Ted-Jiang commented on code in PR #3967:
URL: https://github.com/apache/arrow-datafusion/pull/3967#discussion_r1005497563
##########
datafusion/core/src/physical_plan/file_format/parquet.rs:
##########
@@ -692,14 +818,11 @@ struct RowGroupPruningStatistics<'a> {
parquet_schema: &'a Schema,
}
-/// Wraps page_index statistics in a way
+/// Wraps one col page_index in one rowGroup statistics in a way
/// that implements [`PruningStatistics`]
struct PagesPruningStatistics<'a> {
- //row_group_metadata: &'a RowGroupMetaData,
- page_indexes: &'a Vec<Index>,
- offset_indexes: &'a Vec<Vec<PageLocation>>,
- parquet_schema: &'a Schema,
- col_id: usize,
+ col_page_indexes: &'a Index,
Review Comment:
simplify the `PagesPruningStatistics ` no need pass all cols index!
--
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]
