,integer-method}
 \alias{collectPartition,integer,RDD-method}
@@ -15,6 +18,10 @@ collect(rdd, ...)
 collectPartition(rdd, partitionId)
 
 \S4method{collectPartition}{RDD,integer}(rdd, partitionId)
+
+collectAsMap(rdd)
+
+\S4method{collectAsMap}{RDD}(rdd)
 }
 \arguments{
 \item{rdd}{The RDD to collect}
@@ -24,15 +31,22 @@ collectPartition(rdd, partitionId)
 \item{flatten}{FALSE if the list should not flattened}
 
 \item{partitionId}{the partition to collect (starts from 0)}
+
+\item{rdd}{The RDD to collect as a map}
 }
 \value{
 a list containing elements in the RDD
+
+a named list containing elements in the RDD
 }
 \description{
 \code{collect} returns a list that contains all of the elements in this RDD.
 
 \code{collectPartition} returns a list that contains all of the elements
 in the specified partition of the RDD.
+
+\code{collectAsMap} returns a named list as a map that contains all of the elements
+in this key-value pair RDD.
 }
 \examples{
 \dontrun{
@@ -41,5 +55,10 @@ rdd <- parallelize(sc, 1:10, 2L)
 collect(rdd) # list from 1 to 10
 collectPartition(rdd, 0L) # list from 1 to 5
 }
+\dontrun{
+sc <- sparkR.init()
+rdd <- parallelize(sc, list(list(1, 2),list(3, 4)), 2L)
+collectAsMap(rdd) # list(`1` = 2, `3` = 4)
+}
 }