update

Author: XiangpengHao

parquet/src/arrow/async_reader/arrow_reader.rs

@@ -120,7 +120,6 @@ impl FilteredParquetRecordBatchReader {
         self.row_filter.take()
     }
 
-    #[inline(never)]
     /// Take a selection, and return the new selection where the rows are filtered by the predicate.
     fn build_predicate_filter(
         &mut self,
@@ -372,7 +371,6 @@ impl<R: ChunkReader> Iterator for CachedPageReader<R> {
 
 impl<R: ChunkReader> PageReader for CachedPageReader<R> {
     fn get_next_page(&mut self) -> Result<Option<Page>, ParquetError> {
-        // self.inner.get_next_page()
         let next_page_offset = self.inner.peek_next_page_offset()?;
 
         let Some(offset) = next_page_offset else {

parquet/src/arrow/async_reader/mod.rs

@@ -686,7 +686,7 @@ where
     /// - `Ok(None)` if the stream has ended.
     /// - `Err(error)` if the stream has errored. All subsequent calls will return `Ok(None)`.
     /// - `Ok(Some(reader))` which holds all the data for the row group.
-    pub async fn next_row_group(&mut self) -> Result<Option<ParquetRecordBatchReader>> {
+    pub async fn next_row_group(&mut self) -> Result<Option<FilteredParquetRecordBatchReader>> {
         loop {
             match &mut self.state {
                 StreamState::Decoding(_) | StreamState::Reading(_) => {

parquet/src/file/serialized_reader.rs

@@ -568,6 +568,9 @@ impl<R: ChunkReader> SerializedPageReader<R> {
         })
     }
 
+    /// Similar to `peek_next_page`, but returns the offset of the next page instead of the page metadata.
+    /// Unlike page metadata, an offset can uniquely identify a page.
+    /// Useful when we want to if the next page is being cached or read previously.
     #[cfg(feature = "async")]
     pub(crate) fn peek_next_page_offset(&mut self) -> Result<Option<usize>> {
         match &mut self.state {