undef/git-commit-vandalism
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Try using Geert similarity code in pack-objects.

Browse Source 
It appears the fingerprinting itself is too expensive to be worth doing
for this purpose.  A failed experiment.

Signed-off-by: Junio C Hamano <junkio@cox.net>
This commit is contained in:
Junio C Hamano 2006-04-16 22:03:01 -07:00
parent 9a305b67f8
commit ca9de6cadf
2 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@ -204,7 +204,7 @@ DIFF_OBJS = \
diffcore-delta.o log-tree.o diffcore-delta.o log-tree.o
LIB_OBJS = \ LIB_OBJS = \
blob.o commit.o connect.o csum-file.o \ blob.o commit.o connect.o csum-file.o gsimm.o rabinpoly.o \
date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \ date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \
object.o pack-check.o patch-delta.o path.o pkt-line.o \ object.o pack-check.o patch-delta.o path.o pkt-line.o \
quote.o read-cache.o refs.o run-command.o \ quote.o read-cache.o refs.o run-command.o \

10
pack-objects.c
View File

@ -8,6 +8,8 @@
#include "pack.h" #include "pack.h"
#include "csum-file.h" #include "csum-file.h"
#include "tree-walk.h" #include "tree-walk.h"
#include "rabinpoly.h"
#include "gsimm.h"
#include <sys/time.h> #include <sys/time.h>
#include <signal.h> #include <signal.h>
@ -993,6 +995,7 @@ static int type_size_sort(const struct object_entry *a, const struct object_entr
struct unpacked { struct unpacked {
struct object_entry *entry; struct object_entry *entry;
unsigned char fingerprint[MD_LENGTH];
void *data; void *data;
}; };
@ -1041,6 +1044,9 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de
if (old_entry->depth >= max_depth) if (old_entry->depth >= max_depth)
return 0; return 0;
if (gb_simm_score(cur->fingerprint, old->fingerprint) < 0.4)
return 0;
/* /*
* NOTE! * NOTE!
* *
@ -1077,6 +1083,7 @@ static void find_deltas(struct object_entry **list, int window, int depth)
unsigned processed = 0; unsigned processed = 0;
unsigned last_percent = 999; unsigned last_percent = 999;
rabin_reset ();
memset(array, 0, array_size); memset(array, 0, array_size);
i = nr_objects; i = nr_objects;
idx = 0; idx = 0;
@ -1115,6 +1122,8 @@ static void find_deltas(struct object_entry **list, int window, int depth)
if (size != entry->size) if (size != entry->size)
die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size); die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
gb_simm_process(n->data, size, n->fingerprint);
j = window; j = window;
while (--j > 0) { while (--j > 0) {
unsigned int other_idx = idx + j; unsigned int other_idx = idx + j;
@ -1124,6 +1133,7 @@ static void find_deltas(struct object_entry **list, int window, int depth)
m = array + other_idx; m = array + other_idx;
if (!m->entry) if (!m->entry)
break; break;
if (try_delta(n, m, depth) < 0) if (try_delta(n, m, depth) < 0)
break; break;
} }