This is an automated email from the ASF dual-hosted git repository.
thisisnic pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new 5cb8bb36ea GH-43357: [R] Fix some lints (#43338)
5cb8bb36ea is described below
commit 5cb8bb36eae75ea5529e2823fbedcf4b9e49f2ed
Author: Etienne Bacher <[email protected]>
AuthorDate: Fri Aug 9 23:47:50 2024 +0200
GH-43357: [R] Fix some lints (#43338)
### Rationale for this change
I'm building a new package to find and automatically fix lints in R code:
[`flint`](https://flint.etiennebacher.com/).
I'm using real-life, large packages to check its performance and `arrow` is
one of them. Since I already test on this, there's no additional cost for me in
proposing those changes.
FYI, those changes were generated with `flint::fix_package(exclude_linters
= "outer_negation")` (I excluded this linter because of
https://github.com/etiennebacher/flint/issues/23).
### What changes are included in this PR?
There are many changes but most of them are trivial:
- replace `any(is.na())` by `anyNA()`
- add a leading 0 to decimal (e.g `.1` -> `0.1`)
- use `expect_named()` in tests
etc.
`flint` is quite new and linter rules are necessarily a bit opinionated, so
some of those changes might not be to your taste.
### Are these changes tested?
They don't change any functionality.
### Are there any user-facing changes?
No.
* GitHub Issue: #43357
Authored-by: Etienne Bacher
<[email protected]>
Signed-off-by: Nic Crane <[email protected]>
---
r/R/arrow-tabular.R | 8 ++++----
r/R/dplyr-datetime-helpers.R | 4 ++--
r/R/dplyr-funcs-datetime.R | 2 +-
r/R/dplyr-slice.R | 2 +-
r/tests/testthat/helper-data.R | 2 +-
r/tests/testthat/test-Array.R | 4 ++--
r/tests/testthat/test-RecordBatch.R | 6 +++---
r/tests/testthat/test-Table.R | 6 +++---
r/tests/testthat/test-compute-aggregate.R | 2 +-
r/tests/testthat/test-compute-arith.R | 8 ++++----
r/tests/testthat/test-csv.R | 4 ++--
r/tests/testthat/test-dataset-csv.R | 16 ++++++++--------
r/tests/testthat/test-dataset-json.R | 2 +-
r/tests/testthat/test-dataset.R | 20 ++++++++++----------
r/tests/testthat/test-dplyr-filter.R | 6 +++---
r/tests/testthat/test-dplyr-funcs-datetime.R | 2 +-
r/tests/testthat/test-dplyr-join.R | 2 +-
r/tests/testthat/test-dplyr-slice.R | 14 +++++++-------
r/tests/testthat/test-json.R | 4 ++--
r/tests/testthat/test-parquet.R | 4 ++--
r/tests/testthat/test-record-batch-reader.R | 2 +-
r/tests/testthat/test-schema.R | 10 +++++-----
r/tests/testthat/test-utf.R | 2 +-
23 files changed, 66 insertions(+), 66 deletions(-)
diff --git a/r/R/arrow-tabular.R b/r/R/arrow-tabular.R
index a67fb7db5d..f569c690fb 100644
--- a/r/R/arrow-tabular.R
+++ b/r/R/arrow-tabular.R
@@ -48,13 +48,13 @@ ArrowTabular <- R6Class("ArrowTabular",
SortIndices = function(names, descending = FALSE) {
assert_that(is.character(names))
assert_that(length(names) > 0)
- assert_that(!any(is.na(names)))
+ assert_that(!anyNA(names))
if (length(descending) == 1L) {
descending <- rep_len(descending, length(names))
}
assert_that(is.logical(descending))
assert_that(identical(length(names), length(descending)))
- assert_that(!any(is.na(descending)))
+ assert_that(!anyNA(descending))
call_function(
"sort_indices",
self,
@@ -113,13 +113,13 @@ as.data.frame.ArrowTabular <- function(x, row.names =
NULL, optional = FALSE, ..
# That way, if we're filtering too, we have fewer arrays to
filter/slice/take
if (is.character(j)) {
j_new <- match(j, names(x))
- if (any(is.na(j_new))) {
+ if (anyNA(j_new)) {
stop("Column not found: ", oxford_paste(j[is.na(j_new)]), call. =
FALSE)
}
j <- j_new
}
if (is_integerish(j)) {
- if (any(is.na(j))) {
+ if (anyNA(j)) {
stop("Column indices cannot be NA", call. = FALSE)
}
if (length(j) && all(j < 0)) {
diff --git a/r/R/dplyr-datetime-helpers.R b/r/R/dplyr-datetime-helpers.R
index 8e6a7f6185..6e08f34708 100644
--- a/r/R/dplyr-datetime-helpers.R
+++ b/r/R/dplyr-datetime-helpers.R
@@ -55,7 +55,7 @@ duration_from_chunks <- function(chunks) {
accepted_chunks <- c("second", "minute", "hour", "day", "week")
matched_chunks <- accepted_chunks[pmatch(names(chunks), accepted_chunks,
duplicates.ok = TRUE)]
- if (any(is.na(matched_chunks))) {
+ if (anyNA(matched_chunks)) {
arrow_not_supported(
paste(
"named `difftime` units other than:",
@@ -442,7 +442,7 @@ parse_period_unit <- function(x) {
str_unit_start <- substr(str_unit, 1, 3)
unit <- as.integer(pmatch(str_unit_start, known_units)) - 1L
- if (any(is.na(unit))) {
+ if (anyNA(unit)) {
validation_error(
sprintf(
"Invalid period name: '%s'",
diff --git a/r/R/dplyr-funcs-datetime.R b/r/R/dplyr-funcs-datetime.R
index 5e6ac4a103..47c8193688 100644
--- a/r/R/dplyr-funcs-datetime.R
+++ b/r/R/dplyr-funcs-datetime.R
@@ -814,7 +814,7 @@ register_bindings_datetime_rounding <- function() {
week_start = getOption("lubridate.week.start", 7)) {
opts <- parse_period_unit(unit)
if (is.null(change_on_boundary)) {
- change_on_boundary <- ifelse(call_binding("is.Date", x), TRUE, FALSE)
+ change_on_boundary <- call_binding("is.Date", x)
}
opts$ceil_is_strictly_greater <- change_on_boundary
diff --git a/r/R/dplyr-slice.R b/r/R/dplyr-slice.R
index 2173d897f1..cc718c5806 100644
--- a/r/R/dplyr-slice.R
+++ b/r/R/dplyr-slice.R
@@ -101,7 +101,7 @@ slice_sample.arrow_dplyr_query <- function(.data,
# just to make sure we get enough, then head(n)
sampling_n <- missing(prop)
if (sampling_n) {
- prop <- min(n_to_prop(.data, n) + .05, 1)
+ prop <- min(n_to_prop(.data, n) + 0.05, 1)
}
validate_prop(prop)
diff --git a/r/tests/testthat/helper-data.R b/r/tests/testthat/helper-data.R
index 0631cfccae..dc83b8861a 100644
--- a/r/tests/testthat/helper-data.R
+++ b/r/tests/testthat/helper-data.R
@@ -17,7 +17,7 @@
example_data <- tibble::tibble(
int = c(1:3, NA_integer_, 5:10),
- dbl = c(1:8, NA, 10) + .1,
+ dbl = c(1:8, NA, 10) + 0.1,
dbl2 = rep(5, 10),
lgl = sample(c(TRUE, FALSE, NA), 10, replace = TRUE),
false = logical(10),
diff --git a/r/tests/testthat/test-Array.R b/r/tests/testthat/test-Array.R
index 98068bdea2..3e41b8b274 100644
--- a/r/tests/testthat/test-Array.R
+++ b/r/tests/testthat/test-Array.R
@@ -539,14 +539,14 @@ test_that("StructArray methods", {
expect_equal(a$x, arrow_array(df$x))
expect_equal(a[["x"]], arrow_array(df$x))
expect_equal(a[[1]], arrow_array(df$x))
- expect_identical(names(a), c("x", "y", "z"))
+ expect_named(a, c("x", "y", "z"))
expect_identical(dim(a), c(10L, 3L))
})
test_that("StructArray creation", {
# from data.frame
a <- StructArray$create(example_data)
- expect_identical(names(a), c("int", "dbl", "dbl2", "lgl", "false", "chr",
"fct"))
+ expect_named(a, c("int", "dbl", "dbl2", "lgl", "false", "chr", "fct"))
expect_identical(dim(a), c(10L, 7L))
expect_r6_class(a, "StructArray")
diff --git a/r/tests/testthat/test-RecordBatch.R
b/r/tests/testthat/test-RecordBatch.R
index 5987f5a4b7..96052047e2 100644
--- a/r/tests/testthat/test-RecordBatch.R
+++ b/r/tests/testthat/test-RecordBatch.R
@@ -42,7 +42,7 @@ test_that("RecordBatch", {
expect_equal(batch$column_name(2), "lgl")
expect_equal(batch$column_name(3), "chr")
expect_equal(batch$column_name(4), "fct")
- expect_equal(names(batch), c("int", "dbl", "lgl", "chr", "fct"))
+ expect_named(batch, c("int", "dbl", "lgl", "chr", "fct"))
# input validation
expect_error(batch$column_name(NA), "'i' cannot be NA")
@@ -497,9 +497,9 @@ test_that("RecordBatch$Equals(check_metadata)", {
test_that("RecordBatch name assignment", {
rb <- record_batch(x = 1:10, y = 1:10)
- expect_identical(names(rb), c("x", "y"))
+ expect_named(rb, c("x", "y"))
names(rb) <- c("a", "b")
- expect_identical(names(rb), c("a", "b"))
+ expect_named(rb, c("a", "b"))
expect_error(names(rb) <- "f")
expect_error(names(rb) <- letters)
expect_error(names(rb) <- character(0))
diff --git a/r/tests/testthat/test-Table.R b/r/tests/testthat/test-Table.R
index f6cec3b2b7..3c0cbb1e32 100644
--- a/r/tests/testthat/test-Table.R
+++ b/r/tests/testthat/test-Table.R
@@ -66,7 +66,7 @@ tbl <- tibble::tibble(
tab <- Table$create(tbl)
test_that("[, [[, $ for Table", {
- expect_identical(names(tab), names(tbl))
+ expect_named(tab, names(tbl))
expect_equal_data_frame(tab[6:7, ], tbl[6:7, ])
expect_equal_data_frame(tab[6:7, 2:4], tbl[6:7, 2:4])
@@ -393,9 +393,9 @@ test_that("Table$SelectColumns()", {
test_that("Table name assignment", {
tab <- Table$create(x = 1:10, y = 1:10)
- expect_identical(names(tab), c("x", "y"))
+ expect_named(tab, c("x", "y"))
names(tab) <- c("a", "b")
- expect_identical(names(tab), c("a", "b"))
+ expect_named(tab, c("a", "b"))
expect_error(names(tab) <- "f")
expect_error(names(tab) <- letters)
expect_error(names(tab) <- character(0))
diff --git a/r/tests/testthat/test-compute-aggregate.R
b/r/tests/testthat/test-compute-aggregate.R
index 2732cdef3e..090a31b805 100644
--- a/r/tests/testthat/test-compute-aggregate.R
+++ b/r/tests/testthat/test-compute-aggregate.R
@@ -286,7 +286,7 @@ test_that("median passes ... args to quantile", {
Scalar$create(2)
)
expect_error(
- median(Array$create(c(1, 2)), probs = c(.25, .75))
+ median(Array$create(c(1, 2)), probs = c(0.25, 0.75))
)
})
diff --git a/r/tests/testthat/test-compute-arith.R
b/r/tests/testthat/test-compute-arith.R
index bbdcb10a6b..22c4ee8002 100644
--- a/r/tests/testthat/test-compute-arith.R
+++ b/r/tests/testthat/test-compute-arith.R
@@ -108,22 +108,22 @@ test_that("Power", {
expect_equal(a^0, Array$create(c(1, 1, 1, 1, NA_real_)))
expect_equal(a^2, Array$create(c(1, 4, 9, 16, NA_real_)))
expect_equal(a^(-1), Array$create(c(1, 1 / 2, 1 / 3, 1 / 4, NA_real_)))
- expect_equal(a^(.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4), NA_real_)))
+ expect_equal(a^(0.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4),
NA_real_)))
expect_equal(b^0, Array$create(c(1, 1, 1, 1, NA_real_)))
expect_equal(b^2, Array$create(c(1, 4, 9, 16, NA_real_)))
expect_equal(b^(-1), Array$create(c(1, 1 / 2, 1 / 3, 1 / 4, NA_real_)))
- expect_equal(b^(.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4), NA_real_)))
+ expect_equal(b^(0.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4),
NA_real_)))
expect_equal(c^0, Array$create(c(1, 1, 1, 1, NA_real_)))
expect_equal(c^2, Array$create(c(1, 4, 9, 16, NA_real_)))
expect_equal(c^(-1), Array$create(c(1, 1 / 2, 1 / 3, 1 / 4, NA_real_)))
- expect_equal(c^(.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4), NA_real_)))
+ expect_equal(c^(0.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4),
NA_real_)))
expect_equal(d^0, Array$create(c(1, 1, 1, 1, NA_real_)))
expect_equal(d^2, Array$create(c(1, 4, 9, 16, NA_real_)))
expect_equal(d^(-1), Array$create(c(1, 1 / 2, 1 / 3, 1 / 4, NA_real_)))
- expect_equal(d^(.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4), NA_real_)))
+ expect_equal(d^(0.5), Array$create(c(1, sqrt(2), sqrt(3), sqrt(4),
NA_real_)))
})
test_that("Dates casting", {
diff --git a/r/tests/testthat/test-csv.R b/r/tests/testthat/test-csv.R
index a6291ebda0..84c1786f6f 100644
--- a/r/tests/testthat/test-csv.R
+++ b/r/tests/testthat/test-csv.R
@@ -90,7 +90,7 @@ test_that("read_csv_arrow parsing options: col_names", {
tab1 <- read_csv_arrow(tf, col_names = names(tbl))
- expect_identical(names(tab1), names(tbl))
+ expect_named(tab1, names(tbl))
expect_equal(tbl, tab1)
# This errors (correctly) because I haven't given enough names
@@ -114,7 +114,7 @@ test_that("read_csv_arrow parsing options: skip", {
tab1 <- read_csv_arrow(tf, skip = 2)
- expect_identical(names(tab1), names(tbl))
+ expect_named(tab1, names(tbl))
expect_equal(tbl, tab1)
})
diff --git a/r/tests/testthat/test-dataset-csv.R
b/r/tests/testthat/test-dataset-csv.R
index 2698cd854a..387346a0d6 100644
--- a/r/tests/testthat/test-dataset-csv.R
+++ b/r/tests/testthat/test-dataset-csv.R
@@ -49,7 +49,7 @@ test_that("CSV dataset", {
ds <- open_dataset(csv_dir, partitioning = "part", format = "csv")
expect_r6_class(ds$format, "CsvFileFormat")
expect_r6_class(ds$filesystem, "LocalFileSystem")
- expect_identical(names(ds), c(names(df1), "part"))
+ expect_named(ds, c(names(df1), "part"))
expect_identical(dim(ds), c(20L, 7L))
expect_equal(
@@ -349,7 +349,7 @@ test_that("Can use col_names readr parameter", {
format = "csv",
col_names = expected_names
)
- expect_equal(names(ds), expected_names)
+ expect_named(ds, expected_names)
expect_equal(ds %>% collect(), set_names(tbl, expected_names))
# WITHOUT header, makes up names
@@ -358,7 +358,7 @@ test_that("Can use col_names readr parameter", {
format = "csv",
col_names = FALSE
)
- expect_equal(names(ds), c("f0", "f1"))
+ expect_named(ds, c("f0", "f1"))
expect_equal(ds %>% collect(), set_names(tbl, c("f0", "f1")))
# WITH header, gets names
@@ -367,7 +367,7 @@ test_that("Can use col_names readr parameter", {
format = "csv",
col_names = TRUE
)
- expect_equal(names(ds), c("int", "dbl"))
+ expect_named(ds, c("int", "dbl"))
expect_equal(ds %>% collect(), tbl)
ds <- open_dataset(
@@ -376,7 +376,7 @@ test_that("Can use col_names readr parameter", {
col_names = FALSE,
skip = 1
)
- expect_equal(names(ds), c("f0", "f1"))
+ expect_named(ds, c("f0", "f1"))
expect_equal(ds %>% collect(), set_names(tbl, c("f0", "f1")))
expect_error(
@@ -481,7 +481,7 @@ test_that("open_delim_dataset params passed through to
open_dataset", {
ds <- open_delim_dataset(csv_dir, delim = ",", partitioning = "part")
expect_r6_class(ds$format, "CsvFileFormat")
expect_r6_class(ds$filesystem, "LocalFileSystem")
- expect_identical(names(ds), c(names(df1), "part"))
+ expect_named(ds, c(names(df1), "part"))
expect_identical(dim(ds), c(20L, 7L))
# quote
@@ -629,8 +629,8 @@ test_that("GH-34640 - CSV datasets are read in correctly
when both schema and pa
)
expect_r6_class(ds$format, "CsvFileFormat")
expect_r6_class(ds$filesystem, "LocalFileSystem")
- expect_identical(names(ds), c(names(df1), "part"))
- expect_identical(names(collect(ds)), c(names(df1), "part"))
+ expect_named(ds, c(names(df1), "part"))
+ expect_named(collect(ds), c(names(df1), "part"))
expect_identical(dim(ds), c(20L, 7L))
expect_equal(schema(ds), target_schema)
diff --git a/r/tests/testthat/test-dataset-json.R
b/r/tests/testthat/test-dataset-json.R
index 699beacb85..2a999d8a0c 100644
--- a/r/tests/testthat/test-dataset-json.R
+++ b/r/tests/testthat/test-dataset-json.R
@@ -40,7 +40,7 @@ test_that("JSON dataset", {
expect_r6_class(ds$format, "JsonFileFormat")
expect_r6_class(ds$filesystem, "LocalFileSystem")
- expect_identical(names(ds), c(names(df1), "part"))
+ expect_named(ds, c(names(df1), "part"))
expect_identical(dim(ds), c(20L, 7L))
expect_equal(
diff --git a/r/tests/testthat/test-dataset.R b/r/tests/testthat/test-dataset.R
index cafe7ada53..626210f5b9 100644
--- a/r/tests/testthat/test-dataset.R
+++ b/r/tests/testthat/test-dataset.R
@@ -50,7 +50,7 @@ test_that("IPC/Feather format data", {
ds <- open_dataset(ipc_dir, partitioning = "part", format = "feather")
expect_r6_class(ds$format, "IpcFileFormat")
expect_r6_class(ds$filesystem, "LocalFileSystem")
- expect_identical(names(ds), c(names(df1), "part"))
+ expect_named(ds, c(names(df1), "part"))
expect_identical(dim(ds), c(20L, 7L))
expect_equal(
@@ -396,7 +396,7 @@ test_that("input validation", {
test_that("Partitioning inference", {
# These are the same tests as above, just using the *PartitioningFactory
ds1 <- open_dataset(dataset_dir, partitioning = "part")
- expect_identical(names(ds1), c(names(df1), "part"))
+ expect_named(ds1, c(names(df1), "part"))
expect_equal(
ds1 %>%
select(string = chr, integer = int, part) %>%
@@ -410,7 +410,7 @@ test_that("Partitioning inference", {
)
ds2 <- open_dataset(hive_dir)
- expect_identical(names(ds2), c(names(df1), "group", "other"))
+ expect_named(ds2, c(names(df1), "group", "other"))
expect_equal(
ds2 %>%
filter(group == 2) %>%
@@ -511,7 +511,7 @@ test_that("Including partition columns in schema and
partitioning, hive style CS
test_that("partitioning = NULL to ignore partition information (but why?)", {
ds <- open_dataset(hive_dir, partitioning = NULL)
- expect_identical(names(ds), names(df1)) # i.e. not c(names(df1), "group",
"other")
+ expect_named(ds, names(df1)) # i.e. not c(names(df1), "group", "other")
})
test_that("Dataset with multiple file formats", {
@@ -520,7 +520,7 @@ test_that("Dataset with multiple file formats", {
open_dataset(dataset_dir, format = "parquet", partitioning = "part"),
open_dataset(ipc_dir, format = "arrow", partitioning = "part")
))
- expect_identical(names(ds), c(names(df1), "part"))
+ expect_named(ds, c(names(df1), "part"))
expect_equal(
ds %>%
filter(int > 6 & part %in% c(1, 3)) %>%
@@ -1085,14 +1085,14 @@ test_that("Assembling a Dataset manually and getting a
Table", {
expect_r6_class(schm, "Schema")
phys_schm <- ParquetFileReader$create(files[1])$GetSchema()
- expect_equal(names(phys_schm), names(df1))
- expect_equal(names(schm), c(names(phys_schm), "part"))
+ expect_named(phys_schm, names(df1))
+ expect_named(schm, c(names(phys_schm), "part"))
child <- factory$Finish(schm)
expect_r6_class(child, "FileSystemDataset")
expect_r6_class(child$schema, "Schema")
expect_r6_class(child$format, "ParquetFileFormat")
- expect_equal(names(schm), names(child$schema))
+ expect_named(schm, names(child$schema))
expect_equal(child$files, files)
ds <- Dataset$create(list(child), schm)
@@ -1112,12 +1112,12 @@ test_that("Assembling multiple DatasetFactories with
DatasetFactory", {
expect_r6_class(schm, "Schema")
phys_schm <- ParquetFileReader$create(files[1])$GetSchema()
- expect_equal(names(phys_schm), names(df1))
+ expect_named(phys_schm, names(df1))
ds <- factory$Finish(schm)
expect_r6_class(ds, "UnionDataset")
expect_r6_class(ds$schema, "Schema")
- expect_equal(names(schm), names(ds$schema))
+ expect_named(schm, names(ds$schema))
expect_equal(unlist(map(ds$children, ~ .$files)), files)
expect_scan_result(ds, schm)
diff --git a/r/tests/testthat/test-dplyr-filter.R
b/r/tests/testthat/test-dplyr-filter.R
index ba086133dc..ae3ce29edf 100644
--- a/r/tests/testthat/test-dplyr-filter.R
+++ b/r/tests/testthat/test-dplyr-filter.R
@@ -314,7 +314,7 @@ test_that("Filtering on a column that doesn't exist errors
correctly", {
test_that("Filtering with unsupported functions", {
compare_dplyr_binding(
.input %>%
- filter(int > 2, pnorm(dbl) > .99) %>%
+ filter(int > 2, pnorm(dbl) > 0.99) %>%
collect(),
tbl,
warning = paste(
@@ -329,7 +329,7 @@ test_that("Filtering with unsupported functions", {
filter(
nchar(chr, type = "bytes", allowNA = TRUE) == 1, # bad, Arrow msg
int > 2, # good
- pnorm(dbl) > .99 # bad, opaque, but we'll error on the first one
before we get here
+ pnorm(dbl) > 0.99 # bad, opaque, but we'll error on the first one
before we get here
) %>%
collect(),
tbl,
@@ -472,7 +472,7 @@ test_that(".by argument", {
# filter should pulling not grouped data into R when using the .by argument
compare_dplyr_binding(
.input %>%
- filter(int > 2, pnorm(dbl) > .99, .by = chr) %>%
+ filter(int > 2, pnorm(dbl) > 0.99, .by = chr) %>%
collect(),
tbl,
warning = paste(
diff --git a/r/tests/testthat/test-dplyr-funcs-datetime.R
b/r/tests/testthat/test-dplyr-funcs-datetime.R
index e53daf8317..d613a9cc5c 100644
--- a/r/tests/testthat/test-dplyr-funcs-datetime.R
+++ b/r/tests/testthat/test-dplyr-funcs-datetime.R
@@ -3411,7 +3411,7 @@ check_boundary_with_unit <- function(unit, ...) {
test_that("ceiling_date() applies change_on_boundary correctly", {
check_boundary_with_unit(".001 second")
check_boundary_with_unit("second")
- check_boundary_with_unit("minute", tolerance = .001) # floating point issue?
+ check_boundary_with_unit("minute", tolerance = 0.001) # floating point issue?
check_boundary_with_unit("hour")
check_boundary_with_unit("day")
})
diff --git a/r/tests/testthat/test-dplyr-join.R
b/r/tests/testthat/test-dplyr-join.R
index 9a1c8b7b80..3609e53b18 100644
--- a/r/tests/testthat/test-dplyr-join.R
+++ b/r/tests/testthat/test-dplyr-join.R
@@ -353,7 +353,7 @@ test_that("suffix and implicit schema", {
join_op <- inner_join(left_suf, right_suf, by = "key", suffix = c("_left",
"_right"))
output <- collect(join_op)
impl_schema <- implicit_schema(join_op)
- expect_equal(names(output), names(implicit_schema(join_op)))
+ expect_named(output, names(implicit_schema(join_op)))
})
test_that("summarize and join", {
diff --git a/r/tests/testthat/test-dplyr-slice.R
b/r/tests/testthat/test-dplyr-slice.R
index 3b103d2e3c..870f1b2d78 100644
--- a/r/tests/testthat/test-dplyr-slice.R
+++ b/r/tests/testthat/test-dplyr-slice.R
@@ -40,13 +40,13 @@ test_that("slice_head/tail, ungrouped", {
expect_equal(
tab %>%
- slice_head(prop = .25) %>%
+ slice_head(prop = 0.25) %>%
nrow(),
2
)
expect_equal(
tab %>%
- slice_tail(prop = .25) %>%
+ slice_tail(prop = 0.25) %>%
nrow(),
2
)
@@ -78,13 +78,13 @@ test_that("slice_min/max, ungrouped", {
compare_dplyr_binding(
.input %>%
- slice_max(int, prop = .25, with_ties = FALSE) %>%
+ slice_max(int, prop = 0.25, with_ties = FALSE) %>%
collect(),
tbl
)
compare_dplyr_binding(
.input %>%
- slice_min(int, prop = .25, with_ties = FALSE) %>%
+ slice_min(int, prop = 0.25, with_ties = FALSE) %>%
collect(),
tbl
)
@@ -108,7 +108,7 @@ test_that("slice_sample, ungrouped", {
# Because this is random (and we only have 10 rows), try several times
for (i in 1:50) {
sampled_prop <- tab %>%
- slice_sample(prop = .2) %>%
+ slice_sample(prop = 0.2) %>%
collect() %>%
nrow()
if (sampled_prop == 2) break
@@ -184,7 +184,7 @@ test_that("slice_* not supported with groups", {
test_that("input validation", {
tab <- arrow_table(tbl)
- for (p in list("a", -1, 2, c(.01, .02), NA_real_)) {
+ for (p in list("a", -1, 2, c(0.01, 0.02), NA_real_)) {
expect_error(
slice_head(tab, prop = !!p),
"`prop` must be a single numeric value between 0 and 1",
@@ -206,7 +206,7 @@ test_that("n <-> prop conversion when nrow is not known", {
expect_error(
joined %>%
- slice_min(int, prop = .25, with_ties = FALSE),
+ slice_min(int, prop = 0.25, with_ties = FALSE),
"Slicing with `prop` when"
)
diff --git a/r/tests/testthat/test-json.R b/r/tests/testthat/test-json.R
index 12c9ce0178..88ce07a8a6 100644
--- a/r/tests/testthat/test-json.R
+++ b/r/tests/testthat/test-json.R
@@ -80,10 +80,10 @@ test_that("read_json_arrow() supports col_select=", {
', tf)
tab1 <- read_json_arrow(tf, col_select = c(hello, world))
- expect_equal(names(tab1), c("hello", "world"))
+ expect_named(tab1, c("hello", "world"))
tab2 <- read_json_arrow(tf, col_select = 1:2)
- expect_equal(names(tab2), c("hello", "world"))
+ expect_named(tab2, c("hello", "world"))
})
test_that("read_json_arrow(schema=) with empty schema", {
diff --git a/r/tests/testthat/test-parquet.R b/r/tests/testthat/test-parquet.R
index cc57022600..738febb7b3 100644
--- a/r/tests/testthat/test-parquet.R
+++ b/r/tests/testthat/test-parquet.R
@@ -42,10 +42,10 @@ test_that("simple int column roundtrip", {
test_that("read_parquet() supports col_select", {
skip_if_not_available("snappy")
df <- read_parquet(pq_file, col_select = c(x, y, z))
- expect_equal(names(df), c("x", "y", "z"))
+ expect_named(df, c("x", "y", "z"))
df <- read_parquet(pq_file, col_select = starts_with("c"))
- expect_equal(names(df), c("carat", "cut", "color", "clarity"))
+ expect_named(df, c("carat", "cut", "color", "clarity"))
})
test_that("read_parquet() with raw data", {
diff --git a/r/tests/testthat/test-record-batch-reader.R
b/r/tests/testthat/test-record-batch-reader.R
index a59523790a..540bbfebd5 100644
--- a/r/tests/testthat/test-record-batch-reader.R
+++ b/r/tests/testthat/test-record-batch-reader.R
@@ -183,7 +183,7 @@ test_that("RBR methods", {
x: int32
y: string"
)
- expect_equal(names(reader), c("x", "y"))
+ expect_named(reader, c("x", "y"))
expect_identical(dim(reader), c(NA_integer_, 2L))
expect_equal(
diff --git a/r/tests/testthat/test-schema.R b/r/tests/testthat/test-schema.R
index 68db5c819b..0c45d24ce1 100644
--- a/r/tests/testthat/test-schema.R
+++ b/r/tests/testthat/test-schema.R
@@ -21,7 +21,7 @@ test_that("Alternate type names are supported", {
schema(b = double(), c = bool(), d = string(), e = float(), f =
halffloat()),
schema(b = float64(), c = boolean(), d = utf8(), e = float32(), f =
float16())
)
- expect_equal(names(schema(b = double(), c = bool(), d = string())), c("b",
"c", "d"))
+ expect_named(schema(b = double(), c = bool(), d = string()), c("b", "c",
"d"))
})
test_that("Schema print method", {
@@ -279,9 +279,9 @@ test_that("as_schema() works for StructType objects", {
test_that("schema name assignment", {
schm <- schema(x = int8(), y = string(), z = double())
- expect_identical(names(schm), c("x", "y", "z"))
+ expect_named(schm, c("x", "y", "z"))
names(schm) <- c("a", "b", "c")
- expect_identical(names(schm), c("a", "b", "c"))
+ expect_named(schm, c("a", "b", "c"))
expect_error(names(schm) <- "f", regexp = "Replacement names must contain
same number of items as current names")
expect_error(names(schm) <- NULL, regexp = "Replacement names must be
character vector, not NULL")
@@ -289,8 +289,8 @@ test_that("schema name assignment", {
df <- data.frame(x = 1:3, y = c("a", "b", "c"))
schm2 <- arrow_table(df)$schema
names(schm2) <- c("col1", "col2")
- expect_identical(names(schm2), c("col1", "col2"))
- expect_identical(names(schm2$r_metadata$columns), c("col1", "col2"))
+ expect_named(schm2, c("col1", "col2"))
+ expect_named(schm2$r_metadata$columns, c("col1", "col2"))
})
test_that("schema extraction", {
diff --git a/r/tests/testthat/test-utf.R b/r/tests/testthat/test-utf.R
index 660b2a4784..00f52ae9d1 100644
--- a/r/tests/testthat/test-utf.R
+++ b/r/tests/testthat/test-utf.R
@@ -54,7 +54,7 @@ test_that("We handle non-UTF strings", {
# Schema field name
df_schema <- schema(raw_schema)
- expect_identical(names(df_schema), names(df))
+ expect_named(df_schema, names(df))
df_struct_schema <- schema(a = do.call(struct, raw_schema))
