opt: fixup CTE stats on placeholder queries

During optbuilder phase we copy the initial expressions stats into the
fake-rel but this value can change when placeholders are assigned so add
a normalization step to do this so it happens on the assignplaceholder
path.

Fixes: cockroachdb#99389
Epic: none
Release note: none

pkg/sql/opt/norm/rules/with.opt

@@ -64,3 +64,20 @@
     )
     $private
 )
+
+# ApplyBindingRowCountToCTE makes sure to that stats changes are propagated on
+# placeholder assignment.
+[ApplyBindingRowCountToCTE, Normalize]
+(RecursiveCTE
+    $binding:*
+    $initial:* & (RowCountDifferent $binding $initial)
+    $recursive:*
+    $private:*
+)
+=>
+(RecursiveCTE
+    (ApplyBindingRowCount $binding $initial)
+    $initial
+    $recursive
+    $private
+)

pkg/sql/opt/norm/with_funcs.go

@@ -297,3 +297,23 @@ func (c *CustomFuncs) CanAddRecursiveLimit(
 func (c *CustomFuncs) GetRecursiveWithID(private *memo.RecursiveCTEPrivate) opt.WithID {
 	return private.WithID
 }
+
+func (c *CustomFuncs) ApplyBindingRowCount(
+	binding, initial memo.RelExpr,
+) memo.RelExpr {
+	// The properties of the binding are tricky: the recursive expression is
+	// invoked repeatedly and these must hold each time. We can't use the initial
+	// expression's properties directly, as those only hold the first time the
+	// recursive query is executed. We don't really know the input row count,
+	// except for the first time we run the recursive query. We don't have
+	// anything better though.
+	initialRowCount := initial.Relational().Statistics().RowCount
+	binding.Relational().Statistics().RowCount = initialRowCount
+	return binding
+}
+
+func (c *CustomFuncs) RowCountDifferent(
+	binding, initial memo.RelExpr,
+) bool {
+	return initial.Relational().Statistics().RowCount != binding.Relational().Statistics().RowCount
+}

pkg/sql/opt/xform/testdata/rules/cte

@@ -0,0 +1,57 @@
+exec-ddl
+CREATE TABLE xy (x INT, y INT, INDEX (x) STORING (y));
+----
+
+exec-ddl
+ALTER TABLE xy INJECT STATISTICS '[
+  {
+    "columns": ["x"],
+    "created_at": "2018-01-01 1:00:00.00000+00:00",
+    "row_count": 100000,
+    "distinct_count": 100000
+  },
+  {
+    "columns": ["y"],
+    "created_at": "2018-01-01 1:00:00.00000+00:00",
+    "row_count": 100000,
+    "distinct_count": 2
+  }
+]';
+----
+
+# Regression test for #99389.
+assign-placeholders-opt query-args=(1) format=show-stats
+WITH RECURSIVE cte(a,b) AS (
+  (SELECT * FROM xy WHERE x = $1)
+  UNION ALL
+  (SELECT * FROM cte WHERE False)
+)
+SELECT * FROM cte;
+----
+project
+ ├── columns: a:10 b:11
+ ├── stats: [rows=10]
+ ├── recursive-c-t-e
+ │    ├── columns: a:6 b:7
+ │    ├── working table binding: &1
+ │    ├── initial columns: x:1 y:2
+ │    ├── recursive columns: a:8 b:9
+ │    ├── stats: [rows=10]
+ │    ├── fake-rel
+ │    │    ├── columns: a:6 b:7
+ │    │    ├── cardinality: [1 - ]
+ │    │    └── stats: [rows=1.00001]
+ │    ├── scan xy@xy_x_idx
+ │    │    ├── columns: x:1!null y:2
+ │    │    ├── constraint: /1/3: [/1 - /1]
+ │    │    ├── stats: [rows=1.00001, distinct(1)=1, null(1)=0]
+ │    │    └── fd: ()-->(1)
+ │    └── values
+ │         ├── columns: a:8!null b:9!null
+ │         ├── cardinality: [0 - 0]
+ │         ├── stats: [rows=0]
+ │         ├── key: ()
+ │         └── fd: ()-->(8,9)
+ └── projections
+      ├── a:6 [as=a:10, outer=(6)]
+      └── b:7 [as=b:11, outer=(7)]