Fix EXPLAIN to handle SEARCH BREADTH FIRST queries.

The rewriter transformation for SEARCH BREADTH FIRST produces a
FieldSelect on a Var of type RECORD, where the Var references the
recursive union's worktable output.  EXPLAIN VERBOSE failed to handle
this case, because it only expected such Vars to appear in CteScans
not WorkTableScans.  Fix that, and add some test cases exercising
EXPLAIN on SEARCH and CYCLE queries.

In principle this oversight is an old bug, but it seems that the
case is unreachable without SEARCH BREADTH FIRST, because the
parser fails when attempting to create such a reference manually.
So for today I'll just patch HEAD/v14.  Someday we might find that
the code portion of this patch needs to be back-patched further.

Per report from Atsushi Torikoshi.

Discussion: https://postgr.es/m/5bafa66ad529e11860339565c9e7c166@oss.nttdata.com

diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c
index b932a83827f7185cf248145d5ad3108c331b62f3..b15bd81b9ca8827b9ffdf270ae590483c1bd7a3a 100644 (file)
--- a/src/backend/utils/adt/ruleutils.c
+++ b/src/backend/utils/adt/ruleutils.c
@@ -375,6 +375,8 @@ static void identify_join_columns(JoinExpr *j, RangeTblEntry *jrte,
                                  deparse_columns *colinfo);
 static char *get_rtable_name(int rtindex, deparse_context *context);
 static void set_deparse_plan(deparse_namespace *dpns, Plan *plan);
+static Plan *find_recursive_union(deparse_namespace *dpns,
+                                 WorkTableScan *wtscan);
 static void push_child_plan(deparse_namespace *dpns, Plan *plan,
                            deparse_namespace *save_dpns);
 static void pop_child_plan(deparse_namespace *dpns,
@@ -4866,6 +4868,9 @@ set_deparse_plan(deparse_namespace *dpns, Plan *plan)
     * For a SubqueryScan, pretend the subplan is INNER referent.  (We don't
     * use OUTER because that could someday conflict with the normal meaning.)
     * Likewise, for a CteScan, pretend the subquery's plan is INNER referent.
+    * For a WorkTableScan, locate the parent RecursiveUnion plan node and use
+    * that as INNER referent.
+    *
     * For ON CONFLICT .. UPDATE we just need the inner tlist to point to the
     * excluded expression's tlist. (Similar to the SubqueryScan we don't want
     * to reuse OUTER, it's used for RETURNING in some modify table cases,
@@ -4876,6 +4881,9 @@ set_deparse_plan(deparse_namespace *dpns, Plan *plan)
    else if (IsA(plan, CteScan))
        dpns->inner_plan = list_nth(dpns->subplans,
                                    ((CteScan *) plan)->ctePlanId - 1);
+   else if (IsA(plan, WorkTableScan))
+       dpns->inner_plan = find_recursive_union(dpns,
+                                               (WorkTableScan *) plan);
    else if (IsA(plan, ModifyTable))
        dpns->inner_plan = plan;
    else
@@ -4899,6 +4907,29 @@ set_deparse_plan(deparse_namespace *dpns, Plan *plan)
        dpns->index_tlist = NIL;
 }
 
+/*
+ * Locate the ancestor plan node that is the RecursiveUnion generating
+ * the WorkTableScan's work table.  We can match on wtParam, since that
+ * should be unique within the plan tree.
+ */
+static Plan *
+find_recursive_union(deparse_namespace *dpns, WorkTableScan *wtscan)
+{
+   ListCell   *lc;
+
+   foreach(lc, dpns->ancestors)
+   {
+       Plan       *ancestor = (Plan *) lfirst(lc);
+
+       if (IsA(ancestor, RecursiveUnion) &&
+           ((RecursiveUnion *) ancestor)->wtParam == wtscan->wtParam)
+           return ancestor;
+   }
+   elog(ERROR, "could not find RecursiveUnion for WorkTableScan with wtParam %d",
+        wtscan->wtParam);
+   return NULL;
+}
+
 /*
  * push_child_plan: temporarily transfer deparsing attention to a child plan
  *
@@ -7646,9 +7677,12 @@ get_name_for_var_field(Var *var, int fieldno,
                {
                    /*
                     * We're deparsing a Plan tree so we don't have a CTE
-                    * list.  But the only place we'd see a Var directly
-                    * referencing a CTE RTE is in a CteScan plan node, and we
-                    * can look into the subplan's tlist instead.
+                    * list.  But the only places we'd see a Var directly
+                    * referencing a CTE RTE are in CteScan or WorkTableScan
+                    * plan nodes.  For those cases, set_deparse_plan arranged
+                    * for dpns->inner_plan to be the plan node that emits the
+                    * CTE or RecursiveUnion result, and we can look at its
+                    * tlist instead.
                     */
                    TargetEntry *tle;
                    deparse_namespace save_dpns;

diff --git a/src/test/regress/expected/with.out b/src/test/regress/expected/with.out
index 622d5da7d272b585361c044c68ce54331f60d937..a3a2e383e3c98f24941e6f73fa6abed5665bf29d 100644 (file)
--- a/src/test/regress/expected/with.out
+++ b/src/test/regress/expected/with.out
@@ -644,6 +644,41 @@ insert into graph0 values
    (2, 3, 'arc 2 -> 3'),
    (1, 4, 'arc 1 -> 4'),
    (4, 5, 'arc 4 -> 5');
+explain (verbose, costs off)
+with recursive search_graph(f, t, label) as (
+   select * from graph0 g
+   union all
+   select g.*
+   from graph0 g, search_graph sg
+   where g.f = sg.t
+) search depth first by f, t set seq
+select * from search_graph order by seq;
+                                          QUERY PLAN                                          
+----------------------------------------------------------------------------------------------
+ Sort
+   Output: search_graph.f, search_graph.t, search_graph.label, search_graph.seq
+   Sort Key: search_graph.seq
+   CTE search_graph
+     ->  Recursive Union
+           ->  Seq Scan on pg_temp.graph0 g
+                 Output: g.f, g.t, g.label, ARRAY[ROW(g.f, g.t)]
+           ->  Merge Join
+                 Output: g_1.f, g_1.t, g_1.label, array_cat(sg.seq, ARRAY[ROW(g_1.f, g_1.t)])
+                 Merge Cond: (g_1.f = sg.t)
+                 ->  Sort
+                       Output: g_1.f, g_1.t, g_1.label
+                       Sort Key: g_1.f
+                       ->  Seq Scan on pg_temp.graph0 g_1
+                             Output: g_1.f, g_1.t, g_1.label
+                 ->  Sort
+                       Output: sg.seq, sg.t
+                       Sort Key: sg.t
+                       ->  WorkTable Scan on search_graph sg
+                             Output: sg.seq, sg.t
+   ->  CTE Scan on search_graph
+         Output: search_graph.f, search_graph.t, search_graph.label, search_graph.seq
+(22 rows)
+
 with recursive search_graph(f, t, label) as (
    select * from graph0 g
    union all
@@ -682,6 +717,41 @@ select * from search_graph order by seq;
  4 | 5 | arc 4 -> 5 | {"(4,5)"}
 (7 rows)
 
+explain (verbose, costs off)
+with recursive search_graph(f, t, label) as (
+   select * from graph0 g
+   union all
+   select g.*
+   from graph0 g, search_graph sg
+   where g.f = sg.t
+) search breadth first by f, t set seq
+select * from search_graph order by seq;
+                                           QUERY PLAN                                            
+-------------------------------------------------------------------------------------------------
+ Sort
+   Output: search_graph.f, search_graph.t, search_graph.label, search_graph.seq
+   Sort Key: search_graph.seq
+   CTE search_graph
+     ->  Recursive Union
+           ->  Seq Scan on pg_temp.graph0 g
+                 Output: g.f, g.t, g.label, ROW('0'::bigint, g.f, g.t)
+           ->  Merge Join
+                 Output: g_1.f, g_1.t, g_1.label, ROW(int8inc((sg.seq)."*DEPTH*"), g_1.f, g_1.t)
+                 Merge Cond: (g_1.f = sg.t)
+                 ->  Sort
+                       Output: g_1.f, g_1.t, g_1.label
+                       Sort Key: g_1.f
+                       ->  Seq Scan on pg_temp.graph0 g_1
+                             Output: g_1.f, g_1.t, g_1.label
+                 ->  Sort
+                       Output: sg.seq, sg.t
+                       Sort Key: sg.t
+                       ->  WorkTable Scan on search_graph sg
+                             Output: sg.seq, sg.t
+   ->  CTE Scan on search_graph
+         Output: search_graph.f, search_graph.t, search_graph.label, search_graph.seq
+(22 rows)
+
 with recursive search_graph(f, t, label) as (
    select * from graph0 g
    union all
@@ -945,6 +1015,39 @@ select * from search_graph order by path;
 (25 rows)
 
 -- CYCLE clause
+explain (verbose, costs off)
+with recursive search_graph(f, t, label) as (
+   select * from graph g
+   union all
+   select g.*
+   from graph g, search_graph sg
+   where g.f = sg.t
+) cycle f, t set is_cycle using path
+select * from search_graph;
+                                                                              QUERY PLAN                                                                               
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ CTE Scan on search_graph
+   Output: search_graph.f, search_graph.t, search_graph.label, search_graph.is_cycle, search_graph.path
+   CTE search_graph
+     ->  Recursive Union
+           ->  Seq Scan on pg_temp.graph g
+                 Output: g.f, g.t, g.label, false, ARRAY[ROW(g.f, g.t)]
+           ->  Merge Join
+                 Output: g_1.f, g_1.t, g_1.label, CASE WHEN (ROW(g_1.f, g_1.t) = ANY (sg.path)) THEN true ELSE false END, array_cat(sg.path, ARRAY[ROW(g_1.f, g_1.t)])
+                 Merge Cond: (g_1.f = sg.t)
+                 ->  Sort
+                       Output: g_1.f, g_1.t, g_1.label
+                       Sort Key: g_1.f
+                       ->  Seq Scan on pg_temp.graph g_1
+                             Output: g_1.f, g_1.t, g_1.label
+                 ->  Sort
+                       Output: sg.path, sg.t
+                       Sort Key: sg.t
+                       ->  WorkTable Scan on search_graph sg
+                             Output: sg.path, sg.t
+                             Filter: (NOT sg.is_cycle)
+(20 rows)
+
 with recursive search_graph(f, t, label) as (
    select * from graph g
    union all

diff --git a/src/test/regress/sql/with.sql b/src/test/regress/sql/with.sql
index 0476c55fee14b00febbc71d16299c8dbd2e243d7..46668a903eaffc6b4d6b1df587ce64b92baa0ca7 100644 (file)
--- a/src/test/regress/sql/with.sql
+++ b/src/test/regress/sql/with.sql
@@ -358,6 +358,16 @@ insert into graph0 values
    (1, 4, 'arc 1 -> 4'),
    (4, 5, 'arc 4 -> 5');
 
+explain (verbose, costs off)
+with recursive search_graph(f, t, label) as (
+   select * from graph0 g
+   union all
+   select g.*
+   from graph0 g, search_graph sg
+   where g.f = sg.t
+) search depth first by f, t set seq
+select * from search_graph order by seq;
+
 with recursive search_graph(f, t, label) as (
    select * from graph0 g
    union all
@@ -376,6 +386,16 @@ with recursive search_graph(f, t, label) as (
 ) search depth first by f, t set seq
 select * from search_graph order by seq;
 
+explain (verbose, costs off)
+with recursive search_graph(f, t, label) as (
+   select * from graph0 g
+   union all
+   select g.*
+   from graph0 g, search_graph sg
+   where g.f = sg.t
+) search breadth first by f, t set seq
+select * from search_graph order by seq;
+
 with recursive search_graph(f, t, label) as (
    select * from graph0 g
    union all
@@ -503,6 +523,16 @@ select * from search_graph order by path;
 
 -- CYCLE clause
 
+explain (verbose, costs off)
+with recursive search_graph(f, t, label) as (
+   select * from graph g
+   union all
+   select g.*
+   from graph g, search_graph sg
+   where g.f = sg.t
+) cycle f, t set is_cycle using path
+select * from search_graph;
+
 with recursive search_graph(f, t, label) as (
    select * from graph g
    union all