refactor: Incorporate RewriteDisjunctivePredicate rule into SimplifyExpressions (#13032)

* Elliminate common factors in disjunctions

This adds a rewrite rule that elliminates common factors in OR. This is
already implmented in RewriteDisjunctivePredicate but this
implementation is simpler and will apply in more cases.

* Remove RewriteDisjunctivePredicate rule

* Fix cse test

* Update datafusion/optimizer/src/simplify_expressions/expr_simplifier.rs

Co-authored-by: Andrew Lamb <[email protected]>

---------

Co-authored-by: Andrew Lamb <[email protected]>

Author: eejbyfeldt

datafusion/expr/src/utils.rs

@@ -1101,6 +1101,54 @@ fn split_conjunction_impl<'a>(expr: &'a Expr, mut exprs: Vec<&'a Expr>) -> Vec<&
     }
 }
 
+/// Iteratate parts in a conjunctive [`Expr`] such as `A AND B AND C` => `[A, B, C]`
+///
+/// See [`split_conjunction_owned`] for more details and an example.
+pub fn iter_conjunction(expr: &Expr) -> impl Iterator<Item = &Expr> {
+    let mut stack = vec![expr];
+    std::iter::from_fn(move || {
+        while let Some(expr) = stack.pop() {
+            match expr {
+                Expr::BinaryExpr(BinaryExpr {
+                    right,
+                    op: Operator::And,
+                    left,
+                }) => {
+                    stack.push(right);
+                    stack.push(left);
+                }
+                Expr::Alias(Alias { expr, .. }) => stack.push(expr),
+                other => return Some(other),
+            }
+        }
+        None
+    })
+}
+
+/// Iteratate parts in a conjunctive [`Expr`] such as `A AND B AND C` => `[A, B, C]`
+///
+/// See [`split_conjunction_owned`] for more details and an example.
+pub fn iter_conjunction_owned(expr: Expr) -> impl Iterator<Item = Expr> {
+    let mut stack = vec![expr];
+    std::iter::from_fn(move || {
+        while let Some(expr) = stack.pop() {
+            match expr {
+                Expr::BinaryExpr(BinaryExpr {
+                    right,
+                    op: Operator::And,
+                    left,
+                }) => {
+                    stack.push(*right);
+                    stack.push(*left);
+                }
+                Expr::Alias(Alias { expr, .. }) => stack.push(*expr),
+                other => return Some(other),
+            }
+        }
+        None
+    })
+}
+
 /// Splits an owned conjunctive [`Expr`] such as `A AND B AND C` => `[A, B, C]`
 ///
 /// This is often used to "split" filter expressions such as `col1 = 5

datafusion/optimizer/src/lib.rs

@@ -51,7 +51,6 @@ pub mod propagate_empty_relation;
 pub mod push_down_filter;
 pub mod push_down_limit;
 pub mod replace_distinct_aggregate;
-pub mod rewrite_disjunctive_predicate;
 pub mod scalar_subquery_to_join;
 pub mod simplify_expressions;
 pub mod single_distinct_to_groupby;

datafusion/optimizer/src/optimizer.rs

@@ -51,7 +51,6 @@ use crate::propagate_empty_relation::PropagateEmptyRelation;
 use crate::push_down_filter::PushDownFilter;
 use crate::push_down_limit::PushDownLimit;
 use crate::replace_distinct_aggregate::ReplaceDistinctWithAggregate;
-use crate::rewrite_disjunctive_predicate::RewriteDisjunctivePredicate;
 use crate::scalar_subquery_to_join::ScalarSubqueryToJoin;
 use crate::simplify_expressions::SimplifyExpressions;
 use crate::single_distinct_to_groupby::SingleDistinctToGroupBy;
@@ -255,7 +254,6 @@ impl Optimizer {
             // run it again after running the optimizations that potentially converted
             // subqueries to joins
             Arc::new(SimplifyExpressions::new()),
-            Arc::new(RewriteDisjunctivePredicate::new()),
             Arc::new(EliminateDuplicatedExpr::new()),
             Arc::new(EliminateFilter::new()),
             Arc::new(EliminateCrossJoin::new()),

datafusion/optimizer/src/push_down_filter.rs

@@ -1213,7 +1213,7 @@ mod tests {
     };
 
     use crate::optimizer::Optimizer;
-    use crate::rewrite_disjunctive_predicate::RewriteDisjunctivePredicate;
+    use crate::simplify_expressions::SimplifyExpressions;
     use crate::test::*;
     use crate::OptimizerContext;
     use datafusion_expr::test::function_stub::sum;
@@ -1235,7 +1235,7 @@ mod tests {
         expected: &str,
     ) -> Result<()> {
         let optimizer = Optimizer::with_rules(vec![
-            Arc::new(RewriteDisjunctivePredicate::new()),
+            Arc::new(SimplifyExpressions::new()),
             Arc::new(PushDownFilter::new()),
         ]);
         let optimized_plan =