cleanup: fix possible overflow errors in binary search

A common mistake when writing binary search is to allow possible
integer overflow by using the simple average:

	mid = (min + max) / 2;

Instead, use the overflow-safe version:

	mid = min + (max - min) / 2;

This translation is safe since the operation occurs inside a loop
conditioned on "min < max". The included changes were found using
the following git grep:

	git grep '/ *2;' '*.c'

Making this cleanup will prevent future review friction when a new
binary search is contructed based on existing code.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Reviewed-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index f2be145..8ec459f 100644 (file)
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -633,7 +633,7 @@ static int find_ofs_delta(const off_t offset, enum object_type type)
        int first = 0, last = nr_ofs_deltas;
 
        while (first < last) {
-               int next = (first + last) / 2;
+               int next = first + (last - first) / 2;
                struct ofs_delta_entry *delta = &ofs_deltas[next];
                int cmp;
 
@@ -687,7 +687,7 @@ static int find_ref_delta(const unsigned char *sha1, enum object_type type)
        int first = 0, last = nr_ref_deltas;
 
        while (first < last) {
-               int next = (first + last) / 2;
+               int next = first + (last - first) / 2;
                struct ref_delta_entry *delta = &ref_deltas[next];
                int cmp;
 

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 5ee2c48..6e77dfd 100644 (file)
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -1277,7 +1277,7 @@ static int done_pbase_path_pos(unsigned hash)
        int lo = 0;
        int hi = done_pbase_paths_num;
        while (lo < hi) {
-               int mi = (hi + lo) / 2;
+               int mi = lo + (hi - lo) / 2;
                if (done_pbase_paths[mi] == hash)
                        return mi;
                if (done_pbase_paths[mi] < hash)

diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index 689a29f..62ea264 100644 (file)
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -394,7 +394,7 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
                lo = 0;
                hi = nr;
                while (lo < hi) {
-                       mid = (lo + hi)/2;
+                       mid = lo + (hi - lo) / 2;
                        if (base_offset < obj_list[mid].offset) {
                                hi = mid;
                        } else if (base_offset > obj_list[mid].offset) {

diff --git a/cache-tree.c b/cache-tree.c
index 71d092e..d3f7401 100644 (file)
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -49,7 +49,7 @@ static int subtree_pos(struct cache_tree *it, const char *path, int pathlen)
        lo = 0;
        hi = it->subtree_nr;
        while (lo < hi) {
-               int mi = (lo + hi) / 2;
+               int mi = lo + (hi - lo) / 2;
                struct cache_tree_sub *mdl = down[mi];
                int cmp = subtree_name_cmp(path, pathlen,
                                           mdl->name, mdl->namelen);

diff --git a/compat/regex/regex_internal.c b/compat/regex/regex_internal.c
index d4121f2..98342b8 100644 (file)
--- a/compat/regex/regex_internal.c
+++ b/compat/regex/regex_internal.c
@@ -613,7 +613,7 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
              int low = 0, high = pstr->valid_len, mid;
              do
                {
-                 mid = (high + low) / 2;
+                 mid = low + (high - low) / 2;
                  if (pstr->offsets[mid] > offset)
                    high = mid;
                  else if (pstr->offsets[mid] < offset)
@@ -1394,7 +1394,7 @@ re_node_set_contains (const re_node_set *set, int elem)
   right = set->nelem - 1;
   while (idx < right)
     {
-      mid = (idx + right) / 2;
+      mid = idx + (right - idx) / 2;
       if (set->elems[mid] < elem)
        idx = mid + 1;
       else

diff --git a/compat/regex/regexec.c b/compat/regex/regexec.c
index 0a745d9..6f2b48a 100644 (file)
--- a/compat/regex/regexec.c
+++ b/compat/regex/regexec.c
@@ -4284,7 +4284,7 @@ search_cur_bkref_entry (const re_match_context_t *mctx, int str_idx)
   last = right = mctx->nbkref_ents;
   for (left = 0; left < right;)
     {
-      mid = (left + right) / 2;
+      mid = left + (right - left) / 2;
       if (mctx->bkref_ents[mid].str_idx < str_idx)
        left = mid + 1;
       else

diff --git a/packfile.c b/packfile.c
index eab7542..4a5fe7a 100644 (file)
--- a/packfile.c
+++ b/packfile.c
@@ -1743,7 +1743,7 @@ off_t find_pack_entry_one(const unsigned char *sha1,
                       sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
 
        while (lo < hi) {
-               unsigned mi = (lo + hi) / 2;
+               unsigned mi = lo + (hi - lo) / 2;
                int cmp = hashcmp(index + mi * stride, sha1);
 
                if (debug_lookup)

diff --git a/sha1-lookup.c b/sha1-lookup.c
index 2552b79..4cf3ebd 100644 (file)
--- a/sha1-lookup.c
+++ b/sha1-lookup.c
@@ -10,7 +10,7 @@ static uint32_t take2(const unsigned char *sha1)
  * Conventional binary search loop looks like this:
  *
  *      do {
- *              int mi = (lo + hi) / 2;
+ *              int mi = lo + (hi - lo) / 2;
  *              int cmp = "entry pointed at by mi" minus "target";
  *              if (!cmp)
  *                      return (mi is the wanted one)
@@ -95,7 +95,7 @@ int sha1_pos(const unsigned char *sha1, void *table, size_t nr,
                        hi = mi;
                else
                        lo = mi + 1;
-               mi = (hi + lo) / 2;
+               mi = lo + (hi - lo) / 2;
        } while (lo < hi);
        return -lo-1;
 }

diff --git a/sha1_name.c b/sha1_name.c
index 134ac97..c7c5ab3 100644 (file)
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -157,7 +157,7 @@ static void unique_in_pack(struct packed_git *p,
        num = p->num_objects;
        last = num;
        while (first < last) {
-               uint32_t mid = (first + last) / 2;
+               uint32_t mid = first + (last - first) / 2;
                const unsigned char *current;
                int cmp;
 

diff --git a/string-list.c b/string-list.c
index 806b4c8..a0cf0cf 100644 (file)
--- a/string-list.c
+++ b/string-list.c
@@ -16,7 +16,7 @@ static int get_entry_index(const struct string_list *list, const char *string,
        compare_strings_fn cmp = list->cmp ? list->cmp : strcmp;
 
        while (left + 1 < right) {
-               int middle = (left + right) / 2;
+               int middle = left + (right - left) / 2;
                int compare = cmp(string, list->items[middle].string);
                if (compare < 0)
                        right = middle;

diff --git a/utf8.c b/utf8.c
index 47a4204..2c27ce0 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -32,7 +32,7 @@ static int bisearch(ucs_char_t ucs, const struct interval *table, int max)
        if (ucs < table[0].first || ucs > table[max].last)
                return 0;
        while (max >= min) {
-               mid = (min + max) / 2;
+               mid = min + (max - min) / 2;
                if (ucs > table[mid].last)
                        min = mid + 1;
                else if (ucs < table[mid].first)

diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c
index a613efc..9f91702 100644 (file)
--- a/xdiff/xpatience.c
+++ b/xdiff/xpatience.c
@@ -166,7 +166,7 @@ static int binary_search(struct entry **sequence, int longest,
        int left = -1, right = longest;
 
        while (left + 1 < right) {
-               int middle = (left + right) / 2;
+               int middle = left + (right - left) / 2;
                /* by construction, no two entries can be equal */
                if (sequence[middle]->line2 > entry->line2)
                        right = middle;