diff options
| -rw-r--r-- | Documentation/technical/api-hashmap.txt | 309 | ||||
| -rw-r--r-- | attr.c | 7 | ||||
| -rw-r--r-- | builtin/describe.c | 8 | ||||
| -rw-r--r-- | builtin/difftool.c | 24 | ||||
| -rw-r--r-- | builtin/fast-export.c | 7 | ||||
| -rw-r--r-- | config.c | 9 | ||||
| -rw-r--r-- | convert.c | 3 | ||||
| -rw-r--r-- | diffcore-rename.c | 2 | ||||
| -rw-r--r-- | hashmap.c | 17 | ||||
| -rw-r--r-- | hashmap.h | 360 | ||||
| -rw-r--r-- | name-hash.c | 16 | ||||
| -rw-r--r-- | oidset.c | 5 | ||||
| -rw-r--r-- | patch-ids.c | 10 | ||||
| -rw-r--r-- | refs.c | 5 | ||||
| -rw-r--r-- | remote.c | 7 | ||||
| -rw-r--r-- | sha1_file.c | 5 | ||||
| -rw-r--r-- | sub-process.c | 7 | ||||
| -rw-r--r-- | sub-process.h | 6 | ||||
| -rw-r--r-- | submodule-config.c | 14 | ||||
| -rw-r--r-- | t/helper/test-hashmap.c | 19 |
20 files changed, 431 insertions, 409 deletions
diff --git a/Documentation/technical/api-hashmap.txt b/Documentation/technical/api-hashmap.txt deleted file mode 100644 index ccc634bbd..000000000 --- a/Documentation/technical/api-hashmap.txt +++ /dev/null @@ -1,309 +0,0 @@ -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. @@ -76,9 +76,10 @@ struct attr_hash_entry { }; /* attr_hashmap comparison function */ -static int attr_hash_entry_cmp(const struct attr_hash_entry *a, +static int attr_hash_entry_cmp(void *unused_cmp_data, + const struct attr_hash_entry *a, const struct attr_hash_entry *b, - void *unused) + void *unused_keydata) { return (a->keylen != b->keylen) || strncmp(a->key, b->key, a->keylen); } @@ -86,7 +87,7 @@ static int attr_hash_entry_cmp(const struct attr_hash_entry *a, /* Initialize an 'attr_hashmap' object */ static void attr_hashmap_init(struct attr_hashmap *map) { - hashmap_init(&map->map, (hashmap_cmp_fn) attr_hash_entry_cmp, 0); + hashmap_init(&map->map, (hashmap_cmp_fn) attr_hash_entry_cmp, NULL, 0); } /* diff --git a/builtin/describe.c b/builtin/describe.c index 19eacdd17..89ea1cdd6 100644 --- a/builtin/describe.c +++ b/builtin/describe.c @@ -54,8 +54,10 @@ static const char *prio_names[] = { N_("head"), N_("lightweight"), N_("annotated"), }; -static int commit_name_cmp(const struct commit_name *cn1, - const struct commit_name *cn2, const void *peeled) +static int commit_name_cmp(const void *unused_cmp_data, + const struct commit_name *cn1, + const struct commit_name *cn2, + const void *peeled) { return oidcmp(&cn1->peeled, peeled ? peeled : &cn2->peeled); } @@ -501,7 +503,7 @@ int cmd_describe(int argc, const char **argv, const char *prefix) return cmd_name_rev(args.argc, args.argv, prefix); } - hashmap_init(&names, (hashmap_cmp_fn) commit_name_cmp, 0); + hashmap_init(&names, (hashmap_cmp_fn) commit_name_cmp, NULL, 0); for_each_rawref(get_name, NULL); if (!names.size && !always) die(_("No names found, cannot describe anything.")); diff --git a/builtin/difftool.c b/builtin/difftool.c index 9199227f6..a1a26ba89 100644 --- a/builtin/difftool.c +++ b/builtin/difftool.c @@ -130,8 +130,10 @@ struct working_tree_entry { char path[FLEX_ARRAY]; }; -static int working_tree_entry_cmp(struct working_tree_entry *a, - struct working_tree_entry *b, void *keydata) +static int working_tree_entry_cmp(const void *unused_cmp_data, + struct working_tree_entry *a, + struct working_tree_entry *b, + void *unused_keydata) { return strcmp(a->path, b->path); } @@ -146,7 +148,9 @@ struct pair_entry { const char path[FLEX_ARRAY]; }; -static int pair_cmp(struct pair_entry *a, struct pair_entry *b, void *keydata) +static int pair_cmp(const void *unused_cmp_data, + struct pair_entry *a, struct pair_entry *b, + void *unused_keydata) { return strcmp(a->path, b->path); } @@ -174,7 +178,9 @@ struct path_entry { char path[FLEX_ARRAY]; }; -static int path_entry_cmp(struct path_entry *a, struct path_entry *b, void *key) +static int path_entry_cmp(const void *unused_cmp_data, + struct path_entry *a, struct path_entry *b, + void *key) { return strcmp(a->path, key ? key : b->path); } @@ -367,9 +373,9 @@ static int run_dir_diff(const char *extcmd, int symlinks, const char *prefix, wtdir_len = wtdir.len; hashmap_init(&working_tree_dups, - (hashmap_cmp_fn)working_tree_entry_cmp, 0); - hashmap_init(&submodules, (hashmap_cmp_fn)pair_cmp, 0); - hashmap_init(&symlinks2, (hashmap_cmp_fn)pair_cmp, 0); + (hashmap_cmp_fn)working_tree_entry_cmp, NULL, 0); + hashmap_init(&submodules, (hashmap_cmp_fn)pair_cmp, NULL, 0); + hashmap_init(&symlinks2, (hashmap_cmp_fn)pair_cmp, NULL, 0); child.no_stdin = 1; child.git_cmd = 1; @@ -580,9 +586,9 @@ static int run_dir_diff(const char *extcmd, int symlinks, const char *prefix, * files through the symlink. */ hashmap_init(&wt_modified, (hashmap_cmp_fn)path_entry_cmp, - wtindex.cache_nr); + NULL, wtindex.cache_nr); hashmap_init(&tmp_modified, (hashmap_cmp_fn)path_entry_cmp, - wtindex.cache_nr); + NULL, wtindex.cache_nr); for (i = 0; i < wtindex.cache_nr; i++) { struct hashmap_entry dummy; diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 12d501bfd..d412c0a8f 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -93,8 +93,9 @@ struct anonymized_entry { size_t anon_len; }; -static int anonymized_entry_cmp(const void *va, const void *vb, - const void *data) +static int anonymized_entry_cmp(const void *unused_cmp_data, + const void *va, const void *vb, + const void *unused_keydata) { const struct anonymized_entry *a = va, *b = vb; return a->orig_len != b->orig_len || @@ -113,7 +114,7 @@ static const void *anonymize_mem(struct hashmap *map, struct anonymized_entry key, *ret; if (!map->cmpfn) - hashmap_init(map, anonymized_entry_cmp, 0); + hashmap_init(map, anonymized_entry_cmp, NULL, 0); hashmap_entry_init(&key, memhash(orig, *len)); key.orig = orig; @@ -1714,15 +1714,18 @@ static int configset_add_value(struct config_set *cs, const char *key, const cha return 0; } -static int config_set_element_cmp(const struct config_set_element *e1, - const struct config_set_element *e2, const void *unused) +static int config_set_element_cmp(const void *unused_cmp_data, + const struct config_set_element *e1, + const struct config_set_element *e2, + const void *unused_keydata) { 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); + hashmap_init(&cs->config_hash, (hashmap_cmp_fn)config_set_element_cmp, + NULL, 0); cs->hash_initialized = 1; cs->list.nr = 0; cs->list.alloc = 0; @@ -583,7 +583,8 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len if (!subprocess_map_initialized) { subprocess_map_initialized = 1; - hashmap_init(&subprocess_map, (hashmap_cmp_fn) cmd2process_cmp, 0); + hashmap_init(&subprocess_map, (hashmap_cmp_fn) cmd2process_cmp, + NULL, 0); entry = NULL; } else { entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd); diff --git a/diffcore-rename.c b/diffcore-rename.c index 1e4678b7d..786f38949 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -341,7 +341,7 @@ static int find_exact_renames(struct diff_options *options) /* Add all sources to the hash table in reverse order, because * later on they will be retrieved in LIFO order. */ - hashmap_init(&file_table, NULL, rename_src_nr); + hashmap_init(&file_table, NULL, NULL, rename_src_nr); for (i = rename_src_nr-1; i >= 0; i--) insert_file_table(&file_table, i, rename_src[i].p->one); @@ -95,7 +95,9 @@ static inline int entry_equals(const struct hashmap *map, const struct hashmap_entry *e1, const struct hashmap_entry *e2, const void *keydata) { - return (e1 == e2) || (e1->hash == e2->hash && !map->cmpfn(e1, e2, keydata)); + return (e1 == e2) || + (e1->hash == e2->hash && + !map->cmpfn(map->cmpfn_data, e1, e2, keydata)); } static inline unsigned int bucket(const struct hashmap *map, @@ -140,19 +142,23 @@ static inline struct hashmap_entry **find_entry_ptr(const struct hashmap *map, return e; } -static int always_equal(const void *unused1, const void *unused2, const void *unused3) +static int always_equal(const void *unused_cmp_data, + const void *unused1, + const void *unused2, + const void *unused_keydata) { return 0; } void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, - size_t initial_size) + const void *cmpfn_data, size_t initial_size) { unsigned int size = HASHMAP_INITIAL_SIZE; memset(map, 0, sizeof(*map)); map->cmpfn = equals_function ? equals_function : always_equal; + map->cmpfn_data = cmpfn_data; /* calculate initial table size and allocate the table */ initial_size = (unsigned int) ((uint64_t) initial_size * 100 @@ -260,7 +266,8 @@ struct pool_entry { unsigned char data[FLEX_ARRAY]; }; -static int pool_entry_cmp(const struct pool_entry *e1, +static int pool_entry_cmp(const void *unused_cmp_data, + const struct pool_entry *e1, const struct pool_entry *e2, const unsigned char *keydata) { @@ -275,7 +282,7 @@ const void *memintern(const void *data, size_t len) /* initialize string pool hashmap */ if (!map.tablesize) - hashmap_init(&map, (hashmap_cmp_fn) pool_entry_cmp, 0); + hashmap_init(&map, (hashmap_cmp_fn) pool_entry_cmp, NULL, 0); /* lookup interned string in pool */ hashmap_entry_init(&key, memhash(data, len)); @@ -3,17 +3,123 @@ /* * Generic implementation of hash-based key-value mappings. - * See Documentation/technical/api-hashmap.txt. + * + * 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 struct long2string *e1, + * const struct long2string *e2, + * const void *keydata, const void *userdata) + * { + * char *string = keydata; + * unsigned *flags = (unsigned*)userdata; + * + * if (flags & COMPARE_VALUE) + * return !(e1->key == e2->key) || (keydata ? + * strcmp(e1->value, keydata) : strcmp(e1->value, e2->value)); + * else + * return !(e1->key == e2->key); + * } + * + * int main(int argc, char **argv) + * { + * long key; + * char *value, *action; + * + * unsigned flags = ALLOW_DUPLICATE_KEYS; + * + * hashmap_init(&map, (hashmap_cmp_fn) long2string_cmp, &flags, 0); + * + * while (scanf("%s %l %s", action, key, value)) { + * + * if (!strcmp("add", action)) { + * struct long2string *e; + * e = malloc(sizeof(struct long2string) + strlen(value)); + * hashmap_entry_init(e, memhash(&key, sizeof(long))); + * e->key = key; + * memcpy(e->value, value, strlen(value)); + * hashmap_add(&map, e); + * } + * + * if (!strcmp("print_all_by_key", action)) { + * flags &= ~COMPARE_VALUE; + * + * struct long2string k; + * hashmap_entry_init(&k, memhash(&key, sizeof(long))); + * k.key = key; + * + * struct long2string *e = hashmap_get(&map, &k, NULL); + * if (e) { + * printf("first: %l %s\n", e->key, e->value); + * while (e = hashmap_get_next(&map, e)) + * printf("found more: %l %s\n", e->key, e->value); + * } + * } + * + * if (!strcmp("has_exact_match", action)) { + * flags |= COMPARE_VALUE; + * + * struct long2string *e; + * e = malloc(sizeof(struct long2string) + strlen(value)); + * hashmap_entry_init(e, memhash(&key, sizeof(long))); + * e->key = key; + * memcpy(e->value, value, strlen(value)); + * + * printf("%s found\n", hashmap_get(&map, e, NULL) ? "" : "not"); + * } + * + * if (!strcmp("has_exact_match_no_heap_alloc", action)) { + * flags |= COMPARE_VALUE; + * + * struct long2string e; + * hashmap_entry_init(e, memhash(&key, sizeof(long))); + * e.key = key; + * + * printf("%s found\n", hashmap_get(&map, e, value) ? "" : "not"); + * } + * + * if (!strcmp("end", action)) { + * hashmap_free(&map, 1); + * break; + * } + * } + * } */ -/* FNV-1 functions */ - +/* + * 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. + */ extern unsigned int strhash(const char *buf); extern unsigned int strihash(const char *buf); extern unsigned int memhash(const void *buf, size_t len); extern unsigned int memihash(const void *buf, size_t len); extern 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 sha1hash(const unsigned char *sha1) { /* @@ -25,86 +131,255 @@ static inline unsigned int sha1hash(const unsigned char *sha1) return hash; } -/* data structures */ - +/* + * 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; }; -typedef 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` 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; - unsigned int size, tablesize, grow_at, shrink_at; - unsigned disallow_rehash : 1; -}; + const void *cmpfn_data; -struct hashmap_iter { - struct hashmap *map; - struct hashmap_entry *next; - unsigned int tablepos; + /* total number of entries (0 means the hashmap is empty) */ + unsigned int 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; + + /* See `hashmap_disallow_rehash`. */ + unsigned disallow_rehash : 1; }; /* hashmap functions */ -extern 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. + * + * 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. + */ +extern 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(). + */ extern 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(void *entry, unsigned int hash) { struct hashmap_entry *e = entry; e->hash = hash; e->next = NULL; } + +/* + * 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. + */ extern void *hashmap_get(const struct hashmap *map, const void *key, - const void *keydata); -extern void *hashmap_get_next(const struct hashmap *map, const void *entry); -extern void hashmap_add(struct hashmap *map, void *entry); -extern void *hashmap_put(struct hashmap *map, void *entry); -extern void *hashmap_remove(struct hashmap *map, const void *key, - const void *keydata); + 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) + 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`. + */ +extern void *hashmap_get_next(const struct hashmap *map, const 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. + */ +extern void hashmap_add(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). + */ +extern void *hashmap_put(struct hashmap *map, void *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`. + */ +extern void *hashmap_remove(struct hashmap *map, const void *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); /* * Disallow/allow rehashing of the hashmap. - * This is useful if the caller knows that the hashmap - * needs multi-threaded access. The caller is still - * required to guard/lock searches and inserts in a - * manner appropriate to their usage. This simply - * prevents the table from being unexpectedly re-mapped. + * This is useful if the caller knows that the hashmap needs multi-threaded + * access. The caller is still required to guard/lock searches and inserts + * in a manner appropriate to their usage. This simply prevents the table + * from being unexpectedly re-mapped. * - * If is up to the caller to ensure that the hashmap is - * initialized to a reasonable size to prevent poor - * performance. + * It is up to the caller to ensure that the hashmap is initialized to a + * reasonable size to prevent poor performance. * - * When value=1, prevent future rehashes on adds and deleted. - * When value=0, allow future rehahses. This DOES NOT force - * a rehash now. + * A call to allow rehashing does not force a rehash; that might happen + * with the next insert or delete. */ static inline void hashmap_disallow_rehash(struct hashmap *map, unsigned value) { map->disallow_rehash = value; } -/* hashmap_iter functions */ +/* + * 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. */ extern void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter); + +/* Returns the next hashmap_entry, or NULL if there are no more entries. */ extern 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) { @@ -112,8 +387,21 @@ static inline void *hashmap_iter_first(struct hashmap *map, return hashmap_iter_next(iter); } -/* string interning */ +/* 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. + */ extern const void *memintern(const void *data, size_t len); static inline const char *strintern(const char *string) { diff --git a/name-hash.c b/name-hash.c index 39309efb7..0e10f3eab 100644 --- a/name-hash.c +++ b/name-hash.c @@ -16,8 +16,10 @@ struct dir_entry { char name[FLEX_ARRAY]; }; -static int dir_entry_cmp(const struct dir_entry *e1, - const struct dir_entry *e2, const char *name) +static int dir_entry_cmp(const void *unused_cmp_data, + const struct dir_entry *e1, + const struct dir_entry *e2, + const char *name) { return e1->namelen != e2->namelen || strncasecmp(e1->name, name ? name : e2->name, e1->namelen); @@ -107,8 +109,10 @@ static void hash_index_entry(struct index_state *istate, struct cache_entry *ce) add_dir_entry(istate, ce); } -static int cache_entry_cmp(const struct cache_entry *ce1, - const struct cache_entry *ce2, const void *remove) +static int cache_entry_cmp(const void *unused_cmp_data, + const struct cache_entry *ce1, + const struct cache_entry *ce2, + const void *remove) { /* * For remove_name_hash, find the exact entry (pointer equality); for @@ -571,9 +575,9 @@ static void lazy_init_name_hash(struct index_state *istate) if (istate->name_hash_initialized) return; hashmap_init(&istate->name_hash, (hashmap_cmp_fn) cache_entry_cmp, - istate->cache_nr); + NULL, istate->cache_nr); hashmap_init(&istate->dir_hash, (hashmap_cmp_fn) dir_entry_cmp, - istate->cache_nr); + NULL, istate->cache_nr); if (lookup_lazy_params(istate)) { hashmap_disallow_rehash(&istate->dir_hash, 1); @@ -6,7 +6,8 @@ struct oidset_entry { struct object_id oid; }; -static int oidset_hashcmp(const void *va, const void *vb, +static int oidset_hashcmp(const void *unused_cmp_data, + const void *va, const void *vb, const void *vkey) { const struct oidset_entry *a = va, *b = vb; @@ -30,7 +31,7 @@ int oidset_insert(struct oidset *set, const struct object_id *oid) struct oidset_entry *entry; if (!set->map.cmpfn) - hashmap_init(&set->map, oidset_hashcmp, 0); + hashmap_init(&set->map, oidset_hashcmp, NULL, 0); if (oidset_contains(set, oid)) return 1; diff --git a/patch-ids.c b/patch-ids.c index 9c0ab9e67..b4166b0f3 100644 --- a/patch-ids.c +++ b/patch-ids.c @@ -35,9 +35,10 @@ int commit_patch_id(struct commit *commit, struct diff_options *options, * the side of safety. The actual value being negative does not have * any significance; only that it is non-zero matters. */ -static int patch_id_cmp(struct patch_id *a, +static int patch_id_cmp(struct diff_options *opt, + struct patch_id *a, struct patch_id *b, - struct diff_options *opt) + const void *unused_keydata) { if (is_null_oid(&a->patch_id) && commit_patch_id(a->commit, opt, &a->patch_id, 0)) @@ -57,7 +58,8 @@ int init_patch_ids(struct patch_ids *ids) ids->diffopts.detect_rename = 0; DIFF_OPT_SET(&ids->diffopts, RECURSIVE); diff_setup_done(&ids->diffopts); - hashmap_init(&ids->patches, (hashmap_cmp_fn)patch_id_cmp, 256); + hashmap_init(&ids->patches, (hashmap_cmp_fn)patch_id_cmp, + &ids->diffopts, 256); return 0; } @@ -93,7 +95,7 @@ struct patch_id *has_commit_patch_id(struct commit *commit, if (init_patch_id_entry(&patch, commit, ids)) return NULL; - return hashmap_get(&ids->patches, &patch, &ids->diffopts); + return hashmap_get(&ids->patches, &patch, NULL); } struct patch_id *add_commit_patch_id(struct commit *commit, @@ -1525,7 +1525,8 @@ struct ref_store_hash_entry char name[FLEX_ARRAY]; }; -static int ref_store_hash_cmp(const void *entry, const void *entry_or_key, +static int ref_store_hash_cmp(const void *unused_cmp_data, + const void *entry, const void *entry_or_key, const void *keydata) { const struct ref_store_hash_entry *e1 = entry, *e2 = entry_or_key; @@ -1608,7 +1609,7 @@ static void register_ref_store_map(struct hashmap *map, const char *name) { if (!map->tablesize) - hashmap_init(map, ref_store_hash_cmp, 0); + hashmap_init(map, ref_store_hash_cmp, NULL, 0); if (hashmap_put(map, alloc_ref_store_hash_entry(name, refs))) die("BUG: %s ref_store '%s' initialized twice", type, name); @@ -133,7 +133,10 @@ struct remotes_hash_key { int len; }; -static int remotes_hash_cmp(const struct remote *a, const struct remote *b, const struct remotes_hash_key *key) +static int remotes_hash_cmp(const void *unused_cmp_data, + const struct remote *a, + const struct remote *b, + const struct remotes_hash_key *key) { if (key) return strncmp(a->name, key->str, key->len) || a->name[key->len]; @@ -144,7 +147,7 @@ static int remotes_hash_cmp(const struct remote *a, const struct remote *b, cons static inline void init_remotes_hash(void) { if (!remotes_hash.cmpfn) - hashmap_init(&remotes_hash, (hashmap_cmp_fn)remotes_hash_cmp, 0); + hashmap_init(&remotes_hash, (hashmap_cmp_fn)remotes_hash_cmp, NULL, 0); } static struct remote *make_remote(const char *name, int len) diff --git a/sha1_file.c b/sha1_file.c index 5862386cd..fca165f13 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -2275,7 +2275,8 @@ static int delta_base_cache_key_eq(const struct delta_base_cache_key *a, return a->p == b->p && a->base_offset == b->base_offset; } -static int delta_base_cache_hash_cmp(const void *va, const void *vb, +static int delta_base_cache_hash_cmp(const void *unused_cmp_data, + const void *va, const void *vb, const void *vkey) { const struct delta_base_cache_entry *a = va, *b = vb; @@ -2360,7 +2361,7 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset, list_add_tail(&ent->lru, &delta_base_cache_lru); if (!delta_base_cache.cmpfn) - hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, 0); + hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, NULL, 0); hashmap_entry_init(ent, pack_entry_hash(p, base_offset)); hashmap_add(&delta_base_cache, ent); } diff --git a/sub-process.c b/sub-process.c index 92f8aea70..a3cfab1a9 100644 --- a/sub-process.c +++ b/sub-process.c @@ -5,9 +5,10 @@ #include "sigchain.h" #include "pkt-line.h" -int cmd2process_cmp(const struct subprocess_entry *e1, - const struct subprocess_entry *e2, - const void *unused) +int cmd2process_cmp(const void *unused_cmp_data, + const struct subprocess_entry *e1, + const struct subprocess_entry *e2, + const void *unused_keydata) { return strcmp(e1->cmd, e2->cmd); } diff --git a/sub-process.h b/sub-process.h index d9a45cd35..96a2cca36 100644 --- a/sub-process.h +++ b/sub-process.h @@ -20,8 +20,10 @@ struct subprocess_entry { /* subprocess functions */ -int cmd2process_cmp(const struct subprocess_entry *e1, - const struct subprocess_entry *e2, const void *unused); +extern int cmd2process_cmp(const void *unused_cmp_data, + const struct subprocess_entry *e1, + const struct subprocess_entry *e2, + const void *unused_keydata); typedef int(*subprocess_start_fn)(struct subprocess_entry *entry); int subprocess_start(struct hashmap *hashmap, struct subprocess_entry *entry, const char *cmd, diff --git a/submodule-config.c b/submodule-config.c index 37cfcceb9..eeb154a89 100644 --- a/submodule-config.c +++ b/submodule-config.c @@ -33,17 +33,19 @@ enum lookup_type { lookup_path }; -static int config_path_cmp(const struct submodule_entry *a, +static int config_path_cmp(const void *unused_cmp_data, + const struct submodule_entry *a, const struct submodule_entry *b, - const void *unused) + const void *unused_keydata) { return strcmp(a->config->path, b->config->path) || hashcmp(a->config->gitmodules_sha1, b->config->gitmodules_sha1); } -static int config_name_cmp(const struct submodule_entry *a, +static int config_name_cmp(const void *unused_cmp_data, + const struct submodule_entry *a, const struct submodule_entry *b, - const void *unused) + const void *unused_keydata) { return strcmp(a->config->name, b->config->name) || hashcmp(a->config->gitmodules_sha1, b->config->gitmodules_sha1); @@ -56,8 +58,8 @@ static struct submodule_cache *submodule_cache_alloc(void) static void submodule_cache_init(struct submodule_cache *cache) { - hashmap_init(&cache->for_path, (hashmap_cmp_fn) config_path_cmp, 0); - hashmap_init(&cache->for_name, (hashmap_cmp_fn) config_name_cmp, 0); + hashmap_init(&cache->for_path, (hashmap_cmp_fn) config_path_cmp, NULL, 0); + hashmap_init(&cache->for_name, (hashmap_cmp_fn) config_name_cmp, NULL, 0); cache->initialized = 1; } diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c index 7aa9440e2..095d7395f 100644 --- a/t/helper/test-hashmap.c +++ b/t/helper/test-hashmap.c @@ -13,14 +13,18 @@ static const char *get_value(const struct test_entry *e) return e->key + strlen(e->key) + 1; } -static int test_entry_cmp(const struct test_entry *e1, - const struct test_entry *e2, const char* key) +static int test_entry_cmp(const void *unused_cmp_data, + const struct test_entry *e1, + const struct test_entry *e2, + const char* key) { return strcmp(e1->key, key ? key : e2->key); } -static int test_entry_cmp_icase(const struct test_entry *e1, - const struct test_entry *e2, const char* key) +static int test_entry_cmp_icase(const void *unused_cmp_data, + const struct test_entry *e1, + const struct test_entry *e2, + const char* key) { return strcasecmp(e1->key, key ? key : e2->key); } @@ -92,7 +96,8 @@ static void perf_hashmap(unsigned int method, unsigned int rounds) if (method & TEST_ADD) { /* test adding to the map */ for (j = 0; j < rounds; j++) { - hashmap_init(&map, (hashmap_cmp_fn) test_entry_cmp, 0); + hashmap_init(&map, (hashmap_cmp_fn) test_entry_cmp, + NULL, 0); /* add entries */ for (i = 0; i < TEST_SIZE; i++) { @@ -104,7 +109,7 @@ static void perf_hashmap(unsigned int method, unsigned int rounds) } } else { /* test map lookups */ - hashmap_init(&map, (hashmap_cmp_fn) test_entry_cmp, 0); + hashmap_init(&map, (hashmap_cmp_fn) test_entry_cmp, NULL, 0); /* fill the map (sparsely if specified) */ j = (method & TEST_SPARSE) ? TEST_SIZE / 10 : TEST_SIZE; @@ -147,7 +152,7 @@ int cmd_main(int argc, const char **argv) /* init hash map */ icase = argc > 1 && !strcmp("ignorecase", argv[1]); hashmap_init(&map, (hashmap_cmp_fn) (icase ? test_entry_cmp_icase - : test_entry_cmp), 0); + : test_entry_cmp), NULL, 0); /* process commands from stdin */ while (fgets(line, sizeof(line), stdin)) { |