jonahgao commented on code in PR #14194:
URL: https://github.com/apache/datafusion/pull/14194#discussion_r1924615742
##########
datafusion/substrait/src/logical_plan/producer.rs:
##########
@@ -559,12 +559,31 @@ pub fn from_table_scan(
let table_schema = scan.source.schema().to_dfschema_ref()?;
let base_schema = to_substrait_named_struct(&table_schema)?;
+ let best_effort_filter_option = if !scan.filters.is_empty() {
+ let table_schema_qualified = Arc::new(
+ DFSchema::try_from_qualified_schema(
+ scan.table_name.clone(),
+ &(scan.source.schema()),
+ )
+ .unwrap(),
+ );
+ let mut combined_expr = scan.filters[0].clone();
+ for i in 1..scan.filters.len() {
+ combined_expr = combined_expr.and(scan.filters[i].clone());
+ }
+ let best_effort_filter_expr =
+ producer.handle_expr(&combined_expr, &table_schema_qualified)?;
+ Some(Box::new(best_effort_filter_expr))
+ } else {
+ None
+ };
+
Ok(Box::new(Rel {
rel_type: Some(RelType::Read(Box::new(ReadRel {
common: None,
base_schema: Some(base_schema),
filter: None,
- best_effort_filter: None,
+ best_effort_filter: best_effort_filter_option,
Review Comment:
I am confused about what type of filter is considered a 'best effort'
filter. From the substrait
[documentation](https://substrait.io/relations/logical_relations/#read-filtering),
it seems that some expressions should not be put into the scan relation. cc
@Blizzara @vbarua
> In this case the filter should be set to my_int < 10 and the
best_effort_filter should be set to my_string < "x" and the remaining portion
(upper(my_string) > "B") should be put into a filter relation.
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
