is_ntfs_dotgit(): only verify the leading segment

[thirdparty/git.git] / path.c

diff --git a/path.c b/path.c
index 335d4dd8777bccfe84415f8d8b738a9a844e248d..f62a37d5f5122b660ae695685f5f87a4c9e5e255 100644 (file)
--- a/path.c
+++ b/path.c
@@ -1302,9 +1302,37 @@ static int only_spaces_and_periods(const char *path, size_t len, size_t skip)
        return 1;
 }
 
+/*
+ * On NTFS, we need to be careful to disallow certain synonyms of the `.git/`
+ * directory:
+ *
+ * - For historical reasons, file names that end in spaces or periods are
+ *   automatically trimmed. Therefore, `.git . . ./` is a valid way to refer
+ *   to `.git/`.
+ *
+ * - For other historical reasons, file names that do not conform to the 8.3
+ *   format (up to eight characters for the basename, three for the file
+ *   extension, certain characters not allowed such as `+`, etc) are associated
+ *   with a so-called "short name", at least on the `C:` drive by default.
+ *   Which means that `git~1/` is a valid way to refer to `.git/`.
+ *
+ *   Note: Technically, `.git/` could receive the short name `git~2` if the
+ *   short name `git~1` were already used. In Git, however, we guarantee that
+ *   `.git` is the first item in a directory, therefore it will be associated
+ *   with the short name `git~1` (unless short names are disabled).
+ *
+ * When this function returns 1, it indicates that the specified file/directory
+ * name refers to a `.git` file or directory, or to any of these synonyms, and
+ * Git should therefore not track it.
+ *
+ * This function is intended to be used by `git fsck` even on platforms where
+ * the backslash is a regular filename character, therefore it needs to handle
+ * backlash characters in the provided `name` specially: they are interpreted
+ * as directory separators.
+ */
 int is_ntfs_dotgit(const char *name)
 {
-       int len;
+       size_t len;
 
        for (len = 0; ; len++)
                if (!name[len] || name[len] == '\\' || is_dir_sep(name[len])) {
@@ -1314,11 +1342,92 @@ int is_ntfs_dotgit(const char *name)
                        if (only_spaces_and_periods(name, len, 5) &&
                                        !strncasecmp(name, "git~1", 5))
                                return 1;
-                       if (name[len] != '\\')
+                       return 0;
+               }
+}
+
+static int is_ntfs_dot_generic(const char *name,
+                              const char *dotgit_name,
+                              size_t len,
+                              const char *dotgit_ntfs_shortname_prefix)
+{
+       int saw_tilde;
+       size_t i;
+
+       if ((name[0] == '.' && !strncasecmp(name + 1, dotgit_name, len))) {
+               i = len + 1;
+only_spaces_and_periods:
+               for (;;) {
+                       char c = name[i++];
+                       if (!c)
+                               return 1;
+                       if (c != ' ' && c != '.')
                                return 0;
-                       name += len + 1;
-                       len = -1;
                }
+       }
+
+       /*
+        * Is it a regular NTFS short name, i.e. shortened to 6 characters,
+        * followed by ~1, ... ~4?
+        */
+       if (!strncasecmp(name, dotgit_name, 6) && name[6] == '~' &&
+           name[7] >= '1' && name[7] <= '4') {
+               i = 8;
+               goto only_spaces_and_periods;
+       }
+
+       /*
+        * Is it a fall-back NTFS short name (for details, see
+        * https://en.wikipedia.org/wiki/8.3_filename?
+        */
+       for (i = 0, saw_tilde = 0; i < 8; i++)
+               if (name[i] == '\0')
+                       return 0;
+               else if (saw_tilde) {
+                       if (name[i] < '0' || name[i] > '9')
+                               return 0;
+               } else if (name[i] == '~') {
+                       if (name[++i] < '1' || name[i] > '9')
+                               return 0;
+                       saw_tilde = 1;
+               } else if (i >= 6)
+                       return 0;
+               else if (name[i] < 0) {
+                       /*
+                        * We know our needles contain only ASCII, so we clamp
+                        * here to make the results of tolower() sane.
+                        */
+                       return 0;
+               } else if (tolower(name[i]) != dotgit_ntfs_shortname_prefix[i])
+                       return 0;
+
+       goto only_spaces_and_periods;
+}
+
+/*
+ * Inline helper to make sure compiler resolves strlen() on literals at
+ * compile time.
+ */
+static inline int is_ntfs_dot_str(const char *name, const char *dotgit_name,
+                                 const char *dotgit_ntfs_shortname_prefix)
+{
+       return is_ntfs_dot_generic(name, dotgit_name, strlen(dotgit_name),
+                                  dotgit_ntfs_shortname_prefix);
+}
+
+int is_ntfs_dotgitmodules(const char *name)
+{
+       return is_ntfs_dot_str(name, "gitmodules", "gi7eba");
+}
+
+int is_ntfs_dotgitignore(const char *name)
+{
+       return is_ntfs_dot_str(name, "gitignore", "gi250a");
+}
+
+int is_ntfs_dotgitattributes(const char *name)
+{
+       return is_ntfs_dot_str(name, "gitattributes", "gi7d29");
 }
 
 int looks_like_command_line_option(const char *str)