Merge branch 'jt/binsearch-with-fanout'
Refactor the code to binary search starting from a fan-out table (which is how the packfile is indexed with object names) into a reusable helper. * jt/binsearch-with-fanout: packfile: refactor hash search with fanout table packfile: remove GIT_DEBUG_LOOKUP log statements
This commit is contained in:
commit
f2fcbeb3bf
29
packfile.c
29
packfile.c
@ -1722,11 +1722,8 @@ off_t find_pack_entry_one(const unsigned char *sha1,
|
|||||||
{
|
{
|
||||||
const uint32_t *level1_ofs = p->index_data;
|
const uint32_t *level1_ofs = p->index_data;
|
||||||
const unsigned char *index = p->index_data;
|
const unsigned char *index = p->index_data;
|
||||||
unsigned hi, lo, stride;
|
unsigned stride;
|
||||||
static int debug_lookup = -1;
|
uint32_t result;
|
||||||
|
|
||||||
if (debug_lookup < 0)
|
|
||||||
debug_lookup = !!getenv("GIT_DEBUG_LOOKUP");
|
|
||||||
|
|
||||||
if (!index) {
|
if (!index) {
|
||||||
if (open_pack_index(p))
|
if (open_pack_index(p))
|
||||||
@ -1739,8 +1736,6 @@ off_t find_pack_entry_one(const unsigned char *sha1,
|
|||||||
index += 8;
|
index += 8;
|
||||||
}
|
}
|
||||||
index += 4 * 256;
|
index += 4 * 256;
|
||||||
hi = ntohl(level1_ofs[*sha1]);
|
|
||||||
lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
|
|
||||||
if (p->index_version > 1) {
|
if (p->index_version > 1) {
|
||||||
stride = 20;
|
stride = 20;
|
||||||
} else {
|
} else {
|
||||||
@ -1748,24 +1743,8 @@ off_t find_pack_entry_one(const unsigned char *sha1,
|
|||||||
index += 4;
|
index += 4;
|
||||||
}
|
}
|
||||||
|
|
||||||
if (debug_lookup)
|
if (bsearch_hash(sha1, level1_ofs, index, stride, &result))
|
||||||
printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n",
|
return nth_packed_object_offset(p, result);
|
||||||
sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
|
|
||||||
|
|
||||||
while (lo < hi) {
|
|
||||||
unsigned mi = lo + (hi - lo) / 2;
|
|
||||||
int cmp = hashcmp(index + mi * stride, sha1);
|
|
||||||
|
|
||||||
if (debug_lookup)
|
|
||||||
printf("lo %u hi %u rg %u mi %u\n",
|
|
||||||
lo, hi, hi - lo, mi);
|
|
||||||
if (!cmp)
|
|
||||||
return nth_packed_object_offset(p, mi);
|
|
||||||
if (cmp > 0)
|
|
||||||
hi = mi;
|
|
||||||
else
|
|
||||||
lo = mi+1;
|
|
||||||
}
|
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -99,3 +99,31 @@ int sha1_pos(const unsigned char *sha1, void *table, size_t nr,
|
|||||||
} while (lo < hi);
|
} while (lo < hi);
|
||||||
return -lo-1;
|
return -lo-1;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
int bsearch_hash(const unsigned char *sha1, const uint32_t *fanout_nbo,
|
||||||
|
const unsigned char *table, size_t stride, uint32_t *result)
|
||||||
|
{
|
||||||
|
uint32_t hi, lo;
|
||||||
|
|
||||||
|
hi = ntohl(fanout_nbo[*sha1]);
|
||||||
|
lo = ((*sha1 == 0x0) ? 0 : ntohl(fanout_nbo[*sha1 - 1]));
|
||||||
|
|
||||||
|
while (lo < hi) {
|
||||||
|
unsigned mi = lo + (hi - lo) / 2;
|
||||||
|
int cmp = hashcmp(table + mi * stride, sha1);
|
||||||
|
|
||||||
|
if (!cmp) {
|
||||||
|
if (result)
|
||||||
|
*result = mi;
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
if (cmp > 0)
|
||||||
|
hi = mi;
|
||||||
|
else
|
||||||
|
lo = mi + 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (result)
|
||||||
|
*result = lo;
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
@ -7,4 +7,26 @@ extern int sha1_pos(const unsigned char *sha1,
|
|||||||
void *table,
|
void *table,
|
||||||
size_t nr,
|
size_t nr,
|
||||||
sha1_access_fn fn);
|
sha1_access_fn fn);
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Searches for sha1 in table, using the given fanout table to determine the
|
||||||
|
* interval to search, then using binary search. Returns 1 if found, 0 if not.
|
||||||
|
*
|
||||||
|
* Takes the following parameters:
|
||||||
|
*
|
||||||
|
* - sha1: the hash to search for
|
||||||
|
* - fanout_nbo: a 256-element array of NETWORK-order 32-bit integers; the
|
||||||
|
* integer at position i represents the number of elements in table whose
|
||||||
|
* first byte is less than or equal to i
|
||||||
|
* - table: a sorted list of hashes with optional extra information in between
|
||||||
|
* - stride: distance between two consecutive elements in table (should be
|
||||||
|
* GIT_MAX_RAWSZ or greater)
|
||||||
|
* - result: if not NULL, this function stores the element index of the
|
||||||
|
* position found (if the search is successful) or the index of the least
|
||||||
|
* element that is greater than sha1 (if the search is not successful)
|
||||||
|
*
|
||||||
|
* This function does not verify the validity of the fanout table.
|
||||||
|
*/
|
||||||
|
int bsearch_hash(const unsigned char *sha1, const uint32_t *fanout_nbo,
|
||||||
|
const unsigned char *table, size_t stride, uint32_t *result);
|
||||||
#endif
|
#endif
|
||||||
|
Loading…
Reference in New Issue
Block a user