rgbuilds commented on code in PR #26195:
URL: https://github.com/apache/datafusion/pull/26195#discussion_r4291627753
##########
datafusion/datasource-parquet/src/file_format.rs:
##########
@@ -272,32 +272,83 @@ fn clear_metadata(
})
}
-/// Marks every field that is missing from at least one of the `file_count`
-/// files as nullable: reading such a file yields nulls for that column.
-fn mark_partially_present_fields_nullable(
- schema: Schema,
- presence: &HashMap<String, usize>,
- file_count: usize,
-) -> Schema {
- if presence.values().all(|&count| count == file_count) {
+/// Widen fields missing from some of their containing schemas. An absent
parent
+/// produces a null parent, not a null value for each required child, so
children
+/// are compared only across files in which their parent exists.
+fn mark_partially_present_fields_nullable(schema: Schema, sources: &[Schema])
-> Schema {
+ if sources.len() <= 1 {
return schema;
}
- let metadata = schema.metadata().clone();
- let fields = schema
- .fields()
+ let fields = widen_fields(
+ schema.fields(),
+ &sources.iter().map(Schema::fields).collect::<Vec<_>>(),
+ );
+ Schema::new_with_metadata(fields, schema.metadata().clone())
+}
+
+fn widen_fields(fields: &Fields, sources: &[&Fields]) -> Fields {
+ let mut present: HashMap<&str, Vec<&FieldRef>> = HashMap::new();
+ for source in sources {
+ for field in *source {
+ present.entry(field.name()).or_default().push(field);
+ }
+ }
+ fields
.iter()
.map(|field| {
- let present_everywhere = presence
- .get(field.name())
- .is_some_and(|&count| count == file_count);
- if present_everywhere || field.is_nullable() {
- Arc::clone(field)
+ let occurrences = &present[field.name().as_str()];
Review Comment:
Agreed. I replaced the indexing operation with a guarded lookup and treat an
absent occurrence list as missing. I also added a focused unit test confirming
the merged field becomes nullable instead of panicking.
The duplicate-name point is valid and also affects the pre-existing
top-level counting. Correctly consolidating duplicate fields within one source
has broader semantics than this nested-nullability fix, so I left it unchanged
and propose tracking it separately unless you consider it blocking.
--
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]
