GH-47106: [R] Update R package to use R 4.1+ native forward pipe syntax

r/R/dataset-write.R

@@ -105,8 +105,8 @@
 #' # output directory will be different.
 #' library(dplyr)
 #' two_levels_tree_2 <- tempfile()
-#' mtcars %>%
-#'   group_by(cyl, gear) %>%
+#' mtcars |>
+#'   group_by(cyl, gear) |>
 #'   write_dataset(two_levels_tree_2)
 #' list.files(two_levels_tree_2, recursive = TRUE)
 #'
@@ -115,8 +115,8 @@
 #'
 #' # Write a structure X/Y/part-Z.parquet.
 #' two_levels_tree_no_hive <- tempfile()
-#' mtcars %>%
-#'   group_by(cyl, gear) %>%
+#' mtcars |>
+#'   group_by(cyl, gear) |>
 #'   write_dataset(two_levels_tree_no_hive, hive_style = FALSE)
 #' list.files(two_levels_tree_no_hive, recursive = TRUE)
 #' @export

r/R/dplyr-funcs-augmented.R

@@ -28,16 +28,16 @@
 #' augmented column.
 #'
 #' @examples \dontrun{
-#' open_dataset("nyc-taxi") %>% mutate(
+#' open_dataset("nyc-taxi") |> mutate(
 #'   file =
 #'     add_filename()
 #' )
 #'
 #' # To use a verb like mutate() with add_filename() we need to first call
 #' # compute()
-#' open_dataset("nyc-taxi") %>%
-#'   mutate(file = add_filename()) %>%
-#'   compute() %>%
+#' open_dataset("nyc-taxi") |>
+#'   mutate(file = add_filename()) |>
+#'   compute() |>
 #'   mutate(filename_length = nchar(file))
 #' }
 #'

r/R/dplyr-funcs-type.R

@@ -38,8 +38,8 @@ register_bindings_type <- function() {
 #'
 #' @examples
 #' \dontrun{
-#' mtcars %>%
-#'   arrow_table() %>%
+#' mtcars |>
+#'   arrow_table() |>
 #'   mutate(cyl = cast(cyl, string()))
 #' }
 #' @keywords internal

r/R/dplyr-summarize.R

@@ -57,8 +57,8 @@ do_arrow_summarize <- function(.data, ..., .groups = NULL) {
   # and aggregations, but that's not how Acero works. For example, for us to do
   #   summarize(mean = sum(x) / n())
   # we basically have to translate it into
-  #   summarize(..temp0 = sum(x), ..temp1 = n()) %>%
-  #   mutate(mean = ..temp0 / ..temp1) %>%
+  #   summarize(..temp0 = sum(x), ..temp1 = n()) |>
+  #   mutate(mean = ..temp0 / ..temp1) |>
   #   select(-starts_with("..temp"))
   # That is, "first aggregate, then transform the result further."
   #
@@ -97,7 +97,7 @@ do_arrow_summarize <- function(.data, ..., .groups = NULL) {
     # One last check: it's possible that an expression like y - mean(y) would
     # successfully evaluate, but it's not supported. It gets transformed to:
     # nolint start
-    #   summarize(..temp0 = mean(y)) %>%
+    #   summarize(..temp0 = mean(y)) |>
     #   mutate(y - ..temp0)
     # nolint end
     # but y is not in the schema of the data after summarize(). To catch this

r/R/dplyr.R

@@ -279,10 +279,10 @@ tail.arrow_dplyr_query <- function(x, n = 6L, ...) {
 #'
 #' @examplesIf arrow_with_dataset() && requireNamespace("dplyr", quietly = TRUE)
 #' library(dplyr)
-#' mtcars %>%
-#'   arrow_table() %>%
-#'   filter(mpg > 20) %>%
-#'   mutate(x = gear / carb) %>%
+#' mtcars |>
+#'   arrow_table() |>
+#'   filter(mpg > 20) |>
+#'   mutate(x = gear / carb) |>
 #'   show_exec_plan()
 show_exec_plan <- function(x) {
   result <- as_record_batch_reader(as_adq(x))

r/R/duckdb.R

@@ -45,10 +45,10 @@
 #'
 #' ds <- InMemoryDataset$create(mtcars)
 #'
-#' ds %>%
-#'   filter(mpg < 30) %>%
-#'   group_by(cyl) %>%
-#'   to_duckdb() %>%
+#' ds |>
+#'   filter(mpg < 30) |>
+#'   group_by(cyl) |>
+#'   to_duckdb() |>
 #'   slice_min(disp)
 to_duckdb <- function(.data,
                       con = arrow_duck_connection(),
@@ -154,12 +154,12 @@ duckdb_disconnector <- function(con, tbl_name) {
 #'
 #' ds <- InMemoryDataset$create(mtcars)
 #'
-#' ds %>%
-#'   filter(mpg < 30) %>%
-#'   to_duckdb() %>%
-#'   group_by(cyl) %>%
-#'   summarize(mean_mpg = mean(mpg, na.rm = TRUE)) %>%
-#'   to_arrow() %>%
+#' ds |>
+#'   filter(mpg < 30) |>
+#'   to_duckdb() |>
+#'   group_by(cyl) |>
+#'   summarize(mean_mpg = mean(mpg, na.rm = TRUE)) |>
+#'   to_arrow() |>
 #'   collect()
 to_arrow <- function(.data) {
   # If this is an Arrow object already, return quickly since we're already Arrow

r/R/type.R

@@ -408,11 +408,11 @@ NestedType <- R6Class("NestedType", inherit = DataType)
 #' # You can also use `cast()` in an Arrow dplyr query.
 #' if (requireNamespace("dplyr", quietly = TRUE)) {
 #'   library(dplyr, warn.conflicts = FALSE)
-#'   arrow_table(mtcars) %>%
+#'   arrow_table(mtcars) |>
 #'     transmute(
 #'       col1 = cast(cyl, string()),
 #'       col2 = cast(cyl, int8())
-#'     ) %>%
+#'     ) |>
 #'     compute()
 #' }
 int8 <- function() Int8__initialize()

r/R/udf.R

@@ -66,9 +66,9 @@
 #'   auto_convert = TRUE
 #' )
 #'
-#' as_arrow_table(mtcars) %>%
-#'   transmute(mpg, mpg_predicted = mtcars_predict_mpg(disp, cyl)) %>%
-#'   collect() %>%
+#' as_arrow_table(mtcars) |>
+#'   transmute(mpg, mpg_predicted = mtcars_predict_mpg(disp, cyl)) |>
+#'   collect() |>
 #'   head()
 #'
 register_scalar_function <- function(name, fun, in_type, out_type,

r/data-raw/codegen.R

@@ -41,13 +41,13 @@ suppressPackageStartupMessages({
 })
 
 get_exported_functions <- function(decorations, export_tag) {
-  out <- decorations %>%
-    filter(decoration %in% paste0(export_tag, "::export")) %>%
-    mutate(functions = map(context, decor:::parse_cpp_function)) %>%
+  out <- decorations |>
+    filter(decoration %in% paste0(export_tag, "::export")) |>
+    mutate(functions = map(context, decor:::parse_cpp_function)) |>
     {
       vec_cbind(., vec_rbind(!!!pull(., functions)))
-    } %>%
-    select(-functions) %>%
+    } |>
+    select(-functions) |>
     mutate(decoration = sub("::export", "", decoration))
   message(glue("*** > {n} functions decorated with [[{tags}::export]]", n = nrow(out), tags = paste0(export_tag, collapse = "|")))
   out
@@ -123,8 +123,8 @@ extern "C" SEXP {sexp_signature}{{
 #endif\n\n')
 }
 
-cpp_functions_definitions <- arrow_exports %>%
-  select(name, return_type, args, file, line, decoration) %>%
+cpp_functions_definitions <- arrow_exports |>
+  select(name, return_type, args, file, line, decoration) |>
   pmap_chr(function(name, return_type, args, file, line, decoration) {
     sexp_params <- glue_collapse_data(args, "SEXP {name}_sexp")
     sexp_signature <- glue("_arrow_{name}({sexp_params})")
@@ -147,14 +147,14 @@ cpp_functions_definitions <- arrow_exports %>%
     ",
       sep = "\n"
     )
-  }) %>%
+  }) |>
   glue_collapse(sep = "\n")
 
-cpp_functions_registration <- arrow_exports %>%
-  select(name, return_type, args) %>%
+cpp_functions_registration <- arrow_exports |>
+  select(name, return_type, args) |>
   pmap_chr(function(name, return_type, args) {
     glue('\t\t{{ "_arrow_{name}", (DL_FUNC) &_arrow_{name}, {nrow(args)}}}, ')
-  }) %>%
+  }) |>
   glue_collapse(sep = "\n")
 
 cpp_file_header <- '// Generated by using data-raw/codegen.R -> do not edit by hand
@@ -198,8 +198,8 @@ static const R_CallMethodDef CallEntries[] = {
 
 write_if_modified(arrow_exports_cpp, "src/arrowExports.cpp")
 
-r_functions <- arrow_exports %>%
-  select(name, return_type, args) %>%
+r_functions <- arrow_exports |>
+  select(name, return_type, args) |>
   pmap_chr(function(name, return_type, args) {
     params <- if (nrow(args)) {
       paste0(", ", glue_collapse_data(args, "{name}"))
@@ -220,7 +220,7 @@ r_functions <- arrow_exports %>%
       list_params = glue_collapse_data(args, "{name}"),
       sep = "\n"
     )
-  }) %>%
+  }) |>
   glue_collapse(sep = "\n")
 
 arrow_exports_r <- glue::glue("

r/data-raw/docgen.R

@@ -115,8 +115,8 @@ render_fun <- function(fun, pkg_fun, notes) {
 
 # This renders a bulleted list under a package heading
 render_pkg <- function(df, pkg) {
-  bullets <- df %>%
-    transmute(render_fun(fun, pkg_fun, notes)) %>%
+  bullets <- df |>
+    transmute(render_fun(fun, pkg_fun, notes)) |>
     pull()
   header <- paste0("## ", pkg, "\n#'")
   # Some packages have global notes to include
@@ -158,7 +158,7 @@ docs <- c(docs, setNames(rep(list(NULL), length(tidyselect)), tidyselect))
 fun_df <- tibble::tibble(
   pkg_fun = names(docs),
   notes = docs
-) %>%
+) |>
   mutate(
     has_pkg = grepl("::", pkg_fun),
     fun = sub("^.*?:{+}", "", pkg_fun),
@@ -167,7 +167,7 @@ fun_df <- tibble::tibble(
     pkg = if_else(has_pkg, pkg, "base"),
     # Flatten notes to a single string
     notes = map_chr(notes, ~ paste(., collapse = "\n#' "))
-  ) %>%
+  ) |>
   arrange(pkg, fun)
 
 # Group by package name and render the lists
@@ -182,13 +182,13 @@ dplyr_verbs <- c(
 verb_bullets <- tibble::tibble(
   fun = names(dplyr_verbs),
   notes = dplyr_verbs
-) %>%
+) |>
   mutate(
     pkg_fun = paste0("dplyr::", fun),
     notes = map_chr(notes, ~ paste(., collapse = " "))
-  ) %>%
-  arrange(fun) %>%
-  transmute(render_fun(fun, pkg_fun, notes)) %>%
+  ) |>
+  arrange(fun) |>
+  transmute(render_fun(fun, pkg_fun, notes)) |>
   pull()
 
 writeLines(

r/tests/testthat/_snaps/dataset-dplyr.md

@@ -1,7 +1,7 @@
 # dplyr method not implemented messages
 
     Code
-      ds %>% filter(int > 6, dbl > max(dbl))
+      filter(ds, int > 6, dbl > max(dbl))
     Condition
       Error in `dbl > max(dbl)`:
       ! Expression not supported in filter() in Arrow

r/tests/testthat/_snaps/dplyr-across.md

@@ -1,7 +1,7 @@
 # expand_across correctly expands quosures
 
     Code
-      InMemoryDataset$create(example_data) %>% mutate(across(c(dbl, dbl2), round,
+      mutate(InMemoryDataset$create(example_data), across(c(dbl, dbl2), round,
       digits = -1))
     Condition
       Error in `mutate.Dataset()`:

r/tests/testthat/_snaps/dplyr-funcs-datetime.md

@@ -1,8 +1,8 @@
 # `as.Date()` and `as_date()`
 
     Code
-      test_df %>% InMemoryDataset$create() %>% transmute(date_char_ymd = as.Date(
-        character_ymd_var, tryFormats = c("%Y-%m-%d", "%Y/%m/%d"))) %>% collect()
+      collect(transmute(InMemoryDataset$create(test_df), date_char_ymd = as.Date(
+        character_ymd_var, tryFormats = c("%Y-%m-%d", "%Y/%m/%d"))))
     Condition
       Error in `as.Date()`:
       ! `as.Date()` with multiple `tryFormats` not supported in Arrow

r/tests/testthat/_snaps/dplyr-glimpse.md

@@ -86,7 +86,7 @@
 # glimpse() calls print() instead of showing data for RBR
 
     Code
-      example_data %>% as_record_batch_reader() %>% glimpse()
+      glimpse(as_record_batch_reader(example_data))
     Message
       Cannot glimpse() data from a RecordBatchReader because it can only be read one time; call `as_arrow_table()` to consume it first.
     Output
@@ -103,7 +103,7 @@
 ---
 
     Code
-      example_data %>% as_record_batch_reader() %>% select(int) %>% glimpse()
+      glimpse(select(as_record_batch_reader(example_data), int))
     Message
       Cannot glimpse() data from a RecordBatchReader because it can only be read one time. Call `compute()` to evaluate the query first.
     Output
@@ -131,7 +131,7 @@
 # glimpse() on Dataset query only shows data for streaming eval
 
     Code
-      ds %>% summarize(max(int)) %>% glimpse()
+      glimpse(summarize(ds, max(int)))
     Message
       This query requires a full table scan, so glimpse() may be expensive. Call `compute()` to evaluate the query first.
     Output
@@ -143,8 +143,7 @@
 # glimpse() on in-memory query shows data even if aggregating
 
     Code
-      example_data %>% arrow_table() %>% summarize(sum(int, na.rm = TRUE)) %>%
-        glimpse()
+      glimpse(summarize(arrow_table(example_data), sum(int, na.rm = TRUE)))
     Output
       Table (query)
       ?? rows x 1 columns

r/tests/testthat/_snaps/dplyr-mutate.md

@@ -1,8 +1,8 @@
 # transmute() defuses dots arguments (ARROW-13262)
 
     Code
-      tbl %>% Table$create() %>% transmute(a = stringr::str_c(padded_strings,
-        padded_strings), b = stringr::str_squish(a)) %>% collect()
+      collect(transmute(Table$create(tbl), a = stringr::str_c(padded_strings,
+        padded_strings), b = stringr::str_squish(a)))
     Condition
       Warning:
       In stringr::str_squish(a): 

r/tests/testthat/_snaps/dplyr-summarize.md

@@ -1,7 +1,7 @@
 # Functions that take ... but we only accept a single arg
 
     Code
-      InMemoryDataset$create(tbl) %>% summarize(distinct = n_distinct())
+      summarize(InMemoryDataset$create(tbl), distinct = n_distinct())
     Condition
       Error in `n_distinct()`:
       ! n_distinct() with 0 arguments not supported in Arrow
@@ -16,7 +16,7 @@
 # Expressions on aggregations
 
     Code
-      record_batch(tbl) %>% summarise(any(any(lgl)))
+      summarise(record_batch(tbl), any(any(lgl)))
     Condition
       Warning:
       In any(any(lgl)): 
@@ -31,8 +31,8 @@
 # Can use across() within summarise()
 
     Code
-      data.frame(x = 1, y = 2) %>% arrow_table() %>% group_by(x) %>% summarise(across(
-        everything())) %>% collect()
+      collect(summarise(group_by(arrow_table(data.frame(x = 1, y = 2)), x), across(
+        everything())))
     Condition
       Warning:
       In y: