Fix handling of bare boolean expressions in mcv_get_match_bitmap.

tglsfdc · tglsfdc · commit 3fe2fc6bbdb2 · 2022-08-05T15:00:03.000-04:00
Since v14, the extended stats machinery will try to estimate for otherwise-unsupported boolean expressions if they match an expression available from an extended stats object. mcv.c did not get the memo about this, and would spit up with "unknown clause type". Fortunately the case is easy to handle, since we can expect the expression yields boolean. While here, replace some not-terribly-on-point assertions with simpler runtime tests for lookup failure. That seems appropriate so that we get an elog not a crash if we somehow get to the new it-should-be-a-bool-expression code with a subexpression that doesn't match any stats column. Per report from Danny Shemesh. Thanks to Justin Pryzby for preliminary investigation. Discussion: https://postgr.es/m/CAFZC=QqD6=27wQPOW1pbRa98KPyuyn+7cL_Ay_Ck-roZV84vHg@mail.gmail.com
diff --git a/src/backend/statistics/mcv.c b/src/backend/statistics/mcv.c
@@ -1531,13 +1531,13 @@ pg_mcv_list_send(PG_FUNCTION_ARGS)
 /*
  * match the attribute/expression to a dimension of the statistic
  *
- * Match the attribute/expression to statistics dimension. Optionally
- * determine the collation.
+ * Returns the zero-based index of the matching statistics dimension.
+ * Optionally determines the collation.
  */
 static int
 mcv_match_expression(Node *expr, Bitmapset *keys, List *exprs, Oid *collid)
 {
-	int			idx = -1;
+	int			idx;
 
 	if (IsA(expr, Var))
 	{
@@ -1549,20 +1549,19 @@ mcv_match_expression(Node *expr, Bitmapset *keys, List *exprs, Oid *collid)
 
 		idx = bms_member_index(keys, var->varattno);
 
-		/* make sure the index is valid */
-		Assert((idx >= 0) && (idx <= bms_num_members(keys)));
+		if (idx < 0)
+			elog(ERROR, "variable not found in statistics object");
 	}
 	else
 	{
+		/* expression - lookup in stats expressions */
 		ListCell   *lc;
 
-		/* expressions are stored after the simple columns */
-		idx = bms_num_members(keys);
-
 		if (collid)
 			*collid = exprCollation(expr);
 
-		/* expression - lookup in stats expressions */
+		/* expressions are stored after the simple columns */
+		idx = bms_num_members(keys);
 		foreach(lc, exprs)
 		{
 			Node	   *stat_expr = (Node *) lfirst(lc);
@@ -1573,13 +1572,10 @@ mcv_match_expression(Node *expr, Bitmapset *keys, List *exprs, Oid *collid)
 			idx++;
 		}
 
-		/* make sure the index is valid */
-		Assert((idx >= bms_num_members(keys)) &&
-			   (idx <= bms_num_members(keys) + list_length(exprs)));
+		if (lc == NULL)
+			elog(ERROR, "expression not found in statistics object");
 	}
 
-	Assert((idx >= 0) && (idx < bms_num_members(keys) + list_length(exprs)));
-
 	return idx;
 }
 
@@ -1659,8 +1655,6 @@ mcv_get_match_bitmap(PlannerInfo *root, List *clauses,
 			/* match the attribute/expression to a dimension of the statistic */
 			idx = mcv_match_expression(clause_expr, keys, exprs, &collid);
 
-			Assert((idx >= 0) && (idx < bms_num_members(keys) + list_length(exprs)));
-
 			/*
 			 * Walk through the MCV items and evaluate the current clause. We
 			 * can skip items that were already ruled out, and terminate if
@@ -1944,7 +1938,30 @@ mcv_get_match_bitmap(PlannerInfo *root, List *clauses,
 			}
 		}
 		else
-			elog(ERROR, "unknown clause type: %d", clause->type);
+		{
+			/* Otherwise, it must be a bare boolean-returning expression */
+			int			idx;
+
+			/* match the expression to a dimension of the statistic */
+			idx = mcv_match_expression(clause, keys, exprs, NULL);
+
+			/*
+			 * Walk through the MCV items and evaluate the current clause. We
+			 * can skip items that were already ruled out, and terminate if
+			 * there are no remaining MCV items that might possibly match.
+			 */
+			for (i = 0; i < mcvlist->nitems; i++)
+			{
+				bool		match;
+				MCVItem    *item = &mcvlist->items[i];
+
+				/* "match" just means it's bool TRUE */
+				match = !item->isnull[idx] && DatumGetBool(item->values[idx]);
+
+				/* now, update the match bitmap, depending on OR/AND type */
+				matches[i] = RESULT_MERGE(matches[i], is_or, match);
+			}
+		}
 	}
 
 	return matches;
diff --git a/src/test/regress/expected/stats_ext.out b/src/test/regress/expected/stats_ext.out
@@ -260,14 +260,23 @@ SELECT stxkind FROM pg_statistic_ext WHERE stxname = 'ab1_exprstat_3';
 CREATE STATISTICS ab1_exprstat_4 ON date_trunc('day', d) FROM ab1;
 -- date_trunc on timestamp is immutable
 CREATE STATISTICS ab1_exprstat_5 ON date_trunc('day', c) FROM ab1;
+-- check use of a boolean-returning expression
+CREATE STATISTICS ab1_exprstat_6 ON
+  (case a when 1 then true else false end), b FROM ab1;
 -- insert some data and run analyze, to test that these cases build properly
 INSERT INTO ab1
-SELECT
-    generate_series(1,10),
-    generate_series(1,10),
-    generate_series('2020-10-01'::timestamp, '2020-10-10'::timestamp, interval '1 day'),
-    generate_series('2020-10-01'::timestamptz, '2020-10-10'::timestamptz, interval '1 day');
+SELECT x / 10, x / 3,
+    '2020-10-01'::timestamp + x * interval '1 day',
+    '2020-10-01'::timestamptz + x * interval '1 day'
+FROM generate_series(1, 100) x;
 ANALYZE ab1;
+-- apply some stats
+SELECT * FROM check_estimated_rows('SELECT * FROM ab1 WHERE (case a when 1 then true else false end) AND b=2');
+ estimated | actual 
+-----------+--------
+         1 |      0
+(1 row)
+
 DROP TABLE ab1;
 -- Verify supported object types for extended statistics
 CREATE schema tststats;
diff --git a/src/test/regress/sql/stats_ext.sql b/src/test/regress/sql/stats_ext.sql
@@ -164,14 +164,21 @@ CREATE STATISTICS ab1_exprstat_4 ON date_trunc('day', d) FROM ab1;
 -- date_trunc on timestamp is immutable
 CREATE STATISTICS ab1_exprstat_5 ON date_trunc('day', c) FROM ab1;
 
+-- check use of a boolean-returning expression
+CREATE STATISTICS ab1_exprstat_6 ON
+  (case a when 1 then true else false end), b FROM ab1;
+
 -- insert some data and run analyze, to test that these cases build properly
 INSERT INTO ab1
-SELECT
-    generate_series(1,10),
-    generate_series(1,10),
-    generate_series('2020-10-01'::timestamp, '2020-10-10'::timestamp, interval '1 day'),
-    generate_series('2020-10-01'::timestamptz, '2020-10-10'::timestamptz, interval '1 day');
+SELECT x / 10, x / 3,
+    '2020-10-01'::timestamp + x * interval '1 day',
+    '2020-10-01'::timestamptz + x * interval '1 day'
+FROM generate_series(1, 100) x;
 ANALYZE ab1;
+
+-- apply some stats
+SELECT * FROM check_estimated_rows('SELECT * FROM ab1 WHERE (case a when 1 then true else false end) AND b=2');
+
 DROP TABLE ab1;
 
 -- Verify supported object types for extended statistics
