git/builtin/diff.c

619 lines
16 KiB
C
Raw Normal View History

/*
* Builtin "git diff"
*
* Copyright (c) 2006 Junio C Hamano
*/
#define USE_THE_INDEX_VARIABLE
#include "builtin.h"
#include "config.h"
#include "ewah/ewok.h"
#include "lockfile.h"
#include "color.h"
#include "commit.h"
#include "blob.h"
#include "gettext.h"
#include "tag.h"
#include "diff.h"
#include "diff-merges.h"
#include "diffcore.h"
#include "preload-index.h"
#include "read-cache-ll.h"
#include "revision.h"
#include "log-tree.h"
#include "setup.h"
#include "submodule.h"
#include "oid-array.h"
#include "tree.h"
#define DIFF_NO_INDEX_EXPLICIT 1
#define DIFF_NO_INDEX_IMPLICIT 2
static const char builtin_diff_usage[] =
"git diff [<options>] [<commit>] [--] [<path>...]\n"
" or: git diff [<options>] --cached [--merge-base] [<commit>] [--] [<path>...]\n"
" or: git diff [<options>] [--merge-base] <commit> [<commit>...] <commit> [--] [<path>...]\n"
" or: git diff [<options>] <commit>...<commit> [--] [<path>...]\n"
" or: git diff [<options>] <blob> <blob>\n"
" or: git diff [<options>] --no-index [--] <path> <path>"
"\n"
COMMON_DIFF_OPTIONS_HELP;
static const char *blob_path(struct object_array_entry *entry)
{
return entry->path ? entry->path : entry->name;
}
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_path,
const char *new_path)
{
struct diff_filespec *one, *two;
if (!is_null_oid(old_oid) && !is_null_oid(new_oid) &&
oideq(old_oid, new_oid) && (old_mode == new_mode))
return;
diff: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 18:19:11 +00:00
if (opt->flags.reverse_diff) {
SWAP(old_mode, new_mode);
SWAP(old_oid, new_oid);
SWAP(old_path, new_path);
}
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>
2008-02-12 22:26:02 +00:00
if (opt->prefix &&
(strncmp(old_path, opt->prefix, opt->prefix_length) ||
strncmp(new_path, opt->prefix, opt->prefix_length)))
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>
2008-02-12 22:26:02 +00:00
return;
one = alloc_filespec(old_path);
two = alloc_filespec(new_path);
fill_filespec(one, old_oid, old_oid_valid, old_mode);
fill_filespec(two, new_oid, new_oid_valid, new_mode);
diff_queue(&diff_queued_diff, one, two);
}
static void builtin_diff_b_f(struct rev_info *revs,
int argc, const char **argv UNUSED,
struct object_array_entry **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]->item->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 15:03:01 +00:00
1, 0,
blob[0]->path ? blob[0]->path : path,
path);
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
}
static void builtin_diff_blobs(struct rev_info *revs,
int argc, const char **argv UNUSED,
struct object_array_entry **blob)
{
const 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]->item->oid, &blob[1]->item->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 15:03:01 +00:00
1, 1,
blob_path(blob[0]), blob_path(blob[1]));
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
}
static void builtin_diff_index(struct rev_info *revs,
int argc, const char **argv)
{
unsigned int option = 0;
while (1 < argc) {
const char *arg = argv[1];
if (!strcmp(arg, "--cached") || !strcmp(arg, "--staged"))
option |= DIFF_INDEX_CACHED;
else if (!strcmp(arg, "--merge-base"))
option |= DIFF_INDEX_MERGE_BASE;
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 00:42:35 +00:00
if (revs->pending.nr != 1 ||
revs->max_count != -1 || revs->min_age != -1 ||
revs->max_age != -1)
usage(builtin_diff_usage);
if (!(option & DIFF_INDEX_CACHED)) {
setup_work_tree();
if (repo_read_index_preload(the_repository,
&revs->diffopt.pathspec, 0) < 0) {
die_errno("repo_read_index_preload");
}
} else if (repo_read_index(the_repository) < 0) {
die_errno("repo_read_cache");
}
diff: drop useless return from run_diff_{files,index} functions Neither of these functions ever returns a value other than zero. Instead, they expect unrecoverable errors to exit immediately, and things like "--exit-code" are stored inside the diff_options struct to be handled later via diff_result_code(). Some callers do check the return values, but many don't bother. Let's drop the useless return values, which are misleading callers about how the functions work. This could be seen as a step in the wrong direction, as we might want to eventually "lib-ify" these to more cleanly return errors up the stack, in which case we'd have to add the return values back in. But there are some benefits to doing this now: 1. In the current code, somebody could accidentally add a "return -1" to one of the functions, which would be erroneously ignored by many callers. By removing the return code, the compiler can notice the mismatch and force the developer to decide what to do. Obviously the other option here is that we could start consistently checking the error code in every caller. But it would be dead code, and we wouldn't get any compile-time help in catching new cases. 2. It communicates the situation to callers, who may want to choose a different function. These functions are really thin wrappers for doing git-diff-files and git-diff-index within the process. But callers who care about recovering from an error here are probably better off using the underlying library functions, many of which do return errors. If somebody eventually wants to teach these functions to propagate errors, they'll have to switch back to returning a value, effectively reverting this patch. But at least then they will be starting with a level playing field: they know that they will need to inspect each caller to see how it should handle the error. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-08-21 20:18:55 +00:00
run_diff_index(revs, option);
}
static void 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]);
struct object_id mb_oid;
int merge_base = 0;
while (1 < argc) {
const char *arg = argv[1];
if (!strcmp(arg, "--merge-base"))
merge_base = 1;
else
usage(builtin_diff_usage);
argv++; argc--;
}
if (merge_base) {
diff_get_merge_base(revs, &mb_oid);
oid[0] = &mb_oid;
oid[1] = &revs->pending.objects[1].item->oid;
} else {
int swap = 0;
/*
* We saw two trees, ent0 and ent1. If ent1 is uninteresting,
* swap them.
*/
if (ent1->item->flags & UNINTERESTING)
swap = 1;
oid[swap] = &ent0->item->oid;
oid[1 - swap] = &ent1->item->oid;
}
diff_tree_oid(oid[0], oid[1], "", &revs->diffopt);
log_tree_diff_flush(revs);
}
static void builtin_diff_combined(struct rev_info *revs,
int argc, const char **argv UNUSED,
struct object_array_entry *ent,
int ents, int first_non_parent)
{
struct oid_array parents = OID_ARRAY_INIT;
int i;
if (argc > 1)
usage(builtin_diff_usage);
if (first_non_parent < 0)
die(_("no merge given, only parents."));
if (first_non_parent >= ents)
BUG("first_non_parent out of range: %d", first_non_parent);
diff_merges_set_dense_combined_if_unset(revs);
for (i = 0; i < ents; i++) {
if (i != first_non_parent)
oid_array_append(&parents, &ent[i].item->oid);
}
diff_tree_combined(&ent[first_non_parent].item->oid, &parents, revs);
oid_array_clear(&parents);
}
static void refresh_index_quietly(void)
{
struct lock_file lock_file = LOCK_INIT;
int fd;
fd = repo_hold_locked_index(the_repository, &lock_file, 0);
if (fd < 0)
return;
discard_index(&the_index);
repo_read_index(the_repository);
refresh_index(&the_index, REFRESH_QUIET|REFRESH_UNMERGED, NULL, NULL,
NULL);
repo_update_index_if_able(the_repository, &lock_file);
}
static void 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);
diff: show usage for unknown builtin_diff_files() options The git-diff command has many modes (comparing worktree to index, index to HEAD, individual blobs, etc). As a result, it dispatches to many helper functions and cannot completely parse its options until we're in those helper functions. Most of them, when seeing an unknown option, exit immediately by calling usage(). But builtin_diff_files(), which is the default if no revision or blob arguments are given, instead prints an error() and returns -1. One obvious shortcoming here is that the user doesn't get to see the usual usage message. But there's a much more important bug: the -1 return is fed to diff_result_code(), which is not ready to handle it. By default, it passes the code along as an exit code. We try to avoid negative exit codes because they get converted to unsigned values, but it should at least consistently show up as non-zero (i.e., a failure). But much worse is that when --exit-code is in effect, diff_result_code() will _ignore_ the status passed in by the caller, and instead only report on whether the diff found changes. It didn't, of course, because we never ran the diff, and the program unexpectedly exits with success! We can fix this bug by just calling usage(), like the other helpers do. Another option would of course be to teach diff_result_code() to handle this value. But as we'll see in the next few patches, it can be cleaned up even further. Let's just fix this bug directly to start with. Reported-by: Romain Chossart <romainchossart@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-08-21 20:16:26 +00:00
else {
error(_("invalid option: %s"), argv[1]);
usage(builtin_diff_usage);
}
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->diffopt.output_format & DIFF_FORMAT_PATCH))
diff_merges_set_dense_combined_if_unset(revs);
setup_work_tree();
if (repo_read_index_preload(the_repository, &revs->diffopt.pathspec,
0) < 0) {
die_errno("repo_read_index_preload");
}
diff: drop useless return from run_diff_{files,index} functions Neither of these functions ever returns a value other than zero. Instead, they expect unrecoverable errors to exit immediately, and things like "--exit-code" are stored inside the diff_options struct to be handled later via diff_result_code(). Some callers do check the return values, but many don't bother. Let's drop the useless return values, which are misleading callers about how the functions work. This could be seen as a step in the wrong direction, as we might want to eventually "lib-ify" these to more cleanly return errors up the stack, in which case we'd have to add the return values back in. But there are some benefits to doing this now: 1. In the current code, somebody could accidentally add a "return -1" to one of the functions, which would be erroneously ignored by many callers. By removing the return code, the compiler can notice the mismatch and force the developer to decide what to do. Obviously the other option here is that we could start consistently checking the error code in every caller. But it would be dead code, and we wouldn't get any compile-time help in catching new cases. 2. It communicates the situation to callers, who may want to choose a different function. These functions are really thin wrappers for doing git-diff-files and git-diff-index within the process. But callers who care about recovering from an error here are probably better off using the underlying library functions, many of which do return errors. If somebody eventually wants to teach these functions to propagate errors, they'll have to switch back to returning a value, effectively reverting this patch. But at least then they will be starting with a level playing field: they know that they will need to inspect each caller to see how it should handle the error. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-08-21 20:18:55 +00:00
run_diff_files(revs, options);
}
struct symdiff {
struct bitmap *skip;
int warn;
const char *base, *left, *right;
};
/*
* Check for symmetric-difference arguments, and if present, arrange
* everything we need to know to handle them correctly. As a bonus,
* weed out all bogus range-based revision specifications, e.g.,
* "git diff A..B C..D" or "git diff A..B C" get rejected.
*
* For an actual symmetric diff, *symdiff is set this way:
*
* - its skip is non-NULL and marks *all* rev->pending.objects[i]
* indices that the caller should ignore (extra merge bases, of
* which there might be many, and A in A...B). Note that the
* chosen merge base and right side are NOT marked.
* - warn is set if there are multiple merge bases.
* - base, left, and right point to the names to use in a
* warning about multiple merge bases.
*
* If there is no symmetric diff argument, sym->skip is NULL and
* sym->warn is cleared. The remaining fields are not set.
*/
static void symdiff_prepare(struct rev_info *rev, struct symdiff *sym)
{
int i, is_symdiff = 0, basecount = 0, othercount = 0;
int lpos = -1, rpos = -1, basepos = -1;
struct bitmap *map = NULL;
/*
* Use the whence fields to find merge bases and left and
* right parts of symmetric difference, so that we do not
* depend on the order that revisions are parsed. If there
* are any revs that aren't from these sources, we have a
* "git diff C A...B" or "git diff A...B C" case. Or we
* could even get "git diff A...B C...E", for instance.
*
* If we don't have just one merge base, we pick one
* at random.
*
* NB: REV_CMD_LEFT, REV_CMD_RIGHT are also used for A..B,
* so we must check for SYMMETRIC_LEFT too. The two arrays
* rev->pending.objects and rev->cmdline.rev are parallel.
*/
for (i = 0; i < rev->cmdline.nr; i++) {
struct object *obj = rev->pending.objects[i].item;
switch (rev->cmdline.rev[i].whence) {
case REV_CMD_MERGE_BASE:
if (basepos < 0)
basepos = i;
basecount++;
break; /* do mark all bases */
case REV_CMD_LEFT:
if (lpos >= 0)
usage(builtin_diff_usage);
lpos = i;
if (obj->flags & SYMMETRIC_LEFT) {
is_symdiff = 1;
break; /* do mark A */
}
continue;
case REV_CMD_RIGHT:
if (rpos >= 0)
usage(builtin_diff_usage);
rpos = i;
continue; /* don't mark B */
case REV_CMD_PARENTS_ONLY:
case REV_CMD_REF:
case REV_CMD_REV:
othercount++;
continue;
}
if (!map)
map = bitmap_new();
bitmap_set(map, i);
}
/*
* Forbid any additional revs for both A...B and A..B.
*/
if (lpos >= 0 && othercount > 0)
usage(builtin_diff_usage);
if (!is_symdiff) {
bitmap_free(map);
sym->warn = 0;
sym->skip = NULL;
return;
}
sym->left = rev->pending.objects[lpos].name;
sym->right = rev->pending.objects[rpos].name;
if (basecount == 0)
die(_("%s...%s: no merge base"), sym->left, sym->right);
sym->base = rev->pending.objects[basepos].name;
bitmap_unset(map, basepos); /* unmark the base we want */
sym->warn = basecount > 1;
sym->skip = map;
}
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 00:42:35 +00:00
int i;
struct rev_info rev;
struct object_array ent = OBJECT_ARRAY_INIT;
int first_non_parent = -1;
int blobs = 0, paths = 0;
struct object_array_entry *blob[2];
int nongit = 0, no_index = 0;
int result;
struct symdiff sdiff;
/*
* We could get N tree-ish in the rev.pending_objects list.
* Also there could be M blobs there, and P pathspecs. --cached may
* also be present.
*
* N=0, M=0:
* cache vs files (diff-files)
*
* N=0, M=0, --cached:
* HEAD vs cache (diff-index --cached)
*
* 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 files (diff-index)
*
* N=1, M=0, --cached:
* 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 03:23:36 +00:00
prefix = setup_git_directory_gently(&nongit);
diff: enable and test the sparse index Enable the sparse index within the 'git diff' command. Its implementation already safely integrates with the sparse index because it shares code with the 'git status' and 'git checkout' commands that were already integrated. For more details see: d76723ee53 (status: use sparse-index throughout, 2021-07-14) 1ba5f45132 (checkout: stop expanding sparse indexes, 2021-06-29) The most interesting thing to do is to add tests that verify that 'git diff' behaves correctly when the sparse index is enabled. These cases are: 1. The index is not expanded for 'diff' and 'diff --staged' 2. 'diff' and 'diff --staged' behave the same in full checkout, sparse checkout, and sparse index repositories in the following partially-staged scenarios (i.e. the index, HEAD, and working directory differ at a given path): 1. Path is within sparse-checkout cone 2. Path is outside sparse-checkout cone 3. A merge conflict exists for paths outside sparse-checkout cone The `p2000` tests demonstrate a ~44% execution time reduction for 'git diff' and a ~86% execution time reduction for 'git diff --staged' using a sparse index: Test before after ------------------------------------------------------------- 2000.30: git diff (full-v3) 0.33 0.34 +3.0% 2000.31: git diff (full-v4) 0.33 0.35 +6.1% 2000.32: git diff (sparse-v3) 0.53 0.31 -41.5% 2000.33: git diff (sparse-v4) 0.54 0.29 -46.3% 2000.34: git diff --cached (full-v3) 0.07 0.07 +0.0% 2000.35: git diff --cached (full-v4) 0.07 0.08 +14.3% 2000.36: git diff --cached (sparse-v3) 0.28 0.04 -85.7% 2000.37: git diff --cached (sparse-v4) 0.23 0.03 -87.0% Co-authored-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Lessley Dennington <lessleydennington@gmail.com> Reviewed-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-12-06 15:56:00 +00:00
if (!nongit) {
prepare_repo_settings(the_repository);
the_repository->settings.command_requires_full_index = 0;
}
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 $GIT_DIR variable). We find the repo config no matter where we started, and respect it. So we already respect the repository config in a number of common cases, and case (2) is the only one that does not. And at least one of our tests, t4034, depends on case (1) behaving as it does now (though it is just incidental, not an explicit test for this behavior). So let's bring case (2) in line with the others by always running the repository setup, even with an explicit "--no-index". We shouldn't need to change anything else, as the implicit case already handles the prefix. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-13 03:23:36 +00:00
if (!no_index) {
/*
* Treat git diff with at least one path outside of the
* repo the same as if the command would have been executed
* outside of a git repository. In this case it behaves
* the same way as "git diff --no-index <a> <b>", which acts
* as a colourful "diff" replacement.
*/
if (nongit || ((argc == i + 2) &&
(!path_inside_repo(prefix, argv[i]) ||
!path_inside_repo(prefix, argv[i + 1]))))
no_index = DIFF_NO_INDEX_IMPLICIT;
}
init_diff_ui_defaults();
git_config(git_diff_ui_config, NULL);
MacOS: precompose_argv_prefix() The following sequence leads to a "BUG" assertion running under MacOS: DIR=git-test-restore-p Adiarnfd=$(printf 'A\314\210') DIRNAME=xx${Adiarnfd}yy mkdir $DIR && cd $DIR && git init && mkdir $DIRNAME && cd $DIRNAME && echo "Initial" >file && git add file && echo "One more line" >>file && echo y | git restore -p . Initialized empty Git repository in /tmp/git-test-restore-p/.git/ BUG: pathspec.c:495: error initializing pathspec_item Cannot close git diff-index --cached --numstat [snip] The command `git restore` is run from a directory inside a Git repo. Git needs to split the $CWD into 2 parts: The path to the repo and "the rest", if any. "The rest" becomes a "prefix" later used inside the pathspec code. As an example, "/path/to/repo/dir-inside-repå" would determine "/path/to/repo" as the root of the repo, the place where the configuration file .git/config is found. The rest becomes the prefix ("dir-inside-repå"), from where the pathspec machinery expands the ".", more about this later. If there is a decomposed form, (making the decomposing visible like this), "dir-inside-rep°a" doesn't match "dir-inside-repå". Git commands need to: (a) read the configuration variable "core.precomposeunicode" (b) precocompose argv[] (c) precompose the prefix, if there was any The first commit, 76759c7dff53 "git on Mac OS and precomposed unicode" addressed (a) and (b). The call to precompose_argv() was added into parse-options.c, because that seemed to be a good place when the patch was written. Commands that don't use parse-options need to do (a) and (b) themselfs. The commands `diff-files`, `diff-index`, `diff-tree` and `diff` learned (a) and (b) in commit 90a78b83e0b8 "diff: run arguments through precompose_argv" Branch names (or refs in general) using decomposed code points resulting in decomposed file names had been fixed in commit 8e712ef6fc97 "Honor core.precomposeUnicode in more places" The bug report from above shows 2 things: - more commands need to handle precomposed unicode - (c) should be implemented for all commands using pathspecs Solution: precompose_argv() now handles the prefix (if needed), and is renamed into precompose_argv_prefix(). Inside this function the config variable core.precomposeunicode is read into the global variable precomposed_unicode, as before. This reading is skipped if precomposed_unicode had been read before. The original patch for preocomposed unicode, 76759c7dff53, placed precompose_argv() into parse-options.c Now add it into git.c::run_builtin() as well. Existing precompose calls in diff-files.c and others may become redundant, and if we audit the callflows that reach these places to make sure that they can never be reached without going through the new call added to run_builtin(), we might be able to remove these existing ones. But in this commit, we do not bother to do so and leave these precompose callsites as they are. Because precompose() is idempotent and can be called on an already precomposed string safely, this is safer than removing existing calls without fully vetting the callflows. There is certainly room for cleanups - this change intends to be a bug fix. Cleanups needs more tests in e.g. t/t3910-mac-os-precompose.sh, and should be done in future commits. [1] git-bugreport-2021-01-06-1209.txt (git can't deal with special characters) [2] https://lore.kernel.org/git/A102844A-9501-4A86-854D-E3B387D378AA@icloud.com/ Reported-by: Daniel Troger <random_n0body@icloud.com> Helped-By: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-03 16:28:23 +00:00
prefix = precompose_argv_prefix(argc, argv, prefix);
repo_init_revisions(the_repository, &rev, prefix);
/* Set up defaults that will apply to both no-index and regular diffs. */
rev.diffopt.stat_width = -1;
rev.diffopt.stat_graph_width = -1;
diff: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 18:19:11 +00:00
rev.diffopt.flags.allow_external = 1;
rev.diffopt.flags.allow_textconv = 1;
/* If this is a no-index diff, just run it and exit there. */
if (no_index)
exit(diff_no_index(&rev, no_index == DIFF_NO_INDEX_IMPLICIT,
argc, argv));
/*
* Otherwise, we are doing the usual "git" diff; set up any
* further defaults that apply to regular diffs.
*/
rev.diffopt.skip_stat_unmatch = !!diff_auto_refresh_index;
diff: turn --ita-invisible-in-index on by default Due to the implementation detail of intent-to-add entries, the current "git diff" (i.e. no treeish or --cached argument) would show the changes in the i-t-a file, but it does not mark the file as new, while "diff --cached" would mark the file as new while showing its content as empty. $ git diff | $ diff --cached --------------------------------|------------------------------- diff --git a/new b/new | diff --git a/new b/new index e69de29..5ad28e2 100644 | new file mode 100644 --- a/new | index 0000000..e69de29 +++ b/new | @@ -0,0 +1 @@ | +haha | One evidence of the current output being wrong is that, the output from "git diff" (with ita entries) cannot be applied because it assumes empty files exist before applying. Turning on --ita-invisible-in-index [1] [2] would fix this. The result is "new file" line moving from "git diff --cached" to "git diff". $ git diff | $ diff --cached --------------------------------|------------------------------- diff --git a/new b/new | new file mode 100644 | index 0000000..5ad28e2 | --- /dev/null | +++ b/new | @@ -0,0 +1 @@ | +haha | This option is on by default in git-status [1] but we need more fixup in rename detection code [3]. Luckily we don't need to do anything else for the rename detection code in diff.c (wt-status.c uses a customized one). [1] 425a28e0a4 (diff-lib: allow ita entries treated as "not yet exist in index" - 2016-10-24) [2] b42b451919 (diff: add --ita-[in]visible-in-index - 2016-10-24) [3] bc3dca07f4 (Merge branch 'nd/ita-wt-renames-in-status' - 2018-01-23) Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-05-26 12:08:44 +00:00
/*
* Default to intent-to-add entries invisible in the
* index. This makes them show up as new files in diff-files
* and not at all in diff-cached.
*/
rev.diffopt.ita_invisible_in_index = 1;
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: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 18:19:11 +00:00
rev.diffopt.flags.recursive = 1;
rev.diffopt.rotate_to_strict = 1;
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 00:42:35 +00:00
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(the_repository,
the_repository->hash_algo->empty_tree);
add_pending_object(&rev, &tree->object, "HEAD");
}
break;
}
}
}
symdiff_prepare(&rev, &sdiff);
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 00:42:35 +00:00
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(the_repository, &obj->oid);
obj = deref_tag(the_repository, obj, NULL, 0);
if (!obj)
die(_("invalid object '%s' given."), name);
if (obj->type == OBJ_COMMIT)
obj = &repo_get_commit_tree(the_repository,
((struct commit *)obj))->object;
if (obj->type == OBJ_TREE) {
if (sdiff.skip && bitmap_get(sdiff.skip, i))
continue;
obj->flags |= flags;
add_object_array(obj, name, &ent);
if (first_non_parent < 0 &&
(i >= rev.cmdline.nr || /* HEAD by hand. */
rev.cmdline.rev[i].whence != REV_CMD_PARENTS_ONLY))
first_non_parent = ent.nr - 1;
} else if (obj->type == OBJ_BLOB) {
if (2 <= blobs)
die(_("more than two blobs given: '%s'"), name);
blob[blobs] = entry;
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:
builtin_diff_files(&rev, argc, argv);
break;
case 1:
if (paths != 1)
usage(builtin_diff_usage);
builtin_diff_b_f(&rev, argc, argv, blob);
break;
case 2:
if (paths)
usage(builtin_diff_usage);
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)
builtin_diff_index(&rev, argc, argv);
else if (ent.nr == 2) {
if (sdiff.warn)
warning(_("%s...%s: multiple merge bases, using %s"),
sdiff.left, sdiff.right, sdiff.base);
builtin_diff_tree(&rev, argc, argv,
&ent.objects[0], &ent.objects[1]);
} else
builtin_diff_combined(&rev, argc, argv,
ent.objects, ent.nr,
first_non_parent);
result = diff_result_code(&rev.diffopt);
if (1 < rev.diffopt.skip_stat_unmatch)
refresh_index_quietly();
release_revisions(&rev);
built-ins: use free() not UNLEAK() if trivial, rm dead code For a lot of uses of UNLEAK() it would be quite tricky to release the memory involved, or we're missing the relevant *_(release|clear)() functions. But in these cases we have them already, and can just invoke them on the variable(s) involved, instead of UNLEAK(). For "builtin/worktree.c" the UNLEAK() was also added in [1], but the struct member it's unleaking was removed in [2]. The only non-"int" member of that structure is "const char *keep_locked", which comes to us via "argv" or a string literal[3]. We have good visibility via the compiler and tooling (e.g. SANITIZE=address) on bad free()-ing, but none on UNLEAK() we don't need anymore. So let's prefer releasing the memory when it's easy. For "bugreport", "worktree" and "config" we need to start using a "ret = ..." return pattern. For "builtin/bugreport.c" these UNLEAK() were added in [4], and for "builtin/config.c" in [1]. For "config" the code seen here was the only user of the "value" variable. For "ACTION_{RENAME,REMOVE}_SECTION" we need to be sure to return the right exit code in the cases where we were relying on falling through to the top-level. I think there's still a use-case for UNLEAK(), but hat it's changed since then. Using it so that "we can see the real leaks" is counter-productive in these cases. It's more useful to have UNLEAK() be a marker of the remaining odd cases where it's hard to free() the memory for whatever reason. With this change less than 20 of them remain in-tree. 1. 0e5bba53af7 (add UNLEAK annotation for reducing leak false positives, 2017-09-08) 2. d861d34a6ed (worktree: remove extra members from struct add_opts, 2018-04-24) 3. 0db4961c49b (worktree: teach `add` to accept --reason <string> with --lock, 2021-07-15) 4. 0e5bba53af7 and 00d8c311050 (commit: fix "author_ident" leak, 2022-05-12). Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Taylor Blau <me@ttaylorr.com>
2022-11-08 18:17:51 +00:00
object_array_clear(&ent);
UNLEAK(blob);
return result;
}