Skip to content

bugfix for dataset overwrite method #794

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
gsilvestrin merged 3 commits into from
Apr 22, 2023
Merged

bugfix for dataset overwrite method #794

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d8aa081
bugfix for dataset overwrite method
Apr 21, 2023
e562573
cargo fmt
Apr 21, 2023
3b779be
cleanup
Apr 21, 2023
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
23 changes: 16 additions & 7 deletions rust/src/dataset.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,7 +194,10 @@ impl Dataset {
}

// append + dataset doesn't already exists = warn + switch to create mode
if !flag_dataset_exists && matches!(params.mode, WriteMode::Append) {
if !flag_dataset_exists
&& (matches!(params.mode, WriteMode::Append)
|| matches!(params.mode, WriteMode::Overwrite))
{
eprintln!("Warning: No existing dataset at {uri}, it will be created");
params = WriteParams {
mode: WriteMode::Create,
Expand Down Expand Up @@ -713,10 +716,7 @@ mod tests {
use futures::stream::TryStreamExt;
use tempfile::tempdir;

#[tokio::test]
async fn create_dataset() {
let test_dir = tempdir().unwrap();

async fn create_file(path: &std::path::Path, mode: WriteMode) {
let schema = Arc::new(ArrowSchema::new(vec![
Field::new("i", DataType::Int32, false),
Field::new(
Expand Down Expand Up @@ -748,11 +748,11 @@ mod tests {
);
let expected_batches = batches.batches.clone();

let test_uri = test_dir.path().to_str().unwrap();

let test_uri = path.to_str().unwrap();
let mut write_params = WriteParams::default();
write_params.max_rows_per_file = 40;
write_params.max_rows_per_group = 10;
write_params.mode = mode;
let mut reader: Box<dyn RecordBatchReader> = Box::new(batches);
Dataset::write(&mut reader, test_uri, Some(write_params))
.await
Expand Down Expand Up @@ -793,6 +793,15 @@ mod tests {
)
}

#[tokio::test]
async fn test_create_dataset() {
// Appending / Overwriting a dataset that does not exist is treated as Create
for mode in [WriteMode::Create, WriteMode::Append, Overwrite] {
let test_dir = tempdir().unwrap();
create_file(test_dir.path(), mode).await
}
}

#[tokio::test]
async fn append_dataset() {
let test_dir = tempdir().unwrap();
Expand Down