[PATCH v4 3/6] mailinfo: warn if CRLF found in decoded base64/QP email

["Đoàn Trần Công Danh" <congdanhqx@gmail.com>]

When SMTP servers receive 8-bit email messages, possibly with only
LF as line ending, some of them decide to change said LF to CRLF.

Some mailing list softwares, when receive 8-bit email messages,
decide to encode those messages in base64 or quoted-printable.

If an email is transfered through above mail servers, then distributed
by such mailing list softwares, the recipients will receive an email
contains a patch mungled with CRLF encoded inside another encoding.

Thus, such CR (in CRLF) couldn't be dropped by "mailsplit".
Hence, the mailed patch couldn't be applied cleanly.
Such accidents have been observed in the wild [1].

Instead of silently rejecting those messages, let's give our users
some warnings if such CR (as part of CRLF) is found.

[1]: https://nmbug.notmuchmail.org/nmweb/show/m2lf9ejegj.fsf%40guru.guru-group.fi

Signed-off-by: Đoàn Trần Công Danh <congdanhqx@gmail.com>
---
 mailinfo.c              | 14 ++++++++++++
 mailinfo.h              |  1 +
 t/t5100-mailinfo.sh     | 30 ++++++++++++++++++++++++++
 t/t5100/quoted-cr-info  |  5 +++++
 t/t5100/quoted-cr-msg   |  2 ++
 t/t5100/quoted-cr-patch | 22 +++++++++++++++++++
 t/t5100/quoted-cr.mbox  | 47 +++++++++++++++++++++++++++++++++++++++++
 7 files changed, 121 insertions(+)
 create mode 100644 t/t5100/quoted-cr-info
 create mode 100644 t/t5100/quoted-cr-msg
 create mode 100644 t/t5100/quoted-cr-patch
 create mode 100644 t/t5100/quoted-cr.mbox

diff --git a/mailinfo.c b/mailinfo.c
index 5681d9130d..c8caee4f55 100644
--- a/mailinfo.c
+++ b/mailinfo.c
@@ -994,6 +994,11 @@ static void handle_filter_flowed(struct mailinfo *mi, struct strbuf *line,
 	const char *rest;
 
 	if (!mi->format_flowed) {
+		if (len >= 2 &&
+		    line->buf[len - 2] == '\r' &&
+		    line->buf[len - 1] == '\n') {
+			mi->have_quoted_cr = 1;
+		}
 		handle_filter(mi, line);
 		return;
 	}
@@ -1033,6 +1038,12 @@ static void handle_filter_flowed(struct mailinfo *mi, struct strbuf *line,
 	handle_filter(mi, line);
 }
 
+static void summarize_quoted_cr(struct mailinfo *mi)
+{
+	if (mi->have_quoted_cr)
+		warning(_("quoted CRLF detected"));
+}
+
 static void handle_body(struct mailinfo *mi, struct strbuf *line)
 {
 	struct strbuf prev = STRBUF_INIT;
@@ -1051,6 +1062,8 @@ static void handle_body(struct mailinfo *mi, struct strbuf *line)
 				handle_filter(mi, &prev);
 				strbuf_reset(&prev);
 			}
+			summarize_quoted_cr(mi);
+			mi->have_quoted_cr = 0;
 			if (!handle_boundary(mi, line))
 				goto handle_body_out;
 		}
@@ -1100,6 +1113,7 @@ static void handle_body(struct mailinfo *mi, struct strbuf *line)
 
 	if (prev.len)
 		handle_filter(mi, &prev);
+	summarize_quoted_cr(mi);
 
 	flush_inbody_header_accum(mi);
 
diff --git a/mailinfo.h b/mailinfo.h
index 79b1d6774e..b394ef9bce 100644
--- a/mailinfo.h
+++ b/mailinfo.h
@@ -24,6 +24,7 @@ struct mailinfo {
 	struct strbuf charset;
 	unsigned int format_flowed:1;
 	unsigned int delsp:1;
+	unsigned int have_quoted_cr:1;
 	char *message_id;
 	enum  {
 		TE_DONTCARE, TE_QP, TE_BASE64
diff --git a/t/t5100-mailinfo.sh b/t/t5100-mailinfo.sh
index 147e616533..ac6fbfe596 100755
--- a/t/t5100-mailinfo.sh
+++ b/t/t5100-mailinfo.sh
@@ -228,4 +228,34 @@ test_expect_success 'mailinfo handles unusual header whitespace' '
 	test_cmp expect actual
 '
 
+check_quoted_cr_mail () {
+	mail="$1" && shift &&
+	git mailinfo -u "$@" "$mail.msg" "$mail.patch" \
+		<"$mail" >"$mail.info" 2>"$mail.err" &&
+	test_cmp "$mail-expected.msg" "$mail.msg" &&
+	test_cmp "$mail-expected.patch" "$mail.patch" &&
+	test_cmp "$DATA/quoted-cr-info" "$mail.info"
+}
+
+test_expect_success 'split base64 email with quoted-cr' '
+	mkdir quoted-cr &&
+	git mailsplit -oquoted-cr "$DATA/quoted-cr.mbox" >quoted-cr/last &&
+	test $(cat quoted-cr/last) = 2
+'
+
+test_expect_success 'mailinfo warn CR in base64 encoded email' '
+	sed -e "s/%%$//" -e "s/%%/$(printf \\015)/g" "$DATA/quoted-cr-msg" \
+		>quoted-cr/0001-expected.msg &&
+	sed "s/%%/$(printf \\015)/g" "$DATA/quoted-cr-msg" \
+		>quoted-cr/0002-expected.msg &&
+	sed -e "s/%%$//" -e "s/%%/$(printf \\015)/g" "$DATA/quoted-cr-patch" \
+		>quoted-cr/0001-expected.patch &&
+	sed "s/%%/$(printf \\015)/g" "$DATA/quoted-cr-patch" \
+		>quoted-cr/0002-expected.patch &&
+	check_quoted_cr_mail quoted-cr/0001 &&
+	test_must_be_empty quoted-cr/0001.err &&
+	check_quoted_cr_mail quoted-cr/0002 &&
+	grep "quoted CRLF detected" quoted-cr/0002.err
+'
+
 test_done
diff --git a/t/t5100/quoted-cr-info b/t/t5100/quoted-cr-info
new file mode 100644
index 0000000000..dab2228b70
--- /dev/null
+++ b/t/t5100/quoted-cr-info
@@ -0,0 +1,5 @@
+Author: A U Thor
+Email: mail@example.com
+Subject: sample
+Date: Mon, 3 Aug 2020 22:40:55 +0700
+
diff --git a/t/t5100/quoted-cr-msg b/t/t5100/quoted-cr-msg
new file mode 100644
index 0000000000..89b05a0784
--- /dev/null
+++ b/t/t5100/quoted-cr-msg
@@ -0,0 +1,2 @@
+On different distro, %%pytest is suffixed with different patterns.%%
+%%
diff --git a/t/t5100/quoted-cr-patch b/t/t5100/quoted-cr-patch
new file mode 100644
index 0000000000..65b13eeef7
--- /dev/null
+++ b/t/t5100/quoted-cr-patch
@@ -0,0 +1,22 @@
+---%%
+ configure | 2 +-%%
+ 1 file changed, 1 insertion(+), 1 deletion(-)%%
+%%
+diff --git a/configure b/configure%%
+index db3538b3..f7c1c095 100755%%
+--- a/configure%%
++++ b/configure%%
+@@ -814,7 +814,7 @@ if [ $have_python3 -eq 1 ]; then%%
+     printf "%%Checking for python3 pytest (>= 3.0)... "%%
+     conf=$(mktemp)%%
+     printf "[pytest]\nminversion=3.0\n" > $conf%%
+-    if pytest-3 -c $conf --version >/dev/null 2>&1; then%%
++    if "$python" -m pytest -c $conf --version >/dev/null 2>&1; then%%
+         printf "Yes.\n"%%
+         have_python3_pytest=1%%
+     else%%
+-- %%
+2.28.0%%
+_______________________________________________
+example mailing list -- list@example.org
+To unsubscribe send an email to list-leave@example.org
diff --git a/t/t5100/quoted-cr.mbox b/t/t5100/quoted-cr.mbox
new file mode 100644
index 0000000000..909021bb7a
--- /dev/null
+++ b/t/t5100/quoted-cr.mbox
@@ -0,0 +1,47 @@
+From nobody Mon Sep 17 00:00:00 2001
+From: A U Thor <mail@example.com>
+To: list@example.org
+Subject: [PATCH v2] sample
+Date: Mon,  3 Aug 2020 22:40:55 +0700
+Message-Id: <msg-id@example.com>
+Content-Type: text/plain; charset="utf-8"
+Content-Transfer-Encoding: base64
+
+T24gZGlmZmVyZW50IGRpc3RybywgDXB5dGVzdCBpcyBzdWZmaXhlZCB3aXRoIGRpZmZlcmVudCBw
+YXR0ZXJucy4KCi0tLQogY29uZmlndXJlIHwgMiArLQogMSBmaWxlIGNoYW5nZWQsIDEgaW5zZXJ0
+aW9uKCspLCAxIGRlbGV0aW9uKC0pCgpkaWZmIC0tZ2l0IGEvY29uZmlndXJlIGIvY29uZmlndXJl
+CmluZGV4IGRiMzUzOGIzLi5mN2MxYzA5NSAxMDA3NTUKLS0tIGEvY29uZmlndXJlCisrKyBiL2Nv
+bmZpZ3VyZQpAQCAtODE0LDcgKzgxNCw3IEBAIGlmIFsgJGhhdmVfcHl0aG9uMyAtZXEgMSBdOyB0
+aGVuCiAgICAgcHJpbnRmICINQ2hlY2tpbmcgZm9yIHB5dGhvbjMgcHl0ZXN0ICg+PSAzLjApLi4u
+ICIKICAgICBjb25mPSQobWt0ZW1wKQogICAgIHByaW50ZiAiW3B5dGVzdF1cbm1pbnZlcnNpb249
+My4wXG4iID4gJGNvbmYKLSAgICBpZiBweXRlc3QtMyAtYyAkY29uZiAtLXZlcnNpb24gPi9kZXYv
+bnVsbCAyPiYxOyB0aGVuCisgICAgaWYgIiRweXRob24iIC1tIHB5dGVzdCAtYyAkY29uZiAtLXZl
+cnNpb24gPi9kZXYvbnVsbCAyPiYxOyB0aGVuCiAgICAgICAgIHByaW50ZiAiWWVzLlxuIgogICAg
+ICAgICBoYXZlX3B5dGhvbjNfcHl0ZXN0PTEKICAgICBlbHNlCi0tIAoyLjI4LjAKX19fX19fX19f
+X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZXhhbXBsZSBtYWlsaW5nIGxp
+c3QgLS0gbGlzdEBleGFtcGxlLm9yZwpUbyB1bnN1YnNjcmliZSBzZW5kIGFuIGVtYWlsIHRvIGxp
+c3QtbGVhdmVAZXhhbXBsZS5vcmcK
+
+From nobody Mon Sep 17 00:00:00 2001
+From: A U Thor <mail@example.com>
+To: list@example.org
+Subject: [PATCH v2] sample
+Date: Mon,  3 Aug 2020 22:40:55 +0700
+Message-Id: <msg-id2@example.com>
+Content-Type: text/plain; charset="utf-8"
+Content-Transfer-Encoding: base64
+
+T24gZGlmZmVyZW50IGRpc3RybywgDXB5dGVzdCBpcyBzdWZmaXhlZCB3aXRoIGRpZmZlcmVudCBw
+YXR0ZXJucy4NCg0KLS0tDQogY29uZmlndXJlIHwgMiArLQ0KIDEgZmlsZSBjaGFuZ2VkLCAxIGlu
+c2VydGlvbigrKSwgMSBkZWxldGlvbigtKQ0KDQpkaWZmIC0tZ2l0IGEvY29uZmlndXJlIGIvY29u
+ZmlndXJlDQppbmRleCBkYjM1MzhiMy4uZjdjMWMwOTUgMTAwNzU1DQotLS0gYS9jb25maWd1cmUN
+CisrKyBiL2NvbmZpZ3VyZQ0KQEAgLTgxNCw3ICs4MTQsNyBAQCBpZiBbICRoYXZlX3B5dGhvbjMg
+LWVxIDEgXTsgdGhlbg0KICAgICBwcmludGYgIg1DaGVja2luZyBmb3IgcHl0aG9uMyBweXRlc3Qg
+KD49IDMuMCkuLi4gIg0KICAgICBjb25mPSQobWt0ZW1wKQ0KICAgICBwcmludGYgIltweXRlc3Rd
+XG5taW52ZXJzaW9uPTMuMFxuIiA+ICRjb25mDQotICAgIGlmIHB5dGVzdC0zIC1jICRjb25mIC0t
+dmVyc2lvbiA+L2Rldi9udWxsIDI+JjE7IHRoZW4NCisgICAgaWYgIiRweXRob24iIC1tIHB5dGVz
+dCAtYyAkY29uZiAtLXZlcnNpb24gPi9kZXYvbnVsbCAyPiYxOyB0aGVuDQogICAgICAgICBwcmlu
+dGYgIlllcy5cbiINCiAgICAgICAgIGhhdmVfcHl0aG9uM19weXRlc3Q9MQ0KICAgICBlbHNlDQot
+LSANCjIuMjguMA0KX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19f
+X18KZXhhbXBsZSBtYWlsaW5nIGxpc3QgLS0gbGlzdEBleGFtcGxlLm9yZwpUbyB1bnN1YnNjcmli
+ZSBzZW5kIGFuIGVtYWlsIHRvIGxpc3QtbGVhdmVAZXhhbXBsZS5vcmcK
-- 
2.31.1.448.g9c2f8508d1