adriangb commented on code in PR #13795:
URL: https://github.com/apache/datafusion/pull/13795#discussion_r1888502887
##########
datafusion/physical-optimizer/src/pruning.rs:
##########
@@ -2052,6 +2052,109 @@ mod tests {
}
}
+ #[test]
+ fn prune_all_rows_null_counts() {
+ // if null_count = row_count then we should prune the container for i
= 0
+ // regardless of the statistics
+ let schema = Arc::new(Schema::new(vec![Field::new("i",
DataType::Int32, true)]));
+ let statistics = TestStatistics::new().with(
+ "i",
+ ContainerStats::new_i32(
+ vec![Some(0)], // min
+ vec![Some(0)], // max
+ )
+ .with_null_counts(vec![Some(1)])
+ .with_row_counts(vec![Some(1)]),
+ );
+ let expected_ret = &[false];
+ prune_with_expr(col("i").eq(lit(0)), &schema, &statistics,
expected_ret);
+
+ // this should be true even if the container stats are missing
+ let schema = Arc::new(Schema::new(vec![Field::new("i",
DataType::Int32, true)]));
+ let container_stats = ContainerStats {
+ min: Some(Arc::new(Int32Array::from(vec![None]))),
+ max: Some(Arc::new(Int32Array::from(vec![None]))),
+ null_counts: Some(Arc::new(UInt64Array::from(vec![Some(1)]))),
+ row_counts: Some(Arc::new(UInt64Array::from(vec![Some(1)]))),
+ ..ContainerStats::default()
+ };
+ let statistics = TestStatistics::new().with("i", container_stats);
+ let expected_ret = &[false];
+ prune_with_expr(col("i").eq(lit(0)), &schema, &statistics,
expected_ret);
+
+ // If the null counts themselves are missing we should be able to fall
back to the stats
+ let schema = Arc::new(Schema::new(vec![Field::new("i",
DataType::Int32, true)]));
+ let container_stats = ContainerStats {
+ min: Some(Arc::new(Int32Array::from(vec![Some(0)]))),
+ max: Some(Arc::new(Int32Array::from(vec![Some(0)]))),
+ null_counts: Some(Arc::new(UInt64Array::from(vec![None]))),
+ row_counts: Some(Arc::new(UInt64Array::from(vec![Some(1)]))),
+ ..ContainerStats::default()
+ };
+ let statistics = TestStatistics::new().with("i", container_stats);
+ let expected_ret = &[true];
+ prune_with_expr(col("i").eq(lit(0)), &schema, &statistics,
expected_ret);
+ let expected_ret = &[false];
+ prune_with_expr(col("i").gt(lit(0)), &schema, &statistics,
expected_ret);
+
+ // Same for the row counts
+ let schema = Arc::new(Schema::new(vec![Field::new("i",
DataType::Int32, true)]));
+ let container_stats = ContainerStats {
+ min: Some(Arc::new(Int32Array::from(vec![Some(0)]))),
+ max: Some(Arc::new(Int32Array::from(vec![Some(0)]))),
+ null_counts: Some(Arc::new(UInt64Array::from(vec![Some(1)]))),
+ row_counts: Some(Arc::new(UInt64Array::from(vec![None]))),
+ ..ContainerStats::default()
+ };
+ let statistics = TestStatistics::new().with("i", container_stats);
+ let expected_ret = &[true];
+ prune_with_expr(col("i").eq(lit(0)), &schema, &statistics,
expected_ret);
+ let expected_ret = &[false];
+ prune_with_expr(col("i").gt(lit(0)), &schema, &statistics,
expected_ret);
+ }
+
+ #[test]
+ fn prune_missing_statistics() {
+ // If the min or max stats are missing we should not prune
Review Comment:
```suggestion
// If the min or max stats are missing we should not prune
// (unless we know all rows are null, see
`prune_all_rows_null_counts`)
```
--
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
