builtin-add: simplify (and increase accuracy of) exclude handling

Previously, the code would always set up the excludes, and then manually
pick through the pathspec we were given, assuming that non-added but
existing paths were just ignored. This was mostly correct, but would
erroneously mark a totally empty directory as 'ignored'.

Instead, we now use the collect_ignored option of dir_struct, which
unambiguously tells us whether a path was ignored. This simplifies the
code, and means empty directories are now just not mentioned at all.

Furthermore, we now conditionally ask dir_struct to respect excludes,
depending on whether the '-f' flag has been set. This means we don't have
to pick through the result, checking for an 'ignored' flag; ignored entries
were either added or not in the first place.

We can safely get rid of the special 'ignored' flags to dir_entry, which
were not used anywhere else.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Jonas Fonseca <fonseca@diku.dk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin-add.c

@@ -40,42 +40,29 @@ static void prune_directory(struct dir_struct *dir, const char **pathspec, int p
 	dir->nr = dst - dir->entries;
 
 	for (i = 0; i < specs; i++) {
-		struct stat st;
-		const char *match;
-		if (seen[i])
-			continue;
-
-		match = pathspec[i];
-		if (!match[0])
-			continue;
-
-		/* Existing file? We must have ignored it */
-		if (!lstat(match, &st)) {
-			struct dir_entry *ent;
-
-			ent = dir_add_name(dir, match, strlen(match));
-			ent->ignored = 1;
-			if (S_ISDIR(st.st_mode))
-				ent->ignored_dir = 1;
-			continue;
-		}
-		die("pathspec '%s' did not match any files", match);
+		if (!seen[i] && !file_exists(pathspec[i]))
+			die("pathspec '%s' did not match any files",
+					pathspec[i]);
 	}
 }
 
-static void fill_directory(struct dir_struct *dir, const char **pathspec)
+static void fill_directory(struct dir_struct *dir, const char **pathspec,
+		int ignored_too)
 {
 	const char *path, *base;
 	int baselen;
 
 	/* Set up the default git porcelain excludes */
 	memset(dir, 0, sizeof(*dir));
-	dir->exclude_per_dir = ".gitignore";
-	path = git_path("info/exclude");
-	if (!access(path, R_OK))
-		add_excludes_from_file(dir, path);
-	if (!access(excludes_file, R_OK))
-		add_excludes_from_file(dir, excludes_file);
+	if (!ignored_too) {
+		dir->collect_ignored = 1;
+		dir->exclude_per_dir = ".gitignore";
+		path = git_path("info/exclude");
+		if (!access(path, R_OK))
+			add_excludes_from_file(dir, path);
+		if (!access(excludes_file, R_OK))
+			add_excludes_from_file(dir, excludes_file);
+	}
 
 	/*
 	 * Calculate common prefix for the pathspec, and
@@ -219,13 +206,11 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 	}
 	pathspec = get_pathspec(prefix, argv + i);
 
-	fill_directory(&dir, pathspec);
+	fill_directory(&dir, pathspec, ignored_too);
 
 	if (show_only) {
 		const char *sep = "", *eof = "";
 		for (i = 0; i < dir.nr; i++) {
-			if (!ignored_too && dir.entries[i]->ignored)
-				continue;
 			printf("%s%s", sep, dir.entries[i]->name);
 			sep = " ";
 			eof = "\n";
@@ -237,25 +222,13 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 	if (read_cache() < 0)
 		die("index file corrupt");
 
-	if (!ignored_too) {
-		int has_ignored = 0;
-		for (i = 0; i < dir.nr; i++)
-			if (dir.entries[i]->ignored)
-				has_ignored = 1;
-		if (has_ignored) {
-			fprintf(stderr, ignore_warning);
-			for (i = 0; i < dir.nr; i++) {
-				if (!dir.entries[i]->ignored)
-					continue;
-				fprintf(stderr, "%s", dir.entries[i]->name);
-				if (dir.entries[i]->ignored_dir)
-					fprintf(stderr, " (directory)");
-				fputc('\n', stderr);
-			}
-			fprintf(stderr,
-				"Use -f if you really want to add them.\n");
-			exit(1);
+	if (dir.ignored_nr) {
+		fprintf(stderr, ignore_warning);
+		for (i = 0; i < dir.ignored_nr; i++) {
+			fprintf(stderr, "%s\n", dir.ignored[i]->name);
 		}
+		fprintf(stderr, "Use -f if you really want to add them.\n");
+		exit(1);
 	}
 
 	for (i = 0; i < dir.nr; i++)

dir.c

@@ -275,7 +275,6 @@ static struct dir_entry *dir_entry_new(const char *pathname, int len) {
 	struct dir_entry *ent;
 
 	ent = xmalloc(sizeof(*ent) + len + 1);
-	ent->ignored = ent->ignored_dir = 0;
 	ent->len = len;
 	memcpy(ent->name, pathname, len);
 	ent->name[len] = 0;
@@ -432,6 +431,18 @@ static int simplify_away(const char *path, int pathlen, const struct path_simpli
 	return 0;
 }
 
+static int in_pathspec(const char *path, int len, const struct path_simplify *simplify)
+{
+	if (simplify) {
+		for (; simplify->path; simplify++) {
+			if (len == simplify->len
+			    && !memcmp(path, simplify->path, len))
+				return 1;
+		}
+	}
+	return 0;
+}
+
 /*
  * Read a directory tree. We currently ignore anything but
  * directories, regular files and symlinks. That's because git
@@ -472,7 +483,8 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
 				continue;
 
 			exclude = excluded(dir, fullname);
-			if (exclude && dir->collect_ignored)
+			if (exclude && dir->collect_ignored
+			    && in_pathspec(fullname, baselen + len, simplify))
 				dir_add_ignored(dir, fullname, baselen + len);
 			if (exclude != dir->show_ignored) {
 				if (!dir->show_ignored || DTYPE(de) != DT_DIR) {

dir.h

@@ -13,9 +13,7 @@
 
 
 struct dir_entry {
-	unsigned int ignored : 1;
-	unsigned int ignored_dir : 1;
-	unsigned int len : 30;
+	unsigned int len;
 	char name[FLEX_ARRAY]; /* more */
 };