1
0
mirror of https://github.com/MariaDB/server.git synced 2025-07-18 23:03:28 +03:00

MDEV-28835 Assertion `(length % 4) == 0' failed in my_lengthsp_utf32 on INSERT

Problem:

Item_func_date_format::val_str() and make_date_time() did not take into
account that the format string and the result string
(separately or at the same time) can be of a tricky character set
like UCS2, UTF16, UTF32. As a result, DATE_FORMAT() could generate
an ill-formed result which crashed on DBUG_ASSERTs testing well-formedness
in other parts of the code.

Fix:

1. class String changes
   Removing String::append_with_prefill(). It was not compatible with
   tricky character sets. Also it was inconvenient to use and required
   too much duplicate code on the caller side.
   Adding String::append_zerofill() instead. It's compatible with tricky
   character sets and is easier to use.
   Adding helper methods Static_binary_string::q_append_wc() and
   String::append_wc(), to append a single wide character
   (a Unicode code point in my_wc_t).

2. storage/spider changes
   Removing spider_string::append_with_prefill().
   It used String::append_with_prefix() inside, but it was unused itself.

3. Changing tricky charset incompatible code pieces in make_date_time()
   to compatible replacements:

   - Fixing the loop scanning the format string to iterate in terms
     of Unicode code points (using mb_wc()) rather than in terms
     of "char" items.
   - Using append_wc(my_wc_t) instead of append(char) to append
     a single character to the result string.
   - Using append_zerofill() instead of append_with_prefill() to
     append date/time numeric components to the result string.
This commit is contained in:
Alexander Barkov
2023-07-19 15:10:47 +04:00
parent 3626379d42
commit e2da748c29
9 changed files with 280 additions and 113 deletions

View File

@ -392,6 +392,19 @@ public:
float8store(Ptr + str_length, *d);
str_length += 8;
}
/*
Append a wide character.
The caller must have allocated at least cs->mbmaxlen bytes.
*/
int q_append_wc(my_wc_t wc, CHARSET_INFO *cs)
{
int mblen;
if ((mblen= cs->cset->wc_mb(cs, wc,
(uchar *) end(),
(uchar *) end() + cs->mbmaxlen)) > 0)
str_length+= (uint32) mblen;
return mblen;
}
void q_append(const char *data, size_t data_len)
{
if (data_len)
@ -1009,8 +1022,6 @@ public:
(quot && append(quot));
}
bool append(const char *s, size_t size);
bool append_with_prefill(const char *s, uint32 arg_length,
uint32 full_length, char fill_char);
bool append_parenthesized(long nr, int radix= 10);
// Append with optional character set conversion from cs to charset()
@ -1020,6 +1031,31 @@ public:
return append(s.str, s.length, cs);
}
// Append a wide character
bool append_wc(my_wc_t wc)
{
if (reserve(mbmaxlen()))
return true;
int mblen= q_append_wc(wc, charset());
if (mblen > 0)
return false;
else if (mblen == MY_CS_ILUNI && wc != '?')
return q_append_wc('?', charset()) <= 0;
return true;
}
// Append a number with zero prefilling
bool append_zerofill(uint num, uint width)
{
static const char zeros[15]= "00000000000000";
char intbuff[15];
uint length= (uint) (int10_to_str(num, intbuff, 10) - intbuff);
if (length < width &&
append(zeros, width - length, &my_charset_latin1))
return true;
return append(intbuff, length, &my_charset_latin1);
}
/*
Append a bitmask in an uint32 with a translation into a
C-style human readable representation, e.g.: