Merge branch 'js/merge-base'

Documentation/git-rev-list.txt

@@ -15,6 +15,7 @@ SYNOPSIS
 	     [ \--sparse ]
 	     [ \--no-merges ]
 	     [ \--remove-empty ]
+	     [ \--not ]
 	     [ \--all ]
 	     [ \--topo-order ]
 	     [ \--parents ]
@@ -37,6 +38,14 @@ not in 'baz'".
 A special notation <commit1>..<commit2> can be used as a
 short-hand for {caret}<commit1> <commit2>.
 
+Another special notation is <commit1>...<commit2> which is useful for
+merges.  The resulting set of commits is the symmetric difference
+between the two operands.  The following two commands are equivalent:
+
+------------
+$ git-rev-list A B --not $(git-merge-base --all A B)
+$ git-rev-list A...B
+------------
 
 OPTIONS
 -------
@@ -93,6 +102,11 @@ OPTIONS
 --remove-empty::
 	Stop when a given path disappears from the tree.
 
+--not::
+	Reverses the meaning of the '{caret}' prefix (or lack
+	thereof) for all following revision specifiers, up to
+	the next `--not`.
+
 --all::
 	Pretend as if all the refs in `$GIT_DIR/refs/` are
 	listed on the command line as <commit>.

builtin-rev-parse.c

@@ -164,6 +164,51 @@ static int show_file(const char *arg)
 	return 0;
 }
 
+static int try_difference(const char *arg)
+{
+	char *dotdot;
+	unsigned char sha1[20];
+	unsigned char end[20];
+	const char *next;
+	const char *this;
+	int symmetric;
+
+	if (!(dotdot = strstr(arg, "..")))
+		return 0;
+	next = dotdot + 2;
+	this = arg;
+	symmetric = (*next == '.');
+
+	*dotdot = 0;
+	next += symmetric;
+
+	if (!*next)
+		next = "HEAD";
+	if (dotdot == arg)
+		this = "HEAD";
+	if (!get_sha1(this, sha1) && !get_sha1(next, end)) {
+		show_rev(NORMAL, end, next);
+		show_rev(symmetric ? NORMAL : REVERSED, sha1, this);
+		if (symmetric) {
+			struct commit_list *exclude;
+			struct commit *a, *b;
+			a = lookup_commit_reference(sha1);
+			b = lookup_commit_reference(end);
+			exclude = get_merge_bases(a, b, 1);
+			while (exclude) {
+				struct commit_list *n = exclude->next;
+				show_rev(REVERSED,
+					 exclude->item->object.sha1,NULL);
+				free(exclude);
+				exclude = n;
+			}
+		}
+		return 1;
+	}
+	*dotdot = '.';
+	return 0;
+}
+
 int cmd_rev_parse(int argc, const char **argv, char **envp)
 {
 	int i, as_is = 0, verify = 0;
@@ -174,7 +219,6 @@ int cmd_rev_parse(int argc, const char **argv, char **envp)
 
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
-		char *dotdot;
 
 		if (as_is) {
 			if (show_file(arg) && as_is < 2)
@@ -326,23 +370,8 @@ int cmd_rev_parse(int argc, const char **argv, char **envp)
 		}
 
 		/* Not a flag argument */
-		dotdot = strstr(arg, "..");
+		if (try_difference(arg))
-		if (dotdot) {
-			unsigned char end[20];
-			const char *next = dotdot + 2;
-			const char *this = arg;
-			*dotdot = 0;
-			if (!*next)
-				next = "HEAD";
-			if (dotdot == arg)
-				this = "HEAD";
-			if (!get_sha1(this, sha1) && !get_sha1(next, end)) {
-				show_rev(NORMAL, end, next);
-				show_rev(REVERSED, sha1, this);
 			continue;
-			}
-			*dotdot = '.';
-		}
 		if (!get_sha1(arg, sha1)) {
 			show_rev(NORMAL, sha1, arg);
 			continue;

commit.c

@@ -397,12 +397,13 @@ void clear_commit_marks(struct commit *commit, unsigned int mark)
 {
 	struct commit_list *parents;
 
-	parents = commit->parents;
 	commit->object.flags &= ~mark;
+	parents = commit->parents;
 	while (parents) {
 		struct commit *parent = parents->item;
-		if (parent && parent->object.parsed &&
+
-		    (parent->object.flags & mark))
+		/* Have we already cleared this? */
+		if (mark & parent->object.flags)
 			clear_commit_marks(parent, mark);
 		parents = parents->next;
 	}
@@ -846,3 +847,247 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
 	}
 	free(nodes);
 }
+
+/* merge-rebase stuff */
+
+/* bits #0..7 in revision.h */
+#define PARENT1		(1u<< 8)
+#define PARENT2		(1u<< 9)
+#define STALE		(1u<<10)
+
+static struct commit *interesting(struct commit_list *list)
+{
+	while (list) {
+		struct commit *commit = list->item;
+		list = list->next;
+		if (commit->object.flags & STALE)
+			continue;
+		return commit;
+	}
+	return NULL;
+}
+
+/*
+ * A pathological example of how this thing works.
+ *
+ * Suppose we had this commit graph, where chronologically
+ * the timestamp on the commit are A <= B <= C <= D <= E <= F
+ * and we are trying to figure out the merge base for E and F
+ * commits.
+ *
+ *                  F
+ *                 / \
+ *            E   A   D
+ *             \ /   /
+ *              B   /
+ *               \ /
+ *                C
+ *
+ * First we push E and F to list to be processed.  E gets bit 1
+ * and F gets bit 2.  The list becomes:
+ *
+ *     list=F(2) E(1), result=empty
+ *
+ * Then we pop F, the newest commit, from the list.  Its flag is 2.
+ * We scan its parents, mark them reachable from the side that F is
+ * reachable from, and push them to the list:
+ *
+ *     list=E(1) D(2) A(2), result=empty
+ *
+ * Next pop E and do the same.
+ *
+ *     list=D(2) B(1) A(2), result=empty
+ *
+ * Next pop D and do the same.
+ *
+ *     list=C(2) B(1) A(2), result=empty
+ *
+ * Next pop C and do the same.
+ *
+ *     list=B(1) A(2), result=empty
+ *
+ * Now it is B's turn.  We mark its parent, C, reachable from B's side,
+ * and push it to the list:
+ *
+ *     list=C(3) A(2), result=empty
+ *
+ * Now pop C and notice it has flags==3.  It is placed on the result list,
+ * and the list now contains:
+ *
+ *     list=A(2), result=C(3)
+ *
+ * We pop A and do the same.
+ *
+ *     list=B(3), result=C(3)
+ *
+ * Next, we pop B and something very interesting happens.  It has flags==3
+ * so it is also placed on the result list, and its parents are marked
+ * stale, retroactively, and placed back on the list:
+ *
+ *    list=C(7), result=C(7) B(3)
+ *
+ * Now, list does not have any interesting commit.  So we find the newest
+ * commit from the result list that is not marked stale.  Which is
+ * commit B.
+ *
+ *
+ * Another pathological example how this thing used to fail to mark an
+ * ancestor of a merge base as STALE before we introduced the
+ * postprocessing phase (mark_reachable_commits).
+ *
+ *		  2
+ *		  H
+ *	    1    / \
+ *	    G   A   \
+ *	    |\ /     \
+ *	    | B       \
+ *	    |  \       \
+ *	     \  C       F
+ *	      \  \     /
+ *	       \  D   /
+ *		\ |  /
+ *		 \| /
+ *		  E
+ *
+ *	 list			A B C D E F G H
+ *	 G1 H2			- - - - - - 1 2
+ *	 H2 E1 B1		- 1 - - 1 - 1 2
+ *	 F2 E1 B1 A2		2 1 - - 1 2 1 2
+ *	 E3 B1 A2		2 1 - - 3 2 1 2
+ *	 B1 A2			2 1 - - 3 2 1 2
+ *	 C1 A2			2 1 1 - 3 2 1 2
+ *	 D1 A2			2 1 1 1 3 2 1 2
+ *	 A2			2 1 1 1 3 2 1 2
+ *	 B3			2 3 1 1 3 2 1 2
+ *	 C7			2 3 7 1 3 2 1 2
+ *
+ * At this point, unfortunately, everybody in the list is
+ * stale, so we fail to complete the following two
+ * steps to fully marking stale commits.
+ *
+ *	 D7			2 3 7 7 3 2 1 2
+ *	 E7			2 3 7 7 7 2 1 2
+ *
+ * and we ended up showing E as an interesting merge base.
+ * The postprocessing phase re-injects C and continues traversal
+ * to contaminate D and E.
+ */
+
+static void mark_reachable_commits(struct commit_list *result,
+				   struct commit_list *list)
+{
+	struct commit_list *tmp;
+
+	/*
+	 * Postprocess to fully contaminate the well.
+	 */
+	for (tmp = result; tmp; tmp = tmp->next) {
+		struct commit *c = tmp->item;
+		/* Reinject stale ones to list,
+		 * so we can scan their parents.
+		 */
+		if (c->object.flags & STALE)
+			commit_list_insert(c, &list);
+	}
+	while (list) {
+		struct commit *c = list->item;
+		struct commit_list *parents;
+
+		tmp = list;
+		list = list->next;
+		free(tmp);
+
+		/* Anything taken out of the list is stale, so
+		 * mark all its parents stale.  We do not
+		 * parse new ones (we already parsed all the relevant
+		 * ones).
+		 */
+		parents = c->parents;
+		while (parents) {
+			struct commit *p = parents->item;
+			parents = parents->next;
+			if (!(p->object.flags & STALE)) {
+				p->object.flags |= STALE;
+				commit_list_insert(p, &list);
+			}
+		}
+	}
+}
+
+struct commit_list *get_merge_bases(struct commit *rev1, struct commit *rev2,
+                                    int cleanup)
+{
+	struct commit_list *list = NULL;
+	struct commit_list *result = NULL;
+	struct commit_list *tmp = NULL;
+
+	if (rev1 == rev2)
+		return commit_list_insert(rev1, &result);
+
+	parse_commit(rev1);
+	parse_commit(rev2);
+
+	rev1->object.flags |= PARENT1;
+	rev2->object.flags |= PARENT2;
+	insert_by_date(rev1, &list);
+	insert_by_date(rev2, &list);
+
+	while (interesting(list)) {
+		struct commit *commit = list->item;
+		struct commit_list *parents;
+		int flags = commit->object.flags
+			& (PARENT1 | PARENT2 | STALE);
+
+		tmp = list;
+		list = list->next;
+		free(tmp);
+		if (flags == (PARENT1 | PARENT2)) {
+			insert_by_date(commit, &result);
+
+			/* Mark parents of a found merge stale */
+			flags |= STALE;
+		}
+		parents = commit->parents;
+		while (parents) {
+			struct commit *p = parents->item;
+			parents = parents->next;
+			if ((p->object.flags & flags) == flags)
+				continue;
+			parse_commit(p);
+			p->object.flags |= flags;
+			insert_by_date(p, &list);
+		}
+	}
+
+	if (!result)
+		goto finish;
+
+	if (result->next && list)
+		mark_reachable_commits(result, list);
+
+	/* cull duplicates */
+	for (tmp = result, list = NULL; tmp; ) {
+		struct commit *commit = tmp->item;
+		struct commit_list *next = tmp->next;
+		if (commit->object.flags & STALE) {
+			if (list != NULL)
+				list->next = next;
+			free(tmp);
+		} else {
+			if (list == NULL)
+				result = tmp;
+			list = tmp;
+			commit->object.flags |= STALE;
+		}
+
+		tmp = next;
+	}
+
+ finish:
+	if (cleanup) {
+		clear_commit_marks(rev1, PARENT1 | PARENT2 | STALE);
+		clear_commit_marks(rev2, PARENT1 | PARENT2 | STALE);
+	}
+
+	return result;
+}

commit.h

@@ -105,4 +105,6 @@ struct commit_graft *read_graft_line(char *buf, int len);
 int register_commit_graft(struct commit_graft *, int);
 int read_graft_file(const char *graft_file);
 
+extern struct commit_list *get_merge_bases(struct commit *rev1, struct commit *rev2, int cleanup);
+
 #endif /* COMMIT_H */

merge-base.c

@@ -2,232 +2,22 @@
 #include "cache.h"
 #include "commit.h"
 
-#define PARENT1 1
-#define PARENT2 2
-#define UNINTERESTING 4
-
-static struct commit *interesting(struct commit_list *list)
-{
-	while (list) {
-		struct commit *commit = list->item;
-		list = list->next;
-		if (commit->object.flags & UNINTERESTING)
-			continue;
-		return commit;
-	}
-	return NULL;
-}
-
-/*
- * A pathological example of how this thing works.
- *
- * Suppose we had this commit graph, where chronologically
- * the timestamp on the commit are A <= B <= C <= D <= E <= F
- * and we are trying to figure out the merge base for E and F
- * commits.
- *
- *                  F
- *                 / \
- *            E   A   D
- *             \ /   /  
- *              B   /
- *               \ /
- *                C
- *
- * First we push E and F to list to be processed.  E gets bit 1
- * and F gets bit 2.  The list becomes:
- *
- *     list=F(2) E(1), result=empty
- *
- * Then we pop F, the newest commit, from the list.  Its flag is 2.
- * We scan its parents, mark them reachable from the side that F is
- * reachable from, and push them to the list:
- *
- *     list=E(1) D(2) A(2), result=empty
- *
- * Next pop E and do the same.
- *
- *     list=D(2) B(1) A(2), result=empty
- *
- * Next pop D and do the same.
- *
- *     list=C(2) B(1) A(2), result=empty
- *
- * Next pop C and do the same.
- *
- *     list=B(1) A(2), result=empty
- *
- * Now it is B's turn.  We mark its parent, C, reachable from B's side,
- * and push it to the list:
- *
- *     list=C(3) A(2), result=empty
- *
- * Now pop C and notice it has flags==3.  It is placed on the result list,
- * and the list now contains:
- *
- *     list=A(2), result=C(3)
- *
- * We pop A and do the same.
- * 
- *     list=B(3), result=C(3)
- *
- * Next, we pop B and something very interesting happens.  It has flags==3
- * so it is also placed on the result list, and its parents are marked
- * uninteresting, retroactively, and placed back on the list:
- *
- *    list=C(7), result=C(7) B(3)
- * 
- * Now, list does not have any interesting commit.  So we find the newest
- * commit from the result list that is not marked uninteresting.  Which is
- * commit B.
- *
- *
- * Another pathological example how this thing used to fail to mark an
- * ancestor of a merge base as UNINTERESTING before we introduced the
- * postprocessing phase (mark_reachable_commits).
- *
- *		  2
- *		  H
- *	    1    / \
- *	    G   A   \
- *	    |\ /     \ 
- *	    | B       \
- *	    |  \       \
- *	     \  C       F
- *	      \  \     / 
- *	       \  D   /   
- *		\ |  /
- *		 \| /
- *		  E
- *
- *	 list			A B C D E F G H
- *	 G1 H2			- - - - - - 1 2
- *	 H2 E1 B1		- 1 - - 1 - 1 2
- *	 F2 E1 B1 A2		2 1 - - 1 2 1 2
- *	 E3 B1 A2		2 1 - - 3 2 1 2
- *	 B1 A2			2 1 - - 3 2 1 2
- *	 C1 A2			2 1 1 - 3 2 1 2
- *	 D1 A2			2 1 1 1 3 2 1 2
- *	 A2			2 1 1 1 3 2 1 2
- *	 B3			2 3 1 1 3 2 1 2
- *	 C7			2 3 7 1 3 2 1 2
- *
- * At this point, unfortunately, everybody in the list is
- * uninteresting, so we fail to complete the following two
- * steps to fully marking uninteresting commits.
- *
- *	 D7			2 3 7 7 3 2 1 2
- *	 E7			2 3 7 7 7 2 1 2
- *
- * and we ended up showing E as an interesting merge base.
- * The postprocessing phase re-injects C and continues traversal
- * to contaminate D and E.
- */
-
 static int show_all = 0;
 
-static void mark_reachable_commits(struct commit_list *result,
-				   struct commit_list *list)
-{
-	struct commit_list *tmp;
-
-	/*
-	 * Postprocess to fully contaminate the well.
-	 */
-	for (tmp = result; tmp; tmp = tmp->next) {
-		struct commit *c = tmp->item;
-		/* Reinject uninteresting ones to list,
-		 * so we can scan their parents.
-		 */
-		if (c->object.flags & UNINTERESTING)
-			commit_list_insert(c, &list);
-	}
-	while (list) {
-		struct commit *c = list->item;
-		struct commit_list *parents;
-
-		tmp = list;
-		list = list->next;
-		free(tmp);
-
-		/* Anything taken out of the list is uninteresting, so
-		 * mark all its parents uninteresting.  We do not
-		 * parse new ones (we already parsed all the relevant
-		 * ones).
-		 */
-		parents = c->parents;
-		while (parents) {
-			struct commit *p = parents->item;
-			parents = parents->next;
-			if (!(p->object.flags & UNINTERESTING)) {
-				p->object.flags |= UNINTERESTING;
-				commit_list_insert(p, &list);
-			}
-		}
-	}
-}
-
 static int merge_base(struct commit *rev1, struct commit *rev2)
 {
-	struct commit_list *list = NULL;
+	struct commit_list *result = get_merge_bases(rev1, rev2, 0);
-	struct commit_list *result = NULL;
-	struct commit_list *tmp = NULL;
-
-	if (rev1 == rev2) {
-		printf("%s\n", sha1_to_hex(rev1->object.sha1));
-		return 0;
-	}
-
-	parse_commit(rev1);
-	parse_commit(rev2);
-
-	rev1->object.flags |= 1;
-	rev2->object.flags |= 2;
-	insert_by_date(rev1, &list);
-	insert_by_date(rev2, &list);
-
-	while (interesting(list)) {
-		struct commit *commit = list->item;
-		struct commit_list *parents;
-		int flags = commit->object.flags & 7;
-
-		tmp = list;
-		list = list->next;
-		free(tmp);
-		if (flags == 3) {
-			insert_by_date(commit, &result);
-
-			/* Mark parents of a found merge uninteresting */
-			flags |= UNINTERESTING;
-		}
-		parents = commit->parents;
-		while (parents) {
-			struct commit *p = parents->item;
-			parents = parents->next;
-			if ((p->object.flags & flags) == flags)
-				continue;
-			parse_commit(p);
-			p->object.flags |= flags;
-			insert_by_date(p, &list);
-		}
-	}
 
 	if (!result)
 		return 1;
 
-	if (result->next && list)
-		mark_reachable_commits(result, list);
-
 	while (result) {
-		struct commit *commit = result->item;
+		printf("%s\n", sha1_to_hex(result->item->object.sha1));
-		result = result->next;
-		if (commit->object.flags & UNINTERESTING)
-			continue;
-		printf("%s\n", sha1_to_hex(commit->object.sha1));
 		if (!show_all)
 			return 0;
-		commit->object.flags |= UNINTERESTING;
+		result = result->next;
 	}
+
 	return 0;
 }
 

revision.c

@@ -537,6 +537,18 @@ void init_revisions(struct rev_info *revs)
 	diff_setup(&revs->diffopt);
 }
 
+static void add_pending_commit_list(struct rev_info *revs,
+                                    struct commit_list *commit_list,
+                                    unsigned int flags)
+{
+	while (commit_list) {
+		struct object *object = &commit_list->item->object;
+		object->flags |= flags;
+		add_pending_object(revs, object, sha1_to_hex(object->sha1));
+		commit_list = commit_list->next;
+	}
+}
+
 /*
  * Parse revision information, filling in the "rev_info" structure,
  * and removing the used arguments from the argument list.
@@ -772,27 +784,46 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 			unsigned char from_sha1[20];
 			const char *next = dotdot + 2;
 			const char *this = arg;
+			int symmetric = *next == '.';
+			unsigned int flags_exclude = flags ^ UNINTERESTING;
+
 			*dotdot = 0;
+			next += symmetric;
+
 			if (!*next)
 				next = "HEAD";
 			if (dotdot == arg)
 				this = "HEAD";
 			if (!get_sha1(this, from_sha1) &&
 			    !get_sha1(next, sha1)) {
-				struct object *exclude;
+				struct commit *a, *b;
-				struct object *include;
+				struct commit_list *exclude;
 
-				exclude = get_reference(revs, this, from_sha1, flags ^ UNINTERESTING);
+				a = lookup_commit_reference(from_sha1);
-				include = get_reference(revs, next, sha1, flags);
+				b = lookup_commit_reference(sha1);
-				if (!exclude || !include)
+				if (!a || !b) {
-					die("Invalid revision range %s..%s", arg, next);
+					die(symmetric ?
+					    "Invalid symmetric difference expression %s...%s" :
+					    "Invalid revision range %s..%s",
+					    arg, next);
+				}
 
 				if (!seen_dashdash) {
 					*dotdot = '.';
 					verify_non_filename(revs->prefix, arg);
 				}
-				add_pending_object(revs, exclude, this);
+
-				add_pending_object(revs, include, next);
+				if (symmetric) {
+					exclude = get_merge_bases(a, b, 1);
+					add_pending_commit_list(revs, exclude,
+					                        flags_exclude);
+					free_commit_list(exclude);
+					a->object.flags |= flags;
+				} else
+					a->object.flags |= flags_exclude;
+				b->object.flags |= flags;
+				add_pending_object(revs, &a->object, this);
+				add_pending_object(revs, &b->object, next);
 				continue;
 			}
 			*dotdot = '.';