git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v3 2/3] config: add hashtable for config parsing & retrieval

From
Tanay Abhra <tanayabh@gmail.com>
Date
Jun 23, 2014, 10:11 UTC
Message-ID
<1403518300-23053-3-git-send-email-tanayabh@gmail.com>
In-Reply-To
<1403518300-23053-1-git-send-email-tanayabh@gmail.com>

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 hash table to cache all key-value pairs read from config files (repo specific .git/config, user wide ~/.gitconfig and the global /etc/gitconfig). Add two external functions `git_config_get_string` and `git_config_get_string_multi` for querying in a non-callback manner from the hash table. They support O(1) lookups once the hash table is constructed.

Signed-off-by: Tanay Abhra <tanayabh@gmail.com>
---
 Documentation/technical/api-config.txt |  26 ++++++
 cache.h                                |   2 +
 config.c                               | 144 +++++++++++++++++++++++++++++++++
 3 files changed, 172 insertions(+)
diff --git a/Documentation/technical/api-config.txt b/Documentation/technical/api-config.txt
index 230b3a0..13f3f40 100644
--- a/Documentation/technical/api-config.txt
+++ b/Documentation/technical/api-config.txt
@@ -77,6 +77,32 @@ To read a specific file in git-config format, use
 `git_config_from_file`. This takes the same callback and data parameters
 as `git_config`.
 
+Querying For Specific Variables
+-------------------------------
+
+For programs wanting to query for specific variables in a non-callback
+manner, the config API provides two functions `git_config_get_string`
+and `git_config_get_string_multi`.They both read values from an internal
+cache generated previously from reading the config files.
+
+`git_config_get_string` takes two parameters,
+
+- a key string in canonical flat form for which the corresponding value
+  with the highest priority (i.e. value in the repo config will be
+  preferred over value in user wide config for the same variable) will
+  be retrieved.
+
+- a pointer to a string which will point to the retrieved value.
+
+`git_config_get_string` returns 0 for success, or -1 for no value found.
+
+`git_config_get_string_multi` returns a `string_list` containing all the
+values for the key passed as parameter, sorted in order of increasing
+priority (Note: NULL values are flagged as 1, check `util` for each
+'string_list_item` for flag value).
+
+See test-config.c for usage examples.
+
 Value Parsing Helpers
 ---------------------
 
diff --git a/cache.h b/cache.h
index cbe1935..fec0a63 100644
--- a/cache.h
+++ b/cache.h
@@ -1294,6 +1294,8 @@ extern int check_repository_format_version(const char *var, const char *value, v
 extern int git_env_bool(const char *, int);
 extern int git_config_system(void);
 extern int config_error_nonbool(const char *);
+extern int git_config_get_string(const char *, const char **);
+extern const struct string_list *git_config_get_string_multi(const char *);
 #if defined(__GNUC__)
 #define config_error_nonbool(s) (config_error_nonbool(s), const_error())
 #endif
diff --git a/config.c b/config.c
index a1aef1c..6200f36 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;
@@ -37,6 +39,141 @@ static struct config_source *cf;
 
 static int zlib_compression_seen;
 
+struct config_cache_entry {
+	struct hashmap_entry ent;
+	char *key;
+	struct string_list value_list;
+};
+
+static int hashmap_initialized;
+
+static int config_cache_add_value(const char *key, const char *value);
+
+static int config_cache_entry_cmp(const struct config_cache_entry *e1,
+				 const struct config_cache_entry *e2, const void *unused)
+{
+	return strcmp(e1->key, e2->key);
+}
+
+static void config_cache_init(struct hashmap *config_cache)
+{
+	hashmap_init(config_cache, (hashmap_cmp_fn)config_cache_entry_cmp, 0);
+}
+
+static int config_cache_callback(const char *key, const char *value, void *unused)
+{
+	config_cache_add_value(key, value);
+	return 0;
+}
+
+static struct hashmap *get_config_cache(void)
+{
+	static struct hashmap config_cache;
+	if (!hashmap_initialized) {
+		config_cache_init(&config_cache);
+		hashmap_initialized = 1;
+		git_config(config_cache_callback, NULL);
+	}
+	return &config_cache;
+}
+
+static void config_cache_free(void)
+{
+	struct hashmap *config_cache;
+	struct config_cache_entry *entry;
+	struct hashmap_iter iter;
+	config_cache = get_config_cache();
+	hashmap_iter_init(config_cache, &iter);
+	while ((entry = hashmap_iter_next(&iter))) {
+		free(entry->key);
+		string_list_clear(&entry->value_list, 1);
+	}
+	hashmap_free(config_cache, 1);
+	hashmap_initialized = 0;
+}
+
+static struct config_cache_entry *config_cache_find_entry(const char *key)
+{
+	struct hashmap *config_cache;
+	struct config_cache_entry k;
+	struct config_cache_entry *found_entry;
+	char *normalized_key;
+	int ret;
+	config_cache = get_config_cache();
+	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(config_cache, &k, NULL);
+	free(normalized_key);
+	return found_entry;
+}
+
+static struct string_list *config_cache_get_value(const char *key)
+{
+	struct config_cache_entry *e = config_cache_find_entry(key);
+	return e ? &e->value_list : NULL;
+}
+
+static int config_cache_add_value(const char *key, const char *value)
+{
+	struct hashmap *config_cache;
+	struct config_cache_entry *e;
+	struct string_list_item *item;
+	int *boolean_null_flag;
+
+	config_cache = get_config_cache();
+	e = config_cache_find_entry(key);
+
+	boolean_null_flag = xcalloc(1, sizeof(*boolean_null_flag));
+
+	if (!e) {
+		e = xmalloc(sizeof(*e));
+		hashmap_entry_init(e, strhash(key));
+		e->key = xstrdup(key);
+		string_list_init_dup(&e->value_list);
+		hashmap_add(config_cache, e);
+	}
+	/*
+	 * If the variable had no value specified, the value will be NULL
+	 * (typically this means it should be interpreted as boolean true).
+	 * For such values, silently convert them to "BOOLEAN_NULL" to
+	 * store in hashmap and flag that string_list_item as 1.
+	 */
+	if (value == NULL) {
+		value = "BOOLEAN_NULL";
+		*boolean_null_flag = 1;
+	}
+	item = string_list_append(&e->value_list, value);
+	item->util = boolean_null_flag;
+
+	return 0;
+}
+
+int git_config_get_string(const char *key, const char **value)
+{
+	struct string_list *values;
+	int *flag;
+	values = config_cache_get_value(key);
+	if (!values)
+		return -1;
+	assert(values->nr > 0);
+	*value = values->items[values->nr - 1].string;
+	flag = values->items[values->nr - 1].util;
+	if (*flag)
+		*value = NULL;
+	return 0;
+}
+
+/* for NULL values, 'util' for each `string_list_item` is flagged as 1 */
+const struct string_list *git_config_get_string_multi(const char *key)
+{
+	return config_cache_get_value(key);
+}
+
 static int config_file_fgetc(struct config_source *conf)
 {
 	return fgetc(conf->u.file);
@@ -1708,6 +1845,13 @@ int git_config_set_multivar_in_file(const char *config_filename,
 	lock = NULL;
 	ret = 0;
 
+	/*
+	 * content of config file has changed, so invalidate the
+	 * config cache used by non-callback based query functions.
+	 */
+	if (hashmap_initialized)
+		config_cache_free();
+
 out_free:
 	if (lock)
 		rollback_lock_file(lock);
-- 
1.9.0.GIT
Previous: Tanay AbhraNext: Matthieu Moy
Message 5 of 35 in “git config cache & special querying api utilizing the cache”
  1. 0/3 git config cache & special querying api utilizing the cacheTanay Abhra, Jun 23, 2014
  2. 1/3 string-list: add string_list initialiser helper functionsTanay Abhra, Jun 23, 2014
  3. Torsten BögershausenJun 23, 2014
  4. Tanay AbhraJun 23, 2014
  5. 2/3 config: add hashtable for config parsing & retrievalTanay Abhra, Jun 23, 2014
  6. Matthieu MoyJun 23, 2014
  7. Tanay AbhraJun 24, 2014
  8. Karsten BleesJun 25, 2014
  9. Ramsay JonesJun 23, 2014
  10. Tanay AbhraJun 23, 2014
  11. Ramsay JonesJun 24, 2014
  12. Matthieu MoyJun 26, 2014
  13. Junio C HamanoJun 23, 2014
  14. Tanay AbhraJun 24, 2014
  15. Junio C HamanoJun 25, 2014
  16. Tanay AbhraJun 24, 2014
  17. Ramsay JonesJun 24, 2014
  18. Junio C HamanoJun 25, 2014
  19. Karsten BleesJun 25, 2014
  20. Junio C HamanoJun 25, 2014
  21. Matthieu MoyJun 26, 2014
  22. Junio C HamanoJun 26, 2014
  23. Karsten BleesJun 26, 2014
  24. Junio C HamanoJun 26, 2014
  25. Karsten BleesJun 27, 2014
  26. Matthieu MoyJun 27, 2014
  27. Junio C HamanoJun 27, 2014
  28. Junio C HamanoJun 23, 2014
  29. Tanay AbhraJun 24, 2014
  30. Matthieu MoyJun 26, 2014
  31. Karsten BleesJun 25, 2014
  32. Matthieu MoyJun 26, 2014
  33. 3/3 test-config: add usage examples for non-callback query functionsTanay Abhra, Jun 23, 2014
  34. Eric SunshineJun 25, 2014
  35. Tanay AbhraJun 26, 2014

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.