Re: [GSoC][PATCH v2 2/2] rebase -i: support --committer-date-is-author-date

[Phillip Wood <phillip.wood123@gmail.com>]

Hi Rohit

It's good to see this patch reducing the differences between the rebase 
backends.

On 18/07/2019 20:03, Rohit Ashiwal wrote:
> rebase am already has this flag to "lie" about the committer date
> by changing it to the author date. Let's add the same for
> interactive machinery.
> 
> Signed-off-by: Rohit Ashiwal <rohit.ashiwal265@gmail.com>
> ---
>   Documentation/git-rebase.txt            |  7 ++--
>   builtin/rebase.c                        | 23 ++++++++++---
>   sequencer.c                             | 46 ++++++++++++++++++++++++-
>   sequencer.h                             |  1 +
>   t/t3422-rebase-incompatible-options.sh  |  1 -
>   t/t3431-rebase-options-compatibility.sh | 21 +++++++++++
>   6 files changed, 90 insertions(+), 9 deletions(-)
> 
> diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt
> index eda52ed824..ddd111de69 100644
> --- a/Documentation/git-rebase.txt
> +++ b/Documentation/git-rebase.txt
> @@ -383,8 +383,12 @@ default is `--no-fork-point`, otherwise the default is `--fork-point`.
>   See also INCOMPATIBLE OPTIONS below.
>   
>   --committer-date-is-author-date::
> +	Instead of recording the time the rebased commits are
> +	created as the committer date, reuse the author date
> +	as the committer date. This implies --force-rebase.
> +
>   --ignore-date::
> -	These flags are passed to 'git am' to easily change the dates
> +	This flag is passed to 'git am' to change the author date
>   	of the rebased commits (see linkgit:git-am[1]).
>   +
>   See also INCOMPATIBLE OPTIONS below.
> @@ -522,7 +526,6 @@ INCOMPATIBLE OPTIONS
>   
>   The following options:
>   
> - * --committer-date-is-author-date
>    * --ignore-date
>    * --whitespace
>    * -C
> diff --git a/builtin/rebase.c b/builtin/rebase.c
> index afe376c3fe..c317fbe53c 100644
> --- a/builtin/rebase.c
> +++ b/builtin/rebase.c
> @@ -82,6 +82,7 @@ struct rebase_options {
>   	int ignore_whitespace;
>   	char *gpg_sign_opt;
>   	int autostash;
> +	int committer_date_is_author_date;
>   	char *cmd;
>   	int allow_empty_message;
>   	int rebase_merges, rebase_cousins;
> @@ -113,6 +114,8 @@ static struct replay_opts get_replay_opts(const struct rebase_options *opts)
>   	replay.allow_empty_message = opts->allow_empty_message;
>   	replay.verbose = opts->flags & REBASE_VERBOSE;
>   	replay.reschedule_failed_exec = opts->reschedule_failed_exec;
> +	replay.committer_date_is_author_date =
> +					opts->committer_date_is_author_date;
>   	replay.gpg_sign = xstrdup_or_null(opts->gpg_sign_opt);
>   	replay.strategy = opts->strategy;
>   	if (opts->strategy_opts)
> @@ -467,6 +470,9 @@ int cmd_rebase__interactive(int argc, const char **argv, const char *prefix)
>   		OPT_BOOL(0, "autosquash", &opts.autosquash,
>   			 N_("move commits that begin with squash!/fixup!")),
>   		OPT_BOOL(0, "signoff", &opts.signoff, N_("sign commits")),
> +		OPT_BOOL(0, "committer-date-is-author-date",
> +			 &opts.committer_date_is_author_date,
> +			 N_("make committer date match author date")),

I guess it's good to do this for completeness but does 
rebase--preserver-merges.sh support --committer-date-is-author-date? It 
is the only caller of rebase--interactive I think so would be the only 
user of this code.

>   		OPT_BIT('v', "verbose", &opts.flags,
>   			N_("display a diffstat of what changed upstream"),
>   			REBASE_NO_QUIET | REBASE_VERBOSE | REBASE_DIFFSTAT),
> @@ -534,6 +540,9 @@ int cmd_rebase__interactive(int argc, const char **argv, const char *prefix)
>   		warning(_("--[no-]rebase-cousins has no effect without "
>   			  "--rebase-merges"));
>   
> +	if (opts.committer_date_is_author_date)
> +		opts.flags |= REBASE_FORCE;
> +
>   	return !!run_rebase_interactive(&opts, command);
>   }
>   
> @@ -972,6 +981,8 @@ static int run_am(struct rebase_options *opts)
>   
>   	if (opts->ignore_whitespace)
>   		argv_array_push(&am.args, "--ignore-whitespace");
> +	if (opts->committer_date_is_author_date)
> +		argv_array_push(&opts->git_am_opts, "--committer-date-is-author-date");
>   	if (opts->action && !strcmp("continue", opts->action)) {
>   		argv_array_push(&am.args, "--resolved");
>   		argv_array_pushf(&am.args, "--resolvemsg=%s", resolvemsg);
> @@ -1419,9 +1430,9 @@ int cmd_rebase(int argc, const char **argv, const char *prefix)
>   			PARSE_OPT_NOARG, NULL, REBASE_DIFFSTAT },
>   		OPT_BOOL(0, "signoff", &options.signoff,
>   			 N_("add a Signed-off-by: line to each commit")),
> -		OPT_PASSTHRU_ARGV(0, "committer-date-is-author-date",
> -				  &options.git_am_opts, NULL,
> -				  N_("passed to 'git am'"), PARSE_OPT_NOARG),
> +		OPT_BOOL(0, "committer-date-is-author-date",
> +			 &options.committer_date_is_author_date,
> +			 N_("make committer date match author date")),
>   		OPT_PASSTHRU_ARGV(0, "ignore-date", &options.git_am_opts, NULL,
>   				  N_("passed to 'git am'"), PARSE_OPT_NOARG),
>   		OPT_PASSTHRU_ARGV('C', NULL, &options.git_am_opts, N_("n"),
> @@ -1688,10 +1699,12 @@ int cmd_rebase(int argc, const char **argv, const char *prefix)
>   		    state_dir_base, cmd_live_rebase, buf.buf);
>   	}
>   
> +	if (options.committer_date_is_author_date)
> +		options.flags |= REBASE_FORCE;
> +
>   	for (i = 0; i < options.git_am_opts.argc; i++) {
>   		const char *option = options.git_am_opts.argv[i], *p;
> -		if (!strcmp(option, "--committer-date-is-author-date") ||
> -		    !strcmp(option, "--ignore-date") ||
> +		if (!strcmp(option, "--ignore-date") ||
>   		    !strcmp(option, "--whitespace=fix") ||
>   		    !strcmp(option, "--whitespace=strip"))
>   			options.flags |= REBASE_FORCE;
> diff --git a/sequencer.c b/sequencer.c
> index a2d7b0925e..a65f01a422 100644
> --- a/sequencer.c
> +++ b/sequencer.c
> @@ -147,6 +147,7 @@ static GIT_PATH_FUNC(rebase_path_refs_to_delete, "rebase-merge/refs-to-delete")
>    * command-line.
>    */
>   static GIT_PATH_FUNC(rebase_path_gpg_sign_opt, "rebase-merge/gpg_sign_opt")
> +static GIT_PATH_FUNC(rebase_path_cdate_is_adate, "rebase-merge/cdate_is_adate")
>   static GIT_PATH_FUNC(rebase_path_orig_head, "rebase-merge/orig-head")
>   static GIT_PATH_FUNC(rebase_path_verbose, "rebase-merge/verbose")
>   static GIT_PATH_FUNC(rebase_path_quiet, "rebase-merge/quiet")
> @@ -876,6 +877,18 @@ static char *get_author(const char *message)
>   	return NULL;
>   }
>   
> +/* Returns a "date" string that needs to be free()'d by the caller */
> +static char *read_author_date_or_die(void)
> +{
> +	char *date;
> +
> +	if (read_author_script(rebase_path_author_script(),
> +			       NULL, NULL, &date, 0))
> +		die(_("failed to read author date"));

Can we have this return an error please - we try quite hard in the 
sequencer not to die in library code.

> +
> +	return date;
> +}
> +
>   /* Read author-script and return an ident line (author <email> timestamp) */
>   static const char *read_author_ident(struct strbuf *buf)
>   {
> @@ -986,10 +999,17 @@ static int run_git_commit(struct repository *r,
>   
>   		if (res <= 0)
>   			res = error_errno(_("could not read '%s'"), defmsg);
> -		else
> +		else {
> +			if (opts->committer_date_is_author_date) {
> +				char *date = read_author_date_or_die();
> +				setenv("GIT_COMMITTER_DATE", date, 1);
> +				free(date);
> +			}
> +
>   			res = commit_tree(msg.buf, msg.len, cache_tree_oid,
>   					  NULL, &root_commit, author,
>   					  opts->gpg_sign);
> +		}
>   
>   		strbuf_release(&msg);
>   		strbuf_release(&script);
> @@ -1019,6 +1039,11 @@ static int run_git_commit(struct repository *r,
>   		argv_array_push(&cmd.args, "--amend");
>   	if (opts->gpg_sign)
>   		argv_array_pushf(&cmd.args, "-S%s", opts->gpg_sign);
> +	if (opts->committer_date_is_author_date) {
> +		char *date = read_author_date_or_die();
> +		argv_array_pushf(&cmd.env_array, "GIT_COMMITTER_DATE=%s", date);
> +		free(date);
> +	}

It's a shame to be doing this twice is slightly different ways in the 
same function (and again in try_to_commit() but I don't think that can 
be avoided as not all callers of run_git_commit() go through 
try_to_commit()). As I think the child inherits the current environment 
modified by cmd.env_array we could just call setenv() at the top of the 
function. It would be worth looking to see if it would be simpler to do 
the setenv() call in the loop that picks the commits, then we would 
avoid having to do it in do_merge() and try_to_commit() separately.

>   	if (defmsg)
>   		argv_array_pushl(&cmd.args, "-F", defmsg, NULL);
>   	else if (!(flags & EDIT_MSG))
> @@ -1467,6 +1492,12 @@ static int try_to_commit(struct repository *r,
>   
>   	reset_ident_date();
>   
> +	if (opts->committer_date_is_author_date) {
> +		char *date = read_author_date_or_die();
> +		setenv("GIT_COMMITTER_DATE", date, 1);
> +		free(date);
> +	}
> +
>   	if (commit_tree_extended(msg->buf, msg->len, &tree, parents,
>   				 oid, author, opts->gpg_sign, extra)) {
>   		res = error(_("failed to write commit object"));
> @@ -2538,6 +2569,11 @@ static int read_populate_opts(struct replay_opts *opts)
>   			opts->signoff = 1;
>   		}
>   
> +		if (file_exists(rebase_path_cdate_is_adate())) {
> +			opts->allow_ff = 0;

This is safe as we don't save the state of allow_ff for rebases so it 
wont be overridden later. It would be an idea to add to the checks in 
the assert() at the beginning of pick_commits() no we have another 
option that implies --force-rebase.

Best Wishes

Phillip

> +			opts->committer_date_is_author_date = 1;
> +		}
> +
>   		if (file_exists(rebase_path_reschedule_failed_exec()))
>   			opts->reschedule_failed_exec = 1;
>   
> @@ -2620,6 +2656,8 @@ int write_basic_state(struct replay_opts *opts, const char *head_name,
>   		write_file(rebase_path_gpg_sign_opt(), "-S%s\n", opts->gpg_sign);
>   	if (opts->signoff)
>   		write_file(rebase_path_signoff(), "--signoff\n");
> +	if (opts->committer_date_is_author_date)
> +		write_file(rebase_path_cdate_is_adate(), "%s", "");
>   	if (opts->reschedule_failed_exec)
>   		write_file(rebase_path_reschedule_failed_exec(), "%s", "");
>   
> @@ -3437,6 +3475,12 @@ static int do_merge(struct repository *r,
>   		argv_array_push(&cmd.args, git_path_merge_msg(r));
>   		if (opts->gpg_sign)
>   			argv_array_push(&cmd.args, opts->gpg_sign);
> +		if (opts->committer_date_is_author_date) {
> +			char *date = read_author_date_or_die();
> +			argv_array_pushf(&cmd.env_array,
> +					 "GIT_COMMITTER_DATE=%s", date);
> +			free(date);
> +		}
>   
>   		/* Add the tips to be merged */
>   		for (j = to_merge; j; j = j->next)
> diff --git a/sequencer.h b/sequencer.h
> index 303047a133..0cfe184fc2 100644
> --- a/sequencer.h
> +++ b/sequencer.h
> @@ -44,6 +44,7 @@ struct replay_opts {
>   	int quiet;
>   	int reschedule_failed_exec;
>   	int ignore_whitespace;
> +	int committer_date_is_author_date;
>   
>   	int mainline;
>   
> diff --git a/t/t3422-rebase-incompatible-options.sh b/t/t3422-rebase-incompatible-options.sh
> index 4342f79eea..7402f7e3da 100755
> --- a/t/t3422-rebase-incompatible-options.sh
> +++ b/t/t3422-rebase-incompatible-options.sh
> @@ -61,7 +61,6 @@ test_rebase_am_only () {
>   }
>   
>   test_rebase_am_only --whitespace=fix
> -test_rebase_am_only --committer-date-is-author-date
>   test_rebase_am_only -C4
>   
>   test_expect_success REBASE_P '--preserve-merges incompatible with --signoff' '
> diff --git a/t/t3431-rebase-options-compatibility.sh b/t/t3431-rebase-options-compatibility.sh
> index f38ae6f5fc..c3f7f6d5d0 100755
> --- a/t/t3431-rebase-options-compatibility.sh
> +++ b/t/t3431-rebase-options-compatibility.sh
> @@ -7,6 +7,9 @@ test_description='tests to ensure compatibility between am and interactive backe
>   
>   . ./test-lib.sh
>   
> +GIT_AUTHOR_DATE="1999-04-02T08:03:20+05:30"
> +export GIT_AUTHOR_DATE
> +
>   # This is a special case in which both am and interactive backends
>   # provide the same outputs. It was done intentionally because
>   # --ignore-whitespace both the backends fall short of optimal
> @@ -63,4 +66,22 @@ test_expect_success '--ignore-whitespace works with interactive backend' '
>   	test_cmp expect file
>   '
>   
> +test_expect_success '--committer-date-is-author-date works with am backend' '
> +	git rebase -f HEAD^ &&
> +	git rebase --committer-date-is-author-date HEAD^ &&
> +	git cat-file commit HEAD | sed -e "/^\$/q" >head &&
> +	sed -ne "/^author /s/.*> //p" head >authortime &&
> +	sed -ne "/^committer /s/.*> //p" head >committertime &&
> +	test_cmp authortime committertime
> +'
> +
> +test_expect_success '--committer-date-is-author-date works with interactive backend' '
> +	git rebase -f HEAD^ &&
> +	git rebase -i --committer-date-is-author-date HEAD^ &&
> +	git cat-file commit HEAD | sed -e "/^\$/q" >head &&
> +	sed -ne "/^author /s/.*> //p" head >authortime &&
> +	sed -ne "/^committer /s/.*> //p" head >committertime &&
> +	test_cmp authortime committertime
> +'
> +
>   test_done
>