teach format-patch to place other authors into in-body "From"

Format-patch generates emails with the "From" address set to the
author of each patch. If you are going to send the emails, however,
you would want to replace the author identity with yours (if they
are not the same), and bump the author identity to an in-body
header.

Normally this is handled by git-send-email, which does the
transformation before sending out the emails. However, some
workflows may not use send-email (e.g., imap-send, or a custom
script which feeds the mbox to a non-git MUA). They could each
implement this feature themselves, but getting it right is
non-trivial (one must canonicalize the identities by reversing any
RFC2047 encoding or RFC822 quoting of the headers, which has caused
many bugs in send-email over the years).

This patch takes a different approach: it teaches format-patch a
"--from" option which handles the ident check and in-body header
while it is writing out the email.  It's much simpler to do at this
level (because we haven't done any quoting yet), and any workflow
based on format-patch can easily turn it on.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

7 files changed, 128 insertions, 0 deletions

diff --git a/Documentation/git-format-patch.txt b/Documentation/git-format-patch.txt
index 39118774af..e394276b1a 100644
--- a/Documentation/git-format-patch.txt
+++ b/Documentation/git-format-patch.txt
@@ -187,6 +187,21 @@ will want to ensure that threading is disabled for `git send-email`.
 	The negated form `--no-cc` discards all `Cc:` headers added so
 	far (from config or command line).
 
+--from::
+--from=<ident>::
+	Use `ident` in the `From:` header of each commit email. If the
+	author ident of the commit is not textually identical to the
+	provided `ident`, place a `From:` header in the body of the
+	message with the original author. If no `ident` is given, use
+	the committer ident.
++
+Note that this option is only useful if you are actually sending the
+emails and want to identify yourself as the sender, but retain the
+original author (and `git am` will correctly pick up the in-body
+header). Note also that `git send-email` already handles this
+transformation for you, and this option should not be used if you are
+feeding the result to `git send-email`.
+
 --add-header=<header>::
 	Add an arbitrary header to the email headers.  This is in addition
 	to any configured headers, and may be used multiple times.
diff --git a/builtin/log.c b/builtin/log.c
index e3222ed9f9..2625f9881a 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -1112,6 +1112,21 @@ static int cc_callback(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+static int from_callback(const struct option *opt, const char *arg, int unset)
+{
+	char **from = opt->value;
+
+	free(*from);
+
+	if (unset)
+		*from = NULL;
+	else if (arg)
+		*from = xstrdup(arg);
+	else
+		*from = xstrdup(git_committer_info(IDENT_NO_DATE));
+	return 0;
+}
+
 int cmd_format_patch(int argc, const char **argv, const char *prefix)
 {
 	struct commit *commit;
@@ -1134,6 +1149,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 	int quiet = 0;
 	int reroll_count = -1;
 	char *branch_name = NULL;
+	char *from = NULL;
 	const struct option builtin_format_patch_options[] = {
 		{ OPTION_CALLBACK, 'n', "numbered", &numbered, NULL,
 			    N_("use [PATCH n/m] even with a single patch"),
@@ -1177,6 +1193,9 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 			    0, to_callback },
 		{ OPTION_CALLBACK, 0, "cc", NULL, N_("email"), N_("add Cc: header"),
 			    0, cc_callback },
+		{ OPTION_CALLBACK, 0, "from", &from, N_("ident"),
+			    N_("set From address to <ident> (or committer ident if absent)"),
+			    PARSE_OPT_OPTARG, from_callback },
 		OPT_STRING(0, "in-reply-to", &in_reply_to, N_("message-id"),
 			    N_("make first mail a reply to <message-id>")),
 		{ OPTION_CALLBACK, 0, "attach", &rev, N_("boundary"),
@@ -1264,6 +1283,11 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 
 	rev.extra_headers = strbuf_detach(&buf, NULL);
 
+	if (from) {
+		if (split_ident_line(&rev.from_ident, from, strlen(from)))
+			die(_("invalid ident line: %s"), from);
+	}
+
 	if (start_number < 0)
 		start_number = 1;
 
diff --git a/commit.h b/commit.h
index 011ddb146f..c56bc3a091 100644
--- a/commit.h
+++ b/commit.h
@@ -6,6 +6,7 @@
 #include "strbuf.h"
 #include "decorate.h"
 #include "gpg-interface.h"
+#include "string-list.h"
 
 struct commit_list {
 	struct commit *item;
@@ -95,11 +96,15 @@ struct pretty_print_context {
 	const char *output_encoding;
 	struct string_list *mailmap;
 	int color;
+	struct ident_split *from_ident;
 
 	/*
 	 * Fields below here are manipulated internally by pp_* functions and
 	 * should not be counted on by callers.
 	 */
+
+	/* Manipulated by the pp_* functions internally. */
+	struct string_list in_body_headers;
 };
 
 struct userformat_want {
diff --git a/log-tree.c b/log-tree.c
index 2eb69bcfed..67da27f909 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -617,6 +617,8 @@ void show_log(struct rev_info *opt)
 	ctx.fmt = opt->commit_format;
 	ctx.mailmap = opt->mailmap;
 	ctx.color = opt->diffopt.use_color;
+	if (opt->from_ident.mail_begin && opt->from_ident.name_begin)
+		ctx.from_ident = &opt->from_ident;
 	pretty_print_commit(&ctx, commit, &msgbuf);
 
 	if (opt->add_signoff)
diff --git a/pretty.c b/pretty.c
index 68cd7a035b..74563c92b4 100644
--- a/pretty.c
+++ b/pretty.c
@@ -432,6 +432,23 @@ void pp_user_info(struct pretty_print_context *pp,
 		map_user(pp->mailmap, &mailbuf, &maillen, &namebuf, &namelen);
 
 	if (pp->fmt == CMIT_FMT_EMAIL) {
+		if (pp->from_ident) {
+			struct strbuf buf = STRBUF_INIT;
+
+			strbuf_addstr(&buf, "From: ");
+			strbuf_add(&buf, namebuf, namelen);
+			strbuf_addstr(&buf, " <");
+			strbuf_add(&buf, mailbuf, maillen);
+			strbuf_addstr(&buf, ">\n");
+			string_list_append(&pp->in_body_headers,
+					   strbuf_detach(&buf, NULL));
+
+			mailbuf = pp->from_ident->mail_begin;
+			maillen = pp->from_ident->mail_end - mailbuf;
+			namebuf = pp->from_ident->name_begin;
+			namelen = pp->from_ident->name_end - namebuf;
+		}
+
 		strbuf_addstr(sb, "From: ");
 		if (needs_rfc2047_encoding(namebuf, namelen, RFC2047_ADDRESS)) {
 			add_rfc2047(sb, namebuf, namelen,
@@ -1602,6 +1619,16 @@ void pp_title_line(struct pretty_print_context *pp,
 	}
 	strbuf_addch(sb, '\n');
 
+	if (need_8bit_cte == 0) {
+		int i;
+		for (i = 0; i < pp->in_body_headers.nr; i++) {
+			if (has_non_ascii(pp->in_body_headers.items[i].string)) {
+				need_8bit_cte = 1;
+				break;
+			}
+		}
+	}
+
 	if (need_8bit_cte > 0) {
 		const char *header_fmt =
 			"MIME-Version: 1.0\n"
@@ -1615,6 +1642,17 @@ void pp_title_line(struct pretty_print_context *pp,
 	if (pp->fmt == CMIT_FMT_EMAIL) {
 		strbuf_addch(sb, '\n');
 	}
+
+	if (pp->in_body_headers.nr) {
+		int i;
+		for (i = 0; i < pp->in_body_headers.nr; i++) {
+			strbuf_addstr(sb, pp->in_body_headers.items[i].string);
+			free(pp->in_body_headers.items[i].string);
+		}
+		string_list_clear(&pp->in_body_headers, 0);
+		strbuf_addch(sb, '\n');
+	}
+
 	strbuf_release(&title);
 }
 
diff --git a/revision.h b/revision.h
index 92d6614af6..95859ba119 100644
--- a/revision.h
+++ b/revision.h
@@ -144,6 +144,7 @@ struct rev_info {
 	int		numbered_files;
 	int		reroll_count;
 	char		*message_id;
+	struct ident_split from_ident;
 	struct string_list *ref_message_ids;
 	int		add_signoff;
 	const char	*extra_headers;
diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh
index 58d418098d..668933bfb2 100755
--- a/t/t4014-format-patch.sh
+++ b/t/t4014-format-patch.sh
@@ -972,6 +972,49 @@ test_expect_success 'empty subject prefix does not have extra space' '
 	test_cmp expect actual
 '
 
+test_expect_success '--from=ident notices bogus ident' '
+	test_must_fail git format-patch -1 --stdout --from=foo >patch
+'
+
+test_expect_success '--from=ident replaces author' '
+	git format-patch -1 --stdout --from="Me <me@example.com>" >patch &&
+	cat >expect <<-\EOF &&
+	From: Me <me@example.com>
+
+	From: A U Thor <author@example.com>
+
+	EOF
+	sed -ne "/^From:/p; /^$/p; /^---$/q" <patch >patch.head &&
+	test_cmp expect patch.head
+'
+
+test_expect_success '--from uses committer ident' '
+	git format-patch -1 --stdout --from >patch &&
+	cat >expect <<-\EOF &&
+	From: C O Mitter <committer@example.com>
+
+	From: A U Thor <author@example.com>
+
+	EOF
+	sed -ne "/^From:/p; /^$/p; /^---$/q" <patch >patch.head &&
+	test_cmp expect patch.head
+'
+
+test_expect_success 'in-body headers trigger content encoding' '
+	GIT_AUTHOR_NAME="éxötìc" test_commit exotic &&
+	test_when_finished "git reset --hard HEAD^" &&
+	git format-patch -1 --stdout --from >patch &&
+	cat >expect <<-\EOF &&
+	From: C O Mitter <committer@example.com>
+	Content-Type: text/plain; charset=UTF-8
+
+	From: éxötìc <author@example.com>
+
+	EOF
+	sed -ne "/^From:/p; /^$/p; /^Content-Type/p; /^---$/q" <patch >patch.head &&
+	test_cmp expect patch.head
+'
+
 append_signoff()
 {
 	C=$(git commit-tree HEAD^^{tree} -p HEAD) &&