Skip to content

Minor: rename ParquetRecordBatchStream::reader to ParquetRecordBatchStream::reader_factory #7319

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
merged 1 commit into from
Mar 26, 2025
Merged

Minor: rename ParquetRecordBatchStream::reader to ParquetRecordBatchStream::reader_factory #7319

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
16 changes: 8 additions & 8 deletions parquet/src/arrow/async_reader/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -557,7 +557,7 @@ impl<T: AsyncFileReader + Send + 'static> ParquetRecordBatchStreamBuilder<T> {
let batch_size = self
.batch_size
.min(self.metadata.file_metadata().num_rows() as usize);
let reader = ReaderFactory {
let reader_factory = ReaderFactory {
Copy link
Contributor Author

Choose a reason for hiding this comment

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

reader_factory I think better expresses that this is not a Reader but something that makes Readers

input: self.input.0,
filter: self.filter,
metadata: self.metadata.clone(),
Expand All @@ -568,7 +568,7 @@ impl<T: AsyncFileReader + Send + 'static> ParquetRecordBatchStreamBuilder<T> {

// Ensure schema of ParquetRecordBatchStream respects projection, and does
// not store metadata (same as for ParquetRecordBatchReader and emitted RecordBatches)
let projected_fields = match reader.fields.as_deref().map(|pf| &pf.arrow_type) {
let projected_fields = match reader_factory.fields.as_deref().map(|pf| &pf.arrow_type) {
Some(DataType::Struct(fields)) => {
fields.filter_leaves(|idx, _| self.projection.leaf_included(idx))
}
Expand All @@ -584,7 +584,7 @@ impl<T: AsyncFileReader + Send + 'static> ParquetRecordBatchStreamBuilder<T> {
projection: self.projection,
selection: self.selection,
schema,
reader: Some(reader),
reader_factory: Some(reader_factory),
state: StreamState::Init,
})
}
Expand Down Expand Up @@ -764,7 +764,7 @@ pub struct ParquetRecordBatchStream<T> {
selection: Option<RowSelection>,

/// This is an option so it can be moved into a future
reader: Option<ReaderFactory<T>>,
reader_factory: Option<ReaderFactory<T>>,

state: StreamState<T>,
}
Expand Down Expand Up @@ -826,7 +826,7 @@ where

let selection = self.selection.as_mut().map(|s| s.split_off(row_count));

let reader_factory = self.reader.take().expect("lost reader");
let reader_factory = self.reader_factory.take().expect("lost reader factory");

let (reader_factory, maybe_reader) = reader_factory
.read_row_group(
Expand All @@ -840,7 +840,7 @@ where
self.state = StreamState::Error;
err
})?;
self.reader = Some(reader_factory);
self.reader_factory = Some(reader_factory);

if let Some(reader) = maybe_reader {
return Ok(Some(reader));
Expand Down Expand Up @@ -880,7 +880,7 @@ where
None => return Poll::Ready(None),
};

let reader = self.reader.take().expect("lost reader");
let reader = self.reader_factory.take().expect("lost reader factory");

let row_count = self.metadata.row_group(row_group_idx).num_rows() as usize;

Expand All @@ -899,7 +899,7 @@ where
}
StreamState::Reading(f) => match ready!(f.poll_unpin(cx)) {
Ok((reader_factory, maybe_reader)) => {
self.reader = Some(reader_factory);
self.reader_factory = Some(reader_factory);
match maybe_reader {
// Read records from [`ParquetRecordBatchReader`]
Some(reader) => self.state = StreamState::Decoding(reader),
Expand Down
Loading