ShayanGho commented on code in PR #25212:
URL: https://github.com/apache/datafusion/pull/25212#discussion_r4088897745
##########
datafusion/catalog-listing/src/table.rs:
##########
@@ -225,6 +225,32 @@ impl ListingTable {
.options
.ok_or_else(|| internal_datafusion_err!("No ListingOptions
provided"))?;
+ // Files may physically contain the partition columns, for example when
+ // they were written with `keep_partition_by_columns = true`. Partition
+ // column values are always taken from the path, so drop such columns
+ // from the file schema to avoid duplicated fields in the table schema.
+ let file_schema = if options
+ .table_partition_cols
+ .iter()
+ .any(|(name, _)| file_schema.field_with_name(name).is_ok())
+ {
+ let indices: Vec<usize> = file_schema
+ .fields()
+ .iter()
+ .enumerate()
+ .filter(|(_, field)| {
+ !options
Review Comment:
Thank you, added a test for two overlapping partition columns with one
mid-schema.
--
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]
