config: include file if remote URL matches a glob

This is a feature that supports config file inclusion conditional on
whether the repo has a remote with a URL that matches a glob.

Similar to my previous work on remote-suggested hooks [1], the main
motivation is to allow remote repo administrators to provide recommended
configs in a way that can be consumed more easily (e.g. through a
package installable by a package manager - it could, for example,
contain a file to be included conditionally and a post-install script
that adds the include directive to the system-wide config file).

In order to do this, Git reruns the config parsing mechanism upon
noticing the first URL-conditional include in order to find all remote
URLs, and these remote URLs are then used to determine if that first and
all subsequent includes are executed. Remote URLs are not allowed to be
configued in any URL-conditionally-included file.

[1] https://lore.kernel.org/git/cover.1623881977.git.jonathantanmy@google.com/

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Acked-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 113 insertions, 7 deletions

diff --git a/config.c b/config.c
index b700b71d0c..d98e6c9dc0 100644
--- a/config.c
+++ b/config.c
@@ -125,6 +125,12 @@ struct config_include_data {
 	config_fn_t fn;
 	void *data;
 	const struct config_options *opts;
+	struct git_config_source *config_source;
+
+	/*
+	 * All remote URLs discovered when reading all config files.
+	 */
+	struct string_list *remote_urls;
 };
 #define CONFIG_INCLUDE_INIT { 0 }
 
@@ -304,9 +310,92 @@ static int include_by_branch(const char *cond, size_t cond_len)
 	return ret;
 }
 
-static int include_condition_is_true(const struct config_options *opts,
+static int add_remote_url(const char *var, const char *value, void *data)
+{
+	struct string_list *remote_urls = data;
+	const char *remote_name;
+	size_t remote_name_len;
+	const char *key;
+
+	if (!parse_config_key(var, "remote", &remote_name, &remote_name_len,
+			      &key) &&
+	    remote_name &&
+	    !strcmp(key, "url"))
+		string_list_append(remote_urls, value);
+	return 0;
+}
+
+static void populate_remote_urls(struct config_include_data *inc)
+{
+	struct config_options opts;
+
+	struct config_source *store_cf = cf;
+	struct key_value_info *store_kvi = current_config_kvi;
+	enum config_scope store_scope = current_parsing_scope;
+
+	opts = *inc->opts;
+	opts.unconditional_remote_url = 1;
+
+	cf = NULL;
+	current_config_kvi = NULL;
+	current_parsing_scope = 0;
+
+	inc->remote_urls = xmalloc(sizeof(*inc->remote_urls));
+	string_list_init_dup(inc->remote_urls);
+	config_with_options(add_remote_url, inc->remote_urls, inc->config_source, &opts);
+
+	cf = store_cf;
+	current_config_kvi = store_kvi;
+	current_parsing_scope = store_scope;
+}
+
+static int forbid_remote_url(const char *var, const char *value, void *data)
+{
+	const char *remote_name;
+	size_t remote_name_len;
+	const char *key;
+
+	if (!parse_config_key(var, "remote", &remote_name, &remote_name_len,
+			      &key) &&
+	    remote_name &&
+	    !strcmp(key, "url"))
+		die(_("remote URLs cannot be configured in file directly or indirectly included by includeIf.hasconfig:remote.*.url"));
+	return 0;
+}
+
+static int at_least_one_url_matches_glob(const char *glob, int glob_len,
+					 struct string_list *remote_urls)
+{
+	struct strbuf pattern = STRBUF_INIT;
+	struct string_list_item *url_item;
+	int found = 0;
+
+	strbuf_add(&pattern, glob, glob_len);
+	for_each_string_list_item(url_item, remote_urls) {
+		if (!wildmatch(pattern.buf, url_item->string, WM_PATHNAME)) {
+			found = 1;
+			break;
+		}
+	}
+	strbuf_release(&pattern);
+	return found;
+}
+
+static int include_by_remote_url(struct config_include_data *inc,
+		const char *cond, size_t cond_len)
+{
+	if (inc->opts->unconditional_remote_url)
+		return 1;
+	if (!inc->remote_urls)
+		populate_remote_urls(inc);
+	return at_least_one_url_matches_glob(cond, cond_len,
+					     inc->remote_urls);
+}
+
+static int include_condition_is_true(struct config_include_data *inc,
 				     const char *cond, size_t cond_len)
 {
+	const struct config_options *opts = inc->opts;
 
 	if (skip_prefix_mem(cond, cond_len, "gitdir:", &cond, &cond_len))
 		return include_by_gitdir(opts, cond, cond_len, 0);
@@ -314,6 +403,9 @@ static int include_condition_is_true(const struct config_options *opts,
 		return include_by_gitdir(opts, cond, cond_len, 1);
 	else if (skip_prefix_mem(cond, cond_len, "onbranch:", &cond, &cond_len))
 		return include_by_branch(cond, cond_len);
+	else if (skip_prefix_mem(cond, cond_len, "hasconfig:remote.*.url:", &cond,
+				   &cond_len))
+		return include_by_remote_url(inc, cond, cond_len);
 
 	/* unknown conditionals are always false */
 	return 0;
@@ -338,9 +430,15 @@ static int git_config_include(const char *var, const char *value, void *data)
 		ret = handle_path_include(value, inc);
 
 	if (!parse_config_key(var, "includeif", &cond, &cond_len, &key) &&
-	    (cond && include_condition_is_true(inc->opts, cond, cond_len)) &&
-	    !strcmp(key, "path"))
+	    cond && include_condition_is_true(inc, cond, cond_len) &&
+	    !strcmp(key, "path")) {
+		config_fn_t old_fn = inc->fn;
+
+		if (inc->opts->unconditional_remote_url)
+			inc->fn = forbid_remote_url;
 		ret = handle_path_include(value, inc);
+		inc->fn = old_fn;
+	}
 
 	return ret;
 }
@@ -1936,11 +2034,13 @@ int config_with_options(config_fn_t fn, void *data,
 			const struct config_options *opts)
 {
 	struct config_include_data inc = CONFIG_INCLUDE_INIT;
+	int ret;
 
 	if (opts->respect_includes) {
 		inc.fn = fn;
 		inc.data = data;
 		inc.opts = opts;
+		inc.config_source = config_source;
 		fn = git_config_include;
 		data = &inc;
 	}
@@ -1953,17 +2053,23 @@ int config_with_options(config_fn_t fn, void *data,
 	 * regular lookup sequence.
 	 */
 	if (config_source && config_source->use_stdin) {
-		return git_config_from_stdin(fn, data);
+		ret = git_config_from_stdin(fn, data);
 	} else if (config_source && config_source->file) {
-		return git_config_from_file(fn, config_source->file, data);
+		ret = git_config_from_file(fn, config_source->file, data);
 	} else if (config_source && config_source->blob) {
 		struct repository *repo = config_source->repo ?
 			config_source->repo : the_repository;
-		return git_config_from_blob_ref(fn, repo, config_source->blob,
+		ret = git_config_from_blob_ref(fn, repo, config_source->blob,
 						data);
+	} else {
+		ret = do_git_config_sequence(opts, fn, data);
 	}
 
-	return do_git_config_sequence(opts, fn, data);
+	if (inc.remote_urls) {
+		string_list_clear(inc.remote_urls, 0);
+		FREE_AND_NULL(inc.remote_urls);
+	}
+	return ret;
 }
 
 static void configset_iter(struct config_set *cs, config_fn_t fn, void *data)