d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bsdgrep: fix escape map building for multibyte strings

Browse Source 
In BSD grep, fix escape map building in the regex parser. It was
previously using memory not explicitly initialized, and the MBS escape
map was being built based on a version of the pattern with escapes
already parsed out.

This is Kyle's change, but I restored the broken style that already
exists in this file.

Submitted by:	Kyle Evans <kevans91 at ksu.edu>
Reviewed by:	cem, Kyle Evans (my style changes)
Differential Revision:	https://reviews.freebsd.org/D10098
This commit is contained in:
Ed Maste 2017-05-02 20:44:06 +00:00
parent a4f3f02be6
commit 41e04e8c77
Notes: svn2git 2020-12-20 02:59:44 +00:00 
svn path=/head/; revision=317704
1 changed files with 33 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
usr.bin/grep/regex/tre-fastmatch.c
View File

@ -98,6 +98,18 @@ static int fastcmp(const fastmatch_t *fg, const void *data,
fg->pattern[siz] = '\0'; \
} \
#define CONV_MBS_PAT(src, dest, destsz) \
{ \
destsz = wcstombs(NULL, src, 0); \
if (destsz == (size_t)-1) \
return REG_BADPAT; \
dest = malloc(destsz + 1); \
if (dest == NULL) \
return REG_ESPACE; \
wcstombs(dest, src, destsz); \
dest[destsz] = '\0'; \
} \
#define IS_OUT_OF_BOUNDS \
((!fg->reversed \
? ((type == STR_WIDE) ? ((j + fg->wlen) > len) \
@ -723,15 +735,29 @@ tre_compile_fast(fastmatch_t *fg, const tre_char_t *pat, size_t n,
}
escaped = false;
for (unsigned int i = 0; i < fg->len; i++)
if (fg->pattern[i] == '\\')
escaped = !escaped;
else if (fg->pattern[i] == '.' && fg->escmap && escaped)
char *_checkpat = NULL;
size_t _checklen = 0;
unsigned int escofs = 0;
/*
* Make a copy here of the original pattern, because fg->pattern has
* already been stripped of all escape sequences in the above processing.
* This is necessary if we wish to later treat fg->escmap as an actual,
* functional replacement of fg->wescmap.
*/
CONV_MBS_PAT(pat, _checkpat, _checklen);
for (unsigned int i = 0; i < n; i++)
if (_checkpat[i] == '\\')
{
fg->escmap[i] = true;
escaped = !escaped;
if (escaped)
++escofs;
}
else if (_checkpat[i] == '.' && fg->escmap != NULL && escaped)
{
fg->escmap[i - escofs] = true;
escaped = false;
}
else if (fg->pattern[i] == '.' && !escaped)
else if (_checkpat[i] == '.' && !escaped)
{
hasdot = i;
if (firstdot == -1)
@ -739,6 +765,7 @@ tre_compile_fast(fastmatch_t *fg, const tre_char_t *pat, size_t n,
}
else
escaped = false;
free(_checkpat);
}
#else
SAVE_PATTERN(tmp, pos, fg->pattern, fg->len);