Skip to content

fix: [df52] Fix/dictionary unpack tests #3473

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

Open
andygrove wants to merge 1 commit into
base: df52
Choose a base branch
from
+24 −43
Open

fix: [df52] Fix/dictionary unpack tests #3473

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
67 changes: 24 additions & 43 deletions native/core/src/execution/planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3504,42 +3504,33 @@ mod tests {
let mut stream = datafusion_plan.native_plan.execute(0, task_ctx).unwrap();

let runtime = tokio::runtime::Runtime::new().unwrap();
let (tx, mut rx) = mpsc::channel(1);

// Separate thread to send the EOF signal once we've processed the only input batch
runtime.spawn(async move {
// Create a dictionary array with 100 values, and use it as input to the execution.
let keys = Int32Array::new((0..(row_count as i32)).map(|n| n % 4).collect(), None);
let values = Int32Array::from(vec![0, 1, 2, 3]);
let input_array = DictionaryArray::new(keys, Arc::new(values));
let input_batch1 = InputBatch::Batch(vec![Arc::new(input_array)], row_count);
let input_batch2 = InputBatch::EOF;

let batches = vec![input_batch1, input_batch2];

for batch in batches.into_iter() {
tx.send(batch).await.unwrap();
}
});

runtime.block_on(async move {
let mut eof_sent = false;
let mut got_result = false;
loop {
let batch = rx.recv().await.unwrap();
scans[0].set_input_batch(batch);
match poll!(stream.next()) {
Poll::Ready(Some(batch)) => {
assert!(batch.is_ok(), "got error {}", batch.unwrap_err());
let batch = batch.unwrap();
assert_eq!(batch.num_rows(), row_count / 4);
// dictionary should be unpacked
assert!(matches!(batch.column(0).data_type(), DataType::Int32));
got_result = true;
}
Poll::Ready(None) => {
break;
}
_ => {}
Poll::Pending => {
// Stream needs more input (e.g. FilterExec's batch coalescer
// is accumulating). Send EOF to flush.
if !eof_sent {
scans[0].set_input_batch(InputBatch::EOF);
eof_sent = true;
}
}
}
}
assert!(got_result, "Expected at least one result batch");
});
}

Expand Down Expand Up @@ -3589,43 +3580,33 @@ mod tests {
let mut stream = datafusion_plan.native_plan.execute(0, task_ctx).unwrap();

let runtime = tokio::runtime::Runtime::new().unwrap();
let (tx, mut rx) = mpsc::channel(1);

// Separate thread to send the EOF signal once we've processed the only input batch
runtime.spawn(async move {
// Create a dictionary array with 100 values, and use it as input to the execution.
let keys = Int32Array::new((0..(row_count as i32)).map(|n| n % 4).collect(), None);
let values = StringArray::from(vec!["foo", "bar", "hello", "comet"]);
let input_array = DictionaryArray::new(keys, Arc::new(values));
let input_batch1 = InputBatch::Batch(vec![Arc::new(input_array)], row_count);

let input_batch2 = InputBatch::EOF;

let batches = vec![input_batch1, input_batch2];

for batch in batches.into_iter() {
tx.send(batch).await.unwrap();
}
});

runtime.block_on(async move {
let mut eof_sent = false;
let mut got_result = false;
loop {
let batch = rx.recv().await.unwrap();
scans[0].set_input_batch(batch);
match poll!(stream.next()) {
Poll::Ready(Some(batch)) => {
assert!(batch.is_ok(), "got error {}", batch.unwrap_err());
let batch = batch.unwrap();
assert_eq!(batch.num_rows(), row_count / 4);
// string/binary should no longer be packed with dictionary
assert!(matches!(batch.column(0).data_type(), DataType::Utf8));
got_result = true;
}
Poll::Ready(None) => {
break;
}
_ => {}
Poll::Pending => {
// Stream needs more input (e.g. FilterExec's batch coalescer
// is accumulating). Send EOF to flush.
if !eof_sent {
scans[0].set_input_batch(InputBatch::EOF);
eof_sent = true;
}
}
}
}
assert!(got_result, "Expected at least one result batch");
});
}

Expand Down
Loading