Merge branch 'tc/replay-linearize' into jch

The 'git replay' command has been taught the '--linearize' option to
drop merge commits and linearize the replayed history, mimicking 'git
rebase --no-rebase-merges'.

* tc/replay-linearize:
  replay: offer an option to linearize the commit topology
  replay: resolve the replay base outside pick_regular_commit()
  replay: add helper to put entry into replayed_commits

Documentation/git-replay.adoc

@@ -10,7 +10,7 @@ SYNOPSIS
 --------
 [verse]
 (EXPERIMENTAL!) 'git replay' ([--contained] --onto=<newbase> | --advance=<branch> | --revert=<branch>)
-			     [--ref=<ref>] [--ref-action=<mode>] <revision-range>
+			     [--ref=<ref>] [--ref-action=<mode>] [--linearize] <revision-range>
 
 DESCRIPTION
 -----------
@@ -91,6 +91,23 @@ Expanded description list compared to 'replay.refAction'.
 +
 The default mode can be configured via the `replay.refAction` configuration variable.
 
+--linearize::
+	In this mode, each replayed commit is stacked on top of the
+	previously replayed one, so all replayed commits are flattened into
+	a single linear history.
++
+When a merge commit is encountered, the behavior of git-rebase(1)'s
+option `--no-rebase-merges` is imitated. All commits in the range
+reachable from the merge commit are replayed into a linear history, and
+the merge commit itself is dropped. A ref that pointed to a merge commit
+is updated to the merge's last replayed ancestor.
++
+Only a single branch can be linearized at a time: `--linearize` cannot
+be combined with multiple positive revisions or with `--contained`,
+because that would concatenate otherwise unrelated histories into one
+line. To linearize several branches, replay them in separate `git
+replay` invocations.
+
 <revision-range>::
 	Range of commits to replay; see "Specifying Ranges" in
 	linkgit:git-rev-parse[1]. In `--advance=<branch>` or

builtin/replay.c

@@ -85,7 +85,7 @@ int cmd_replay(int argc,
 	const char *const replay_usage[] = {
 		N_("(EXPERIMENTAL!) git replay "
 		   "([--contained] --onto=<newbase> | --advance=<branch> | --revert=<branch>)\n"
-		   "[--ref=<ref>] [--ref-action=<mode>] <revision-range>"),
+		   "[--ref=<ref>] [--ref-action=<mode>] [--linearize] <revision-range>"),
 		NULL
 	};
 	struct option replay_options[] = {
@@ -111,6 +111,8 @@ int cmd_replay(int argc,
 			     N_("mode"),
 			     N_("control ref update behavior (update|print)"),
 			     PARSE_OPT_NONEG),
+		OPT_BOOL(0, "linearize", &opts.linearize,
+			 N_("drop merge commits, replaying only non-merge commits")),
 		OPT_END()
 	};
 
@@ -132,6 +134,8 @@ int cmd_replay(int argc,
 				  opts.contained, "--contained");
 	die_for_incompatible_opt2(!!opts.ref, "--ref",
 				  !!opts.contained, "--contained");
+	die_for_incompatible_opt2(opts.linearize, "--linearize",
+				  !!opts.contained, "--contained");
 
 	/* Parse ref action mode from command line or config */
 	ref_mode = get_ref_action_mode(repo, ref_action);

replay.c

@@ -254,9 +254,9 @@ static void set_up_replay_mode(struct repository *repo,
 	strset_clear(&rinfo.positive_refs);
 }
 
-static struct commit *mapped_commit(kh_oid_map_t *replayed_commits,
-				    struct commit *commit,
-				    struct commit *fallback)
+static struct commit *get_mapped_commit(kh_oid_map_t *replayed_commits,
+					struct commit *commit,
+					struct commit *fallback)
 {
 	khint_t pos;
 	if (!commit)
@@ -267,27 +267,36 @@ static struct commit *mapped_commit(kh_oid_map_t *replayed_commits,
 	return kh_value(replayed_commits, pos);
 }
 
+static void put_mapped_commit(kh_oid_map_t *replayed_commits,
+			      struct commit *commit,
+			      struct commit *new_commit)
+{
+	khint_t pos;
+	int ret;
+
+	pos = kh_put_oid_map(replayed_commits, commit->object.oid, &ret);
+	if (ret == 0)
+		BUG("Duplicate rewritten commit: %s",
+		    oid_to_hex(&commit->object.oid));
+
+	kh_value(replayed_commits, pos) = new_commit;
+}
+
 static struct commit *pick_regular_commit(struct repository *repo,
 					  struct commit *pickme,
-					  kh_oid_map_t *replayed_commits,
-					  struct commit *onto,
+					  struct commit *replayed_base,
 					  struct merge_options *merge_opt,
 					  struct merge_result *result,
 					  enum replay_mode mode,
 					  enum replay_empty_commit_action empty)
 {
-	struct commit *base, *replayed_base;
 	struct tree *pickme_tree, *base_tree, *replayed_base_tree;
 
-	if (pickme->parents) {
-		base = pickme->parents->item;
-		base_tree = repo_get_commit_tree(repo, base);
-	} else {
-		base = NULL;
+	if (pickme->parents)
+		base_tree = repo_get_commit_tree(repo, pickme->parents->item);
+	else
 		base_tree = lookup_tree(repo, repo->hash_algo->empty_tree);
-	}
 
-	replayed_base = mapped_commit(replayed_commits, base, onto);
 	replayed_base_tree = repo_get_commit_tree(repo, replayed_base);
 	pickme_tree = repo_get_commit_tree(repo, pickme);
 
@@ -395,6 +404,12 @@ int replay_revisions(struct rev_info *revs,
 	set_up_replay_mode(revs->repo, &revs->cmdline, opts->onto,
 			   &detached_head, &advance, &revert, &onto, &update_refs);
 
+	if (opts->linearize &&
+	    update_refs && strset_get_size(update_refs) > 1) {
+		ret = error(_("'--linearize' cannot be used with multiple revision ranges"));
+		goto out;
+	}
+
 	if (opts->ref) {
 		struct object_id oid;
 
@@ -427,24 +442,46 @@ int replay_revisions(struct rev_info *revs,
 	replayed_commits = kh_init_oid_map();
 	while ((commit = get_revision(revs))) {
 		const struct name_decoration *decoration;
-		khint_t pos;
-		int hr;
 
-		if (commit->parents && commit->parents->next)
-			die(_("replaying merge commits is not supported yet!"));
+		if (commit->parents && commit->parents->next) {
+			if (!opts->linearize)
+				die(_("replaying merge commits is not supported yet!"));
+			/*
+			 * Drop the merge commit: do not pick it, leave
+			 * `last_commit` unchanged, and fall through to the
+			 * rest of the loop. As a result:
+			 * - refs pointing to the merge commit will be updated
+			 *   to `last_commit`.
+			 * - the next replayed commit uses `last_commit` as its
+			 *   `base`.
+			 */
+		} else {
+			/*
+			 * Decide where to replay this commit onto.
+			 * If the parent commit was replayed already, the replayed result
+			 * can be found in `replayed_commits`. Otherwise fall back to `onto`.
+			 * When reverting, commits are replayed in reverse order and thus
+			 * its parent isn't replayed yet. Therefore revert commits are
+			 * always replayed onto `last_commit`.
+			 * Also when opts->linearize is true, set the base to
+			 * `last_commit` to create a single linear history.
+			 */
+			struct commit *parent = commit->parents ? commit->parents->item : NULL;
+			struct commit *base = get_mapped_commit(replayed_commits, parent, onto);
+
+			if (opts->linearize || mode == REPLAY_MODE_REVERT)
+				base = last_commit;
+
+			last_commit = pick_regular_commit(revs->repo, commit, base,
+							  &merge_opt, &result,
+							  mode, opts->empty);
+		}
 
-		last_commit = pick_regular_commit(revs->repo, commit, replayed_commits,
-						  mode == REPLAY_MODE_REVERT ? last_commit : onto,
-						  &merge_opt, &result, mode, opts->empty);
 		if (!last_commit)
 			break;
 
 		/* Record commit -> last_commit mapping */
-		pos = kh_put_oid_map(replayed_commits, commit->object.oid, &hr);
-		if (hr == 0)
-			BUG("Duplicate rewritten commit: %s\n",
-			    oid_to_hex(&commit->object.oid));
-		kh_value(replayed_commits, pos) = last_commit;
+		put_mapped_commit(replayed_commits, commit, last_commit);
 
 		/* Update any necessary branches */
 		if (ref)

replay.h

@@ -62,6 +62,11 @@ struct replay_revisions_options {
 	 * Defaults to REPLAY_EMPTY_COMMIT_DROP.
 	 */
 	enum replay_empty_commit_action empty;
+
+	/*
+	 * Whether to linearize the commits (i.e. drop merge commits).
+	 */
+	int linearize;
 };
 
 /* This struct is used as an out-parameter by `replay_revisions()`. */

t/t3650-replay-basics.sh

@@ -52,8 +52,19 @@ test_expect_success 'setup' '
 	test_merge P O --no-ff &&
 	git switch main &&
 
+	git switch --orphan unrelated &&
+	test_commit unrelated-root &&
+
 	git switch -c conflict B &&
-	test_commit C.conflict C.t conflict
+	test_commit C.conflict C.t conflict &&
+	git branch -D unrelated &&
+
+	git switch -c divergent-x main &&
+	test_commit X &&
+	git switch -c divergent-y main &&
+	test_commit Y &&
+	git switch divergent-x &&
+	test_merge Z divergent-y --no-ff
 '
 
 test_expect_success 'setup bare' '
@@ -565,4 +576,100 @@ test_expect_success '--onto with --ref rejects multiple revision ranges' '
 	test_grep "cannot be used with multiple revision ranges" err
 '
 
+test_expect_success 'replay to rebase merge commit with --linearize' '
+	git replay --ref-action=print --linearize \
+		--onto main I..topic-with-merge >result &&
+
+	test_line_count = 1 result &&
+
+	git log --format=%s $(cut -f 3 -d " " result) >actual &&
+	test_write_lines O N J M L B A >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'replay to rebase merge commit with --linearize down to the root commit' '
+	git replay --ref-action=print --linearize \
+		--onto unrelated-root topic-with-merge >result &&
+
+	test_line_count = 1 result &&
+
+	git log --format=%s $(cut -f 3 -d " " result) >actual &&
+	test_write_lines O N J I B A unrelated-root >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'replay to cherry-pick merge commit with --linearize' '
+	git replay --ref-action=print --linearize \
+		--advance main I..topic-with-merge >result &&
+
+	test_line_count = 1 result &&
+
+	git log --format=%s $(cut -f 3 -d " " result) >actual &&
+	test_write_lines O N J M L B A >expect &&
+	test_cmp expect actual &&
+
+	printf "update refs/heads/main " >expect &&
+	printf "%s " $(cut -f 3 -d " " result) >>expect &&
+	git rev-parse main >>expect &&
+	test_cmp expect result
+'
+
+test_expect_success 'replay --linearize produces the same patches' '
+	git replay --ref-action=print --linearize \
+		--onto main I..topic-with-merge >result &&
+
+	test_line_count = 1 result &&
+	tip=$(cut -f 3 -d " " result) &&
+
+	# range-diff does not care about the dropped merge,
+	# so the original commits (I..topic-with-merge)
+	# and the replayed chain (main..tip) must produce identical patches.
+	git range-diff I..topic-with-merge main..$tip >out &&
+	test_file_not_empty out &&
+	test_grep ! -v "=" out &&
+
+	git log --oneline main..$tip >out &&
+	test_line_count = 3 out
+'
+
+test_expect_success '--linearize rejects multiple revision ranges' '
+	test_must_fail git replay --ref-action=print --linearize \
+		--onto main ^B topic2 topic3 topic4 2>err &&
+	test_grep "cannot be used with multiple revision ranges" err
+'
+
+test_expect_success 'replay with --linearize of a divergent merge keeps both sides' '
+	git replay --ref-action=print --linearize \
+		--onto main main..divergent-x >result &&
+	test_line_count = 1 result &&
+	tip=$(cut -f 3 -d " " result) &&
+
+	# The merge Z is dropped, but both X and Y are linearized onto main;
+	# neither side is lost.
+	git log --format=%s main..$tip >actual &&
+	test_write_lines Y X >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success '--linearize and --contained cannot be used together' '
+	test_must_fail git replay --ref-action=print --linearize --contained \
+		--onto main ^B topic-with-merge 2>err &&
+	test_grep "cannot be used together" err
+'
+
+test_expect_success 'replay --revert with --linearize reverts a range containing a merge' '
+	git replay --ref-action=print --revert=divergent-x --linearize \
+		main..divergent-x >result &&
+	test_line_count = 1 result &&
+	tip=$(cut -f 3 -d " " result) &&
+
+	git log --format=%s $tip >actual &&
+	test_write_lines \
+		"Revert \"X\"" "Revert \"Y\"" Z Y X M L B A >expect &&
+	test_cmp expect actual &&
+
+	test_must_fail git cat-file -e $tip:X.t &&
+	test_must_fail git cat-file -e $tip:Y.t
+'
+
 test_done