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>

1 files changed, 134 insertions, 34 deletions

diff --git a/revision.c b/revision.c
index 0505f3f455..1d26e0d911 100644
--- a/revision.c
+++ b/revision.c
@@ -116,21 +116,27 @@ static void add_pending_object(struct rev_info *revs, struct object *obj, const
 	add_object(obj, &revs->pending_objects, NULL, name);
 }
 
-static struct commit *get_commit_reference(struct rev_info *revs, const char *name, const unsigned char *sha1, unsigned int flags)
+static struct object *get_reference(struct rev_info *revs, const char *name, const unsigned char *sha1, unsigned int flags)
 {
 	struct object *object;
 
 	object = parse_object(sha1);
 	if (!object)
 		die("bad object %s", name);
+	object->flags |= flags;
+	return object;
+}
+
+static struct commit *handle_commit(struct rev_info *revs, struct object *object, const char *name)
+{
+	unsigned long flags = object->flags;
 
 	/*
 	 * Tag object? Look what it points to..
 	 */
 	while (object->type == tag_type) {
 		struct tag *tag = (struct tag *) object;
-		object->flags |= flags;
-		if (revs->tag_objects && !(object->flags & UNINTERESTING))
+		if (revs->tag_objects && !(flags & UNINTERESTING))
 			add_pending_object(revs, object, tag->tag);
 		object = parse_object(tag->tagged->sha1);
 		if (!object)
@@ -143,7 +149,6 @@ static struct commit *get_commit_reference(struct rev_info *revs, const char *na
 	 */
 	if (object->type == commit_type) {
 		struct commit *commit = (struct commit *)object;
-		object->flags |= flags;
 		if (parse_commit(commit) < 0)
 			die("unable to parse commit %s", name);
 		if (flags & UNINTERESTING) {
@@ -241,7 +246,7 @@ int rev_compare_tree(struct rev_info *revs, struct tree *t1, struct tree *t2)
 		return REV_TREE_DIFFERENT;
 	tree_difference = REV_TREE_SAME;
 	if (diff_tree_sha1(t1->object.sha1, t2->object.sha1, "",
-			   &revs->diffopt) < 0)
+			   &revs->pruning) < 0)
 		return REV_TREE_DIFFERENT;
 	return tree_difference;
 }
@@ -264,7 +269,7 @@ int rev_same_tree_as_empty(struct rev_info *revs, struct tree *t1)
 	empty.size = 0;
 
 	tree_difference = 0;
-	retval = diff_tree(&empty, &real, "", &revs->diffopt);
+	retval = diff_tree(&empty, &real, "", &revs->pruning);
 	free(tree);
 
 	return retval >= 0 && !tree_difference;
@@ -451,21 +456,13 @@ static void limit_list(struct rev_info *revs)
 	revs->commits = newlist;
 }
 
-static void add_one_commit(struct commit *commit, struct rev_info *revs)
-{
-	if (!commit || (commit->object.flags & SEEN))
-		return;
-	commit->object.flags |= SEEN;
-	commit_list_insert(commit, &revs->commits);
-}
-
 static int all_flags;
 static struct rev_info *all_revs;
 
 static int handle_one_ref(const char *path, const unsigned char *sha1)
 {
-	struct commit *commit = get_commit_reference(all_revs, path, sha1, all_flags);
-	add_one_commit(commit, all_revs);
+	struct object *object = get_reference(all_revs, path, sha1, all_flags);
+	add_pending_object(all_revs, object, "");
 	return 0;
 }
 
@@ -479,9 +476,9 @@ static void handle_all(struct rev_info *revs, unsigned flags)
 void init_revisions(struct rev_info *revs)
 {
 	memset(revs, 0, sizeof(*revs));
-	revs->diffopt.recursive = 1;
-	revs->diffopt.add_remove = file_add_remove;
-	revs->diffopt.change = file_change;
+	revs->pruning.recursive = 1;
+	revs->pruning.add_remove = file_add_remove;
+	revs->pruning.change = file_change;
 	revs->lifo = 1;
 	revs->dense = 1;
 	revs->prefix = setup_git_directory();
@@ -494,6 +491,11 @@ void init_revisions(struct rev_info *revs)
 
 	revs->topo_setter = topo_sort_default_setter;
 	revs->topo_getter = topo_sort_default_getter;
+
+	revs->header_prefix = "";
+	revs->commit_format = CMIT_FMT_DEFAULT;
+
+	diff_setup(&revs->diffopt);
 }
 
 /*
@@ -526,13 +528,14 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 
 	flags = 0;
 	for (i = 1; i < argc; i++) {
-		struct commit *commit;
+		struct object *object;
 		const char *arg = argv[i];
 		unsigned char sha1[20];
 		char *dotdot;
 		int local_flags;
 
 		if (*arg == '-') {
+			int opts;
 			if (!strncmp(arg, "--max-count=", 12)) {
 				revs->max_count = atoi(arg + 12);
 				continue;
@@ -640,6 +643,78 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 				revs->unpacked = 1;
 				continue;
 			}
+			if (!strcmp(arg, "-r")) {
+				revs->diff = 1;
+				revs->diffopt.recursive = 1;
+				continue;
+			}
+			if (!strcmp(arg, "-t")) {
+				revs->diff = 1;
+				revs->diffopt.recursive = 1;
+				revs->diffopt.tree_in_recursive = 1;
+				continue;
+			}
+			if (!strcmp(arg, "-m")) {
+				revs->ignore_merges = 0;
+				continue;
+			}
+			if (!strcmp(arg, "-c")) {
+				revs->diff = 1;
+				revs->combine_merges = 1;
+				continue;
+			}
+			if (!strcmp(arg, "--cc")) {
+				revs->diff = 1;
+				revs->dense_combined_merges = 1;
+				revs->combine_merges = 1;
+				continue;
+			}
+			if (!strcmp(arg, "-v")) {
+				revs->verbose_header = 1;
+				revs->header_prefix = "diff-tree ";
+				continue;
+			}
+			if (!strncmp(arg, "--pretty", 8)) {
+				revs->verbose_header = 1;
+				revs->header_prefix = "diff-tree ";
+				revs->commit_format = get_commit_format(arg+8);
+				continue;
+			}
+			if (!strcmp(arg, "--root")) {
+				revs->show_root_diff = 1;
+				continue;
+			}
+			if (!strcmp(arg, "--no-commit-id")) {
+				revs->no_commit_id = 1;
+				continue;
+			}
+			if (!strcmp(arg, "--always")) {
+				revs->always_show_header = 1;
+				continue;
+			}
+			if (!strcmp(arg, "--no-abbrev")) {
+				revs->abbrev = 0;
+				continue;
+			}
+			if (!strcmp(arg, "--abbrev")) {
+				revs->abbrev = DEFAULT_ABBREV;
+				continue;
+			}
+			if (!strcmp(arg, "--abbrev-commit")) {
+				revs->abbrev_commit = 1;
+				continue;
+			}
+			if (!strcmp(arg, "--full-diff")) {
+				revs->diff = 1;
+				revs->full_diff = 1;
+				continue;
+			}
+			opts = diff_opt_parse(&revs->diffopt, argv+i, argc-i);
+			if (opts > 0) {
+				revs->diff = 1;
+				i += opts - 1;
+				continue;
+			}
 			*unrecognized++ = arg;
 			left++;
 			continue;
@@ -656,15 +731,15 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 				this = "HEAD";
 			if (!get_sha1(this, from_sha1) &&
 			    !get_sha1(next, sha1)) {
-				struct commit *exclude;
-				struct commit *include;
+				struct object *exclude;
+				struct object *include;
 
-				exclude = get_commit_reference(revs, this, from_sha1, flags ^ UNINTERESTING);
-				include = get_commit_reference(revs, next, sha1, flags);
+				exclude = get_reference(revs, this, from_sha1, flags ^ UNINTERESTING);
+				include = get_reference(revs, next, sha1, flags);
 				if (!exclude || !include)
 					die("Invalid revision range %s..%s", arg, next);
-				add_one_commit(exclude, revs);
-				add_one_commit(include, revs);
+				add_pending_object(revs, exclude, this);
+				add_pending_object(revs, include, next);
 				continue;
 			}
 			*dotdot = '.';
@@ -689,32 +764,57 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 			revs->prune_data = get_pathspec(revs->prefix, argv + i);
 			break;
 		}
-		commit = get_commit_reference(revs, arg, sha1, flags ^ local_flags);
-		add_one_commit(commit, revs);
+		object = get_reference(revs, arg, sha1, flags ^ local_flags);
+		add_pending_object(revs, object, arg);
 	}
-	if (def && !revs->commits) {
+	if (def && !revs->pending_objects) {
 		unsigned char sha1[20];
-		struct commit *commit;
+		struct object *object;
 		if (get_sha1(def, sha1) < 0)
 			die("bad default revision '%s'", def);
-		commit = get_commit_reference(revs, def, sha1, 0);
-		add_one_commit(commit, revs);
+		object = get_reference(revs, def, sha1, 0);
+		add_pending_object(revs, object, def);
 	}
 
 	if (revs->topo_order || revs->unpacked)
 		revs->limited = 1;
 
 	if (revs->prune_data) {
-		diff_tree_setup_paths(revs->prune_data, &revs->diffopt);
+		diff_tree_setup_paths(revs->prune_data, &revs->pruning);
 		revs->prune_fn = try_to_simplify_commit;
+		if (!revs->full_diff)
+			diff_tree_setup_paths(revs->prune_data, &revs->diffopt);
 	}
+	if (revs->combine_merges) {
+		revs->ignore_merges = 0;
+		if (revs->dense_combined_merges)
+			revs->diffopt.output_format = DIFF_FORMAT_PATCH;
+	}
+	if (revs->diffopt.output_format == DIFF_FORMAT_PATCH)
+		revs->diffopt.recursive = 1;
+	revs->diffopt.abbrev = revs->abbrev;
+	diff_setup_done(&revs->diffopt);
 
 	return left;
 }
 
 void prepare_revision_walk(struct rev_info *revs)
 {
-	sort_by_date(&revs->commits);
+	struct object_list *list;
+
+	list = revs->pending_objects;
+	revs->pending_objects = NULL;
+	while (list) {
+		struct commit *commit = handle_commit(revs, list->item, list->name);
+		if (commit) {
+			if (!(commit->object.flags & SEEN)) {
+				commit->object.flags |= SEEN;
+				insert_by_date(commit, &revs->commits);
+			}
+		}
+		list = list->next;
+	}
+
 	if (revs->limited)
 		limit_list(revs);
 	if (revs->topo_order)