lyang24 commented on code in PR #9093:
URL: https://github.com/apache/arrow-rs/pull/9093#discussion_r3069031360
##########
parquet/src/arrow/array_reader/builder.rs:
##########
@@ -96,15 +96,26 @@ pub struct ArrayReaderBuilder<'a> {
parquet_metadata: Option<&'a ParquetMetaData>,
/// metrics
metrics: &'a ArrowReaderMetrics,
+ /// Batch size for pre-allocating internal buffers
+ batch_size: usize,
}
impl<'a> ArrayReaderBuilder<'a> {
- pub fn new(row_groups: &'a dyn RowGroups, metrics: &'a ArrowReaderMetrics)
-> Self {
+ /// Create a new `ArrayReaderBuilder`
+ ///
+ /// `batch_size` is used to pre-allocate internal buffers with the
expected capacity,
+ /// avoiding reallocations when reading the first batch of data.
+ pub fn new(
+ row_groups: &'a dyn RowGroups,
+ metrics: &'a ArrowReaderMetrics,
+ batch_size: usize,
Review Comment:
this is done ty
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
