Mercurial > p > roundup > code
view test/test_mailgw_roundupmessage.py @ 5542:29346d92d80c
Fix email interfaces with Python 3 (issue 2550974, issue 2551000).
This patch fixes various issues handling incoming email with
roundup-mailgw with Python 3.
Incoming email must always be handled as bytes, not strings, because
it may contain 8-bit-encoded MIME parts with different encodings in
each part. When handling piped input, that means using
sys.stdin.buffer in Python 3 for binary input, along with
message_from_binary_file, not sys.stdin which is text input and may be
for the wrong encoding and not message_from_file. (In turn, tests
that use MailGW.main with text input are affected so an s2b call is
inserted in the test code and it is made to use BytesIO not StringIO.
Properly all the test messages in test_mailgw.py ought to use b''
explicitly rather than having such an s2b conversion, and there ought
to be test messages using 8-bit encodings with non-ASCII characters to
verify that that case works.)
imaplib and poplib return bytes not strings with Python 3 (from
inspection of the code, not tested), as is necessary for the above
reasons. Thus, the handling of IMAP and POP messages must expect
bytes and handle the data accordingly.
For messages from mailboxes, I saw the same problem described in issue
2551000 for a multipart message with a single (non-ASCII) part. The
Roundup code requires RoundupMessage not email.message.Message to be
used recursively for all MIME parts of a message. Because the mailbox
module uses email.message_from_* directly without passing the _class
argument to them, fixing this requires temporarily patching the email
module to ensure _class=RoundupMessage gets passed to those methods.
| author | Joseph Myers <jsm@polyomino.org.uk> |
|---|---|
| date | Sun, 16 Sep 2018 13:55:53 +0000 |
| parents | 725266c03eab |
| children | 081be318661b |
line wrap: on
line source
# -*- coding: utf-8 -*- import email import textwrap from unittest import TestCase from roundup.mailgw import RoundupMessage PART_TYPES = { 'multipart/signed': ' boundary="boundary-{indent}";\n', 'multipart/mixed': ' boundary="boundary-{indent}";\n', 'multipart/alternative': ' boundary="boundary-{indent}";\n', 'text/plain': ' name="foo.txt"\n\nfoo\n', 'text/plain_2': ' name="foo2.txt"\n\nfoo2\n', 'text/plain_3': ' name="foo3.txt"\n\nfoo3\n', 'text/html': ' name="foo.html"\n\n<html>foo</html>\n', 'application/pgp-signature': ' name="foo.gpg"\nfoo\n', 'application/pdf': ' name="foo.pdf"\nfoo\n', 'application/pdf_2': ' name="foo2.pdf"\nfoo2\n', 'message/rfc822': '\nSubject: foo\n\nfoo\n', } def message_from_string(msg): return email.message_from_string( textwrap.dedent(msg).lstrip(), RoundupMessage) def construct_message(spec, depth=0): parts = [] for content_type in spec: if isinstance(content_type, list): parts.extend(construct_message(content_type, depth=(depth + 1))) parts.append('\n--boundary-{0}--\n'.format(depth + 1)) else: if depth > 0: parts.append('\n--boundary-{0}\n'.format(depth)) parts.append( 'Content-Type: {0};\n'.format(content_type.split('_')[0])) parts.append(PART_TYPES[content_type].format(indent=(depth + 1))) if depth == 0: return email.message_from_string(''.join(parts), RoundupMessage) else: return parts class FlattenRoundupMessageTests(TestCase): def test_flatten_with_from(self): msg_string = textwrap.dedent(""" From: Some User <some.user@example.com> To: issue_tracker@example.com Message-Id: <dummy_test_message_id> Subject: Test line start with from From here to there! """).lstrip() msg = email.message_from_string(msg_string, RoundupMessage) self.assertEqual(msg.flatten(), msg_string) class HeaderRoundupMessageTests(TestCase): msg = message_from_string(""" Content-Type: text/plain; charset="iso-8859-1" From: =?utf8?b?SOKCrGxsbw==?= <hello@example.com> To: Issue Tracker <issue_tracker@example.com> Cc: =?utf8?b?SOKCrGxsbw==?= <hello@example.com>, Some User <some.user@example.com> Message-Id: <dummy_test_message_id> Subject: [issue] Testing... This is a test submission of a new issue. """) def test_get_plain_header(self): self.assertEqual( self.msg.get_header('to'), 'Issue Tracker <issue_tracker@example.com>') def test_get_encoded_header(self): self.assertEqual( self.msg.get_header('from'), 'H€llo <hello@example.com>') def test_get_address_list(self): self.assertEqual(self.msg.get_address_list('cc'), [ ('H€llo', 'hello@example.com'), ('Some User', 'some.user@example.com'), ]) class BodyRoundupMessageTests(TestCase): def test_get_body_iso_8859_1(self): msg = message_from_string(""" Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable A message with encoding (encoded oe =F6) """) self.assertEqual( msg.get_body(), 'A message with encoding (encoded oe ö)\n') def test_get_body_utf_8(self): msg = message_from_string(""" Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable A message with encoding (encoded oe =C3=B6) """) self.assertEqual( msg.get_body(), 'A message with encoding (encoded oe ö)\n') def test_get_body_base64(self): msg = message_from_string(""" Content-Type: application/octet-stream Content-Disposition: attachment; filename="message.dat" Content-Transfer-Encoding: base64 dGVzdCBlbmNvZGVkIG1lc3NhZ2U= """) self.assertEqual(msg.get_body(), 'test encoded message') class AsAttachmentRoundupMessageTests(TestCase): def test_text_plain(self): msg = message_from_string(""" Content-Type: text/plain; charset="iso-8859-1 Plain text message """) self.assertEqual( msg.as_attachment(), (None, 'text/plain', 'Plain text message\n')) def test_octet_stream(self): msg = message_from_string(""" Content-Type: application/octet-stream Content-Disposition: attachment; filename="message.dat" Content-Transfer-Encoding: base64 dGVzdCBlbmNvZGVkIG1lc3NhZ2U= """) self.assertEqual( msg.as_attachment(), ('message.dat', 'application/octet-stream', 'test encoded message')) def test_rfc822(self): msg = message_from_string(""" Content-Type: message/rfc822 Subject: foo foo """) self.assertEqual( msg.as_attachment(), ('foo.eml', 'message/rfc822', 'Subject: foo\n\nfoo\n')) def test_rfc822_no_subject(self): msg = message_from_string(""" Content-Type: message/rfc822 X-No-Headers: nope foo """) self.assertEqual( msg.as_attachment(), (None, 'message/rfc822', 'X-No-Headers: nope\n\nfoo\n')) def test_rfc822_no_payload(self): msg = message_from_string("""\ Content-Type: message/rfc822 """) self.assertEqual( msg.as_attachment(), (None, 'message/rfc822', '\n')) class ExtractContentRoundupMessageTests(TestCase): def test_text_plain(self): msg = construct_message(['text/plain']) self.assertEqual(msg.extract_content(), ('foo\n', [], False)) def test_attached_text_plain(self): msg = construct_message([ 'multipart/mixed', [ 'text/plain', 'text/plain', ], ]) self.assertEqual(msg.extract_content(), ( 'foo\n', [('foo.txt', 'text/plain', 'foo\n')], False )) def test_multipart_mixed(self): msg = construct_message([ 'multipart/mixed', [ 'text/plain', 'application/pdf', ], ]) self.assertEqual(msg.extract_content(), ( 'foo\n', [('foo.pdf', 'application/pdf', 'foo\n')], False )) def test_multipart_alternative(self): msg = construct_message([ 'multipart/alternative', [ 'text/plain', 'text/html', ], ]) self.assertEqual(msg.extract_content(), ( 'foo\n', [('foo.html', 'text/html', '<html>foo</html>\n')], False )) def test_deep_multipart_alternative(self): msg = construct_message([ 'multipart/mixed', [ 'multipart/alternative', [ 'text/plain', 'application/pdf', 'text/plain_2', 'text/html', ], 'multipart/alternative', [ 'text/plain_3', 'application/pdf_2', ], ], ]) self.assertEqual(msg.extract_content(), ( 'foo2\n', [ ('foo.pdf', 'application/pdf', 'foo\n'), ('foo.txt', 'text/plain', 'foo\n'), ('foo.html', 'text/html', '<html>foo</html>\n'), ('foo3.txt', 'text/plain', 'foo3\n'), ('foo2.pdf', 'application/pdf', 'foo2\n'), ], False )) def test_deep_multipart_alternative_ignore(self): msg = construct_message([ 'multipart/mixed', [ 'multipart/alternative', [ 'text/plain', 'application/pdf', 'text/plain_2', 'text/html', ], 'multipart/alternative', [ 'text/plain_3', 'application/pdf_2', ], ], ]) msg.extract_content(ignore_alternatives=True) self.assertEqual(msg.extract_content(ignore_alternatives=True), ( 'foo2\n', [ ('foo3.txt', 'text/plain', 'foo3\n'), ('foo2.pdf', 'application/pdf', 'foo2\n'), ], False )) def test_signed_text(self): msg = construct_message([ 'multipart/signed', [ 'text/plain', 'application/pgp-signature', ], ]) self.assertEqual(msg.extract_content(), ('foo\n', [], False)) def test_signed_attachemts(self): msg = construct_message([ 'multipart/signed', [ 'multipart/mixed', [ 'text/plain', 'application/pdf', ], 'application/pgp-signature', ], ]) self.assertEqual(msg.extract_content(), ( 'foo\n', [('foo.pdf', 'application/pdf', 'foo\n')], False )) def test_attached_signature(self): msg = construct_message([ 'multipart/mixed', [ 'text/plain', 'application/pgp-signature', ], ]) self.assertEqual(msg.extract_content(), ( 'foo\n', [('foo.gpg', 'application/pgp-signature', 'foo\n')], False )) def test_rfc822_message(self): msg = construct_message([ 'multipart/mixed', [ 'message/rfc822', ], ]) self.assertEqual(msg.extract_content(), ( None, [('foo.eml', 'message/rfc822', 'Subject: foo\n\nfoo\n')], False )) def test_rfc822_message_unpack(self): msg = construct_message([ 'multipart/mixed', [ 'text/plain', 'message/rfc822', ], ]) self.assertEqual(msg.extract_content(unpack_rfc822=True), ( 'foo\n', [(None, 'text/plain', 'foo\n')], False )) class PgpDetectRoundupMessageTests(TestCase): def test_pgp_message_signed(self): msg = message_from_string(""" Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature" Fake Body """) self.assertTrue(msg.pgp_signed()) def test_pgp_message_not_signed(self): msg = message_from_string(""" Content-Type: text/plain Fake Body """) self.assertFalse(msg.pgp_signed()) def test_pgp_message_signed_protocol_missing(self): msg = message_from_string(""" Content-Type: multipart/signed; micalg=pgp-sha1 Fake Body """) self.assertFalse(msg.pgp_signed()) def test_pgp_message_signed_protocol_invalid(self): msg = message_from_string(""" Content-Type: multipart/signed; protocol="application/not-pgp-signature" Fake Body """) self.assertFalse(msg.pgp_signed()) def test_pgp_message_encrypted(self): msg = message_from_string(""" Content-Type: multipart/encrypted; protocol="application/pgp-encrypted" Fake Body """) self.assertTrue(msg.pgp_encrypted()) def test_pgp_message_not_encrypted(self): msg = message_from_string(""" Content-Type: text/plain Fake Body """) self.assertFalse(msg.pgp_encrypted()) def test_pgp_message_encrypted_protocol_missing(self): msg = message_from_string(""" Content-Type: multipart/encrypted Fake Body """) self.assertFalse(msg.pgp_encrypted()) def test_pgp_message_encrypted_protocol_invalid(self): msg = message_from_string(""" Content-Type: multipart/encrypted; protocol="application/not-pgp-encrypted" Fake Body """) self.assertFalse(msg.pgp_encrypted()) # TODO: testing of the verify_signature() and decrypt() RoundupMessage methods. # The whole PGP testing stuff seems a bit messy, so we will rely on the tests # in test_mailgw for the time being