[PATCH v3 4/7] dir: add generic "walk all files" helper

From: Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com>
Date: Sep 12, 2025, 10:30 UTC
Message-ID: <6b29dda4b8961a999855ada42996de120513f218.1757673011.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1941.v3.git.1757673011.gitgitgadget@gmail.com>

From: Derrick Stolee <stolee@gmail.com>

There is sometimes a need to visit every file within a directory, recursively. The main example is remove_dir_recursively(), though it has some extra flags that make it want to iterate over paths in a custom way. There is also the fill_directory() approach but that involves an index and a pathspec.

This change adds a new for_each_file_in_dir() method that will be helpful in the next change.

Signed-off-by: Derrick Stolee <stolee@gmail.com>
---
 dir.c | 28 ++++++++++++++++++++++++++++
 dir.h | 14 ++++++++++++++
 2 files changed, 42 insertions(+)

diff --git a/dir.c b/dir.c
index 71108ac79b..194b36a8c4 100644
--- a/dir.c
+++ b/dir.c
@@ -30,6 +30,7 @@
 #include "read-cache-ll.h"
 #include "setup.h"
 #include "sparse-index.h"
+#include "strbuf.h"
 #include "submodule-config.h"
 #include "symlinks.h"
 #include "trace2.h"
@@ -87,6 +88,33 @@ struct dirent *readdir_skip_dot_and_dotdot(DIR *dirp)
 	return e;
 }
 
+int for_each_file_in_dir(struct strbuf *path, file_iterator fn, const void *data)
+{
+	struct dirent *e;
+	int res = 0;
+	size_t baselen = path->len;
+	DIR *dir = opendir(path->buf);
+
+	if (!dir)
+		return 0;
+
+	while (!res && (e = readdir_skip_dot_and_dotdot(dir)) != NULL) {
+		unsigned char dtype = get_dtype(e, path, 0);
+		strbuf_setlen(path, baselen);
+		strbuf_addstr(path, e->d_name);
+
+		if (dtype == DT_REG) {
+			res = fn(path->buf, data);
+		} else if (dtype == DT_DIR) {
+			strbuf_addch(path, '/');
+			res = for_each_file_in_dir(path, fn, data);
+		}
+	}
+
+	closedir(dir);
+	return res;
+}
+
 int count_slashes(const char *s)
 {
 	int cnt = 0;
diff --git a/dir.h b/dir.h
index fc9be7b427..20d4a078d6 100644
--- a/dir.h
+++ b/dir.h
@@ -536,6 +536,20 @@ int get_sparse_checkout_patterns(struct pattern_list *pl);
  */
 int remove_dir_recursively(struct strbuf *path, int flag);
 
+/*
+ * This function pointer type is called on each file discovered in
+ * for_each_file_in_dir. The iteration stops if this method returns
+ * non-zero.
+ */
+typedef int (*file_iterator)(const char *path, const void *data);
+
+struct strbuf;
+/*
+ * Given a directory path, recursively visit each file within, including
+ * within subdirectories.
+ */
+int for_each_file_in_dir(struct strbuf *path, file_iterator fn, const void *data);
+
 /*
  * Tries to remove the path, along with leading empty directories so long as
  * those empty directories are not startup_info->original_cwd.  Ignores

-- 
gitgitgadget