Revive stringsAsFactors option for collect() in SparkR

Author: HyukjinKwon

R/pkg/R/DataFrame.R

@@ -1191,6 +1191,9 @@ setMethod("collect",
                     vec <- do.call(c, col)
                     stopifnot(class(vec) != "list")
                     class(vec) <- PRIMITIVE_TYPES[[colType]]
+                    if (stringsAsFactors && is.character(vec)) {
+                      vec <- as.factor(vec)
+                    }
                     df[[colIndex]] <- vec
                   } else {
                     df[[colIndex]] <- col

R/pkg/tests/fulltests/test_sparkSQL.R

@@ -499,6 +499,12 @@ test_that("create DataFrame with different data types", {
   expect_equal(collect(df), data.frame(l, stringsAsFactors = FALSE))
 })
 
+test_that("SPARK-17902: collect() with stringsAsFactors enabled", {
+  df <- suppressWarnings(collect(createDataFrame(iris), stringsAsFactors = TRUE))
+  expect_equal(class(iris$Species), class(df$Species))
+  expect_equal(iris$Species, df$Species)
+})
+
 test_that("SPARK-17811: can create DataFrame containing NA as date and time", {
   df <- data.frame(
     id = 1:2,