read-cache: update submodule need --force given ignore=all configuration

Submodules configured with ignore=all are now skipped during add operations
unless overridden by --force and the submodule path is explicitly specified.

A message is printed (like ignored files) guiding the user to use the
--force flag if the user has explicitely want to update the submodule
reference.

The reason for the change is support submodule branch tracking or
similar and git status states nothing and git add should not add either
as a default behaviour. The workflow is more logic and similar to regular
ignored files even the submodule is already tracked.

The change opens up a lot of possibilities for submodules to be used
more freely and simular to the repo tool. A submodule can be added for many
more reason and loosely coupled dependencies to the super repo which often
gives the friction of handle the explicit commits and updates without
the need for tracking the submodule sha1 by sha1.

Signed-off-by: Claus Schneider(Eficode) <claus.schneider@eficode.com>

Author: bicschneider

read-cache.c

@@ -48,6 +48,9 @@
 #include "csum-file.h"
 #include "promisor-remote.h"
 #include "hook.h"
+#include "submodule.h"
+#include "submodule-config.h"
+#include "advice.h"
 
 /* Mask for the name length in ce_flags in the on-disk index */
 
@@ -3909,8 +3912,66 @@ static int fix_unmerged_status(struct diff_filepair *p,
 		return DIFF_STATUS_MODIFIED;
 }
 
+static int should_skip_submodule_with_ignore_all(const char *path,
+                        struct repository *repo,
+                        struct pathspec *pathspec,
+                        int ignored_too)
+{
+    struct stat st;
+    const struct submodule *sub;
+    int pathspec_matches = 0;
+    int ps_i;
+    char *norm_pathspec = NULL;
+
+    /* Only consider if path is a directory */
+    if (lstat(path, &st) || !S_ISDIR(st.st_mode))
+        return 0;
+
+    /* Check if it's a submodule with ignore=all */
+    sub = submodule_from_path(repo, null_oid(the_hash_algo), path);
+    if (!sub || !sub->name || !sub->ignore || strcmp(sub->ignore, "all"))
+        return 0;
+
+    trace_printf("ignore=all %s\n", path);
+    trace_printf("pathspec %s\n",
+             (pathspec && pathspec->nr) ? "has pathspec" : "no pathspec");
+
+    /* Check if submodule path is explicitly mentioned in pathspec */
+    if (pathspec) {
+        for (ps_i = 0; ps_i < pathspec->nr; ps_i++) {
+            const char *m = pathspec->items[ps_i].match;
+            if (!m)
+                continue;
+            norm_pathspec = xstrdup(m);
+            strip_dir_trailing_slashes(norm_pathspec);
+            if (!strcmp(path, norm_pathspec)) {
+                pathspec_matches = 1;
+                FREE_AND_NULL(norm_pathspec);
+                break;
+            }
+            FREE_AND_NULL(norm_pathspec);
+        }
+    }
+
+    /* If explicitly matched and forced, allow adding */
+    if (pathspec_matches) {
+        if (ignored_too && ignored_too > 0) {
+            trace_printf("Add submodule due to --force: %s\n", path);
+            return 0;
+        } else {advise_if_enabled(ADVICE_ADD_IGNORED_FILE,
+                    _("Skipping submodule due to ignore=all: %s\n"
+                      "Use --force if you really want to add the submodule."), path);
+            return 1;
+        }
+    }
+
+    /* No explicit pathspec match -> skip silently */
+    trace_printf("Pathspec to submodule does not match explicitly: %s\n", path);
+    return 1;
+}
+
 static void update_callback(struct diff_queue_struct *q,
-			    struct diff_options *opt UNUSED, void *cbdata)
+							struct diff_options *opt UNUSED, void *cbdata)
 {
 	int i;
 	struct update_callback_data *data = cbdata;
@@ -3919,56 +3980,19 @@ static void update_callback(struct diff_queue_struct *q,
 		struct diff_filepair *p = q->queue[i];
 		const char *path = p->one->path;
 
-		if (!data->include_sparse &&
-		    !path_in_sparse_checkout(path, data->index))
+		if (!data->include_sparse && !path_in_sparse_checkout(path, data->index))
 			continue;
 
 		switch (fix_unmerged_status(p, data)) {
 		default:
 			die(_("unexpected diff status %c"), p->status);
 		case DIFF_STATUS_MODIFIED:
-		case DIFF_STATUS_TYPE_CHANGED: {
-			struct stat st;
-			if (!lstat(path, &st) && S_ISDIR(st.st_mode)) { // only consider submodule if it is a directory
-				const struct submodule *sub = submodule_from_path(data->repo, null_oid(the_hash_algo), path);
-				if (sub && sub->name && sub->ignore && !strcmp(sub->ignore, "all")) {
-					int pathspec_matches = 0;
-					char *norm_pathspec = NULL;
-					int ps_i;
-					trace_printf("ignore=all %s\n", path);
-					trace_printf("pathspec %s\n",
-							(data->pathspec && data->pathspec->nr) ? "has pathspec" : "no pathspec");
-					/* Safely scan all pathspec items (q->nr may exceed pathspec->nr). */
-					if (data->pathspec) {
-						for (ps_i = 0; ps_i < data->pathspec->nr; ps_i++) {
-							const char *m = data->pathspec->items[ps_i].match;
-							if (!m)
-								continue;
-							norm_pathspec = xstrdup(m);
-							strip_dir_trailing_slashes(norm_pathspec);
-							if (!strcmp(path, norm_pathspec)) {
-								pathspec_matches = 1;
-								FREE_AND_NULL(norm_pathspec);
-								break;
-							}
-							FREE_AND_NULL(norm_pathspec);
-						}
-					}
-					if (pathspec_matches) {
-						if (data->include_ignored_submodules && data->include_ignored_submodules > 0) {
-							trace_printf("Add ignored=all submodule due to --include_ignored_submodules: %s\n", path);
-						} else {
-							printf(_("Skipping submodule due to ignore=all: %s"), path);
-							printf(_("Use --include_ignored_submodules, if you really want to add them.") );
-							continue;
-						}
-					} else {
-						/* No explicit pathspec match -> skip silently (or with trace). */
-						trace_printf("pathspec does not match %s\n", path);
-						continue;
-					}
-				}
-			}
+		case DIFF_STATUS_TYPE_CHANGED:
+			if (should_skip_submodule_with_ignore_all(path, data->repo,
+								  data->pathspec,
+								  data->ignored_too))
+				continue;
+
 			if (add_file_to_index(data->index, path, data->flags)) {
 				if (!(data->flags & ADD_CACHE_IGNORE_ERRORS))
 					die(_("updating files failed"));