1
0
mirror of https://github.com/git/git synced 2024-07-07 19:39:27 +00:00
git/builtin-diff.c
Junio C Hamano fb13227e08 git-diff: squelch "empty" diffs
After starting to edit a working tree file but later when your edit ends
up identical to the original (this can also happen when you ran a
wholesale regexp replace with something like "perl -i" that does not
actually modify many of the paths), "git diff" between the index and the
working tree outputs many "empty" diffs that show "diff --git" headers
and nothing else, because these paths are stat-dirty.  While it was a
way to warn the user that the earlier action of the user made the index
ineffective as an optimization mechanism, it was felt too loud for the
purpose of warning even to experienced users, and also resulted in
confusing people new to git.

This replaces the "empty" diffs with a single warning message at the
end.  Having many such paths hurts performance, and you can run
"git-update-index --refresh" to update the lstat(2) information recorded
in the index in such a case.  "git-status" does so as a side effect, and
that is more familiar to the end-user, so we recommend it to them.

The change affects only "git diff" that outputs patch text, because that
is where the annoyance of too many "empty" diff is most strongly felt,
and because the warning message can be safely ignored by downstream
tools without getting mistaken as part of the patch.  For the low-level
"git diff-files" and "git diff-index", the traditional behaviour is
retained.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-08-14 01:55:00 -07:00

357 lines
8.7 KiB
C

/*
* Builtin "git diff"
*
* Copyright (c) 2006 Junio C Hamano
*/
#include "cache.h"
#include "commit.h"
#include "blob.h"
#include "tag.h"
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
#include "log-tree.h"
#include "builtin.h"
struct blobinfo {
unsigned char sha1[20];
const char *name;
unsigned mode;
};
static const char builtin_diff_usage[] =
"git-diff <options> <rev>{0,2} -- <path>*";
static void stuff_change(struct diff_options *opt,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
const char *old_name,
const char *new_name)
{
struct diff_filespec *one, *two;
if (!is_null_sha1(old_sha1) && !is_null_sha1(new_sha1) &&
!hashcmp(old_sha1, new_sha1) && (old_mode == new_mode))
return;
if (opt->reverse_diff) {
unsigned tmp;
const unsigned char *tmp_u;
const char *tmp_c;
tmp = old_mode; old_mode = new_mode; new_mode = tmp;
tmp_u = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_u;
tmp_c = old_name; old_name = new_name; new_name = tmp_c;
}
one = alloc_filespec(old_name);
two = alloc_filespec(new_name);
fill_filespec(one, old_sha1, old_mode);
fill_filespec(two, new_sha1, new_mode);
/* NEEDSWORK: shouldn't this part of diffopt??? */
diff_queue(&diff_queued_diff, one, two);
}
static int builtin_diff_b_f(struct rev_info *revs,
int argc, const char **argv,
struct blobinfo *blob,
const char *path)
{
/* Blob vs file in the working tree*/
struct stat st;
if (argc > 1)
usage(builtin_diff_usage);
if (lstat(path, &st))
die("'%s': %s", path, strerror(errno));
if (!(S_ISREG(st.st_mode) || S_ISLNK(st.st_mode)))
die("'%s': not a regular file or symlink", path);
if (blob[0].mode == S_IFINVALID)
blob[0].mode = canon_mode(st.st_mode);
stuff_change(&revs->diffopt,
blob[0].mode, canon_mode(st.st_mode),
blob[0].sha1, null_sha1,
path, path);
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
return 0;
}
static int builtin_diff_blobs(struct rev_info *revs,
int argc, const char **argv,
struct blobinfo *blob)
{
unsigned mode = canon_mode(S_IFREG | 0644);
if (argc > 1)
usage(builtin_diff_usage);
if (blob[0].mode == S_IFINVALID)
blob[0].mode = mode;
if (blob[1].mode == S_IFINVALID)
blob[1].mode = mode;
stuff_change(&revs->diffopt,
blob[0].mode, blob[1].mode,
blob[0].sha1, blob[1].sha1,
blob[0].name, blob[1].name);
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
return 0;
}
static int builtin_diff_index(struct rev_info *revs,
int argc, const char **argv)
{
int cached = 0;
while (1 < argc) {
const char *arg = argv[1];
if (!strcmp(arg, "--cached"))
cached = 1;
else
usage(builtin_diff_usage);
argv++; argc--;
}
/*
* Make sure there is one revision (i.e. pending object),
* and there is no revision filtering parameters.
*/
if (revs->pending.nr != 1 ||
revs->max_count != -1 || revs->min_age != -1 ||
revs->max_age != -1)
usage(builtin_diff_usage);
if (read_cache() < 0) {
perror("read_cache");
return -1;
}
return run_diff_index(revs, cached);
}
static int builtin_diff_tree(struct rev_info *revs,
int argc, const char **argv,
struct object_array_entry *ent)
{
const unsigned char *(sha1[2]);
int swap = 0;
if (argc > 1)
usage(builtin_diff_usage);
/* We saw two trees, ent[0] and ent[1].
* if ent[1] is uninteresting, they are swapped
*/
if (ent[1].item->flags & UNINTERESTING)
swap = 1;
sha1[swap] = ent[0].item->sha1;
sha1[1-swap] = ent[1].item->sha1;
diff_tree_sha1(sha1[0], sha1[1], "", &revs->diffopt);
log_tree_diff_flush(revs);
return 0;
}
static int builtin_diff_combined(struct rev_info *revs,
int argc, const char **argv,
struct object_array_entry *ent,
int ents)
{
const unsigned char (*parent)[20];
int i;
if (argc > 1)
usage(builtin_diff_usage);
if (!revs->dense_combined_merges && !revs->combine_merges)
revs->dense_combined_merges = revs->combine_merges = 1;
parent = xmalloc(ents * sizeof(*parent));
/* Again, the revs are all reverse */
for (i = 0; i < ents; i++)
hashcpy((unsigned char *)(parent + i),
ent[ents - 1 - i].item->sha1);
diff_tree_combined(parent[0], parent + 1, ents - 1,
revs->dense_combined_merges, revs);
return 0;
}
void add_head(struct rev_info *revs)
{
unsigned char sha1[20];
struct object *obj;
if (get_sha1("HEAD", sha1))
return;
obj = parse_object(sha1);
if (!obj)
return;
add_pending_object(revs, obj, "HEAD");
}
int cmd_diff(int argc, const char **argv, const char *prefix)
{
int i;
struct rev_info rev;
struct object_array_entry ent[100];
int ents = 0, blobs = 0, paths = 0;
const char *path = NULL;
struct blobinfo blob[2];
int nongit = 0;
int result = 0;
/*
* We could get N tree-ish in the rev.pending_objects list.
* Also there could be M blobs there, and P pathspecs.
*
* N=0, M=0:
* cache vs files (diff-files)
* N=0, M=2:
* compare two random blobs. P must be zero.
* N=0, M=1, P=1:
* compare a blob with a working tree file.
*
* N=1, M=0:
* tree vs cache (diff-index --cached)
*
* N=2, M=0:
* tree vs tree (diff-tree)
*
* Other cases are errors.
*/
prefix = setup_git_directory_gently(&nongit);
git_config(git_diff_ui_config);
init_revisions(&rev, prefix);
rev.diffopt.skip_stat_unmatch = 1;
if (!setup_diff_no_index(&rev, argc, argv, nongit, prefix))
argc = 0;
else
argc = setup_revisions(argc, argv, &rev, NULL);
if (!rev.diffopt.output_format) {
rev.diffopt.output_format = DIFF_FORMAT_PATCH;
if (diff_setup_done(&rev.diffopt) < 0)
die("diff_setup_done failed");
}
rev.diffopt.allow_external = 1;
rev.diffopt.recursive = 1;
/* If the user asked for our exit code then don't start a
* pager or we would end up reporting its exit code instead.
*/
if (!rev.diffopt.exit_with_status)
setup_pager();
/* Do we have --cached and not have a pending object, then
* default to HEAD by hand. Eek.
*/
if (!rev.pending.nr) {
int i;
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
if (!strcmp(arg, "--"))
break;
else if (!strcmp(arg, "--cached")) {
add_head(&rev);
if (!rev.pending.nr)
die("No HEAD commit to compare with (yet)");
break;
}
}
}
for (i = 0; i < rev.pending.nr; i++) {
struct object_array_entry *list = rev.pending.objects+i;
struct object *obj = list->item;
const char *name = list->name;
int flags = (obj->flags & UNINTERESTING);
if (!obj->parsed)
obj = parse_object(obj->sha1);
obj = deref_tag(obj, NULL, 0);
if (!obj)
die("invalid object '%s' given.", name);
if (obj->type == OBJ_COMMIT)
obj = &((struct commit *)obj)->tree->object;
if (obj->type == OBJ_TREE) {
if (ARRAY_SIZE(ent) <= ents)
die("more than %d trees given: '%s'",
(int) ARRAY_SIZE(ent), name);
obj->flags |= flags;
ent[ents].item = obj;
ent[ents].name = name;
ents++;
continue;
}
if (obj->type == OBJ_BLOB) {
if (2 <= blobs)
die("more than two blobs given: '%s'", name);
hashcpy(blob[blobs].sha1, obj->sha1);
blob[blobs].name = name;
blob[blobs].mode = list->mode;
blobs++;
continue;
}
die("unhandled object '%s' given.", name);
}
if (rev.prune_data) {
const char **pathspec = rev.prune_data;
while (*pathspec) {
if (!path)
path = *pathspec;
paths++;
pathspec++;
}
}
/*
* Now, do the arguments look reasonable?
*/
if (!ents) {
switch (blobs) {
case 0:
result = run_diff_files_cmd(&rev, argc, argv);
break;
case 1:
if (paths != 1)
usage(builtin_diff_usage);
result = builtin_diff_b_f(&rev, argc, argv, blob, path);
break;
case 2:
if (paths)
usage(builtin_diff_usage);
result = builtin_diff_blobs(&rev, argc, argv, blob);
break;
default:
usage(builtin_diff_usage);
}
}
else if (blobs)
usage(builtin_diff_usage);
else if (ents == 1)
result = builtin_diff_index(&rev, argc, argv);
else if (ents == 2)
result = builtin_diff_tree(&rev, argc, argv, ent);
else if ((ents == 3) && (ent[0].item->flags & UNINTERESTING)) {
/* diff A...B where there is one sane merge base between
* A and B. We have ent[0] == merge-base, ent[1] == A,
* and ent[2] == B. Show diff between the base and B.
*/
ent[1] = ent[2];
result = builtin_diff_tree(&rev, argc, argv, ent);
}
else
result = builtin_diff_combined(&rev, argc, argv,
ent, ents);
if (rev.diffopt.exit_with_status)
result = rev.diffopt.has_changes;
if ((rev.diffopt.output_format & DIFF_FORMAT_PATCH)
&& (1 < rev.diffopt.skip_stat_unmatch))
printf("Warning: %d path%s touched but unmodified. "
"Consider running git-status.\n",
rev.diffopt.skip_stat_unmatch - 1,
rev.diffopt.skip_stat_unmatch == 2 ? "" : "s");
return result;
}