This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/main by this push:
new a01886db20 Minor: rename `ParquetRecordBatchStream::reader` to
`ParquetRecordBatchStream::factory` (#7319)
a01886db20 is described below
commit a01886db20982155fb38f101181ae14f31ed9256
Author: Andrew Lamb <[email protected]>
AuthorDate: Wed Mar 26 12:45:25 2025 -0400
Minor: rename `ParquetRecordBatchStream::reader` to
`ParquetRecordBatchStream::factory` (#7319)
---
parquet/src/arrow/async_reader/mod.rs | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/parquet/src/arrow/async_reader/mod.rs
b/parquet/src/arrow/async_reader/mod.rs
index 3f04a14090..4478162e52 100644
--- a/parquet/src/arrow/async_reader/mod.rs
+++ b/parquet/src/arrow/async_reader/mod.rs
@@ -558,7 +558,7 @@ 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 {
input: self.input.0,
filter: self.filter,
metadata: self.metadata.clone(),
@@ -569,7 +569,7 @@ 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))
}
@@ -585,7 +585,7 @@ 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,
})
}
@@ -765,7 +765,7 @@ 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>,
}
@@ -827,7 +827,7 @@ 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(
@@ -841,7 +841,7 @@ 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));
@@ -881,7 +881,7 @@ 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;
@@ -900,7 +900,7 @@ 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),