Don't duplicate grouping variables in distinct

Fixes #354
tidyverse · Sep 24, 2020 · 74260eb · 74260eb
1 parent 0bf2176
commit 74260eb
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 1 deletion.
diff --git a/NEWS.md b/NEWS.md
@@ -1,5 +1,7 @@
 # dbplyr (development version)
 
+* `distinct()` no longer duplicates column if grouped (#354).
+
 * `mutate()` grouping variables no longer generates a downstream error (#396)
 
 * `mutate()` correctly generates subqueries when you re-use the same variable

diff --git a/R/verb-distinct.R b/R/verb-distinct.R
@@ -17,7 +17,7 @@ distinct.tbl_lazy <- function(.data, ..., .keep_all = FALSE) {
 
 #' @export
 op_vars.op_distinct <- function(op) {
-  c(op_grps(op$x), op_vars(op$x))
+  union(op_grps(op$x), op_vars(op$x))
 }
 
 #' @export

diff --git a/tests/testthat/test-verb-distinct.R b/tests/testthat/test-verb-distinct.R
@@ -26,6 +26,11 @@ test_that("distinct throws error if column is specified and .keep_all is TRUE",
   expect_snapshot_error(mf %>% distinct(x, .keep_all = TRUE) %>% collect())
 })
 
+test_that("distinct doesn't duplicate colum names if grouped (#354)", {
+  df <- lazy_frame(a = 1)
+  expect_equal(df %>% group_by(a) %>% distinct() %>% op_vars(), "a")
+})
+
 # sql-render --------------------------------------------------------------
 
 test_that("distinct adds DISTINCT suffix", {