Commit bfdbb780 authored by unknown's avatar unknown
Browse files

Fix for bug #20709: Collation not used in group by on 4.1. 

myisam/mi_uniue.c:mi_check_unique() should skip trailing spaces comparing 
TEXT and VARTTEXT key segments.


myisam/mi_unique.c:
  Fix for bug #20709: Collation not used in group by on 4.1.    
  
  myisam/mi_uniue.c:mi_check_unique() should skip trailing spaces comparing 
  TEXT and VARTTEXT key segments.
    
  Example: assume, we have a 'char(200) collate utf8_unicode_ci' field,
  there are two records with _utf8"0x65" and _utf8"0xC3A9" characters;
  these values are equal according
  to the utf8_unicode_ci collation, but two 600 byte length corresponding keys:  
  "0x65<0x20 repeats 599 times>" and "0xC3A9<0x20 repeats 598 times>" are not    
  equal if we count trailing spaces and it may cause inconsequent behavior.
  
  So, let's pass 1 as the skip_end_space parameter value to the mi_compare_text()
  function for proper TEXT and VARTTEXT key segments comparison.
mysql-test/r/ctype_utf8.result:
  Fix for bug #20709: Collation not used in group by on 4.1.    
    - test results.
mysql-test/t/ctype_utf8.test:
  Fix for bug #20709: Collation not used in group by on 4.1.    
    - test case.
parent 70269a09

myisam/mi_unique.c

+1 −1
Original line number Diff line number Diff line
@@ -185,7 +185,7 @@ int mi_unique_comp(MI_UNIQUEDEF *def, const byte *a, const byte *b, 
    if (type == HA_KEYTYPE_TEXT || type == HA_KEYTYPE_VARTEXT)

    {

      if (mi_compare_text(keyseg->charset, (uchar *) pos_a, length,

                                           (uchar *) pos_b, length, 0, 0))

                                           (uchar *) pos_b, length, 0, 1))

	  return 1;

    }

    else

mysql-test/r/ctype_utf8.result

+16 −0
Original line number Diff line number Diff line
@@ -1293,3 +1293,19 @@ id tid val 
42749	72	VOLN ADSL

44205	72	VOLN ADSL

DROP TABLE t1;

create table t1(a char(200) collate utf8_unicode_ci NOT NULL default '')

default charset=utf8 collate=utf8_unicode_ci;

insert into t1 values (unhex('65')), (unhex('C3A9')), (unhex('65'));

explain select distinct a from t1;

id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra

1	SIMPLE	t1	ALL	NULL	NULL	NULL	NULL	3	Using temporary

select distinct a from t1;

a

e

explain select a from t1 group by a;

id	select_type	table	type	possible_keys	key	key_len	ref	rows	Extra

1	SIMPLE	t1	ALL	NULL	NULL	NULL	NULL	3	Using temporary; Using filesort

select a from t1 group by a;

a

e

drop table t1;

mysql-test/t/ctype_utf8.test

+14 −0
Original line number Diff line number Diff line
@@ -1040,4 +1040,18 @@ ALTER TABLE t1 ADD KEY idx (tid,val(11)); 
SELECT * FROM t1 WHERE tid=72 and val LIKE 'VOLN ADSL'; 



DROP TABLE t1;



#

# Bug 20709: problem with utf8 fields in temporary tables

#



create table t1(a char(200) collate utf8_unicode_ci NOT NULL default '')

  default charset=utf8 collate=utf8_unicode_ci;

insert into t1 values (unhex('65')), (unhex('C3A9')), (unhex('65'));

explain select distinct a from t1;

select distinct a from t1;

explain select a from t1 group by a;

select a from t1 group by a;

drop table t1;



# End of 4.1 tests