rdelaage/postgresql
1
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2024-09-04 17:47:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix not-terribly-safe coding in NIImportOOAffixes() and NIImportAffixes().

Browse Source 
There were two places in spell.c that supposed that they could search
for a location in a string produced by lowerstr() and then transpose
the offset into the original string.  But this fails completely if
lowerstr() transforms any characters into characters of different byte
length, as can happen in Turkish UTF8 for instance.

We'd added some comments about this coding in commit 51e78ab4ff,
but failed to realize that it was not merely confusing but wrong.

Coverity complained about this code years ago, but in such an opaque
fashion that nobody understood what it was on about.  I'm not entirely
sure that this issue *is* what it's on about, actually, but perhaps
this patch will shut it up -- and in any case the problem is clear.

Back-patch to all supported branches.
This commit is contained in:
Tom Lane 2016-03-06 19:21:03 -05:00
parent ababe02ac2
commit c2d61adc32
1 changed files with 22 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
src/backend/tsearch/spell.c
View File

@ -169,6 +169,19 @@ findchar(char *str, int c)
return NULL;
}
static char *
findchar2(char *str, int c1, int c2)
{
while (*str)
{
if (t_iseq(str, c1) || t_iseq(str, c2))
return str;
str += pg_mblen(str);
}
return NULL;
}
/* backward string compare for suffix tree operations */
static int
@ -856,22 +869,20 @@ NIImportOOAffixes(IspellDict *Conf, const char *filename)
if (strlen(sflag) != 1 || flag != *sflag || flag == 0)
goto nextline;
prepl = lowerstr_ctx(Conf, repl);
/* Find position of '/' in lowercased string "prepl" */
if ((ptr = strchr(prepl, '/')) != NULL)
/* Get flags after '/' (flags are case sensitive) */
if ((ptr = strchr(repl, '/')) != NULL)
{
/*
* Here we use non-lowercased string "repl". We need position
* of '/' in "repl".
*/
*ptr = '\0';
ptr = repl + (ptr - prepl) + 1;
ptr++;
while (*ptr)
{
aflg |= Conf->flagval[*(unsigned char *) ptr];
ptr++;
}
}
/* Get lowercased version of string before '/' */
prepl = lowerstr_ctx(Conf, repl);
if ((ptr = strchr(prepl, '/')) != NULL)
*ptr = '\0';
pfind = lowerstr_ctx(Conf, find);
pmask = lowerstr_ctx(Conf, mask);
if (t_iseq(find, '0'))
@ -939,12 +950,10 @@ NIImportAffixes(IspellDict *Conf, const char *filename)
if (STRNCMP(pstr, "compoundwords") == 0)
{
/* Find position in lowercased string "pstr" */
s = findchar(pstr, 'l');
/* Find case-insensitive L flag in non-lowercased string */
s = findchar2(recoded, 'l', 'L');
if (s)
{
/* Here we use non-lowercased string "recoded" */
s = recoded + (s - pstr);
while (*s && !t_isspace(s))
s += pg_mblen(s);
while (*s && t_isspace(s))