builtin/history: implement "drop" subcommand

A common operation when editing the commit history is to drop a specific
commit from the history entirely, but this operation is not currently
covered by git-history(1).

A couple of noteworthy bits:

  - This is the first git-history(1) command that will ultimately result
    in changes to both the index and the working tree. We thus have to
    add logic to merge resulting changes into those.

  - It is still not possible to replay merge commits, so this limitation
    is inherited for the new "drop" command.

  - For now we refuse to drop root commits. While we _can_ indeed drop
    root commits in the general case, there are edge cases where the
    resulting history would become completely empty. This is thus left
    to a subsequent patch series.

Other than that, most of the logic is rather straight-forward as we can
continue to build on the preexisting logic in git-history(1) for most of
the part.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: pks-t

Documentation/git-history.adoc

@@ -8,6 +8,7 @@ git-history - EXPERIMENTAL: Rewrite history
 SYNOPSIS
 --------
 [synopsis]
+git history drop <commit> [--dry-run] [--update-refs=(branches|head)] [--empty=(drop|keep|abort)]
 git history fixup <commit> [--dry-run] [--update-refs=(branches|head)] [--reedit-message] [--empty=(drop|keep|abort)]
 git history reword <commit> [--dry-run] [--update-refs=(branches|head)]
 git history split <commit> [--dry-run] [--update-refs=(branches|head)] [--] [<pathspec>...]
@@ -51,13 +52,28 @@ be stateful operations. The limitation can be lifted once (if) Git learns about
 first-class conflicts.
 
 When using `fixup` with `--empty=drop`, dropping the root commit is not yet
-supported.
+supported. Likewise, `drop` cannot remove the root commit or a merge commit.
 
 COMMANDS
 --------
 
 The following commands are available to rewrite history in different ways:
 
+`drop <commit>`::
+	Remove the specified commit from the history. All descendants of the
+	commit are replayed directly onto its parent.
++
+The root commit cannot be dropped as that may lead to edge cases where refs
+end up with no commits anymore. Merge commits cannot be dropped either; see
+LIMITATIONS.
++
+If `HEAD` points at a commit that is to be rewritten, the index and working
+tree are updated to match the new `HEAD`. The command aborts before any
+references are updated in case local modifications would be overwritten.
++
+If replaying any descendant would result in a conflict, the command aborts
+with an error.
+
 `fixup <commit>`::
 	Apply the currently staged changes to the specified commit. This is
 	similar in nature to `git commit --fixup=<commit>` followed by `git
@@ -170,6 +186,26 @@ The staged addition of `unrelated.txt` has been incorporated into the `first`
 commit. All descendant commits have been replayed on top of the rewritten
 history.
 
+Drop a commit
+~~~~~~~~~~~~~
+
+----------
+$ git log --oneline
+abc1234 (HEAD -> main) third
+def5678 second
+ghi9012 first
+
+$ git history drop 'main^{/second}'
+
+$ git log --oneline
+jkl3456 (HEAD -> main) third
+ghi9012 first
+----------
+
+The `second` commit has been removed from the history, and `third` has been
+replayed directly on top of `first`. All branches that pointed at the dropped
+commit have been moved to its parent.
+
 Split a commit
 ~~~~~~~~~~~~~~
 

builtin/history.c

@@ -17,13 +17,17 @@
 #include "read-cache.h"
 #include "refs.h"
 #include "replay.h"
+#include "reset.h"
 #include "revision.h"
 #include "sequencer.h"
 #include "strvec.h"
 #include "tree.h"
+#include "tree-walk.h"
 #include "unpack-trees.h"
 #include "wt-status.h"
 
+#define GIT_HISTORY_DROP_USAGE \
+	N_("git history drop <commit> [--dry-run] [--update-refs=(branches|head)] [--empty=(drop|keep|abort)]")
 #define GIT_HISTORY_FIXUP_USAGE \
 	N_("git history fixup <commit> [--dry-run] [--update-refs=(branches|head)] [--reedit-message] [--empty=(drop|keep|abort)]")
 #define GIT_HISTORY_REWORD_USAGE \
@@ -1001,19 +1005,201 @@ static int cmd_history_split(int argc,
 	return ret;
 }
 
+static int update_worktree(struct repository *repo,
+			   const struct commit *old_head,
+			   const struct commit *new_head,
+			   bool dry_run)
+{
+	struct reset_working_tree_options opts = {
+		.oid_from = &old_head->object.oid,
+		.oid = &new_head->object.oid,
+	};
+	if (dry_run)
+		opts.flags |= RESET_WORKING_TREE_DRY_RUN;
+	return reset_working_tree(repo, &opts);
+}
+
+static int find_head_tree_change(struct repository *repo,
+				 const struct replay_result *result,
+				 struct commit **old_head,
+				 struct commit **new_head,
+				 bool *changed)
+{
+	const struct replay_ref_update *head_update = NULL;
+	struct commit *old_head_commit, *new_head_commit;
+	struct tree *old_head_tree, *new_head_tree;
+	const char *head_target;
+	int head_flags;
+
+	*changed = false;
+
+	head_target = refs_resolve_ref_unsafe(get_main_ref_store(repo),
+					      "HEAD", RESOLVE_REF_NO_RECURSE,
+					      NULL, &head_flags);
+	if (!head_target)
+		return error(_("cannot look up HEAD"));
+	if (!(head_flags & REF_ISSYMREF))
+		head_target = "HEAD";
+
+	for (size_t i = 0; i < result->updates_nr; i++) {
+		if (!strcmp(result->updates[i].refname, head_target)) {
+			head_update = &result->updates[i];
+			break;
+		}
+	}
+
+	if (!head_update)
+		return 0;
+
+	old_head_commit = lookup_commit_reference(repo, &head_update->old_oid);
+	new_head_commit = lookup_commit_reference(repo, &head_update->new_oid);
+	if (!old_head_commit || !new_head_commit)
+		return error(_("cannot resolve HEAD commit"));
+
+	old_head_tree = repo_get_commit_tree(repo, old_head_commit);
+	new_head_tree = repo_get_commit_tree(repo, new_head_commit);
+	if (!old_head_tree || !new_head_tree)
+		return error(_("cannot resolve tree for HEAD"));
+
+	if (oideq(&old_head_tree->object.oid, &new_head_tree->object.oid))
+		return 0;
+
+	*old_head = old_head_commit;
+	*new_head = new_head_commit;
+	*changed = true;
+
+	return 0;
+}
+
+static int cmd_history_drop(int argc,
+			    const char **argv,
+			    const char *prefix,
+			    struct repository *repo)
+{
+	const char * const usage[] = {
+		GIT_HISTORY_DROP_USAGE,
+		NULL,
+	};
+	enum replay_empty_commit_action empty = REPLAY_EMPTY_COMMIT_DROP;
+	enum ref_action action = REF_ACTION_DEFAULT;
+	int dry_run = 0;
+	struct option options[] = {
+		OPT_CALLBACK_F(0, "update-refs", &action, "(branches|head)",
+			       N_("control which refs should be updated"),
+			       PARSE_OPT_NONEG, parse_ref_action),
+		OPT_BOOL('n', "dry-run", &dry_run,
+			 N_("perform a dry-run without updating any refs")),
+		OPT_CALLBACK_F(0, "empty", &empty, "(drop|keep|abort)",
+			       N_("how to handle descendants that become empty"),
+			       PARSE_OPT_NONEG, parse_opt_empty),
+		OPT_END(),
+	};
+	struct strbuf reflog_msg = STRBUF_INIT;
+	struct commit *original, *rewritten;
+	struct rev_info revs = { 0 };
+	struct replay_result result = { 0 };
+	struct commit *old_head, *new_head;
+	bool head_moves = false;
+	int ret;
+
+	argc = parse_options(argc, argv, prefix, options, usage, 0);
+	if (argc != 1) {
+		ret = error(_("command expects a single revision"));
+		goto out;
+	}
+	repo_config(repo, git_default_config, NULL);
+
+	if (action == REF_ACTION_DEFAULT)
+		action = REF_ACTION_BRANCHES;
+
+	original = lookup_commit_reference_by_name(argv[0]);
+	if (!original) {
+		ret = error(_("commit cannot be found: %s"), argv[0]);
+		goto out;
+	}
+
+	if (!original->parents) {
+		ret = error(_("cannot drop root commit %s: "
+			      "it has no parent to replay onto"),
+			    argv[0]);
+		goto out;
+	} else if (original->parents->next) {
+		ret = error(_("cannot drop merge commit: %s"), argv[0]);
+		goto out;
+	}
+
+	ret = setup_revwalk(repo, action, original, &revs);
+	if (ret)
+		goto out;
+
+	rewritten = original->parents->item;
+
+	ret = compute_pending_ref_updates(&revs, action, original, rewritten,
+					  empty, &result);
+	if (ret) {
+		ret = error(_("failed replaying descendants"));
+		goto out;
+	}
+
+	/*
+	 * If HEAD will move as a result of the rewrite then we'll have to
+	 * merge in the changes into the worktree and index. This merge can of
+	 * course conflict, which will cause the whole operation to abort.
+	 *
+	 * If we had already updated the refs at that point then we'd have an
+	 * inconsistent repository state. So we first perform a dry-run merge
+	 * here before updating refs.
+	 */
+	if (!is_bare_repository()) {
+		ret = find_head_tree_change(repo, &result, &old_head,
+					    &new_head, &head_moves);
+		if (ret < 0)
+			goto out;
+
+		if (head_moves && update_worktree(repo, old_head, new_head, true) < 0) {
+			ret = error(_("dropping this commit would "
+				      "overwrite local changes; aborting"));
+			goto out;
+		}
+	}
+
+	strbuf_addf(&reflog_msg, "drop: dropping %s", argv[0]);
+	ret = apply_pending_ref_updates(repo, &result, reflog_msg.buf, dry_run);
+	if (ret < 0) {
+		ret = error(_("failed to update references"));
+		goto out;
+	}
+
+	if (!dry_run && head_moves && update_worktree(repo, old_head, new_head, false) < 0) {
+		ret = error(_("could not update working tree to new commit %s"),
+			    oid_to_hex(&new_head->object.oid));
+		goto out;
+	}
+
+	ret = 0;
+
+out:
+	replay_result_release(&result);
+	strbuf_release(&reflog_msg);
+	release_revisions(&revs);
+	return ret;
+}
+
 int cmd_history(int argc,
 		const char **argv,
 		const char *prefix,
 		struct repository *repo)
 {
 	const char * const usage[] = {
+		GIT_HISTORY_DROP_USAGE,
 		GIT_HISTORY_FIXUP_USAGE,
 		GIT_HISTORY_REWORD_USAGE,
 		GIT_HISTORY_SPLIT_USAGE,
 		NULL,
 	};
 	parse_opt_subcommand_fn *fn = NULL;
 	struct option options[] = {
+		OPT_SUBCOMMAND("drop", &fn, cmd_history_drop),
 		OPT_SUBCOMMAND("fixup", &fn, cmd_history_fixup),
 		OPT_SUBCOMMAND("reword", &fn, cmd_history_reword),
 		OPT_SUBCOMMAND("split", &fn, cmd_history_split),

t/meson.build

@@ -399,6 +399,7 @@ integration_tests = [
   't3451-history-reword.sh',
   't3452-history-split.sh',
   't3453-history-fixup.sh',
+  't3454-history-drop.sh',
   't3500-cherry.sh',
   't3501-revert-cherry-pick.sh',
   't3502-cherry-pick-merge.sh',