Merge branch 'jt/conditional-config-on-remote-url'

The conditional inclusion mechanism of configuration files using
"[includeIf <condition>]" learns to base its decision on the
URL of the remote repository the repository interacts with.

* jt/conditional-config-on-remote-url:
  config: include file if remote URL matches a glob
  config: make git_config_include() static

Author: gitster

Documentation/config.txt

@@ -159,6 +159,33 @@ all branches that begin with `foo/`. This is useful if your branches are
 organized hierarchically and you would like to apply a configuration to
 all the branches in that hierarchy.
 
+`hasconfig:remote.*.url:`::
+	The data that follows this keyword is taken to
+	be a pattern with standard globbing wildcards and two
+	additional ones, `**/` and `/**`, that can match multiple
+	components. The first time this keyword is seen, the rest of
+	the config files will be scanned for remote URLs (without
+	applying any values). If there exists at least one remote URL
+	that matches this pattern, the include condition is met.
++
+Files included by this option (directly or indirectly) are not allowed
+to contain remote URLs.
++
+Note that unlike other includeIf conditions, resolving this condition
+relies on information that is not yet known at the point of reading the
+condition. A typical use case is this option being present as a
+system-level or global-level config, and the remote URL being in a
+local-level config; hence the need to scan ahead when resolving this
+condition. In order to avoid the chicken-and-egg problem in which
+potentially-included files can affect whether such files are potentially
+included, Git breaks the cycle by prohibiting these files from affecting
+the resolution of these conditions (thus, prohibiting them from
+declaring remote URLs).
++
+As for the naming of this keyword, it is for forwards compatibiliy with
+a naming scheme that supports more variable-based include conditions,
+but currently Git only supports the exact keyword described above.
+
 A few more notes on matching via `gitdir` and `gitdir/i`:
 
  * Symlinks in `$GIT_DIR` are not resolved before matching.
@@ -226,6 +253,14 @@ Example
 ; currently checked out
 [includeIf "onbranch:foo-branch"]
 	path = foo.inc
+
+; include only if a remote with the given URL exists (note
+; that such a URL may be provided later in a file or in a
+; file read after this file is read, as seen in this example)
+[includeIf "hasconfig:remote.*.url:https://example.com/**"]
+	path = foo.inc
+[remote "origin"]
+	url = https://example.com/git
 ----
 
 Values

config.c

@@ -120,6 +120,22 @@ static long config_buf_ftell(struct config_source *conf)
 	return conf->u.buf.pos;
 }
 
+struct config_include_data {
+	int depth;
+	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 }
+
+static int git_config_include(const char *var, const char *value, void *data);
+
 #define MAX_INCLUDE_DEPTH 10
 static const char include_depth_advice[] = N_(
 "exceeded maximum include depth (%d) while including\n"
@@ -294,22 +310,108 @@ 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);
 	else if (skip_prefix_mem(cond, cond_len, "gitdir/i:", &cond, &cond_len))
 		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;
 }
 
-int git_config_include(const char *var, const char *value, void *data)
+static int git_config_include(const char *var, const char *value, void *data)
 {
 	struct config_include_data *inc = data;
 	const char *cond, *key;
@@ -328,9 +430,15 @@ 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;
 }
@@ -1929,11 +2037,13 @@ 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;
 	}
@@ -1946,17 +2056,23 @@ 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)

config.h

@@ -89,6 +89,15 @@ struct config_options {
 	unsigned int ignore_worktree : 1;
 	unsigned int ignore_cmdline : 1;
 	unsigned int system_gently : 1;
+
+	/*
+	 * For internal use. Include all includeif.hasremoteurl paths without
+	 * checking if the repo has that remote URL, and when doing so, verify
+	 * that files included in this way do not configure any remote URLs
+	 * themselves.
+	 */
+	unsigned int unconditional_remote_url : 1;
+
 	const char *commondir;
 	const char *git_dir;
 	config_parser_event_fn_t event_fn;
@@ -126,6 +135,8 @@ int git_default_config(const char *, const char *, void *);
 /**
  * Read a specific file in git-config format.
  * This function takes the same callback and data parameters as `git_config`.
+ *
+ * Unlike git_config(), this function does not respect includes.
  */
 int git_config_from_file(config_fn_t fn, const char *, void *);
 
@@ -158,6 +169,8 @@ void read_very_early_config(config_fn_t cb, void *data);
  * will first feed the user-wide one to the callback, and then the
  * repo-specific one; by overwriting, the higher-priority repo-specific
  * value is left at the end).
+ *
+ * Unlike git_config_from_file(), this function respects includes.
  */
 void git_config(config_fn_t fn, void *);
 
@@ -338,39 +351,6 @@ const char *current_config_origin_type(void);
 const char *current_config_name(void);
 int current_config_line(void);
 
-/**
- * Include Directives
- * ------------------
- *
- * By default, the config parser does not respect include directives.
- * However, a caller can use the special `git_config_include` wrapper
- * callback to support them. To do so, you simply wrap your "real" callback
- * function and data pointer in a `struct config_include_data`, and pass
- * the wrapper to the regular config-reading functions. For example:
- *
- * -------------------------------------------
- * int read_file_with_include(const char *file, config_fn_t fn, void *data)
- * {
- * struct config_include_data inc = CONFIG_INCLUDE_INIT;
- * inc.fn = fn;
- * inc.data = data;
- * return git_config_from_file(git_config_include, file, &inc);
- * }
- * -------------------------------------------
- *
- * `git_config` respects includes automatically. The lower-level
- * `git_config_from_file` does not.
- *
- */
-struct config_include_data {
-	int depth;
-	config_fn_t fn;
-	void *data;
-	const struct config_options *opts;
-};
-#define CONFIG_INCLUDE_INIT { 0 }
-int git_config_include(const char *name, const char *value, void *data);
-
 /*
  * Match and parse a config key of the form:
  *