From c367fc69bfbd7e515cf26d4499483b56319f05db Mon Sep 17 00:00:00 2001
From: Tomas Vondra <tomas.vondra@postgresql.org>
Date: Mon, 16 Aug 2021 17:19:33 +0200
Subject: [PATCH 2/2] fix: identify single-attribute references

---
 src/backend/commands/statscmds.c        | 23 +++++++++++++++++++++++
 src/bin/pg_dump/t/002_pg_dump.pl        |  2 +-
 src/test/regress/expected/stats_ext.out |  2 ++
 src/test/regress/sql/stats_ext.sql      |  1 +
 4 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/src/backend/commands/statscmds.c b/src/backend/commands/statscmds.c
index 4856f4b41d..63c7529635 100644
--- a/src/backend/commands/statscmds.c
+++ b/src/backend/commands/statscmds.c
@@ -33,6 +33,7 @@
 #include "optimizer/optimizer.h"
 #include "statistics/statistics.h"
 #include "utils/builtins.h"
+#include "utils/lsyscache.h"
 #include "utils/fmgroids.h"
 #include "utils/inval.h"
 #include "utils/memutils.h"
@@ -258,6 +259,28 @@ CreateStatistics(CreateStatsStmt *stmt)
 			nattnums++;
 			ReleaseSysCache(atttuple);
 		}
+		else if (IsA(selem->expr, Var))
+		{
+			Var *var = (Var *) selem->expr;
+			TypeCacheEntry *type;
+
+			/* Disallow use of system attributes in extended stats */
+			if (var->varattno <= 0)
+				ereport(ERROR,
+						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+						 errmsg("statistics creation on system columns is not supported")));
+
+			/* Disallow data types without a less-than operator */
+			type = lookup_type_cache(var->vartype, TYPECACHE_LT_OPR);
+			if (type->lt_opr == InvalidOid)
+				ereport(ERROR,
+						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+						 errmsg("column \"%s\" cannot be used in statistics because its type %s has no default btree operator class",
+								get_attname(relid, var->varattno, false), format_type_be(var->vartype))));
+
+			attnums[nattnums] = var->varattno;
+			nattnums++;
+		}
 		else					/* expression */
 		{
 			Node	   *expr = selem->expr;
diff --git a/src/bin/pg_dump/t/002_pg_dump.pl b/src/bin/pg_dump/t/002_pg_dump.pl
index a4ee54d516..be1f3a5175 100644
--- a/src/bin/pg_dump/t/002_pg_dump.pl
+++ b/src/bin/pg_dump/t/002_pg_dump.pl
@@ -2811,7 +2811,7 @@ my %tests = (
 		create_sql   => 'CREATE STATISTICS dump_test.test_ext_stats_expr
 							ON (2 * col1) FROM dump_test.test_fifth_table',
 		regexp => qr/^
-			\QCREATE STATISTICS dump_test.test_ext_stats_expr ON ((2 * col1)) FROM dump_test.test_fifth_table;\E
+			\QCREATE STATISTICS dump_test.test_ext_stats_expr ON (2 * col1) FROM dump_test.test_fifth_table;\E
 		    /xms,
 		like =>
 		  { %full_runs, %dump_test_schema_runs, section_post_data => 1, },
diff --git a/src/test/regress/expected/stats_ext.out b/src/test/regress/expected/stats_ext.out
index 4e52910df2..2d7d05057f 100644
--- a/src/test/regress/expected/stats_ext.out
+++ b/src/test/regress/expected/stats_ext.out
@@ -55,6 +55,8 @@ ERROR:  duplicate expression in statistics definition
 CREATE STATISTICS tst (unrecognized) ON x, y FROM ext_stats_test;
 ERROR:  unrecognized statistics kind "unrecognized"
 -- incorrect expressions
+CREATE STATISTICS tst ON (y) FROM ext_stats_test; -- single column reference
+ERROR:  extended statistics require at least 2 columns
 CREATE STATISTICS tst ON y + z FROM ext_stats_test; -- missing parentheses
 ERROR:  syntax error at or near "+"
 LINE 1: CREATE STATISTICS tst ON y + z FROM ext_stats_test;
diff --git a/src/test/regress/sql/stats_ext.sql b/src/test/regress/sql/stats_ext.sql
index d563c4654c..9cdc34e82c 100644
--- a/src/test/regress/sql/stats_ext.sql
+++ b/src/test/regress/sql/stats_ext.sql
@@ -41,6 +41,7 @@ CREATE STATISTICS tst ON (x || 'x'), (x || 'x'), (y + 1), (x || 'x'), (x || 'x')
 CREATE STATISTICS tst ON (x || 'x'), (x || 'x'), y FROM ext_stats_test;
 CREATE STATISTICS tst (unrecognized) ON x, y FROM ext_stats_test;
 -- incorrect expressions
+CREATE STATISTICS tst ON (y) FROM ext_stats_test; -- single column reference
 CREATE STATISTICS tst ON y + z FROM ext_stats_test; -- missing parentheses
 CREATE STATISTICS tst ON (x, y) FROM ext_stats_test; -- tuple expression
 DROP TABLE ext_stats_test;
-- 
2.31.1