Fix EXPLAIN failure when deparsing SQL/JSON aggregates

If an expression containing an aggregate is evaluated above the plan
node that computes the aggregate, as happens with window functions or
with expressions postponed to above the final sort, setrefs.c replaces
the Aggref or WindowFunc with a Var referencing the lower node's
output.  For SQL/JSON aggregates such as JSON_ARRAYAGG and
JSON_OBJECTAGG, deparsing the containing JsonConstructorExpr then
failed with "invalid JsonConstructorExpr underlying node type", since
get_json_agg_constructor() did not expect a Var there.

Fix by resolving the Var back to the underlying Aggref or WindowFunc
and deparsing the constructor as if the aggregate were computed at the
current node.  The JsonConstructorExpr retains the RETURNING clause
and the ABSENT/NULL ON NULL and WITH UNIQUE options, and the arguments
come from the resolved aggregate, so the original JSON aggregate
syntax is reproduced in full.  This mirrors how get_agg_expr() already
looks through such a Var when deparsing a combining aggregate.

Reported-by: Thom Brown <thom@linux.com>
Author: Richard Guo <guofenglinux@gmail.com>
Discussion: https://postgr.es/m/CAA-aLv5QYTaMOk=Qhv6cgwceeHETZV8YJvWZ_rH+yVZCuchATA@mail.gmail.com
Backpatch-through: 16

diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c
index 3d6e6bdbfd21b1be4faed9e6948873f7a3326fb8..e3e23433192e3d7e4e1f29b5851231a0e1098793 100644 (file)
--- a/src/backend/utils/adt/ruleutils.c
+++ b/src/backend/utils/adt/ruleutils.c
@@ -503,6 +503,8 @@ static void get_json_agg_constructor(JsonConstructorExpr *ctor,
                                                                         deparse_context *context,
                                                                         const char *funcname,
                                                                         bool is_json_objectagg);
+static void get_json_agg_constructor_expr(Node *node, deparse_context *context,
+                                                                                 void *callback_arg);
 static void simple_quote_literal(StringInfo buf, const char *val);
 static void get_sublink_expr(SubLink *sublink, deparse_context *context);
 static void get_tablefunc(TableFunc *tf, deparse_context *context,
@@ -11781,11 +11783,41 @@ get_json_agg_constructor(JsonConstructorExpr *ctor, deparse_context *context,
                get_windowfunc_expr_helper((WindowFunc *) ctor->func, context,
                                                                   funcname, options.data,
                                                                   is_json_objectagg);
+       else if (IsA(ctor->func, Var))
+       {
+               /*
+                * If the aggregate is computed by a lower plan node, setrefs.c will
+                * have replaced the Aggref or WindowFunc with a Var referencing that
+                * node's output.  Chase the Var back to it so we can still print the
+                * original JSON aggregate syntax.  This only happens in EXPLAIN.
+                */
+               resolve_special_varno((Node *) ctor->func, context,
+                                                         get_json_agg_constructor_expr, ctor);
+       }
        else
                elog(ERROR, "invalid JsonConstructorExpr underlying node type: %d",
                         nodeTag(ctor->func));
 }
 
+/*
+ * Deparse a JsonConstructorExpr whose aggregate is computed by a lower plan
+ * node; resolve_special_varno has located the underlying Aggref/WindowFunc.
+ */
+static void
+get_json_agg_constructor_expr(Node *node, deparse_context *context,
+                                                         void *callback_arg)
+{
+       JsonConstructorExpr ctor;
+
+       if (!IsA(node, Aggref) && !IsA(node, WindowFunc))
+               elog(ERROR, "JSON aggregate constructor does not point to an Aggref or WindowFunc");
+
+       /* Flat copy suffices; we only replace func. */
+       ctor = *(JsonConstructorExpr *) callback_arg;
+       ctor.func = (Expr *) node;
+       get_json_constructor(&ctor, context, false);
+}
+
 /*
  * simple_quote_literal - Format a string as a SQL literal, append to buf
  */

diff --git a/src/test/regress/expected/sqljson.out b/src/test/regress/expected/sqljson.out
index 6b0d881550839951025776974a0d1c50a7bfbe0e..0d2fedb7d8357c45bd0e6edcc27bc2819bade801 100644 (file)
--- a/src/test/regress/expected/sqljson.out
+++ b/src/test/regress/expected/sqljson.out
@@ -1411,3 +1411,104 @@ SELECT JSON_OBJECT('a': JSON_OBJECTAGG('b': 1 RETURNING text) FORMAT JSON);
 (1 row)
 
 DROP FUNCTION volatile_one, stable_one;
+-- Test deparsing of JSON aggregates that are computed below a WindowAgg
+-- node.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT i % 2 AS g,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING jsonb) AS ja,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING text) AS ja_text,
+       JSON_ARRAYAGG(i ORDER BY i NULL ON NULL RETURNING jsonb) AS ja_null,
+       JSON_OBJECTAGG(i: i ABSENT ON NULL RETURNING jsonb) AS jo_absent,
+       JSON_OBJECTAGG(i: i WITH UNIQUE RETURNING jsonb) AS jo_unique,
+       row_number() OVER (ORDER BY i % 2) AS rn
+FROM generate_series(1, 3) i
+GROUP BY i % 2;
+                                                                                                                                                 QUERY PLAN                                                                                                                                                 
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ WindowAgg
+   Output: ((i % 2)), JSON_ARRAYAGG(i ORDER BY i RETURNING jsonb), JSON_ARRAYAGG(i ORDER BY i RETURNING text), JSON_ARRAYAGG(i ORDER BY i NULL ON NULL RETURNING jsonb), JSON_OBJECTAGG(i : i ABSENT ON NULL RETURNING jsonb), JSON_OBJECTAGG(i : i WITH UNIQUE KEYS RETURNING jsonb), row_number() OVER w1
+   Window: w1 AS (ORDER BY ((i.i % 2)) ROWS UNBOUNDED PRECEDING)
+   ->  GroupAggregate
+         Output: ((i % 2)), jsonb_agg_strict(i ORDER BY i), json_agg_strict(i ORDER BY i), jsonb_agg(i ORDER BY i), jsonb_object_agg_strict(i, i), jsonb_object_agg_unique(i, i)
+         Group Key: ((i.i % 2))
+         ->  Sort
+               Output: ((i % 2)), i
+               Sort Key: ((i.i % 2)), i.i
+               ->  Function Scan on pg_catalog.generate_series i
+                     Output: (i % 2), i
+                     Function Call: generate_series(1, 3)
+(12 rows)
+
+SELECT i % 2 AS g,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING jsonb) AS ja,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING text) AS ja_text,
+       JSON_ARRAYAGG(i ORDER BY i NULL ON NULL RETURNING jsonb) AS ja_null,
+       JSON_OBJECTAGG(i: i ABSENT ON NULL RETURNING jsonb) AS jo_absent,
+       JSON_OBJECTAGG(i: i WITH UNIQUE RETURNING jsonb) AS jo_unique,
+       row_number() OVER (ORDER BY i % 2) AS rn
+FROM generate_series(1, 3) i
+GROUP BY i % 2;
+ g |   ja   | ja_text | ja_null |    jo_absent     |    jo_unique     | rn 
+---+--------+---------+---------+------------------+------------------+----
+ 0 | [2]    | [2]     | [2]     | {"2": 2}         | {"2": 2}         |  1
+ 1 | [1, 3] | [1, 3]  | [1, 3]  | {"1": 1, "3": 3} | {"1": 1, "3": 3} |  2
+(2 rows)
+
+-- The same, but with the JSON aggregate used as a window function that is
+-- computed below another WindowAgg node.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT JSON_ARRAYAGG(i NULL ON NULL RETURNING jsonb) OVER (ORDER BY i DESC) AS ja,
+       row_number() OVER (ORDER BY i) AS rn
+FROM generate_series(1, 3) i;
+                                        QUERY PLAN                                        
+------------------------------------------------------------------------------------------
+ WindowAgg
+   Output: JSON_ARRAYAGG(i NULL ON NULL RETURNING jsonb) OVER w1, row_number() OVER w2, i
+   Window: w2 AS (ORDER BY i.i ROWS UNBOUNDED PRECEDING)
+   ->  Sort
+         Output: i, (jsonb_agg(i) OVER w1)
+         Sort Key: i.i
+         ->  WindowAgg
+               Output: i, jsonb_agg(i) OVER w1
+               Window: w1 AS (ORDER BY i.i)
+               ->  Sort
+                     Output: i
+                     Sort Key: i.i DESC
+                     ->  Function Scan on pg_catalog.generate_series i
+                           Output: i
+                           Function Call: generate_series(1, 3)
+(15 rows)
+
+SELECT JSON_ARRAYAGG(i NULL ON NULL RETURNING jsonb) OVER (ORDER BY i DESC) AS ja,
+       row_number() OVER (ORDER BY i) AS rn
+FROM generate_series(1, 3) i;
+    ja     | rn 
+-----------+----
+ [3, 2, 1] |  1
+ [3, 2]    |  2
+ [3]       |  3
+(3 rows)
+
+-- The same, but with the expression containing the JSON aggregate postponed
+-- to above the final sort due to being volatile.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT i % 2 AS g,
+          JSON_ARRAYAGG(i RETURNING text) || random()::text AS ja
+FROM generate_series(1, 3) i
+GROUP BY i % 2
+ORDER BY count(*);
+                                       QUERY PLAN                                       
+----------------------------------------------------------------------------------------
+ Result
+   Output: ((i % 2)), (JSON_ARRAYAGG(i RETURNING text) || (random())::text), (count(*))
+   ->  Sort
+         Output: ((i % 2)), (count(*)), (json_agg_strict(i))
+         Sort Key: (count(*))
+         ->  HashAggregate
+               Output: ((i % 2)), count(*), json_agg_strict(i)
+               Group Key: (i.i % 2)
+               ->  Function Scan on pg_catalog.generate_series i
+                     Output: (i % 2), i
+                     Function Call: generate_series(1, 3)
+(11 rows)
+

diff --git a/src/test/regress/sql/sqljson.sql b/src/test/regress/sql/sqljson.sql
index 0b77deb3b24b77b53faff38f1a4a6c7aeb294874..a995bfa9153d31096f3133b2ed64b930bcdc8b07 100644 (file)
--- a/src/test/regress/sql/sqljson.sql
+++ b/src/test/regress/sql/sqljson.sql
@@ -529,3 +529,44 @@ SELECT JSON_OBJECT('a': JSON_OBJECTAGG('b': stable_one() RETURNING text) FORMAT
 EXPLAIN (VERBOSE, COSTS OFF) SELECT JSON_OBJECT('a': JSON_OBJECTAGG('b': 1 RETURNING text) FORMAT JSON);
 SELECT JSON_OBJECT('a': JSON_OBJECTAGG('b': 1 RETURNING text) FORMAT JSON);
 DROP FUNCTION volatile_one, stable_one;
+
+-- Test deparsing of JSON aggregates that are computed below a WindowAgg
+-- node.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT i % 2 AS g,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING jsonb) AS ja,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING text) AS ja_text,
+       JSON_ARRAYAGG(i ORDER BY i NULL ON NULL RETURNING jsonb) AS ja_null,
+       JSON_OBJECTAGG(i: i ABSENT ON NULL RETURNING jsonb) AS jo_absent,
+       JSON_OBJECTAGG(i: i WITH UNIQUE RETURNING jsonb) AS jo_unique,
+       row_number() OVER (ORDER BY i % 2) AS rn
+FROM generate_series(1, 3) i
+GROUP BY i % 2;
+SELECT i % 2 AS g,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING jsonb) AS ja,
+       JSON_ARRAYAGG(i ORDER BY i RETURNING text) AS ja_text,
+       JSON_ARRAYAGG(i ORDER BY i NULL ON NULL RETURNING jsonb) AS ja_null,
+       JSON_OBJECTAGG(i: i ABSENT ON NULL RETURNING jsonb) AS jo_absent,
+       JSON_OBJECTAGG(i: i WITH UNIQUE RETURNING jsonb) AS jo_unique,
+       row_number() OVER (ORDER BY i % 2) AS rn
+FROM generate_series(1, 3) i
+GROUP BY i % 2;
+
+-- The same, but with the JSON aggregate used as a window function that is
+-- computed below another WindowAgg node.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT JSON_ARRAYAGG(i NULL ON NULL RETURNING jsonb) OVER (ORDER BY i DESC) AS ja,
+       row_number() OVER (ORDER BY i) AS rn
+FROM generate_series(1, 3) i;
+SELECT JSON_ARRAYAGG(i NULL ON NULL RETURNING jsonb) OVER (ORDER BY i DESC) AS ja,
+       row_number() OVER (ORDER BY i) AS rn
+FROM generate_series(1, 3) i;
+
+-- The same, but with the expression containing the JSON aggregate postponed
+-- to above the final sort due to being volatile.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT i % 2 AS g,
+          JSON_ARRAYAGG(i RETURNING text) || random()::text AS ja
+FROM generate_series(1, 3) i
+GROUP BY i % 2
+ORDER BY count(*);