git/builtin/diff.c

472 строки
12 KiB
C
Исходник Обычный вид История

/*
* Builtin "git diff"
*
* Copyright (c) 2006 Junio C Hamano
*/
#include "cache.h"
#include "lockfile.h"
#include "color.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"
#include "submodule.h"
#include "sha1-array.h"
#define DIFF_NO_INDEX_EXPLICIT 1
#define DIFF_NO_INDEX_IMPLICIT 2
struct blobinfo {
struct object_id oid;
const char *name;
unsigned mode;
};
static const char builtin_diff_usage[] =
"git diff [<options>] [<commit> [<commit>]] [--] [<path>...]";
static void stuff_change(struct diff_options *opt,
unsigned old_mode, unsigned new_mode,
const struct object_id *old_oid,
const struct object_id *new_oid,
int old_oid_valid,
int new_oid_valid,
const char *old_name,
const char *new_name)
{
struct diff_filespec *one, *two;
if (!is_null_oid(old_oid) && !is_null_oid(new_oid) &&
!oidcmp(old_oid, new_oid) && (old_mode == new_mode))
return;
if (DIFF_OPT_TST(opt, REVERSE_DIFF)) {
SWAP(old_mode, new_mode);
SWAP(old_oid, new_oid);
SWAP(old_name, new_name);
}
diff --relative: output paths as relative to the current subdirectory This adds --relative option to the diff family. When you start from a subdirectory: $ git diff --relative shows only the diff that is inside your current subdirectory, and without $prefix part. People who usually live in subdirectories may like it. There are a few things I should also mention about the change: - This works not just with diff but also works with the log family of commands, but the history pruning is not affected. In other words, if you go to a subdirectory, you can say: $ git log --relative -p but it will show the log message even for commits that do not touch the current directory. You can limit it by giving pathspec yourself: $ git log --relative -p . This originally was not a conscious design choice, but we have a way to affect diff pathspec and pruning pathspec independently. IOW "git log --full-diff -p ." tells it to prune history to commits that affect the current subdirectory but show the changes with full context. I think it makes more sense to leave pruning independent from --relative than the obvious alternative of always pruning with the current subdirectory, which would break the symmetry. - Because this works also with the log family, you could format-patch a single change, limiting the effect to your subdirectory, like so: $ cd gitk-git $ git format-patch -1 --relative 911f1eb But because that is a special purpose usage, this option will never become the default, with or without repository or user preference configuration. The risk of producing a partial patch and sending it out by mistake is too great if we did so. - This is inherently incompatible with --no-index, which is a bolted-on hack that does not have much to do with git itself. I didn't bother checking and erroring out on the combined use of the options, but probably I should. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-13 01:26:02 +03:00
if (opt->prefix &&
(strncmp(old_name, opt->prefix, opt->prefix_length) ||
strncmp(new_name, opt->prefix, opt->prefix_length)))
return;
one = alloc_filespec(old_name);
two = alloc_filespec(new_name);
fill_filespec(one, old_oid->hash, old_oid_valid, old_mode);
fill_filespec(two, new_oid->hash, new_oid_valid, new_mode);
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)
{
/* Blob vs file in the working tree*/
struct stat st;
const char *path;
if (argc > 1)
usage(builtin_diff_usage);
GUARD_PATHSPEC(&revs->prune_data, PATHSPEC_FROMTOP | PATHSPEC_LITERAL);
path = revs->prune_data.items[0].match;
if (lstat(path, &st))
die_errno(_("failed to stat '%s'"), path);
if (!(S_ISREG(st.st_mode) || S_ISLNK(st.st_mode)))
die(_("'%s': not a regular file or symlink"), path);
diff_set_mnemonic_prefix(&revs->diffopt, "o/", "w/");
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].oid, &null_oid,
diff: do not use null sha1 as a sentinel value The diff code represents paths using the diff_filespec struct. This struct has a sha1 to represent the sha1 of the content at that path, as well as a sha1_valid member which indicates whether its sha1 field is actually useful. If sha1_valid is not true, then the filespec represents a working tree file (e.g., for the no-index case, or for when the index is not up-to-date). The diff_filespec is only used internally, though. At the interfaces to the diff subsystem, callers feed the sha1 directly, and we create a diff_filespec from it. It's at that point that we look at the sha1 and decide whether it is valid or not; callers may pass the null sha1 as a sentinel value to indicate that it is not. We should not typically see the null sha1 coming from any other source (e.g., in the index itself, or from a tree). However, a corrupt tree might have a null sha1, which would cause "diff --patch" to accidentally diff the working tree version of a file instead of treating it as a blob. This patch extends the edges of the diff interface to accept a "sha1_valid" flag whenever we accept a sha1, and to use that flag when creating a filespec. In some cases, this means passing the flag through several layers, making the code change larger than would be desirable. One alternative would be to simply die() upon seeing corrupted trees with null sha1s. However, this fix more directly addresses the problem (while bogus sha1s in a tree are probably a bad thing, it is really the sentinel confusion sending us down the wrong code path that is what makes it devastating). And it means that git is more capable of examining and debugging these corrupted trees. For example, you can still "diff --raw" such a tree to find out when the bogus entry was introduced; you just cannot do a "--patch" diff (just as you could not with any other corrupted tree, as we do not have any content to diff). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-28 19:03:01 +04:00
1, 0,
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].oid, &blob[1].oid,
diff: do not use null sha1 as a sentinel value The diff code represents paths using the diff_filespec struct. This struct has a sha1 to represent the sha1 of the content at that path, as well as a sha1_valid member which indicates whether its sha1 field is actually useful. If sha1_valid is not true, then the filespec represents a working tree file (e.g., for the no-index case, or for when the index is not up-to-date). The diff_filespec is only used internally, though. At the interfaces to the diff subsystem, callers feed the sha1 directly, and we create a diff_filespec from it. It's at that point that we look at the sha1 and decide whether it is valid or not; callers may pass the null sha1 as a sentinel value to indicate that it is not. We should not typically see the null sha1 coming from any other source (e.g., in the index itself, or from a tree). However, a corrupt tree might have a null sha1, which would cause "diff --patch" to accidentally diff the working tree version of a file instead of treating it as a blob. This patch extends the edges of the diff interface to accept a "sha1_valid" flag whenever we accept a sha1, and to use that flag when creating a filespec. In some cases, this means passing the flag through several layers, making the code change larger than would be desirable. One alternative would be to simply die() upon seeing corrupted trees with null sha1s. However, this fix more directly addresses the problem (while bogus sha1s in a tree are probably a bad thing, it is really the sentinel confusion sending us down the wrong code path that is what makes it devastating). And it means that git is more capable of examining and debugging these corrupted trees. For example, you can still "diff --raw" such a tree to find out when the bogus entry was introduced; you just cannot do a "--patch" diff (just as you could not with any other corrupted tree, as we do not have any content to diff). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-07-28 19:03:01 +04:00
1, 1,
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") || !strcmp(arg, "--staged"))
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.
*/
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 04:42:35 +04:00
if (revs->pending.nr != 1 ||
revs->max_count != -1 || revs->min_age != -1 ||
revs->max_age != -1)
usage(builtin_diff_usage);
if (!cached) {
setup_work_tree();
if (read_cache_preload(&revs->diffopt.pathspec) < 0) {
perror("read_cache_preload");
return -1;
}
} else 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 *ent0,
struct object_array_entry *ent1)
{
const struct object_id *(oid[2]);
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 04:42:35 +04:00
int swap = 0;
if (argc > 1)
usage(builtin_diff_usage);
/*
* We saw two trees, ent0 and ent1. If ent1 is uninteresting,
* swap them.
*/
if (ent1->item->flags & UNINTERESTING)
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 04:42:35 +04:00
swap = 1;
oid[swap] = &ent0->item->oid;
oid[1 - swap] = &ent1->item->oid;
diff_tree_sha1(oid[0]->hash, oid[1]->hash, "", &revs->diffopt);
log_tree_diff_flush(revs);
return 0;
}
static int builtin_diff_combined(struct rev_info *revs,
int argc, const char **argv,
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 04:42:35 +04:00
struct object_array_entry *ent,
int ents)
{
struct oid_array parents = OID_ARRAY_INIT;
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;
for (i = 1; i < ents; i++)
oid_array_append(&parents, &ent[i].item->oid);
diff_tree_combined(ent[0].item->oid.hash, &parents,
revs->dense_combined_merges, revs);
oid_array_clear(&parents);
return 0;
}
static void refresh_index_quietly(void)
{
struct lock_file *lock_file;
int fd;
lock_file = xcalloc(1, sizeof(struct lock_file));
fd = hold_locked_index(lock_file, 0);
if (fd < 0)
return;
discard_cache();
read_cache();
refresh_cache(REFRESH_QUIET|REFRESH_UNMERGED);
update_index_if_able(&the_index, lock_file);
}
static int builtin_diff_files(struct rev_info *revs, int argc, const char **argv)
{
unsigned int options = 0;
while (1 < argc && argv[1][0] == '-') {
if (!strcmp(argv[1], "--base"))
revs->max_count = 1;
else if (!strcmp(argv[1], "--ours"))
revs->max_count = 2;
else if (!strcmp(argv[1], "--theirs"))
revs->max_count = 3;
else if (!strcmp(argv[1], "-q"))
options |= DIFF_SILENT_ON_REMOVED;
else if (!strcmp(argv[1], "-h"))
usage(builtin_diff_usage);
else
return error(_("invalid option: %s"), argv[1]);
argv++; argc--;
}
/*
* "diff --base" should not combine merges because it was not
* asked to. "diff -c" should not densify (if the user wants
* dense one, --cc can be explicitly asked for, or just rely
* on the default).
*/
if (revs->max_count == -1 && !revs->combine_merges &&
(revs->diffopt.output_format & DIFF_FORMAT_PATCH))
revs->combine_merges = revs->dense_combined_merges = 1;
setup_work_tree();
if (read_cache_preload(&revs->diffopt.pathspec) < 0) {
perror("read_cache_preload");
return -1;
}
return run_diff_files(revs, options);
}
int cmd_diff(int argc, const char **argv, const char *prefix)
{
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 04:42:35 +04:00
int i;
struct rev_info rev;
struct object_array ent = OBJECT_ARRAY_INIT;
int blobs = 0, paths = 0;
struct blobinfo blob[2];
int nongit = 0, no_index = 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)
*
* N=0, M=0, P=2:
* compare two filesystem entities (aka --no-index).
*
* Other cases are errors.
*/
/* Were we asked to do --no-index explicitly? */
for (i = 1; i < argc; i++) {
if (!strcmp(argv[i], "--")) {
i++;
break;
}
if (!strcmp(argv[i], "--no-index"))
no_index = DIFF_NO_INDEX_EXPLICIT;
if (argv[i][0] != '-')
break;
}
diff: always try to set up the repository If we see an explicit "--no-index", we do not bother calling setup_git_directory_gently() at all. This means that we may miss out on reading repo-specific config. It's arguable whether this is correct or not. If we were designing from scratch, making "git diff --no-index" completely ignore the repository makes some sense. But we are nowhere near scratch, so let's look at the existing behavior: 1. If you're in the top-level of a repository and run an explicit "diff --no-index", the config subsystem falls back to reading ".git/config", and we will respect repo config. 2. If you're in a subdirectory of a repository, then we still try to read ".git/config", but it generally doesn't exist. So "diff --no-index" there does not respect repo config. 3. If you have $GIT_DIR set in the environment, we read and respect $GIT_DIR/config, 4. If you run "git diff /tmp/foo /tmp/bar" to get an implicit no-index, we _do_ run the repository setup, and set $GIT_DIR (or respect an existing $GIT_DIR variable). We find the repo config no matter where we started, and respect it. So we already respect the repository config in a number of common cases, and case (2) is the only one that does not. And at least one of our tests, t4034, depends on case (1) behaving as it does now (though it is just incidental, not an explicit test for this behavior). So let's bring case (2) in line with the others by always running the repository setup, even with an explicit "--no-index". We shouldn't need to change anything else, as the implicit case already handles the prefix. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-13 06:23:36 +03:00
prefix = setup_git_directory_gently(&nongit);
diff: always try to set up the repository If we see an explicit "--no-index", we do not bother calling setup_git_directory_gently() at all. This means that we may miss out on reading repo-specific config. It's arguable whether this is correct or not. If we were designing from scratch, making "git diff --no-index" completely ignore the repository makes some sense. But we are nowhere near scratch, so let's look at the existing behavior: 1. If you're in the top-level of a repository and run an explicit "diff --no-index", the config subsystem falls back to reading ".git/config", and we will respect repo config. 2. If you're in a subdirectory of a repository, then we still try to read ".git/config", but it generally doesn't exist. So "diff --no-index" there does not respect repo config. 3. If you have $GIT_DIR set in the environment, we read and respect $GIT_DIR/config, 4. If you run "git diff /tmp/foo /tmp/bar" to get an implicit no-index, we _do_ run the repository setup, and set $GIT_DIR (or respect an existing $GIT_DIR variable). We find the repo config no matter where we started, and respect it. So we already respect the repository config in a number of common cases, and case (2) is the only one that does not. And at least one of our tests, t4034, depends on case (1) behaving as it does now (though it is just incidental, not an explicit test for this behavior). So let's bring case (2) in line with the others by always running the repository setup, even with an explicit "--no-index". We shouldn't need to change anything else, as the implicit case already handles the prefix. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-13 06:23:36 +03:00
if (!no_index) {
/*
* Treat git diff with at least one path outside of the
* repo the same as if the command would have been executed
* outside of a git repository. In this case it behaves
* the same way as "git diff --no-index <a> <b>", which acts
* as a colourful "diff" replacement.
*/
if (nongit || ((argc == i + 2) &&
(!path_inside_repo(prefix, argv[i]) ||
!path_inside_repo(prefix, argv[i + 1]))))
no_index = DIFF_NO_INDEX_IMPLICIT;
}
if (!no_index)
gitmodules_config();
init_diff_ui_defaults();
git_config(git_diff_ui_config, NULL);
precompose_argv(argc, argv);
init_revisions(&rev, prefix);
if (no_index && argc != i + 2) {
if (no_index == DIFF_NO_INDEX_IMPLICIT) {
/*
* There was no --no-index and there were not two
* paths. It is possible that the user intended
* to do an inside-repository operation.
*/
fprintf(stderr, "Not a git repository\n");
fprintf(stderr,
"To compare two paths outside a working tree:\n");
}
/* Give the usage message for non-repository usage and exit. */
usagef("git diff %s <path> <path>",
no_index == DIFF_NO_INDEX_EXPLICIT ?
"--no-index" : "[--no-index]");
}
if (no_index)
/* If this is a no-index diff, just run it and exit there. */
diff_no_index(&rev, argc, argv);
/* Otherwise, we are doing the usual "git" diff */
rev.diffopt.skip_stat_unmatch = !!diff_auto_refresh_index;
/* Scale to real terminal size and respect statGraphWidth config */
rev.diffopt.stat_width = -1;
rev.diffopt.stat_graph_width = -1;
/* Default to let external and textconv be used */
DIFF_OPT_SET(&rev.diffopt, ALLOW_EXTERNAL);
DIFF_OPT_SET(&rev.diffopt, ALLOW_TEXTCONV);
if (nongit)
die(_("Not a git repository"));
argc = setup_revisions(argc, argv, &rev, NULL);
if (!rev.diffopt.output_format) {
rev.diffopt.output_format = DIFF_FORMAT_PATCH;
diff_setup_done(&rev.diffopt);
}
DIFF_OPT_SET(&rev.diffopt, RECURSIVE);
setup_diff_pager(&rev.diffopt);
/*
* Do we have --cached and not have a pending object, then
* default to HEAD by hand. Eek.
*/
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 04:42:35 +04:00
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") ||
!strcmp(arg, "--staged")) {
add_head_to_pending(&rev);
if (!rev.pending.nr) {
struct tree *tree;
tree = lookup_tree(&empty_tree_oid);
add_pending_object(&rev, &tree->object, "HEAD");
}
break;
}
}
}
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 04:42:35 +04:00
for (i = 0; i < rev.pending.nr; i++) {
struct object_array_entry *entry = &rev.pending.objects[i];
struct object *obj = entry->item;
const char *name = entry->name;
int flags = (obj->flags & UNINTERESTING);
if (!obj->parsed)
obj = parse_object(&obj->oid);
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) {
obj->flags |= flags;
add_object_array(obj, name, &ent);
} else if (obj->type == OBJ_BLOB) {
if (2 <= blobs)
die(_("more than two blobs given: '%s'"), name);
oidcpy(&blob[blobs].oid, &obj->oid);
blob[blobs].name = name;
blob[blobs].mode = entry->mode;
blobs++;
} else {
die(_("unhandled object '%s' given."), name);
}
}
if (rev.prune_data.nr)
paths += rev.prune_data.nr;
/*
* Now, do the arguments look reasonable?
*/
if (!ent.nr) {
switch (blobs) {
case 0:
result = builtin_diff_files(&rev, argc, argv);
break;
case 1:
if (paths != 1)
usage(builtin_diff_usage);
result = builtin_diff_b_f(&rev, argc, argv, blob);
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 (ent.nr == 1)
result = builtin_diff_index(&rev, argc, argv);
else if (ent.nr == 2)
result = builtin_diff_tree(&rev, argc, argv,
&ent.objects[0], &ent.objects[1]);
else if (ent.objects[0].item->flags & UNINTERESTING) {
/*
* diff A...B where there is at least one merge base
* between A and B. We have ent.objects[0] ==
* merge-base, ent.objects[ents-2] == A, and
* ent.objects[ents-1] == B. Show diff between the
* base and B. Note that we pick one merge base at
* random if there are more than one.
*/
result = builtin_diff_tree(&rev, argc, argv,
&ent.objects[0],
&ent.objects[ent.nr-1]);
} else
result = builtin_diff_combined(&rev, argc, argv,
ent.objects, ent.nr);
result = diff_result_code(&rev.diffopt, result);
if (1 < rev.diffopt.skip_stat_unmatch)
refresh_index_quietly();
return result;
}