database/mariadb
1
0
Fork 0
mirror of https://github.com/MariaDB/server.git synced 2025-08-01 03:47:19 +03:00
Code Activity

Bug#27345 Incorrect data returned when range-read from utf8_danish_ci indexes

Browse Source 
Problem: like_range() returned wrong ranges for contractions (like 'ch' in Czech').
Fix: adding a special code to handle tricky cases:
- contraction head followed by a wild character
- full contraction
- contraction part followed by another contraction part,
  but they are not a contraction together.


mysql-test/r/ctype_uca.result:
  Adding test case
mysql-test/t/ctype_uca.test:
  Adding test case
strings/ctype-mb.c:
  Adding test case
strings/ctype-uca.c:
  Allocate additional 256 bytes for flags "is contraction part".
strings/ctype-ucs2.c:
  Adding test case
This commit is contained in:
unknown
2007-06-28 13:34:44 +05:00
parent 9b940d0cb7
commit 54344f681d
5 changed files with 261 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
strings/ctype-ucs2.c
View File

@ -1524,6 +1524,8 @@ my_bool my_like_range_ucs2(CHARSET_INFO *cs,
char *min_org=min_str;
char *min_end=min_str+res_length;
uint charlen= res_length / cs->mbmaxlen;
const char *contraction_flags= cs->contractions ?
((const char*) cs->contractions) + 0x40*0x40 : NULL;
for ( ; ptr + 1 < end && min_str + 1 < min_end && charlen > 0
; ptr+=2, charlen--)
@ -1545,6 +1547,7 @@ my_bool my_like_range_ucs2(CHARSET_INFO *cs,
}
if (ptr[0] == '\0' && ptr[1] == w_many) /* '%' in SQL */
{
fill_max_and_min:
/*
Calculate length of keys:
'a\0\0... is the smallest possible string when we have space expand
@ -1561,6 +1564,38 @@ my_bool my_like_range_ucs2(CHARSET_INFO *cs,
} while (min_str + 1 < min_end);
return 0;
}
if (contraction_flags && ptr + 3 < end &&
ptr[0] == '\0' && contraction_flags[(uchar) ptr[1]])
{
/* Contraction head found */
if (ptr[2] == '\0' && (ptr[3] == w_one || ptr[3] == w_many))
{
/* Contraction head followed by a wildcard, quit */
goto fill_max_and_min;
}
/*
Check if the second letter can be contraction part,
and if two letters really produce a contraction.
*/
if (ptr[2] == '\0' && contraction_flags[(uchar) ptr[3]] &&
cs->contractions[(ptr[1]-0x40)*0x40 + ptr[3] - 0x40])
{
/* Contraction found */
if (charlen == 1 || min_str + 2 >= min_end)
{
/* Full contraction doesn't fit, quit */
goto fill_max_and_min;
}
/* Put contraction head */
*min_str++= *max_str++= *ptr++;
*min_str++= *max_str++= *ptr++;
charlen--;
}
}
/* Put contraction tail, or a single character */
*min_str++= *max_str++ = ptr[0];
*min_str++= *max_str++ = ptr[1];
}