From d9d354ed40eec56b3f03d32f4e2629d367b1bf02 Mon Sep 17 00:00:00 2001
From: Yanbo Liang <ybliang8@gmail.com>
Date: Thu, 10 Dec 2015 10:18:58 -0800
Subject: [SPARK-12234][SPARKR] Fix ```subset``` function error when only set
 ```select``` argument

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 #10217 from yanboliang/spark-12234.
---
 R/pkg/R/DataFrame.R                       | 9 +++++++--
 R/pkg/inst/tests/testthat/test_sparkSQL.R | 4 ++++
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'R/pkg')

diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
index 81b4e6b91d..f4c4a2585e 100644
--- 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
index 222c04a32c..2051784427 100644
--- 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)
 })
-- 
cgit v1.2.3