is_ntfs_dotgit(): speed it up

Previously, this function was written without focusing on speed,
intending to make reviewing the code as easy as possible, to avoid any
bugs in this critical code.

Turns out: we can do much better on both accounts. With this patch, we
make it as fast as this developer can make it go:

- We avoid the call to `is_dir_sep()` and make all the character
  comparisons explicit.

- We avoid the cost of calling `strncasecmp()` and unroll the test for
  `.git` and `git~1`, not even using `tolower()` because it is faster to
  compare against two constant values.

- We look for `.git` and `.git~1` first thing, and return early if not
  found.

- We also avoid calling a separate function for detecting chains of
  spaces and periods.

Each of these improvements has a noticeable impact on the speed of
`is_ntfs_dotgit()`.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>

diff --git a/path.c b/path.c
index 2037e2d8c1daed5337c9311c1490341707ecc601..43b16aabd4235c2ddb0913c3235be566a07f76ff 100644 (file)
--- a/path.c
+++ b/path.c
@@ -1288,20 +1288,6 @@ int daemon_avoid_alias(const char *p)
        }
 }
 
-static int only_spaces_and_periods(const char *path, size_t len, size_t skip)
-{
-       if (len < skip)
-               return 0;
-       len -= skip;
-       path += skip;
-       while (len-- > 0) {
-               char c = *(path++);
-               if (c != ' ' && c != '.')
-                       return 0;
-       }
-       return 1;
-}
-
 /*
  * On NTFS, we need to be careful to disallow certain synonyms of the `.git/`
  * directory:
@@ -1341,19 +1327,38 @@ static int only_spaces_and_periods(const char *path, size_t len, size_t skip)
  */
 int is_ntfs_dotgit(const char *name)
 {
-       size_t len;
+       char c;
 
-       for (len = 0; ; len++)
-               if (!name[len] || name[len] == '\\' || is_dir_sep(name[len]) ||
-                   name[len] == ':') {
-                       if (only_spaces_and_periods(name, len, 4) &&
-                                       !strncasecmp(name, ".git", 4))
-                               return 1;
-                       if (only_spaces_and_periods(name, len, 5) &&
-                                       !strncasecmp(name, "git~1", 5))
-                               return 1;
+       /*
+        * Note that when we don't find `.git` or `git~1` we end up with `name`
+        * advanced partway through the string. That's okay, though, as we
+        * return immediately in those cases, without looking at `name` any
+        * further.
+        */
+       c = *(name++);
+       if (c == '.') {
+               /* .git */
+               if (((c = *(name++)) != 'g' && c != 'G') ||
+                   ((c = *(name++)) != 'i' && c != 'I') ||
+                   ((c = *(name++)) != 't' && c != 'T'))
                        return 0;
-               }
+       } else if (c == 'g' || c == 'G') {
+               /* git ~1 */
+               if (((c = *(name++)) != 'i' && c != 'I') ||
+                   ((c = *(name++)) != 't' && c != 'T') ||
+                   *(name++) != '~' ||
+                   *(name++) != '1')
+                       return 0;
+       } else
+               return 0;
+
+       for (;;) {
+               c = *(name++);
+               if (!c || c == '\\' || c == '/' || c == ':')
+                       return 1;
+               if (c != '.' && c != ' ')
+                       return 0;
+       }
 }
 
 static int is_ntfs_dot_generic(const char *name,