(datafusion) 01/01: Return None for cardinality overflow (#22309)

[gi...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

github-merge-queue[bot] pushed a commit to branch gh-readonly-queue/main/pr-22309-c3f3b7a6eacd73ac4dc766452dc4d6cdfcb5bde7
in repository https://gitbox.apache.org/repos/asf/datafusion.git

commit c48e9936033ffceaaae6d534bfd31dc1cac520b4
Author: jj.lee <63...@users.noreply.github.com>
AuthorDate: Thu May 28 20:51:33 2026 +0900

    Return None for cardinality overflow (#22309)
    
    ## Which issue does this PR close?
    
    Closes #22232
    (cc @Dandandan )
    
    ## Rationale for this change
    
    Prevent `Interval::cardinality()` from overflowing on the full `i64`
    range.
    
    ## What changes are included in this PR?
    
    - use `checked_add(1)` instead of `+ 1`
    - add a regression test for the full `i64` range
    
    ## Are these changes tested?
    
    - `cargo fmt --all --check`
    - `cargo test -p datafusion-expr-common
    test_cardinality_full_i64_range_does_not_overflow --lib`
    - `cargo clippy --all-targets --all-features -- -D warnings` could not
    run locally because `cmake` is not installed
    
    ## Are there any user-facing changes?
    
    - No
---
 datafusion/expr-common/src/interval_arithmetic.rs | 17 ++++++++++++++++-
 datafusion/sqllogictest/test_files/select.slt     |  6 ++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/datafusion/expr-common/src/interval_arithmetic.rs b/datafusion/expr-common/src/interval_arithmetic.rs
index e2f8198c92..51858be538 100644
--- a/datafusion/expr-common/src/interval_arithmetic.rs
+++ b/datafusion/expr-common/src/interval_arithmetic.rs
@@ -944,7 +944,7 @@ impl Interval {
             // Cardinality calculations are not implemented for this data type yet:
             None
         }
-        .map(|result| result + 1)
+        .and_then(|result| result.checked_add(1))
     }
 
     /// Reflects an [`Interval`] around the point zero.
@@ -4157,7 +4157,22 @@ mod tests {
             ScalarValue::TimestampNanosecond(Some(2_000_000_000), None),
         )?;
         assert_eq!(interval.cardinality().unwrap(), 1_000_000_001);
+        Ok(())
+    }
+
+    #[test]
+    fn test_cardinality_full_integer_range_does_not_overflow() -> Result<()> {
+        let interval = Interval::try_new(
+            ScalarValue::Int64(Some(i64::MIN)),
+            ScalarValue::Int64(Some(i64::MAX)),
+        )?;
+        assert_eq!(interval.cardinality(), None);
 
+        let interval = Interval::try_new(
+            ScalarValue::UInt64(Some(0)),
+            ScalarValue::UInt64(Some(u64::MAX)),
+        )?;
+        assert_eq!(interval.cardinality(), None);
         Ok(())
     }
 
diff --git a/datafusion/sqllogictest/test_files/select.slt b/datafusion/sqllogictest/test_files/select.slt
index 3e97dc4588..762f5c1133 100644
--- a/datafusion/sqllogictest/test_files/select.slt
+++ b/datafusion/sqllogictest/test_files/select.slt
@@ -960,6 +960,12 @@ physical_plan
 01)ProjectionExec: expr=[c1@0 >= 2 AND c1@0 <= 3 as select_between_data.c1 BETWEEN Int64(2) AND Int64(3)]
 02)--DataSourceExec: partitions=1, partition_sizes=[1]
 
+# regression test: full i64 BETWEEN bounds should not overflow
+query I
+SELECT * FROM (VALUES (1)) AS t(x)
+WHERE x BETWEEN -9223372036854775808 AND 9223372036854775807
+----
+1
 
 # TODO: query_get_indexed_field
 


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datafusion.apache.org
For additional commands, e-mail: commits-help@datafusion.apache.org