database/mariadb
1
0
Fork 0
mirror of https://github.com/MariaDB/server.git synced 2025-07-30 16:24:05 +03:00
Code Activity

Bug#28875 Conversion between ASCII and LATIN1 charsets does not function

Browse Source 
(Regression, caused by a patch for the bug 22646).
Problem: when result type of date_format() was changed from
binary string to character string, mixing date_format()
with a ascii column in CONCAT() stopped to work.
Fix:
- adding "repertoire" flag into DTCollation class,
to mark items which can return only pure ASCII strings.
- allow character set conversion from pure ASCII to other character sets.


include/m_ctype.h:
  Defining new flags.
  Adding new function prototypes.
mysql-test/r/ctype_ucs.result:
  Adding tests.
mysql-test/r/ctype_utf8.result:
  Adding tests.
mysql-test/r/func_time.result:
  Adding tests.
mysql-test/t/ctype_ucs.test:
  Adding tests.
mysql-test/t/ctype_utf8.test:
  Adding tests.
mysql-test/t/func_time.test:
  Adding test.
mysys/charset.c:
  Adding pure ASCII detection when loading a dynamic character set.
sql/item.cc:
  - Moving detection of a Unicode superset into function.
  - Adding detection of a ASCII subset.
  - Adding creation of to-ASCII character set convertor when
    safe_charset_converter() failed and when the argument.
    repertoire is know to be pure ASCII.
sql/item.h:
  - Adding "repertoire" member into DTCollation class.
  - Adding "repertoire" argument to constructors.
  - Adding new methods:
    set_repertoire_from_charset()
    set_repertoire_from_value()
sql/item_func.cc:
  Adding "repertoire" argument.
sql/item_strfunc.cc:
  Adding "repertoire" argument.
sql/item_timefunc.cc:
  Initializing the result repertoire taking into account the "is_ascii"
  flag of the current locale.
sql/sql_lex.cc:
  Detect 7bit strings, return in Lex->text_string_is_7bit.
sql/sql_lex.h:
  Adding new member into LEX structure.
  Adding new member into Lex_input_stream
sql/sql_string.cc:
  Allow simple copy from pure ASCII to a ASCII-based character set.
sql/sql_yacc.yy:
  Depening on Lex->text_string_is_7bit and character set features,
  create Item_string with MY_REPERTOIRE_ASCII when it is possible.
strings/conf_to_src.c:
  - Adding printing of the "MY_CS_PUREASCII" flag
  - Adding printing of copyright
strings/ctype-extra.c:
  Recreating ctype-extra.c: ascii_general_ci and ascii_bin
  are now marked with MY_CS_PUREASCII flag.
strings/ctype.c:
  Adding new functions.
This commit is contained in:
unknown
2007-08-03 15:25:23 +05:00
parent b307fc4d8f
commit 53df09a9a6
20 changed files with 457 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
mysql-test/r/ctype_ucs.result
View File

@ -865,4 +865,30 @@ blob 65535 65535
text 65535 65535
text 65535 32767
drop table t1;
create table t1 (a varchar(15) character set ascii not null, b int);
insert into t1 values ('a',1);
select concat(a,if(b<10,_ucs2 0x0061,_ucs2 0x0062)) from t1;
concat(a,if(b<10,_ucs2 0x0061,_ucs2 0x0062))
aa
select concat(a,if(b>10,_ucs2 0x0061,_ucs2 0x0062)) from t1;
concat(a,if(b>10,_ucs2 0x0061,_ucs2 0x0062))
ab
select * from t1 where a=if(b<10,_ucs2 0x0061,_ucs2 0x0062);
a b
a 1
select * from t1 where a=if(b>10,_ucs2 0x0061,_ucs2 0x0062);
a b
select concat(a,if(b<10,_ucs2 0x00C0,_ucs2 0x0062)) from t1;
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (ucs2_general_ci,COERCIBLE) for operation 'concat'
select concat(a,if(b>10,_ucs2 0x00C0,_ucs2 0x0062)) from t1;
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (ucs2_general_ci,COERCIBLE) for operation 'concat'
select concat(a,if(b<10,_ucs2 0x0062,_ucs2 0x00C0)) from t1;
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (ucs2_general_ci,COERCIBLE) for operation 'concat'
select concat(a,if(b>10,_ucs2 0x0062,_ucs2 0x00C0)) from t1;
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (ucs2_general_ci,COERCIBLE) for operation 'concat'
select * from t1 where a=if(b<10,_ucs2 0x00C0,_ucs2 0x0062);
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (ucs2_general_ci,COERCIBLE) for operation '='
select * from t1 where a=if(b<10,_ucs2 0x0062,_ucs2 0x00C0);
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (ucs2_general_ci,COERCIBLE) for operation '='
drop table t1;
End of 5.0 tests

36
mysql-test/r/ctype_utf8.result
View File

@ -1639,6 +1639,42 @@ coercibility(col1) collation(col1)
0 utf8_swedish_ci
drop view v1, v2;
drop table t1;
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, N'x', N'y')) from t1;
concat(a, if(b>10, N'x', N'y'))
ay
select concat(a, if(b>10, N'æ', N'ß')) from t1;
ERROR HY000: Illegal mix of collations (latin1_swedish_ci,IMPLICIT) and (utf8_general_ci,COERCIBLE) for operation 'concat'
drop table t1;
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, _utf8'x', _utf8'y')) from t1;
concat(a, if(b>10, _utf8'x', _utf8'y'))
ay
select concat(a, if(b>10, _utf8'æ', _utf8'ß')) from t1;
ERROR HY000: Illegal mix of collations (latin1_swedish_ci,IMPLICIT) and (utf8_general_ci,COERCIBLE) for operation 'concat'
drop table t1;
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, _utf8 0x78, _utf8 0x79)) from t1;
concat(a, if(b>10, _utf8 0x78, _utf8 0x79))
ay
select concat(a, if(b>10, _utf8 0xC3A6, _utf8 0xC3AF)) from t1;
ERROR HY000: Illegal mix of collations (latin1_swedish_ci,IMPLICIT) and (utf8_general_ci,COERCIBLE) for operation 'concat'
drop table t1;
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, 'x' 'x', 'y' 'y')) from t1;
concat(a, if(b>10, 'x' 'x', 'y' 'y'))
ayy
select concat(a, if(b>10, 'x' 'æ', 'y' 'ß')) from t1;
ERROR HY000: Illegal mix of collations (latin1_swedish_ci,IMPLICIT) and (utf8_general_ci,COERCIBLE) for operation 'concat'
drop table t1;
CREATE TABLE t1 (
colA int(11) NOT NULL,
colB varchar(255) character set utf8 NOT NULL,

16
mysql-test/r/func_time.result
View File

@ -1246,3 +1246,19 @@ SELECT TIME_FORMAT(SEC_TO_TIME(a),"%H:%i:%s") FROM (SELECT 3020399 AS a UNION SE
TIME_FORMAT(SEC_TO_TIME(a),"%H:%i:%s")
838:59:58
838:59:59
set names latin1;
create table t1 (a varchar(15) character set ascii not null);
insert into t1 values ('070514-000000');
select concat(a,ifnull(min(date_format(now(), '%Y-%m-%d')),' ull')) from t1;
concat(a,ifnull(min(date_format(now(), '%Y-%m-%d')),' ull'))
#
set names swe7;
select concat(a,ifnull(min(date_format(now(), '%Y-%m-%d')),' ull')) from t1;
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (swe7_swedish_ci,COERCIBLE) for operation 'concat'
set names latin1;
set lc_time_names=fr_FR;
select concat(a,ifnull(min(date_format(now(), '%Y-%m-%d')),' ull')) from t1;
ERROR HY000: Illegal mix of collations (ascii_general_ci,IMPLICIT) and (latin1_swedish_ci,COERCIBLE) for operation 'concat'
set lc_time_names=en_US;
drop table t1;
End of 5.0 tests

30
mysql-test/t/ctype_ucs.test
View File

@ -594,4 +594,34 @@ select data_type, character_octet_length, character_maximum_length
from information_schema.columns where table_name='t1';
drop table t1;
#
# Conversion from UCS2 to ASCII is possible
# if the UCS2 string consists of only ASCII characters
#
create table t1 (a varchar(15) character set ascii not null, b int);
insert into t1 values ('a',1);
select concat(a,if(b<10,_ucs2 0x0061,_ucs2 0x0062)) from t1;
select concat(a,if(b>10,_ucs2 0x0061,_ucs2 0x0062)) from t1;
select * from t1 where a=if(b<10,_ucs2 0x0061,_ucs2 0x0062);
select * from t1 where a=if(b>10,_ucs2 0x0061,_ucs2 0x0062);
#
# Conversion from UCS2 to ASCII is not possible if
# the UCS2 string has non-ASCII characters
#
--error 1267
select concat(a,if(b<10,_ucs2 0x00C0,_ucs2 0x0062)) from t1;
--error 1267
select concat(a,if(b>10,_ucs2 0x00C0,_ucs2 0x0062)) from t1;
--error 1267
select concat(a,if(b<10,_ucs2 0x0062,_ucs2 0x00C0)) from t1;
--error 1267
select concat(a,if(b>10,_ucs2 0x0062,_ucs2 0x00C0)) from t1;
--error 1267
select * from t1 where a=if(b<10,_ucs2 0x00C0,_ucs2 0x0062);
--error 1267
select * from t1 where a=if(b<10,_ucs2 0x0062,_ucs2 0x00C0);
drop table t1;
--echo End of 5.0 tests

40
mysql-test/t/ctype_utf8.test
View File

@ -1314,6 +1314,46 @@ select coercibility(col1), collation(col1) from v2;
drop view v1, v2;
drop table t1;
#
# Check conversion of NCHAR strings to subset (e.g. latin1).
# Conversion is possible if string repertoire is ASCII.
# Conversion is not possible if the string have extended characters
#
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, N'x', N'y')) from t1;
--error 1267
select concat(a, if(b>10, N'æ', N'ß')) from t1;
drop table t1;
# Conversion tests for character set introducers
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, _utf8'x', _utf8'y')) from t1;
--error 1267
select concat(a, if(b>10, _utf8'æ', _utf8'ß')) from t1;
drop table t1;
# Conversion tests for introducer + HEX string
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, _utf8 0x78, _utf8 0x79)) from t1;
--error 1267
select concat(a, if(b>10, _utf8 0xC3A6, _utf8 0xC3AF)) from t1;
drop table t1;
# Conversion tests for "text_literal TEXT_STRING_literal" syntax structure
set names utf8;
create table t1 (a varchar(10) character set latin1, b int);
insert into t1 values ('a',1);
select concat(a, if(b>10, 'x' 'x', 'y' 'y')) from t1;
--error 1267
select concat(a, if(b>10, 'x' 'æ', 'y' 'ß')) from t1;
drop table t1;
#
# Bug#19960: Inconsistent results when joining

26
mysql-test/t/func_time.test
View File

@ -752,3 +752,29 @@ DROP TABLE t1;
# Check if using GROUP BY with TIME_FORMAT() produces correct results
SELECT TIME_FORMAT(SEC_TO_TIME(a),"%H:%i:%s") FROM (SELECT 3020399 AS a UNION SELECT 3020398 ) x GROUP BY 1;
#
# Bug#28875 Conversion between ASCII and LATIN1 charsets does not function
#
set names latin1;
create table t1 (a varchar(15) character set ascii not null);
insert into t1 values ('070514-000000');
# Conversion of date_format() result to ASCII
# is safe with the default locale en_US
--replace_column 1 #
select concat(a,ifnull(min(date_format(now(), '%Y-%m-%d')),' ull')) from t1;
# Error for swe7: it is not ASCII compatible
set names swe7;
--error 1267
select concat(a,ifnull(min(date_format(now(), '%Y-%m-%d')),' ull')) from t1;
set names latin1;
# Conversion of date_format() result to ASCII
# is not safe with the non-default locale fr_FR
# because month and day names can have accented characters
set lc_time_names=fr_FR;
--error 1267
select concat(a,ifnull(min(date_format(now(), '%Y-%m-%d')),' ull')) from t1;
set lc_time_names=en_US;
drop table t1;
--echo End of 5.0 tests