From 3859277e16fd308eafb9a3d3c8b3a837622b7a09 Mon Sep 17 00:00:00 2001
From: Lixun Zhang <lxzhang@gmail.com>
Date: Mon, 21 Dec 2015 16:03:40 -0500
Subject: [PATCH 1/2] Add an update.dataset() function

---
 R/datasets.R                   | 36 ++++++++++++++++++++++++++++++++++
 inst/examples/example_update.R | 17 ++++++++++++++++
 2 files changed, 53 insertions(+)
 create mode 100644 inst/examples/example_update.R

diff --git a/R/datasets.R b/R/datasets.R
index f631674..44c5a51 100644
--- a/R/datasets.R
+++ b/R/datasets.R
@@ -228,3 +228,39 @@ delete.datasets <- function(ws, name, host){
   refresh(ws, "datasets")
   ans
 }
+
+#' Update an existing R data frame in an AzureML workspace.
+#'
+#' Update an existing R data frame to an AzureML workspace using the \code{GenericTSV} format.
+#' 
+#' @inheritParams refresh
+#' @param x An R data frame object
+#' @param name A character name for an existing AzureML dataset
+#' @param description An optional character description of the dataset, description for the existing dataset will be used if none provided here
+#' @param family_id An optional AzureML family identifier, family identifier for the existing dataset will be used if none provided here
+#' @param ... Optional additional options passed to \code{write.table}
+#' @note The additional \code{\link[utils]{write.table}} options may not include \code{sep} or \code{row.names} or \code{file}, but any other options are accepted.
+#' 
+#' @return A single-row data frame of "Datasets" class that corresponds to the updated object now available in ws$datasets.
+#' @importFrom curl curl_escape new_handle handle_setheaders handle_reset handle_setopt curl_fetch_memory
+#' @importFrom jsonlite fromJSON
+#' @export
+#' @family dataset functions
+#' @example inst/examples/example_update.R
+
+update.dataset <- function(x, ws, name, description = "", family_id="", ...)
+{
+  # use description and family_id from the existing dataset if no new values are provided
+  if (description == "") description = ws$datasets$Description[ws$datasets$Name == name]
+  if (family_id == "") family_id = ws$datasets$FamilyId[ws$datasets$Name == name]
+  
+  # delete existing data and save status
+  dr <- delete.datasets(ws, name)
+  
+  # take care of exceptions from delete: dataset does not exist or it's Microsoft dataset
+  if (dim(dr)[1] == 0) stop("The dataset named '", name, "' does not exist")
+  else if (dr$Deleted == FALSE) stop("Update not allowed for Microsoft default datasets") 
+  
+  # upload
+  upload.dataset(x, ws, name, description, family_id)
+}
\ No newline at end of file
diff --git a/inst/examples/example_update.R b/inst/examples/example_update.R
new file mode 100644
index 0000000..2a8dc13
--- /dev/null
+++ b/inst/examples/example_update.R
@@ -0,0 +1,17 @@
+\dontrun{
+  library(AzureML)
+  
+  ws <- workspace()
+  
+  # Upload the R airquality data.frame to the workspace.
+  upload.dataset(airquality, ws, "airquality")
+
+  # Make an update by using only the first 10 rows
+  update.dataset(airquality[1:10, ], ws, "airquality")
+  
+  # Download the updated dataset to check its content
+  download.datasets(ws, name = "airquality")
+
+  # Now delete what we've just uploaded
+  delete.datasets(ws, "airquality")
+}

From 8331e6368d6a454133ecbcaf39be0525a33500e2 Mon Sep 17 00:00:00 2001
From: Lixun Zhang <lxzhang@gmail.com>
Date: Tue, 22 Dec 2015 11:12:12 -0500
Subject: [PATCH 2/2] Modify update.dataset() function to 1)make sure of data
 type GenericTSV and 2) check data existence before deletion

---
 R/datasets.R | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/R/datasets.R b/R/datasets.R
index 44c5a51..a766a89 100644
--- a/R/datasets.R
+++ b/R/datasets.R
@@ -248,19 +248,23 @@ delete.datasets <- function(ws, name, host){
 #' @family dataset functions
 #' @example inst/examples/example_update.R
 
-update.dataset <- function(x, ws, name, description = "", family_id="", ...)
+update.dataset <- function(x, ws, name, description = "", family_id = "", ...)
 {
+
+  # take care of exceptions from delete: it's Microsoft dataset or dataset does not exist
+  if (name %in% datasets(ws, filter = "samples")$Name) stop("Update not allowed for Microsoft sample datasets.") 
+  else if (!(name %in% datasets(ws, filter = "my datasets")$Name)) stop("The dataset named '", name, "' does not exist.")
+  
+  # check to make sure the existing file is in GenericTSV format
+  if (tolower(ws$datasets$DataTypeId[ws$datasets$Name == name]) != "generictsv") stop("The existing dataset is not of type GenericTSV.")
+  
   # use description and family_id from the existing dataset if no new values are provided
   if (description == "") description = ws$datasets$Description[ws$datasets$Name == name]
   if (family_id == "") family_id = ws$datasets$FamilyId[ws$datasets$Name == name]
   
-  # delete existing data and save status
+  # delete existing data
   dr <- delete.datasets(ws, name)
   
-  # take care of exceptions from delete: dataset does not exist or it's Microsoft dataset
-  if (dim(dr)[1] == 0) stop("The dataset named '", name, "' does not exist")
-  else if (dr$Deleted == FALSE) stop("Update not allowed for Microsoft default datasets") 
-  
   # upload
   upload.dataset(x, ws, name, description, family_id)
-}
\ No newline at end of file
+}