Bug#30315 Character sets: insertion of euckr code value 0xa141 fails

Problem: some valid euc-kr characters were rejected because
condition checking multi-byte tail didn't allow 
multi-byte characters having the second byte in the ranges
[0x41..0x5A]  and [0x61..0x7A].

Fix: allow these byte ranges for mb tails
parent 1e265379
......@@ -165,3 +165,44 @@ hex(a)
A2E6
FEF7
DROP TABLE t1;
create table t1 (s1 varchar(5) character set euckr);
insert into t1 values (0xA141);
insert into t1 values (0xA15A);
insert into t1 values (0xA161);
insert into t1 values (0xA17A);
insert into t1 values (0xA181);
insert into t1 values (0xA1FE);
insert into t1 values (0xA140);
Warnings:
Warning 1366 Incorrect string value: '\xA1@' for column 's1' at row 1
insert into t1 values (0xA15B);
Warnings:
Warning 1366 Incorrect string value: '\xA1[' for column 's1' at row 1
insert into t1 values (0xA160);
Warnings:
Warning 1366 Incorrect string value: '\xA1`' for column 's1' at row 1
insert into t1 values (0xA17B);
Warnings:
Warning 1366 Incorrect string value: '\xA1{' for column 's1' at row 1
insert into t1 values (0xA180);
Warnings:
Warning 1366 Incorrect string value: '\xA1\x80' for column 's1' at row 1
insert into t1 values (0xA1FF);
Warnings:
Warning 1366 Incorrect string value: '\xA1\xFF' for column 's1' at row 1
select hex(s1), hex(convert(s1 using utf8)) from t1 order by binary s1;
hex(s1) hex(convert(s1 using utf8))
A141 ECA2A5
A15A ECA381
A161 ECA382
A17A ECA3A5
A181 ECA3A6
A1FE EFBFA2
drop table t1;
End of 5.0 tests
......@@ -31,3 +31,26 @@ SELECT hex(a) FROM t1 ORDER BY a;
DROP TABLE t1;
# End of 4.1 tests
#
#Bug #30315 Character sets: insertion of euckr code value 0xa141 fails
#
create table t1 (s1 varchar(5) character set euckr);
# Insert some valid characters
insert into t1 values (0xA141);
insert into t1 values (0xA15A);
insert into t1 values (0xA161);
insert into t1 values (0xA17A);
insert into t1 values (0xA181);
insert into t1 values (0xA1FE);
# Insert some invalid characters
insert into t1 values (0xA140);
insert into t1 values (0xA15B);
insert into t1 values (0xA160);
insert into t1 values (0xA17B);
insert into t1 values (0xA180);
insert into t1 values (0xA1FF);
select hex(s1), hex(convert(s1 using utf8)) from t1 order by binary s1;
drop table t1;
--echo End of 5.0 tests
......@@ -179,20 +179,39 @@ static uchar NEAR sort_order_euc_kr[]=
/* Support for Korean(EUC_KR) characters, by powerm90@tinc.co.kr and mrpark@tinc.co.kr */
#define iseuc_kr(c) ((0xa1<=(uchar)(c) && (uchar)(c)<=0xfe))
/*
Unicode mapping is done according to:
ftp://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/KSC/KSC5601.TXT
Valid multi-byte characters:
[A1..FE][41..5A,61..7A,81..FE]
Note, 0x5C is not a valid MB tail,
so escape_with_backslash_is_dangerous is not set.
*/
#define iseuc_kr_head(c) ((0xa1<=(uchar)(c) && (uchar)(c)<=0xfe))
#define iseuc_kr_tail1(c) ((uchar) (c) >= 0x41 && (uchar) (c) <= 0x5A)
#define iseuc_kr_tail2(c) ((uchar) (c) >= 0x61 && (uchar) (c) <= 0x7A)
#define iseuc_kr_tail3(c) ((uchar) (c) >= 0x81 && (uchar) (c) <= 0xFE)
#define iseuc_kr_tail(c) (iseuc_kr_tail1(c) || \
iseuc_kr_tail2(c) || \
iseuc_kr_tail3(c))
static int ismbchar_euc_kr(CHARSET_INFO *cs __attribute__((unused)),
const char* p, const char *e)
{
return ((*(uchar*)(p)<0x80)? 0:\
iseuc_kr(*(p)) && (e)-(p)>1 && iseuc_kr(*((p)+1))? 2:\
iseuc_kr_head(*(p)) && (e)-(p)>1 && iseuc_kr_tail(*((p)+1))? 2:\
0);
}
static int mbcharlen_euc_kr(CHARSET_INFO *cs __attribute__((unused)),uint c)
{
return (iseuc_kr(c) ? 2 : 1);
return (iseuc_kr_head(c) ? 2 : 1);
}
......@@ -8653,7 +8672,7 @@ my_well_formed_len_euckr(CHARSET_INFO *cs __attribute__((unused)),
/* Single byte ascii character */
b++;
}
else if (b < emb && iseuc_kr(*b) && iseuc_kr(b[1]))
else if (b < emb && iseuc_kr_head(*b) && iseuc_kr_tail(b[1]))
{
/* Double byte character */
b+= 2;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment