scan_path(): Do not recurse into hidden directories by default

Paths that start with a period ('.') are considered hidden in the Unix world.
scan_path() should arguably not recurse into these directories by default.
This patch makes it so, and introduces the "scan-hidden-path" config variable
for overriding the new default and revert to the old behaviour (scanning _all_
directories, including hidden .directories).

Signed-off-by: Johan Herland <johan@herland.net>
Signed-off-by: Lars Hjemli <larsh@prediktor.no>

4 files changed, 14 insertions, 0 deletions

diff --git a/cgit.c b/cgit.c
index 412fbf0..6a76281 100644
--- a/cgit.c
+++ b/cgit.c
@@ -174,48 +174,50 @@ void config_cb(const char *name, const char *value)
 	else if (!strcmp(name, "embedded"))
 		ctx.cfg.embedded = atoi(value);
 	else if (!strcmp(name, "max-atom-items"))
 		ctx.cfg.max_atom_items = atoi(value);
 	else if (!strcmp(name, "max-message-length"))
 		ctx.cfg.max_msg_len = atoi(value);
 	else if (!strcmp(name, "max-repodesc-length"))
 		ctx.cfg.max_repodesc_len = atoi(value);
 	else if (!strcmp(name, "max-blob-size"))
 		ctx.cfg.max_blob_size = atoi(value);
 	else if (!strcmp(name, "max-repo-count"))
 		ctx.cfg.max_repo_count = atoi(value);
 	else if (!strcmp(name, "max-commit-count"))
 		ctx.cfg.max_commit_count = atoi(value);
 	else if (!strcmp(name, "project-list"))
 		ctx.cfg.project_list = xstrdup(expand_macros(value));
 	else if (!strcmp(name, "scan-path"))
 		if (!ctx.cfg.nocache && ctx.cfg.cache_size)
 			process_cached_repolist(expand_macros(value));
 		else if (ctx.cfg.project_list)
 			scan_projects(expand_macros(value),
 				      ctx.cfg.project_list, repo_config);
 		else
 			scan_tree(expand_macros(value), repo_config);
+	else if (!strcmp(name, "scan-hidden-path"))
+		ctx.cfg.scan_hidden_path = atoi(value);
 	else if (!strcmp(name, "section-from-path"))
 		ctx.cfg.section_from_path = atoi(value);
 	else if (!strcmp(name, "source-filter"))
 		ctx.cfg.source_filter = new_filter(value, 1);
 	else if (!strcmp(name, "summary-log"))
 		ctx.cfg.summary_log = atoi(value);
 	else if (!strcmp(name, "summary-branches"))
 		ctx.cfg.summary_branches = atoi(value);
 	else if (!strcmp(name, "summary-tags"))
 		ctx.cfg.summary_tags = atoi(value);
 	else if (!strcmp(name, "side-by-side-diffs"))
 		ctx.cfg.ssdiff = atoi(value);
 	else if (!strcmp(name, "agefile"))
 		ctx.cfg.agefile = xstrdup(value);
 	else if (!strcmp(name, "renamelimit"))
 		ctx.cfg.renamelimit = atoi(value);
 	else if (!strcmp(name, "remove-suffix"))
 		ctx.cfg.remove_suffix = atoi(value);
 	else if (!strcmp(name, "robots"))
 		ctx.cfg.robots = xstrdup(value);
 	else if (!strcmp(name, "clone-prefix"))
 		ctx.cfg.clone_prefix = xstrdup(value);
 	else if (!strcmp(name, "local-time"))
 		ctx.cfg.local_time = atoi(value);
@@ -294,48 +296,49 @@ static void prepare_context(struct cgit_context *ctx)
 	ctx->cfg.cache_repo_ttl = 5;
 	ctx->cfg.cache_root = CGIT_CACHE_ROOT;
 	ctx->cfg.cache_root_ttl = 5;
 	ctx->cfg.cache_scanrc_ttl = 15;
 	ctx->cfg.cache_static_ttl = -1;
 	ctx->cfg.css = "/cgit.css";
 	ctx->cfg.logo = "/cgit.png";
 	ctx->cfg.local_time = 0;
 	ctx->cfg.enable_gitweb_owner = 1;
 	ctx->cfg.enable_tree_linenumbers = 1;
 	ctx->cfg.max_repo_count = 50;
 	ctx->cfg.max_commit_count = 50;
 	ctx->cfg.max_lock_attempts = 5;
 	ctx->cfg.max_msg_len = 80;
 	ctx->cfg.max_repodesc_len = 80;
 	ctx->cfg.max_blob_size = 0;
 	ctx->cfg.max_stats = 0;
 	ctx->cfg.module_link = "./?repo=%s&page=commit&id=%s";
 	ctx->cfg.project_list = NULL;
 	ctx->cfg.renamelimit = -1;
 	ctx->cfg.remove_suffix = 0;
 	ctx->cfg.robots = "index, nofollow";
 	ctx->cfg.root_title = "Git repository browser";
 	ctx->cfg.root_desc = "a fast webinterface for the git dscm";
+	ctx->cfg.scan_hidden_path = 0;
 	ctx->cfg.script_name = CGIT_SCRIPT_NAME;
 	ctx->cfg.section = "";
 	ctx->cfg.summary_branches = 10;
 	ctx->cfg.summary_log = 10;
 	ctx->cfg.summary_tags = 10;
 	ctx->cfg.max_atom_items = 10;
 	ctx->cfg.ssdiff = 0;
 	ctx->env.cgit_config = xstrdupn(getenv("CGIT_CONFIG"));
 	ctx->env.http_host = xstrdupn(getenv("HTTP_HOST"));
 	ctx->env.https = xstrdupn(getenv("HTTPS"));
 	ctx->env.no_http = xstrdupn(getenv("NO_HTTP"));
 	ctx->env.path_info = xstrdupn(getenv("PATH_INFO"));
 	ctx->env.query_string = xstrdupn(getenv("QUERY_STRING"));
 	ctx->env.request_method = xstrdupn(getenv("REQUEST_METHOD"));
 	ctx->env.script_name = xstrdupn(getenv("SCRIPT_NAME"));
 	ctx->env.server_name = xstrdupn(getenv("SERVER_NAME"));
 	ctx->env.server_port = xstrdupn(getenv("SERVER_PORT"));
 	ctx->page.mimetype = "text/html";
 	ctx->page.charset = PAGE_ENCODING;
 	ctx->page.filename = NULL;
 	ctx->page.size = 0;
 	ctx->page.modified = time(NULL);
 	ctx->page.expires = ctx->page.modified;
 	ctx->page.etag = NULL;
diff --git a/cgit.h b/cgit.h
index f5f68ac..ad94905 100644
--- a/cgit.h
+++ b/cgit.h
@@ -186,48 +186,49 @@ struct cgit_config {
 	int cache_static_ttl;
 	int embedded;
 	int enable_filter_overrides;
 	int enable_gitweb_owner;
 	int enable_index_links;
 	int enable_log_filecount;
 	int enable_log_linecount;
 	int enable_remote_branches;
 	int enable_subject_links;
 	int enable_tree_linenumbers;
 	int local_time;
 	int max_atom_items;
 	int max_repo_count;
 	int max_commit_count;
 	int max_lock_attempts;
 	int max_msg_len;
 	int max_repodesc_len;
 	int max_blob_size;
 	int max_stats;
 	int nocache;
 	int noplainemail;
 	int noheader;
 	int renamelimit;
 	int remove_suffix;
+	int scan_hidden_path;
 	int section_from_path;
 	int snapshots;
 	int summary_branches;
 	int summary_log;
 	int summary_tags;
 	int ssdiff;
 	struct string_list mimetypes;
 	struct cgit_filter *about_filter;
 	struct cgit_filter *commit_filter;
 	struct cgit_filter *source_filter;
 };
 
 struct cgit_page {
 	time_t modified;
 	time_t expires;
 	size_t size;
 	char *mimetype;
 	char *charset;
 	char *filename;
 	char *etag;
 	char *title;
 	int status;
 	char *statusmsg;
 };
diff --git a/cgitrc.5.txt b/cgitrc.5.txt
index 8e51ca5..1dc3cce 100644
--- a/cgitrc.5.txt
+++ b/cgitrc.5.txt
@@ -248,48 +248,56 @@ renamelimit::
 	 "-1" uses the compiletime value in git (for further info, look at
 	  `man git-diff`). Default value: "-1".
 
 repo.group::
 	Legacy alias for "section". This option is deprecated and will not be
 	supported in cgit-1.0.
 
 robots::
 	Text used as content for the "robots" meta-tag. Default value:
 	"index, nofollow".
 
 root-desc::
 	Text printed below the heading on the repository index page. Default
 	value: "a fast webinterface for the git dscm".
 
 root-readme::
 	The content of the file specified with this option will be included
 	verbatim below the "about" link on the repository index page. Default
 	value: none.
 
 root-title::
 	Text printed as heading on the repository index page. Default value:
 	"Git Repository Browser".
 
+scan-hidden-path::
+	If set to "1" and scan-path is enabled, scan-path will recurse into
+	directories whose name starts with a period ('.'). Otherwise,
+	scan-path will stay away from such directories (considered as
+	"hidden"). Note that this does not apply to the ".git" directory in
+	non-bare repos. This must be defined prior to scan-path.
+	Default value: 0. See also: scan-path.
+
 scan-path::
 	A path which will be scanned for repositories. If caching is enabled,
 	the result will be cached as a cgitrc include-file in the cache
 	directory. If project-list has been defined prior to scan-path,
 	scan-path loads only the directories listed in the file pointed to by
 	project-list. Default value: none. See also: cache-scanrc-ttl,
 	project-list.
 
 section::
 	The name of the current repository section - all repositories defined
 	after this option will inherit the current section name. Default value:
 	none.
 
 section-from-path::
 	A number which, if specified before scan-path, specifies how many
 	path elements from each repo path to use as a default section name.
 	If negative, cgit will discard the specified number of path elements
 	above the repo directory. Default value: 0.
 
 side-by-side-diffs::
 	If set to "1" shows side-by-side diffs instead of unidiffs per
 	default. Default value: "0".
 
 snapshots::
diff --git a/scan-tree.c b/scan-tree.c
index eda8c67..627af1b 100644
--- a/scan-tree.c
+++ b/scan-tree.c
@@ -162,48 +162,50 @@ static void scan_path(const char *base, const char *path, repo_config_fn fn)
 	DIR *dir = opendir(path);
 	struct dirent *ent;
 	char *buf;
 	struct stat st;
 
 	if (!dir) {
 		fprintf(stderr, "Error opening directory %s: %s (%d)\n",
 			path, strerror(errno), errno);
 		return;
 	}
 	if (is_git_dir(path)) {
 		add_repo(base, path, fn);
 		goto end;
 	}
 	if (is_git_dir(fmt("%s/.git", path))) {
 		add_repo(base, fmt("%s/.git", path), fn);
 		goto end;
 	}
 	while((ent = readdir(dir)) != NULL) {
 		if (ent->d_name[0] == '.') {
 			if (ent->d_name[1] == '\0')
 				continue;
 			if (ent->d_name[1] == '.' && ent->d_name[2] == '\0')
 				continue;
+			if (!ctx.cfg.scan_hidden_path)
+				continue;
 		}
 		buf = malloc(strlen(path) + strlen(ent->d_name) + 2);
 		if (!buf) {
 			fprintf(stderr, "Alloc error on %s: %s (%d)\n",
 				path, strerror(errno), errno);
 			exit(1);
 		}
 		sprintf(buf, "%s/%s", path, ent->d_name);
 		if (stat(buf, &st)) {
 			fprintf(stderr, "Error checking path %s: %s (%d)\n",
 				buf, strerror(errno), errno);
 			free(buf);
 			continue;
 		}
 		if (S_ISDIR(st.st_mode))
 			scan_path(base, buf, fn);
 		free(buf);
 	}
 end:
 	closedir(dir);
 }
 
 #define lastc(s) s[strlen(s) - 1]