add `config_set` API for caching config-like files

Currently `git_config()` uses a callback mechanism and file rereads for
config values. Due to this approach, it is not uncommon for the config
files to be parsed several times during the run of a git program, with
different callbacks picking out different variables useful to themselves.

Add a `config_set`, that can be used to construct an in-memory cache for
config-like files that the caller specifies (i.e., files like `.gitmodules`,
`~/.gitconfig` etc.). Add two external functions `git_configset_get_value`
and `git_configset_get_value_multi` for querying from the config sets.
`git_configset_get_value` follows `last one wins` semantic (i.e. if there
are multiple matches for the queried key in the files of the configset the
value returned will be the last entry in `value_list`).
`git_configset_get_value_multi` returns a list of values sorted in order of
increasing priority (i.e. last match will be at the end of the list). Add
type specific query functions like `git_configset_get_bool` and similar.

Add a default `config_set`, `the_config_set` to cache all key-value pairs
read from usual config files (repo specific .git/config, user wide
~/.gitconfig, XDG config and the global /etc/gitconfig). `the_config_set`
is populated using `git_config()`.

Add two external functions `git_config_get_value` and
`git_config_get_value_multi` for querying in a non-callback manner from
`the_config_set`. Also, add type specific query functions that are
implemented as a thin wrapper around the `config_set` API.

Signed-off-by: Matthieu Moy <Matthieu.Moy@imag.fr>
Signed-off-by: Tanay Abhra <tanayabh@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 274 insertions, 0 deletions

diff --git a/config.c b/config.c
index 9767c4bad0..d3ad661fca 100644
--- a/config.c
+++ b/config.c
@@ -9,6 +9,8 @@
 #include "exec_cmd.h"
 #include "strbuf.h"
 #include "quote.h"
+#include "hashmap.h"
+#include "string-list.h"
 
 struct config_source {
 	struct config_source *prev;
@@ -33,10 +35,23 @@ struct config_source {
 	long (*do_ftell)(struct config_source *c);
 };
 
+struct config_set_element {
+	struct hashmap_entry ent;
+	char *key;
+	struct string_list value_list;
+};
+
 static struct config_source *cf;
 
 static int zlib_compression_seen;
 
+/*
+ * Default config_set that contains key-value pairs from the usual set of config
+ * config files (i.e repo specific .git/config, user wide ~/.gitconfig, XDG
+ * config file and the global /etc/gitconfig)
+ */
+static struct config_set the_config_set;
+
 static int config_file_fgetc(struct config_source *conf)
 {
 	return fgetc(conf->u.file);
@@ -1212,6 +1227,262 @@ int git_config(config_fn_t fn, void *data)
 	return git_config_with_options(fn, data, NULL, 1);
 }
 
+static struct config_set_element *configset_find_element(struct config_set *cs, const char *key)
+{
+	struct config_set_element k;
+	struct config_set_element *found_entry;
+	char *normalized_key;
+	int ret;
+	/*
+	 * `key` may come from the user, so normalize it before using it
+	 * for querying entries from the hashmap.
+	 */
+	ret = git_config_parse_key(key, &normalized_key, NULL);
+
+	if (ret)
+		return NULL;
+
+	hashmap_entry_init(&k, strhash(normalized_key));
+	k.key = normalized_key;
+	found_entry = hashmap_get(&cs->config_hash, &k, NULL);
+	free(normalized_key);
+	return found_entry;
+}
+
+static int configset_add_value(struct config_set *cs, const char *key, const char *value)
+{
+	struct config_set_element *e;
+	e = configset_find_element(cs, key);
+	/*
+	 * Since the keys are being fed by git_config*() callback mechanism, they
+	 * are already normalized. So simply add them without any further munging.
+	 */
+	if (!e) {
+		e = xmalloc(sizeof(*e));
+		hashmap_entry_init(e, strhash(key));
+		e->key = xstrdup(key);
+		string_list_init(&e->value_list, 1);
+		hashmap_add(&cs->config_hash, e);
+	}
+	string_list_append_nodup(&e->value_list, value ? xstrdup(value) : NULL);
+
+	return 0;
+}
+
+static int config_set_element_cmp(const struct config_set_element *e1,
+				 const struct config_set_element *e2, const void *unused)
+{
+	return strcmp(e1->key, e2->key);
+}
+
+void git_configset_init(struct config_set *cs)
+{
+	hashmap_init(&cs->config_hash, (hashmap_cmp_fn)config_set_element_cmp, 0);
+	cs->hash_initialized = 1;
+}
+
+void git_configset_clear(struct config_set *cs)
+{
+	struct config_set_element *entry;
+	struct hashmap_iter iter;
+	if (!cs->hash_initialized)
+		return;
+
+	hashmap_iter_init(&cs->config_hash, &iter);
+	while ((entry = hashmap_iter_next(&iter))) {
+		free(entry->key);
+		string_list_clear(&entry->value_list, 0);
+	}
+	hashmap_free(&cs->config_hash, 1);
+	cs->hash_initialized = 0;
+}
+
+static int config_set_callback(const char *key, const char *value, void *cb)
+{
+	struct config_set *cs = cb;
+	configset_add_value(cs, key, value);
+	return 0;
+}
+
+int git_configset_add_file(struct config_set *cs, const char *filename)
+{
+	return git_config_from_file(config_set_callback, filename, cs);
+}
+
+int git_configset_get_value(struct config_set *cs, const char *key, const char **value)
+{
+	const struct string_list *values = NULL;
+	/*
+	 * Follows "last one wins" semantic, i.e., if there are multiple matches for the
+	 * queried key in the files of the configset, the value returned will be the last
+	 * value in the value list for that key.
+	 */
+	values = git_configset_get_value_multi(cs, key);
+
+	if (!values)
+		return 1;
+	assert(values->nr > 0);
+	*value = values->items[values->nr - 1].string;
+	return 0;
+}
+
+const struct string_list *git_configset_get_value_multi(struct config_set *cs, const char *key)
+{
+	struct config_set_element *e = configset_find_element(cs, key);
+	return e ? &e->value_list : NULL;
+}
+
+int git_configset_get_string_const(struct config_set *cs, const char *key, const char **dest)
+{
+	const char *value;
+	if (!git_configset_get_value(cs, key, &value))
+		return git_config_string(dest, key, value);
+	else
+		return 1;
+}
+
+int git_configset_get_string(struct config_set *cs, const char *key, char **dest)
+{
+	return git_configset_get_string_const(cs, key, (const char **)dest);
+}
+
+int git_configset_get_int(struct config_set *cs, const char *key, int *dest)
+{
+	const char *value;
+	if (!git_configset_get_value(cs, key, &value)) {
+		*dest = git_config_int(key, value);
+		return 0;
+	} else
+		return 1;
+}
+
+int git_configset_get_ulong(struct config_set *cs, const char *key, unsigned long *dest)
+{
+	const char *value;
+	if (!git_configset_get_value(cs, key, &value)) {
+		*dest = git_config_ulong(key, value);
+		return 0;
+	} else
+		return 1;
+}
+
+int git_configset_get_bool(struct config_set *cs, const char *key, int *dest)
+{
+	const char *value;
+	if (!git_configset_get_value(cs, key, &value)) {
+		*dest = git_config_bool(key, value);
+		return 0;
+	} else
+		return 1;
+}
+
+int git_configset_get_bool_or_int(struct config_set *cs, const char *key,
+				int *is_bool, int *dest)
+{
+	const char *value;
+	if (!git_configset_get_value(cs, key, &value)) {
+		*dest = git_config_bool_or_int(key, value, is_bool);
+		return 0;
+	} else
+		return 1;
+}
+
+int git_configset_get_maybe_bool(struct config_set *cs, const char *key, int *dest)
+{
+	const char *value;
+	if (!git_configset_get_value(cs, key, &value)) {
+		*dest = git_config_maybe_bool(key, value);
+		if (*dest == -1)
+			return -1;
+		return 0;
+	} else
+		return 1;
+}
+
+int git_configset_get_pathname(struct config_set *cs, const char *key, const char **dest)
+{
+	const char *value;
+	if (!git_configset_get_value(cs, key, &value))
+		return git_config_pathname(dest, key, value);
+	else
+		return 1;
+}
+
+static void git_config_check_init(void)
+{
+	if (the_config_set.hash_initialized)
+		return;
+	git_configset_init(&the_config_set);
+	git_config(config_set_callback, &the_config_set);
+}
+
+void git_config_clear(void)
+{
+	if (!the_config_set.hash_initialized)
+		return;
+	git_configset_clear(&the_config_set);
+}
+
+int git_config_get_value(const char *key, const char **value)
+{
+	git_config_check_init();
+	return git_configset_get_value(&the_config_set, key, value);
+}
+
+const struct string_list *git_config_get_value_multi(const char *key)
+{
+	git_config_check_init();
+	return git_configset_get_value_multi(&the_config_set, key);
+}
+
+int git_config_get_string_const(const char *key, const char **dest)
+{
+	git_config_check_init();
+	return git_configset_get_string_const(&the_config_set, key, dest);
+}
+
+int git_config_get_string(const char *key, char **dest)
+{
+	git_config_check_init();
+	return git_config_get_string_const(key, (const char **)dest);
+}
+
+int git_config_get_int(const char *key, int *dest)
+{
+	git_config_check_init();
+	return git_configset_get_int(&the_config_set, key, dest);
+}
+
+int git_config_get_ulong(const char *key, unsigned long *dest)
+{
+	git_config_check_init();
+	return git_configset_get_ulong(&the_config_set, key, dest);
+}
+
+int git_config_get_bool(const char *key, int *dest)
+{
+	git_config_check_init();
+	return git_configset_get_bool(&the_config_set, key, dest);
+}
+
+int git_config_get_bool_or_int(const char *key, int *is_bool, int *dest)
+{
+	git_config_check_init();
+	return git_configset_get_bool_or_int(&the_config_set, key, is_bool, dest);
+}
+
+int git_config_get_maybe_bool(const char *key, int *dest)
+{
+	git_config_check_init();
+	return git_configset_get_maybe_bool(&the_config_set, key, dest);
+}
+
+int git_config_get_pathname(const char *key, const char **dest)
+{
+	git_config_check_init();
+	return git_configset_get_pathname(&the_config_set, key, dest);
+}
+
 /*
  * Find all the stuff for git_config_set() below.
  */
@@ -1707,6 +1978,9 @@ int git_config_set_multivar_in_file(const char *config_filename,
 	lock = NULL;
 	ret = 0;
 
+	/* Invalidate the config cache */
+	git_config_clear();
+
 out_free:
 	if (lock)
 		rollback_lock_file(lock);