1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-11-05 08:47:56 +01:00
git/diff-lib.c

372 lines
8.7 KiB
C
Raw Normal View History

/*
* Copyright (C) 2005 Junio C Hamano
*/
#include "cache.h"
#include "quote.h"
#include "commit.h"
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
/*
* diff-files
*/
int run_diff_files(struct rev_info *revs, int silent_on_removed)
{
int entries, i;
int diff_unmerged_stage = revs->max_count;
if (diff_unmerged_stage < 0)
diff_unmerged_stage = 2;
entries = read_cache();
if (entries < 0) {
perror("read_cache");
return -1;
}
for (i = 0; i < entries; i++) {
struct stat st;
unsigned int oldmode, newmode;
struct cache_entry *ce = active_cache[i];
int changed;
if (!ce_path_match(ce, revs->prune_data))
continue;
if (ce_stage(ce)) {
struct combine_diff_path *dpath;
int num_compare_stages = 0;
size_t path_len;
path_len = ce_namelen(ce);
dpath = xmalloc (combine_diff_path_size (5, path_len));
dpath->path = (char *) &(dpath->parent[5]);
dpath->next = NULL;
dpath->len = path_len;
memcpy(dpath->path, ce->name, path_len);
dpath->path[path_len] = '\0';
dpath->mode = 0;
hashclr(dpath->sha1);
memset(&(dpath->parent[0]), 0,
sizeof(struct combine_diff_parent)*5);
while (i < entries) {
struct cache_entry *nce = active_cache[i];
int stage;
if (strcmp(ce->name, nce->name))
break;
/* Stage #2 (ours) is the first parent,
* stage #3 (theirs) is the second.
*/
stage = ce_stage(nce);
if (2 <= stage) {
int mode = ntohl(nce->ce_mode);
num_compare_stages++;
hashcpy(dpath->parent[stage-2].sha1, nce->sha1);
dpath->parent[stage-2].mode =
canon_mode(mode);
dpath->parent[stage-2].status =
DIFF_STATUS_MODIFIED;
}
/* diff against the proper unmerged stage */
if (stage == diff_unmerged_stage)
ce = nce;
i++;
}
/*
* Compensate for loop update
*/
i--;
if (revs->combine_merges && num_compare_stages == 2) {
show_combined_diff(dpath, 2,
revs->dense_combined_merges,
revs);
free(dpath);
continue;
}
free(dpath);
dpath = NULL;
/*
* Show the diff for the 'ce' if we found the one
* from the desired stage.
*/
diff_unmerge(&revs->diffopt, ce->name);
if (ce_stage(ce) != diff_unmerged_stage)
continue;
[PATCH] diff: Update -B heuristics. As Linus pointed out on the mailing list discussion, -B should break a files that has many inserts even if it still keeps enough of the original contents, so that the broken pieces can later be matched with other files by -M or -C. However, if such a broken pair does not get picked up by -M or -C, we would want to apply different criteria; namely, regardless of the amount of new material in the result, the determination of "rewrite" should be done by looking at the amount of original material still left in the result. If you still have the original 97 lines from a 100-line document, it does not matter if you add your own 13 lines to make a 110-line document, or if you add 903 lines to make a 1000-line document. It is not a rewrite but an in-place edit. On the other hand, if you did lose 97 lines from the original, it does not matter if you added 27 lines to make a 30-line document or if you added 997 lines to make a 1000-line document. You did a complete rewrite in either case. This patch introduces a post-processing phase that runs after diffcore-rename matches up broken pairs diffcore-break creates. The purpose of this post-processing is to pick up these broken pieces and merge them back into in-place modifications. For this, the score parameter -B option takes is changed into a pair of numbers, and it takes "-B99/80" format when fully spelled out. The first number is the minimum amount of "edit" (same definition as what diffcore-rename uses, which is "sum of deletion and insertion") that a modification needs to have to be broken, and the second number is the minimum amount of "delete" a surviving broken pair must have to avoid being merged back together. It can be abbreviated to "-B" to use default for both, "-B9" or "-B9/" to use 90% for "edit" but default (80%) for merge avoidance, or "-B/75" to use default (99%) "edit" and 75% for merge avoidance. Signed-off-by: Junio C Hamano <junkio@cox.net> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-03 10:40:28 +02:00
}
if (lstat(ce->name, &st) < 0) {
if (errno != ENOENT && errno != ENOTDIR) {
perror(ce->name);
continue;
}
if (silent_on_removed)
continue;
diff_addremove(&revs->diffopt, '-', ntohl(ce->ce_mode),
ce->sha1, ce->name, NULL);
continue;
}
changed = ce_match_stat(ce, &st, 0);
if (!changed && !revs->diffopt.find_copies_harder)
continue;
oldmode = ntohl(ce->ce_mode);
newmode = canon_mode(st.st_mode);
if (!trust_executable_bit &&
S_ISREG(newmode) && S_ISREG(oldmode) &&
((newmode ^ oldmode) == 0111))
newmode = oldmode;
diff_change(&revs->diffopt, oldmode, newmode,
ce->sha1, (changed ? null_sha1 : ce->sha1),
ce->name, NULL);
}
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
return 0;
}
/*
* diff-index
*/
/* A file entry went away or appeared */
static void diff_index_show_file(struct rev_info *revs,
const char *prefix,
struct cache_entry *ce,
unsigned char *sha1, unsigned int mode)
{
diff_addremove(&revs->diffopt, prefix[0], ntohl(mode),
sha1, ce->name, NULL);
}
static int get_stat_data(struct cache_entry *ce,
unsigned char **sha1p,
unsigned int *modep,
int cached, int match_missing)
{
unsigned char *sha1 = ce->sha1;
unsigned int mode = ce->ce_mode;
if (!cached) {
static unsigned char no_sha1[20];
int changed;
struct stat st;
if (lstat(ce->name, &st) < 0) {
if (errno == ENOENT && match_missing) {
*sha1p = sha1;
*modep = mode;
return 0;
}
return -1;
}
changed = ce_match_stat(ce, &st, 0);
if (changed) {
mode = create_ce_mode(st.st_mode);
if (!trust_executable_bit && S_ISREG(st.st_mode))
mode = ce->ce_mode;
sha1 = no_sha1;
}
}
*sha1p = sha1;
*modep = mode;
return 0;
}
static void show_new_file(struct rev_info *revs,
struct cache_entry *new,
int cached, int match_missing)
{
unsigned char *sha1;
unsigned int mode;
/* New file in the index: it might actually be different in
* the working copy.
*/
if (get_stat_data(new, &sha1, &mode, cached, match_missing) < 0)
return;
diff_index_show_file(revs, "+", new, sha1, mode);
}
static int show_modified(struct rev_info *revs,
struct cache_entry *old,
struct cache_entry *new,
int report_missing,
int cached, int match_missing)
{
unsigned int mode, oldmode;
unsigned char *sha1;
if (get_stat_data(new, &sha1, &mode, cached, match_missing) < 0) {
if (report_missing)
diff_index_show_file(revs, "-", old,
old->sha1, old->ce_mode);
return -1;
}
if (revs->combine_merges && !cached &&
(hashcmp(sha1, old->sha1) || hashcmp(old->sha1, new->sha1))) {
struct combine_diff_path *p;
int pathlen = ce_namelen(new);
p = xmalloc(combine_diff_path_size(2, pathlen));
p->path = (char *) &p->parent[2];
p->next = NULL;
p->len = pathlen;
memcpy(p->path, new->name, pathlen);
p->path[pathlen] = 0;
p->mode = ntohl(mode);
hashclr(p->sha1);
memset(p->parent, 0, 2 * sizeof(struct combine_diff_parent));
p->parent[0].status = DIFF_STATUS_MODIFIED;
p->parent[0].mode = ntohl(new->ce_mode);
hashcpy(p->parent[0].sha1, new->sha1);
p->parent[1].status = DIFF_STATUS_MODIFIED;
p->parent[1].mode = ntohl(old->ce_mode);
hashcpy(p->parent[1].sha1, old->sha1);
show_combined_diff(p, 2, revs->dense_combined_merges, revs);
free(p);
return 0;
}
oldmode = old->ce_mode;
if (mode == oldmode && !hashcmp(sha1, old->sha1) &&
!revs->diffopt.find_copies_harder)
return 0;
mode = ntohl(mode);
oldmode = ntohl(oldmode);
diff_change(&revs->diffopt, oldmode, mode,
old->sha1, sha1, old->name, NULL);
return 0;
}
static int diff_cache(struct rev_info *revs,
struct cache_entry **ac, int entries,
const char **pathspec,
int cached, int match_missing)
{
while (entries) {
struct cache_entry *ce = *ac;
int same = (entries > 1) && ce_same_name(ce, ac[1]);
if (!ce_path_match(ce, pathspec))
goto skip_entry;
switch (ce_stage(ce)) {
case 0:
/* No stage 1 entry? That means it's a new file */
if (!same) {
show_new_file(revs, ce, cached, match_missing);
break;
}
/* Show difference between old and new */
show_modified(revs,ac[1], ce, 1,
cached, match_missing);
break;
case 1:
/* No stage 3 (merge) entry?
* That means it's been deleted.
*/
if (!same) {
diff_index_show_file(revs, "-", ce,
ce->sha1, ce->ce_mode);
break;
}
/* We come here with ce pointing at stage 1
* (original tree) and ac[1] pointing at stage
* 3 (unmerged). show-modified with
* report-missing set to false does not say the
* file is deleted but reports true if work
* tree does not have it, in which case we
* fall through to report the unmerged state.
* Otherwise, we show the differences between
* the original tree and the work tree.
*/
if (!cached &&
!show_modified(revs, ce, ac[1], 0,
cached, match_missing))
break;
/* fallthru */
case 3:
diff_unmerge(&revs->diffopt, ce->name);
break;
default:
die("impossible cache entry stage");
}
skip_entry:
/*
* Ignore all the different stages for this file,
* we've handled the relevant cases now.
*/
do {
ac++;
entries--;
} while (entries && ce_same_name(ce, ac[0]));
}
return 0;
}
/*
* This turns all merge entries into "stage 3". That guarantees that
* when we read in the new tree (into "stage 1"), we won't lose sight
* of the fact that we had unmerged entries.
*/
static void mark_merge_entries(void)
{
int i;
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
if (!ce_stage(ce))
continue;
ce->ce_flags |= htons(CE_STAGEMASK);
}
}
int run_diff_index(struct rev_info *revs, int cached)
{
int ret;
struct object *ent;
struct tree *tree;
const char *tree_name;
int match_missing = 0;
/*
* Backward compatibility wart - "diff-index -m" does
* not mean "do not ignore merges", but totally different.
*/
if (!revs->ignore_merges)
match_missing = 1;
if (read_cache() < 0) {
perror("read_cache");
return -1;
}
mark_merge_entries();
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 02:42:35 +02:00
ent = revs->pending.objects[0].item;
tree_name = revs->pending.objects[0].name;
tree = parse_tree_indirect(ent->sha1);
if (!tree)
return error("bad tree object %s", tree_name);
if (read_tree(tree, 1, revs->prune_data))
return error("unable to read tree object %s", tree_name);
ret = diff_cache(revs, active_cache, active_nr, revs->prune_data,
cached, match_missing);
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
return ret;
}