wirybeaver commented on code in PR #3342:
URL: https://github.com/apache/iceberg-rust/pull/3342#discussion_r4462066136
##########
crates/iceberg/src/writer/file_writer/parquet_writer.rs:
##########
@@ -401,8 +489,48 @@ impl MinMaxColAggregator {
Ok(())
}
+ fn update_geo(&mut self, field_id: i32, column: &ColumnChunkMetaData) {
+ // Null-only row groups do not contribute coordinates and need no
bounding box.
+ if column.num_values() == 0
+ || column
+ .statistics()
+ .and_then(Statistics::null_count_opt)
+ .is_some_and(|nulls| nulls == column.num_values() as u64)
+ {
+ return;
+ }
+ let bbox = column
+ .geo_statistics()
+ .and_then(|stats| stats.bounding_box());
+ self.geo_bounds
+ .entry(field_id)
+ .and_modify(|state| {
+ if let (Some(bounds), Some(bbox)) = (state.as_mut(), bbox) {
+ bounds.merge(bbox);
+ } else {
+ *state = None;
+ }
+ })
+ .or_insert_with(|| bbox.map(GeospatialBounds::from));
+ }
+
/// Returns lower and upper bounds
- fn produce(self) -> (HashMap<i32, Datum>, HashMap<i32, Datum>) {
+ fn produce(mut self) -> (HashMap<i32, Datum>, HashMap<i32, Datum>) {
+ for (field_id, bounds) in self.geo_bounds {
+ if let Some(bounds) = bounds {
+ let ty = self
+ .schema
+ .field_by_id(field_id)
+ .unwrap()
+ .field_type
+ .as_primitive_type()
+ .unwrap()
+ .clone();
+ let (lower, upper) = bounds.into_datums(ty);
Review Comment:
done
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
