liurenjie1024 commented on code in PR #245:
URL: https://github.com/apache/iceberg-rust/pull/245#discussion_r1545535512
##########
crates/iceberg/src/arrow.rs:
##########
@@ -101,8 +114,53 @@ impl ArrowReader {
.boxed())
}
- fn get_arrow_projection_mask(&self, _task: &FileScanTask) ->
ProjectionMask {
- // TODO: full implementation
- ProjectionMask::all()
+ fn get_arrow_projection_mask(
+ &self,
+ parquet_schema: &SchemaDescriptor,
+ ) -> crate::Result<ProjectionMask> {
+ if self.field_ids.is_empty() {
+ Ok(ProjectionMask::all())
+ } else {
+ let mut column_map = HashMap::new();
+ for (idx, field) in parquet_schema.columns().iter().enumerate() {
+ let field_type = field.self_type();
+ match field_type {
+ Type::PrimitiveType { basic_info, .. } => {
+ if !basic_info.has_id() {
+ return Err(Error::new(
+ ErrorKind::DataInvalid,
+ format!(
+ "Leave column {:?} in schema doesn't have
field id",
+ field_type
+ ),
+ ));
+ }
+ column_map.insert(basic_info.id(), idx);
Review Comment:
Yes, I agree that maybe we should modify `filter_leaves`'s api to return
error.
--
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
