test_email.py

来自「mallet是自然语言处理、机器学习领域的一个开源项目。」· Python 代码 · 共 1,770 行 · 第 1/5 页

            ('report-type', old_val)])

    def test_set_type(self):
        eq = self.assertEqual
        msg = Message()
        self.assertRaises(ValueError, msg.set_type, 'text')
        msg.set_type('text/plain')
        eq(msg['content-type'], 'text/plain')
        msg.set_param('charset', 'us-ascii')
        eq(msg['content-type'], 'text/plain; charset="us-ascii"')
        msg.set_type('text/html')
        eq(msg['content-type'], 'text/html; charset="us-ascii"')

    def test_get_content_type_missing(self):
        msg = Message()
        self.assertEqual(msg.get_content_type(), 'text/plain')

    def test_get_content_type_missing_with_default_type(self):
        msg = Message()
        msg.set_default_type('message/rfc822')
        self.assertEqual(msg.get_content_type(), 'message/rfc822')

    def test_get_content_type_from_message_implicit(self):
        msg = self._msgobj('msg_30.txt')
        self.assertEqual(msg.get_payload(0).get_content_type(),
                         'message/rfc822')

    def test_get_content_type_from_message_explicit(self):
        msg = self._msgobj('msg_28.txt')
        self.assertEqual(msg.get_payload(0).get_content_type(),
                         'message/rfc822')

    def test_get_content_type_from_message_text_plain_implicit(self):
        msg = self._msgobj('msg_03.txt')
        self.assertEqual(msg.get_content_type(), 'text/plain')

    def test_get_content_type_from_message_text_plain_explicit(self):
        msg = self._msgobj('msg_01.txt')
        self.assertEqual(msg.get_content_type(), 'text/plain')

    def test_get_content_maintype_missing(self):
        msg = Message()
        self.assertEqual(msg.get_content_maintype(), 'text')

    def test_get_content_maintype_missing_with_default_type(self):
        msg = Message()
        msg.set_default_type('message/rfc822')
        self.assertEqual(msg.get_content_maintype(), 'message')

    def test_get_content_maintype_from_message_implicit(self):
        msg = self._msgobj('msg_30.txt')
        self.assertEqual(msg.get_payload(0).get_content_maintype(), 'message')

    def test_get_content_maintype_from_message_explicit(self):
        msg = self._msgobj('msg_28.txt')
        self.assertEqual(msg.get_payload(0).get_content_maintype(), 'message')

    def test_get_content_maintype_from_message_text_plain_implicit(self):
        msg = self._msgobj('msg_03.txt')
        self.assertEqual(msg.get_content_maintype(), 'text')

    def test_get_content_maintype_from_message_text_plain_explicit(self):
        msg = self._msgobj('msg_01.txt')
        self.assertEqual(msg.get_content_maintype(), 'text')

    def test_get_content_subtype_missing(self):
        msg = Message()
        self.assertEqual(msg.get_content_subtype(), 'plain')

    def test_get_content_subtype_missing_with_default_type(self):
        msg = Message()
        msg.set_default_type('message/rfc822')
        self.assertEqual(msg.get_content_subtype(), 'rfc822')

    def test_get_content_subtype_from_message_implicit(self):
        msg = self._msgobj('msg_30.txt')
        self.assertEqual(msg.get_payload(0).get_content_subtype(), 'rfc822')

    def test_get_content_subtype_from_message_explicit(self):
        msg = self._msgobj('msg_28.txt')
        self.assertEqual(msg.get_payload(0).get_content_subtype(), 'rfc822')

    def test_get_content_subtype_from_message_text_plain_implicit(self):
        msg = self._msgobj('msg_03.txt')
        self.assertEqual(msg.get_content_subtype(), 'plain')

    def test_get_content_subtype_from_message_text_plain_explicit(self):
        msg = self._msgobj('msg_01.txt')
        self.assertEqual(msg.get_content_subtype(), 'plain')

    def test_get_content_maintype_error(self):
        msg = Message()
        msg['Content-Type'] = 'no-slash-in-this-string'
        self.assertEqual(msg.get_content_maintype(), 'text')

    def test_get_content_subtype_error(self):
        msg = Message()
        msg['Content-Type'] = 'no-slash-in-this-string'
        self.assertEqual(msg.get_content_subtype(), 'plain')

    def test_replace_header(self):
        eq = self.assertEqual
        msg = Message()
        msg.add_header('First', 'One')
        msg.add_header('Second', 'Two')
        msg.add_header('Third', 'Three')
        eq(msg.keys(), ['First', 'Second', 'Third'])
        eq(msg.values(), ['One', 'Two', 'Three'])
        msg.replace_header('Second', 'Twenty')
        eq(msg.keys(), ['First', 'Second', 'Third'])
        eq(msg.values(), ['One', 'Twenty', 'Three'])
        msg.add_header('First', 'Eleven')
        msg.replace_header('First', 'One Hundred')
        eq(msg.keys(), ['First', 'Second', 'Third', 'First'])
        eq(msg.values(), ['One Hundred', 'Twenty', 'Three', 'Eleven'])
        self.assertRaises(KeyError, msg.replace_header, 'Fourth', 'Missing')

    def test_broken_base64_payload(self):
        x = 'AwDp0P7//y6LwKEAcPa/6Q=9'
        msg = Message()
        msg['content-type'] = 'audio/x-midi'
        msg['content-transfer-encoding'] = 'base64'
        msg.set_payload(x)
        self.assertEqual(msg.get_payload(decode=True), x)



# Test the email.Encoders module
class TestEncoders(unittest.TestCase):
    def test_encode_noop(self):
        eq = self.assertEqual
        msg = MIMEText('hello world', _encoder=Encoders.encode_noop)
        eq(msg.get_payload(), 'hello world')

    def test_encode_7bit(self):
        eq = self.assertEqual
        msg = MIMEText('hello world', _encoder=Encoders.encode_7or8bit)
        eq(msg.get_payload(), 'hello world')
        eq(msg['content-transfer-encoding'], '7bit')
        msg = MIMEText('hello \x7f world', _encoder=Encoders.encode_7or8bit)
        eq(msg.get_payload(), 'hello \x7f world')
        eq(msg['content-transfer-encoding'], '7bit')

    def test_encode_8bit(self):
        eq = self.assertEqual
        msg = MIMEText('hello \x80 world', _encoder=Encoders.encode_7or8bit)
        eq(msg.get_payload(), 'hello \x80 world')
        eq(msg['content-transfer-encoding'], '8bit')

    def test_encode_empty_payload(self):
        eq = self.assertEqual
        msg = Message()
        msg.set_charset('us-ascii')
        eq(msg['content-transfer-encoding'], '7bit')

    def test_encode_base64(self):
        eq = self.assertEqual
        msg = MIMEText('hello world', _encoder=Encoders.encode_base64)
        eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=')
        eq(msg['content-transfer-encoding'], 'base64')

    def test_encode_quoted_printable(self):
        eq = self.assertEqual
        msg = MIMEText('hello world', _encoder=Encoders.encode_quopri)
        eq(msg.get_payload(), 'hello=20world')
        eq(msg['content-transfer-encoding'], 'quoted-printable')

    def test_default_cte(self):
        eq = self.assertEqual
        msg = MIMEText('hello world')
        eq(msg['content-transfer-encoding'], '7bit')

    def test_default_cte(self):
        eq = self.assertEqual
        # With no explicit _charset its us-ascii, and all are 7-bit
        msg = MIMEText('hello world')
        eq(msg['content-transfer-encoding'], '7bit')
        # Similar, but with 8-bit data
        msg = MIMEText('hello \xf8 world')
        eq(msg['content-transfer-encoding'], '8bit')
        # And now with a different charset
        msg = MIMEText('hello \xf8 world', _charset='iso-8859-1')
        eq(msg['content-transfer-encoding'], 'quoted-printable')



# Test long header wrapping
class TestLongHeaders(TestEmailBase):
    def test_split_long_continuation(self):
        eq = self.ndiffAssertEqual
        msg = email.message_from_string("""\
Subject: bug demonstration
\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
\tmore text

test
""")
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
Subject: bug demonstration
\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
\tmore text

test
""")

    def test_another_long_almost_unsplittable_header(self):
        eq = self.ndiffAssertEqual
        hstr = """\
bug demonstration
\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
\tmore text"""
        h = Header(hstr, continuation_ws='\t')
        eq(h.encode(), """\
bug demonstration
\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
\tmore text""")
        h = Header(hstr)
        eq(h.encode(), """\
bug demonstration
 12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
 more text""")

    def test_long_nonstring(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, header_name='Subject')
        h.append(cz_head, cz)
        h.append(utf8_head, utf8)
        msg = Message()
        msg['Subject'] = h
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
Subject: =?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerd?=
 =?iso-8859-1?q?erband_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndi?=
 =?iso-8859-1?q?schen_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Kling?=
 =?iso-8859-1?q?en_bef=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_met?=
 =?iso-8859-2?q?ropole_se_hroutily_pod_tlakem_jejich_d=F9vtipu=2E=2E_?=
 =?utf-8?b?5q2j56K644Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE?=
 =?utf-8?b?44G+44Gb44KT44CC5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB?=
 =?utf-8?b?44GC44Go44Gv44Gn44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CM?=
 =?utf-8?q?Wenn_ist_das_Nunstuck_git_und_Slotermeyer=3F_Ja!_Beiherhund_das?=
 =?utf-8?b?IE9kZXIgZGllIEZsaXBwZXJ3YWxkdCBnZXJzcHV0LuOAjeOBqOiogOOBow==?=
 =?utf-8?b?44Gm44GE44G+44GZ44CC?=

""")
        eq(h.encode(), """\
=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerd?=
 =?iso-8859-1?q?erband_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndi?=
 =?iso-8859-1?q?schen_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Kling?=
 =?iso-8859-1?q?en_bef=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_met?=
 =?iso-8859-2?q?ropole_se_hroutily_pod_tlakem_jejich_d=F9vtipu=2E=2E_?=
 =?utf-8?b?5q2j56K644Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE?=
 =?utf-8?b?44G+44Gb44KT44CC5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB?=
 =?utf-8?b?44GC44Go44Gv44Gn44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CM?=
 =?utf-8?q?Wenn_ist_das_Nunstuck_git_und_Slotermeyer=3F_Ja!_Beiherhund_das?=
 =?utf-8?b?IE9kZXIgZGllIEZsaXBwZXJ3YWxkdCBnZXJzcHV0LuOAjeOBqOiogOOBow==?=
 =?utf-8?b?44Gm44GE44G+44GZ44CC?=""")

    def test_long_header_encode(self):
        eq = self.ndiffAssertEqual
        h = Header('wasnipoop; giraffes="very-long-necked-animals"; '
                   'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"',
                   header_name='X-Foobar-Spoink-Defrobnit')
        eq(h.encode(), '''\
wasnipoop; giraffes="very-long-necked-animals";
 spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''')

    def test_long_header_encode_with_tab_continuation(self):
        eq = self.ndiffAssertEqual
        h = Header('wasnipoop; giraffes="very-long-necked-animals"; '
                   'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"',
                   header_name='X-Foobar-Spoink-Defrobnit',
                   continuation_ws='\t')
        eq(h.encode(), '''\
wasnipoop; giraffes="very-long-necked-animals";
\tspooge="yummy"; hippos="gargantuan"; marshmallows="gooey"''')

    def test_header_splitter(self):
        eq = self.ndiffAssertEqual
        msg = MIMEText('')
        # It'd be great if we could use add_header() here, but that doesn't
        # guarantee an order of the parameters.
        msg['X-Foobar-Spoink-Defrobnit'] = (
            'wasnipoop; giraffes="very-long-necked-animals"; '
            'spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"')
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), '''\
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Foobar-Spoink-Defrobnit: wasnipoop; giraffes="very-long-necked-animals";
\tspooge="yummy"; hippos="gargantuan"; marshmallows="gooey"

''')

    def test_no_semis_header_splitter(self):
        eq = self.ndiffAssertEqual
        msg = Message()
        msg['From'] = '[e-mail]'
        msg['References'] = SPACE.join(['<[e-mail]>' % i for i in range(10)])
        msg.set_payload('Test')
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
From: [e-mail]
References: <[e-mail]> <[e-mail]> <[e-mail]> <[e-mail]> <[e-mail]>
\t<[e-mail]> <[e-mail]> <[e-mail]> <[e-mail]> <[e-mail]>

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 <[e-mail]>; 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 <[e-mail]>; 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 <[e-mail]>; 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 <[e-mail]>;
\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 <[e-mail]>;
\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 <[e-mail]>;
\tSat, 2 Feb 2002 17:00:06 -0800 (PST)""")

    def test_splitting_first_line_only_is_long(self):
        eq = self.ndiffAssertEqual