diff options
Diffstat (limited to 'Documentation/technical/api-hashmap.txt')
-rw-r--r-- | Documentation/technical/api-hashmap.txt | 309 |
1 files changed, 309 insertions, 0 deletions
diff --git a/Documentation/technical/api-hashmap.txt b/Documentation/technical/api-hashmap.txt new file mode 100644 index 0000000000..ccc634bbd7 --- /dev/null +++ b/Documentation/technical/api-hashmap.txt @@ -0,0 +1,309 @@ +hashmap API +=========== + +The hashmap API is a generic implementation of hash-based key-value mappings. + +Data Structures +--------------- + +`struct hashmap`:: + + The hash table structure. Members can be used as follows, but should + not be modified directly: ++ +The `size` member keeps track of the total number of entries (0 means the +hashmap is empty). ++ +`tablesize` is the allocated size of the hash table. A non-0 value indicates +that the hashmap is initialized. It may also be useful for statistical purposes +(i.e. `size / tablesize` is the current load factor). ++ +`cmpfn` stores the comparison function specified in `hashmap_init()`. In +advanced scenarios, it may be useful to change this, e.g. to switch between +case-sensitive and case-insensitive lookup. ++ +When `disallow_rehash` is set, automatic rehashes are prevented during inserts +and deletes. + +`struct hashmap_entry`:: + + An opaque structure representing an entry in the hash table, which must + be used as first member of user data structures. Ideally it should be + followed by an int-sized member to prevent unused memory on 64-bit + systems due to alignment. ++ +The `hash` member is the entry's hash code and the `next` member points to the +next entry in case of collisions (i.e. if multiple entries map to the same +bucket). + +`struct hashmap_iter`:: + + An iterator structure, to be used with hashmap_iter_* functions. + +Types +----- + +`int (*hashmap_cmp_fn)(const void *entry, const void *entry_or_key, const void *keydata)`:: + + User-supplied function to test two hashmap entries for equality. Shall + return 0 if the entries are equal. ++ +This function is always called with non-NULL `entry` / `entry_or_key` +parameters that have the same hash code. When looking up an entry, the `key` +and `keydata` parameters to hashmap_get and hashmap_remove are always passed +as second and third argument, respectively. Otherwise, `keydata` is NULL. + +Functions +--------- + +`unsigned int strhash(const char *buf)`:: +`unsigned int strihash(const char *buf)`:: +`unsigned int memhash(const void *buf, size_t len)`:: +`unsigned int memihash(const void *buf, size_t len)`:: +`unsigned int memihash_cont(unsigned int hash_seed, const void *buf, size_t len)`:: + + Ready-to-use hash functions for strings, using the FNV-1 algorithm (see + http://www.isthe.com/chongo/tech/comp/fnv). ++ +`strhash` and `strihash` take 0-terminated strings, while `memhash` and +`memihash` operate on arbitrary-length memory. ++ +`strihash` and `memihash` are case insensitive versions. ++ +`memihash_cont` is a variant of `memihash` that allows a computation to be +continued with another chunk of data. + +`unsigned int sha1hash(const unsigned char *sha1)`:: + + Converts a cryptographic hash (e.g. SHA-1) into an int-sized hash code + for use in hash tables. Cryptographic hashes are supposed to have + uniform distribution, so in contrast to `memhash()`, this just copies + the first `sizeof(int)` bytes without shuffling any bits. Note that + the results will be different on big-endian and little-endian + platforms, so they should not be stored or transferred over the net. + +`void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, size_t initial_size)`:: + + Initializes a hashmap structure. ++ +`map` is the hashmap to initialize. ++ +The `equals_function` can be specified to compare two entries for equality. +If NULL, entries are considered equal if their hash codes are equal. ++ +If the total number of entries is known in advance, the `initial_size` +parameter may be used to preallocate a sufficiently large table and thus +prevent expensive resizing. If 0, the table is dynamically resized. + +`void hashmap_free(struct hashmap *map, int free_entries)`:: + + Frees a hashmap structure and allocated memory. ++ +`map` is the hashmap to free. ++ +If `free_entries` is true, each hashmap_entry in the map is freed as well +(using stdlib's free()). + +`void hashmap_entry_init(void *entry, unsigned int hash)`:: + + Initializes a hashmap_entry structure. ++ +`entry` points to the entry to initialize. ++ +`hash` is the hash code of the entry. ++ +The hashmap_entry structure does not hold references to external resources, +and it is safe to just discard it once you are done with it (i.e. if +your structure was allocated with xmalloc(), you can just free(3) it, +and if it is on stack, you can just let it go out of scope). + +`void *hashmap_get(const struct hashmap *map, const void *key, const void *keydata)`:: + + Returns the hashmap entry for the specified key, or NULL if not found. ++ +`map` is the hashmap structure. ++ +`key` is a hashmap_entry structure (or user data structure that starts with +hashmap_entry) that has at least been initialized with the proper hash code +(via `hashmap_entry_init`). ++ +If an entry with matching hash code is found, `key` and `keydata` are passed +to `hashmap_cmp_fn` to decide whether the entry matches the key. + +`void *hashmap_get_from_hash(const struct hashmap *map, unsigned int hash, const void *keydata)`:: + + Returns the hashmap entry for the specified hash code and key data, + or NULL if not found. ++ +`map` is the hashmap structure. ++ +`hash` is the hash code of the entry to look up. ++ +If an entry with matching hash code is found, `keydata` is passed to +`hashmap_cmp_fn` to decide whether the entry matches the key. The +`entry_or_key` parameter points to a bogus hashmap_entry structure that +should not be used in the comparison. + +`void *hashmap_get_next(const struct hashmap *map, const void *entry)`:: + + Returns the next equal hashmap entry, or NULL if not found. This can be + used to iterate over duplicate entries (see `hashmap_add`). ++ +`map` is the hashmap structure. ++ +`entry` is the hashmap_entry to start the search from, obtained via a previous +call to `hashmap_get` or `hashmap_get_next`. + +`void hashmap_add(struct hashmap *map, void *entry)`:: + + Adds a hashmap entry. This allows to add duplicate entries (i.e. + separate values with the same key according to hashmap_cmp_fn). ++ +`map` is the hashmap structure. ++ +`entry` is the entry to add. + +`void *hashmap_put(struct hashmap *map, void *entry)`:: + + Adds or replaces a hashmap entry. If the hashmap contains duplicate + entries equal to the specified entry, only one of them will be replaced. ++ +`map` is the hashmap structure. ++ +`entry` is the entry to add or replace. ++ +Returns the replaced entry, or NULL if not found (i.e. the entry was added). + +`void *hashmap_remove(struct hashmap *map, const void *key, const void *keydata)`:: + + Removes a hashmap entry matching the specified key. If the hashmap + contains duplicate entries equal to the specified key, only one of + them will be removed. ++ +`map` is the hashmap structure. ++ +`key` is a hashmap_entry structure (or user data structure that starts with +hashmap_entry) that has at least been initialized with the proper hash code +(via `hashmap_entry_init`). ++ +If an entry with matching hash code is found, `key` and `keydata` are +passed to `hashmap_cmp_fn` to decide whether the entry matches the key. ++ +Returns the removed entry, or NULL if not found. + +`void hashmap_disallow_rehash(struct hashmap *map, unsigned value)`:: + + Disallow/allow automatic rehashing of the hashmap during inserts + and deletes. ++ +This is useful if the caller knows that the hashmap will be accessed +by multiple threads. ++ +The caller is still responsible for any necessary locking; this simply +prevents unexpected rehashing. The caller is also responsible for properly +sizing the initial hashmap to ensure good performance. ++ +A call to allow rehashing does not force a rehash; that might happen +with the next insert or delete. + +`void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter)`:: +`void *hashmap_iter_next(struct hashmap_iter *iter)`:: +`void *hashmap_iter_first(struct hashmap *map, struct hashmap_iter *iter)`:: + + Used to iterate over all entries of a hashmap. Note that it is + not safe to add or remove entries to the hashmap while + iterating. ++ +`hashmap_iter_init` initializes a `hashmap_iter` structure. ++ +`hashmap_iter_next` returns the next hashmap_entry, or NULL if there are no +more entries. ++ +`hashmap_iter_first` is a combination of both (i.e. initializes the iterator +and returns the first entry, if any). + +`const char *strintern(const char *string)`:: +`const void *memintern(const void *data, size_t len)`:: + + Returns the unique, interned version of the specified string or data, + similar to the `String.intern` API in Java and .NET, respectively. + Interned strings remain valid for the entire lifetime of the process. ++ +Can be used as `[x]strdup()` or `xmemdupz` replacement, except that interned +strings / data must not be modified or freed. ++ +Interned strings are best used for short strings with high probability of +duplicates. ++ +Uses a hashmap to store the pool of interned strings. + +Usage example +------------- + +Here's a simple usage example that maps long keys to double values. +------------ +struct hashmap map; + +struct long2double { + struct hashmap_entry ent; /* must be the first member! */ + long key; + double value; +}; + +static int long2double_cmp(const struct long2double *e1, const struct long2double *e2, const void *unused) +{ + return !(e1->key == e2->key); +} + +void long2double_init(void) +{ + hashmap_init(&map, (hashmap_cmp_fn) long2double_cmp, 0); +} + +void long2double_free(void) +{ + hashmap_free(&map, 1); +} + +static struct long2double *find_entry(long key) +{ + struct long2double k; + hashmap_entry_init(&k, memhash(&key, sizeof(long))); + k.key = key; + return hashmap_get(&map, &k, NULL); +} + +double get_value(long key) +{ + struct long2double *e = find_entry(key); + return e ? e->value : 0; +} + +void set_value(long key, double value) +{ + struct long2double *e = find_entry(key); + if (!e) { + e = malloc(sizeof(struct long2double)); + hashmap_entry_init(e, memhash(&key, sizeof(long))); + e->key = key; + hashmap_add(&map, e); + } + e->value = value; +} +------------ + +Using variable-sized keys +------------------------- + +The `hashmap_entry_get` and `hashmap_entry_remove` functions expect an ordinary +`hashmap_entry` structure as key to find the correct entry. If the key data is +variable-sized (e.g. a FLEX_ARRAY string) or quite large, it is undesirable +to create a full-fledged entry structure on the heap and copy all the key data +into the structure. + +In this case, the `keydata` parameter can be used to pass +variable-sized key data directly to the comparison function, and the `key` +parameter can be a stripped-down, fixed size entry structure allocated on the +stack. + +See test-hashmap.c for an example using arbitrary-length strings as keys. |