Ted-Jiang commented on code in PR #3780:
URL: https://github.com/apache/arrow-datafusion/pull/3780#discussion_r992223085
##########
datafusion/core/src/physical_plan/file_format/parquet.rs:
##########
@@ -785,6 +902,57 @@ impl<'a> PruningStatistics for
RowGroupPruningStatistics<'a> {
}
}
+impl<'a> PruningStatistics for PagesPruningStatistics<'a> {
+ fn min_values(&self, column: &Column) -> Option<ArrayRef> {
+ get_min_max_values_form_page_index!(self, column, min)
+ }
+
+ fn max_values(&self, column: &Column) -> Option<ArrayRef> {
+ get_min_max_values_form_page_index!(self, column, max)
+ }
+
+ fn num_containers(&self) -> usize {
+ self.offset_indexes.get(self.col_id).unwrap().len()
+ }
+
+ fn null_counts(&self, column: &Column) -> Option<ArrayRef> {
+ if let Some((col_id_index, _field)) =
+ self.parquet_schema.column_with_name(&column.name)
+ {
+ if let Some(page_index) = self.page_indexes.get(col_id_index) {
+ match page_index {
+ Index::NONE => None,
+ Index::BOOLEAN(index) =>
Some(Arc::new(Int64Array::from_iter(
+ index.indexes.iter().map(|x| x.null_count),
+ ))),
+ Index::INT32(index) => Some(Arc::new(Int64Array::from_iter(
+ index.indexes.iter().map(|x| x.null_count),
+ ))),
+ Index::INT64(index) => Some(Arc::new(Int64Array::from_iter(
+ index.indexes.iter().map(|x| x.null_count),
+ ))),
+ Index::FLOAT(index) => Some(Arc::new(Int64Array::from_iter(
+ index.indexes.iter().map(|x| x.null_count),
+ ))),
+ Index::DOUBLE(index) =>
Some(Arc::new(Int64Array::from_iter(
+ index.indexes.iter().map(|x| x.null_count),
+ ))),
+ Index::INT96(_)
+ | Index::BYTE_ARRAY(_)
+ | Index::FIXED_LEN_BYTE_ARRAY(_) => {
+ // Todo support these types
+ None
+ }
+ }
+ } else {
+ None
+ }
+ } else {
+ None
Review Comment:
I think its ok return None here🤔
--
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]
