Skip to content
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

Jump to bottom

fix: read entire file with ArrowReader #25

Merged
merged 2 commits into from
Nov 5, 2023
Merged

fix: read entire file with ArrowReader #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a5defdc
Fix bug where not reading all stripes in file
Jefffrey Nov 5, 2023
e0aa734
Add async test
Jefffrey Nov 5, 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
54 changes: 33 additions & 21 deletions src/arrow_reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,30 @@ impl<R: Read> ArrowReader<R> {
}
}

impl<R: Read + Seek> ArrowReader<R> {
fn try_advance_stripe(&mut self) -> Option<std::result::Result<RecordBatch, ArrowError>> {
match self
.cursor
.next()
.map(|r| r.map_err(|err| ArrowError::ExternalError(Box::new(err))))
{
Some(Ok(stripe)) => {
match NaiveStripeDecoder::new(stripe, self.schema_ref.clone(), self.batch_size)
.map_err(|err| ArrowError::ExternalError(Box::new(err)))
{
Ok(decoder) => {
self.current_stripe = Some(Box::new(decoder));
self.next()
}
Err(err) => Some(Err(err)),
}
}
Some(Err(err)) => Some(Err(err)),
None => None,
}
}
}

pub fn create_arrow_schema<R>(cursor: &Cursor<R>) -> Schema {
let metadata = cursor
.reader
Expand Down Expand Up @@ -93,28 +117,16 @@ impl<R: Read + Seek> Iterator for ArrowReader<R> {

fn next(&mut self) -> Option<Self::Item> {
match self.current_stripe.as_mut() {
Some(stripe) => stripe
.next()
.map(|batch| batch.map_err(|err| ArrowError::ExternalError(Box::new(err)))),
None => match self
.cursor
.next()
.map(|r| r.map_err(|err| ArrowError::ExternalError(Box::new(err))))
{
Some(Ok(stripe)) => {
match NaiveStripeDecoder::new(stripe, self.schema_ref.clone(), self.batch_size)
.map_err(|err| ArrowError::ExternalError(Box::new(err)))
{
Ok(decoder) => {
self.current_stripe = Some(Box::new(decoder));
self.next()
}
Err(err) => Some(Err(err)),
}
Some(stripe) => {
match stripe
.next()
.map(|batch| batch.map_err(|err| ArrowError::ExternalError(Box::new(err))))
{
Some(rb) => Some(rb),
None => self.try_advance_stripe(),
Comment on lines +120 to +126
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Bug was here as after stripe returned None, iterator would not advance any further

Copy link
Collaborator

Choose a reason for hiding this comment

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

Good catch!

}
Some(Err(err)) => Some(Err(err)),
None => None,
},
}
None => self.try_advance_stripe(),
}
}
}
Expand Down
16 changes: 12 additions & 4 deletions tests/basic/main.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,11 +269,19 @@ pub async fn async_basic_test_0() {
pub fn v0_file_test() {
let path = basic_path("demo-11-zlib.orc");
let reader = new_arrow_reader_root(&path);
let _expected_row_count = reader.total_row_count();
let expected_row_count = reader.total_row_count();
let batches = reader.collect::<Result<Vec<_>, _>>().unwrap();
let _total_rows: usize = batches.iter().map(|b| b.num_rows()).sum();
// TODO: not reading entire file, debug
// assert_eq!(expected_row_count as usize, total_rows);
let total_rows: usize = batches.iter().map(|b| b.num_rows()).sum();
assert_eq!(expected_row_count as usize, total_rows);
}

#[tokio::test]
pub async fn v0_file_test_async() {
let path = basic_path("demo-11-zlib.orc");
let reader = new_arrow_stream_reader_root(&path).await;
let batches = reader.try_collect::<Vec<_>>().await.unwrap();
let total_rows: usize = batches.iter().map(|b| b.num_rows()).sum();
assert_eq!(1_920_800, total_rows);
}

#[test]
Expand Down
Loading