git-rev-list libification: rev-list walking

This actually moves the "meat" of the revision walking from rev-list.c
to the new library code in revision.h. It introduces the new functions

	void prepare_revision_walk(struct rev_info *revs);
	struct commit *get_revision(struct rev_info *revs);

to prepare and then walk the revisions that we have.

Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

1 files changed, 245 insertions, 2 deletions

diff --git a/revision.c b/revision.c
index 67ff4de2d1..f1ac62d7d8 100644
--- a/revision.c
+++ b/revision.c
@@ -3,6 +3,7 @@
 #include "blob.h"
 #include "tree.h"
 #include "commit.h"
+#include "diff.h"
 #include "refs.h"
 #include "revision.h"
 
@@ -183,6 +184,229 @@ static struct commit *get_commit_reference(struct rev_info *revs, const char *na
 	die("%s is unknown object", name);
 }
 
+static int everybody_uninteresting(struct commit_list *orig)
+{
+	struct commit_list *list = orig;
+	while (list) {
+		struct commit *commit = list->item;
+		list = list->next;
+		if (commit->object.flags & UNINTERESTING)
+			continue;
+		return 0;
+	}
+	return 1;
+}
+
+#define TREE_SAME	0
+#define TREE_NEW	1
+#define TREE_DIFFERENT	2
+static int tree_difference = TREE_SAME;
+
+static void file_add_remove(struct diff_options *options,
+		    int addremove, unsigned mode,
+		    const unsigned char *sha1,
+		    const char *base, const char *path)
+{
+	int diff = TREE_DIFFERENT;
+
+	/*
+	 * Is it an add of a new file? It means that
+	 * the old tree didn't have it at all, so we
+	 * will turn "TREE_SAME" -> "TREE_NEW", but
+	 * leave any "TREE_DIFFERENT" alone (and if
+	 * it already was "TREE_NEW", we'll keep it
+	 * "TREE_NEW" of course).
+	 */
+	if (addremove == '+') {
+		diff = tree_difference;
+		if (diff != TREE_SAME)
+			return;
+		diff = TREE_NEW;
+	}
+	tree_difference = diff;
+}
+
+static void file_change(struct diff_options *options,
+		 unsigned old_mode, unsigned new_mode,
+		 const unsigned char *old_sha1,
+		 const unsigned char *new_sha1,
+		 const char *base, const char *path)
+{
+	tree_difference = TREE_DIFFERENT;
+}
+
+static struct diff_options diff_opt = {
+	.recursive = 1,
+	.add_remove = file_add_remove,
+	.change = file_change,
+};
+
+static int compare_tree(struct tree *t1, struct tree *t2)
+{
+	if (!t1)
+		return TREE_NEW;
+	if (!t2)
+		return TREE_DIFFERENT;
+	tree_difference = TREE_SAME;
+	if (diff_tree_sha1(t1->object.sha1, t2->object.sha1, "", &diff_opt) < 0)
+		return TREE_DIFFERENT;
+	return tree_difference;
+}
+
+static int same_tree_as_empty(struct tree *t1)
+{
+	int retval;
+	void *tree;
+	struct tree_desc empty, real;
+
+	if (!t1)
+		return 0;
+
+	tree = read_object_with_reference(t1->object.sha1, "tree", &real.size, NULL);
+	if (!tree)
+		return 0;
+	real.buf = tree;
+
+	empty.buf = "";
+	empty.size = 0;
+
+	tree_difference = 0;
+	retval = diff_tree(&empty, &real, "", &diff_opt);
+	free(tree);
+
+	return retval >= 0 && !tree_difference;
+}
+
+static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
+{
+	struct commit_list **pp, *parent;
+
+	if (!commit->tree)
+		return;
+
+	if (!commit->parents) {
+		if (!same_tree_as_empty(commit->tree))
+			commit->object.flags |= TREECHANGE;
+		return;
+	}
+
+	pp = &commit->parents;
+	while ((parent = *pp) != NULL) {
+		struct commit *p = parent->item;
+
+		if (p->object.flags & UNINTERESTING) {
+			pp = &parent->next;
+			continue;
+		}
+
+		parse_commit(p);
+		switch (compare_tree(p->tree, commit->tree)) {
+		case TREE_SAME:
+			parent->next = NULL;
+			commit->parents = parent;
+			return;
+
+		case TREE_NEW:
+			if (revs->remove_empty_trees && same_tree_as_empty(p->tree)) {
+				*pp = parent->next;
+				continue;
+			}
+		/* fallthrough */
+		case TREE_DIFFERENT:
+			pp = &parent->next;
+			continue;
+		}
+		die("bad tree compare for commit %s", sha1_to_hex(commit->object.sha1));
+	}
+	commit->object.flags |= TREECHANGE;
+}
+
+static void add_parents_to_list(struct rev_info *revs, struct commit *commit, struct commit_list **list)
+{
+	struct commit_list *parent = commit->parents;
+
+	/*
+	 * If the commit is uninteresting, don't try to
+	 * prune parents - we want the maximal uninteresting
+	 * set.
+	 *
+	 * Normally we haven't parsed the parent
+	 * yet, so we won't have a parent of a parent
+	 * here. However, it may turn out that we've
+	 * reached this commit some other way (where it
+	 * wasn't uninteresting), in which case we need
+	 * to mark its parents recursively too..
+	 */
+	if (commit->object.flags & UNINTERESTING) {
+		while (parent) {
+			struct commit *p = parent->item;
+			parent = parent->next;
+			parse_commit(p);
+			p->object.flags |= UNINTERESTING;
+			if (p->parents)
+				mark_parents_uninteresting(p);
+			if (p->object.flags & SEEN)
+				continue;
+			p->object.flags |= SEEN;
+			insert_by_date(p, list);
+		}
+		return;
+	}
+
+	/*
+	 * Ok, the commit wasn't uninteresting. Try to
+	 * simplify the commit history and find the parent
+	 * that has no differences in the path set if one exists.
+	 */
+	if (revs->paths)
+		try_to_simplify_commit(revs, commit);
+
+	parent = commit->parents;
+	while (parent) {
+		struct commit *p = parent->item;
+
+		parent = parent->next;
+
+		parse_commit(p);
+		if (p->object.flags & SEEN)
+			continue;
+		p->object.flags |= SEEN;
+		insert_by_date(p, list);
+	}
+}
+
+static void limit_list(struct rev_info *revs)
+{
+	struct commit_list *list = revs->commits;
+	struct commit_list *newlist = NULL;
+	struct commit_list **p = &newlist;
+
+	while (list) {
+		struct commit_list *entry = list;
+		struct commit *commit = list->item;
+		struct object *obj = &commit->object;
+
+		list = list->next;
+		free(entry);
+
+		if (revs->max_age != -1 && (commit->date < revs->max_age))
+			obj->flags |= UNINTERESTING;
+		if (revs->unpacked && has_sha1_pack(obj->sha1))
+			obj->flags |= UNINTERESTING;
+		add_parents_to_list(revs, commit, &list);
+		if (obj->flags & UNINTERESTING) {
+			mark_parents_uninteresting(commit);
+			if (everybody_uninteresting(list))
+				break;
+			continue;
+		}
+		if (revs->min_age != -1 && (commit->date > revs->min_age))
+			continue;
+		p = &commit_list_insert(commit, p)->next;
+	}
+	revs->commits = newlist;
+}
+
 static void add_one_commit(struct commit *commit, struct rev_info *revs)
 {
 	if (!commit || (commit->object.flags & SEEN))
@@ -214,10 +438,9 @@ static void handle_all(struct rev_info *revs, unsigned flags)
  *
  * Returns the number of arguments left ("new argc").
  */
-int setup_revisions(int argc, const char **argv, struct rev_info *revs)
+int setup_revisions(int argc, const char **argv, struct rev_info *revs, const char *def)
 {
 	int i, flags, seen_dashdash;
-	const char *def = NULL;
 	const char **unrecognized = argv+1;
 	int left = 1;
 
@@ -381,3 +604,23 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs)
 	*unrecognized = NULL;
 	return left;
 }
+
+void prepare_revision_walk(struct rev_info *revs)
+{
+	if (revs->paths)
+		diff_tree_setup_paths(revs->paths);
+	sort_by_date(&revs->commits);
+	if (revs->limited)
+		limit_list(revs);
+	if (revs->topo_order)
+		sort_in_topological_order(&revs->commits, revs->lifo);
+}
+
+struct commit *get_revision(struct rev_info *revs)
+{
+	if (!revs->commits)
+		return NULL;
+	return pop_most_recent_commit(&revs->commits, SEEN);
+}
+
+