[GitHub] [arrow-datafusion] mustafasrepo commented on a diff in pull request #6034: Implement Streaming Aggregation: Do not break pipeline in aggregation if group by columns are ordered

["mustafasrepo (via GitHub)" <gi...@apache.org>]

mustafasrepo commented on code in PR #6034:
URL: https://github.com/apache/arrow-datafusion/pull/6034#discussion_r1174949244


##########
datafusion/core/src/physical_plan/aggregates/mod.rs:
##########
@@ -822,13 +930,127 @@ mod tests {
     use std::task::{Context, Poll};
 
     use super::StreamType;
+    use crate::physical_plan::aggregates::GroupByOrderMode::{Ordered, PartiallyOrdered};
     use crate::physical_plan::coalesce_partitions::CoalescePartitionsExec;
+    use crate::physical_plan::file_format::{CsvExec, FileScanConfig};
     use crate::physical_plan::{
         ExecutionPlan, Partitioning, RecordBatchStream, SendableRecordBatchStream,
         Statistics,
     };
     use crate::prelude::SessionContext;
 
+    // Generate a schema which consists of 5 columns (a, b, c, d, e)
+    fn create_test_schema() -> Result<SchemaRef> {
+        let a = Field::new("a", DataType::Int32, true);
+        let b = Field::new("b", DataType::Int32, true);
+        let c = Field::new("c", DataType::Int32, true);
+        let d = Field::new("d", DataType::Int32, true);
+        let e = Field::new("e", DataType::Int32, true);
+        let schema = Arc::new(Schema::new(vec![a, b, c, d, e]));
+
+        Ok(schema)
+    }
+
+    // Created a sorted parquet exec
+    fn csv_exec_sorted(

Review Comment:
   Removed it. Thanks for pointing it out



-- 
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-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org