apply: avoid out-of-bounds access in fuzzy_matchlines()

fuzzy_matchlines() uses a pointers to the first and last characters of
two lines to keep track while matching them.  This makes it impossible
to deal with empty strings.  It accesses characters before the start of
empty lines.  It can also access characters after the end when checking
for trailing whitespace in the main loop.

Avoid that by using pointers to the first character and the one *after*
the last one.  This is well-defined as long as the latter is not
dereferenced.  Basically rewrite the function based on that premise; it
becomes much simpler as a result.  There is no need to check for
leading whitespace outside of the main loop anymore.

Reported-by: Mahmoud Al-Qudsi <mqudsi@neosmart.net>
Signed-off-by: Rene Scharfe <l.s.r@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/apply.c b/apply.c
index 705cf562f07098aafcd9f6e27105d2105714751f..fd00919513340052144e777101a7f5de5d164aa6 100644 (file)
--- a/apply.c
+++ b/apply.c
@@ -303,52 +303,33 @@ static uint32_t hash_line(const char *cp, size_t len)
 static int fuzzy_matchlines(const char *s1, size_t n1,
                            const char *s2, size_t n2)
 {
-       const char *last1 = s1 + n1 - 1;
-       const char *last2 = s2 + n2 - 1;
-       int result = 0;
+       const char *end1 = s1 + n1;
+       const char *end2 = s2 + n2;
 
        /* ignore line endings */
-       while ((*last1 == '\r') || (*last1 == '\n'))
-               last1--;
-       while ((*last2 == '\r') || (*last2 == '\n'))
-               last2--;
-
-       /* skip leading whitespaces, if both begin with whitespace */
-       if (s1 <= last1 && s2 <= last2 && isspace(*s1) && isspace(*s2)) {
-               while (isspace(*s1) && (s1 <= last1))
-                       s1++;
-               while (isspace(*s2) && (s2 <= last2))
-                       s2++;
-       }
-       /* early return if both lines are empty */
-       if ((s1 > last1) && (s2 > last2))
-               return 1;
-       while (!result) {
-               result = *s1++ - *s2++;
-               /*
-                * Skip whitespace inside. We check for whitespace on
-                * both buffers because we don't want "a b" to match
-                * "ab"
-                */
-               if (isspace(*s1) && isspace(*s2)) {
-                       while (isspace(*s1) && s1 <= last1)
+       while (s1 < end1 && (end1[-1] == '\r' || end1[-1] == '\n'))
+               end1--;
+       while (s2 < end2 && (end2[-1] == '\r' || end2[-1] == '\n'))
+               end2--;
+
+       while (s1 < end1 && s2 < end2) {
+               if (isspace(*s1)) {
+                       /*
+                        * Skip whitespace. We check on both buffers
+                        * because we don't want "a b" to match "ab".
+                        */
+                       if (!isspace(*s2))
+                               return 0;
+                       while (s1 < end1 && isspace(*s1))
                                s1++;
-                       while (isspace(*s2) && s2 <= last2)
+                       while (s2 < end2 && isspace(*s2))
                                s2++;
-               }
-               /*
-                * If we reached the end on one side only,
-                * lines don't match
-                */
-               if (
-                   ((s2 > last2) && (s1 <= last1)) ||
-                   ((s1 > last1) && (s2 <= last2)))
+               } else if (*s1++ != *s2++)
                        return 0;
-               if ((s1 > last1) && (s2 > last2))
-                       break;
        }
 
-       return !result;
+       /* If we reached the end on one side only, lines don't match. */
+       return s1 == end1 && s2 == end2;
 }
 
 static void add_line_info(struct image *img, const char *bol, size_t len, unsigned flag)