dir API: add a generalized path_match_flags() function

Add a path_match_flags() function and have the two sets of
starts_with_dot_{,dot_}slash() functions added in
63e95be (submodule: port resolve_relative_url from shell to C,
2016-04-15) and a2b26ff (fsck: convert gitmodules url to URL
passed to curl, 2020-04-18) be thin wrappers for it.

As the latter of those notes the fsck version was copied from the
initial builtin/submodule--helper.c version.

Since the code added in a2b26ff was doing really doing the same as
win32_is_dir_sep() added in 1cadad6 (git clone <url>
C:\cygwin\home\USER\repo' is working (again), 2018-12-15) let's move
the latter to git-compat-util.h is a is_xplatform_dir_sep(). We can
then call either it or the platform-specific is_dir_sep() from this
new function.

Let's likewise change code in various other places that was hardcoding
checks for "'/' || '\\'" with the new is_xplatform_dir_sep(). As can
be seen in those callers some of them still concern themselves with
':' (Mac OS classic?), but let's leave the question of whether that
should be consolidated for some other time.

As we expect to make wider use of the "native" case in the future,
define and use two starts_with_dot_{,dot_}slash_native() convenience
wrappers. This makes the diff in builtin/submodule--helper.c much
smaller.

Signed-off-by: Ævar Arnfjörð Bjarmason <[email protected]>
Signed-off-by: Derrick Stolee <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: avar

builtin/submodule--helper.c

@@ -72,16 +72,6 @@ static char *get_default_remote(void)
 	return repo_get_default_remote(the_repository);
 }
 
-static int starts_with_dot_slash(const char *str)
-{
-	return str[0] == '.' && is_dir_sep(str[1]);
-}
-
-static int starts_with_dot_dot_slash(const char *str)
-{
-	return str[0] == '.' && str[1] == '.' && is_dir_sep(str[2]);
-}
-
 /*
  * Returns 1 if it was the last chop before ':'.
  */
@@ -108,6 +98,16 @@ static int chop_last_dir(char **remoteurl, int is_relative)
 	return 0;
 }
 
+static int starts_with_dot_slash(const char *const path)
+{
+	return starts_with_dot_slash_native(path);;
+}
+
+static int starts_with_dot_dot_slash(const char *const path)
+{
+	return starts_with_dot_dot_slash_native(path);
+}
+
 /*
  * The `url` argument is the URL that navigates to the submodule origin
  * repo. When relative, this URL is relative to the superproject origin

compat/mingw.c

@@ -2830,7 +2830,7 @@ int is_valid_win32_path(const char *path, int allow_literal_nul)
 			}
 
 			c = path[i];
-			if (c && c != '.' && c != ':' && c != '/' && c != '\\')
+			if (c && c != '.' && c != ':' && !is_xplatform_dir_sep(c))
 				goto not_a_reserved_name;
 
 			/* contains reserved name */

compat/win32/path-utils.h

@@ -6,11 +6,7 @@ int win32_has_dos_drive_prefix(const char *path);
 
 int win32_skip_dos_drive_prefix(char **path);
 #define skip_dos_drive_prefix win32_skip_dos_drive_prefix
-static inline int win32_is_dir_sep(int c)
-{
-	return c == '/' || c == '\\';
-}
-#define is_dir_sep win32_is_dir_sep
+#define is_dir_sep is_xplatform_dir_sep
 static inline char *win32_find_last_dir_sep(const char *path)
 {
 	char *ret = NULL;

dir.c

@@ -3890,3 +3890,32 @@ void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_
 
 	connect_work_tree_and_git_dir(path, new_git_dir, 0);
 }
+
+int path_match_flags(const char *const str, const enum path_match_flags flags)
+{
+	const char *p = str;
+
+	if (flags & PATH_MATCH_NATIVE &&
+	    flags & PATH_MATCH_XPLATFORM)
+		BUG("path_match_flags() must get one match kind, not multiple!");
+	else if (!(flags & PATH_MATCH_KINDS_MASK))
+		BUG("path_match_flags() must get at least one match kind!");
+
+	if (flags & PATH_MATCH_STARTS_WITH_DOT_SLASH &&
+	    flags & PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH)
+		BUG("path_match_flags() must get one platform kind, not multiple!");
+	else if (!(flags & PATH_MATCH_PLATFORM_MASK))
+		BUG("path_match_flags() must get at least one platform kind!");
+
+	if (*p++ != '.')
+		return 0;
+	if (flags & PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH &&
+	    *p++ != '.')
+		return 0;
+
+	if (flags & PATH_MATCH_NATIVE)
+		return is_dir_sep(*p);
+	else if (flags & PATH_MATCH_XPLATFORM)
+		return is_xplatform_dir_sep(*p);
+	BUG("unreachable");
+}

dir.h

@@ -578,4 +578,67 @@ void connect_work_tree_and_git_dir(const char *work_tree,
 void relocate_gitdir(const char *path,
 		     const char *old_git_dir,
 		     const char *new_git_dir);
+
+/**
+ * The "enum path_matches_kind" determines how path_match_flags() will
+ * behave. The flags come in sets, and one (and only one) must be
+ * provided out of each "set":
+ *
+ * PATH_MATCH_NATIVE:
+ *	Path separator is is_dir_sep()
+ * PATH_MATCH_XPLATFORM:
+ *	Path separator is is_xplatform_dir_sep()
+ *
+ * Do we use is_dir_sep() to check for a directory separator
+ * (*_NATIVE), or do we always check for '/' or '\' (*_XPLATFORM). The
+ * "*_NATIVE" version on Windows is the same as "*_XPLATFORM",
+ * everywhere else "*_NATIVE" means "only /".
+ *
+ * PATH_MATCH_STARTS_WITH_DOT_SLASH:
+ *	Match a path starting with "./"
+ * PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH:
+ *	Match a path starting with "../"
+ *
+ * The "/" in the above is adjusted based on the "*_NATIVE" and
+ * "*_XPLATFORM" flags.
+ */
+enum path_match_flags {
+	PATH_MATCH_NATIVE = 1 << 0,
+	PATH_MATCH_XPLATFORM = 1 << 1,
+	PATH_MATCH_STARTS_WITH_DOT_SLASH = 1 << 2,
+	PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH = 1 << 3,
+};
+#define PATH_MATCH_KINDS_MASK (PATH_MATCH_STARTS_WITH_DOT_SLASH | \
+	PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH)
+#define PATH_MATCH_PLATFORM_MASK (PATH_MATCH_NATIVE | PATH_MATCH_XPLATFORM)
+
+/**
+ * path_match_flags() checks if a given "path" matches a given "enum
+ * path_match_flags" criteria.
+ */
+int path_match_flags(const char *const path, const enum path_match_flags f);
+
+/**
+ * starts_with_dot_slash_native(): convenience wrapper for
+ * path_match_flags() with PATH_MATCH_STARTS_WITH_DOT_SLASH and
+ * PATH_MATCH_NATIVE.
+ */
+static inline int starts_with_dot_slash_native(const char *const path)
+{
+	const enum path_match_flags what = PATH_MATCH_STARTS_WITH_DOT_SLASH;
+
+	return path_match_flags(path, what | PATH_MATCH_NATIVE);
+}
+
+/**
+ * starts_with_dot_slash_native(): convenience wrapper for
+ * path_match_flags() with PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH and
+ * PATH_MATCH_NATIVE.
+ */
+static inline int starts_with_dot_dot_slash_native(const char *const path)
+{
+	const enum path_match_flags what = PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH;
+
+	return path_match_flags(path, what | PATH_MATCH_NATIVE);
+}
 #endif

fsck.c

@@ -975,27 +975,16 @@ int fsck_tag_standalone(const struct object_id *oid, const char *buffer,
 	return ret;
 }
 
-/*
- * Like builtin/submodule--helper.c's starts_with_dot_slash, but without
- * relying on the platform-dependent is_dir_sep helper.
- *
- * This is for use in checking whether a submodule URL is interpreted as
- * relative to the current directory on any platform, since \ is a
- * directory separator on Windows but not on other platforms.
- */
-static int starts_with_dot_slash(const char *str)
+static int starts_with_dot_slash(const char *const path)
 {
-	return str[0] == '.' && (str[1] == '/' || str[1] == '\\');
+	return path_match_flags(path, PATH_MATCH_STARTS_WITH_DOT_SLASH |
+				PATH_MATCH_XPLATFORM);
 }
 
-/*
- * Like starts_with_dot_slash, this is a variant of submodule--helper's
- * helper of the same name with the twist that it accepts backslash as a
- * directory separator even on non-Windows platforms.
- */
-static int starts_with_dot_dot_slash(const char *str)
+static int starts_with_dot_dot_slash(const char *const path)
 {
-	return str[0] == '.' && starts_with_dot_slash(str + 1);
+	return path_match_flags(path, PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH |
+				PATH_MATCH_XPLATFORM);
 }
 
 static int submodule_url_is_relative(const char *url)

git-compat-util.h

@@ -236,6 +236,12 @@
 #include <sys/sysctl.h>
 #endif
 
+/* Used by compat/win32/path-utils.h, and more */
+static inline int is_xplatform_dir_sep(int c)
+{
+	return c == '/' || c == '\\';
+}
+
 #if defined(__CYGWIN__)
 #include "compat/win32/path-utils.h"
 #endif
@@ -416,11 +422,11 @@ static inline int git_skip_dos_drive_prefix(char **path)
 #define skip_dos_drive_prefix git_skip_dos_drive_prefix
 #endif
 
-#ifndef is_dir_sep
 static inline int git_is_dir_sep(int c)
 {
 	return c == '/';
 }
+#ifndef is_dir_sep
 #define is_dir_sep git_is_dir_sep
 #endif
 

path.c

@@ -1413,7 +1413,7 @@ int is_ntfs_dotgit(const char *name)
 
 	for (;;) {
 		c = *(name++);
-		if (!c || c == '\\' || c == '/' || c == ':')
+		if (!c || is_xplatform_dir_sep(c) || c == ':')
 			return 1;
 		if (c != '.' && c != ' ')
 			return 0;

submodule-config.c

@@ -204,17 +204,17 @@ int check_submodule_name(const char *name)
 		return -1;
 
 	/*
-	 * Look for '..' as a path component. Check both '/' and '\\' as
+	 * Look for '..' as a path component. Check is_xplatform_dir_sep() as
 	 * separators rather than is_dir_sep(), because we want the name rules
 	 * to be consistent across platforms.
 	 */
 	goto in_component; /* always start inside component */
 	while (*name) {
 		char c = *name++;
-		if (c == '/' || c == '\\') {
+		if (is_xplatform_dir_sep(c)) {
 in_component:
 			if (name[0] == '.' && name[1] == '.' &&
-			    (!name[2] || name[2] == '/' || name[2] == '\\'))
+			    (!name[2] || is_xplatform_dir_sep(name[2])))
 				return -1;
 		}
 	}