sdd commented on code in PR #1017:
URL: https://github.com/apache/iceberg-rust/pull/1017#discussion_r2179403667
##########
crates/iceberg/src/arrow/caching_delete_file_loader.rs:
##########
@@ -308,28 +319,231 @@ impl CachingDeleteFileLoader {
Ok(result)
}
- /// Parses record batch streams from individual equality delete files
- ///
- /// Returns an unbound Predicate for each batch stream
async fn parse_equality_deletes_record_batch_stream(
- streams: ArrowRecordBatchStream,
+ mut stream: ArrowRecordBatchStream,
+ equality_ids: HashSet<i32>,
) -> Result<Predicate> {
- // TODO
+ let mut result_predicate = AlwaysTrue;
+
+ while let Some(record_batch) = stream.next().await {
+ let record_batch = record_batch?;
+
+ if record_batch.num_columns() == 0 {
+ return Ok(AlwaysTrue);
+ }
+
+ let batch_schema_arrow = record_batch.schema();
+ let batch_schema_iceberg =
arrow_schema_to_schema(batch_schema_arrow.as_ref())?;
+
+ let mut datum_columns_with_names: Vec<_> = record_batch
+ .columns()
+ .iter()
+ .zip(batch_schema_iceberg.as_struct().fields())
+ // only use columns that are in the set of equality_ids for
this delete file
+ .filter(|(field, value)| equality_ids.contains(&value.id))
Review Comment:
I've fixed this, thanks!
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
