1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-11-14 13:13:01 +01:00
git/hash.c
Jeff King 9ea0980a09 hash: fix lookup_hash semantics
We were returning the _address of_ the stored item (or NULL)
instead of the item itself. While this sort of indirection
is useful for insertion (since you can lookup and then
modify), it is unnecessary for read-only lookup. Since the
hash code splits these functions between the internal
lookup_hash_entry function and the public lookup_hash
function, it makes sense for the latter to provide what
users of the library expect.

The result of this was that the index caching returned bogus
results on lookup. We unfortunately didn't catch this
because we were returning a "struct cache_entry **" as a
"void *", and accidentally assigning it to a "struct
cache_entry *".

As it happens, this actually _worked_ most of the time,
because the entries were defined as:

  struct cache_entry {
	  struct cache_entry *next;
	  ...
  };

meaning that interpreting a "struct cache_entry **" as a
"struct cache_entry *" would yield an entry where all fields
were totally bogus _except_ for the next pointer, which
pointed to the actual cache entry. When walking the list, we
would look at the bogus "name" field, which was unlikely to
match our lookup, and then proceed to the "real" entry.

The reading of bogus data was silently ignored most of the
time, but could cause a segfault for some data (which seems
to be more common on OS X).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-22 13:39:20 -08:00

110 lines
2.5 KiB
C

/*
* Some generic hashing helpers.
*/
#include "cache.h"
#include "hash.h"
/*
* Look up a hash entry in the hash table. Return the pointer to
* the existing entry, or the empty slot if none existed. The caller
* can then look at the (*ptr) to see whether it existed or not.
*/
static struct hash_table_entry *lookup_hash_entry(unsigned int hash, struct hash_table *table)
{
unsigned int size = table->size, nr = hash % size;
struct hash_table_entry *array = table->array;
while (array[nr].ptr) {
if (array[nr].hash == hash)
break;
nr++;
if (nr >= size)
nr = 0;
}
return array + nr;
}
/*
* Insert a new hash entry pointer into the table.
*
* If that hash entry already existed, return the pointer to
* the existing entry (and the caller can create a list of the
* pointers or do anything else). If it didn't exist, return
* NULL (and the caller knows the pointer has been inserted).
*/
static void **insert_hash_entry(unsigned int hash, void *ptr, struct hash_table *table)
{
struct hash_table_entry *entry = lookup_hash_entry(hash, table);
if (!entry->ptr) {
entry->ptr = ptr;
entry->hash = hash;
table->nr++;
return NULL;
}
return &entry->ptr;
}
static void grow_hash_table(struct hash_table *table)
{
unsigned int i;
unsigned int old_size = table->size, new_size;
struct hash_table_entry *old_array = table->array, *new_array;
new_size = alloc_nr(old_size);
new_array = xcalloc(sizeof(struct hash_table_entry), new_size);
table->size = new_size;
table->array = new_array;
table->nr = 0;
for (i = 0; i < old_size; i++) {
unsigned int hash = old_array[i].hash;
void *ptr = old_array[i].ptr;
if (ptr)
insert_hash_entry(hash, ptr, table);
}
free(old_array);
}
void *lookup_hash(unsigned int hash, struct hash_table *table)
{
if (!table->array)
return NULL;
return lookup_hash_entry(hash, table)->ptr;
}
void **insert_hash(unsigned int hash, void *ptr, struct hash_table *table)
{
unsigned int nr = table->nr;
if (nr >= table->size/2)
grow_hash_table(table);
return insert_hash_entry(hash, ptr, table);
}
int for_each_hash(struct hash_table *table, int (*fn)(void *))
{
int sum = 0;
unsigned int i;
unsigned int size = table->size;
struct hash_table_entry *array = table->array;
for (i = 0; i < size; i++) {
void *ptr = array->ptr;
array++;
if (ptr) {
int val = fn(ptr);
if (val < 0)
return val;
sum += val;
}
}
return sum;
}
void free_hash(struct hash_table *table)
{
free(table->array);
table->array = NULL;
table->size = 0;
table->nr = 0;
}