Merge

mysql-test/r/subselect2.result

@@ -123,14 +123,14 @@ DOCID	DOCNAME	DOCTYPEID	FOLDERID	AUTHOR	CREATED	TITLE	SUBTITLE	DOCABSTRACT	PUBLI
 c373e9f5ad07993f3859444553544200	Last Discussion	c373e9f5ad079174ff17444553544200	c373e9f5ad0796c0eca4444553544200	Goldilocks	2003-06-09 11:21:06	Title: Last Discussion	NULL	Setting new abstract and keeping doc checked out	2003-06-09 10:51:26	2003-06-09 10:51:26	NULL	NULL	NULL	03eea05112b845949f3fd03278b5fe43	2003-06-09 11:21:06	admin	0	NULL	Discussion	NULL	NULL
 EXPLAIN SELECT t2.*, t4.DOCTYPENAME, t1.CONTENTSIZE,t1.MIMETYPE FROM t2 INNER JOIN t4 ON t2.DOCTYPEID = t4.DOCTYPEID LEFT OUTER JOIN t1 ON t2.DOCID = t1.DOCID WHERE t2.FOLDERID IN(SELECT t3.FOLDERID FROM t3 WHERE t3.PARENTID IN(SELECT t3.FOLDERID FROM t3 WHERE t3.PARENTID IN(SELECT t3.FOLDERID FROM t3 WHERE t3.PARENTID IN(SELECT t3.FOLDERID FROM t3 WHERE t3.PARENTID IN(SELECT t3.FOLDERID FROM t3 WHERE t3.PARENTID='2f6161e879db43c1a5b82c21ddc49089' AND t3.FOLDERNAME = 'Level1') AND t3.FOLDERNAME = 'Level2') AND t3.FOLDERNAME = 'Level3') AND t3.FOLDERNAME = 'CopiedFolder') AND t3.FOLDERNAME = 'Movie Reviews') AND t2.DOCNAME = 'Last Discussion';
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
-1	PRIMARY	t2	ALL	DDOCTYPEID_IDX	NULL	NULL	NULL	9	Using where
+1	PRIMARY	t3	ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	CMFLDRPARNT_IDX	35	const	6	Using index condition; Using where
+1	PRIMARY	t3	ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	CMFLDRPARNT_IDX	35	test.t3.FOLDERID	1	Using where
+1	PRIMARY	t3	ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	CMFLDRPARNT_IDX	35	test.t3.FOLDERID	1	Using where
+1	PRIMARY	t3	ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	CMFLDRPARNT_IDX	35	test.t3.FOLDERID	1	Using where
+1	PRIMARY	t3	ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	CMFLDRPARNT_IDX	35	test.t3.FOLDERID	1	Using where
+1	PRIMARY	t2	ALL	DDOCTYPEID_IDX,DFOLDERID_IDX	NULL	NULL	NULL	9	Using where; Using join buffer (flat, BNL join)
 1	PRIMARY	t1	eq_ref	PRIMARY	PRIMARY	34	test.t2.DOCID	1	
 1	PRIMARY	t4	eq_ref	PRIMARY	PRIMARY	34	test.t2.DOCTYPEID	1	
-2	DEPENDENT SUBQUERY	t3	eq_ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	PRIMARY	34	func	1	Using where
-2	DEPENDENT SUBQUERY	t3	eq_ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	PRIMARY	34	test.t3.PARENTID	1	Using where
-2	DEPENDENT SUBQUERY	t3	eq_ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	PRIMARY	34	test.t3.PARENTID	1	Using where
-2	DEPENDENT SUBQUERY	t3	eq_ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	PRIMARY	34	test.t3.PARENTID	1	Using where
-2	DEPENDENT SUBQUERY	t3	eq_ref	PRIMARY,FFOLDERID_IDX,CMFLDRPARNT_IDX	PRIMARY	34	test.t3.PARENTID	1	Using where
 drop table t1, t2, t3, t4;
 CREATE TABLE t1 (a int(10) , PRIMARY KEY (a)) Engine=InnoDB;
 INSERT INTO t1 VALUES (1),(2);

mysql-test/r/subselect4.result

@@ -1200,33 +1200,33 @@ EXPLAIN
 SELECT * FROM t1 RIGHT JOIN t2 ON t1.c1 WHERE 's' IN (SELECT c1 FROM t2);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
 1	PRIMARY	t1	system	NULL	NULL	NULL	NULL	0	const row not found
-1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	
-2	DEPENDENT SUBQUERY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where; FirstMatch(t1)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using join buffer (flat, BNL join)
 SELECT * FROM t1 RIGHT JOIN t2 ON t1.c1 WHERE 's' IN (SELECT c1 FROM t2);
 c1	c1
 EXPLAIN
 SELECT * FROM t2 LEFT JOIN t1 ON t1.c1 WHERE 's' IN (SELECT c1 FROM t2);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
 1	PRIMARY	t1	system	NULL	NULL	NULL	NULL	0	const row not found
-1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	
-2	DEPENDENT SUBQUERY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where; FirstMatch(t1)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using join buffer (flat, BNL join)
 SELECT * FROM t2 LEFT JOIN t1 ON t1.c1 WHERE 's' IN (SELECT c1 FROM t2);
 c1	c1
 EXPLAIN
 SELECT * FROM (t2 LEFT JOIN t1 ON t1.c1) LEFT JOIN t3 on t3.c1 WHERE 's' IN (SELECT c1 FROM t2);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
 1	PRIMARY	t1	system	NULL	NULL	NULL	NULL	0	const row not found
-1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where; FirstMatch(t1)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using join buffer (flat, BNL join)
 1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	3	Using where
-2	DEPENDENT SUBQUERY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where
 SELECT * FROM (t2 LEFT JOIN t1 ON t1.c1) LEFT JOIN t3 on t3.c1 WHERE 's' IN (SELECT c1 FROM t2);
 c1	c1	c1
 EXPLAIN
 SELECT * FROM t4 LEFT JOIN t2 ON t4.c1 WHERE 's' IN (SELECT c1 FROM t2);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
-1	PRIMARY	t4	index	NULL	PRIMARY	3	NULL	2	Using index
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where; FirstMatch
+1	PRIMARY	t4	index	NULL	PRIMARY	3	NULL	2	Using index; Using join buffer (flat, BNL join)
 1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where
-2	DEPENDENT SUBQUERY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where
 SELECT * FROM t4 LEFT JOIN t2 ON t4.c1 WHERE 's' IN (SELECT c1 FROM t2);
 c1	c1
 drop table t1, t2, t3, t4;

mysql-test/r/subselect_sj.result

@@ -1277,9 +1277,9 @@ CREATE VIEW v1 AS SELECT 1;
 EXPLAIN
 SELECT * FROM t1 INNER JOIN t2 ON t2.a != 0 AND t2.a IN (SELECT * FROM v1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
-1	PRIMARY	<derived3>	system	NULL	NULL	NULL	NULL	1	
 1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	2	
 1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where; Using join buffer (flat, BNL join)
+2	DEPENDENT SUBQUERY	<derived3>	ALL	NULL	NULL	NULL	NULL	2	Using where
 3	DERIVED	NULL	NULL	NULL	NULL	NULL	NULL	NULL	No tables used
 SELECT * FROM t1 INNER JOIN t2 ON t2.a != 0 AND t2.a IN (SELECT * FROM v1);
 a	a
@@ -1358,4 +1358,161 @@ f10	f11
 0	0
 set optimizer_switch=@tmp_751484;
 drop table t1, t3;
+#
+# BUG#795530 Wrong result with subquery semijoin materialization and outer join 
+#  Simplified testcase that uses DuplicateElimination
+#
+create table t1 (a int);
+create table t2 (a int, b char(10));
+insert into t1 values (1),(2);
+insert into t2 values (1, 'one'), (3, 'three');
+create table t3 (b char(10));
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+explain select * from t3 where t3.b in (select t2.b from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	8	Using where; End temporary; Using join buffer (flat, BNL join)
+select * from t3 where t3.b in (select t2.b from t1 left join t2 on t1.a=t2.a);
+b
+drop table t1, t2, t3;
+#
+# BUG#600958 RQG: Crash in optimize_semijoin_nests
+#
+CREATE TABLE t1 (
+pk int(11) NOT NULL AUTO_INCREMENT,
+col_int_key int(11) DEFAULT NULL,
+col_date_key date DEFAULT NULL,
+col_varchar_key varchar(1) DEFAULT NULL,
+PRIMARY KEY (pk),
+KEY col_int_key (col_int_key),
+KEY col_date_key (col_date_key),
+KEY col_varchar_key (col_varchar_key,col_int_key)
+) ENGINE=MyISAM AUTO_INCREMENT=11 DEFAULT CHARSET=latin1;
+INSERT INTO t1 VALUES (10,8,'2002-02-21',NULL);
+CREATE TABLE t2 (
+pk int(11) NOT NULL AUTO_INCREMENT,
+col_int_key int(11) DEFAULT NULL,
+col_date_key date DEFAULT NULL,
+col_varchar_key varchar(1) DEFAULT NULL,
+PRIMARY KEY (pk),
+KEY col_int_key (col_int_key),
+KEY col_date_key (col_date_key),
+KEY col_varchar_key (col_varchar_key,col_int_key)
+) ENGINE=MyISAM AUTO_INCREMENT=2 DEFAULT CHARSET=latin1;
+INSERT INTO t2 VALUES (1,7,'1900-01-01','f');
+SELECT col_date_key FROM t1
+WHERE 5 IN (
+SELECT SUBQUERY3_t1 .col_int_key
+FROM t2 SUBQUERY3_t1
+LEFT JOIN t1 SUBQUERY3_t2 ON SUBQUERY3_t1 .col_varchar_key
+);
+col_date_key
+drop table t2, t1;
+#
+# No BUG#: Duplicate weedout check is not done for outer joins
+#
+create table t1 (a int);
+create table t2 (a int);
+insert into t1 values (1),(1),(2),(2);
+insert into t2 values (1);
+create table t0 (a int);
+insert into t0 values (1),(2);
+set @tmp_20110622= @@optimizer_switch;
+set optimizer_switch='firstmatch=off,loosescan=off,materialization=off';
+# Check DuplicateWeedout + join buffer
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Using join buffer (flat, BNL join)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+a
+1
+2
+# Check DuplicateWeedout without join buffer
+set @tmp_jcl_20110622= @@join_cache_level;
+set join_cache_level= 0;
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Start temporary
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+a
+1
+2
+# Check FirstMatch without join buffer:
+set optimizer_switch='firstmatch=on';
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; FirstMatch(t0)
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+a
+1
+2
+#
+# Now, check the same for multiple inner tables:
+alter table t2 add b int;
+update t2 set b=a;
+create table t3 as select * from t2;
+set optimizer_switch='firstmatch=off';
+set join_cache_level= 0;
+# DuplicateWeedout without join buffer
+explain 
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Start temporary
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	1	Using where
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+a
+1
+2
+set @@join_cache_level=@tmp_jcl_20110622;
+# DuplicateWeedout + join buffer
+explain
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Using join buffer (flat, BNL join)
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	1	Using where
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+a
+1
+2
+# Now, let the inner join side have a 'partial' match
+select * from t3;
+a	b
+1	1
+insert into t3 values(2,2);
+explain
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Using join buffer (flat, BNL join)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	2	Using where; End temporary
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+a
+1
+2
+set @@optimizer_switch=@tmp_20110622;
+drop table t0, t1, t2, t3;
 set @@optimizer_switch=@save_optimizer_switch;

mysql-test/r/subselect_sj_jcl6.result

@@ -1285,9 +1285,9 @@ CREATE VIEW v1 AS SELECT 1;
 EXPLAIN
 SELECT * FROM t1 INNER JOIN t2 ON t2.a != 0 AND t2.a IN (SELECT * FROM v1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
-1	PRIMARY	<derived3>	system	NULL	NULL	NULL	NULL	1	
 1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	2	
 1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where; Using join buffer (flat, BNL join)
+2	DEPENDENT SUBQUERY	<derived3>	ALL	NULL	NULL	NULL	NULL	2	Using where
 3	DERIVED	NULL	NULL	NULL	NULL	NULL	NULL	NULL	No tables used
 SELECT * FROM t1 INNER JOIN t2 ON t2.a != 0 AND t2.a IN (SELECT * FROM v1);
 a	a
@@ -1366,6 +1366,163 @@ f10	f11
 0	0
 set optimizer_switch=@tmp_751484;
 drop table t1, t3;
+#
+# BUG#795530 Wrong result with subquery semijoin materialization and outer join 
+#  Simplified testcase that uses DuplicateElimination
+#
+create table t1 (a int);
+create table t2 (a int, b char(10));
+insert into t1 values (1),(2);
+insert into t2 values (1, 'one'), (3, 'three');
+create table t3 (b char(10));
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+explain select * from t3 where t3.b in (select t2.b from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	2	Using where; Using join buffer (flat, BNL join)
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	8	Using where; End temporary; Using join buffer (incremental, BNL join)
+select * from t3 where t3.b in (select t2.b from t1 left join t2 on t1.a=t2.a);
+b
+drop table t1, t2, t3;
+#
+# BUG#600958 RQG: Crash in optimize_semijoin_nests
+#
+CREATE TABLE t1 (
+pk int(11) NOT NULL AUTO_INCREMENT,
+col_int_key int(11) DEFAULT NULL,
+col_date_key date DEFAULT NULL,
+col_varchar_key varchar(1) DEFAULT NULL,
+PRIMARY KEY (pk),
+KEY col_int_key (col_int_key),
+KEY col_date_key (col_date_key),
+KEY col_varchar_key (col_varchar_key,col_int_key)
+) ENGINE=MyISAM AUTO_INCREMENT=11 DEFAULT CHARSET=latin1;
+INSERT INTO t1 VALUES (10,8,'2002-02-21',NULL);
+CREATE TABLE t2 (
+pk int(11) NOT NULL AUTO_INCREMENT,
+col_int_key int(11) DEFAULT NULL,
+col_date_key date DEFAULT NULL,
+col_varchar_key varchar(1) DEFAULT NULL,
+PRIMARY KEY (pk),
+KEY col_int_key (col_int_key),
+KEY col_date_key (col_date_key),
+KEY col_varchar_key (col_varchar_key,col_int_key)
+) ENGINE=MyISAM AUTO_INCREMENT=2 DEFAULT CHARSET=latin1;
+INSERT INTO t2 VALUES (1,7,'1900-01-01','f');
+SELECT col_date_key FROM t1
+WHERE 5 IN (
+SELECT SUBQUERY3_t1 .col_int_key
+FROM t2 SUBQUERY3_t1
+LEFT JOIN t1 SUBQUERY3_t2 ON SUBQUERY3_t1 .col_varchar_key
+);
+col_date_key
+drop table t2, t1;
+#
+# No BUG#: Duplicate weedout check is not done for outer joins
+#
+create table t1 (a int);
+create table t2 (a int);
+insert into t1 values (1),(1),(2),(2);
+insert into t2 values (1);
+create table t0 (a int);
+insert into t0 values (1),(2);
+set @tmp_20110622= @@optimizer_switch;
+set optimizer_switch='firstmatch=off,loosescan=off,materialization=off';
+# Check DuplicateWeedout + join buffer
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Using join buffer (flat, BNL join)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary; Using join buffer (incremental, BNL join)
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+a
+1
+2
+# Check DuplicateWeedout without join buffer
+set @tmp_jcl_20110622= @@join_cache_level;
+set join_cache_level= 0;
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Start temporary
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+a
+1
+2
+# Check FirstMatch without join buffer:
+set optimizer_switch='firstmatch=on';
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; FirstMatch(t0)
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+a
+1
+2
+#
+# Now, check the same for multiple inner tables:
+alter table t2 add b int;
+update t2 set b=a;
+create table t3 as select * from t2;
+set optimizer_switch='firstmatch=off';
+set join_cache_level= 0;
+# DuplicateWeedout without join buffer
+explain 
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Start temporary
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	1	Using where
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+a
+1
+2
+set @@join_cache_level=@tmp_jcl_20110622;
+# DuplicateWeedout + join buffer
+explain
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Using join buffer (flat, BNL join)
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	1	Using where; Using join buffer (incremental, BNL join)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using where; End temporary; Using join buffer (incremental, BNL join)
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+a
+1
+2
+# Now, let the inner join side have a 'partial' match
+select * from t3;
+a	b
+1	1
+insert into t3 values(2,2);
+explain
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
+1	PRIMARY	t0	ALL	NULL	NULL	NULL	NULL	2	Start temporary
+1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	4	Using where; Using join buffer (flat, BNL join)
+1	PRIMARY	t2	ALL	NULL	NULL	NULL	NULL	1	Using join buffer (incremental, BNL join)
+1	PRIMARY	t3	ALL	NULL	NULL	NULL	NULL	2	Using where; End temporary; Using join buffer (incremental, BNL join)
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+a
+1
+2
+set @@optimizer_switch=@tmp_20110622;
+drop table t0, t1, t2, t3;
 set @@optimizer_switch=@save_optimizer_switch;
 #
 # BUG#49129: Wrong result with IN-subquery with join_cache_level=6 and firstmatch=off

mysql-test/r/subselect_sj_mat.result

@@ -365,7 +365,7 @@ id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 3	DEPENDENT SUBQUERY	t3a	ALL	NULL	NULL	NULL	NULL	4	100.00	Using where
 Warnings:
 Note	1276	Field or reference 'test.t1.a1' of SELECT #3 was resolved in SELECT #1
-Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` semi join (`test`.`t2`) semi join (`test`.`t2i` join `test`.`t3` `t3c`) where ((`test`.`t2`.`b2` = `test`.`t1`.`a2`) and (`test`.`t2i`.`b2` = `test`.`t3c`.`c2`) and (`test`.`t2`.`b1` = `test`.`t1`.`a1`) and (`test`.`t2i`.`b1` = `test`.`t3c`.`c1`) and (<expr_cache><`test`.`t2`.`b2`,`test`.`t1`.`a1`>(<in_optimizer>(`test`.`t2`.`b2`,<exists>(select `test`.`t3a`.`c2` from `test`.`t3` `t3a` where ((`test`.`t3a`.`c1` = `test`.`t1`.`a1`) and (<cache>(`test`.`t2`.`b2`) = `test`.`t3a`.`c2`))))) or <expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3b`.`c2` from `test`.`t3` `t3b` where (`test`.`t3b`.`c2` like '%03') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery4>`.`c2`))))))) and (`test`.`t3c`.`c2` > '0'))
+Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` semi join (`test`.`t2`) semi join (`test`.`t2i` join `test`.`t3` `t3c`) where ((`test`.`t2`.`b2` = `test`.`t1`.`a2`) and (`test`.`t2i`.`b2` = `test`.`t3c`.`c2`) and (`test`.`t2`.`b1` = `test`.`t1`.`a1`) and (`test`.`t2i`.`b1` = `test`.`t3c`.`c1`) and (<expr_cache><`test`.`t2`.`b2`,`test`.`t1`.`a1`>(<in_optimizer>(`test`.`t2`.`b2`,<exists>(select `test`.`t3a`.`c2` from `test`.`t3` `t3a` where ((`test`.`t1`.`a1` = `test`.`t3a`.`c1`) and (<cache>(`test`.`t2`.`b2`) = `test`.`t3a`.`c2`))))) or <expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3b`.`c2` from `test`.`t3` `t3b` where (`test`.`t3b`.`c2` like '%03') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery4>`.`c2`))))))) and (`test`.`t3c`.`c2` > '0'))
 select * from t1
 where (a1, a2) in (select b1, b2 from t2
 where b2 in (select c2 from t3 t3a where c1 = a1) or
@@ -504,7 +504,7 @@ id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 Warnings:
 Note	1276	Field or reference 'test.t1.a1' of SELECT #3 was resolved in SELECT #1
 Note	1276	Field or reference 'test.t1.a2' of SELECT #6 was resolved in SELECT #1
-Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` semi join (`test`.`t2`) semi join (`test`.`t2i` join `test`.`t3` `t3c`) where ((`test`.`t2i`.`b2` = `test`.`t1`.`a2`) and (`test`.`t2`.`b2` = `test`.`t1`.`a2`) and (`test`.`t3c`.`c2` = `test`.`t1`.`a2`) and (`test`.`t2i`.`b1` = `test`.`t1`.`a1`) and (`test`.`t2`.`b1` = `test`.`t1`.`a1`) and (`test`.`t3c`.`c1` = `test`.`t1`.`a1`) and (<expr_cache><`test`.`t2`.`b2`,`test`.`t1`.`a1`>(<in_optimizer>(`test`.`t2`.`b2`,<exists>(select `test`.`t3a`.`c2` from `test`.`t3` `t3a` where ((`test`.`t3a`.`c1` = `test`.`t1`.`a1`) and (<cache>(`test`.`t2`.`b2`) = `test`.`t3a`.`c2`))))) or <expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3b`.`c2` from `test`.`t3` `t3b` where (`test`.`t3b`.`c2` like '%03') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery4>`.`c2`))))))))
+Note	1003	select `test`.`t1`.`a1` AS `a1`,`test`.`t1`.`a2` AS `a2` from `test`.`t1` semi join (`test`.`t2`) semi join (`test`.`t2i` join `test`.`t3` `t3c`) where ((`test`.`t2i`.`b2` = `test`.`t1`.`a2`) and (`test`.`t2`.`b2` = `test`.`t1`.`a2`) and (`test`.`t3c`.`c2` = `test`.`t1`.`a2`) and (`test`.`t2i`.`b1` = `test`.`t1`.`a1`) and (`test`.`t2`.`b1` = `test`.`t1`.`a1`) and (`test`.`t3c`.`c1` = `test`.`t1`.`a1`) and (<expr_cache><`test`.`t2`.`b2`,`test`.`t1`.`a1`>(<in_optimizer>(`test`.`t2`.`b2`,<exists>(select `test`.`t3a`.`c2` from `test`.`t3` `t3a` where ((`test`.`t1`.`a1` = `test`.`t3a`.`c1`) and (<cache>(`test`.`t2`.`b2`) = `test`.`t3a`.`c2`))))) or <expr_cache><`test`.`t2`.`b2`>(<in_optimizer>(`test`.`t2`.`b2`,`test`.`t2`.`b2` in ( <materialize> (select `test`.`t3b`.`c2` from `test`.`t3` `t3b` where (`test`.`t3b`.`c2` like '%03') ), <primary_index_lookup>(`test`.`t2`.`b2` in <temporary table> on distinct_key where ((`test`.`t2`.`b2` = `<subquery4>`.`c2`))))))))
 explain extended
 select * from t1 where (a1, a2) in (select '1 - 01', '2 - 01');
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
@@ -636,7 +636,7 @@ from t1_16
 where a1 in (select substring(b1,1,16) from t2_16 where b1 > '0');
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1_16	ALL	NULL	NULL	NULL	NULL	3	100.00	
-1	PRIMARY	<subquery2>	eq_ref	distinct_key	distinct_key	20	func	1	100.00	Using where
+1	PRIMARY	<subquery2>	eq_ref	distinct_key	distinct_key	20	func	1	100.00	
 2	SUBQUERY	t2_16	ALL	NULL	NULL	NULL	NULL	3	100.00	Using where
 Warnings:
 Note	1003	select left(`test`.`t1_16`.`a1`,7) AS `left(a1,7)`,left(`test`.`t1_16`.`a2`,7) AS `left(a2,7)` from `test`.`t1_16` semi join (`test`.`t2_16`) where ((`test`.`t2_16`.`b1` > '0') and (`test`.`t1_16`.`a1` = substr(`test`.`t2_16`.`b1`,1,16)))
@@ -751,7 +751,7 @@ from t1_512
 where a1 in (select substring(b1,1,512) from t2_512 where b1 > '0');
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1_512	ALL	NULL	NULL	NULL	NULL	3	100.00	
-1	PRIMARY	<subquery2>	eq_ref	distinct_key	distinct_key	517	func	1	100.00	Using where
+1	PRIMARY	<subquery2>	eq_ref	distinct_key	distinct_key	517	func	1	100.00	
 2	SUBQUERY	t2_512	ALL	NULL	NULL	NULL	NULL	3	100.00	Using where
 Warnings:
 Note	1003	select left(`test`.`t1_512`.`a1`,7) AS `left(a1,7)`,left(`test`.`t1_512`.`a2`,7) AS `left(a2,7)` from `test`.`t1_512` semi join (`test`.`t2_512`) where ((`test`.`t2_512`.`b1` > '0') and (`test`.`t1_512`.`a1` = substr(`test`.`t2_512`.`b1`,1,512)))
@@ -847,7 +847,7 @@ from t1_1024
 where a1 in (select substring(b1,1,1024) from t2_1024 where b1 > '0');
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1_1024	ALL	NULL	NULL	NULL	NULL	3	100.00	
-1	PRIMARY	<subquery2>	eq_ref	NULL	distinct_key	15	func,func	1	100.00	Using where
+1	PRIMARY	<subquery2>	eq_ref	NULL	distinct_key	15	func,func	1	100.00	
 2	SUBQUERY	t2_1024	ALL	NULL	NULL	NULL	NULL	3	100.00	Using where
 Warnings:
 Note	1003	select left(`test`.`t1_1024`.`a1`,7) AS `left(a1,7)`,left(`test`.`t1_1024`.`a2`,7) AS `left(a2,7)` from `test`.`t1_1024` semi join (`test`.`t2_1024`) where ((`test`.`t2_1024`.`b1` > '0') and (`test`.`t1_1024`.`a1` = substr(`test`.`t2_1024`.`b1`,1,1024)))
@@ -941,7 +941,7 @@ from t1_1025
 where a1 in (select substring(b1,1,1025) from t2_1025 where b1 > '0');
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	filtered	Extra
 1	PRIMARY	t1_1025	ALL	NULL	NULL	NULL	NULL	3	100.00	
-1	PRIMARY	<subquery2>	eq_ref	NULL	distinct_key	15	func,func	1	100.00	Using where
+1	PRIMARY	<subquery2>	eq_ref	NULL	distinct_key	15	func,func	1	100.00	
 2	SUBQUERY	t2_1025	ALL	NULL	NULL	NULL	NULL	3	100.00	Using where
 Warnings:
 Note	1003	select left(`test`.`t1_1025`.`a1`,7) AS `left(a1,7)`,left(`test`.`t1_1025`.`a2`,7) AS `left(a2,7)` from `test`.`t1_1025` semi join (`test`.`t2_1025`) where ((`test`.`t2_1025`.`b1` > '0') and (`test`.`t1_1025`.`a1` = substr(`test`.`t2_1025`.`b1`,1,1025)))
@@ -1219,7 +1219,7 @@ insert into t1 values ('aa', 'aaaa');
 explain select a,b from t1 where b in (select a from t1);
 id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra
 1	PRIMARY	t1	ALL	NULL	NULL	NULL	NULL	2	
-1	PRIMARY	<subquery2>	eq_ref	distinct_key	distinct_key	3	func	1	Using where
+1	PRIMARY	<subquery2>	eq_ref	distinct_key	distinct_key	3	func	1	
 2	SUBQUERY	t1	ALL	NULL	NULL	NULL	NULL	2	
 select a,b from t1 where b in (select a from t1);
 a	b

mysql-test/t/subselect_sj.test

@@ -1242,5 +1242,133 @@ WHERE f11 IN (
 set optimizer_switch=@tmp_751484;
 drop table t1, t3;
 
+#
+--echo # BUG#795530 Wrong result with subquery semijoin materialization and outer join 
+--echo #  Simplified testcase that uses DuplicateElimination
+--echo #
+create table t1 (a int);
+create table t2 (a int, b char(10));
+
+insert into t1 values (1),(2);
+insert into t2 values (1, 'one'), (3, 'three');
+
+create table t3 (b char(10));
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+insert into t3 values('three'),( 'four');
+explain select * from t3 where t3.b in (select t2.b from t1 left join t2 on t1.a=t2.a);
+select * from t3 where t3.b in (select t2.b from t1 left join t2 on t1.a=t2.a);
+drop table t1, t2, t3;
+
+--echo #
+--echo # BUG#600958 RQG: Crash in optimize_semijoin_nests
+--echo #
+CREATE TABLE t1 (
+  pk int(11) NOT NULL AUTO_INCREMENT,
+  col_int_key int(11) DEFAULT NULL,
+  col_date_key date DEFAULT NULL,
+  col_varchar_key varchar(1) DEFAULT NULL,
+  PRIMARY KEY (pk),
+  KEY col_int_key (col_int_key),
+  KEY col_date_key (col_date_key),
+  KEY col_varchar_key (col_varchar_key,col_int_key)
+) ENGINE=MyISAM AUTO_INCREMENT=11 DEFAULT CHARSET=latin1;
+INSERT INTO t1 VALUES (10,8,'2002-02-21',NULL);
+CREATE TABLE t2 (
+  pk int(11) NOT NULL AUTO_INCREMENT,
+  col_int_key int(11) DEFAULT NULL,
+  col_date_key date DEFAULT NULL,
+  col_varchar_key varchar(1) DEFAULT NULL,
+  PRIMARY KEY (pk),
+  KEY col_int_key (col_int_key),
+  KEY col_date_key (col_date_key),
+  KEY col_varchar_key (col_varchar_key,col_int_key)
+) ENGINE=MyISAM AUTO_INCREMENT=2 DEFAULT CHARSET=latin1;
+INSERT INTO t2 VALUES (1,7,'1900-01-01','f');
+
+SELECT col_date_key FROM t1
+WHERE 5 IN (
+        SELECT SUBQUERY3_t1 .col_int_key
+        FROM t2 SUBQUERY3_t1
+        LEFT JOIN t1 SUBQUERY3_t2 ON SUBQUERY3_t1 .col_varchar_key
+);
+drop table t2, t1;
+
+
+--echo #
+--echo # No BUG#: Duplicate weedout check is not done for outer joins
+--echo #
+create table t1 (a int);
+create table t2 (a int);
+
+insert into t1 values (1),(1),(2),(2);
+insert into t2 values (1);
+
+create table t0 (a int);
+insert into t0 values (1),(2);
+
+set @tmp_20110622= @@optimizer_switch;
+set optimizer_switch='firstmatch=off,loosescan=off,materialization=off';
+--echo # Check DuplicateWeedout + join buffer
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+
+--echo # Check DuplicateWeedout without join buffer
+set @tmp_jcl_20110622= @@join_cache_level;
+set join_cache_level= 0;
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+
+
+--echo # Check FirstMatch without join buffer:
+set optimizer_switch='firstmatch=on';
+explain 
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+select * from t0 where a in (select t1.a from t1 left join t2 on t1.a=t2.a);
+
+--echo #
+--echo # Now, check the same for multiple inner tables:
+alter table t2 add b int;
+update t2 set b=a;
+create table t3 as select * from t2;
+
+set optimizer_switch='firstmatch=off';
+set join_cache_level= 0;
+--echo # DuplicateWeedout without join buffer
+explain 
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+
+set @@join_cache_level=@tmp_jcl_20110622;
+--echo # DuplicateWeedout + join buffer
+explain
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+
+--echo # Now, let the inner join side have a 'partial' match
+select * from t3;
+insert into t3 values(2,2);
+
+explain
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+
+select * from t0 
+where a in (select t1.a from t1 left join (t3 join t2 on t3.b=t2.b) on t1.a=t3.a);
+
+set @@optimizer_switch=@tmp_20110622;
+
+drop table t0, t1, t2, t3;
+
+
 # The following command must be the last one the file 
 set @@optimizer_switch=@save_optimizer_switch;

sql/item_cmpfunc.h

@@ -1688,7 +1688,8 @@ class Item_equal: public Item_bool_func
   friend class Item_equal_fields_iterator;
   friend Item *eliminate_item_equal(COND *cond, COND_EQUAL *upper_levels,
                            Item_equal *item_equal);
-  friend bool setup_sj_materialization(struct st_join_table *tab);
+  friend bool setup_sj_materialization_part1(struct st_join_table *tab);
+  friend bool setup_sj_materialization_part2(struct st_join_table *tab);
 }; 
 
 class COND_EQUAL: public Sql_alloc

sql/item_subselect.cc

@@ -476,12 +476,10 @@ void Item_subselect::recalc_used_tables(st_select_lex *new_parent,
           upper->item->walk(&Item::enumerate_field_refs_processor, FALSE,
                             (uchar*)&fixer);
           used_tables_cache |= fixer.used_tables;
-          /*
+
           if (after_pullout)
             upper->item->fix_after_pullout(new_parent, &(upper->item));
           upper->item->update_used_tables();
-          used_tables_cache |= upper->item->used_tables();
-          */
         }
       }
     }

sql/opt_subselect.cc

@@ -774,18 +774,20 @@ bool convert_join_subqueries_to_semijoins(JOIN *join)
     if (convert_join_subqueries_to_semijoins(child_join))
       DBUG_RETURN(TRUE);
     (*in_subq)->sj_convert_priority= 
+      test((*in_subq)->emb_on_expr_nest != NO_JOIN_NEST) * MAX_TABLES * 2 +
       (*in_subq)->is_correlated * MAX_TABLES + child_join->outer_tables;
   }
   
   // Temporary measure: disable semi-joins when they are together with outer
   // joins.
+#if 0  
   if (check_for_outer_joins(join->join_list))
   {
     in_subq= join->sj_subselects.front();
     arena= thd->activate_stmt_arena_if_needed(&backup);
     goto skip_conversion;
   }
-
+#endif
   //dump_TABLE_LIST_struct(select_lex, select_lex->leaf_tables);
   /* 
     2. Pick which subqueries to convert:
@@ -803,6 +805,11 @@ bool convert_join_subqueries_to_semijoins(JOIN *join)
        in_subq++)
   {
     bool remove_item= TRUE;
+
+    /* Stop processing if we've reached a subquery that's attached to the ON clause */
+    if ((*in_subq)->emb_on_expr_nest != NO_JOIN_NEST)
+      break;
+
     if ((*in_subq)->is_flattenable_semijoin) 
     {
       if (join->table_count + 
@@ -828,7 +835,7 @@ bool convert_join_subqueries_to_semijoins(JOIN *join)
         DBUG_RETURN(TRUE); /* purecov: inspected */
     }
   }
-skip_conversion:
+//skip_conversion:
   /* 
     3. Finalize (perform IN->EXISTS rewrite) the subqueries that we didn't
     convert:
@@ -861,6 +868,11 @@ bool convert_join_subqueries_to_semijoins(JOIN *join)
                                    do_fix_fields))
       DBUG_RETURN(TRUE);
     (*in_subq)->substitution= NULL;
+#if 0
+    /* 
+      Don't do the following, because the simplify_join() call is after this
+      call, and that call will save to prep_wher/prep_on_expr.
+    */
 
     /*
       If this is a prepared statement, repeat the above operation for
@@ -877,6 +889,7 @@ bool convert_join_subqueries_to_semijoins(JOIN *join)
                                      FALSE))
         DBUG_RETURN(TRUE);
     }
+#endif
     /*
       Revert to the IN->EXISTS strategy in the rare case when the subquery could
       not be flattened.
@@ -2840,9 +2853,8 @@ void fix_semijoin_strategies_for_picked_join_order(JOIN *join)
     TRUE   Error
 */
 
-bool setup_sj_materialization(JOIN_TAB *sjm_tab)
+bool setup_sj_materialization_part1(JOIN_TAB *sjm_tab)
 {
-  uint i;
   DBUG_ENTER("setup_sj_materialization");
   JOIN_TAB *tab= sjm_tab->bush_children->start;
   TABLE_LIST *emb_sj_nest= tab->table->pos_in_table_list->embedding;
@@ -2851,6 +2863,7 @@ bool setup_sj_materialization(JOIN_TAB *sjm_tab)
   /* First the calls come to the materialization function */
   List<Item> &item_list= emb_sj_nest->sj_subq_pred->unit->first_select()->item_list;
   
+  DBUG_ASSERT(sjm->is_used);
   /* 
     Set up the table to write to, do as select_union::create_result_table does
   */
@@ -2878,6 +2891,22 @@ bool setup_sj_materialization(JOIN_TAB *sjm_tab)
   
   sjm->materialized= FALSE;
   sjm_tab->table= sjm->table;
+  sjm->table->pos_in_table_list= emb_sj_nest;
+ 
+  DBUG_RETURN(FALSE);
+}
+
+
+bool setup_sj_materialization_part2(JOIN_TAB *sjm_tab)
+{
+  DBUG_ENTER("setup_sj_materialization_part2");
+  JOIN_TAB *tab= sjm_tab->bush_children->start;
+  TABLE_LIST *emb_sj_nest= tab->table->pos_in_table_list->embedding;
+  SJ_MATERIALIZATION_INFO *sjm= emb_sj_nest->sj_mat_info;
+  THD *thd= tab->join->thd;
+  uint i;
+  List<Item> &item_list= emb_sj_nest->sj_subq_pred->unit->first_select()->item_list;
+  List_iterator<Item> it(item_list);
 
   if (!sjm->is_sj_scan)
   {
@@ -2992,7 +3021,7 @@ bool setup_sj_materialization(JOIN_TAB *sjm_tab)
       in the record buffers for the source tables. 
     */
     sjm->copy_field= new Copy_field[sjm->sjm_table_cols.elements];
-    it.rewind();
+    //it.rewind();
     for (uint i=0; i < sjm->sjm_table_cols.elements; i++)
     {
       bool dummy;

sql/opt_subselect.h

@@ -285,7 +285,9 @@ void restore_prev_sj_state(const table_map remaining_tables,
                                   const JOIN_TAB *tab, uint idx);
 
 void fix_semijoin_strategies_for_picked_join_order(JOIN *join);
-bool setup_sj_materialization(JOIN_TAB *tab);
+
+bool setup_sj_materialization_part1(JOIN_TAB *sjm_tab);
+bool setup_sj_materialization_part2(JOIN_TAB *sjm_tab);
 
 TABLE *create_duplicate_weedout_tmp_table(THD *thd, uint uniq_tuple_length_arg,
                                           SJ_TMP_TABLE *sjtbl);

sql/sql_select.cc

@@ -90,7 +90,7 @@ static store_key *get_store_key(THD *thd,
 				KEYUSE *keyuse, table_map used_tables,
 				KEY_PART_INFO *key_part, uchar *key_buff,
 				uint maybe_null);
-static void make_outerjoin_info(JOIN *join);
+static bool make_outerjoin_info(JOIN *join);
 static Item*
 make_cond_after_sjm(Item *root_cond, Item *cond, table_map tables, table_map sjm_tables);
 static bool make_join_select(JOIN *join,SQL_SELECT *select,COND *item);
@@ -1165,7 +1165,10 @@ JOIN::optimize()
   }
   
   reset_nj_counters(this, join_list);
-  make_outerjoin_info(this);
+  if (make_outerjoin_info(this))
+  {
+    DBUG_RETURN(1);
+  }
 
   /*
     Among the equal fields belonging to the same multiple equality
@@ -7625,6 +7628,12 @@ static void add_not_null_conds(JOIN *join)
   nested outer join and so on until it reaches root_tab
   (root_tab can be 0).
 
+  In other words:
+  add_found_match_trig_cond(tab->first_inner_tab, y, 0) is the way one should 
+  wrap parts of WHERE.  The idea is that the part of WHERE should be only
+  evaluated after we've finished figuring out whether outer joins.
+  ^^^ is the above correct?
+
   @param tab       the first inner table for most nested outer join
   @param cond      the predicate to be guarded (must be set)
   @param root_tab  the first inner table to stop
@@ -7652,6 +7661,12 @@ add_found_match_trig_cond(JOIN_TAB *tab, COND *cond, JOIN_TAB *root_tab)
 }
 
 
+bool TABLE_LIST::is_active_sjm()
+{ 
+  return sj_mat_info && sj_mat_info->is_used;
+}
+
+
 /**
   Fill in outer join related info for the execution plan structure.
 
@@ -7669,6 +7684,12 @@ add_found_match_trig_cond(JOIN_TAB *tab, COND *cond, JOIN_TAB *root_tab)
     corresponding first inner table through the field t0->on_expr_ref.
     Here ti are structures of the JOIN_TAB type.
 
+    In other words, for each join tab, set
+     - first_inner
+     - last_inner
+     - first_upper
+     - on_expr_ref, cond_equal
+
   EXAMPLE. For the query: 
   @code
         SELECT * FROM t1
@@ -7694,20 +7715,33 @@ add_found_match_trig_cond(JOIN_TAB *tab, COND *cond, JOIN_TAB *root_tab)
     has been chosen.
 */
 
-static void
+static bool
 make_outerjoin_info(JOIN *join)
 {
   DBUG_ENTER("make_outerjoin_info");
-  for (JOIN_TAB *tab= first_linear_tab(join, WITHOUT_CONST_TABLES); tab; 
-       tab= next_linear_tab(join, tab, WITHOUT_BUSH_ROOTS))
-  {
-    TABLE *table=tab->table;
+  
   /*
-      psergey: The following is probably incorrect, fix it when we get 
-      semi+outer joins processing to work: 
+    Create temp. tables for merged SJ-Materialization nests. We need to do
+    this now, because further code relies on tab->table and
+    tab->table->pos_in_table_list being set.
   */
-    if (!table)
-      continue;
+  JOIN_TAB *tab;
+  for (tab= first_linear_tab(join, WITHOUT_CONST_TABLES); 
+       tab; 
+       tab= next_linear_tab(join, tab, WITH_BUSH_ROOTS))
+  {
+    if (tab->bush_children)
+    {
+      if (setup_sj_materialization_part1(tab))
+        DBUG_RETURN(TRUE);
+      tab->table->reginfo.join_tab= tab;
+    }
+  }
+
+  for (JOIN_TAB *tab= first_linear_tab(join, WITHOUT_CONST_TABLES); tab; 
+       tab= next_linear_tab(join, tab, WITH_BUSH_ROOTS))
+  {
+    TABLE *table= tab->table;
     TABLE_LIST *tbl= table->pos_in_table_list;
     TABLE_LIST *embedding= tbl->embedding;
 
@@ -7721,11 +7755,16 @@ make_outerjoin_info(JOIN *join)
       tab->last_inner= tab->first_inner= tab;
       tab->on_expr_ref= &tbl->on_expr;
       tab->cond_equal= tbl->cond_equal;
-      if (embedding)
+      if (embedding && !embedding->is_active_sjm())
         tab->first_upper= embedding->nested_join->first_nested;
     }    
     for ( ; embedding ; embedding= embedding->embedding)
     {
+      if (embedding->is_active_sjm())
+      {
+        /* We're trying to walk out of an SJ-Materialization nest. Don't do this.  */
+        break;
+      }
       /* Ignore sj-nests: */
       if (!(embedding->on_expr && embedding->outer_join))
         continue;
@@ -7757,7 +7796,7 @@ make_outerjoin_info(JOIN *join)
       } 
     }
   }
-  DBUG_VOID_RETURN;
+  DBUG_RETURN(FALSE);
 }
 
 
@@ -8132,10 +8171,25 @@ make_join_select(JOIN *join,SQL_SELECT *select,COND *cond)
         the null complemented row.
       */ 
 
-      /* First push down constant conditions from on expressions */
-      for (JOIN_TAB *join_tab= first_linear_tab(join, WITHOUT_CONST_TABLES); 
-           join_tab; 
-           join_tab= next_linear_tab(join, join_tab, WITH_BUSH_ROOTS))
+      /* 
+        First push down constant conditions from ON expressions. 
+         - Each pushed-down condition is wrapped into trigger which is 
+           enabled only for non-NULL-complemented record
+         - The condition is attached to the first_inner_table.
+        
+        With regards to join nests:
+         - if we start at top level, don't walk into nests
+         - if we start inside a nest, stay within that nest.
+      */
+      JOIN_TAB *start_from= tab->bush_root_tab? 
+                               tab->bush_root_tab->bush_children->start : 
+                               join->join_tab + join->const_tables;
+      JOIN_TAB *end_with= tab->bush_root_tab? 
+                               tab->bush_root_tab->bush_children->end : 
+                               join->join_tab + join->top_join_tab_count;
+      for (JOIN_TAB *join_tab= start_from;
+           join_tab != end_with;
+           join_tab++)
       {
         if (*join_tab->on_expr_ref)
         {
@@ -8160,9 +8214,14 @@ make_join_select(JOIN *join,SQL_SELECT *select,COND *cond)
         }       
       }
 
+
       /* Push down non-constant conditions from ON expressions */
-      //JOIN_TAB *first_tab= join->join_tab+join->const_tables;
       JOIN_TAB *last_tab= tab;
+
+      /*
+        while we're inside of an outer join and last_tab is 
+        the last of its tables ... 
+      */
       while (first_inner_tab && first_inner_tab->last_inner == last_tab)
       { 
         /* 
@@ -8173,19 +8232,13 @@ make_join_select(JOIN *join,SQL_SELECT *select,COND *cond)
 
         table_map used_tables2= (join->const_table_map |
                                  OUTER_REF_TABLE_BIT | RAND_TABLE_BIT);
-        for (JOIN_TAB *tab= first_linear_tab(join, WITHOUT_CONST_TABLES); 
-             tab; 
-             tab= (tab == last_tab)? NULL: next_linear_tab(join, tab, 
-                                                           WITH_BUSH_ROOTS))
-        {
-          if (!tab->table)
+
+        start_from= tab->bush_root_tab? 
+                      tab->bush_root_tab->bush_children->start : 
+                      join->join_tab + join->const_tables;
+        for (JOIN_TAB *tab= start_from; tab <= last_tab; tab++)
         {
-            /* 
-              psergey-todo: this is probably incorrect, fix this when we get
-              correct processing for outer joins + semi joins 
-            */
-            continue;
-          }
+          DBUG_ASSERT(tab->table);
           current_map= tab->table->map;
           used_tables2|= current_map;
           /*
@@ -9136,7 +9189,7 @@ make_join_readinfo(JOIN *join, ulonglong options, uint no_jbuf_after)
   {
     if (tab->bush_children)
     {
-      if (setup_sj_materialization(tab))
+      if (setup_sj_materialization_part2(tab))
         return TRUE;
     }
 
@@ -15188,6 +15241,26 @@ evaluate_null_complemented_join_record(JOIN *join, JOIN_TAB *join_tab)
   /*
     The row complemented by nulls satisfies all conditions
     attached to inner tables.
+  */
+  if (join_tab->check_weed_out_table)
+  {
+    int res= do_sj_dups_weedout(join->thd, join_tab->check_weed_out_table);
+    if (res == -1)
+      return NESTED_LOOP_ERROR;
+    else if (res == 1)
+      return NESTED_LOOP_OK;
+  }
+  else if (join_tab->do_firstmatch)
+  {
+    /* 
+      We should return to the join_tab->do_firstmatch after we have 
+      enumerated all the suffixes for current prefix row combination
+    */
+    if (join_tab->do_firstmatch < join->return_tab)
+      join->return_tab= join_tab->do_firstmatch;
+  }
+
+  /*
     Send the row complemented by nulls to be joined with the
     remaining tables.
   */
@@ -20568,8 +20641,7 @@ static void select_describe(JOIN *join, bool need_tmp_table, bool need_order,
             examined_rows= tab->limit;
           else
           {
-            if (!tab->table->pos_in_table_list ||
-                tab->table->is_filled_at_execution()) // temporary, is_filled_at_execution
+            if (tab->table->is_filled_at_execution())
             {
               examined_rows= tab->records;
             }

sql/sql_select.h

@@ -204,7 +204,13 @@ typedef struct st_join_table {
     NULL means no index condition pushdown was performed.
   */
   Item          *pre_idx_push_select_cond;
-  Item	       **on_expr_ref;   /**< pointer to the associated on expression   */
+  /*
+    Pointer to the associated ON expression. on_expr_ref=!NULL except for
+    degenerate joins. 
+    *on_expr_ref!=NULL for tables that are first inner tables within an outer
+    join.
+  */
+  Item	       **on_expr_ref;
   COND_EQUAL    *cond_equal;    /**< multiple equalities for the on expression */
   st_join_table *first_inner;   /**< first inner table for including outerjoin */
   bool           found;         /**< true after all matches or null complement */
@@ -478,6 +484,8 @@ typedef struct st_join_table {
   }
   double scan_time();
   bool preread_init();
+
+  bool is_sjm_nest() { return test(bush_children); }
 } JOIN_TAB;
 
 

sql/table.cc

@@ -5410,9 +5410,11 @@ bool st_table::is_children_attached(void)
 
 bool st_table::is_filled_at_execution()
 { 
-  return test(pos_in_table_list->jtbm_subselect);
+  return test(pos_in_table_list->jtbm_subselect || 
+              pos_in_table_list->is_active_sjm());
 }
 
+
 /*
   Cleanup this table for re-execution.
 

sql/table.h

@@ -1765,6 +1765,7 @@ struct TABLE_LIST
      respectively.
    */
   char *get_table_name() { return view != NULL ? view_name.str : table_name; }
+  bool is_active_sjm();
   st_select_lex_unit *get_unit();
   st_select_lex *get_single_select();
   void wrap_into_nested_join(List<TABLE_LIST> &join_list);