metesynnada commented on code in PR #6724:
URL: https://github.com/apache/arrow-datafusion/pull/6724#discussion_r1236474277
##########
datafusion/core/src/physical_plan/joins/hash_join.rs:
##########
@@ -1097,6 +1098,49 @@ pub fn equal_rows(
err.unwrap_or(Ok(res))
}
+fn eq_dyn_null(
+ left: &dyn Array,
+ right: &dyn Array,
+ null_equals_null: bool,
+) -> Result<BooleanArray, ArrowError> {
+ match (left.data_type(), right.data_type()) {
+ (DataType::Null, DataType::Null) => Ok(BooleanArray::new(
+ BooleanBuffer::collect_bool(left.len(), |_| null_equals_null),
+ None,
+ )),
+ _ => eq_dyn(left, right),
+ }
+}
+
+pub fn equal_rows_arr(
+ indices_left: UInt64Array,
+ indices_right: UInt32Array,
+ left_arrays: &[ArrayRef],
+ right_arrays: &[ArrayRef],
+ null_equals_null: bool,
Review Comment:
How about folding?
```rust
pub fn equal_rows_arr(
indices_left: UInt64Array,
indices_right: UInt32Array,
left_arrays: &[ArrayRef],
right_arrays: &[ArrayRef],
null_equals_null: bool,
) -> Result<(UInt64Array, UInt32Array)> {
let mut iter = left_arrays.iter().zip(right_arrays.iter());
let (first_left, first_right) = iter.next().ok_or_else(|| {
DataFusionError::Internal("At least one array should be provided for
both left and right".to_string())
})?;
let arr_left = take(first_left.as_ref(), &indices_left, None)?;
let arr_right = take(first_right.as_ref(), &indices_right, None)?;
let mut equal = eq_dyn_null(&arr_left, &arr_right, null_equals_null)?;
// Use map and try_fold to iterate over the remaining pairs of arrays.
// In each iteration, take is used on the pair of arrays and their
equality is determined.
// The results are then folded (combined) using the and function to get
a final equality result.
equal = iter
.map(|(left, right)| {
let arr_left = take(left.as_ref(), &indices_left, None)?;
let arr_right = take(right.as_ref(), &indices_right, None)?;
eq_dyn_null(arr_left.as_ref(), arr_right.as_ref(),
null_equals_null)
})
.try_fold(equal, |acc, res| {
let equal2 = res?;
and(&acc, &equal2)
})?;
// Continue
}
```
--
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]
