[PATCH 3/4] dir.[ch]: add 'follow_symlink' arg to 'get_dtype'

["Victoria Dye via GitGitGadget" <gitgitgadget@xxxxxxxxx>]

From: Victoria Dye <vdye@xxxxxxxxxx>

Add a 'follow_symlink' boolean option to 'get_type()'. If 'follow_symlink'
is enabled, DT_LNK (in addition to DT_UNKNOWN) d_types triggers the
stat-based d_type resolution, using 'stat' instead of 'lstat' to get the
type of the followed symlink. Note that symlinks are not followed
recursively, so a symlink pointing to another symlink will still resolve to
DT_LNK.

Update callers in 'diagnose.c' to specify 'follow_symlink = 0' to preserve
current behavior.

Signed-off-by: Victoria Dye <vdye@xxxxxxxxxx>
---
 diagnose.c |  6 +++---
 dir.c      | 13 +++++++++----
 dir.h      |  7 ++++++-
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/diagnose.c b/diagnose.c
index fc4d344bd63..4d096c857f1 100644
--- a/diagnose.c
+++ b/diagnose.c
@@ -81,7 +81,7 @@ static int count_files(struct strbuf *path)
 		return 0;
 
 	while ((e = readdir_skip_dot_and_dotdot(dir)) != NULL)
-		if (get_dtype(e, path) == DT_REG)
+		if (get_dtype(e, path, 0) == DT_REG)
 			count++;
 
 	closedir(dir);
@@ -110,7 +110,7 @@ static void loose_objs_stats(struct strbuf *buf, const char *path)
 	base_path_len = count_path.len;
 
 	while ((e = readdir_skip_dot_and_dotdot(dir)) != NULL)
-		if (get_dtype(e, &count_path) == DT_DIR &&
+		if (get_dtype(e, &count_path, 0) == DT_DIR &&
 		    strlen(e->d_name) == 2 &&
 		    !hex_to_bytes(&c, e->d_name, 1)) {
 			strbuf_setlen(&count_path, base_path_len);
@@ -155,7 +155,7 @@ static int add_directory_to_archiver(struct strvec *archiver_args,
 
 		strbuf_add_absolute_path(&abspath, at_root ? "." : path);
 		strbuf_addch(&abspath, '/');
-		dtype = get_dtype(e, &abspath);
+		dtype = get_dtype(e, &abspath, 0);
 
 		strbuf_setlen(&buf, len);
 		strbuf_addstr(&buf, e->d_name);
diff --git a/dir.c b/dir.c
index 5e01af3a25e..16fdb03f2a5 100644
--- a/dir.c
+++ b/dir.c
@@ -2235,19 +2235,24 @@ static int get_index_dtype(struct index_state *istate,
 	return DT_UNKNOWN;
 }
 
-unsigned char get_dtype(struct dirent *e, struct strbuf *path)
+unsigned char get_dtype(struct dirent *e, struct strbuf *path,
+			int follow_symlink)
 {
 	struct stat st;
 	unsigned char dtype = DTYPE(e);
 	size_t base_path_len;
 
-	if (dtype != DT_UNKNOWN)
+	if (dtype != DT_UNKNOWN && !(follow_symlink && dtype == DT_LNK))
 		return dtype;
 
-	/* d_type unknown in dirent, try to fall back on lstat results */
+	/*
+	 * d_type unknown or unfollowed symlink, try to fall back on [l]stat
+	 * results. If [l]stat fails, explicitly set DT_UNKNOWN.
+	 */
 	base_path_len = path->len;
 	strbuf_addstr(path, e->d_name);
-	if (lstat(path->buf, &st))
+	if ((follow_symlink && stat(path->buf, &st)) ||
+	    (!follow_symlink && lstat(path->buf, &st)))
 		goto cleanup;
 
 	/* determine d_type from st_mode */
diff --git a/dir.h b/dir.h
index 28c630ce806..98aa85fcc0e 100644
--- a/dir.h
+++ b/dir.h
@@ -368,11 +368,16 @@ struct dirent *readdir_skip_dot_and_dotdot(DIR *dirp);
  * stat.st_mode using the path to the dirent's containing directory (path) and
  * the name of the dirent itself.
  *
+ * If 'follow_symlink' is 1, this function will attempt to follow DT_LNK types
+ * using 'stat'. Links are *not* followed recursively, so a symlink pointing
+ * to another symlink will still resolve to 'DT_LNK'.
+ *
  * Note that 'path' is assumed to have a trailing slash. It is also modified
  * in-place during the execution of the function, but is then reverted to its
  * original value before returning.
  */
-unsigned char get_dtype(struct dirent *e, struct strbuf *path);
+unsigned char get_dtype(struct dirent *e, struct strbuf *path,
+			int follow_symlink);
 
 /*Count the number of slashes for string s*/
 int count_slashes(const char *s);
-- 
gitgitgadget