[SPARK-12234][SPARKR] Fix subset function error when only set select argument

yanboliang · shivaram · commit 93ef24638209 · 2015-12-10T10:19:06.000-08:00
Fix ```subset``` function error when only set ```select``` argument. Please refer to the [JIRA](https://issues.apache.org/jira/browse/SPARK-12234) about the error and how to reproduce it. cc sun-rui felixcheung shivaram Author: Yanbo Liang <ybliang8@gmail.com> Closes apache#10217 from yanboliang/spark-12234. (cherry picked from commit d9d354e) Signed-off-by: Shivaram Venkataraman <shivaram@cs.berkeley.edu>
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
@@ -1185,7 +1185,7 @@ setMethod("[", signature(x = "DataFrame", i = "Column"),
 #'
 #' Return subsets of DataFrame according to given conditions
 #' @param x A DataFrame
-#' @param subset A logical expression to filter on rows
+#' @param subset (Optional) A logical expression to filter on rows
 #' @param select expression for the single Column or a list of columns to select from the DataFrame
 #' @return A new DataFrame containing only the rows that meet the condition with selected columns
 #' @export
@@ -1206,10 +1206,15 @@ setMethod("[", signature(x = "DataFrame", i = "Column"),
 #'   df[df$age %in% c(19, 30), 1:2]
 #'   subset(df, df$age %in% c(19, 30), 1:2)
 #'   subset(df, df$age %in% c(19), select = c(1,2))
+#'   subset(df, select = c(1,2))
 #' }
 setMethod("subset", signature(x = "DataFrame"),
           function(x, subset, select, ...) {
-            x[subset, select, ...]
+            if (missing(subset)) {
+              x[, select, ...]
+            } else {
+              x[subset, select, ...]
+            }
           })
 
 #' Select
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R
@@ -799,6 +799,10 @@ test_that("subsetting", {
   expect_equal(count(df6), 1)
   expect_equal(columns(df6), c("name", "age"))
 
+  df7 <- subset(df, select = "name")
+  expect_equal(count(df7), 3)
+  expect_equal(columns(df7), c("name"))
+
   # Test base::subset is working
   expect_equal(nrow(subset(airquality, Temp > 80, select = c(Ozone, Temp))), 68)
 })
