GH-51655: [R] Advance long-standing deprecations in map_batches() and pull()

r/NEWS.md

@@ -19,13 +19,23 @@
 
 # arrow 25.0.1.9000
 
+## Breaking changes
+
+- The `.data.frame` argument to `map_batches()`, deprecated since 9.0.0, has
+  been removed. Call `collect()` on the result to get a data frame (#51655).
+
 ## Minor improvements and fixes
 
 - Factor levels inside list columns are now unified across the whole column
   when converting to R, so data read in multiple batches (e.g. via
   `read_ipc_stream()` or `open_dataset()`) produces valid factors that can be
   unnested. Similarly, `int64` and `uint32` values inside list columns are
   converted to a single R type across the column (#50514).
+- `pull()` on Arrow data no longer warns about a future change of default.
+  The planned switch to returning a `ChunkedArray` has been dropped, so
+  `pull()` will keep returning an R vector by default; use
+  `as_vector = FALSE` or `options(arrow.pull_as_vector = FALSE)` to get a
+  `ChunkedArray` (#51655).
 
 # arrow 25.0.1
 

r/R/arrow-package.R

@@ -56,10 +56,9 @@ supported_dplyr_methods <- list(
   rename = NULL,
   pull = c(
     "the `name` argument is not supported;",
-    "returns an R vector by default but this behavior is deprecated and will",
-    "return an Arrow [ChunkedArray] in a future release. Provide",
-    "`as_vector = TRUE/FALSE` to control this behavior, or set",
-    "`options(arrow.pull_as_vector)` globally."
+    "returns an R vector by default. Provide `as_vector = FALSE`",
+    "to return an Arrow [ChunkedArray] instead, or set",
+    "`options(arrow.pull_as_vector = FALSE)` globally."
   ),
   relocate = NULL,
   compute = NULL,

r/R/dataset-scan.R

@@ -220,17 +220,9 @@ tail_from_batches <- function(batches, n) {
 #'   the result; use `FALSE` to evaluate `FUN` on all batches before returning
 #'   the reader.
 #' @param ... Additional arguments passed to `FUN`
-#' @param .data.frame Deprecated argument, ignored
 #' @return An `arrow_dplyr_query`.
 #' @export
-map_batches <- function(X, FUN, ..., .schema = NULL, .lazy = TRUE, .data.frame = NULL) {
-  if (!is.null(.data.frame)) {
-    warning(
-      "The .data.frame argument is deprecated. ",
-      "Call collect() on the result to get a data.frame.",
-      call. = FALSE
-    )
-  }
+map_batches <- function(X, FUN, ..., .schema = NULL, .lazy = TRUE) {
   FUN <- as_mapper(FUN)
   reader <- as_record_batch_reader(X)
   dots <- list2(...)

r/R/dplyr-collect.R

@@ -56,7 +56,7 @@ compute.arrow_dplyr_query <- function(x, ...) {
 }
 compute.Dataset <- compute.RecordBatchReader <- compute.arrow_dplyr_query
 
-pull.Dataset <- function(.data, var = -1, ..., as_vector = getOption("arrow.pull_as_vector")) {
+pull.Dataset <- function(.data, var = -1, ..., as_vector = getOption("arrow.pull_as_vector", TRUE)) {
   .data <- as_adq(.data)
   var <- vars_pull(names(.data), !!enquo(var))
   .data$selected_columns <- set_names(.data$selected_columns[var], var)
@@ -65,32 +65,12 @@ pull.Dataset <- function(.data, var = -1, ..., as_vector = getOption("arrow.pull
 }
 pull.RecordBatchReader <- pull.arrow_dplyr_query <- pull.Dataset
 
-pull.ArrowTabular <- function(x, var = -1, ..., as_vector = getOption("arrow.pull_as_vector")) {
+pull.ArrowTabular <- function(x, var = -1, ..., as_vector = getOption("arrow.pull_as_vector", TRUE)) {
   out <- x[[vars_pull(names(x), !!enquo(var))]]
   handle_pull_as_vector(out, as_vector)
 }
 
 handle_pull_as_vector <- function(out, as_vector) {
-  if (is.null(as_vector)) {
-    warn(
-      c(
-        paste(
-          "Default behavior of `pull()` on Arrow data is changing. Current",
-          "behavior of returning an R vector is deprecated, and in a future",
-          "release, it will return an Arrow `ChunkedArray`. To control this:"
-        ),
-        i = paste(
-          "Specify `as_vector = TRUE` (the current default) or",
-          "`FALSE` (what it will change to) in `pull()`"
-        ),
-        i = "Or, set `options(arrow.pull_as_vector)` globally"
-      ),
-      .frequency = "regularly",
-      .frequency_id = "arrow.pull_as_vector",
-      class = "lifecycle_warning_deprecated"
-    )
-    as_vector <- TRUE
-  }
   if (as_vector) {
     out <- as.vector(out)
   }

r/R/dplyr-funcs-doc.R

@@ -55,7 +55,7 @@
 #' * [`inner_join()`][dplyr::inner_join()]: the `copy` argument is ignored
 #' * [`left_join()`][dplyr::left_join()]: the `copy` argument is ignored
 #' * [`mutate()`][dplyr::mutate()]
-#' * [`pull()`][dplyr::pull()]: the `name` argument is not supported; returns an R vector by default but this behavior is deprecated and will return an Arrow [ChunkedArray] in a future release. Provide `as_vector = TRUE/FALSE` to control this behavior, or set `options(arrow.pull_as_vector)` globally.
+#' * [`pull()`][dplyr::pull()]: the `name` argument is not supported; returns an R vector by default. Provide `as_vector = FALSE` to return an Arrow [ChunkedArray] instead, or set `options(arrow.pull_as_vector = FALSE)` globally.
 #' * [`relocate()`][dplyr::relocate()]
 #' * [`rename()`][dplyr::rename()]
 #' * [`rename_with()`][dplyr::rename_with()]

r/tests/testthat/helper-arrow.R

@@ -29,10 +29,6 @@ Sys.setlocale("LC_COLLATE", "C")
 # (R CMD check does this, but in case you're running outside of check)
 Sys.setenv(LANGUAGE = "en")
 
-# Set this option so that the deprecation warning isn't shown
-# (except when we test for it)
-options(arrow.pull_as_vector = FALSE)
-
 with_language <- function(lang, expr) {
   skip_on_cran()
   skip_if_not(capabilities("NLS"))

r/tests/testthat/test-dplyr-query.R

@@ -94,17 +94,6 @@ test_that("pull", {
   )
 })
 
-test_that("pull() shows a deprecation warning if the option isn't set", {
-  expect_warning(
-    vec <- tbl |>
-      arrow_table() |>
-      pull(as_vector = NULL),
-    "Current behavior of returning an R vector is deprecated"
-  )
-  # And the default is the old behavior, an R vector
-  expect_identical(vec, pull(tbl))
-})
-
 test_that("collect(as_data_frame=FALSE)", {
   batch <- record_batch(tbl)
 
@@ -761,3 +750,18 @@ test_that("nested field ref error handling", {
     "No match"
   )
 })
+
+test_that("pull() returns an R vector by default", {
+  withr::local_options(arrow.pull_as_vector = NULL)
+  tab <- arrow_table(tbl)
+
+  expect_no_warning(out <- pull(tab, int))
+  expect_identical(out, tbl$int)
+  expect_no_warning(out <- pull(tab |> filter(int > 4), int))
+  expect_identical(out, tbl$int[!is.na(tbl$int) & tbl$int > 4])
+
+  expect_r6_class(pull(tab, int, as_vector = FALSE), "ChunkedArray")
+
+  withr::local_options(arrow.pull_as_vector = FALSE)
+  expect_r6_class(pull(tab, int), "ChunkedArray")
+})