Improve test coverage for multi-column MCV lists

The regression tests for extended statistics were not testing a couple
of important cases for the MCV lists:

  * IS NOT NULL clauses - We did have queries with IS NULL clauses, but
    not the negative case.

  * clauses with variable on the right - All the clauses had the Var on
    the left, i.e. (Var op Const), so this adds (Const op Var) too.

  * columns with fixed-length types passed by reference - All columns
    were using either by-value or varlena types, so add a test with
    UUID columns too. This matters for (de)serialization.

  * NULL-only dimension - When one of the columns contains only NULL
    values, we treat it a a special case during (de)serialization.

  * arrays containing NULL - When the constant parameter contains NULL
    value, we need to handle it correctly during estimation, for all
    IN, ANY and ALL clauses.

Discussion: https://www.postgresql.org/message-id/flat/20200113230008.g67iyk4cs3xbnjju@development
Author: Tomas Vondra

src/test/regress/sql/stats_ext.sql

@@ -454,30 +454,50 @@ ANALYZE mcv_lists;
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 AND b = ''1''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 1 = a AND ''1'' = b');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < 1 AND b < ''1''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 1 > a AND ''1'' > b');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= 0 AND b <= ''0''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 0 >= a AND ''0'' >= b');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 AND b = ''1'' AND c = 1');
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < 5 AND b < ''1'' AND c < 5');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < 5 AND ''1'' > b AND 5 > c');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= 4 AND b <= ''0'' AND c <= 4');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 4 >= a AND ''0'' >= b AND 4 >= c');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1');
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1 OR d IS NOT NULL');
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52) AND b IN ( ''1'', ''2'')');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52, NULL) AND b IN ( ''1'', ''2'', NULL)');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2''])');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[NULL, 1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2'', NULL])');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, 2, 3]) AND b IN (''1'', ''2'', ''3'')');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, NULL, 2, 3]) AND b IN (''1'', ''2'', NULL, ''3'')');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3])');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3, NULL])');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', ''3'') AND c > ANY (ARRAY[1, 2, 3])');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', NULL, ''3'') AND c > ANY (ARRAY[1, 2, NULL, 3])');
+
 -- create statistics
 CREATE STATISTICS mcv_lists_stats (mcv) ON a, b, c FROM mcv_lists;
 
@@ -485,28 +505,48 @@ ANALYZE mcv_lists;
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 AND b = ''1''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 1 = a AND ''1'' = b');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < 1 AND b < ''1''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 1 > a AND ''1'' > b');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= 0 AND b <= ''0''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 0 >= a AND ''0'' >= b');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 AND b = ''1'' AND c = 1');
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < 5 AND b < ''1'' AND c < 5');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < 5 AND ''1'' > b AND 5 > c');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= 4 AND b <= ''0'' AND c <= 4');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE 4 >= a AND ''0'' >= b AND 4 >= c');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1');
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52) AND b IN ( ''1'', ''2'')');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52, NULL) AND b IN ( ''1'', ''2'', NULL)');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2''])');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[NULL, 1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2'', NULL])');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, 2, 3]) AND b IN (''1'', ''2'', ''3'')');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, NULL, 2, 3]) AND b IN (''1'', ''2'', NULL, ''3'')');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3])');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3, NULL])');
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', ''3'') AND c > ANY (ARRAY[1, 2, 3])');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', NULL, ''3'') AND c > ANY (ARRAY[1, 2, NULL, 3])');
+
 -- we can't use the statistic for OR clauses that are not fully covered (missing 'd' attribute)
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1 OR d IS NOT NULL');
 
@@ -545,6 +585,12 @@ SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND b IS NULL AND c IS NULL');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND b IS NOT NULL');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NOT NULL AND b IS NULL AND c IS NOT NULL');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (0, 1) AND b IN (''0'', ''1'')');
+
 -- create statistics
 CREATE STATISTICS mcv_lists_stats (mcv) ON a, b, c FROM mcv_lists;
 
@@ -554,6 +600,12 @@ SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND b IS NULL AND c IS NULL');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND b IS NOT NULL');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NOT NULL AND b IS NULL AND c IS NOT NULL');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (0, 1) AND b IN (''0'', ''1'')');
+
 -- test pg_mcv_list_items with a very simple (single item) MCV list
 TRUNCATE mcv_lists;
 INSERT INTO mcv_lists (a, b, c) SELECT 1, 2, 3 FROM generate_series(1,1000) s(i);
@@ -571,7 +623,7 @@ DROP STATISTICS mcv_lists_stats;
 
 INSERT INTO mcv_lists (a, b, c, d)
      SELECT
-         (CASE WHEN mod(i,2) = 0 THEN NULL ELSE 0 END),
+         NULL, -- always NULL
          (CASE WHEN mod(i,2) = 0 THEN NULL ELSE 'x' END),
          (CASE WHEN mod(i,2) = 0 THEN NULL ELSE 0 END),
          (CASE WHEN mod(i,2) = 0 THEN NULL ELSE 'x' END)
@@ -581,13 +633,59 @@ ANALYZE mcv_lists;
 
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE b = ''x'' OR d = ''x''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''x'' OR d = ''x''');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND (b = ''x'' OR d = ''x'')');
+
 -- create statistics
-CREATE STATISTICS mcv_lists_stats (mcv) ON b, d FROM mcv_lists;
+CREATE STATISTICS mcv_lists_stats (mcv) ON a, b, d FROM mcv_lists;
 
 ANALYZE mcv_lists;
 
+-- test pg_mcv_list_items with MCV list containing variable-length data and NULLs
+SELECT m.*
+  FROM pg_statistic_ext s, pg_statistic_ext_data d,
+       pg_mcv_list_items(d.stxdmcv) m
+ WHERE s.stxname = 'mcv_lists_stats'
+   AND d.stxoid = s.oid;
+
 SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE b = ''x'' OR d = ''x''');
 
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''x'' OR d = ''x''');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IS NULL AND (b = ''x'' OR d = ''x'')');
+
+-- mcv with pass-by-ref fixlen types, e.g. uuid
+CREATE TABLE mcv_lists_uuid (
+    a UUID,
+    b UUID,
+    c UUID
+);
+
+INSERT INTO mcv_lists_uuid (a, b, c)
+     SELECT
+         md5(mod(i,100)::text)::uuid,
+         md5(mod(i,50)::text)::uuid,
+         md5(mod(i,25)::text)::uuid
+     FROM generate_series(1,5000) s(i);
+
+ANALYZE mcv_lists_uuid;
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists_uuid WHERE a = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc'' AND b = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc''');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists_uuid WHERE a = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc'' AND b = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc'' AND c = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc''');
+
+CREATE STATISTICS mcv_lists_uuid_stats (mcv) ON a, b, c
+  FROM mcv_lists_uuid;
+
+ANALYZE mcv_lists_uuid;
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists_uuid WHERE a = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc'' AND b = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc''');
+
+SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists_uuid WHERE a = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc'' AND b = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc'' AND c = ''1679091c-5a88-0faf-6fb5-e6087eb1b2dc''');
+
+DROP TABLE mcv_lists_uuid;
+
 -- mcv with arrays
 CREATE TABLE mcv_lists_arrays (
     a TEXT[],