Skip to content

GH-40742: [R] fix max_rows_per_group must be a positive number #49709

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
thisisnic merged 3 commits into from
May 5, 2026
Merged

GH-40742: [R] fix max_rows_per_group must be a positive number #49709

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
87c3d30
Fix max_rows checking
thisisnic Apr 11, 2026
2528248
Remove redundant test duplication
thisisnic Apr 30, 2026
e8bcc42
Remove redundant space and test
thisisnic Apr 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 24 additions & 4 deletions r/R/dataset-write.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,12 @@ write_dataset <- function(
existing_data_behavior_opts <- c("delete_matching", "overwrite", "error")
existing_data_behavior <- match(match.arg(existing_data_behavior), existing_data_behavior_opts) - 1L

if (!missing(max_rows_per_file) && missing(max_rows_per_group) && max_rows_per_group > max_rows_per_file) {
if (
!missing(max_rows_per_file) &&
missing(max_rows_per_group) &&
max_rows_per_file > 0 &&
Copy link
Copy Markdown
Member

@jonkeane jonkeane May 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This line max_rows_per_file > 0 is the one condition that was change, yeah? The rest is whitespace?

Copy link
Copy Markdown
Member Author

@thisisnic thisisnic May 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yup!

max_rows_per_group > max_rows_per_file
) {
max_rows_per_group <- max_rows_per_file
}

Expand Down Expand Up @@ -290,7 +295,12 @@ write_delim_dataset <- function(
quote = c("needed", "all", "none"),
preserve_order = FALSE
) {
if (!missing(max_rows_per_file) && missing(max_rows_per_group) && max_rows_per_group > max_rows_per_file) {
if (
!missing(max_rows_per_file) &&
missing(max_rows_per_group) &&
max_rows_per_file > 0 &&
max_rows_per_group > max_rows_per_file
) {
max_rows_per_group <- max_rows_per_file
}

Expand Down Expand Up @@ -343,7 +353,12 @@ write_csv_dataset <- function(
quote = c("needed", "all", "none"),
preserve_order = FALSE
) {
if (!missing(max_rows_per_file) && missing(max_rows_per_group) && max_rows_per_group > max_rows_per_file) {
if (
!missing(max_rows_per_file) &&
missing(max_rows_per_group) &&
max_rows_per_file > 0 &&
max_rows_per_group > max_rows_per_file
) {
max_rows_per_group <- max_rows_per_file
}

Expand Down Expand Up @@ -395,7 +410,12 @@ write_tsv_dataset <- function(
quote = c("needed", "all", "none"),
preserve_order = FALSE
) {
if (!missing(max_rows_per_file) && missing(max_rows_per_group) && max_rows_per_group > max_rows_per_file) {
if (
!missing(max_rows_per_file) &&
missing(max_rows_per_group) &&
max_rows_per_file > 0 &&
max_rows_per_group > max_rows_per_file
) {
max_rows_per_group <- max_rows_per_file
}

Expand Down
10 changes: 10 additions & 0 deletions r/tests/testthat/test-dataset-write.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -576,6 +576,16 @@ test_that("max_rows_per_group is adjusted if at odds with max_rows_per_file", {
)
})

test_that("max_rows_per_file = 0 does not trigger max_rows_per_group adjustment (ARROW-40742)", {
skip_if_not_available("parquet")

# max_rows_per_file = 0 means "no limit" and should not error
dst_dir <- make_temp_dir()
expect_no_error(
write_dataset(df1, dst_dir, max_rows_per_file = 0L)
)
})


test_that("write_dataset checks for format-specific arguments", {
df <- tibble::tibble(
Expand Down
Loading