Lib.email.test.test_email.py Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of jython Show documentation
Show all versions of jython Show documentation
Jython is an implementation of the high-level, dynamic, object-oriented
language Python written in 100% Pure Java, and seamlessly integrated with
the Java platform. It thus allows you to run Python on any Java platform.
# Copyright (C) 2001-2010 Python Software Foundation
# Contact: [email protected]
# email package unit tests
import os
import sys
import time
import base64
import difflib
import unittest
import warnings
import textwrap
from cStringIO import StringIO
import email
from email.Charset import Charset
from email.Header import Header, decode_header, make_header
from email.Parser import Parser, HeaderParser
from email.Generator import Generator, DecodedGenerator
from email.Message import Message
from email.MIMEAudio import MIMEAudio
from email.MIMEText import MIMEText
from email.MIMEImage import MIMEImage
from email.MIMEBase import MIMEBase
from email.MIMEMessage import MIMEMessage
from email.MIMEMultipart import MIMEMultipart
from email import Utils
from email import Errors
from email import Encoders
from email import Iterators
from email import base64MIME
from email import quopriMIME
from test.test_support import findfile, run_unittest
from email.test import __file__ as landmark
from test.test_support import is_jython
NL = '\n'
EMPTYSTRING = ''
SPACE = ' '
def openfile(filename, mode='r'):
path = os.path.join(os.path.dirname(landmark), 'data', filename)
return open(path, mode)
# Base test class
class TestEmailBase(unittest.TestCase):
def ndiffAssertEqual(self, first, second):
"""Like assertEqual except use ndiff for readable output."""
if first != second:
sfirst = str(first)
ssecond = str(second)
diff = difflib.ndiff(sfirst.splitlines(), ssecond.splitlines())
fp = StringIO()
print >> fp, NL, NL.join(diff)
raise self.failureException, fp.getvalue()
def _msgobj(self, filename):
fp = openfile(findfile(filename))
try:
msg = email.message_from_file(fp)
finally:
fp.close()
return msg
# Test various aspects of the Message class's API
class TestMessageAPI(TestEmailBase):
def test_get_all(self):
eq = self.assertEqual
msg = self._msgobj('msg_20.txt')
eq(msg.get_all('cc'), ['[email protected]', '[email protected]', '[email protected]'])
eq(msg.get_all('xx', 'n/a'), 'n/a')
def test_getset_charset(self):
eq = self.assertEqual
msg = Message()
eq(msg.get_charset(), None)
charset = Charset('iso-8859-1')
msg.set_charset(charset)
eq(msg['mime-version'], '1.0')
eq(msg.get_content_type(), 'text/plain')
eq(msg['content-type'], 'text/plain; charset="iso-8859-1"')
eq(msg.get_param('charset'), 'iso-8859-1')
eq(msg['content-transfer-encoding'], 'quoted-printable')
eq(msg.get_charset().input_charset, 'iso-8859-1')
# Remove the charset
msg.set_charset(None)
eq(msg.get_charset(), None)
eq(msg['content-type'], 'text/plain')
# Try adding a charset when there's already MIME headers present
msg = Message()
msg['MIME-Version'] = '2.0'
msg['Content-Type'] = 'text/x-weird'
msg['Content-Transfer-Encoding'] = 'quinted-puntable'
msg.set_charset(charset)
eq(msg['mime-version'], '2.0')
eq(msg['content-type'], 'text/x-weird; charset="iso-8859-1"')
eq(msg['content-transfer-encoding'], 'quinted-puntable')
def test_set_charset_from_string(self):
eq = self.assertEqual
msg = Message()
msg.set_charset('us-ascii')
eq(msg.get_charset().input_charset, 'us-ascii')
eq(msg['content-type'], 'text/plain; charset="us-ascii"')
def test_set_payload_with_charset(self):
msg = Message()
charset = Charset('iso-8859-1')
msg.set_payload('This is a string payload', charset)
self.assertEqual(msg.get_charset().input_charset, 'iso-8859-1')
def test_get_charsets(self):
eq = self.assertEqual
msg = self._msgobj('msg_08.txt')
charsets = msg.get_charsets()
eq(charsets, [None, 'us-ascii', 'iso-8859-1', 'iso-8859-2', 'koi8-r'])
msg = self._msgobj('msg_09.txt')
charsets = msg.get_charsets('dingbat')
eq(charsets, ['dingbat', 'us-ascii', 'iso-8859-1', 'dingbat',
'koi8-r'])
msg = self._msgobj('msg_12.txt')
charsets = msg.get_charsets()
eq(charsets, [None, 'us-ascii', 'iso-8859-1', None, 'iso-8859-2',
'iso-8859-3', 'us-ascii', 'koi8-r'])
def test_get_filename(self):
eq = self.assertEqual
msg = self._msgobj('msg_04.txt')
filenames = [p.get_filename() for p in msg.get_payload()]
eq(filenames, ['msg.txt', 'msg.txt'])
msg = self._msgobj('msg_07.txt')
subpart = msg.get_payload(1)
eq(subpart.get_filename(), 'dingusfish.gif')
def test_get_filename_with_name_parameter(self):
eq = self.assertEqual
msg = self._msgobj('msg_44.txt')
filenames = [p.get_filename() for p in msg.get_payload()]
eq(filenames, ['msg.txt', 'msg.txt'])
def test_get_boundary(self):
eq = self.assertEqual
msg = self._msgobj('msg_07.txt')
# No quotes!
eq(msg.get_boundary(), 'BOUNDARY')
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(Errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def test_make_boundary(self):
msg = MIMEMultipart('form-data')
# Note that when the boundary gets created is an implementation
# detail and might change.
self.assertEqual(msg.items()[0][1], 'multipart/form-data')
# Trigger creation of boundary
msg.as_string()
self.assertEqual(msg.items()[0][1][:33],
'multipart/form-data; boundary="==')
# XXX: there ought to be tests of the uniqueness of the boundary, too.
def test_message_rfc822_only(self):
# Issue 7970: message/rfc822 not in multipart parsed by
# HeaderParser caused an exception when flattened.
fp = openfile(findfile('msg_46.txt'))
msgdata = fp.read()
parser = email.Parser.HeaderParser()
msg = parser.parsestr(msgdata)
out = StringIO()
gen = email.Generator.Generator(out, True, 0)
gen.flatten(msg, False)
self.assertEqual(out.getvalue(), msgdata)
def test_get_decoded_payload(self):
eq = self.assertEqual
msg = self._msgobj('msg_10.txt')
# The outer message is a multipart
eq(msg.get_payload(decode=True), None)
# Subpart 1 is 7bit encoded
eq(msg.get_payload(0).get_payload(decode=True),
'This is a 7bit encoded message.\n')
# Subpart 2 is quopri
eq(msg.get_payload(1).get_payload(decode=True),
'\xa1This is a Quoted Printable encoded message!\n')
# Subpart 3 is base64
eq(msg.get_payload(2).get_payload(decode=True),
'This is a Base64 encoded message.')
# Subpart 4 is base64 with a trailing newline, which
# used to be stripped (issue 7143).
eq(msg.get_payload(3).get_payload(decode=True),
'This is a Base64 encoded message.\n')
# Subpart 5 has no Content-Transfer-Encoding: header.
eq(msg.get_payload(4).get_payload(decode=True),
'This has no Content-Transfer-Encoding: header.\n')
def test_get_decoded_uu_payload(self):
eq = self.assertEqual
msg = Message()
msg.set_payload('begin 666 -\n+:&5L;&\\@=V]R;&0 \n \nend\n')
for cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
msg['content-transfer-encoding'] = cte
eq(msg.get_payload(decode=True), 'hello world')
# Now try some bogus data
msg.set_payload('foo')
eq(msg.get_payload(decode=True), 'foo')
def test_decode_bogus_uu_payload_quietly(self):
msg = Message()
msg.set_payload('begin 664 foo.txt\n%' % i for i in range(10)])
msg.set_payload('Test')
sfp = StringIO()
g = Generator(sfp)
g.flatten(msg)
eq(sfp.getvalue(), """\
From: [email protected]
References: <[email protected]> <[email protected]> <[email protected]> <[email protected]> <[email protected]>
<[email protected]> <[email protected]> <[email protected]> <[email protected]> <[email protected]>
Test""")
def test_no_split_long_header(self):
eq = self.ndiffAssertEqual
hstr = 'References: ' + 'x' * 80
h = Header(hstr, continuation_ws='\t')
eq(h.encode(), """\
References: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx""")
def test_splitting_multiple_long_lines(self):
eq = self.ndiffAssertEqual
hstr = """\
from babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for ; Sat, 2 Feb 2002 17:00:06 -0800 (PST)
\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for ; Sat, 2 Feb 2002 17:00:06 -0800 (PST)
\tfrom babylon.socal-raves.org (localhost [127.0.0.1]); by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81; for ; Sat, 2 Feb 2002 17:00:06 -0800 (PST)
"""
h = Header(hstr, continuation_ws='\t')
eq(h.encode(), """\
from babylon.socal-raves.org (localhost [127.0.0.1]);
\tby babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81;
\tfor ;
\tSat, 2 Feb 2002 17:00:06 -0800 (PST)
\tfrom babylon.socal-raves.org (localhost [127.0.0.1]);
\tby babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81;
\tfor ;
\tSat, 2 Feb 2002 17:00:06 -0800 (PST)
\tfrom babylon.socal-raves.org (localhost [127.0.0.1]);
\tby babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81;
\tfor ;
\tSat, 2 Feb 2002 17:00:06 -0800 (PST)""")
def test_splitting_first_line_only_is_long(self):
eq = self.ndiffAssertEqual
hstr = """\
from modemcable093.139-201-24.que.mc.videotron.ca ([24.201.139.93] helo=cthulhu.gerg.ca)
\tby kronos.mems-exchange.org with esmtp (Exim 4.05)
\tid 17k4h5-00034i-00
\tfor [email protected]; Wed, 28 Aug 2002 11:25:20 -0400"""
h = Header(hstr, maxlinelen=78, header_name='Received',
continuation_ws='\t')
eq(h.encode(), """\
from modemcable093.139-201-24.que.mc.videotron.ca ([24.201.139.93]
\thelo=cthulhu.gerg.ca)
\tby kronos.mems-exchange.org with esmtp (Exim 4.05)
\tid 17k4h5-00034i-00
\tfor [email protected]; Wed, 28 Aug 2002 11:25:20 -0400""")
def test_long_8bit_header(self):
eq = self.ndiffAssertEqual
msg = Message()
h = Header('Britische Regierung gibt', 'iso-8859-1',
header_name='Subject')
h.append('gr\xfcnes Licht f\xfcr Offshore-Windkraftprojekte')
msg['Subject'] = h
eq(msg.as_string(), """\
Subject: =?iso-8859-1?q?Britische_Regierung_gibt?= =?iso-8859-1?q?gr=FCnes?=
=?iso-8859-1?q?_Licht_f=FCr_Offshore-Windkraftprojekte?=
""")
def test_long_8bit_header_no_charset(self):
eq = self.ndiffAssertEqual
msg = Message()
msg['Reply-To'] = 'Britische Regierung gibt gr\xfcnes Licht f\xfcr Offshore-Windkraftprojekte '
eq(msg.as_string(), """\
Reply-To: Britische Regierung gibt gr\xfcnes Licht f\xfcr Offshore-Windkraftprojekte
""")
def test_long_to_header(self):
eq = self.ndiffAssertEqual
to = '"Someone Test #A" ,,"Someone Test #B" , "Someone Test #C" , "Someone Test #D" '
msg = Message()
msg['To'] = to
eq(msg.as_string(0), '''\
To: "Someone Test #A" , ,
"Someone Test #B" ,
"Someone Test #C" ,
"Someone Test #D"
''')
def test_long_line_after_append(self):
eq = self.ndiffAssertEqual
s = 'This is an example of string which has almost the limit of header length.'
h = Header(s)
h.append('Add another line.')
eq(h.encode(), """\
This is an example of string which has almost the limit of header length.
Add another line.""")
def test_shorter_line_with_append(self):
eq = self.ndiffAssertEqual
s = 'This is a shorter line.'
h = Header(s)
h.append('Add another sentence. (Surprise?)')
eq(h.encode(),
'This is a shorter line. Add another sentence. (Surprise?)')
def test_long_field_name(self):
eq = self.ndiffAssertEqual
fn = 'X-Very-Very-Very-Long-Header-Name'
gs = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
h = Header(gs, 'iso-8859-1', header_name=fn)
# BAW: this seems broken because the first line is too long
eq(h.encode(), """\
=?iso-8859-1?q?Die_Mieter_treten_hier_?=
=?iso-8859-1?q?ein_werden_mit_einem_Foerderband_komfortabel_den_Korridor_?=
=?iso-8859-1?q?entlang=2C_an_s=FCdl=FCndischen_Wandgem=E4lden_vorbei=2C_g?=
=?iso-8859-1?q?egen_die_rotierenden_Klingen_bef=F6rdert=2E_?=""")
def test_long_received_header(self):
h = 'from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP; Wed, 05 Mar 2003 18:10:18 -0700'
msg = Message()
msg['Received-1'] = Header(h, continuation_ws='\t')
msg['Received-2'] = h
self.assertEqual(msg.as_string(), """\
Received-1: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by
\throthgar.la.mastaler.com (tmda-ofmipd) with ESMTP;
\tWed, 05 Mar 2003 18:10:18 -0700
Received-2: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by
hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP;
Wed, 05 Mar 2003 18:10:18 -0700
""")
def test_string_headerinst_eq(self):
h = '<15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> (David Bremner\'s message of "Thu, 6 Mar 2003 13:58:21 +0100")'
msg = Message()
msg['Received'] = Header(h, header_name='Received',
continuation_ws='\t')
msg['Received'] = h
self.ndiffAssertEqual(msg.as_string(), """\
Received: <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de>
\t(David Bremner's message of "Thu, 6 Mar 2003 13:58:21 +0100")
Received: <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de>
(David Bremner's message of "Thu, 6 Mar 2003 13:58:21 +0100")
""")
def test_long_unbreakable_lines_with_continuation(self):
eq = self.ndiffAssertEqual
msg = Message()
t = """\
iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp"""
msg['Face-1'] = t
msg['Face-2'] = Header(t, header_name='Face-2')
eq(msg.as_string(), """\
Face-1: iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp
Face-2: iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp
""")
def test_another_long_multiline_header(self):
eq = self.ndiffAssertEqual
m = '''\
Received: from siimage.com ([172.25.1.3]) by zima.siliconimage.com with Microsoft SMTPSVC(5.0.2195.4905);
Wed, 16 Oct 2002 07:41:11 -0700'''
msg = email.message_from_string(m)
eq(msg.as_string(), '''\
Received: from siimage.com ([172.25.1.3]) by zima.siliconimage.com with
Microsoft SMTPSVC(5.0.2195.4905); Wed, 16 Oct 2002 07:41:11 -0700
''')
def test_long_lines_with_different_header(self):
eq = self.ndiffAssertEqual
h = """\
List-Unsubscribe: ,
"""
msg = Message()
msg['List'] = h
msg['List'] = Header(h, header_name='List')
eq(msg.as_string(), """\
List: List-Unsubscribe: ,
List: List-Unsubscribe: ,
""")
# Test mangling of "From " lines in the body of a message
class TestFromMangling(unittest.TestCase):
def setUp(self):
self.msg = Message()
self.msg['From'] = '[email protected]'
self.msg.set_payload("""\
From the desk of A.A.A.:
Blah blah blah
""")
def test_mangled_from(self):
s = StringIO()
g = Generator(s, mangle_from_=True)
g.flatten(self.msg)
self.assertEqual(s.getvalue(), """\
From: [email protected]
>From the desk of A.A.A.:
Blah blah blah
""")
def test_dont_mangle_from(self):
s = StringIO()
g = Generator(s, mangle_from_=False)
g.flatten(self.msg)
self.assertEqual(s.getvalue(), """\
From: [email protected]
From the desk of A.A.A.:
Blah blah blah
""")
def test_mangle_from_in_preamble_and_epilog(self):
s = StringIO()
g = Generator(s, mangle_from_=True)
msg = email.message_from_string(textwrap.dedent("""\
From: [email protected]
Mime-Version: 1.0
Content-Type: multipart/mixed; boundary=XXX
From somewhere unknown
--XXX
Content-Type: text/plain
foo
--XXX--
From somewhere unknowable
"""))
g.flatten(msg)
self.assertEqual(len([1 for x in s.getvalue().split('\n')
if x.startswith('>From ')]), 2)
# Test the basic MIMEAudio class
class TestMIMEAudio(unittest.TestCase):
def setUp(self):
# Make sure we pick up the audiotest.au that lives in email/test/data.
# In Python, there's an audiotest.au living in Lib/test but that isn't
# included in some binary distros that don't include the test
# package. The trailing empty string on the .join() is significant
# since findfile() will do a dirname().
datadir = os.path.join(os.path.dirname(landmark), 'data', '')
fp = open(findfile('audiotest.au', datadir), 'rb')
try:
self._audiodata = fp.read()
finally:
fp.close()
self._au = MIMEAudio(self._audiodata)
def test_guess_minor_type(self):
self.assertEqual(self._au.get_content_type(), 'audio/basic')
def test_encoding(self):
payload = self._au.get_payload()
self.assertEqual(base64.decodestring(payload), self._audiodata)
def test_checkSetMinor(self):
au = MIMEAudio(self._audiodata, 'fish')
self.assertEqual(au.get_content_type(), 'audio/fish')
def test_add_header(self):
eq = self.assertEqual
unless = self.assertTrue
self._au.add_header('Content-Disposition', 'attachment',
filename='audiotest.au')
eq(self._au['content-disposition'],
'attachment; filename="audiotest.au"')
eq(self._au.get_params(header='content-disposition'),
[('attachment', ''), ('filename', 'audiotest.au')])
eq(self._au.get_param('filename', header='content-disposition'),
'audiotest.au')
missing = []
eq(self._au.get_param('attachment', header='content-disposition'), '')
unless(self._au.get_param('foo', failobj=missing,
header='content-disposition') is missing)
# Try some missing stuff
unless(self._au.get_param('foobar', missing) is missing)
unless(self._au.get_param('attachment', missing,
header='foobar') is missing)
# Test the basic MIMEImage class
class TestMIMEImage(unittest.TestCase):
def setUp(self):
fp = openfile('PyBanner048.gif')
try:
self._imgdata = fp.read()
finally:
fp.close()
self._im = MIMEImage(self._imgdata)
def test_guess_minor_type(self):
self.assertEqual(self._im.get_content_type(), 'image/gif')
def test_encoding(self):
payload = self._im.get_payload()
self.assertEqual(base64.decodestring(payload), self._imgdata)
def test_checkSetMinor(self):
im = MIMEImage(self._imgdata, 'fish')
self.assertEqual(im.get_content_type(), 'image/fish')
def test_add_header(self):
eq = self.assertEqual
unless = self.assertTrue
self._im.add_header('Content-Disposition', 'attachment',
filename='dingusfish.gif')
eq(self._im['content-disposition'],
'attachment; filename="dingusfish.gif"')
eq(self._im.get_params(header='content-disposition'),
[('attachment', ''), ('filename', 'dingusfish.gif')])
eq(self._im.get_param('filename', header='content-disposition'),
'dingusfish.gif')
missing = []
eq(self._im.get_param('attachment', header='content-disposition'), '')
unless(self._im.get_param('foo', failobj=missing,
header='content-disposition') is missing)
# Try some missing stuff
unless(self._im.get_param('foobar', missing) is missing)
unless(self._im.get_param('attachment', missing,
header='foobar') is missing)
# Test the basic MIMEText class
class TestMIMEText(unittest.TestCase):
def setUp(self):
self._msg = MIMEText('hello there')
def test_types(self):
eq = self.assertEqual
unless = self.assertTrue
eq(self._msg.get_content_type(), 'text/plain')
eq(self._msg.get_param('charset'), 'us-ascii')
missing = []
unless(self._msg.get_param('foobar', missing) is missing)
unless(self._msg.get_param('charset', missing, header='foobar')
is missing)
def test_payload(self):
self.assertEqual(self._msg.get_payload(), 'hello there')
self.assertTrue(not self._msg.is_multipart())
def test_charset(self):
eq = self.assertEqual
msg = MIMEText('hello there', _charset='us-ascii')
eq(msg.get_charset().input_charset, 'us-ascii')
eq(msg['content-type'], 'text/plain; charset="us-ascii"')
def test_7bit_unicode_input(self):
eq = self.assertEqual
msg = MIMEText(u'hello there', _charset='us-ascii')
eq(msg.get_charset().input_charset, 'us-ascii')
eq(msg['content-type'], 'text/plain; charset="us-ascii"')
def test_7bit_unicode_input_no_charset(self):
eq = self.assertEqual
msg = MIMEText(u'hello there')
eq(msg.get_charset(), 'us-ascii')
eq(msg['content-type'], 'text/plain; charset="us-ascii"')
self.assertTrue('hello there' in msg.as_string())
def test_8bit_unicode_input(self):
teststr = u'\u043a\u0438\u0440\u0438\u043b\u0438\u0446\u0430'
eq = self.assertEqual
msg = MIMEText(teststr, _charset='utf-8')
eq(msg.get_charset().output_charset, 'utf-8')
eq(msg['content-type'], 'text/plain; charset="utf-8"')
eq(msg.get_payload(decode=True), teststr.encode('utf-8'))
def test_8bit_unicode_input_no_charset(self):
teststr = u'\u043a\u0438\u0440\u0438\u043b\u0438\u0446\u0430'
self.assertRaises(UnicodeEncodeError, MIMEText, teststr)
# Test complicated multipart/* messages
class TestMultipart(TestEmailBase):
def setUp(self):
fp = openfile('PyBanner048.gif')
try:
data = fp.read()
finally:
fp.close()
container = MIMEBase('multipart', 'mixed', boundary='BOUNDARY')
image = MIMEImage(data, name='dingusfish.gif')
image.add_header('content-disposition', 'attachment',
filename='dingusfish.gif')
intro = MIMEText('''\
Hi there,
This is the dingus fish.
''')
container.attach(intro)
container.attach(image)
container['From'] = 'Barry '
container['To'] = 'Dingus Lovers '
container['Subject'] = 'Here is your dingus fish'
now = 987809702.54848599
timetuple = time.localtime(now)
if timetuple[-1] == 0:
tzsecs = time.timezone
else:
tzsecs = time.altzone
if tzsecs > 0:
sign = '-'
else:
sign = '+'
tzoffset = ' %s%04d' % (sign, tzsecs // 36)
container['Date'] = time.strftime(
'%a, %d %b %Y %H:%M:%S',
time.localtime(now)) + tzoffset
self._msg = container
self._im = image
self._txt = intro
def test_hierarchy(self):
# convenience
eq = self.assertEqual
unless = self.assertTrue
raises = self.assertRaises
# tests
m = self._msg
unless(m.is_multipart())
eq(m.get_content_type(), 'multipart/mixed')
eq(len(m.get_payload()), 2)
raises(IndexError, m.get_payload, 2)
m0 = m.get_payload(0)
m1 = m.get_payload(1)
unless(m0 is self._txt)
unless(m1 is self._im)
eq(m.get_payload(), [m0, m1])
unless(not m0.is_multipart())
unless(not m1.is_multipart())
def test_empty_multipart_idempotent(self):
text = """\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
--BOUNDARY--
"""
msg = Parser().parsestr(text)
self.ndiffAssertEqual(text, msg.as_string())
def test_no_parts_in_a_multipart_with_none_epilogue(self):
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.set_boundary('BOUNDARY')
self.ndiffAssertEqual(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
--BOUNDARY--''')
def test_no_parts_in_a_multipart_with_empty_epilogue(self):
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.preamble = ''
outer.epilogue = ''
outer.set_boundary('BOUNDARY')
self.ndiffAssertEqual(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
--BOUNDARY--
''')
def test_one_part_in_a_multipart(self):
eq = self.ndiffAssertEqual
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.set_boundary('BOUNDARY')
msg = MIMEText('hello world')
outer.attach(msg)
eq(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
hello world
--BOUNDARY--''')
def test_seq_parts_in_a_multipart_with_empty_preamble(self):
eq = self.ndiffAssertEqual
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.preamble = ''
msg = MIMEText('hello world')
outer.attach(msg)
outer.set_boundary('BOUNDARY')
eq(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
hello world
--BOUNDARY--''')
def test_seq_parts_in_a_multipart_with_none_preamble(self):
eq = self.ndiffAssertEqual
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.preamble = None
msg = MIMEText('hello world')
outer.attach(msg)
outer.set_boundary('BOUNDARY')
eq(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
hello world
--BOUNDARY--''')
def test_seq_parts_in_a_multipart_with_none_epilogue(self):
eq = self.ndiffAssertEqual
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.epilogue = None
msg = MIMEText('hello world')
outer.attach(msg)
outer.set_boundary('BOUNDARY')
eq(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
hello world
--BOUNDARY--''')
def test_seq_parts_in_a_multipart_with_empty_epilogue(self):
eq = self.ndiffAssertEqual
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.epilogue = ''
msg = MIMEText('hello world')
outer.attach(msg)
outer.set_boundary('BOUNDARY')
eq(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
hello world
--BOUNDARY--
''')
def test_seq_parts_in_a_multipart_with_nl_epilogue(self):
eq = self.ndiffAssertEqual
outer = MIMEBase('multipart', 'mixed')
outer['Subject'] = 'A subject'
outer['To'] = '[email protected]'
outer['From'] = '[email protected]'
outer.epilogue = '\n'
msg = MIMEText('hello world')
outer.attach(msg)
outer.set_boundary('BOUNDARY')
eq(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: [email protected]
From: [email protected]
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
hello world
--BOUNDARY--
''')
def test_message_external_body(self):
eq = self.assertEqual
msg = self._msgobj('msg_36.txt')
eq(len(msg.get_payload()), 2)
msg1 = msg.get_payload(1)
eq(msg1.get_content_type(), 'multipart/alternative')
eq(len(msg1.get_payload()), 2)
for subpart in msg1.get_payload():
eq(subpart.get_content_type(), 'message/external-body')
eq(len(subpart.get_payload()), 1)
subsubpart = subpart.get_payload(0)
eq(subsubpart.get_content_type(), 'text/plain')
def test_double_boundary(self):
# msg_37.txt is a multipart that contains two dash-boundary's in a
# row. Our interpretation of RFC 2046 calls for ignoring the second
# and subsequent boundaries.
msg = self._msgobj('msg_37.txt')
self.assertEqual(len(msg.get_payload()), 3)
def test_nested_inner_contains_outer_boundary(self):
eq = self.ndiffAssertEqual
# msg_38.txt has an inner part that contains outer boundaries. My
# interpretation of RFC 2046 (based on sections 5.1 and 5.1.2) say
# these are illegal and should be interpreted as unterminated inner
# parts.
msg = self._msgobj('msg_38.txt')
sfp = StringIO()
Iterators._structure(msg, sfp)
eq(sfp.getvalue(), """\
multipart/mixed
multipart/mixed
multipart/alternative
text/plain
text/plain
text/plain
text/plain
""")
def test_nested_with_same_boundary(self):
eq = self.ndiffAssertEqual
# msg 39.txt is similarly evil in that it's got inner parts that use
# the same boundary as outer parts. Again, I believe the way this is
# parsed is closest to the spirit of RFC 2046
msg = self._msgobj('msg_39.txt')
sfp = StringIO()
Iterators._structure(msg, sfp)
eq(sfp.getvalue(), """\
multipart/mixed
multipart/mixed
multipart/alternative
application/octet-stream
application/octet-stream
text/plain
""")
def test_boundary_in_non_multipart(self):
msg = self._msgobj('msg_40.txt')
self.assertEqual(msg.as_string(), '''\
MIME-Version: 1.0
Content-Type: text/html; boundary="--961284236552522269"
----961284236552522269
Content-Type: text/html;
Content-Transfer-Encoding: 7Bit
----961284236552522269--
''')
def test_boundary_with_leading_space(self):
eq = self.assertEqual
msg = email.message_from_string('''\
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary=" XXXX"
-- XXXX
Content-Type: text/plain
-- XXXX
Content-Type: text/plain
-- XXXX--
''')
self.assertTrue(msg.is_multipart())
eq(msg.get_boundary(), ' XXXX')
eq(len(msg.get_payload()), 2)
def test_boundary_without_trailing_newline(self):
m = Parser().parsestr("""\
Content-Type: multipart/mixed; boundary="===============0012394164=="
MIME-Version: 1.0
--===============0012394164==
Content-Type: image/file1.jpg
MIME-Version: 1.0
Content-Transfer-Encoding: base64
YXNkZg==
--===============0012394164==--""")
self.assertEqual(m.get_payload(0).get_payload(), 'YXNkZg==')
# Test some badly formatted messages
class TestNonConformant(TestEmailBase):
def test_parse_missing_minor_type(self):
eq = self.assertEqual
msg = self._msgobj('msg_14.txt')
eq(msg.get_content_type(), 'text/plain')
eq(msg.get_content_maintype(), 'text')
eq(msg.get_content_subtype(), 'plain')
def test_same_boundary_inner_outer(self):
unless = self.assertTrue
msg = self._msgobj('msg_15.txt')
# XXX We can probably eventually do better
inner = msg.get_payload(0)
unless(hasattr(inner, 'defects'))
self.assertEqual(len(inner.defects), 1)
unless(isinstance(inner.defects[0],
Errors.StartBoundaryNotFoundDefect))
def test_multipart_no_boundary(self):
unless = self.assertTrue
msg = self._msgobj('msg_25.txt')
unless(isinstance(msg.get_payload(), str))
self.assertEqual(len(msg.defects), 2)
unless(isinstance(msg.defects[0], Errors.NoBoundaryInMultipartDefect))
unless(isinstance(msg.defects[1],
Errors.MultipartInvariantViolationDefect))
def test_invalid_content_type(self):
eq = self.assertEqual
neq = self.ndiffAssertEqual
msg = Message()
# RFC 2045, $5.2 says invalid yields text/plain
msg['Content-Type'] = 'text'
eq(msg.get_content_maintype(), 'text')
eq(msg.get_content_subtype(), 'plain')
eq(msg.get_content_type(), 'text/plain')
# Clear the old value and try something /really/ invalid
del msg['content-type']
msg['Content-Type'] = 'foo'
eq(msg.get_content_maintype(), 'text')
eq(msg.get_content_subtype(), 'plain')
eq(msg.get_content_type(), 'text/plain')
# Still, make sure that the message is idempotently generated
s = StringIO()
g = Generator(s)
g.flatten(msg)
neq(s.getvalue(), 'Content-Type: foo\n\n')
def test_no_start_boundary(self):
eq = self.ndiffAssertEqual
msg = self._msgobj('msg_31.txt')
eq(msg.get_payload(), """\
--BOUNDARY
Content-Type: text/plain
message 1
--BOUNDARY
Content-Type: text/plain
message 2
--BOUNDARY--
""")
def test_no_separating_blank_line(self):
eq = self.ndiffAssertEqual
msg = self._msgobj('msg_35.txt')
eq(msg.as_string(), """\
From: [email protected]
To: [email protected]
Subject: here's something interesting
counter to RFC 2822, there's no separating newline here
""")
def test_lying_multipart(self):
unless = self.assertTrue
msg = self._msgobj('msg_41.txt')
unless(hasattr(msg, 'defects'))
self.assertEqual(len(msg.defects), 2)
unless(isinstance(msg.defects[0], Errors.NoBoundaryInMultipartDefect))
unless(isinstance(msg.defects[1],
Errors.MultipartInvariantViolationDefect))
def test_missing_start_boundary(self):
outer = self._msgobj('msg_42.txt')
# The message structure is:
#
# multipart/mixed
# text/plain
# message/rfc822
# multipart/mixed [*]
#
# [*] This message is missing its start boundary
bad = outer.get_payload(1).get_payload(0)
self.assertEqual(len(bad.defects), 1)
self.assertTrue(isinstance(bad.defects[0],
Errors.StartBoundaryNotFoundDefect))
def test_first_line_is_continuation_header(self):
eq = self.assertEqual
m = ' Line 1\nLine 2\nLine 3'
msg = email.message_from_string(m)
eq(msg.keys(), [])
eq(msg.get_payload(), 'Line 2\nLine 3')
eq(len(msg.defects), 1)
self.assertTrue(isinstance(msg.defects[0],
Errors.FirstHeaderLineIsContinuationDefect))
eq(msg.defects[0].line, ' Line 1\n')
# Test RFC 2047 header encoding and decoding
class TestRFC2047(unittest.TestCase):
def test_rfc2047_multiline(self):
eq = self.assertEqual
s = """Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz
foo bar =?mac-iceland?q?r=8Aksm=9Arg=8Cs?="""
dh = decode_header(s)
eq(dh, [
('Re:', None),
('r\x8aksm\x9arg\x8cs', 'mac-iceland'),
('baz foo bar', None),
('r\x8aksm\x9arg\x8cs', 'mac-iceland')])
eq(str(make_header(dh)),
"""Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar
=?mac-iceland?q?r=8Aksm=9Arg=8Cs?=""")
def test_whitespace_eater_unicode(self):
eq = self.assertEqual
s = '=?ISO-8859-1?Q?Andr=E9?= Pirard '
dh = decode_header(s)
eq(dh, [('Andr\xe9', 'iso-8859-1'), ('Pirard ', None)])
hu = unicode(make_header(dh)).encode('latin-1')
eq(hu, 'Andr\xe9 Pirard ')
def test_whitespace_eater_unicode_2(self):
eq = self.assertEqual
s = 'The =?iso-8859-1?b?cXVpY2sgYnJvd24gZm94?= jumped over the =?iso-8859-1?b?bGF6eSBkb2c=?='
dh = decode_header(s)
eq(dh, [('The', None), ('quick brown fox', 'iso-8859-1'),
('jumped over the', None), ('lazy dog', 'iso-8859-1')])
hu = make_header(dh).__unicode__()
eq(hu, u'The quick brown fox jumped over the lazy dog')
def test_rfc2047_without_whitespace(self):
s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
dh = decode_header(s)
self.assertEqual(dh, [(s, None)])
def test_rfc2047_with_whitespace(self):
s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord'
dh = decode_header(s)
self.assertEqual(dh, [('Sm', None), ('\xf6', 'iso-8859-1'),
('rg', None), ('\xe5', 'iso-8859-1'),
('sbord', None)])
def test_rfc2047_B_bad_padding(self):
s = '=?iso-8859-1?B?%s?='
data = [ # only test complete bytes
('dm==', 'v'), ('dm=', 'v'), ('dm', 'v'),
('dmk=', 'vi'), ('dmk', 'vi')
]
for q, a in data:
dh = decode_header(s % q)
self.assertEqual(dh, [(a, 'iso-8859-1')])
def test_rfc2047_Q_invalid_digits(self):
# issue 10004.
s = '=?iso-8659-1?Q?andr=e9=zz?='
self.assertEqual(decode_header(s),
[(b'andr\xe9=zz', 'iso-8659-1')])
# Test the MIMEMessage class
class TestMIMEMessage(TestEmailBase):
def setUp(self):
fp = openfile('msg_11.txt')
try:
self._text = fp.read()
finally:
fp.close()
def test_type_error(self):
self.assertRaises(TypeError, MIMEMessage, 'a plain string')
def test_valid_argument(self):
eq = self.assertEqual
unless = self.assertTrue
subject = 'A sub-message'
m = Message()
m['Subject'] = subject
r = MIMEMessage(m)
eq(r.get_content_type(), 'message/rfc822')
payload = r.get_payload()
unless(isinstance(payload, list))
eq(len(payload), 1)
subpart = payload[0]
unless(subpart is m)
eq(subpart['subject'], subject)
def test_bad_multipart(self):
eq = self.assertEqual
msg1 = Message()
msg1['Subject'] = 'subpart 1'
msg2 = Message()
msg2['Subject'] = 'subpart 2'
r = MIMEMessage(msg1)
self.assertRaises(Errors.MultipartConversionError, r.attach, msg2)
def test_generate(self):
# First craft the message to be encapsulated
m = Message()
m['Subject'] = 'An enclosed message'
m.set_payload('Here is the body of the message.\n')
r = MIMEMessage(m)
r['Subject'] = 'The enclosing message'
s = StringIO()
g = Generator(s)
g.flatten(r)
self.assertEqual(s.getvalue(), """\
Content-Type: message/rfc822
MIME-Version: 1.0
Subject: The enclosing message
Subject: An enclosed message
Here is the body of the message.
""")
def test_parse_message_rfc822(self):
eq = self.assertEqual
unless = self.assertTrue
msg = self._msgobj('msg_11.txt')
eq(msg.get_content_type(), 'message/rfc822')
payload = msg.get_payload()
unless(isinstance(payload, list))
eq(len(payload), 1)
submsg = payload[0]
self.assertTrue(isinstance(submsg, Message))
eq(submsg['subject'], 'An enclosed message')
eq(submsg.get_payload(), 'Here is the body of the message.\n')
def test_dsn(self):
eq = self.assertEqual
unless = self.assertTrue
# msg 16 is a Delivery Status Notification, see RFC 1894
msg = self._msgobj('msg_16.txt')
eq(msg.get_content_type(), 'multipart/report')
unless(msg.is_multipart())
eq(len(msg.get_payload()), 3)
# Subpart 1 is a text/plain, human readable section
subpart = msg.get_payload(0)
eq(subpart.get_content_type(), 'text/plain')
eq(subpart.get_payload(), """\
This report relates to a message you sent with the following header fields:
Message-id: <[email protected]>
Date: Sun, 23 Sep 2001 20:10:55 -0700
From: "Ian T. Henry"
To: SoCal Raves
Subject: [scr] yeah for Ians!!
Your message cannot be delivered to the following recipients:
Recipient address: [email protected]
Reason: recipient reached disk quota
""")
# Subpart 2 contains the machine parsable DSN information. It
# consists of two blocks of headers, represented by two nested Message
# objects.
subpart = msg.get_payload(1)
eq(subpart.get_content_type(), 'message/delivery-status')
eq(len(subpart.get_payload()), 2)
# message/delivery-status should treat each block as a bunch of
# headers, i.e. a bunch of Message objects.
dsn1 = subpart.get_payload(0)
unless(isinstance(dsn1, Message))
eq(dsn1['original-envelope-id'], '[email protected]')
eq(dsn1.get_param('dns', header='reporting-mta'), '')
# Try a missing one
eq(dsn1.get_param('nsd', header='reporting-mta'), None)
dsn2 = subpart.get_payload(1)
unless(isinstance(dsn2, Message))
eq(dsn2['action'], 'failed')
eq(dsn2.get_params(header='original-recipient'),
[('rfc822', ''), ('[email protected]', '')])
eq(dsn2.get_param('rfc822', header='final-recipient'), '')
# Subpart 3 is the original message
subpart = msg.get_payload(2)
eq(subpart.get_content_type(), 'message/rfc822')
payload = subpart.get_payload()
unless(isinstance(payload, list))
eq(len(payload), 1)
subsubpart = payload[0]
unless(isinstance(subsubpart, Message))
eq(subsubpart.get_content_type(), 'text/plain')
eq(subsubpart['message-id'],
'<[email protected]>')
def test_epilogue(self):
eq = self.ndiffAssertEqual
fp = openfile('msg_21.txt')
try:
text = fp.read()
finally:
fp.close()
msg = Message()
msg['From'] = '[email protected]'
msg['To'] = '[email protected]'
msg['Subject'] = 'Test'
msg.preamble = 'MIME message'
msg.epilogue = 'End of MIME message\n'
msg1 = MIMEText('One')
msg2 = MIMEText('Two')
msg.add_header('Content-Type', 'multipart/mixed', boundary='BOUNDARY')
msg.attach(msg1)
msg.attach(msg2)
sfp = StringIO()
g = Generator(sfp)
g.flatten(msg)
eq(sfp.getvalue(), text)
def test_no_nl_preamble(self):
eq = self.ndiffAssertEqual
msg = Message()
msg['From'] = '[email protected]'
msg['To'] = '[email protected]'
msg['Subject'] = 'Test'
msg.preamble = 'MIME message'
msg.epilogue = ''
msg1 = MIMEText('One')
msg2 = MIMEText('Two')
msg.add_header('Content-Type', 'multipart/mixed', boundary='BOUNDARY')
msg.attach(msg1)
msg.attach(msg2)
eq(msg.as_string(), """\
From: [email protected]
To: [email protected]
Subject: Test
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME message
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
One
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Two
--BOUNDARY--
""")
def test_default_type(self):
eq = self.assertEqual
fp = openfile('msg_30.txt')
try:
msg = email.message_from_file(fp)
finally:
fp.close()
container1 = msg.get_payload(0)
eq(container1.get_default_type(), 'message/rfc822')
eq(container1.get_content_type(), 'message/rfc822')
container2 = msg.get_payload(1)
eq(container2.get_default_type(), 'message/rfc822')
eq(container2.get_content_type(), 'message/rfc822')
container1a = container1.get_payload(0)
eq(container1a.get_default_type(), 'text/plain')
eq(container1a.get_content_type(), 'text/plain')
container2a = container2.get_payload(0)
eq(container2a.get_default_type(), 'text/plain')
eq(container2a.get_content_type(), 'text/plain')
def test_default_type_with_explicit_container_type(self):
eq = self.assertEqual
fp = openfile('msg_28.txt')
try:
msg = email.message_from_file(fp)
finally:
fp.close()
container1 = msg.get_payload(0)
eq(container1.get_default_type(), 'message/rfc822')
eq(container1.get_content_type(), 'message/rfc822')
container2 = msg.get_payload(1)
eq(container2.get_default_type(), 'message/rfc822')
eq(container2.get_content_type(), 'message/rfc822')
container1a = container1.get_payload(0)
eq(container1a.get_default_type(), 'text/plain')
eq(container1a.get_content_type(), 'text/plain')
container2a = container2.get_payload(0)
eq(container2a.get_default_type(), 'text/plain')
eq(container2a.get_content_type(), 'text/plain')
def test_default_type_non_parsed(self):
eq = self.assertEqual
neq = self.ndiffAssertEqual
# Set up container
container = MIMEMultipart('digest', 'BOUNDARY')
container.epilogue = ''
# Set up subparts
subpart1a = MIMEText('message 1\n')
subpart2a = MIMEText('message 2\n')
subpart1 = MIMEMessage(subpart1a)
subpart2 = MIMEMessage(subpart2a)
container.attach(subpart1)
container.attach(subpart2)
eq(subpart1.get_content_type(), 'message/rfc822')
eq(subpart1.get_default_type(), 'message/rfc822')
eq(subpart2.get_content_type(), 'message/rfc822')
eq(subpart2.get_default_type(), 'message/rfc822')
neq(container.as_string(0), '''\
Content-Type: multipart/digest; boundary="BOUNDARY"
MIME-Version: 1.0
--BOUNDARY
Content-Type: message/rfc822
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
message 1
--BOUNDARY
Content-Type: message/rfc822
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
message 2
--BOUNDARY--
''')
del subpart1['content-type']
del subpart1['mime-version']
del subpart2['content-type']
del subpart2['mime-version']
eq(subpart1.get_content_type(), 'message/rfc822')
eq(subpart1.get_default_type(), 'message/rfc822')
eq(subpart2.get_content_type(), 'message/rfc822')
eq(subpart2.get_default_type(), 'message/rfc822')
neq(container.as_string(0), '''\
Content-Type: multipart/digest; boundary="BOUNDARY"
MIME-Version: 1.0
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
message 1
--BOUNDARY
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
message 2
--BOUNDARY--
''')
def test_mime_attachments_in_constructor(self):
eq = self.assertEqual
text1 = MIMEText('')
text2 = MIMEText('')
msg = MIMEMultipart(_subparts=(text1, text2))
eq(len(msg.get_payload()), 2)
eq(msg.get_payload(0), text1)
eq(msg.get_payload(1), text2)
def test_default_multipart_constructor(self):
msg = MIMEMultipart()
self.assertTrue(msg.is_multipart())
# A general test of parser->model->generator idempotency. IOW, read a message
# in, parse it into a message object tree, then without touching the tree,
# regenerate the plain text. The original text and the transformed text
# should be identical. Note: that we ignore the Unix-From since that may
# contain a changed date.
class TestIdempotent(TestEmailBase):
def _msgobj(self, filename):
fp = openfile(filename)
try:
data = fp.read()
finally:
fp.close()
msg = email.message_from_string(data)
return msg, data
def _idempotent(self, msg, text):
eq = self.ndiffAssertEqual
s = StringIO()
g = Generator(s, maxheaderlen=0)
g.flatten(msg)
eq(text, s.getvalue())
def test_parse_text_message(self):
eq = self.assertEqual
msg, text = self._msgobj('msg_01.txt')
eq(msg.get_content_type(), 'text/plain')
eq(msg.get_content_maintype(), 'text')
eq(msg.get_content_subtype(), 'plain')
eq(msg.get_params()[1], ('charset', 'us-ascii'))
eq(msg.get_param('charset'), 'us-ascii')
eq(msg.preamble, None)
eq(msg.epilogue, None)
self._idempotent(msg, text)
def test_parse_untyped_message(self):
eq = self.assertEqual
msg, text = self._msgobj('msg_03.txt')
eq(msg.get_content_type(), 'text/plain')
eq(msg.get_params(), None)
eq(msg.get_param('charset'), None)
self._idempotent(msg, text)
def test_simple_multipart(self):
msg, text = self._msgobj('msg_04.txt')
self._idempotent(msg, text)
def test_MIME_digest(self):
msg, text = self._msgobj('msg_02.txt')
self._idempotent(msg, text)
def test_long_header(self):
msg, text = self._msgobj('msg_27.txt')
self._idempotent(msg, text)
def test_MIME_digest_with_part_headers(self):
msg, text = self._msgobj('msg_28.txt')
self._idempotent(msg, text)
def test_mixed_with_image(self):
msg, text = self._msgobj('msg_06.txt')
self._idempotent(msg, text)
def test_multipart_report(self):
msg, text = self._msgobj('msg_05.txt')
self._idempotent(msg, text)
def test_dsn(self):
msg, text = self._msgobj('msg_16.txt')
self._idempotent(msg, text)
def test_preamble_epilogue(self):
msg, text = self._msgobj('msg_21.txt')
self._idempotent(msg, text)
def test_multipart_one_part(self):
msg, text = self._msgobj('msg_23.txt')
self._idempotent(msg, text)
def test_multipart_no_parts(self):
msg, text = self._msgobj('msg_24.txt')
self._idempotent(msg, text)
def test_no_start_boundary(self):
msg, text = self._msgobj('msg_31.txt')
self._idempotent(msg, text)
def test_rfc2231_charset(self):
msg, text = self._msgobj('msg_32.txt')
self._idempotent(msg, text)
def test_more_rfc2231_parameters(self):
msg, text = self._msgobj('msg_33.txt')
self._idempotent(msg, text)
def test_text_plain_in_a_multipart_digest(self):
msg, text = self._msgobj('msg_34.txt')
self._idempotent(msg, text)
def test_nested_multipart_mixeds(self):
msg, text = self._msgobj('msg_12a.txt')
self._idempotent(msg, text)
def test_message_external_body_idempotent(self):
msg, text = self._msgobj('msg_36.txt')
self._idempotent(msg, text)
def test_content_type(self):
eq = self.assertEqual
unless = self.assertTrue
# Get a message object and reset the seek pointer for other tests
msg, text = self._msgobj('msg_05.txt')
eq(msg.get_content_type(), 'multipart/report')
# Test the Content-Type: parameters
params = {}
for pk, pv in msg.get_params():
params[pk] = pv
eq(params['report-type'], 'delivery-status')
eq(params['boundary'], 'D1690A7AC1.996856090/mail.example.com')
eq(msg.preamble, 'This is a MIME-encapsulated message.\n')
eq(msg.epilogue, '\n')
eq(len(msg.get_payload()), 3)
# Make sure the subparts are what we expect
msg1 = msg.get_payload(0)
eq(msg1.get_content_type(), 'text/plain')
eq(msg1.get_payload(), 'Yadda yadda yadda\n')
msg2 = msg.get_payload(1)
eq(msg2.get_content_type(), 'text/plain')
eq(msg2.get_payload(), 'Yadda yadda yadda\n')
msg3 = msg.get_payload(2)
eq(msg3.get_content_type(), 'message/rfc822')
self.assertTrue(isinstance(msg3, Message))
payload = msg3.get_payload()
unless(isinstance(payload, list))
eq(len(payload), 1)
msg4 = payload[0]
unless(isinstance(msg4, Message))
eq(msg4.get_payload(), 'Yadda yadda yadda\n')
def test_parser(self):
eq = self.assertEqual
unless = self.assertTrue
msg, text = self._msgobj('msg_06.txt')
# Check some of the outer headers
eq(msg.get_content_type(), 'message/rfc822')
# Make sure the payload is a list of exactly one sub-Message, and that
# that submessage has a type of text/plain
payload = msg.get_payload()
unless(isinstance(payload, list))
eq(len(payload), 1)
msg1 = payload[0]
self.assertTrue(isinstance(msg1, Message))
eq(msg1.get_content_type(), 'text/plain')
self.assertTrue(isinstance(msg1.get_payload(), str))
eq(msg1.get_payload(), '\n')
# Test various other bits of the package's functionality
class TestMiscellaneous(TestEmailBase):
def test_message_from_string(self):
fp = openfile('msg_01.txt')
try:
text = fp.read()
finally:
fp.close()
msg = email.message_from_string(text)
s = StringIO()
# Don't wrap/continue long headers since we're trying to test
# idempotency.
g = Generator(s, maxheaderlen=0)
g.flatten(msg)
self.assertEqual(text, s.getvalue())
def test_message_from_file(self):
fp = openfile('msg_01.txt')
try:
text = fp.read()
fp.seek(0)
msg = email.message_from_file(fp)
s = StringIO()
# Don't wrap/continue long headers since we're trying to test
# idempotency.
g = Generator(s, maxheaderlen=0)
g.flatten(msg)
self.assertEqual(text, s.getvalue())
finally:
fp.close()
def test_message_from_string_with_class(self):
unless = self.assertTrue
fp = openfile('msg_01.txt')
try:
text = fp.read()
finally:
fp.close()
# Create a subclass
class MyMessage(Message):
pass
msg = email.message_from_string(text, MyMessage)
unless(isinstance(msg, MyMessage))
# Try something more complicated
fp = openfile('msg_02.txt')
try:
text = fp.read()
finally:
fp.close()
msg = email.message_from_string(text, MyMessage)
for subpart in msg.walk():
unless(isinstance(subpart, MyMessage))
def test_message_from_file_with_class(self):
unless = self.assertTrue
# Create a subclass
class MyMessage(Message):
pass
fp = openfile('msg_01.txt')
try:
msg = email.message_from_file(fp, MyMessage)
finally:
fp.close()
unless(isinstance(msg, MyMessage))
# Try something more complicated
fp = openfile('msg_02.txt')
try:
msg = email.message_from_file(fp, MyMessage)
finally:
fp.close()
for subpart in msg.walk():
unless(isinstance(subpart, MyMessage))
def test__all__(self):
module = __import__('email')
all = module.__all__
all.sort()
self.assertEqual(all, [
# Old names
'Charset', 'Encoders', 'Errors', 'Generator',
'Header', 'Iterators', 'MIMEAudio', 'MIMEBase',
'MIMEImage', 'MIMEMessage', 'MIMEMultipart',
'MIMENonMultipart', 'MIMEText', 'Message',
'Parser', 'Utils', 'base64MIME',
# new names
'base64mime', 'charset', 'encoders', 'errors', 'generator',
'header', 'iterators', 'message', 'message_from_file',
'message_from_string', 'mime', 'parser',
'quopriMIME', 'quoprimime', 'utils',
])
def test_formatdate(self):
now = time.time()
self.assertEqual(Utils.parsedate(Utils.formatdate(now))[:6],
time.gmtime(now)[:6])
def test_formatdate_localtime(self):
now = time.time()
self.assertEqual(
Utils.parsedate(Utils.formatdate(now, localtime=True))[:6],
time.localtime(now)[:6])
def test_formatdate_usegmt(self):
now = time.time()
self.assertEqual(
Utils.formatdate(now, localtime=False),
time.strftime('%a, %d %b %Y %H:%M:%S -0000', time.gmtime(now)))
self.assertEqual(
Utils.formatdate(now, localtime=False, usegmt=True),
time.strftime('%a, %d %b %Y %H:%M:%S GMT', time.gmtime(now)))
def test_parsedate_none(self):
self.assertEqual(Utils.parsedate(''), None)
def test_parsedate_compact(self):
# The FWS after the comma is optional
self.assertEqual(Utils.parsedate('Wed,3 Apr 2002 14:58:26 +0800'),
Utils.parsedate('Wed, 3 Apr 2002 14:58:26 +0800'))
def test_parsedate_no_dayofweek(self):
eq = self.assertEqual
eq(Utils.parsedate_tz('25 Feb 2003 13:47:26 -0800'),
(2003, 2, 25, 13, 47, 26, 0, 1, -1, -28800))
def test_parsedate_compact_no_dayofweek(self):
eq = self.assertEqual
eq(Utils.parsedate_tz('5 Feb 2003 13:47:26 -0800'),
(2003, 2, 5, 13, 47, 26, 0, 1, -1, -28800))
def test_parsedate_acceptable_to_time_functions(self):
eq = self.assertEqual
timetup = Utils.parsedate('5 Feb 2003 13:47:26 -0800')
t = int(time.mktime(timetup))
eq(time.localtime(t)[:6], timetup[:6])
eq(int(time.strftime('%Y', timetup)), 2003)
timetup = Utils.parsedate_tz('5 Feb 2003 13:47:26 -0800')
t = int(time.mktime(timetup[:9]))
eq(time.localtime(t)[:6], timetup[:6])
eq(int(time.strftime('%Y', timetup[:9])), 2003)
def test_mktime_tz(self):
self.assertEqual(Utils.mktime_tz((1970, 1, 1, 0, 0, 0,
-1, -1, -1, 0)), 0)
self.assertEqual(Utils.mktime_tz((1970, 1, 1, 0, 0, 0,
-1, -1, -1, 1234)), -1234)
def test_parsedate_y2k(self):
"""Test for parsing a date with a two-digit year.
Parsing a date with a two-digit year should return the correct
four-digit year. RFC822 allows two-digit years, but RFC2822 (which
obsoletes RFC822) requires four-digit years.
"""
self.assertEqual(Utils.parsedate_tz('25 Feb 03 13:47:26 -0800'),
Utils.parsedate_tz('25 Feb 2003 13:47:26 -0800'))
self.assertEqual(Utils.parsedate_tz('25 Feb 71 13:47:26 -0800'),
Utils.parsedate_tz('25 Feb 1971 13:47:26 -0800'))
def test_parseaddr_empty(self):
self.assertEqual(Utils.parseaddr('<>'), ('', ''))
self.assertEqual(Utils.formataddr(Utils.parseaddr('<>')), '')
def test_noquote_dump(self):
self.assertEqual(
Utils.formataddr(('A Silly Person', '[email protected]')),
'A Silly Person ')
def test_escape_dump(self):
self.assertEqual(
Utils.formataddr(('A (Very) Silly Person', '[email protected]')),
r'"A \(Very\) Silly Person" ')
a = r'A \(Special\) Person'
b = '[email protected]'
self.assertEqual(Utils.parseaddr(Utils.formataddr((a, b))), (a, b))
def test_escape_backslashes(self):
self.assertEqual(
Utils.formataddr(('Arthur \Backslash\ Foobar', '[email protected]')),
r'"Arthur \\Backslash\\ Foobar" ')
a = r'Arthur \Backslash\ Foobar'
b = '[email protected]'
self.assertEqual(Utils.parseaddr(Utils.formataddr((a, b))), (a, b))
def test_name_with_dot(self):
x = 'John X. Doe '
y = '"John X. Doe" '
a, b = ('John X. Doe', '[email protected]')
self.assertEqual(Utils.parseaddr(x), (a, b))
self.assertEqual(Utils.parseaddr(y), (a, b))
# formataddr() quotes the name if there's a dot in it
self.assertEqual(Utils.formataddr((a, b)), y)
def test_parseaddr_preserves_quoted_pairs_in_addresses(self):
# issue 10005. Note that in the third test the second pair of
# backslashes is not actually a quoted pair because it is not inside a
# comment or quoted string: the address being parsed has a quoted
# string containing a quoted backslash, followed by 'example' and two
# backslashes, followed by another quoted string containing a space and
# the word 'example'. parseaddr copies those two backslashes
# literally. Per rfc5322 this is not technically correct since a \ may
# not appear in an address outside of a quoted string. It is probably
# a sensible Postel interpretation, though.
eq = self.assertEqual
eq(Utils.parseaddr('""example" example"@example.com'),
('', '""example" example"@example.com'))
eq(Utils.parseaddr('"\\"example\\" example"@example.com'),
('', '"\\"example\\" example"@example.com'))
eq(Utils.parseaddr('"\\\\"example\\\\" example"@example.com'),
('', '"\\\\"example\\\\" example"@example.com'))
def test_multiline_from_comment(self):
x = """\
Foo
\tBar """
self.assertEqual(Utils.parseaddr(x), ('Foo Bar', '[email protected]'))
def test_quote_dump(self):
self.assertEqual(
Utils.formataddr(('A Silly; Person', '[email protected]')),
r'"A Silly; Person" ')
def test_fix_eols(self):
eq = self.assertEqual
eq(Utils.fix_eols('hello'), 'hello')
eq(Utils.fix_eols('hello\n'), 'hello\r\n')
eq(Utils.fix_eols('hello\r'), 'hello\r\n')
eq(Utils.fix_eols('hello\r\n'), 'hello\r\n')
eq(Utils.fix_eols('hello\n\r'), 'hello\r\n\r\n')
def test_charset_richcomparisons(self):
eq = self.assertEqual
ne = self.assertNotEqual
cset1 = Charset()
cset2 = Charset()
eq(cset1, 'us-ascii')
eq(cset1, 'US-ASCII')
eq(cset1, 'Us-AsCiI')
eq('us-ascii', cset1)
eq('US-ASCII', cset1)
eq('Us-AsCiI', cset1)
ne(cset1, 'usascii')
ne(cset1, 'USASCII')
ne(cset1, 'UsAsCiI')
ne('usascii', cset1)
ne('USASCII', cset1)
ne('UsAsCiI', cset1)
eq(cset1, cset2)
eq(cset2, cset1)
def test_getaddresses(self):
eq = self.assertEqual
eq(Utils.getaddresses(['[email protected] (Al Person)',
'Bud Person ']),
[('Al Person', '[email protected]'),
('Bud Person', '[email protected]')])
def test_getaddresses_nasty(self):
eq = self.assertEqual
eq(Utils.getaddresses(['foo: ;']), [('', '')])
eq(Utils.getaddresses(
['[]*-- =~$']),
[('', ''), ('', ''), ('', '*--')])
eq(Utils.getaddresses(
['foo: ;', '"Jason R. Mastaler" ']),
[('', ''), ('Jason R. Mastaler', '[email protected]')])
def test_getaddresses_embedded_comment(self):
"""Test proper handling of a nested comment"""
eq = self.assertEqual
addrs = Utils.getaddresses(['User ((nested comment)) '])
eq(addrs[0][1], '[email protected]')
def test_utils_quote_unquote(self):
eq = self.assertEqual
msg = Message()
msg.add_header('content-disposition', 'attachment',
filename='foo\\wacky"name')
eq(msg.get_filename(), 'foo\\wacky"name')
def test_get_body_encoding_with_bogus_charset(self):
charset = Charset('not a charset')
self.assertEqual(charset.get_body_encoding(), 'base64')
def test_get_body_encoding_with_uppercase_charset(self):
eq = self.assertEqual
msg = Message()
msg['Content-Type'] = 'text/plain; charset=UTF-8'
eq(msg['content-type'], 'text/plain; charset=UTF-8')
charsets = msg.get_charsets()
eq(len(charsets), 1)
eq(charsets[0], 'utf-8')
charset = Charset(charsets[0])
eq(charset.get_body_encoding(), 'base64')
msg.set_payload('hello world', charset=charset)
eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n')
eq(msg.get_payload(decode=True), 'hello world')
eq(msg['content-transfer-encoding'], 'base64')
# Try another one
msg = Message()
msg['Content-Type'] = 'text/plain; charset="US-ASCII"'
charsets = msg.get_charsets()
eq(len(charsets), 1)
eq(charsets[0], 'us-ascii')
charset = Charset(charsets[0])
eq(charset.get_body_encoding(), Encoders.encode_7or8bit)
msg.set_payload('hello world', charset=charset)
eq(msg.get_payload(), 'hello world')
eq(msg['content-transfer-encoding'], '7bit')
def test_charsets_case_insensitive(self):
lc = Charset('us-ascii')
uc = Charset('US-ASCII')
self.assertEqual(lc.get_body_encoding(), uc.get_body_encoding())
def test_partial_falls_inside_message_delivery_status(self):
eq = self.ndiffAssertEqual
# The Parser interface provides chunks of data to FeedParser in 8192
# byte gulps. SF bug #1076485 found one of those chunks inside
# message/delivery-status header block, which triggered an
# unreadline() of NeedMoreData.
msg = self._msgobj('msg_43.txt')
sfp = StringIO()
Iterators._structure(msg, sfp)
eq(sfp.getvalue(), """\
multipart/report
text/plain
message/delivery-status
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/plain
text/rfc822-headers
""")
# Test the iterator/generators
class TestIterators(TestEmailBase):
def test_body_line_iterator(self):
eq = self.assertEqual
neq = self.ndiffAssertEqual
# First a simple non-multipart message
msg = self._msgobj('msg_01.txt')
it = Iterators.body_line_iterator(msg)
lines = list(it)
eq(len(lines), 6)
neq(EMPTYSTRING.join(lines), msg.get_payload())
# Now a more complicated multipart
msg = self._msgobj('msg_02.txt')
it = Iterators.body_line_iterator(msg)
lines = list(it)
eq(len(lines), 43)
fp = openfile('msg_19.txt')
try:
neq(EMPTYSTRING.join(lines), fp.read())
finally:
fp.close()
def test_typed_subpart_iterator(self):
eq = self.assertEqual
msg = self._msgobj('msg_04.txt')
it = Iterators.typed_subpart_iterator(msg, 'text')
lines = []
subparts = 0
for subpart in it:
subparts += 1
lines.append(subpart.get_payload())
eq(subparts, 2)
eq(EMPTYSTRING.join(lines), """\
a simple kind of mirror
to reflect upon our own
a simple kind of mirror
to reflect upon our own
""")
def test_typed_subpart_iterator_default_type(self):
eq = self.assertEqual
msg = self._msgobj('msg_03.txt')
it = Iterators.typed_subpart_iterator(msg, 'text', 'plain')
lines = []
subparts = 0
for subpart in it:
subparts += 1
lines.append(subpart.get_payload())
eq(subparts, 1)
eq(EMPTYSTRING.join(lines), """\
Hi,
Do you like this message?
-Me
""")
def test_pushCR_LF(self):
'''FeedParser BufferedSubFile.push() assumed it received complete
line endings. A CR ending one push() followed by a LF starting
the next push() added an empty line.
'''
imt = [
("a\r \n", 2),
("b", 0),
("c\n", 1),
("", 0),
("d\r\n", 1),
("e\r", 0),
("\nf", 1),
("\r\n", 1),
]
from email.feedparser import BufferedSubFile, NeedMoreData
bsf = BufferedSubFile()
om = []
nt = 0
for il, n in imt:
bsf.push(il)
nt += n
n1 = 0
while True:
ol = bsf.readline()
if ol == NeedMoreData:
break
om.append(ol)
n1 += 1
self.assertTrue(n == n1)
self.assertTrue(len(om) == nt)
self.assertTrue(''.join([il for il, n in imt]) == ''.join(om))
class TestParsers(TestEmailBase):
def test_header_parser(self):
eq = self.assertEqual
# Parse only the headers of a complex multipart MIME document
fp = openfile('msg_02.txt')
try:
msg = HeaderParser().parse(fp)
finally:
fp.close()
eq(msg['from'], '[email protected]')
eq(msg['to'], '[email protected]')
eq(msg.get_content_type(), 'multipart/mixed')
self.assertFalse(msg.is_multipart())
self.assertTrue(isinstance(msg.get_payload(), str))
def test_whitespace_continuation(self):
eq = self.assertEqual
# This message contains a line after the Subject: header that has only
# whitespace, but it is not empty!
msg = email.message_from_string("""\
From: [email protected]
To: [email protected]
Subject: the next line has a space on it
\x20
Date: Mon, 8 Apr 2002 15:09:19 -0400
Message-ID: spam
Here's the message body
""")
eq(msg['subject'], 'the next line has a space on it\n ')
eq(msg['message-id'], 'spam')
eq(msg.get_payload(), "Here's the message body\n")
def test_whitespace_continuation_last_header(self):
eq = self.assertEqual
# Like the previous test, but the subject line is the last
# header.
msg = email.message_from_string("""\
From: [email protected]
To: [email protected]
Date: Mon, 8 Apr 2002 15:09:19 -0400
Message-ID: spam
Subject: the next line has a space on it
\x20
Here's the message body
""")
eq(msg['subject'], 'the next line has a space on it\n ')
eq(msg['message-id'], 'spam')
eq(msg.get_payload(), "Here's the message body\n")
def test_crlf_separation(self):
eq = self.assertEqual
fp = openfile('msg_26.txt', mode='rb')
try:
msg = Parser().parse(fp)
finally:
fp.close()
eq(len(msg.get_payload()), 2)
part1 = msg.get_payload(0)
eq(part1.get_content_type(), 'text/plain')
eq(part1.get_payload(), 'Simple email with attachment.\r\n\r\n')
part2 = msg.get_payload(1)
eq(part2.get_content_type(), 'application/riscos')
def test_multipart_digest_with_extra_mime_headers(self):
eq = self.assertEqual
neq = self.ndiffAssertEqual
fp = openfile('msg_28.txt')
try:
msg = email.message_from_file(fp)
finally:
fp.close()
# Structure is:
# multipart/digest
# message/rfc822
# text/plain
# message/rfc822
# text/plain
eq(msg.is_multipart(), 1)
eq(len(msg.get_payload()), 2)
part1 = msg.get_payload(0)
eq(part1.get_content_type(), 'message/rfc822')
eq(part1.is_multipart(), 1)
eq(len(part1.get_payload()), 1)
part1a = part1.get_payload(0)
eq(part1a.is_multipart(), 0)
eq(part1a.get_content_type(), 'text/plain')
neq(part1a.get_payload(), 'message 1\n')
# next message/rfc822
part2 = msg.get_payload(1)
eq(part2.get_content_type(), 'message/rfc822')
eq(part2.is_multipart(), 1)
eq(len(part2.get_payload()), 1)
part2a = part2.get_payload(0)
eq(part2a.is_multipart(), 0)
eq(part2a.get_content_type(), 'text/plain')
neq(part2a.get_payload(), 'message 2\n')
def test_three_lines(self):
# A bug report by Andrew McNamara
lines = ['From: Andrew Person From', 'From'])
eq(msg.get_payload(), 'body')
def test_rfc2822_space_not_allowed_in_header(self):
eq = self.assertEqual
m = '>From [email protected] 11:25:53\nFrom: bar\n!"#QUX;~: zoo\n\nbody'
msg = email.message_from_string(m)
eq(len(msg.keys()), 0)
def test_rfc2822_one_character_header(self):
eq = self.assertEqual
m = 'A: first header\nB: second header\nCC: third header\n\nbody'
msg = email.message_from_string(m)
headers = msg.keys()
headers.sort()
eq(headers, ['A', 'B', 'CC'])
eq(msg.get_payload(), 'body')
def test_CRLFLF_at_end_of_part(self):
# issue 5610: feedparser should not eat two chars from body part ending
# with "\r\n\n".
m = (
"From: [email protected]\n"
"To: baz\n"
"Mime-Version: 1.0\n"
"Content-Type: multipart/mixed; boundary=BOUNDARY\n"
"\n"
"--BOUNDARY\n"
"Content-Type: text/plain\n"
"\n"
"body ending with CRLF newline\r\n"
"\n"
"--BOUNDARY--\n"
)
msg = email.message_from_string(m)
self.assertTrue(msg.get_payload(0).get_payload().endswith('\r\n'))
class TestBase64(unittest.TestCase):
def test_len(self):
eq = self.assertEqual
eq(base64MIME.base64_len('hello'),
len(base64MIME.encode('hello', eol='')))
for size in range(15):
if size == 0 : bsize = 0
elif size <= 3 : bsize = 4
elif size <= 6 : bsize = 8
elif size <= 9 : bsize = 12
elif size <= 12: bsize = 16
else : bsize = 20
eq(base64MIME.base64_len('x'*size), bsize)
def test_decode(self):
eq = self.assertEqual
eq(base64MIME.decode(''), '')
eq(base64MIME.decode('aGVsbG8='), 'hello')
eq(base64MIME.decode('aGVsbG8=', 'X'), 'hello')
eq(base64MIME.decode('aGVsbG8NCndvcmxk\n', 'X'), 'helloXworld')
def test_encode(self):
eq = self.assertEqual
eq(base64MIME.encode(''), '')
eq(base64MIME.encode('hello'), 'aGVsbG8=\n')
# Test the binary flag
eq(base64MIME.encode('hello\n'), 'aGVsbG8K\n')
eq(base64MIME.encode('hello\n', 0), 'aGVsbG8NCg==\n')
# Test the maxlinelen arg
eq(base64MIME.encode('xxxx ' * 20, maxlinelen=40), """\
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg
eHh4eCB4eHh4IA==
""")
# Test the eol argument
eq(base64MIME.encode('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg\r
eHh4eCB4eHh4IA==\r
""")
def test_header_encode(self):
eq = self.assertEqual
he = base64MIME.header_encode
eq(he('hello'), '=?iso-8859-1?b?aGVsbG8=?=')
eq(he('hello\nworld'), '=?iso-8859-1?b?aGVsbG8NCndvcmxk?=')
# Test the charset option
eq(he('hello', charset='iso-8859-2'), '=?iso-8859-2?b?aGVsbG8=?=')
# Test the keep_eols flag
eq(he('hello\nworld', keep_eols=True),
'=?iso-8859-1?b?aGVsbG8Kd29ybGQ=?=')
# Test the maxlinelen argument
eq(he('xxxx ' * 20, maxlinelen=40), """\
=?iso-8859-1?b?eHh4eCB4eHh4IHh4eHggeHg=?=
=?iso-8859-1?b?eHggeHh4eCB4eHh4IHh4eHg=?=
=?iso-8859-1?b?IHh4eHggeHh4eCB4eHh4IHg=?=
=?iso-8859-1?b?eHh4IHh4eHggeHh4eCB4eHg=?=
=?iso-8859-1?b?eCB4eHh4IHh4eHggeHh4eCA=?=
=?iso-8859-1?b?eHh4eCB4eHh4IHh4eHgg?=""")
# Test the eol argument
eq(he('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\
=?iso-8859-1?b?eHh4eCB4eHh4IHh4eHggeHg=?=\r
=?iso-8859-1?b?eHggeHh4eCB4eHh4IHh4eHg=?=\r
=?iso-8859-1?b?IHh4eHggeHh4eCB4eHh4IHg=?=\r
=?iso-8859-1?b?eHh4IHh4eHggeHh4eCB4eHg=?=\r
=?iso-8859-1?b?eCB4eHh4IHh4eHggeHh4eCA=?=\r
=?iso-8859-1?b?eHh4eCB4eHh4IHh4eHgg?=""")
class TestQuopri(unittest.TestCase):
def setUp(self):
self.hlit = [chr(x) for x in range(ord('a'), ord('z')+1)] + \
[chr(x) for x in range(ord('A'), ord('Z')+1)] + \
[chr(x) for x in range(ord('0'), ord('9')+1)] + \
['!', '*', '+', '-', '/', ' ']
self.hnon = [chr(x) for x in range(256) if chr(x) not in self.hlit]
assert len(self.hlit) + len(self.hnon) == 256
self.blit = [chr(x) for x in range(ord(' '), ord('~')+1)] + ['\t']
self.blit.remove('=')
self.bnon = [chr(x) for x in range(256) if chr(x) not in self.blit]
assert len(self.blit) + len(self.bnon) == 256
def test_header_quopri_check(self):
for c in self.hlit:
self.assertFalse(quopriMIME.header_quopri_check(c))
for c in self.hnon:
self.assertTrue(quopriMIME.header_quopri_check(c))
def test_body_quopri_check(self):
for c in self.blit:
self.assertFalse(quopriMIME.body_quopri_check(c))
for c in self.bnon:
self.assertTrue(quopriMIME.body_quopri_check(c))
def test_header_quopri_len(self):
eq = self.assertEqual
hql = quopriMIME.header_quopri_len
enc = quopriMIME.header_encode
for s in ('hello', 'h@e@l@l@o@'):
# Empty charset and no line-endings. 7 == RFC chrome
eq(hql(s), len(enc(s, charset='', eol=''))-7)
for c in self.hlit:
eq(hql(c), 1)
for c in self.hnon:
eq(hql(c), 3)
def test_body_quopri_len(self):
eq = self.assertEqual
bql = quopriMIME.body_quopri_len
for c in self.blit:
eq(bql(c), 1)
for c in self.bnon:
eq(bql(c), 3)
def test_quote_unquote_idempotent(self):
for x in range(256):
c = chr(x)
self.assertEqual(quopriMIME.unquote(quopriMIME.quote(c)), c)
def test_header_encode(self):
eq = self.assertEqual
he = quopriMIME.header_encode
eq(he('hello'), '=?iso-8859-1?q?hello?=')
eq(he('hello\nworld'), '=?iso-8859-1?q?hello=0D=0Aworld?=')
# Test the charset option
eq(he('hello', charset='iso-8859-2'), '=?iso-8859-2?q?hello?=')
# Test the keep_eols flag
eq(he('hello\nworld', keep_eols=True), '=?iso-8859-1?q?hello=0Aworld?=')
# Test a non-ASCII character
eq(he('hello\xc7there'), '=?iso-8859-1?q?hello=C7there?=')
# Test the maxlinelen argument
eq(he('xxxx ' * 20, maxlinelen=40), """\
=?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xx?=
=?iso-8859-1?q?xx_xxxx_xxxx_xxxx_xxxx?=
=?iso-8859-1?q?_xxxx_xxxx_xxxx_xxxx_x?=
=?iso-8859-1?q?xxx_xxxx_xxxx_xxxx_xxx?=
=?iso-8859-1?q?x_xxxx_xxxx_?=""")
# Test the eol argument
eq(he('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\
=?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xx?=\r
=?iso-8859-1?q?xx_xxxx_xxxx_xxxx_xxxx?=\r
=?iso-8859-1?q?_xxxx_xxxx_xxxx_xxxx_x?=\r
=?iso-8859-1?q?xxx_xxxx_xxxx_xxxx_xxx?=\r
=?iso-8859-1?q?x_xxxx_xxxx_?=""")
def test_decode(self):
eq = self.assertEqual
eq(quopriMIME.decode(''), '')
eq(quopriMIME.decode('hello'), 'hello')
eq(quopriMIME.decode('hello', 'X'), 'hello')
eq(quopriMIME.decode('hello\nworld', 'X'), 'helloXworld')
def test_encode(self):
eq = self.assertEqual
eq(quopriMIME.encode(''), '')
eq(quopriMIME.encode('hello'), 'hello')
# Test the binary flag
eq(quopriMIME.encode('hello\r\nworld'), 'hello\nworld')
eq(quopriMIME.encode('hello\r\nworld', 0), 'hello\nworld')
# Test the maxlinelen arg
eq(quopriMIME.encode('xxxx ' * 20, maxlinelen=40), """\
xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx=
xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx=
x xxxx xxxx xxxx xxxx=20""")
# Test the eol argument
eq(quopriMIME.encode('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\
xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx=\r
xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx=\r
x xxxx xxxx xxxx xxxx=20""")
eq(quopriMIME.encode("""\
one line
two line"""), """\
one line
two line""")
# Test the Charset class
class TestCharset(unittest.TestCase):
def tearDown(self):
from email import Charset as CharsetModule
try:
del CharsetModule.CHARSETS['fake']
except KeyError:
pass
def test_idempotent(self):
eq = self.assertEqual
# Make sure us-ascii = no Unicode conversion
c = Charset('us-ascii')
s = 'Hello World!'
sp = c.to_splittable(s)
eq(s, c.from_splittable(sp))
# test 8-bit idempotency with us-ascii
s = '\xa4\xa2\xa4\xa4\xa4\xa6\xa4\xa8\xa4\xaa'
sp = c.to_splittable(s)
eq(s, c.from_splittable(sp))
def test_body_encode(self):
eq = self.assertEqual
# Try a charset with QP body encoding
c = Charset('iso-8859-1')
eq('hello w=F6rld', c.body_encode('hello w\xf6rld'))
# Try a charset with Base64 body encoding
c = Charset('utf-8')
eq('aGVsbG8gd29ybGQ=\n', c.body_encode('hello world'))
# Try a charset with None body encoding
c = Charset('us-ascii')
eq('hello world', c.body_encode('hello world'))
# Try the convert argument, where input codec != output codec
c = Charset('euc-jp')
# With apologies to Tokio Kikuchi ;)
if not is_jython:
# TODO Jython with its Java-based codecs does not
# currently support trailing bytes in CJK texts
try:
eq('\x1b$B5FCO;~IW\x1b(B',
c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7'))
eq('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7',
c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7', False))
except LookupError:
# We probably don't have the Japanese codecs installed
pass
# Testing SF bug #625509, which we have to fake, since there are no
# built-in encodings where the header encoding is QP but the body
# encoding is not.
from email import Charset as CharsetModule
CharsetModule.add_charset('fake', CharsetModule.QP, None)
c = Charset('fake')
eq('hello w\xf6rld', c.body_encode('hello w\xf6rld'))
def test_unicode_charset_name(self):
charset = Charset(u'us-ascii')
self.assertEqual(str(charset), 'us-ascii')
self.assertRaises(Errors.CharsetError, Charset, 'asc\xffii')
def test_codecs_aliases_accepted(self):
charset = Charset('utf8')
self.assertEqual(str(charset), 'utf-8')
# Test multilingual MIME headers.
class TestHeader(TestEmailBase):
def test_simple(self):
eq = self.ndiffAssertEqual
h = Header('Hello World!')
eq(h.encode(), 'Hello World!')
h.append(' Goodbye World!')
eq(h.encode(), 'Hello World! Goodbye World!')
def test_simple_surprise(self):
eq = self.ndiffAssertEqual
h = Header('Hello World!')
eq(h.encode(), 'Hello World!')
h.append('Goodbye World!')
eq(h.encode(), 'Hello World! Goodbye World!')
def test_header_needs_no_decoding(self):
h = 'no decoding needed'
self.assertEqual(decode_header(h), [(h, None)])
def test_long(self):
h = Header("I am the very model of a modern Major-General; I've information vegetable, animal, and mineral; I know the kings of England, and I quote the fights historical from Marathon to Waterloo, in order categorical; I'm very well acquainted, too, with matters mathematical; I understand equations, both the simple and quadratical; about binomial theorem I'm teeming with a lot o' news, with many cheerful facts about the square of the hypotenuse.",
maxlinelen=76)
for l in h.encode(splitchars=' ').split('\n '):
self.assertTrue(len(l) <= 76)
def test_multilingual(self):
eq = self.ndiffAssertEqual
g = Charset("iso-8859-1")
cz = Charset("iso-8859-2")
utf8 = Charset("utf-8")
g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
h = Header(g_head, g)
h.append(cz_head, cz)
h.append(utf8_head, utf8)
enc = h.encode()
eq(enc, """\
=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerderband_ko?=
=?iso-8859-1?q?mfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndischen_Wan?=
=?iso-8859-1?q?dgem=E4lden_vorbei=2C_gegen_die_rotierenden_Klingen_bef=F6?=
=?iso-8859-1?q?rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se_hroutily?=
=?iso-8859-2?q?_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= =?utf-8?b?5q2j56K6?=
=?utf-8?b?44Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE44G+44Gb44KT44CC?=
=?utf-8?b?5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB44GC44Go44Gv44Gn?=
=?utf-8?b?44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CMV2VubiBpc3QgZGFz?=
=?utf-8?q?_Nunstuck_git_und_Slotermeyer=3F_Ja!_Beiherhund_das_Oder_die_Fl?=
=?utf-8?b?aXBwZXJ3YWxkdCBnZXJzcHV0LuOAjeOBqOiogOOBo+OBpuOBhOOBvuOBmQ==?=
=?utf-8?b?44CC?=""")
eq(decode_header(enc),
[(g_head, "iso-8859-1"), (cz_head, "iso-8859-2"),
(utf8_head, "utf-8")])
ustr = unicode(h)
eq(ustr.encode('utf-8'),
'Die Mieter treten hier ein werden mit einem Foerderband '
'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen '
'Wandgem\xc3\xa4lden vorbei, gegen die rotierenden Klingen '
'bef\xc3\xb6rdert. Finan\xc4\x8dni metropole se hroutily pod '
'tlakem jejich d\xc5\xafvtipu.. \xe6\xad\xa3\xe7\xa2\xba\xe3\x81'
'\xab\xe8\xa8\x80\xe3\x81\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3'
'\xe3\x81\xaf\xe3\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3'
'\x81\xbe\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
'\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8\xaa\x9e'
'\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81\xe3\x81\x82\xe3'
'\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81\x9f\xe3\x82\x89\xe3\x82'
'\x81\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\xe5\xae\x9f\xe9\x9a\x9b'
'\xe3\x81\xab\xe3\x81\xaf\xe3\x80\x8cWenn ist das Nunstuck git '
'und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt '
'gersput.\xe3\x80\x8d\xe3\x81\xa8\xe8\xa8\x80\xe3\x81\xa3\xe3\x81'
'\xa6\xe3\x81\x84\xe3\x81\xbe\xe3\x81\x99\xe3\x80\x82')
# Test make_header()
newh = make_header(decode_header(enc))
eq(newh, enc)
def test_header_ctor_default_args(self):
eq = self.ndiffAssertEqual
h = Header()
eq(h, '')
h.append('foo', Charset('iso-8859-1'))
eq(h, '=?iso-8859-1?q?foo?=')
def test_explicit_maxlinelen(self):
eq = self.ndiffAssertEqual
hstr = 'A very long line that must get split to something other than at the 76th character boundary to test the non-default behavior'
h = Header(hstr)
eq(h.encode(), '''\
A very long line that must get split to something other than at the 76th
character boundary to test the non-default behavior''')
h = Header(hstr, header_name='Subject')
eq(h.encode(), '''\
A very long line that must get split to something other than at the
76th character boundary to test the non-default behavior''')
h = Header(hstr, maxlinelen=1024, header_name='Subject')
eq(h.encode(), hstr)
def test_us_ascii_header(self):
eq = self.assertEqual
s = 'hello'
x = decode_header(s)
eq(x, [('hello', None)])
h = make_header(x)
eq(s, h.encode())
def test_string_charset(self):
eq = self.assertEqual
h = Header()
h.append('hello', 'iso-8859-1')
eq(h, '=?iso-8859-1?q?hello?=')
## def test_unicode_error(self):
## raises = self.assertRaises
## raises(UnicodeError, Header, u'[P\xf6stal]', 'us-ascii')
## raises(UnicodeError, Header, '[P\xf6stal]', 'us-ascii')
## h = Header()
## raises(UnicodeError, h.append, u'[P\xf6stal]', 'us-ascii')
## raises(UnicodeError, h.append, '[P\xf6stal]', 'us-ascii')
## raises(UnicodeError, Header, u'\u83ca\u5730\u6642\u592b', 'iso-8859-1')
def test_utf8_shortest(self):
eq = self.assertEqual
h = Header(u'p\xf6stal', 'utf-8')
eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=')
h = Header(u'\u83ca\u5730\u6642\u592b', 'utf-8')
eq(h.encode(), '=?utf-8?b?6I+K5Zyw5pmC5aSr?=')
def test_bad_8bit_header(self):
raises = self.assertRaises
eq = self.assertEqual
x = 'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big'
raises(UnicodeError, Header, x)
h = Header()
raises(UnicodeError, h.append, x)
eq(str(Header(x, errors='replace')), x)
h.append(x, errors='replace')
eq(str(h), x)
def test_encoded_adjacent_nonencoded(self):
eq = self.assertEqual
h = Header()
h.append('hello', 'iso-8859-1')
h.append('world')
s = h.encode()
eq(s, '=?iso-8859-1?q?hello?= world')
h = make_header(decode_header(s))
eq(h.encode(), s)
def test_whitespace_eater(self):
eq = self.assertEqual
s = 'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztk=?= =?koi8-r?q?=CA?= zz.'
parts = decode_header(s)
eq(parts, [('Subject:', None), ('\xf0\xd2\xcf\xd7\xc5\xd2\xcb\xc1 \xce\xc1 \xc6\xc9\xce\xc1\xcc\xd8\xce\xd9\xca', 'koi8-r'), ('zz.', None)])
hdr = make_header(parts)
eq(hdr.encode(),
'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztnK?= zz.')
def test_broken_base64_header(self):
raises = self.assertRaises
s = 'Subject: =?EUC-KR?B?CSixpLDtKSC/7Liuvsax4iC6uLmwMcijIKHaILzSwd/H0SC8+LCjwLsgv7W/+Mj3I ?='
raises(Errors.HeaderParseError, decode_header, s)
# Issue 1078919
def test_ascii_add_header(self):
msg = Message()
msg.add_header('Content-Disposition', 'attachment',
filename='bud.gif')
self.assertEqual('attachment; filename="bud.gif"',
msg['Content-Disposition'])
def test_nonascii_add_header_via_triple(self):
msg = Message()
msg.add_header('Content-Disposition', 'attachment',
filename=('iso-8859-1', '', 'Fu\xdfballer.ppt'))
self.assertEqual(
'attachment; filename*="iso-8859-1\'\'Fu%DFballer.ppt"',
msg['Content-Disposition'])
def test_encode_unaliased_charset(self):
# Issue 1379416: when the charset has no output conversion,
# output was accidentally getting coerced to unicode.
res = Header('abc','iso-8859-2').encode()
self.assertEqual(res, '=?iso-8859-2?q?abc?=')
self.assertIsInstance(res, str)
# Test RFC 2231 header parameters (en/de)coding
class TestRFC2231(TestEmailBase):
def test_get_param(self):
eq = self.assertEqual
msg = self._msgobj('msg_29.txt')
eq(msg.get_param('title'),
('us-ascii', 'en', 'This is even more ***fun*** isn\'t it!'))
eq(msg.get_param('title', unquote=False),
('us-ascii', 'en', '"This is even more ***fun*** isn\'t it!"'))
def test_set_param(self):
eq = self.assertEqual
msg = Message()
msg.set_param('title', 'This is even more ***fun*** isn\'t it!',
charset='us-ascii')
eq(msg.get_param('title'),
('us-ascii', '', 'This is even more ***fun*** isn\'t it!'))
msg.set_param('title', 'This is even more ***fun*** isn\'t it!',
charset='us-ascii', language='en')
eq(msg.get_param('title'),
('us-ascii', 'en', 'This is even more ***fun*** isn\'t it!'))
msg = self._msgobj('msg_01.txt')
msg.set_param('title', 'This is even more ***fun*** isn\'t it!',
charset='us-ascii', language='en')
self.ndiffAssertEqual(msg.as_string(), """\
Return-Path:
Delivered-To: [email protected]
Received: by mail.zzz.org (Postfix, from userid 889)
id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT)
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Message-ID: <[email protected]>
From: [email protected] (John X. Doe)
To: [email protected]
Subject: This is a test message
Date: Fri, 4 May 2001 14:05:44 -0400
Content-Type: text/plain; charset=us-ascii;
title*="us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21"
Hi,
Do you like this message?
-Me
""")
def test_del_param(self):
eq = self.ndiffAssertEqual
msg = self._msgobj('msg_01.txt')
msg.set_param('foo', 'bar', charset='us-ascii', language='en')
msg.set_param('title', 'This is even more ***fun*** isn\'t it!',
charset='us-ascii', language='en')
msg.del_param('foo', header='Content-Type')
eq(msg.as_string(), """\
Return-Path:
Delivered-To: [email protected]
Received: by mail.zzz.org (Postfix, from userid 889)
id 27CEAD38CC; Fri, 4 May 2001 14:05:44 -0400 (EDT)
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Message-ID: <[email protected]>
From: [email protected] (John X. Doe)
To: [email protected]
Subject: This is a test message
Date: Fri, 4 May 2001 14:05:44 -0400
Content-Type: text/plain; charset="us-ascii";
title*="us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21"
Hi,
Do you like this message?
-Me
""")
def test_rfc2231_get_content_charset(self):
eq = self.assertEqual
msg = self._msgobj('msg_32.txt')
eq(msg.get_content_charset(), 'us-ascii')
def test_rfc2231_no_language_or_charset(self):
m = '''\
Content-Transfer-Encoding: 8bit
Content-Disposition: inline; filename="file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEMP_nsmail.htm"
Content-Type: text/html; NAME*0=file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEM; NAME*1=P_nsmail.htm
'''
msg = email.message_from_string(m)
param = msg.get_param('NAME')
self.assertFalse(isinstance(param, tuple))
self.assertEqual(
param,
'file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEMP_nsmail.htm')
def test_rfc2231_no_language_or_charset_in_filename(self):
m = '''\
Content-Disposition: inline;
\tfilename*0*="''This%20is%20even%20more%20";
\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2="is it not.pdf"
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_filename(),
'This is even more ***fun*** is it not.pdf')
def test_rfc2231_no_language_or_charset_in_filename_encoded(self):
m = '''\
Content-Disposition: inline;
\tfilename*0*="''This%20is%20even%20more%20";
\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2="is it not.pdf"
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_filename(),
'This is even more ***fun*** is it not.pdf')
def test_rfc2231_partly_encoded(self):
m = '''\
Content-Disposition: inline;
\tfilename*0="''This%20is%20even%20more%20";
\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2="is it not.pdf"
'''
msg = email.message_from_string(m)
self.assertEqual(
msg.get_filename(),
'This%20is%20even%20more%20***fun*** is it not.pdf')
def test_rfc2231_partly_nonencoded(self):
m = '''\
Content-Disposition: inline;
\tfilename*0="This%20is%20even%20more%20";
\tfilename*1="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2="is it not.pdf"
'''
msg = email.message_from_string(m)
self.assertEqual(
msg.get_filename(),
'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20is it not.pdf')
def test_rfc2231_no_language_or_charset_in_boundary(self):
m = '''\
Content-Type: multipart/alternative;
\tboundary*0*="''This%20is%20even%20more%20";
\tboundary*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tboundary*2="is it not.pdf"
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_boundary(),
'This is even more ***fun*** is it not.pdf')
def test_rfc2231_no_language_or_charset_in_charset(self):
# This is a nonsensical charset value, but tests the code anyway
m = '''\
Content-Type: text/plain;
\tcharset*0*="This%20is%20even%20more%20";
\tcharset*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tcharset*2="is it not.pdf"
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_content_charset(),
'this is even more ***fun*** is it not.pdf')
def test_rfc2231_bad_encoding_in_filename(self):
m = '''\
Content-Disposition: inline;
\tfilename*0*="bogus'xx'This%20is%20even%20more%20";
\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2="is it not.pdf"
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_filename(),
'This is even more ***fun*** is it not.pdf')
def test_rfc2231_bad_encoding_in_charset(self):
m = """\
Content-Type: text/plain; charset*=bogus''utf-8%E2%80%9D
"""
msg = email.message_from_string(m)
# This should return None because non-ascii characters in the charset
# are not allowed.
self.assertEqual(msg.get_content_charset(), None)
def test_rfc2231_bad_character_in_charset(self):
m = """\
Content-Type: text/plain; charset*=ascii''utf-8%E2%80%9D
"""
msg = email.message_from_string(m)
# This should return None because non-ascii characters in the charset
# are not allowed.
self.assertEqual(msg.get_content_charset(), None)
def test_rfc2231_bad_character_in_filename(self):
m = '''\
Content-Disposition: inline;
\tfilename*0*="ascii'xx'This%20is%20even%20more%20";
\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2*="is it not.pdf%E2"
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_filename(),
u'This is even more ***fun*** is it not.pdf\ufffd')
def test_rfc2231_unknown_encoding(self):
m = """\
Content-Transfer-Encoding: 8bit
Content-Disposition: inline; filename*=X-UNKNOWN''myfile.txt
"""
msg = email.message_from_string(m)
self.assertEqual(msg.get_filename(), 'myfile.txt')
def test_rfc2231_single_tick_in_filename_extended(self):
eq = self.assertEqual
m = """\
Content-Type: application/x-foo;
\tname*0*=\"Frank's\"; name*1*=\" Document\"
"""
msg = email.message_from_string(m)
charset, language, s = msg.get_param('name')
eq(charset, None)
eq(language, None)
eq(s, "Frank's Document")
def test_rfc2231_single_tick_in_filename(self):
m = """\
Content-Type: application/x-foo; name*0=\"Frank's\"; name*1=\" Document\"
"""
msg = email.message_from_string(m)
param = msg.get_param('name')
self.assertFalse(isinstance(param, tuple))
self.assertEqual(param, "Frank's Document")
def test_rfc2231_tick_attack_extended(self):
eq = self.assertEqual
m = """\
Content-Type: application/x-foo;
\tname*0*=\"us-ascii'en-us'Frank's\"; name*1*=\" Document\"
"""
msg = email.message_from_string(m)
charset, language, s = msg.get_param('name')
eq(charset, 'us-ascii')
eq(language, 'en-us')
eq(s, "Frank's Document")
def test_rfc2231_tick_attack(self):
m = """\
Content-Type: application/x-foo;
\tname*0=\"us-ascii'en-us'Frank's\"; name*1=\" Document\"
"""
msg = email.message_from_string(m)
param = msg.get_param('name')
self.assertFalse(isinstance(param, tuple))
self.assertEqual(param, "us-ascii'en-us'Frank's Document")
def test_rfc2231_no_extended_values(self):
eq = self.assertEqual
m = """\
Content-Type: application/x-foo; name=\"Frank's Document\"
"""
msg = email.message_from_string(m)
eq(msg.get_param('name'), "Frank's Document")
def test_rfc2231_encoded_then_unencoded_segments(self):
eq = self.assertEqual
m = """\
Content-Type: application/x-foo;
\tname*0*=\"us-ascii'en-us'My\";
\tname*1=\" Document\";
\tname*2*=\" For You\"
"""
msg = email.message_from_string(m)
charset, language, s = msg.get_param('name')
eq(charset, 'us-ascii')
eq(language, 'en-us')
eq(s, 'My Document For You')
def test_rfc2231_unencoded_then_encoded_segments(self):
eq = self.assertEqual
m = """\
Content-Type: application/x-foo;
\tname*0=\"us-ascii'en-us'My\";
\tname*1*=\" Document\";
\tname*2*=\" For You\"
"""
msg = email.message_from_string(m)
charset, language, s = msg.get_param('name')
eq(charset, 'us-ascii')
eq(language, 'en-us')
eq(s, 'My Document For You')
# Tests to ensure that signed parts of an email are completely preserved, as
# required by RFC1847 section 2.1. Note that these are incomplete, because the
# email package does not currently always preserve the body. See issue 1670765.
class TestSigned(TestEmailBase):
def _msg_and_obj(self, filename):
fp = openfile(findfile(filename))
try:
original = fp.read()
msg = email.message_from_string(original)
finally:
fp.close()
return original, msg
def _signed_parts_eq(self, original, result):
# Extract the first mime part of each message
import re
repart = re.compile(r'^--([^\n]+)\n(.*?)\n--\1$', re.S | re.M)
inpart = repart.search(original).group(2)
outpart = repart.search(result).group(2)
self.assertEqual(outpart, inpart)
def test_long_headers_as_string(self):
original, msg = self._msg_and_obj('msg_45.txt')
result = msg.as_string()
self._signed_parts_eq(original, result)
def test_long_headers_flatten(self):
original, msg = self._msg_and_obj('msg_45.txt')
fp = StringIO()
Generator(fp).flatten(msg)
result = fp.getvalue()
self._signed_parts_eq(original, result)
def _testclasses():
mod = sys.modules[__name__]
return [getattr(mod, name) for name in dir(mod) if name.startswith('Test')]
def suite():
suite = unittest.TestSuite()
for testclass in _testclasses():
suite.addTest(unittest.makeSuite(testclass))
return suite
def test_main():
for testclass in _testclasses():
run_unittest(testclass)
if __name__ == '__main__':
unittest.main(defaultTest='suite')