1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-26 19:56:11 +02:00
git/builtin/diff-tree.c

192 lines
5.0 KiB
C
Raw Normal View History

#include "cache.h"
#include "config.h"
#include "diff.h"
#include "commit.h"
#include "log-tree.h"
#include "builtin.h"
#include "submodule.h"
#include "repository.h"
Common option parsing for "git log --diff" and friends This basically does a few things that are sadly somewhat interdependent, and nontrivial to split out - get rid of "struct log_tree_opt" The fields in "log_tree_opt" are moved into "struct rev_info", and all users of log_tree_opt are changed to use the rev_info struct instead. - add the parsing for the log_tree_opt arguments to "setup_revision()" - make setup_revision set a flag (revs->diff) if the diff-related arguments were used. This allows "git log" to decide whether it wants to show diffs or not. - make setup_revision() also initialize the diffopt part of rev_info (which we had from before, but we just didn't initialize it) - make setup_revision() do all the "finishing touches" on it all (it will do the proper flag combination logic, and call "diff_setup_done()") Now, that was the easy and straightforward part. The slightly more involved part is that some of the programs that want to use the new-and-improved rev_info parsing don't actually want _commits_, they may want tree'ish arguments instead. That meant that I had to change setup_revision() to parse the arguments not into the "revs->commits" list, but into the "revs->pending_objects" list. Then, when we do "prepare_revision_walk()", we walk that list, and create the sorted commit list from there. This actually cleaned some stuff up, but it's the less obvious part of the patch, and re-organized the "revision.c" logic somewhat. It actually paves the way for splitting argument parsing _entirely_ out of "revision.c", since now the argument parsing really is totally independent of the commit walking: that didn't use to be true, since there was lots of overlap with get_commit_reference() handling etc, now the _only_ overlap is the shared (and trivial) "add_pending_object()" thing. However, I didn't do that file split, just because I wanted the diff itself to be smaller, and show the actual changes more clearly. If this gets accepted, I'll do further cleanups then - that includes the file split, but also using the new infrastructure to do a nicer "git diff" etc. Even in this form, it actually ends up removing more lines than it adds. It's nice to note how simple and straightforward this makes the built-in "git log" command, even though it continues to support all the diff flags too. It doesn't get much simpler that this. I think this is worth merging soonish, because it does allow for future cleanup and even more sharing of code. However, it obviously touches "revision.c", which is subtle. I've tested that it passes all the tests we have, and it passes my "looks sane" detector, but somebody else should also give it a good look-over. [jc: squashed the original and three "oops this too" updates, with another fix-up.] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-15 01:52:13 +02:00
static struct rev_info log_tree_opt;
static int diff_tree_commit_oid(const struct object_id *oid)
{
struct commit *commit = lookup_commit_reference(the_repository, oid);
if (!commit)
return -1;
return log_tree_commit(&log_tree_opt, commit);
}
/* Diff one or more commits. */
static int stdin_diff_commit(struct commit *commit, const char *p)
{
struct object_id oid;
struct commit_list **pptr = NULL;
/* Graft the fake parents locally to the commit */
while (isspace(*p++) && !parse_oid_hex(p, &oid, &p)) {
struct commit *parent = lookup_commit(the_repository, &oid);
if (!pptr) {
/* Free the real parent list */
free_commit_list(commit->parents);
commit->parents = NULL;
pptr = &(commit->parents);
}
if (parent) {
pptr = &commit_list_insert(parent, pptr)->next;
}
}
return log_tree_commit(&log_tree_opt, commit);
}
/* Diff two trees. */
static int stdin_diff_trees(struct tree *tree1, const char *p)
{
struct object_id oid;
struct tree *tree2;
if (!isspace(*p++) || parse_oid_hex(p, &oid, &p) || *p)
return error("Need exactly two trees, separated by a space");
tree2 = lookup_tree(the_repository, &oid);
if (!tree2 || parse_tree(tree2))
return -1;
printf("%s %s\n", oid_to_hex(&tree1->object.oid),
oid_to_hex(&tree2->object.oid));
diff_tree_oid(&tree1->object.oid, &tree2->object.oid,
"", &log_tree_opt.diffopt);
log_tree_diff_flush(&log_tree_opt);
return 0;
}
static int diff_tree_stdin(char *line)
{
int len = strlen(line);
struct object_id oid;
struct object *obj;
const char *p;
if (!len || line[len-1] != '\n')
return -1;
line[len-1] = 0;
if (parse_oid_hex(line, &oid, &p))
return -1;
obj = parse_object(the_repository, &oid);
if (!obj)
return -1;
if (obj->type == OBJ_COMMIT)
return stdin_diff_commit((struct commit *)obj, p);
if (obj->type == OBJ_TREE)
return stdin_diff_trees((struct tree *)obj, p);
error("Object %s is a %s, not a commit or tree",
oid_to_hex(&oid), type_name(obj->type));
return -1;
}
static const char diff_tree_usage[] =
"git diff-tree [--stdin] [-m] [-c] [--cc] [-s] [-v] [--pretty] [-t] [-r] [--root] "
"[<common-diff-options>] <tree-ish> [<tree-ish>] [<path>...]\n"
" -r diff recursively\n"
" --root include the initial commit as diff against /dev/null\n"
COMMON_DIFF_OPTIONS_HELP;
static void diff_tree_tweak_rev(struct rev_info *rev, struct setup_revision_opt *opt)
{
if (!rev->diffopt.output_format) {
if (rev->dense_combined_merges)
rev->diffopt.output_format = DIFF_FORMAT_PATCH;
else
rev->diffopt.output_format = DIFF_FORMAT_RAW;
}
}
int cmd_diff_tree(int argc, const char **argv, const char *prefix)
{
char line[1000];
Common option parsing for "git log --diff" and friends This basically does a few things that are sadly somewhat interdependent, and nontrivial to split out - get rid of "struct log_tree_opt" The fields in "log_tree_opt" are moved into "struct rev_info", and all users of log_tree_opt are changed to use the rev_info struct instead. - add the parsing for the log_tree_opt arguments to "setup_revision()" - make setup_revision set a flag (revs->diff) if the diff-related arguments were used. This allows "git log" to decide whether it wants to show diffs or not. - make setup_revision() also initialize the diffopt part of rev_info (which we had from before, but we just didn't initialize it) - make setup_revision() do all the "finishing touches" on it all (it will do the proper flag combination logic, and call "diff_setup_done()") Now, that was the easy and straightforward part. The slightly more involved part is that some of the programs that want to use the new-and-improved rev_info parsing don't actually want _commits_, they may want tree'ish arguments instead. That meant that I had to change setup_revision() to parse the arguments not into the "revs->commits" list, but into the "revs->pending_objects" list. Then, when we do "prepare_revision_walk()", we walk that list, and create the sorted commit list from there. This actually cleaned some stuff up, but it's the less obvious part of the patch, and re-organized the "revision.c" logic somewhat. It actually paves the way for splitting argument parsing _entirely_ out of "revision.c", since now the argument parsing really is totally independent of the commit walking: that didn't use to be true, since there was lots of overlap with get_commit_reference() handling etc, now the _only_ overlap is the shared (and trivial) "add_pending_object()" thing. However, I didn't do that file split, just because I wanted the diff itself to be smaller, and show the actual changes more clearly. If this gets accepted, I'll do further cleanups then - that includes the file split, but also using the new infrastructure to do a nicer "git diff" etc. Even in this form, it actually ends up removing more lines than it adds. It's nice to note how simple and straightforward this makes the built-in "git log" command, even though it continues to support all the diff flags too. It doesn't get much simpler that this. I think this is worth merging soonish, because it does allow for future cleanup and even more sharing of code. However, it obviously touches "revision.c", which is subtle. I've tested that it passes all the tests we have, and it passes my "looks sane" detector, but somebody else should also give it a good look-over. [jc: squashed the original and three "oops this too" updates, with another fix-up.] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-15 01:52:13 +02:00
struct object *tree1, *tree2;
static struct rev_info *opt = &log_tree_opt;
struct setup_revision_opt s_r_opt;
int read_stdin = 0;
if (argc == 2 && !strcmp(argv[1], "-h"))
usage(diff_tree_usage);
git_config(git_diff_basic_config, NULL); /* no "diff" UI options */
repo_init_revisions(the_repository, opt, prefix);
if (read_cache() < 0)
die(_("index file corrupt"));
opt->abbrev = 0;
Log message printout cleanups On Sun, 16 Apr 2006, Junio C Hamano wrote: > > In the mid-term, I am hoping we can drop the generate_header() > callchain _and_ the custom code that formats commit log in-core, > found in cmd_log_wc(). Ok, this was nastier than expected, just because the dependencies between the different log-printing stuff were absolutely _everywhere_, but here's a patch that does exactly that. The patch is not very easy to read, and the "--patch-with-stat" thing is still broken (it does not call the "show_log()" thing properly for merges). That's not a new bug. In the new world order it _should_ do something like if (rev->logopt) show_log(rev, rev->logopt, "---\n"); but it doesn't. I haven't looked at the --with-stat logic, so I left it alone. That said, this patch removes more lines than it adds, and in particular, the "cmd_log_wc()" loop is now a very clean: while ((commit = get_revision(rev)) != NULL) { log_tree_commit(rev, commit); free(commit->buffer); commit->buffer = NULL; } so it doesn't get much prettier than this. All the complexity is entirely hidden in log-tree.c, and any code that needs to flush the log literally just needs to do the "if (rev->logopt) show_log(...)" incantation. I had to make the combined_diff() logic take a "struct rev_info" instead of just a "struct diff_options", but that part is pretty clean. This does change "git whatchanged" from using "diff-tree" as the commit descriptor to "commit", and I changed one of the tests to reflect that new reality. Otherwise everything still passes, and my other tests look fine too. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-17 20:59:32 +02:00
opt->diff = 1;
opt->disable_stdin = 1;
memset(&s_r_opt, 0, sizeof(s_r_opt));
s_r_opt.tweak = diff_tree_tweak_rev;
precompose_argv(argc, argv);
argc = setup_revisions(argc, argv, opt, &s_r_opt);
Common option parsing for "git log --diff" and friends This basically does a few things that are sadly somewhat interdependent, and nontrivial to split out - get rid of "struct log_tree_opt" The fields in "log_tree_opt" are moved into "struct rev_info", and all users of log_tree_opt are changed to use the rev_info struct instead. - add the parsing for the log_tree_opt arguments to "setup_revision()" - make setup_revision set a flag (revs->diff) if the diff-related arguments were used. This allows "git log" to decide whether it wants to show diffs or not. - make setup_revision() also initialize the diffopt part of rev_info (which we had from before, but we just didn't initialize it) - make setup_revision() do all the "finishing touches" on it all (it will do the proper flag combination logic, and call "diff_setup_done()") Now, that was the easy and straightforward part. The slightly more involved part is that some of the programs that want to use the new-and-improved rev_info parsing don't actually want _commits_, they may want tree'ish arguments instead. That meant that I had to change setup_revision() to parse the arguments not into the "revs->commits" list, but into the "revs->pending_objects" list. Then, when we do "prepare_revision_walk()", we walk that list, and create the sorted commit list from there. This actually cleaned some stuff up, but it's the less obvious part of the patch, and re-organized the "revision.c" logic somewhat. It actually paves the way for splitting argument parsing _entirely_ out of "revision.c", since now the argument parsing really is totally independent of the commit walking: that didn't use to be true, since there was lots of overlap with get_commit_reference() handling etc, now the _only_ overlap is the shared (and trivial) "add_pending_object()" thing. However, I didn't do that file split, just because I wanted the diff itself to be smaller, and show the actual changes more clearly. If this gets accepted, I'll do further cleanups then - that includes the file split, but also using the new infrastructure to do a nicer "git diff" etc. Even in this form, it actually ends up removing more lines than it adds. It's nice to note how simple and straightforward this makes the built-in "git log" command, even though it continues to support all the diff flags too. It doesn't get much simpler that this. I think this is worth merging soonish, because it does allow for future cleanup and even more sharing of code. However, it obviously touches "revision.c", which is subtle. I've tested that it passes all the tests we have, and it passes my "looks sane" detector, but somebody else should also give it a good look-over. [jc: squashed the original and three "oops this too" updates, with another fix-up.] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-15 01:52:13 +02:00
while (--argc > 0) {
const char *arg = *++argv;
if (!strcmp(arg, "--stdin")) {
read_stdin = 1;
continue;
}
usage(diff_tree_usage);
}
Common option parsing for "git log --diff" and friends This basically does a few things that are sadly somewhat interdependent, and nontrivial to split out - get rid of "struct log_tree_opt" The fields in "log_tree_opt" are moved into "struct rev_info", and all users of log_tree_opt are changed to use the rev_info struct instead. - add the parsing for the log_tree_opt arguments to "setup_revision()" - make setup_revision set a flag (revs->diff) if the diff-related arguments were used. This allows "git log" to decide whether it wants to show diffs or not. - make setup_revision() also initialize the diffopt part of rev_info (which we had from before, but we just didn't initialize it) - make setup_revision() do all the "finishing touches" on it all (it will do the proper flag combination logic, and call "diff_setup_done()") Now, that was the easy and straightforward part. The slightly more involved part is that some of the programs that want to use the new-and-improved rev_info parsing don't actually want _commits_, they may want tree'ish arguments instead. That meant that I had to change setup_revision() to parse the arguments not into the "revs->commits" list, but into the "revs->pending_objects" list. Then, when we do "prepare_revision_walk()", we walk that list, and create the sorted commit list from there. This actually cleaned some stuff up, but it's the less obvious part of the patch, and re-organized the "revision.c" logic somewhat. It actually paves the way for splitting argument parsing _entirely_ out of "revision.c", since now the argument parsing really is totally independent of the commit walking: that didn't use to be true, since there was lots of overlap with get_commit_reference() handling etc, now the _only_ overlap is the shared (and trivial) "add_pending_object()" thing. However, I didn't do that file split, just because I wanted the diff itself to be smaller, and show the actual changes more clearly. If this gets accepted, I'll do further cleanups then - that includes the file split, but also using the new infrastructure to do a nicer "git diff" etc. Even in this form, it actually ends up removing more lines than it adds. It's nice to note how simple and straightforward this makes the built-in "git log" command, even though it continues to support all the diff flags too. It doesn't get much simpler that this. I think this is worth merging soonish, because it does allow for future cleanup and even more sharing of code. However, it obviously touches "revision.c", which is subtle. I've tested that it passes all the tests we have, and it passes my "looks sane" detector, but somebody else should also give it a good look-over. [jc: squashed the original and three "oops this too" updates, with another fix-up.] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-15 01:52:13 +02:00
/*
* NOTE! We expect "a..b" to expand to "^a b" but it is
* perfectly valid for revision range parser to yield "b ^a",
* which means the same thing. If we get the latter, i.e. the
* second one is marked UNINTERESTING, we recover the original
* order the user gave, i.e. "a..b", by swapping the trees.
Common option parsing for "git log --diff" and friends This basically does a few things that are sadly somewhat interdependent, and nontrivial to split out - get rid of "struct log_tree_opt" The fields in "log_tree_opt" are moved into "struct rev_info", and all users of log_tree_opt are changed to use the rev_info struct instead. - add the parsing for the log_tree_opt arguments to "setup_revision()" - make setup_revision set a flag (revs->diff) if the diff-related arguments were used. This allows "git log" to decide whether it wants to show diffs or not. - make setup_revision() also initialize the diffopt part of rev_info (which we had from before, but we just didn't initialize it) - make setup_revision() do all the "finishing touches" on it all (it will do the proper flag combination logic, and call "diff_setup_done()") Now, that was the easy and straightforward part. The slightly more involved part is that some of the programs that want to use the new-and-improved rev_info parsing don't actually want _commits_, they may want tree'ish arguments instead. That meant that I had to change setup_revision() to parse the arguments not into the "revs->commits" list, but into the "revs->pending_objects" list. Then, when we do "prepare_revision_walk()", we walk that list, and create the sorted commit list from there. This actually cleaned some stuff up, but it's the less obvious part of the patch, and re-organized the "revision.c" logic somewhat. It actually paves the way for splitting argument parsing _entirely_ out of "revision.c", since now the argument parsing really is totally independent of the commit walking: that didn't use to be true, since there was lots of overlap with get_commit_reference() handling etc, now the _only_ overlap is the shared (and trivial) "add_pending_object()" thing. However, I didn't do that file split, just because I wanted the diff itself to be smaller, and show the actual changes more clearly. If this gets accepted, I'll do further cleanups then - that includes the file split, but also using the new infrastructure to do a nicer "git diff" etc. Even in this form, it actually ends up removing more lines than it adds. It's nice to note how simple and straightforward this makes the built-in "git log" command, even though it continues to support all the diff flags too. It doesn't get much simpler that this. I think this is worth merging soonish, because it does allow for future cleanup and even more sharing of code. However, it obviously touches "revision.c", which is subtle. I've tested that it passes all the tests we have, and it passes my "looks sane" detector, but somebody else should also give it a good look-over. [jc: squashed the original and three "oops this too" updates, with another fix-up.] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-15 01:52:13 +02:00
*/
switch (opt->pending.nr) {
case 0:
if (!read_stdin)
usage(diff_tree_usage);
break;
case 1:
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 02:42:35 +02:00
tree1 = opt->pending.objects[0].item;
diff_tree_commit_oid(&tree1->oid);
break;
case 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 02:42:35 +02:00
tree1 = opt->pending.objects[0].item;
tree2 = opt->pending.objects[1].item;
if (tree2->flags & UNINTERESTING) {
SWAP(tree2, tree1);
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 02:42:35 +02:00
}
diff_tree_oid(&tree1->oid, &tree2->oid, "", &opt->diffopt);
log_tree_diff_flush(opt);
break;
}
if (read_stdin) {
int saved_nrl = 0;
int saved_dcctc = 0;
if (opt->diffopt.detect_rename) {
if (!the_index.cache)
repo_read_index(the_repository);
opt->diffopt.setup |= DIFF_SETUP_USE_SIZE_CACHE;
}
while (fgets(line, sizeof(line), stdin)) {
struct object_id oid;
if (get_oid_hex(line, &oid)) {
fputs(line, stdout);
fflush(stdout);
}
else {
diff_tree_stdin(line);
if (saved_nrl < opt->diffopt.needed_rename_limit)
saved_nrl = opt->diffopt.needed_rename_limit;
if (opt->diffopt.degraded_cc_to_c)
saved_dcctc = 1;
}
}
opt->diffopt.degraded_cc_to_c = saved_dcctc;
opt->diffopt.needed_rename_limit = saved_nrl;
}
return diff_result_code(&opt->diffopt, 0);
}