alamb commented on code in PR #12135:
URL: https://github.com/apache/datafusion/pull/12135#discussion_r1758962761
##########
datafusion/core/src/datasource/physical_plan/parquet/row_filter.rs:
##########
@@ -268,90 +261,192 @@ impl<'a> FilterCandidateBuilder<'a> {
/// * `Ok(Some(candidate))` if the expression can be used as an ArrowFilter
/// * `Ok(None)` if the expression cannot be used as an ArrowFilter
/// * `Err(e)` if an error occurs while building the candidate
- pub fn build(
- mut self,
- metadata: &ParquetMetaData,
- ) -> Result<Option<FilterCandidate>> {
- let expr = self.expr.clone().rewrite(&mut self).data()?;
-
- if self.non_primitive_columns || self.projected_columns {
- Ok(None)
- } else {
- let required_bytes =
- size_of_columns(&self.required_column_indices, metadata)?;
- let can_use_index = columns_sorted(&self.required_column_indices,
metadata)?;
-
- Ok(Some(FilterCandidate {
- expr,
- required_bytes,
- can_use_index,
- projection: self.required_column_indices.into_iter().collect(),
- }))
+ pub fn build(self, metadata: &ParquetMetaData) ->
Result<Option<FilterCandidate>> {
+ let Some((projection, rewritten_expr)) = pushdown_columns(
+ Arc::clone(&self.expr),
+ self.file_schema,
+ self.table_schema,
+ )?
+ else {
+ return Ok(None);
+ };
+
+ let required_bytes = size_of_columns(&self.required_column_indices,
metadata)?;
+ let can_use_index = columns_sorted(&self.required_column_indices,
metadata)?;
+
+ Ok(Some(FilterCandidate {
+ expr: rewritten_expr,
+ required_bytes,
+ can_use_index,
+ projection,
+ }))
+ }
+}
+
+// a struct that implements TreeNodeRewriter to traverse a PhysicalExpr tree
structure to determine
Review Comment:
Thank you veru much for adding additional comments -- it is a great example
of leaving the code better than you found it
--
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]
