summaryrefslogtreecommitdiff
path: root/hashmap.h
blob: cd42dcc15c2b3be1a9245aa06c711e5c2ec59d73 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
#ifndef HASHMAP_H
#define HASHMAP_H
 
#include "hash.h"
 
/*
 * Generic implementation of hash-based key-value mappings.
 *
 * An example that maps long to a string:
 * For the sake of the example this allows to lookup exact values, too
 * (i.e. it is operated as a set, the value is part of the key)
 * -------------------------------------
 *
 * struct hashmap map;
 * struct long2string {
 *     struct hashmap_entry ent; // must be the first member!
 *     long key;
 *     char value[FLEX_ARRAY];   // be careful with allocating on stack!
 * };
 *
 * #define COMPARE_VALUE 1
 *
 * static int long2string_cmp(const void *hashmap_cmp_fn_data,
 *                            const struct long2string *e1,
 *                            const struct long2string *e2,
 *                            const void *keydata)
 * {
 *     const char *string = keydata;
 *     unsigned flags = *(unsigned *)hashmap_cmp_fn_data;
 *
 *     if (flags & COMPARE_VALUE)
 *         return e1->key != e2->key ||
 *                  strcmp(e1->value, string ? string : e2->value);
 *     else
 *         return e1->key != e2->key;
 * }
 *
 * int main(int argc, char **argv)
 * {
 *     long key;
 *     char value[255], action[32];
 *     unsigned flags = 0;
 *
 *     hashmap_init(&map, (hashmap_cmp_fn) long2string_cmp, &flags, 0);
 *
 *     while (scanf("%s %ld %s", action, &key, value)) {
 *
 *         if (!strcmp("add", action)) {
 *             struct long2string *e;
 *             FLEX_ALLOC_STR(e, value, value);
 *             hashmap_entry_init(&e->ent, memhash(&key, sizeof(long)));
 *             e->key = key;
 *             hashmap_add(&map, &e->ent);
 *         }
 *
 *         if (!strcmp("print_all_by_key", action)) {
 *             struct long2string k, *e;
 *             hashmap_entry_init(&k->ent, memhash(&key, sizeof(long)));
 *             k.key = key;
 *
 *             flags &= ~COMPARE_VALUE;
 *             e = hashmap_get_entry(&map, &k, NULL, struct long2string, ent);
 *             if (e) {
 *                 printf("first: %ld %s\n", e->key, e->value);
 *                 while ((e = hashmap_get_next_entry(&map, e,
 *                                              struct long2string, ent))) {
 *                     printf("found more: %ld %s\n", e->key, e->value);
 *                 }
 *             }
 *         }
 *
 *         if (!strcmp("has_exact_match", action)) {
 *             struct long2string *e;
 *             FLEX_ALLOC_STR(e, value, value);
 *             hashmap_entry_init(&e->ent, memhash(&key, sizeof(long)));
 *             e->key = key;
 *
 *             flags |= COMPARE_VALUE;
 *             printf("%sfound\n",
 *                    hashmap_get(&map, &e->ent, NULL) ? "" : "not ");
 *             free(e);
 *         }
 *
 *         if (!strcmp("has_exact_match_no_heap_alloc", action)) {
 *             struct long2string k;
 *             hashmap_entry_init(&k->ent, memhash(&key, sizeof(long)));
 *             k.key = key;
 *
 *             flags |= COMPARE_VALUE;
 *             printf("%sfound\n",
 *                    hashmap_get(&map, &k->ent, value) ? "" : "not ");
 *         }
 *
 *         if (!strcmp("end", action)) {
 *             hashmap_free(&map, 1);
 *             break;
 *         }
 *     }
 *
 *     return 0;
 * }
 */
 
/*
 * 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 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);
 
/*
 * 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.
 */
static inline unsigned int oidhash(const struct object_id *oid)
{
	/*
	 * Equivalent to 'return *(unsigned int *)oid->hash;', but safe on
	 * platforms that don't support unaligned reads.
	 */
	unsigned int hash;
	memcpy(&hash, oid->hash, sizeof(hash));
	return hash;
}
 
/*
 * struct hashmap_entry is 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.
 */
struct hashmap_entry {
	/*
	 * next points to the next entry in case of collisions (i.e. if
	 * multiple entries map to the same bucket)
	 */
	struct hashmap_entry *next;
 
	/* entry's hash code */
	unsigned int hash;
};
 
/*
 * 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` and `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 `entry_or_key` and third
 * argument `keydata`, respectively. Otherwise, `keydata` is NULL.
 *
 * When it is too expensive to allocate a user entry (either because it is
 * large or varialbe sized, such that it is not on the stack), then the
 * relevant data to check for equality should be passed via `keydata`.
 * In this case `key` can be a stripped down version of the user key data
 * or even just a hashmap_entry having the correct hash.
 *
 * The `hashmap_cmp_fn_data` entry is the pointer given in the init function.
 */
typedef int (*hashmap_cmp_fn)(const void *hashmap_cmp_fn_data,
			      const void *entry, const void *entry_or_key,
			      const void *keydata);
 
/*
 * struct hashmap is the hash table structure. Members can be used as follows,
 * but should not be modified directly.
 */
struct hashmap {
	struct hashmap_entry **table;
 
	/* Stores the comparison function specified in `hashmap_init()`. */
	hashmap_cmp_fn cmpfn;
	const void *cmpfn_data;
 
	/* total number of entries (0 means the hashmap is empty) */
	unsigned int private_size; /* use hashmap_get_size() */
 
	/*
	 * 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).
	 */
	unsigned int tablesize;
 
	unsigned int grow_at;
	unsigned int shrink_at;
 
	unsigned int do_count_items : 1;
};
 
/* hashmap functions */
 
/*
 * 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.
 *
 * The `equals_function_data` parameter can be used to provide additional data
 * (a callback cookie) that will be passed to `equals_function` each time it
 * is called. This allows a single `equals_function` to implement multiple
 * comparison functions.
 *
 * 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_init(struct hashmap *map,
			 hashmap_cmp_fn equals_function,
			 const void *equals_function_data,
			 size_t initial_size);
 
/*
 * Frees a hashmap structure and allocated memory.
 *
 * If `free_entries` is true, each hashmap_entry in the map is freed as well
 * using stdlibs free().
 */
void hashmap_free(struct hashmap *map, int free_entries);
 
/* hashmap_entry functions */
 
/*
 * 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).
 */
static inline void hashmap_entry_init(struct hashmap_entry *e,
					unsigned int hash)
{
	e->hash = hash;
	e->next = NULL;
}
 
/*
 * Return the number of items in the map.
 */
static inline unsigned int hashmap_get_size(struct hashmap *map)
{
	if (map->do_count_items)
		return map->private_size;
 
	BUG("hashmap_get_size: size not set");
	return 0;
}
 
/*
 * Returns the hashmap entry for the specified key, or NULL if not found.
 *
 * `map` is the hashmap structure.
 *
 * `key` is a user data structure that starts with hashmap_entry that has at
 * least been initialized with the proper hash code (via `hashmap_entry_init`).
 *
 * `keydata` is a data structure that holds just enough information to check
 * for equality to a given 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.
 *
 * 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(const struct hashmap *map, const struct hashmap_entry *key,
			 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 of `hashmap_cmp_fn` points to a hashmap_entry
 * structure that should not be used in the comparison.
 */
static inline void *hashmap_get_from_hash(const struct hashmap *map,
					  unsigned int hash,
					  const void *keydata)
{
	struct hashmap_entry key;
	hashmap_entry_init(&key, hash);
	return hashmap_get(map, &key, keydata);
}
 
/*
 * 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`.
 */
struct hashmap_entry *hashmap_get_next(const struct hashmap *map,
			const struct hashmap_entry *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_add(struct hashmap *map, struct hashmap_entry *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_put(struct hashmap *map, struct hashmap_entry *entry);
 
/*
 * 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. Returns the removed entry, or NULL if not found.
 *
 * Argument explanation is the same as in `hashmap_get`.
 */
void *hashmap_remove(struct hashmap *map, const struct hashmap_entry *key,
		const void *keydata);
 
/*
 * Returns the `bucket` an entry is stored in.
 * Useful for multithreaded read access.
 */
int hashmap_bucket(const struct hashmap *map, unsigned int hash);
 
/*
 * 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.
 */
struct hashmap_iter {
	struct hashmap *map;
	struct hashmap_entry *next;
	unsigned int tablepos;
};
 
/* Initializes a `hashmap_iter` structure. */
void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter);
 
/* Returns the next hashmap_entry, or NULL if there are no more entries. */
void *hashmap_iter_next(struct hashmap_iter *iter);
 
/* Initializes the iterator and returns the first entry, if any. */
static inline void *hashmap_iter_first(struct hashmap *map,
		struct hashmap_iter *iter)
{
	hashmap_iter_init(map, iter);
	return hashmap_iter_next(iter);
}
 
/*
 * returns a @pointer of @type matching @keyvar, or NULL if nothing found.
 * @keyvar is a pointer of @type
 * @member is the name of the "struct hashmap_entry" field in @type
 */
#define hashmap_get_entry(map, keyvar, keydata, type, member) \
	container_of_or_null(hashmap_get(map, &(keyvar)->member, keydata), \
				type, member)
 
#define hashmap_get_entry_from_hash(map, hash, keydata, type, member) \
	container_of_or_null(hashmap_get_from_hash(map, hash, keydata), \
				type, member)
/*
 * returns the next equal @type pointer to @var, or NULL if not found.
 * @var is a pointer of @type
 * @member is the name of the "struct hashmap_entry" field in @type
 */
#define hashmap_get_next_entry(map, var, type, member) \
	container_of_or_null(hashmap_get_next(map, &(var)->member), \
				type, member)
 
/*
 * iterate @map starting from @var, where @var is a pointer of @type
 * and @member is the name of the "struct hashmap_entry" field in @type
 */
#define hashmap_for_each_entry_from(map, var, type, member) \
	for (; \
		var; \
		var = hashmap_get_next_entry(map, var, type, member))
 
/*
 * Disable item counting and automatic rehashing when adding/removing items.
 *
 * Normally, the hashmap keeps track of the number of items in the map
 * and uses it to dynamically resize it.  This (both the counting and
 * the resizing) can cause problems when the map is being used by
 * threaded callers (because the hashmap code does not know about the
 * locking strategy used by the threaded callers and therefore, does
 * not know how to protect the "private_size" counter).
 */
static inline void hashmap_disable_item_counting(struct hashmap *map)
{
	map->do_count_items = 0;
}
 
/*
 * Re-enable item couting when adding/removing items.
 * If counting is currently disabled, it will force count them.
 * It WILL NOT automatically rehash them.
 */
static inline void hashmap_enable_item_counting(struct hashmap *map)
{
	unsigned int n = 0;
	struct hashmap_iter iter;
 
	if (map->do_count_items)
		return;
 
	hashmap_iter_init(map, &iter);
	while (hashmap_iter_next(&iter))
		n++;
 
	map->do_count_items = 1;
	map->private_size = n;
}
 
/* String interning */
 
/*
 * 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.
 */
const void *memintern(const void *data, size_t len);
static inline const char *strintern(const char *string)
{
	return memintern(string, strlen(string));
}
 
#endif