test: add known broken test for mislabeled Windows-1252 encoding

Messages that contain Windows-1252 are frequently mislabeled as ISO
8859-1, which may result in non-printable characters when displaying
the message. The test asserts that such characters (in this case
curved quotes) are displayed correctly.

diff --git a/test/T300-encoding.sh b/test/T300-encoding.sh
index 2c656a1e0950fdcfc72e8599a9b605b047dbe324..4a6bfd2f3ae94caf2e9e4ba63c81dcee67308bda 100755 (executable)
--- a/test/T300-encoding.sh
+++ b/test/T300-encoding.sh
@@ -44,4 +44,27 @@ add_message '[subject]="=?utf-8?q?encoded?=word without=?utf-8?q?space?=" '
 output=$(notmuch search id:${gen_msg_id} 2>&1 | notmuch_show_sanitize)
 test_expect_equal "$output" "thread:0000000000000005   2001-01-05 [1/1] Notmuch Test Suite; encodedword withoutspace (inbox unread)"
 
+test_begin_subtest "Mislabeled Windows-1252 encoding"
+test_subtest_known_broken
+add_message '[content-type]="text/plain; charset=iso-8859-1"'                           \
+            "[body]=$'This text contains \x93Windows-1252\x94 character codes.'"
+cat <<EOF > EXPECTED
+\fmessage{ id:XXXXX depth:0 match:1 excluded:0 filename:XXXXX
+\fheader{
+Notmuch Test Suite <test_suite@notmuchmail.org> (2001-01-05) (inbox unread)
+Subject: Mislabeled Windows-1252 encoding
+From: Notmuch Test Suite <test_suite@notmuchmail.org>
+To: Notmuch Test Suite <test_suite@notmuchmail.org>
+Date: GENERATED_DATE
+\fheader}
+\fbody{
+\fpart{ ID: 1, Content-type: text/plain
+This text contains “Windows-1252” character codes.
+\fpart}
+\fbody}
+\fmessage}
+EOF
+notmuch show id:${gen_msg_id} 2>&1 | notmuch_show_sanitize_all > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
 test_done