alamb commented on code in PR #10468:
URL: https://github.com/apache/datafusion/pull/10468#discussion_r1598897904
##########
datafusion/physical-plan/src/common.rs:
##########
@@ -687,4 +694,42 @@ mod tests {
assert_eq!(actual, expected);
Ok(())
}
+
+ #[test]
+ fn test_compute_record_batch_statistics_null() -> Result<()> {
+ let schema = Arc::new(Schema::new(vec![
+ Field::new("u64", DataType::UInt64, true),
+ ]));
+ let batch1 = RecordBatch::try_new(
+ Arc::clone(&schema),
+ vec![
+ Arc::new(UInt64Array::from(vec![Some(1), None, None])),
+ ],
+ )?;
+ let batch2 = RecordBatch::try_new(
+ Arc::clone(&schema),
+ vec![
+ Arc::new(UInt64Array::from(vec![Some(1), Some(2), None])),
+ ],
+ )?;
+ let byte_size = batch1.get_array_memory_size() +
batch2.get_array_memory_size();
+ let actual =
+ compute_record_batch_statistics(&[vec![batch1], vec![batch2]],
&schema, None);
+
+ let expected = Statistics {
+ num_rows: Precision::Exact(6),
+ total_byte_size: Precision::Exact(byte_size),
+ column_statistics: vec![
+ ColumnStatistics {
+ distinct_count: Precision::Absent,
+ max_value: Precision::Absent,
+ min_value: Precision::Absent,
+ null_count: Precision::Exact(3),
+ },
+ ],
+ };
+
+ assert_eq!(actual, expected);
Review Comment:
I verified test coverage by running this test without the code in this PR
and the test fails like this
```
assertion `left == right` failed
left: Statistics { num_rows: Exact(6), total_byte_size: Exact(368),
column_statistics: [ColumnStatistics { null_count: Exact(1), max_value: Absent,
min_value: Absent, distinct_count: Absent }] }
right: Statistics { num_rows: Exact(6), total_byte_size: Exact(368),
column_statistics: [ColumnStatistics { null_count: Exact(3), max_value: Absent,
min_value: Absent, distinct_count: Absent }] }
```
--
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
