This is an automated email from the ASF dual-hosted git repository.
npr pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/master by this push:
new a01b0c20c7 MINOR: [R] Cleanup skips and TODOs (#13576)
a01b0c20c7 is described below
commit a01b0c20c7e2c3283cf195de38372b998dbf17d5
Author: Neal Richardson <[email protected]>
AuthorDate: Tue Jul 12 09:02:40 2022 -0400
MINOR: [R] Cleanup skips and TODOs (#13576)
Authored-by: Neal Richardson <[email protected]>
Signed-off-by: Neal Richardson <[email protected]>
---
r/R/array.R | 6 ---
r/R/arrow-datum.R | 16 +++++--
r/R/chunked-array.R | 12 ------
r/R/compute.R | 1 -
r/R/dplyr-datetime-helpers.R | 20 ++++-----
r/R/dplyr-distinct.R | 3 +-
r/R/dplyr-funcs-datetime.R | 5 +--
r/R/dplyr-summarize.R | 1 -
r/src/altrep.cpp | 1 -
r/tests/testthat/test-compute-arith.R | 6 +--
r/tests/testthat/test-compute-sort.R | 4 +-
r/tests/testthat/test-dplyr-collapse.R | 12 ++++--
r/tests/testthat/test-dplyr-distinct.R | 2 +-
r/tests/testthat/test-dplyr-filter.R | 10 -----
r/tests/testthat/test-dplyr-funcs-datetime.R | 63 +++++++++++++++-------------
r/tests/testthat/test-dplyr-funcs-type.R | 3 +-
r/tests/testthat/test-dplyr-mutate.R | 2 +-
r/tests/testthat/test-dplyr-summarize.R | 2 +-
r/tools/autobrew | 3 +-
19 files changed, 76 insertions(+), 96 deletions(-)
diff --git a/r/R/array.R b/r/R/array.R
index 89e9fbfa33..9ae7631e7d 100644
--- a/r/R/array.R
+++ b/r/R/array.R
@@ -155,12 +155,6 @@ Array <- R6Class("Array",
assert_is(i, "Array")
call_function("filter", self, i, options = list(keep_na = keep_na))
},
- SortIndices = function(descending = FALSE) {
- assert_that(is.logical(descending))
- assert_that(length(descending) == 1L)
- assert_that(!is.na(descending))
- call_function("array_sort_indices", self, options = list(order =
descending))
- },
RangeEquals = function(other, start_idx, end_idx, other_start_idx = 0L) {
assert_is(other, "Array")
Array__RangeEquals(self, other, start_idx, end_idx, other_start_idx)
diff --git a/r/R/arrow-datum.R b/r/R/arrow-datum.R
index 39362628bb..8632ca3053 100644
--- a/r/R/arrow-datum.R
+++ b/r/R/arrow-datum.R
@@ -26,6 +26,16 @@ ArrowDatum <- R6Class("ArrowDatum",
opts <- cast_options(safe, ...)
opts$to_type <- as_type(target_type)
call_function("cast", self, options = opts)
+ },
+ SortIndices = function(descending = FALSE) {
+ assert_that(is.logical(descending))
+ assert_that(length(descending) == 1L)
+ assert_that(!is.na(descending))
+ call_function(
+ "sort_indices",
+ self,
+ options = list(names = "", orders = as.integer(descending))
+ )
}
)
)
@@ -55,8 +65,8 @@ is.na.ArrowDatum <- function(x) {
#' @export
is.nan.ArrowDatum <- function(x) {
if (x$type_id() %in% TYPES_WITH_NAN) {
- # TODO: if an option is added to the is_nan kernel to treat NA as NaN,
- # use that to simplify the code here (ARROW-13366)
+ # TODO(ARROW-13366): if an option is added to the is_nan kernel to treat NA
+ # as NaN, use that to simplify the code here
call_function("is_nan", x) & call_function("is_valid", x)
} else {
Scalar$create(FALSE)$as_array(length(x))
@@ -336,7 +346,7 @@ sort.ArrowDatum <- function(x, decreasing = FALSE, na.last
= NA, ...) {
# Arrow always sorts nulls at the end of the array. This corresponds to
# sort(na.last = TRUE). For the other two cases (na.last = NA and
# na.last = FALSE) we need to use workarounds.
- # TODO: Implement this more cleanly after ARROW-12063
+ # TODO(ARROW-14085): use NullPlacement ArraySortOptions instead of this
workaround
if (is.na(na.last)) {
# Filter out NAs before sorting
x <- x$Filter(!is.na(x))
diff --git a/r/R/chunked-array.R b/r/R/chunked-array.R
index 24ca7e6e58..c16f562017 100644
--- a/r/R/chunked-array.R
+++ b/r/R/chunked-array.R
@@ -113,18 +113,6 @@ ChunkedArray <- R6Class("ChunkedArray",
}
call_function("filter", self, i, options = list(keep_na = keep_na))
},
- SortIndices = function(descending = FALSE) {
- assert_that(is.logical(descending))
- assert_that(length(descending) == 1L)
- assert_that(!is.na(descending))
- # TODO: after ARROW-12042 is closed, review whether this and the
- # Array$SortIndices definition can be consolidated
- call_function(
- "sort_indices",
- self,
- options = list(names = "", orders = as.integer(descending))
- )
- },
View = function(type) {
ChunkedArray__View(self, as_type(type))
},
diff --git a/r/R/compute.R b/r/R/compute.R
index 3ce598c22c..1cd12f2e29 100644
--- a/r/R/compute.R
+++ b/r/R/compute.R
@@ -97,7 +97,6 @@ list_compute_functions <- function(pattern = NULL, ...) {
if (!is.null(pattern)) {
funcs <- grep(pattern, funcs, value = TRUE, ...)
}
- # TODO: Filtering of hash funcs will already happen in C++ with ARROW-13943
funcs <- grep(
"^hash_",
funcs,
diff --git a/r/R/dplyr-datetime-helpers.R b/r/R/dplyr-datetime-helpers.R
index 7099d79c78..af2f1deef8 100644
--- a/r/R/dplyr-datetime-helpers.R
+++ b/r/R/dplyr-datetime-helpers.R
@@ -39,6 +39,7 @@ check_time_locale <- function(locale =
Sys.getlocale("LC_TIME")) {
"dnanoseconds" = list(1, "ns")
)
make_duration <- function(x, unit) {
+ # TODO(ARROW-15862): remove first cast to int64
x <- build_expr("cast", x, options = cast_options(to_type = int64()))
x$cast(duration(unit))
}
@@ -49,9 +50,7 @@ binding_format_datetime <- function(x, format = "", tz = "",
usetz = FALSE) {
}
if (call_binding("is.POSIXct", x)) {
- # the casting part might not be required once
- # https://issues.apache.org/jira/browse/ARROW-14442 is solved
- # TODO revisit the steps below once the PR for that issue is merged
+ # Make sure the timezone is reflected
if (tz == "" && x$type()$timezone() != "") {
tz <- x$type()$timezone()
} else if (tz == "") {
@@ -59,8 +58,8 @@ binding_format_datetime <- function(x, format = "", tz = "",
usetz = FALSE) {
}
x <- build_expr("cast", x, options = cast_options(to_type =
timestamp(x$type()$unit(), tz)))
}
-
- build_expr("strftime", x, options = list(format = format, locale =
Sys.getlocale("LC_TIME")))
+ opts <- list(format = format, locale = Sys.getlocale("LC_TIME"))
+ build_expr("strftime", x, options = opts)
}
# this is a helper function used for creating a difftime / duration objects
from
@@ -104,7 +103,6 @@ binding_as_date <- function(x,
format = NULL,
tryFormats = "%Y-%m-%d",
origin = "1970-01-01") {
-
if (call_binding("is.Date", x)) {
return(x)
@@ -132,16 +130,15 @@ binding_as_date_numeric <- function(x, origin =
"1970-01-01") {
# Arrow does not support direct casting from double to date32(), but for
# integer-like values we can go via int32()
- # https://issues.apache.org/jira/browse/ARROW-15798
- # TODO revisit if arrow decides to support double -> date casting
+ # TODO: revisit after ARROW-15798
if (!call_binding("is.integer", x)) {
x <- build_expr("cast", x, options = cast_options(to_type = int32()))
}
if (origin != "1970-01-01") {
delta_in_sec <- call_binding("difftime", origin, "1970-01-01")
- # TODO revisit once https://issues.apache.org/jira/browse/ARROW-15862
- # (casting from int32 -> duration or double -> duration) is addressed
+ # TODO: revisit after ARROW-15862
+ # (casting from int32 -> duration or double -> duration)
delta_in_days <- (delta_in_sec$cast(int64()) / 86400L)$cast(int32())
x <- build_expr("+", x, delta_in_days)
}
@@ -292,7 +289,6 @@ build_format_from_order <- function(order) {
#' * `augmented_x_qy`
#' @noRd
process_data_for_parsing <- function(x, orders) {
-
processed_x <- x$cast(string())
# make all separators (non-letters and non-numbers) into "-"
@@ -302,7 +298,7 @@ process_data_for_parsing <- function(x, orders) {
# we need to transform `x` when orders are `ym`, `my`, and `yq`
# for `ym` and `my` orders we add a day ("01")
- # TODO revisit after https://issues.apache.org/jira/browse/ARROW-16627
+ # TODO: revisit after ARROW-16627
augmented_x_ym <- NULL
if (any(orders %in% c("ym", "my", "Ym", "mY"))) {
# add day as "-01" if there is a "-" separator and as "01" if not
diff --git a/r/R/dplyr-distinct.R b/r/R/dplyr-distinct.R
index d5a8c81e6b..c663d84e65 100644
--- a/r/R/dplyr-distinct.R
+++ b/r/R/dplyr-distinct.R
@@ -19,7 +19,8 @@
distinct.arrow_dplyr_query <- function(.data, ..., .keep_all = FALSE) {
if (.keep_all == TRUE) {
- # After ARROW-13993 is merged, we can implement this (ARROW-14045)
+ # TODO(ARROW-14045): the function is called "hash_one" (from ARROW-13993)
+ # May need to call it: `summarize(x = one(x), ...)` for x in non-group cols
arrow_not_supported("`distinct()` with `.keep_all = TRUE`")
}
diff --git a/r/R/dplyr-funcs-datetime.R b/r/R/dplyr-funcs-datetime.R
index f7d948fdf2..df830a6b66 100644
--- a/r/R/dplyr-funcs-datetime.R
+++ b/r/R/dplyr-funcs-datetime.R
@@ -297,7 +297,6 @@ register_bindings_datetime_conversion <- function() {
tryFormats = "%Y-%m-%d",
origin = "1970-01-01",
tz = "UTC") {
-
if (is.null(format) && length(tryFormats) > 1) {
abort(
paste(
@@ -461,8 +460,7 @@ register_bindings_duration <- function() {
# numeric -> duration not supported in Arrow yet so we use int64() as an
# intermediate step
- # TODO revisit if https://issues.apache.org/jira/browse/ARROW-15862 results
- # in numeric -> duration support
+ # TODO: revisit after ARROW-15862
if (call_binding("is.numeric", x)) {
# coerce x to be int64(). it should work for integer-like doubles and
fail
@@ -567,7 +565,6 @@ register_bindings_datetime_parsers <- function() {
} else {
coalesce_output
}
-
})
ymd_parser_vec <- c("ymd", "ydm", "mdy", "myd", "dmy", "dym", "ym", "my",
"yq")
diff --git a/r/R/dplyr-summarize.R b/r/R/dplyr-summarize.R
index 59b6533742..9226c476cb 100644
--- a/r/R/dplyr-summarize.R
+++ b/r/R/dplyr-summarize.R
@@ -280,7 +280,6 @@ do_arrow_summarize <- function(.data, ..., .groups = NULL) {
} else {
stop(paste("Invalid .groups argument:", .groups))
}
- # TODO: shouldn't we be doing something with `drop_empty_groups` in
summarize? (ARROW-14044)
out$drop_empty_groups <- .data$drop_empty_groups
}
out
diff --git a/r/src/altrep.cpp b/r/src/altrep.cpp
index 33fe09d398..f0cd33fa95 100644
--- a/r/src/altrep.cpp
+++ b/r/src/altrep.cpp
@@ -85,7 +85,6 @@ const std::shared_ptr<ChunkedArray>& GetChunkedArray(SEXP
alt) {
}
struct ArrayResolve {
- // TODO: ARROW-11989
ArrayResolve(const std::shared_ptr<ChunkedArray>& chunked_array, int64_t i) {
for (int idx_chunk = 0; idx_chunk < chunked_array->num_chunks();
idx_chunk++) {
std::shared_ptr<Array> chunk = chunked_array->chunk(idx_chunk);
diff --git a/r/tests/testthat/test-compute-arith.R
b/r/tests/testthat/test-compute-arith.R
index 02681c2585..1f3432363f 100644
--- a/r/tests/testthat/test-compute-arith.R
+++ b/r/tests/testthat/test-compute-arith.R
@@ -129,9 +129,9 @@ test_that("Power", {
test_that("Dates casting", {
a <- Array$create(c(Sys.Date() + 1:4, NA_integer_))
- skip("ARROW-11090 (date/datetime arithmetic)")
- # Error: NotImplemented: Function add_checked has no kernel matching input
types (array[date32[day]], scalar[double])
- expect_equal(a + 2, Array$create(c((Sys.Date() + 1:4) + 2), NA_integer_))
+ skip("ARROW-17043 (date/datetime arithmetic with integers)")
+ # Error: NotImplemented: Function 'add_checked' has no kernel matching input
types (timestamp[s], int32)
+ expect_equal(a + 2L, Array$create(c((Sys.Date() + 1:4) + 2), NA_integer_))
})
test_that("Unary Ops group generics work on Array objects", {
diff --git a/r/tests/testthat/test-compute-sort.R
b/r/tests/testthat/test-compute-sort.R
index e3574d86f7..f521efeddc 100644
--- a/r/tests/testthat/test-compute-sort.R
+++ b/r/tests/testthat/test-compute-sort.R
@@ -39,7 +39,7 @@ test_that("Array$SortIndices()", {
Array$create(int)$SortIndices(),
Array$create(order(int) - 1L, type = uint64())
)
- # Need to remove NAs because ARROW-12063
+ # TODO(ARROW-14085): remove workaround once NA behavior is supported
int <- na.omit(int)
expect_equal(
Array$create(int)$SortIndices(descending = TRUE),
@@ -57,7 +57,7 @@ test_that("ChunkedArray$SortIndices()", {
ChunkedArray$create(int[1:4], int[5:length(int)])$SortIndices(),
Array$create(order(int) - 1L, type = uint64())
)
- # Need to remove NAs because ARROW-12063
+ # TODO(ARROW-14085): remove workaround once NA behavior is supported
int <- na.omit(int)
expect_equal(
ChunkedArray$create(int[1:4], int[5:length(int)])$SortIndices(descending =
TRUE),
diff --git a/r/tests/testthat/test-dplyr-collapse.R
b/r/tests/testthat/test-dplyr-collapse.R
index 746c4aa074..3c121780da 100644
--- a/r/tests/testthat/test-dplyr-collapse.R
+++ b/r/tests/testthat/test-dplyr-collapse.R
@@ -195,12 +195,18 @@ See $.data for the source Arrow object",
# Component "total": Mean relative difference: 0.9230769
# Component "extra": Mean relative difference: 0.9230769
expect_equal(
- q %>% head(1) %>% collect(),
+ q %>%
+ arrange(lgl) %>%
+ head(1) %>%
+ collect(),
tibble::tibble(lgl = FALSE, total = 8L, extra = 40)
)
- skip("TODO (ARROW-1XXXX): implement sorting option about where NAs go")
+ skip("TODO (ARROW-16630): make sure BottomK can handle NA ordering")
expect_equal(
- q %>% tail(1) %>% collect(),
+ q %>%
+ arrange(lgl) %>%
+ tail(1) %>%
+ collect(),
tibble::tibble(lgl = NA, total = 25L, extra = 125)
)
})
diff --git a/r/tests/testthat/test-dplyr-distinct.R
b/r/tests/testthat/test-dplyr-distinct.R
index 876c192ec3..8b42614084 100644
--- a/r/tests/testthat/test-dplyr-distinct.R
+++ b/r/tests/testthat/test-dplyr-distinct.R
@@ -93,7 +93,7 @@ test_that("distinct() can contain expressions", {
})
test_that("distinct() can return all columns", {
- skip("ARROW-13993 - need this to return correct rows from other cols")
+ skip("ARROW-14045")
compare_dplyr_binding(
.input %>%
distinct(lgl, .keep_all = TRUE) %>%
diff --git a/r/tests/testthat/test-dplyr-filter.R
b/r/tests/testthat/test-dplyr-filter.R
index 12b2a47f4a..60c740a5c1 100644
--- a/r/tests/testthat/test-dplyr-filter.R
+++ b/r/tests/testthat/test-dplyr-filter.R
@@ -399,14 +399,4 @@ test_that("filter() with .data pronoun", {
collect(),
tbl
)
-
- skip("test now faulty - code no longer gives error & outputs a empty tibble")
- # but there is an error if we don't override the masking with `.env`
- compare_dplyr_error(
- .input %>%
- filter(.data$dbl > chr) %>%
- select(.data$chr, .data$int, .data$lgl) %>%
- collect(),
- tbl
- )
})
diff --git a/r/tests/testthat/test-dplyr-funcs-datetime.R
b/r/tests/testthat/test-dplyr-funcs-datetime.R
index 94855fd7d6..ca70de41d0 100644
--- a/r/tests/testthat/test-dplyr-funcs-datetime.R
+++ b/r/tests/testthat/test-dplyr-funcs-datetime.R
@@ -25,7 +25,7 @@ library(dplyr, warn.conflicts = FALSE)
# base::strptime() defaults to local timezone
# but arrow's strptime defaults to UTC.
# So that tests are consistent, set the local timezone to UTC
-# TODO: consider reevaluating this workaround after ARROW-12980
+# TODO: consider reevaluating now that ARROW-12980 has merged
withr::local_timezone("UTC")
if (tolower(Sys.info()[["sysname"]]) == "windows") {
@@ -37,8 +37,7 @@ test_date <- as.POSIXct("2017-01-01 00:00:11.3456789", tz =
"Pacific/Marquesas")
test_df <- tibble::tibble(
# test_date + 1 turns the tzone = "" to NULL, which is functionally
equivalent
- # so we can run some tests on Windows, but this skirts around
- # https://issues.apache.org/jira/browse/ARROW-13588
+ # so we can run some tests on Windows, but this skirts around ARROW-13588.
# That issue is tough because in C++, "" is the "no timezone" value
# due to static typing, so we can't distinguish a literal "" from NULL
datetime = c(test_date, NA) + 1,
@@ -743,7 +742,7 @@ test_that("leap_year mirror lubridate", {
"1998-01-01", # not leap year
"1996-01-01", # leap year (divide by 4 rule)
"1900-01-01", # not leap year (divide by 100 rule)
- "2000-01-01" # leap year (divide by 400 rule)
+ "2000-01-01" # leap year (divide by 400 rule)
))
)
)
@@ -941,7 +940,7 @@ test_that("date works in arrow", {
# we can't (for now) use namespacing, so we need to make sure
lubridate::date()
# and not base::date() is being used. This is due to the way testthat runs
and
# normal use of arrow would not have to do this explicitly.
- # TODO remove once https://issues.apache.org/jira/browse/ARROW-14575 is done
+ # TODO: remove after ARROW-14575
date <- lubridate::date
compare_dplyr_binding(
@@ -1584,7 +1583,7 @@ test_that("`as.Date()` and `as_date()`", {
# strptime does not support a partial format - Arrow returns NA, while
# lubridate parses correctly
- # TODO revisit once - https://issues.apache.org/jira/browse/ARROW-15813
+ # TODO: revisit after ARROW-15813
expect_error(
expect_equal(
test_df %>%
@@ -1611,16 +1610,13 @@ test_that("`as.Date()` and `as_date()`", {
)
# we do not support as.Date() with double/ float (error surfaced from C++)
- # TODO revisit after https://issues.apache.org/jira/browse/ARROW-15798
+ # TODO: revisit after ARROW-15798
expect_error(
test_df %>%
arrow_table() %>%
mutate(date_double = as.Date(double_var, origin = "1970-01-01")) %>%
collect()
)
-
- # we do not support as_date with double/ float (error surfaced from C++)
- # TODO: revisit after https://issues.apache.org/jira/browse/ARROW-15798
expect_error(
test_df %>%
arrow_table() %>%
@@ -1742,8 +1738,7 @@ test_that("parse_date_time() works with year, month, and
date components", {
)
)
- # locale (affecting "%b% and "%B" formats) does not work properly on Windows
- # TODO revisit once https://issues.apache.org/jira/browse/ARROW-16443 is done
+ # TODO(ARROW-16443): locale (affecting "%b% and "%B") does not work on
Windows
skip_on_os("windows")
compare_dplyr_binding(
.input %>%
@@ -1893,7 +1888,6 @@ test_that("ym, my & yq parsers", {
})
test_that("lubridate's fast_strptime", {
-
compare_dplyr_binding(
.input %>%
mutate(
@@ -2032,7 +2026,7 @@ test_that("parse_date_time with hours, minutes and
seconds components", {
dmy_hms_string =
c("09-01-67 12:34:56", "22-05-1970 20:13:59", "220887201359", NA),
dmy_hm_string =
- c("09-01-67 12:34", "22-05-1970 20:13", "2208872013", NA),
+ c("09-01-67 12:34", "22-05-1970 20:13", "2208872013", NA),
dmy_h_string =
c("09-01-67 12", "22-05-1970 20", "22088720", NA),
mdy_hms_string =
@@ -2110,15 +2104,14 @@ test_that("parse_date_time with hours, minutes and
seconds components", {
) %>%
collect(),
tibble(
- ymd_ims_string =
- c("67-01-09 9:34:56", "1970-05-22 10:13:59", "19870822171359", NA)
- )
+ ymd_ims_string =
+ c("67-01-09 9:34:56", "1970-05-22 10:13:59", "19870822171359", NA)
+ )
)
})
test_that("parse_date_time with month names and HMS", {
- # locale (affecting "%b% and "%B" formats) does not work properly on Windows
- # TODO revisit once https://issues.apache.org/jira/browse/ARROW-16443 is done
+ # TODO(ARROW-16443): locale (affecting "%b% and "%B") does not work on
Windows
skip_on_os("windows")
# these functions' internals use some string processing which requires the
@@ -2197,7 +2190,7 @@ test_that("parse_date_time with truncated formats", {
# RE2 library (not available on Windows with R 3.6)
skip_if_not_available("re2")
- test_truncation_df <- tibble(
+ test_truncation_df <- tibble(
truncated_ymd_string =
c(
"2022-05-19 13:46:51",
@@ -2290,22 +2283,26 @@ test_that("build_formats() and
build_format_from_order()", {
"%m%y%d", "%B%y%d", "%b%y%d", "%m%Y%d", "%B%Y%d", "%b%Y%d",
# formats from "%Y-%d-%m" format
"%y-%d-%m", "%Y-%d-%m", "%y-%d-%B", "%Y-%d-%B", "%y-%d-%b", "%Y-%d-%b",
- "%y%d%m", "%Y%d%m", "%y%d%B", "%Y%d%B", "%y%d%b", "%Y%d%b")
+ "%y%d%m", "%Y%d%m", "%y%d%B", "%Y%d%B", "%y%d%b", "%Y%d%b"
+ )
)
expect_equal(
build_formats("ymd_HMS"),
- c("%y-%m-%d-%H-%M-%S", "%Y-%m-%d-%H-%M-%S", "%y-%B-%d-%H-%M-%S",
+ c(
+ "%y-%m-%d-%H-%M-%S", "%Y-%m-%d-%H-%M-%S", "%y-%B-%d-%H-%M-%S",
"%Y-%B-%d-%H-%M-%S", "%y-%b-%d-%H-%M-%S", "%Y-%b-%d-%H-%M-%S",
"%y%m%d%H%M%S", "%Y%m%d%H%M%S", "%y%B%d%H%M%S", "%Y%B%d%H%M%S",
- "%y%b%d%H%M%S", "%Y%b%d%H%M%S")
+ "%y%b%d%H%M%S", "%Y%b%d%H%M%S"
+ )
)
# when order is one of "yq", "qy", "ym" or"my" the data is augmented to "ymd"
# or "ydm" and the formats are built accordingly
ymd_formats <- c(
"%y-%m-%d", "%Y-%m-%d", "%y-%B-%d", "%Y-%B-%d", "%y-%b-%d", "%Y-%b-%d",
- "%y%m%d", "%Y%m%d", "%y%B%d", "%Y%B%d", "%y%b%d", "%Y%b%d")
+ "%y%m%d", "%Y%m%d", "%y%B%d", "%Y%B%d", "%y%b%d", "%Y%b%d"
+ )
expect_equal(
build_formats("yq"),
ymd_formats
@@ -2329,8 +2326,10 @@ test_that("build_formats() and
build_format_from_order()", {
expect_equal(
build_formats("my"),
- c("%m-%y-%d", "%B-%y-%d", "%b-%y-%d", "%m-%Y-%d", "%B-%Y-%d", "%b-%Y-%d",
- "%m%y%d", "%B%y%d", "%b%y%d", "%m%Y%d", "%B%Y%d", "%b%Y%d")
+ c(
+ "%m-%y-%d", "%B-%y-%d", "%b-%y-%d", "%m-%Y-%d", "%B-%Y-%d", "%b-%Y-%d",
+ "%m%y%d", "%B%y%d", "%b%y%d", "%m%Y%d", "%B%Y%d", "%b%Y%d"
+ )
)
# ab not supported yet
@@ -2346,15 +2345,19 @@ test_that("build_formats() and
build_format_from_order()", {
expect_equal(
build_format_from_order("ymd"),
- c("%y-%m-%d", "%Y-%m-%d", "%y-%B-%d", "%Y-%B-%d", "%y-%b-%d", "%Y-%b-%d",
- "%y%m%d", "%Y%m%d", "%y%B%d", "%Y%B%d", "%y%b%d", "%Y%b%d")
+ c(
+ "%y-%m-%d", "%Y-%m-%d", "%y-%B-%d", "%Y-%B-%d", "%y-%b-%d", "%Y-%b-%d",
+ "%y%m%d", "%Y%m%d", "%y%B%d", "%Y%B%d", "%y%b%d", "%Y%b%d"
+ )
)
expect_equal(
build_format_from_order("ymdHMS"),
- c("%y-%m-%d-%H-%M-%S", "%Y-%m-%d-%H-%M-%S", "%y-%B-%d-%H-%M-%S",
+ c(
+ "%y-%m-%d-%H-%M-%S", "%Y-%m-%d-%H-%M-%S", "%y-%B-%d-%H-%M-%S",
"%Y-%B-%d-%H-%M-%S", "%y-%b-%d-%H-%M-%S", "%Y-%b-%d-%H-%M-%S",
"%y%m%d%H%M%S", "%Y%m%d%H%M%S", "%y%B%d%H%M%S", "%Y%B%d%H%M%S",
- "%y%b%d%H%M%S", "%Y%b%d%H%M%S")
+ "%y%b%d%H%M%S", "%Y%b%d%H%M%S"
+ )
)
})
diff --git a/r/tests/testthat/test-dplyr-funcs-type.R
b/r/tests/testthat/test-dplyr-funcs-type.R
index 57561fb08b..7ee0ec4d0f 100644
--- a/r/tests/testthat/test-dplyr-funcs-type.R
+++ b/r/tests/testthat/test-dplyr-funcs-type.R
@@ -806,8 +806,7 @@ test_that("nested structs can be created from scalars and
existing data frames",
})
test_that("format date/time", {
- # locale issues
- # TODO revisit after https://issues.apache.org/jira/browse/ARROW-16399 is
done
+ # TODO(ARROW-16399): remove this workaround
if (tolower(Sys.info()[["sysname"]]) == "windows") {
withr::local_locale(LC_TIME = "C")
}
diff --git a/r/tests/testthat/test-dplyr-mutate.R
b/r/tests/testthat/test-dplyr-mutate.R
index a746335940..beb893afec 100644
--- a/r/tests/testthat/test-dplyr-mutate.R
+++ b/r/tests/testthat/test-dplyr-mutate.R
@@ -365,7 +365,7 @@ test_that("dplyr::mutate's examples", {
# The mutate operation may yield different results on grouped
# tibbles because the expressions are computed within groups.
# The following normalises `mass` by the global average:
- # TODO: ARROW-13926
+ # TODO(ARROW-13926): support window functions
compare_dplyr_binding(
.input %>%
select(name, mass, species) %>%
diff --git a/r/tests/testthat/test-dplyr-summarize.R
b/r/tests/testthat/test-dplyr-summarize.R
index 73e3312ee0..5ad7425ee8 100644
--- a/r/tests/testthat/test-dplyr-summarize.R
+++ b/r/tests/testthat/test-dplyr-summarize.R
@@ -548,7 +548,6 @@ test_that("min() and max() on character strings", {
collect(),
tbl,
)
- skip("Strings not supported by hash_min_max (ARROW-13988)")
compare_dplyr_binding(
.input %>%
group_by(fct) %>%
@@ -556,6 +555,7 @@ test_that("min() and max() on character strings", {
min_chr = min(chr, na.rm = TRUE),
max_chr = max(chr, na.rm = TRUE)
) %>%
+ arrange(min_chr) %>%
collect(),
tbl,
)
diff --git a/r/tools/autobrew b/r/tools/autobrew
index 37a94472bd..ea46be2c0d 100644
--- a/r/tools/autobrew
+++ b/r/tools/autobrew
@@ -60,8 +60,7 @@ for FILE in $BREWDIR/Cellar/*/*/lib/*.a; do
PKG_LIBS=`echo $PKG_LIBS | sed "s/-l$LIBNAME/-lbrew$LIBNAME/g"`
done
-# TODO: add -DARROW_R_WITH_GCS
-PKG_CFLAGS="-I$BREWDIR/opt/$PKG_BREW_NAME/include -DARROW_R_WITH_PARQUET
-DARROW_R_WITH_DATASET -DARROW_R_WITH_JSON -DARROW_R_WITH_S3"
+PKG_CFLAGS="-I$BREWDIR/opt/$PKG_BREW_NAME/include -DARROW_R_WITH_PARQUET
-DARROW_R_WITH_DATASET -DARROW_R_WITH_JSON -DARROW_R_WITH_S3 -DARROW_R_WITH_GCS"
unset HOMEBREW_NO_ANALYTICS
unset HOMEBREW_NO_AUTO_UPDATE
