test_email.py 192 KB
Newer Older
1
# Copyright (C) 2001-2010 Python Software Foundation
2 3 4
# Contact: email-sig@python.org
# email package unit tests

5
import re
6 7 8
import time
import base64
import unittest
9
import textwrap
10

11
from io import StringIO, BytesIO
12 13 14
from itertools import chain

import email
15
import email.policy
16 17 18 19

from email.charset import Charset
from email.header import Header, decode_header, make_header
from email.parser import Parser, HeaderParser
20
from email.generator import Generator, DecodedGenerator, BytesGenerator
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35
from email.message import Message
from email.mime.application import MIMEApplication
from email.mime.audio import MIMEAudio
from email.mime.text import MIMEText
from email.mime.image import MIMEImage
from email.mime.base import MIMEBase
from email.mime.message import MIMEMessage
from email.mime.multipart 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

36
from test.support import unlink
37
from test.test_email import openfile, TestEmailBase
38

39 40 41 42
# These imports are documented to work, but we are testing them using a
# different path, so we import them here just to make sure they are importable.
from email.parser import FeedParser, BytesFeedParser

43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
NL = '\n'
EMPTYSTRING = ''
SPACE = ' '


# 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'), ['ccc@zzz.org', 'ddd@zzz.org', 'eee@zzz.org'])
        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')

158 159 160 161 162 163 164 165 166 167 168
    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.

169 170 171
    def test_message_rfc822_only(self):
        # Issue 7970: message/rfc822 not in multipart parsed by
        # HeaderParser caused an exception when flattened.
172
        with openfile('msg_46.txt') as fp:
173
            msgdata = fp.read()
174 175 176 177 178 179 180
        parser = HeaderParser()
        msg = parser.parsestr(msgdata)
        out = StringIO()
        gen = Generator(out, True, 0)
        gen.flatten(msg, False)
        self.assertEqual(out.getvalue(), msgdata)

181 182
    def test_byte_message_rfc822_only(self):
        # Make sure new bytes header parser also passes this.
183 184
        with openfile('msg_46.txt') as fp:
            msgdata = fp.read().encode('ascii')
185 186 187 188 189 190 191
        parser = email.parser.BytesHeaderParser()
        msg = parser.parsebytes(msgdata)
        out = BytesIO()
        gen = email.generator.BytesGenerator(out)
        gen.flatten(msg)
        self.assertEqual(out.getvalue(), msgdata)

192 193 194 195 196 197 198 199 200 201 202 203 204 205
    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),
           b'This is a 7bit encoded message.\n')
        # Subpart 2 is quopri
        eq(msg.get_payload(1).get_payload(decode=True),
           b'\xa1This is a Quoted Printable encoded message!\n')
        # Subpart 3 is base64
        eq(msg.get_payload(2).get_payload(decode=True),
           b'This is a Base64 encoded message.')
206 207
        # Subpart 4 is base64 with a trailing newline, which
        # used to be stripped (issue 7143).
208
        eq(msg.get_payload(3).get_payload(decode=True),
209 210 211
           b'This is a Base64 encoded message.\n')
        # Subpart 5 has no Content-Transfer-Encoding: header.
        eq(msg.get_payload(4).get_payload(decode=True),
212 213 214 215 216 217 218 219 220 221 222 223 224
           b'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), b'hello world')
        # Now try some bogus data
        msg.set_payload('foo')
        eq(msg.get_payload(decode=True), b'foo')

225 226 227 228
    def test_get_payload_n_raises_on_non_multipart(self):
        msg = Message()
        self.assertRaises(TypeError, msg.get_payload, 1)

229 230 231 232 233 234 235 236 237 238 239 240 241 242 243
    def test_decoded_generator(self):
        eq = self.assertEqual
        msg = self._msgobj('msg_07.txt')
        with openfile('msg_17.txt') as fp:
            text = fp.read()
        s = StringIO()
        g = DecodedGenerator(s)
        g.flatten(msg)
        eq(s.getvalue(), text)

    def test__contains__(self):
        msg = Message()
        msg['From'] = 'Me'
        msg['to'] = 'You'
        # Check for case insensitivity
244 245 246 247 248 249
        self.assertTrue('from' in msg)
        self.assertTrue('From' in msg)
        self.assertTrue('FROM' in msg)
        self.assertTrue('to' in msg)
        self.assertTrue('To' in msg)
        self.assertTrue('TO' in msg)
250 251 252 253 254 255 256 257 258

    def test_as_string(self):
        eq = self.ndiffAssertEqual
        msg = self._msgobj('msg_01.txt')
        with openfile('msg_01.txt') as fp:
            text = fp.read()
        eq(text, str(msg))
        fullrepr = msg.as_string(unixfrom=True)
        lines = fullrepr.split('\n')
259
        self.assertTrue(lines[0].startswith('From '))
260 261
        eq(text, NL.join(lines[1:]))

262
    # test_headerregistry.TestContentTypeHeader.bad_params
263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295
    def test_bad_param(self):
        msg = email.message_from_string("Content-Type: blarg; baz; boo\n")
        self.assertEqual(msg.get_param('baz'), '')

    def test_missing_filename(self):
        msg = email.message_from_string("From: foo\n")
        self.assertEqual(msg.get_filename(), None)

    def test_bogus_filename(self):
        msg = email.message_from_string(
        "Content-Disposition: blarg; filename\n")
        self.assertEqual(msg.get_filename(), '')

    def test_missing_boundary(self):
        msg = email.message_from_string("From: foo\n")
        self.assertEqual(msg.get_boundary(), None)

    def test_get_params(self):
        eq = self.assertEqual
        msg = email.message_from_string(
            'X-Header: foo=one; bar=two; baz=three\n')
        eq(msg.get_params(header='x-header'),
           [('foo', 'one'), ('bar', 'two'), ('baz', 'three')])
        msg = email.message_from_string(
            'X-Header: foo; bar=one; baz=two\n')
        eq(msg.get_params(header='x-header'),
           [('foo', ''), ('bar', 'one'), ('baz', 'two')])
        eq(msg.get_params(), None)
        msg = email.message_from_string(
            'X-Header: foo; bar="one"; baz=two\n')
        eq(msg.get_params(header='x-header'),
           [('foo', ''), ('bar', 'one'), ('baz', 'two')])

296
    # test_headerregistry.TestContentTypeHeader.spaces_around_param_equals
297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
    def test_get_param_liberal(self):
        msg = Message()
        msg['Content-Type'] = 'Content-Type: Multipart/mixed; boundary = "CPIMSSMTPC06p5f3tG"'
        self.assertEqual(msg.get_param('boundary'), 'CPIMSSMTPC06p5f3tG')

    def test_get_param(self):
        eq = self.assertEqual
        msg = email.message_from_string(
            "X-Header: foo=one; bar=two; baz=three\n")
        eq(msg.get_param('bar', header='x-header'), 'two')
        eq(msg.get_param('quuz', header='x-header'), None)
        eq(msg.get_param('quuz'), None)
        msg = email.message_from_string(
            'X-Header: foo; bar="one"; baz=two\n')
        eq(msg.get_param('foo', header='x-header'), '')
        eq(msg.get_param('bar', header='x-header'), 'one')
        eq(msg.get_param('baz', header='x-header'), 'two')
        # XXX: We are not RFC-2045 compliant!  We cannot parse:
        # msg["Content-Type"] = 'text/plain; weird="hey; dolly? [you] @ <\\"home\\">?"'
        # msg.get_param("weird")
        # yet.

319
    # test_headerregistry.TestContentTypeHeader.spaces_around_semis
320 321 322 323
    def test_get_param_funky_continuation_lines(self):
        msg = self._msgobj('msg_22.txt')
        self.assertEqual(msg.get_payload(1).get_param('name'), 'wibble.JPG')

324
    # test_headerregistry.TestContentTypeHeader.semis_inside_quotes
325 326 327 328 329 330 331
    def test_get_param_with_semis_in_quotes(self):
        msg = email.message_from_string(
            'Content-Type: image/pjpeg; name="Jim&amp;&amp;Jill"\n')
        self.assertEqual(msg.get_param('name'), 'Jim&amp;&amp;Jill')
        self.assertEqual(msg.get_param('name', unquote=False),
                         '"Jim&amp;&amp;Jill"')

332
    # test_headerregistry.TestContentTypeHeader.quotes_inside_rfc2231_value
333 334 335 336 337 338 339 340
    def test_get_param_with_quotes(self):
        msg = email.message_from_string(
            'Content-Type: foo; bar*0="baz\\"foobar"; bar*1="\\"baz"')
        self.assertEqual(msg.get_param('bar'), 'baz"foobar"baz')
        msg = email.message_from_string(
            "Content-Type: foo; bar*0=\"baz\\\"foobar\"; bar*1=\"\\\"baz\"")
        self.assertEqual(msg.get_param('bar'), 'baz"foobar"baz')

341
    def test_field_containment(self):
342
        unless = self.assertTrue
343 344 345 346
        msg = email.message_from_string('Header: exists')
        unless('header' in msg)
        unless('Header' in msg)
        unless('HEADER' in msg)
347
        self.assertFalse('headerx' in msg)
348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388

    def test_set_param(self):
        eq = self.assertEqual
        msg = Message()
        msg.set_param('charset', 'iso-2022-jp')
        eq(msg.get_param('charset'), 'iso-2022-jp')
        msg.set_param('importance', 'high value')
        eq(msg.get_param('importance'), 'high value')
        eq(msg.get_param('importance', unquote=False), '"high value"')
        eq(msg.get_params(), [('text/plain', ''),
                              ('charset', 'iso-2022-jp'),
                              ('importance', 'high value')])
        eq(msg.get_params(unquote=False), [('text/plain', ''),
                                       ('charset', '"iso-2022-jp"'),
                                       ('importance', '"high value"')])
        msg.set_param('charset', 'iso-9999-xx', header='X-Jimmy')
        eq(msg.get_param('charset', header='X-Jimmy'), 'iso-9999-xx')

    def test_del_param(self):
        eq = self.assertEqual
        msg = self._msgobj('msg_05.txt')
        eq(msg.get_params(),
           [('multipart/report', ''), ('report-type', 'delivery-status'),
            ('boundary', 'D1690A7AC1.996856090/mail.example.com')])
        old_val = msg.get_param("report-type")
        msg.del_param("report-type")
        eq(msg.get_params(),
           [('multipart/report', ''),
            ('boundary', 'D1690A7AC1.996856090/mail.example.com')])
        msg.set_param("report-type", old_val)
        eq(msg.get_params(),
           [('multipart/report', ''),
            ('boundary', 'D1690A7AC1.996856090/mail.example.com'),
            ('report-type', old_val)])

    def test_del_param_on_other_header(self):
        msg = Message()
        msg.add_header('Content-Disposition', 'attachment', filename='bud.gif')
        msg.del_param('filename', 'content-disposition')
        self.assertEqual(msg['content-disposition'], 'attachment')

389 390
    def test_del_param_on_nonexistent_header(self):
        msg = Message()
391
        # Deleting param on empty msg should not raise exception.
392 393 394 395 396 397 398
        msg.del_param('filename', 'content-disposition')

    def test_del_nonexistent_param(self):
        msg = Message()
        msg.add_header('Content-Type', 'text/plain', charset='utf-8')
        existing_header = msg['Content-Type']
        msg.del_param('foobar', header='Content-Type')
399
        self.assertEqual(msg['Content-Type'], existing_header)
400

401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521
    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_set_type_on_other_header(self):
        msg = Message()
        msg['X-Content-Type'] = 'text/plain'
        msg.set_type('application/octet-stream', 'X-Content-Type')
        self.assertEqual(msg['x-content-type'], 'application/octet-stream')

    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')

522
    # test_defect_handling:test_invalid_chars_in_base64_payload
523 524 525 526 527 528 529
    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),
530 531 532 533
                         (b'\x03\x00\xe9\xd0\xfe\xff\xff.\x8b\xc0'
                          b'\xa1\x00p\xf6\xbf\xe9\x0f'))
        self.assertIsInstance(msg.defects[0],
                              errors.InvalidBase64CharactersDefect)
534

535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555
    def test_broken_unicode_payload(self):
        # This test improves coverage but is not a compliance test.
        # The behavior in this situation is currently undefined by the API.
        x = 'this is a br\xf6ken thing to do'
        msg = Message()
        msg['content-type'] = 'text/plain'
        msg['content-transfer-encoding'] = '8bit'
        msg.set_payload(x)
        self.assertEqual(msg.get_payload(decode=True),
                         bytes(x, 'raw-unicode-escape'))

    def test_questionable_bytes_payload(self):
        # This test improves coverage but is not a compliance test,
        # since it involves poking inside the black box.
        x = 'this is a quéstionable thing to do'.encode('utf-8')
        msg = Message()
        msg['content-type'] = 'text/plain; charset="utf-8"'
        msg['content-transfer-encoding'] = '8bit'
        msg._payload = x
        self.assertEqual(msg.get_payload(decode=True), x)

556 557 558 559 560 561 562 563 564 565 566 567 568
    # 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_noascii_add_header(self):
        msg = Message()
        msg.add_header('Content-Disposition', 'attachment',
            filename="Fußballer.ppt")
        self.assertEqual(
569
            'attachment; filename*=utf-8\'\'Fu%C3%9Fballer.ppt',
570 571 572 573 574 575 576
            msg['Content-Disposition'])

    def test_nonascii_add_header_via_triple(self):
        msg = Message()
        msg.add_header('Content-Disposition', 'attachment',
            filename=('iso-8859-1', '', 'Fußballer.ppt'))
        self.assertEqual(
577
            'attachment; filename*=iso-8859-1\'\'Fu%DFballer.ppt',
578
            msg['Content-Disposition'])
579

580 581 582 583 584 585 586 587 588 589 590 591 592 593
    def test_ascii_add_header_with_tspecial(self):
        msg = Message()
        msg.add_header('Content-Disposition', 'attachment',
            filename="windows [filename].ppt")
        self.assertEqual(
            'attachment; filename="windows [filename].ppt"',
            msg['Content-Disposition'])

    def test_nonascii_add_header_with_tspecial(self):
        msg = Message()
        msg.add_header('Content-Disposition', 'attachment',
            filename="Fußballer [filename].ppt")
        self.assertEqual(
            "attachment; filename*=utf-8''Fu%C3%9Fballer%20%5Bfilename%5D.ppt",
594
            msg['Content-Disposition'])
595

596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631
    def test_binary_quopri_payload(self):
        for charset in ('latin-1', 'ascii'):
            msg = Message()
            msg['content-type'] = 'text/plain; charset=%s' % charset
            msg['content-transfer-encoding'] = 'quoted-printable'
            msg.set_payload(b'foo=e6=96=87bar')
            self.assertEqual(
                msg.get_payload(decode=True),
                b'foo\xe6\x96\x87bar',
                'get_payload returns wrong result with charset %s.' % charset)

    def test_binary_base64_payload(self):
        for charset in ('latin-1', 'ascii'):
            msg = Message()
            msg['content-type'] = 'text/plain; charset=%s' % charset
            msg['content-transfer-encoding'] = 'base64'
            msg.set_payload(b'Zm9v5paHYmFy')
            self.assertEqual(
                msg.get_payload(decode=True),
                b'foo\xe6\x96\x87bar',
                'get_payload returns wrong result with charset %s.' % charset)

    def test_binary_uuencode_payload(self):
        for charset in ('latin-1', 'ascii'):
            for encoding in ('x-uuencode', 'uuencode', 'uue', 'x-uue'):
                msg = Message()
                msg['content-type'] = 'text/plain; charset=%s' % charset
                msg['content-transfer-encoding'] = encoding
                msg.set_payload(b"begin 666 -\n)9F]OYI:'8F%R\n \nend\n")
                self.assertEqual(
                    msg.get_payload(decode=True),
                    b'foo\xe6\x96\x87bar',
                    str(('get_payload returns wrong result ',
                         'with charset {0} and encoding {1}.')).\
                        format(charset, encoding))

632 633 634 635 636 637 638 639 640 641
    def test_add_header_with_name_only_param(self):
        msg = Message()
        msg.add_header('Content-Disposition', 'inline', foo_bar=None)
        self.assertEqual("inline; foo-bar", msg['Content-Disposition'])

    def test_add_header_with_no_value(self):
        msg = Message()
        msg.add_header('X-Status', None)
        self.assertEqual('', msg['X-Status'])

642 643 644 645 646 647 648 649 650 651 652 653
    # Issue 5871: reject an attempt to embed a header inside a header value
    # (header injection attack).
    def test_embeded_header_via_Header_rejected(self):
        msg = Message()
        msg['Dummy'] = Header('dummy\nX-Injected-Header: test')
        self.assertRaises(errors.HeaderParseError, msg.as_string)

    def test_embeded_header_via_string_rejected(self):
        msg = Message()
        msg['Dummy'] = 'dummy\nX-Injected-Header: test'
        self.assertRaises(errors.HeaderParseError, msg.as_string)

654 655 656 657 658 659 660 661 662 663 664 665 666
    def test_unicode_header_defaults_to_utf8_encoding(self):
        # Issue 14291
        m = MIMEText('abc\n')
        m['Subject'] = 'É test'
        self.assertEqual(str(m),textwrap.dedent("""\
            Content-Type: text/plain; charset="us-ascii"
            MIME-Version: 1.0
            Content-Transfer-Encoding: 7bit
            Subject: =?utf-8?q?=C3=89_test?=

            abc
            """))

667 668 669 670 671
    def test_unicode_body_defaults_to_utf8_encoding(self):
        # Issue 14291
        m = MIMEText('É testabc\n')
        self.assertEqual(str(m),textwrap.dedent("""\
            Content-Type: text/plain; charset="utf-8"
672
            MIME-Version: 1.0
673 674 675 676 677 678
            Content-Transfer-Encoding: base64

            w4kgdGVzdGFiYwo=
            """))


679 680
# Test the email.encoders module
class TestEncoders(unittest.TestCase):
681 682 683 684 685 686 687 688 689 690

    def test_EncodersEncode_base64(self):
        with openfile('PyBanner048.gif', 'rb') as fp:
            bindata = fp.read()
        mimed = email.mime.image.MIMEImage(bindata)
        base64ed = mimed.get_payload()
        # the transfer-encoded body lines should all be <=76 characters
        lines = base64ed.split('\n')
        self.assertLessEqual(max([ len(x) for x in lines ]), 76)

691 692 693 694 695 696 697 698
    def test_encode_empty_payload(self):
        eq = self.assertEqual
        msg = Message()
        msg.set_charset('us-ascii')
        eq(msg['content-transfer-encoding'], '7bit')

    def test_default_cte(self):
        eq = self.assertEqual
699
        # 7bit data and the default us-ascii _charset
700 701
        msg = MIMEText('hello world')
        eq(msg['content-transfer-encoding'], '7bit')
702
        # Similar, but with 8bit data
703
        msg = MIMEText('hello \xf8 world')
704
        eq(msg['content-transfer-encoding'], 'base64')
705 706 707 708
        # And now with a different charset
        msg = MIMEText('hello \xf8 world', _charset='iso-8859-1')
        eq(msg['content-transfer-encoding'], 'quoted-printable')

709 710 711 712 713
    def test_encode7or8bit(self):
        # Make sure a charset whose input character set is 8bit but
        # whose output character set is 7bit gets a transfer-encoding
        # of 7bit.
        eq = self.assertEqual
714
        msg = MIMEText('文', _charset='euc-jp')
715
        eq(msg['content-transfer-encoding'], '7bit')
716

717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737
    def test_qp_encode_latin1(self):
        msg = MIMEText('\xe1\xf6\n', 'text', 'ISO-8859-1')
        self.assertEqual(str(msg), textwrap.dedent("""\
            MIME-Version: 1.0
            Content-Type: text/text; charset="iso-8859-1"
            Content-Transfer-Encoding: quoted-printable

            =E1=F6
            """))

    def test_qp_encode_non_latin1(self):
        # Issue 16948
        msg = MIMEText('\u017c\n', 'text', 'ISO-8859-2')
        self.assertEqual(str(msg), textwrap.dedent("""\
            MIME-Version: 1.0
            Content-Type: text/text; charset="iso-8859-2"
            Content-Transfer-Encoding: quoted-printable

            =BF
            """))

738

739 740
# Test long header wrapping
class TestLongHeaders(TestEmailBase):
741 742 743

    maxDiff = None

744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808
    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.replace('\t', ' '))
        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 = (b'Die Mieter treten hier ein werden mit einem Foerderband '
                  b'komfortabel den Korridor entlang, an s\xfcdl\xfcndischen '
                  b'Wandgem\xe4lden vorbei, gegen die rotierenden Klingen '
                  b'bef\xf6rdert. ')
        cz_head = (b'Finan\xe8ni metropole se hroutily pod tlakem jejich '
                   b'd\xf9vtipu.. ')
        utf8_head = ('\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')
        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(), """\
809 810 811 812 813 814 815 816 817 818 819
Subject: =?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerderb?=
 =?iso-8859-1?q?and_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndischen?=
 =?iso-8859-1?q?_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Klingen_bef?=
 =?iso-8859-1?q?=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se_hrouti?=
 =?iso-8859-2?q?ly_pod_tlakem_jejich_d=F9vtipu=2E=2E_?= =?utf-8?b?5q2j56K6?=
 =?utf-8?b?44Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE44G+44Gb44KT44CC5LiA?=
 =?utf-8?b?6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB44GC44Go44Gv44Gn44Gf44KJ?=
 =?utf-8?b?44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CMV2VubiBpc3QgZGFzIE51bnN0dWNr?=
 =?utf-8?b?IGdpdCB1bmQgU2xvdGVybWV5ZXI/IEphISBCZWloZXJodW5kIGRhcyBPZGVyIGRp?=
 =?utf-8?b?ZSBGbGlwcGVyd2FsZHQgZ2Vyc3B1dC7jgI3jgajoqIDjgaPjgabjgYTjgb7jgZk=?=
 =?utf-8?b?44CC?=
820 821

""")
822 823 824 825 826 827 828 829 830 831 832 833
        eq(h.encode(maxlinelen=76), """\
=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerde?=
 =?iso-8859-1?q?rband_komfortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndis?=
 =?iso-8859-1?q?chen_Wandgem=E4lden_vorbei=2C_gegen_die_rotierenden_Klinge?=
 =?iso-8859-1?q?n_bef=F6rdert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se?=
 =?iso-8859-2?q?_hroutily_pod_tlakem_jejich_d=F9vtipu=2E=2E_?=
 =?utf-8?b?5q2j56K644Gr6KiA44GG44Go57+76Kiz44Gv44GV44KM44Gm44GE44G+44Gb?=
 =?utf-8?b?44KT44CC5LiA6YOo44Gv44OJ44Kk44OE6Kqe44Gn44GZ44GM44CB44GC44Go?=
 =?utf-8?b?44Gv44Gn44Gf44KJ44KB44Gn44GZ44CC5a6f6Zqb44Gr44Gv44CMV2VubiBp?=
 =?utf-8?b?c3QgZGFzIE51bnN0dWNrIGdpdCB1bmQgU2xvdGVybWV5ZXI/IEphISBCZWlo?=
 =?utf-8?b?ZXJodW5kIGRhcyBPZGVyIGRpZSBGbGlwcGVyd2FsZHQgZ2Vyc3B1dC7jgI0=?=
 =?utf-8?b?44Go6KiA44Gj44Gm44GE44G+44GZ44CC?=""")
834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863

    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_is_just_a_hint(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";
 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";\t'
                   '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"''')

864 865 866 867 868 869 870 871 872 873 874 875 876 877
    def test_header_encode_with_different_output_charset(self):
        h = Header('文', 'euc-jp')
        self.assertEqual(h.encode(), "=?iso-2022-jp?b?GyRCSjgbKEI=?=")

    def test_long_header_encode_with_different_output_charset(self):
        h = Header(b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5\xa4\xec\xa4'
            b'\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2\xf1\xbc\xd4'
            b'\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3\xa4\xc6\xa4'
            b'\xa4\xa4\xde\xa4\xb9'.decode('euc-jp'), 'euc-jp')
        res = """\
=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKMnE8VCROPjUbKEI=?=
 =?iso-2022-jp?b?GyRCRyckckJUJEMkRiQkJF4kORsoQg==?="""
        self.assertEqual(h.encode(), res)

878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913
    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";
 spooge="yummy"; hippos="gargantuan"; marshmallows="gooey"

''')

    def test_no_semis_header_splitter(self):
        eq = self.ndiffAssertEqual
        msg = Message()
        msg['From'] = 'test@dom.ain'
        msg['References'] = SPACE.join('<%d@dom.ain>' % i for i in range(10))
        msg.set_payload('Test')
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
From: test@dom.ain
References: <0@dom.ain> <1@dom.ain> <2@dom.ain> <3@dom.ain> <4@dom.ain>
 <5@dom.ain> <6@dom.ain> <7@dom.ain> <8@dom.ain> <9@dom.ain>

Test""")

914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
    def test_last_split_chunk_does_not_fit(self):
        eq = self.ndiffAssertEqual
        h = Header('Subject: the first part of this is short, but_the_second'
            '_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line'
            '_all_by_itself')
        eq(h.encode(), """\
Subject: the first part of this is short,
 but_the_second_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line_all_by_itself""")

    def test_splittable_leading_char_followed_by_overlong_unsplitable(self):
        eq = self.ndiffAssertEqual
        h = Header(', but_the_second'
            '_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line'
            '_all_by_itself')
        eq(h.encode(), """\
,
 but_the_second_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line_all_by_itself""")

    def test_multiple_splittable_leading_char_followed_by_overlong_unsplitable(self):
        eq = self.ndiffAssertEqual
        h = Header(', , but_the_second'
            '_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line'
            '_all_by_itself')
        eq(h.encode(), """\
, ,
 but_the_second_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line_all_by_itself""")

    def test_trailing_splitable_on_overlong_unsplitable(self):
        eq = self.ndiffAssertEqual
        h = Header('this_part_does_not_fit_within_maxlinelen_and_thus_should_'
            'be_on_a_line_all_by_itself;')
        eq(h.encode(), "this_part_does_not_fit_within_maxlinelen_and_thus_should_"
            "be_on_a_line_all_by_itself;")

    def test_trailing_splitable_on_overlong_unsplitable_with_leading_splitable(self):
        eq = self.ndiffAssertEqual
        h = Header('; '
            'this_part_does_not_fit_within_maxlinelen_and_thus_should_'
952
            'be_on_a_line_all_by_itself; ')
953 954
        eq(h.encode(), """\
;
955
 this_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line_all_by_itself; """)
956

957 958 959 960 961 962 963 964
    def test_long_header_with_multiple_sequential_split_chars(self):
        eq = self.ndiffAssertEqual
        h = Header('This is a long line that has two whitespaces  in a row.  '
            'This used to cause truncation of the header when folded')
        eq(h.encode(), """\
This is a long line that has two whitespaces  in a row.  This used to cause
 truncation of the header when folded""")

965
    def test_splitter_split_on_punctuation_only_if_fws_with_header(self):
966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
        eq = self.ndiffAssertEqual
        h = Header('thisverylongheaderhas;semicolons;and,commas,but'
            'they;arenotlegal;fold,points')
        eq(h.encode(), "thisverylongheaderhas;semicolons;and,commas,butthey;"
                        "arenotlegal;fold,points")

    def test_leading_splittable_in_the_middle_just_before_overlong_last_part(self):
        eq = self.ndiffAssertEqual
        h = Header('this is a  test where we need to have more than one line '
            'before; our final line that is just too big to fit;; '
            'this_part_does_not_fit_within_maxlinelen_and_thus_should_'
            'be_on_a_line_all_by_itself;')
        eq(h.encode(), """\
this is a  test where we need to have more than one line before;
 our final line that is just too big to fit;;
 this_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line_all_by_itself;""")

    def test_overlong_last_part_followed_by_split_point(self):
        eq = self.ndiffAssertEqual
        h = Header('this_part_does_not_fit_within_maxlinelen_and_thus_should_'
            'be_on_a_line_all_by_itself ')
        eq(h.encode(), "this_part_does_not_fit_within_maxlinelen_and_thus_"
                        "should_be_on_a_line_all_by_itself ")

    def test_multiline_with_overlong_parts_separated_by_two_split_points(self):
        eq = self.ndiffAssertEqual
        h = Header('this_is_a__test_where_we_need_to_have_more_than_one_line_'
            'before_our_final_line_; ; '
            'this_part_does_not_fit_within_maxlinelen_and_thus_should_'
            'be_on_a_line_all_by_itself; ')
        eq(h.encode(), """\
this_is_a__test_where_we_need_to_have_more_than_one_line_before_our_final_line_;
 ;
 this_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line_all_by_itself; """)

    def test_multiline_with_overlong_last_part_followed_by_split_point(self):
        eq = self.ndiffAssertEqual
        h = Header('this is a test where we need to have more than one line '
            'before our final line; ; '
            'this_part_does_not_fit_within_maxlinelen_and_thus_should_'
            'be_on_a_line_all_by_itself; ')
        eq(h.encode(), """\
this is a test where we need to have more than one line before our final line;
 ;
 this_part_does_not_fit_within_maxlinelen_and_thus_should_be_on_a_line_all_by_itself; """)

    def test_long_header_with_whitespace_runs(self):
        eq = self.ndiffAssertEqual
        msg = Message()
        msg['From'] = 'test@dom.ain'
        msg['References'] = SPACE.join(['<foo@dom.ain>  '] * 10)
        msg.set_payload('Test')
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
From: test@dom.ain
References: <foo@dom.ain>   <foo@dom.ain>   <foo@dom.ain>   <foo@dom.ain>
   <foo@dom.ain>   <foo@dom.ain>   <foo@dom.ain>   <foo@dom.ain>
   <foo@dom.ain>   <foo@dom.ain>\x20\x20

Test""")

    def test_long_run_with_semi_header_splitter(self):
        eq = self.ndiffAssertEqual
        msg = Message()
        msg['From'] = 'test@dom.ain'
        msg['References'] = SPACE.join(['<foo@dom.ain>'] * 10) + '; abc'
        msg.set_payload('Test')
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
From: test@dom.ain
References: <foo@dom.ain> <foo@dom.ain> <foo@dom.ain> <foo@dom.ain>
 <foo@dom.ain> <foo@dom.ain> <foo@dom.ain> <foo@dom.ain> <foo@dom.ain>
 <foo@dom.ain>; abc

Test""")

    def test_splitter_split_on_punctuation_only_if_fws(self):
        eq = self.ndiffAssertEqual
        msg = Message()
        msg['From'] = 'test@dom.ain'
        msg['References'] = ('thisverylongheaderhas;semicolons;and,commas,but'
            'they;arenotlegal;fold,points')
        msg.set_payload('Test')
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        # XXX the space after the header should not be there.
        eq(sfp.getvalue(), """\
From: test@dom.ain
References:\x20
 thisverylongheaderhas;semicolons;and,commas,butthey;arenotlegal;fold,points

Test""")

1064 1065 1066
    def test_no_split_long_header(self):
        eq = self.ndiffAssertEqual
        hstr = 'References: ' + 'x' * 80
1067 1068 1069
        h = Header(hstr)
        # These come on two lines because Headers are really field value
        # classes and don't really know about their field names.
1070
        eq(h.encode(), """\
1071 1072 1073 1074
References:
 xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx""")
        h = Header('x' * 80)
        eq(h.encode(), 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx')
1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119

    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 <mailman-admin@babylon.socal-raves.org>; 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 <mailman-admin@babylon.socal-raves.org>; 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 <mailman-admin@babylon.socal-raves.org>; 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]);
 by babylon.socal-raves.org (Postfix) with ESMTP id B570E51B81;
 for <mailman-admin@babylon.socal-raves.org>;
 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 <mailman-admin@babylon.socal-raves.org>;
 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 <mailman-admin@babylon.socal-raves.org>;
 Sat, 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 test@mems-exchange.org; 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]
 helo=cthulhu.gerg.ca)
\tby kronos.mems-exchange.org with esmtp (Exim 4.05)
\tid 17k4h5-00034i-00
\tfor test@mems-exchange.org; 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')
1120 1121 1122
        eq(h.encode(maxlinelen=76), """\
=?iso-8859-1?q?Britische_Regierung_gibt_gr=FCnes_Licht_f=FCr_Offs?=
 =?iso-8859-1?q?hore-Windkraftprojekte?=""")
1123
        msg['Subject'] = h
1124 1125 1126 1127 1128 1129 1130
        eq(msg.as_string(maxheaderlen=76), """\
Subject: =?iso-8859-1?q?Britische_Regierung_gibt_gr=FCnes_Licht_f=FCr_Offs?=
 =?iso-8859-1?q?hore-Windkraftprojekte?=

""")
        eq(msg.as_string(maxheaderlen=0), """\
Subject: =?iso-8859-1?q?Britische_Regierung_gibt_gr=FCnes_Licht_f=FCr_Offshore-Windkraftprojekte?=
1131 1132 1133 1134 1135 1136

""")

    def test_long_8bit_header_no_charset(self):
        eq = self.ndiffAssertEqual
        msg = Message()
Barry Warsaw's avatar
Barry Warsaw committed
1137 1138 1139 1140
        header_string = ('Britische Regierung gibt gr\xfcnes Licht '
                         'f\xfcr Offshore-Windkraftprojekte '
                         '<a-very-long-address@example.com>')
        msg['Reply-To'] = header_string
1141 1142 1143 1144 1145
        eq(msg.as_string(maxheaderlen=78), """\
Reply-To: =?utf-8?q?Britische_Regierung_gibt_gr=C3=BCnes_Licht_f=C3=BCr_Offs?=
 =?utf-8?q?hore-Windkraftprojekte_=3Ca-very-long-address=40example=2Ecom=3E?=

""")
Barry Warsaw's avatar
Barry Warsaw committed
1146
        msg = Message()
1147
        msg['Reply-To'] = Header(header_string,
Barry Warsaw's avatar
Barry Warsaw committed
1148 1149 1150 1151
                                 header_name='Reply-To')
        eq(msg.as_string(maxheaderlen=78), """\
Reply-To: =?utf-8?q?Britische_Regierung_gibt_gr=C3=BCnes_Licht_f=C3=BCr_Offs?=
 =?utf-8?q?hore-Windkraftprojekte_=3Ca-very-long-address=40example=2Ecom=3E?=
1152 1153 1154 1155 1156 1157

""")

    def test_long_to_header(self):
        eq = self.ndiffAssertEqual
        to = ('"Someone Test #A" <someone@eecs.umich.edu>,'
1158
              '<someone@eecs.umich.edu>, '
1159 1160 1161 1162 1163 1164
              '"Someone Test #B" <someone@umich.edu>, '
              '"Someone Test #C" <someone@eecs.umich.edu>, '
              '"Someone Test #D" <someone@eecs.umich.edu>')
        msg = Message()
        msg['To'] = to
        eq(msg.as_string(maxheaderlen=78), '''\
1165
To: "Someone Test #A" <someone@eecs.umich.edu>,<someone@eecs.umich.edu>,
1166
 "Someone Test #B" <someone@umich.edu>,
1167 1168
 "Someone Test #C" <someone@eecs.umich.edu>,
 "Someone Test #D" <someone@eecs.umich.edu>
1169 1170 1171 1172 1173 1174 1175 1176

''')

    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.')
1177
        eq(h.encode(maxlinelen=76), """\
1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191
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'
1192 1193 1194 1195
        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. ')
1196 1197
        h = Header(gs, 'iso-8859-1', header_name=fn)
        # BAW: this seems broken because the first line is too long
1198 1199 1200 1201 1202
        eq(h.encode(maxlinelen=76), """\
=?iso-8859-1?q?Die_Mieter_treten_hier_e?=
 =?iso-8859-1?q?in_werden_mit_einem_Foerderband_komfortabel_den_Korridor_e?=
 =?iso-8859-1?q?ntlang=2C_an_s=FCdl=FCndischen_Wandgem=E4lden_vorbei=2C_ge?=
 =?iso-8859-1?q?gen_die_rotierenden_Klingen_bef=F6rdert=2E_?=""")
1203 1204 1205 1206 1207 1208 1209 1210

    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
1211
        # This should be splitting on spaces not semicolons.
1212
        self.ndiffAssertEqual(msg.as_string(maxheaderlen=78), """\
1213 1214
Received-1: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by
 hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP;
1215
 Wed, 05 Mar 2003 18:10:18 -0700
1216 1217
Received-2: from FOO.TLD (vizworld.acl.foo.tld [123.452.678.9]) by
 hrothgar.la.mastaler.com (tmda-ofmipd) with ESMTP;
1218
 Wed, 05 Mar 2003 18:10:18 -0700
1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229

""")

    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-1'] = Header(h, header_name='Received-1',
                                   continuation_ws='\t')
        msg['Received-2'] = h
1230
        # XXX The space after the ':' should not be there.
1231
        self.ndiffAssertEqual(msg.as_string(maxheaderlen=78), """\
1232 1233 1234 1235 1236 1237
Received-1:\x20
 <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> (David
 Bremner's message of \"Thu, 6 Mar 2003 13:58:21 +0100\")
Received-2:\x20
 <15975.17901.207240.414604@sgigritzmann1.mathematik.tu-muenchen.de> (David
 Bremner's message of \"Thu, 6 Mar 2003 13:58:21 +0100\")
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248

""")

    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')
1249
        msg['Face-3'] = ' ' + t
1250
        # XXX This splitting is all wrong.  It the first value line should be
1251
        # snug against the field name or the space after the header not there.
1252
        eq(msg.as_string(maxheaderlen=78), """\
1253
Face-1:\x20
1254
 iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
1255
 locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp
1256
Face-2:\x20
1257
 iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
1258
 locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp
1259 1260 1261
Face-3:\x20
 iVBORw0KGgoAAAANSUhEUgAAADAAAAAwBAMAAAClLOS0AAAAGFBMVEUAAAAkHiJeRUIcGBi9
 locQDQ4zJykFBAXJfWDjAAACYUlEQVR4nF2TQY/jIAyFc6lydlG5x8Nyp1Y69wj1PN2I5gzp
1262 1263 1264 1265 1266 1267 1268

""")

    def test_another_long_multiline_header(self):
        eq = self.ndiffAssertEqual
        m = ('Received: from siimage.com '
             '([172.25.1.3]) by zima.siliconimage.com with '
1269 1270
             'Microsoft SMTPSVC(5.0.2195.4905); '
             'Wed, 16 Oct 2002 07:41:11 -0700')
1271 1272
        msg = email.message_from_string(m)
        eq(msg.as_string(maxheaderlen=78), '''\
1273 1274
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
1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287

''')

    def test_long_lines_with_different_header(self):
        eq = self.ndiffAssertEqual
        h = ('List-Unsubscribe: '
             '<http://lists.sourceforge.net/lists/listinfo/spamassassin-talk>,'
             '        <mailto:spamassassin-talk-request@lists.sourceforge.net'
             '?subject=unsubscribe>')
        msg = Message()
        msg['List'] = h
        msg['List'] = Header(h, header_name='List')
        eq(msg.as_string(maxheaderlen=78), """\
1288 1289
List: List-Unsubscribe:
 <http://lists.sourceforge.net/lists/listinfo/spamassassin-talk>,
1290
        <mailto:spamassassin-talk-request@lists.sourceforge.net?subject=unsubscribe>
1291 1292
List: List-Unsubscribe:
 <http://lists.sourceforge.net/lists/listinfo/spamassassin-talk>,
1293
        <mailto:spamassassin-talk-request@lists.sourceforge.net?subject=unsubscribe>
1294 1295 1296

""")

1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309
    def test_long_rfc2047_header_with_embedded_fws(self):
        h = Header(textwrap.dedent("""\
            We're going to pretend this header is in a non-ascii character set
            \tto see if line wrapping with encoded words and embedded
               folding white space works"""),
                   charset='utf-8',
                   header_name='Test')
        self.assertEqual(h.encode()+'\n', textwrap.dedent("""\
            =?utf-8?q?We=27re_going_to_pretend_this_header_is_in_a_non-ascii_chara?=
             =?utf-8?q?cter_set?=
             =?utf-8?q?_to_see_if_line_wrapping_with_encoded_words_and_embedded?=
             =?utf-8?q?_folding_white_space_works?=""")+'\n')

1310

1311

1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
# Test mangling of "From " lines in the body of a message
class TestFromMangling(unittest.TestCase):
    def setUp(self):
        self.msg = Message()
        self.msg['From'] = 'aaa@bbb.org'
        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: aaa@bbb.org

>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: aaa@bbb.org

From the desk of A.A.A.:
Blah blah blah
""")

1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365
    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: foo@bar.com
            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)
1366

1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380
    def test_mangled_from_with_bad_bytes(self):
        source = textwrap.dedent("""\
            Content-Type: text/plain; charset="utf-8"
            MIME-Version: 1.0
            Content-Transfer-Encoding: 8bit
            From: aaa@bbb.org

        """).encode('utf-8')
        msg = email.message_from_bytes(source + b'From R\xc3\xb6lli\n')
        b = BytesIO()
        g = BytesGenerator(b, mangle_from_=True)
        g.flatten(msg)
        self.assertEqual(b.getvalue(), source + b'>From R\xc3\xb6lli\n')

1381

1382 1383 1384
# Test the basic MIMEAudio class
class TestMIMEAudio(unittest.TestCase):
    def setUp(self):
1385
        with openfile('audiotest.au', 'rb') as fp:
1386 1387 1388 1389 1390 1391 1392 1393
            self._audiodata = fp.read()
        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()
1394 1395
        self.assertEqual(base64.decodebytes(bytes(payload, 'ascii')),
                self._audiodata)
1396 1397 1398 1399 1400 1401 1402

    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
1403
        unless = self.assertTrue
1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
        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)


1422

1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434
# Test the basic MIMEImage class
class TestMIMEImage(unittest.TestCase):
    def setUp(self):
        with openfile('PyBanner048.gif', 'rb') as fp:
            self._imgdata = fp.read()
        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()
1435 1436
        self.assertEqual(base64.decodebytes(bytes(payload, 'ascii')),
                self._imgdata)
1437 1438 1439 1440 1441 1442 1443

    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
1444
        unless = self.assertTrue
1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462
        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)


1463

1464 1465 1466 1467
# Test the basic MIMEApplication class
class TestMIMEApplication(unittest.TestCase):
    def test_headers(self):
        eq = self.assertEqual
Barry Warsaw's avatar
Barry Warsaw committed
1468
        msg = MIMEApplication(b'\xfa\xfb\xfc\xfd\xfe\xff')
1469 1470 1471 1472 1473
        eq(msg.get_content_type(), 'application/octet-stream')
        eq(msg['content-transfer-encoding'], 'base64')

    def test_body(self):
        eq = self.assertEqual
1474 1475 1476 1477 1478
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
        msg = MIMEApplication(bytesdata)
        # whitespace in the cte encoded block is RFC-irrelevant.
        eq(msg.get_payload().strip(), '+vv8/f7/')
        eq(msg.get_payload(decode=True), bytesdata)
1479

1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497
    def test_binary_body_with_encode_7or8bit(self):
        # Issue 17171.
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_7or8bit)
        # Treated as a string, this will be invalid code points.
        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
        self.assertEqual(msg.get_payload(decode=True), bytesdata)
        self.assertEqual(msg['Content-Transfer-Encoding'], '8bit')
        s = BytesIO()
        g = BytesGenerator(s)
        g.flatten(msg)
        wireform = s.getvalue()
        msg2 = email.message_from_bytes(wireform)
        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
        self.assertEqual(msg2.get_payload(decode=True), bytesdata)
        self.assertEqual(msg2['Content-Transfer-Encoding'], '8bit')

    def test_binary_body_with_encode_noop(self):
1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512
        # Issue 16564: This does not produce an RFC valid message, since to be
        # valid it should have a CTE of binary.  But the below works in
        # Python2, and is documented as working this way.
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_noop)
        # Treated as a string, this will be invalid code points.
        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
        self.assertEqual(msg.get_payload(decode=True), bytesdata)
        s = BytesIO()
        g = BytesGenerator(s)
        g.flatten(msg)
        wireform = s.getvalue()
        msg2 = email.message_from_bytes(wireform)
        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
        self.assertEqual(msg2.get_payload(decode=True), bytesdata)
1513

1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542
    def test_binary_body_with_encode_quopri(self):
        # Issue 14360.
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff '
        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_quopri)
        self.assertEqual(msg.get_payload(), '=FA=FB=FC=FD=FE=FF=20')
        self.assertEqual(msg.get_payload(decode=True), bytesdata)
        self.assertEqual(msg['Content-Transfer-Encoding'], 'quoted-printable')
        s = BytesIO()
        g = BytesGenerator(s)
        g.flatten(msg)
        wireform = s.getvalue()
        msg2 = email.message_from_bytes(wireform)
        self.assertEqual(msg.get_payload(), '=FA=FB=FC=FD=FE=FF=20')
        self.assertEqual(msg2.get_payload(decode=True), bytesdata)
        self.assertEqual(msg2['Content-Transfer-Encoding'], 'quoted-printable')

    def test_binary_body_with_encode_base64(self):
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_base64)
        self.assertEqual(msg.get_payload(), '+vv8/f7/\n')
        self.assertEqual(msg.get_payload(decode=True), bytesdata)
        s = BytesIO()
        g = BytesGenerator(s)
        g.flatten(msg)
        wireform = s.getvalue()
        msg2 = email.message_from_bytes(wireform)
        self.assertEqual(msg.get_payload(), '+vv8/f7/\n')
        self.assertEqual(msg2.get_payload(decode=True), bytesdata)

1543

1544 1545 1546 1547 1548 1549 1550
# Test the basic MIMEText class
class TestMIMEText(unittest.TestCase):
    def setUp(self):
        self._msg = MIMEText('hello there')

    def test_types(self):
        eq = self.assertEqual
1551
        unless = self.assertTrue
1552 1553 1554 1555 1556 1557 1558 1559 1560
        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')
1561
        self.assertTrue(not self._msg.is_multipart())
1562 1563 1564 1565 1566 1567 1568

    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"')

1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595
    def test_7bit_input(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_input_no_charset(self):
        eq = self.assertEqual
        msg = MIMEText('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_utf8_input(self):
        teststr = '\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'))

    @unittest.skip("can't fix because of backward compat in email5, "
        "will fix in email6")
    def test_utf8_input_no_charset(self):
        teststr = '\u043a\u0438\u0440\u0438\u043b\u0438\u0446\u0430'
        self.assertRaises(UnicodeEncodeError, MIMEText, teststr)

1596

1597

1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638
# Test complicated multipart/* messages
class TestMultipart(TestEmailBase):
    def setUp(self):
        with openfile('PyBanner048.gif', 'rb') as fp:
            data = fp.read()
        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 <barry@digicool.com>'
        container['To'] = 'Dingus Lovers <cravindogs@cravindogs.com>'
        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
1639
        unless = self.assertTrue
1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952
        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: aperson@dom.ain
From: bperson@dom.ain


--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'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        outer.set_boundary('BOUNDARY')
        self.ndiffAssertEqual(outer.as_string(), '''\
Content-Type: multipart/mixed; boundary="BOUNDARY"
MIME-Version: 1.0
Subject: A subject
To: aperson@dom.ain
From: bperson@dom.ain

--BOUNDARY

--BOUNDARY--''')

    def test_no_parts_in_a_multipart_with_empty_epilogue(self):
        outer = MIMEBase('multipart', 'mixed')
        outer['Subject'] = 'A subject'
        outer['To'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        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: aperson@dom.ain
From: bperson@dom.ain


--BOUNDARY

--BOUNDARY--
''')

    def test_one_part_in_a_multipart(self):
        eq = self.ndiffAssertEqual
        outer = MIMEBase('multipart', 'mixed')
        outer['Subject'] = 'A subject'
        outer['To'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        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: aperson@dom.ain
From: bperson@dom.ain

--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'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        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: aperson@dom.ain
From: bperson@dom.ain


--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'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        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: aperson@dom.ain
From: bperson@dom.ain

--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'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        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: aperson@dom.ain
From: bperson@dom.ain

--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'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        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: aperson@dom.ain
From: bperson@dom.ain

--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'] = 'aperson@dom.ain'
        outer['From'] = 'bperson@dom.ain'
        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: aperson@dom.ain
From: bperson@dom.ain

--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

<html></html>

----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--
''')
1953
        self.assertTrue(msg.is_multipart())
1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968
        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==--""")
1969 1970
        self.assertEqual(m.get_payload(0).get_payload(), 'YXNkZg==')

1971 1972 1973 1974


# Test some badly formatted messages
class TestNonConformant(TestEmailBase):
1975

1976 1977 1978 1979 1980 1981 1982
    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')

1983
    # test_defect_handling
1984
    def test_same_boundary_inner_outer(self):
1985
        unless = self.assertTrue
1986 1987 1988 1989 1990 1991 1992 1993
        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))

1994
    # test_defect_handling
1995
    def test_multipart_no_boundary(self):
1996
        unless = self.assertTrue
1997 1998 1999
        msg = self._msgobj('msg_25.txt')
        unless(isinstance(msg.get_payload(), str))
        self.assertEqual(len(msg.defects), 2)
2000
        unless(isinstance(msg.defects[0],
2001
                          errors.NoBoundaryInMultipartDefect))
2002 2003 2004
        unless(isinstance(msg.defects[1],
                          errors.MultipartInvariantViolationDefect))

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027
    multipart_msg = textwrap.dedent("""\
        Date: Wed, 14 Nov 2007 12:56:23 GMT
        From: foo@bar.invalid
        To: foo@bar.invalid
        Subject: Content-Transfer-Encoding: base64 and multipart
        MIME-Version: 1.0
        Content-Type: multipart/mixed;
            boundary="===============3344438784458119861=="{}

        --===============3344438784458119861==
        Content-Type: text/plain

        Test message

        --===============3344438784458119861==
        Content-Type: application/octet-stream
        Content-Transfer-Encoding: base64

        YWJj

        --===============3344438784458119861==--
        """)

2028
    # test_defect_handling
2029
    def test_multipart_invalid_cte(self):
2030 2031 2032 2033
        msg = self._str_msg(
            self.multipart_msg.format("\nContent-Transfer-Encoding: base64"))
        self.assertEqual(len(msg.defects), 1)
        self.assertIsInstance(msg.defects[0],
2034 2035
            errors.InvalidMultipartContentTransferEncodingDefect)

2036
    # test_defect_handling
2037
    def test_multipart_no_cte_no_defect(self):
2038 2039
        msg = self._str_msg(self.multipart_msg.format(''))
        self.assertEqual(len(msg.defects), 0)
2040

2041
    # test_defect_handling
2042 2043
    def test_multipart_valid_cte_no_defect(self):
        for cte in ('7bit', '8bit', 'BINary'):
2044
            msg = self._str_msg(
2045
                self.multipart_msg.format(
2046 2047
                    "\nContent-Transfer-Encoding: {}".format(cte)))
            self.assertEqual(len(msg.defects), 0)
2048

2049
    # test_headerregistry.TestContentTyopeHeader invalid_1 and invalid_2.
2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098
    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: aperson@dom.ain
To: bperson@dom.ain
Subject: here's something interesting

counter to RFC 2822, there's no separating newline here
""")

2099
    # test_defect_handling
2100
    def test_lying_multipart(self):
2101
        unless = self.assertTrue
2102 2103 2104
        msg = self._msgobj('msg_41.txt')
        unless(hasattr(msg, 'defects'))
        self.assertEqual(len(msg.defects), 2)
2105
        unless(isinstance(msg.defects[0],
2106
                          errors.NoBoundaryInMultipartDefect))
2107 2108 2109
        unless(isinstance(msg.defects[1],
                          errors.MultipartInvariantViolationDefect))

2110
    # test_defect_handling
2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122
    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)
2123
        self.assertTrue(isinstance(bad.defects[0],
2124 2125
                                   errors.StartBoundaryNotFoundDefect))

2126
    # test_defect_handling
2127 2128
    def test_first_line_is_continuation_header(self):
        eq = self.assertEqual
2129
        m = ' Line 1\nSubject: test\n\nbody'
2130
        msg = email.message_from_string(m)
2131 2132
        eq(msg.keys(), ['Subject'])
        eq(msg.get_payload(), 'body')
2133
        eq(len(msg.defects), 1)
2134 2135
        self.assertDefectsEqual(msg.defects,
                                 [errors.FirstHeaderLineIsContinuationDefect])
2136 2137
        eq(msg.defects[0].line, ' Line 1\n')

2138
    # test_defect_handling
2139 2140 2141 2142 2143 2144 2145 2146 2147 2148
    def test_missing_header_body_separator(self):
        # Our heuristic if we see a line that doesn't look like a header (no
        # leading whitespace but no ':') is to assume that the blank line that
        # separates the header from the body is missing, and to stop parsing
        # headers and start parsing the body.
        msg = self._str_msg('Subject: test\nnot a header\nTo: abc\n\nb\n')
        self.assertEqual(msg.keys(), ['Subject'])
        self.assertEqual(msg.get_payload(), 'not a header\nTo: abc\n\nb\n')
        self.assertDefectsEqual(msg.defects,
                                [errors.MissingHeaderBodySeparatorDefect])
2149

2150

2151
# Test RFC 2047 header encoding and decoding
2152
class TestRFC2047(TestEmailBase):
2153 2154 2155 2156 2157 2158
    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, [
2159
            (b'Re: ', None),
2160
            (b'r\x8aksm\x9arg\x8cs', 'mac-iceland'),
2161
            (b' baz foo bar ', None),
2162 2163 2164 2165
            (b'r\x8aksm\x9arg\x8cs', 'mac-iceland')])
        header = make_header(dh)
        eq(str(header),
           'Re: r\xe4ksm\xf6rg\xe5s baz foo bar r\xe4ksm\xf6rg\xe5s')
Barry Warsaw's avatar
Barry Warsaw committed
2166
        self.ndiffAssertEqual(header.encode(maxlinelen=76), """\
2167 2168
Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar =?mac-iceland?q?r=8Aksm?=
 =?mac-iceland?q?=9Arg=8Cs?=""")
2169

2170
    def test_whitespace_keeper_unicode(self):
2171 2172 2173 2174
        eq = self.assertEqual
        s = '=?ISO-8859-1?Q?Andr=E9?= Pirard <pirard@dom.ain>'
        dh = decode_header(s)
        eq(dh, [(b'Andr\xe9', 'iso-8859-1'),
2175
                (b' Pirard <pirard@dom.ain>', None)])
2176 2177 2178
        header = str(make_header(dh))
        eq(header, 'Andr\xe9 Pirard <pirard@dom.ain>')

2179
    def test_whitespace_keeper_unicode_2(self):
2180 2181 2182
        eq = self.assertEqual
        s = 'The =?iso-8859-1?b?cXVpY2sgYnJvd24gZm94?= jumped over the =?iso-8859-1?b?bGF6eSBkb2c=?='
        dh = decode_header(s)
2183 2184
        eq(dh, [(b'The ', None), (b'quick brown fox', 'iso-8859-1'),
                (b' jumped over the ', None), (b'lazy dog', 'iso-8859-1')])
2185 2186 2187 2188 2189 2190
        hu = str(make_header(dh))
        eq(hu, 'The quick brown fox jumped over the lazy dog')

    def test_rfc2047_missing_whitespace(self):
        s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
        dh = decode_header(s)
2191 2192 2193
        self.assertEqual(dh, [(b'Sm', None), (b'\xf6', 'iso-8859-1'),
                              (b'rg', None), (b'\xe5', 'iso-8859-1'),
                              (b'sbord', None)])
2194 2195 2196 2197

    def test_rfc2047_with_whitespace(self):
        s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord'
        dh = decode_header(s)
2198 2199 2200
        self.assertEqual(dh, [(b'Sm ', None), (b'\xf6', 'iso-8859-1'),
                              (b' rg ', None), (b'\xe5', 'iso-8859-1'),
                              (b' sbord', None)])
2201

2202 2203 2204 2205 2206 2207 2208 2209 2210
    def test_rfc2047_B_bad_padding(self):
        s = '=?iso-8859-1?B?%s?='
        data = [                                # only test complete bytes
            ('dm==', b'v'), ('dm=', b'v'), ('dm', b'v'),
            ('dmk=', b'vi'), ('dmk', b'vi')
          ]
        for q, a in data:
            dh = decode_header(s % q)
            self.assertEqual(dh, [(a, 'iso-8859-1')])
2211

2212 2213 2214 2215 2216 2217
    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')])

2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268
    def test_rfc2047_rfc2047_1(self):
        # 1st testcase at end of rfc2047
        s = '(=?ISO-8859-1?Q?a?=)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'a', 'iso-8859-1'), (b')', None)])

    def test_rfc2047_rfc2047_2(self):
        # 2nd testcase at end of rfc2047
        s = '(=?ISO-8859-1?Q?a?= b)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'a', 'iso-8859-1'), (b' b)', None)])

    def test_rfc2047_rfc2047_3(self):
        # 3rd testcase at end of rfc2047
        s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])

    def test_rfc2047_rfc2047_4(self):
        # 4th testcase at end of rfc2047
        s = '(=?ISO-8859-1?Q?a?=  =?ISO-8859-1?Q?b?=)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])

    def test_rfc2047_rfc2047_5a(self):
        # 5th testcase at end of rfc2047 newline is \r\n
        s = '(=?ISO-8859-1?Q?a?=\r\n    =?ISO-8859-1?Q?b?=)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])

    def test_rfc2047_rfc2047_5b(self):
        # 5th testcase at end of rfc2047 newline is \n
        s = '(=?ISO-8859-1?Q?a?=\n    =?ISO-8859-1?Q?b?=)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])

    def test_rfc2047_rfc2047_6(self):
        # 6th testcase at end of rfc2047
        s = '(=?ISO-8859-1?Q?a_b?=)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'a b', 'iso-8859-1'), (b')', None)])

    def test_rfc2047_rfc2047_7(self):
        # 7th testcase at end of rfc2047
        s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)'
        self.assertEqual(decode_header(s),
            [(b'(', None), (b'a', 'iso-8859-1'), (b' b', 'iso-8859-2'),
             (b')', None)])
        self.assertEqual(make_header(decode_header(s)).encode(), s.lower())
        self.assertEqual(str(make_header(decode_header(s))), '(a b)')

2269 2270 2271 2272 2273 2274 2275 2276 2277 2278
    def test_multiline_header(self):
        s = '=?windows-1252?q?=22M=FCller_T=22?=\r\n <T.Mueller@xxx.com>'
        self.assertEqual(decode_header(s),
            [(b'"M\xfcller T"', 'windows-1252'),
             (b'<T.Mueller@xxx.com>', None)])
        self.assertEqual(make_header(decode_header(s)).encode(),
                         ''.join(s.splitlines()))
        self.assertEqual(str(make_header(decode_header(s))),
                         '"Müller T" <T.Mueller@xxx.com>')

2279

2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290
# Test the MIMEMessage class
class TestMIMEMessage(TestEmailBase):
    def setUp(self):
        with openfile('msg_11.txt') as fp:
            self._text = fp.read()

    def test_type_error(self):
        self.assertRaises(TypeError, MIMEMessage, 'a plain string')

    def test_valid_argument(self):
        eq = self.assertEqual
2291
        unless = self.assertTrue
2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333
        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):
        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
2334
        unless = self.assertTrue
2335 2336 2337 2338 2339 2340
        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]
2341
        self.assertTrue(isinstance(submsg, Message))
2342 2343 2344 2345 2346
        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
2347
        unless = self.assertTrue
2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574
        # 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: <002001c144a6$8752e060$56104586@oxy.edu>
  Date: Sun, 23 Sep 2001 20:10:55 -0700
  From: "Ian T. Henry" <henryi@oxy.edu>
  To: SoCal Raves <scr@socal-raves.org>
  Subject: [scr] yeah for Ians!!

Your message cannot be delivered to the following recipients:

  Recipient address: jangel1@cougar.noc.ucla.edu
  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'], '0GK500B4HD0888@cougar.noc.ucla.edu')
        eq(dsn1.get_param('dns', header='reporting-mta'), '')
        # Try a missing one <wink>
        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', ''), ('jangel1@cougar.noc.ucla.edu', '')])
        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'],
           '<002001c144a6$8752e060$56104586@oxy.edu>')

    def test_epilogue(self):
        eq = self.ndiffAssertEqual
        with openfile('msg_21.txt') as fp:
            text = fp.read()
        msg = Message()
        msg['From'] = 'aperson@dom.ain'
        msg['To'] = 'bperson@dom.ain'
        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'] = 'aperson@dom.ain'
        msg['To'] = 'bperson@dom.ain'
        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: aperson@dom.ain
To: bperson@dom.ain
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
        with openfile('msg_30.txt') as fp:
            msg = email.message_from_file(fp)
        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
        with openfile('msg_28.txt') as fp:
            msg = email.message_from_file(fp)
        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)

2575 2576 2577
    def test_default_multipart_constructor(self):
        msg = MIMEMultipart()
        self.assertTrue(msg.is_multipart())
2578

2579

2580 2581 2582 2583 2584 2585
# 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):
2586 2587 2588

    linesep = '\n'

2589 2590 2591 2592 2593 2594
    def _msgobj(self, filename):
        with openfile(filename) as fp:
            data = fp.read()
        msg = email.message_from_string(data)
        return msg, data

2595
    def _idempotent(self, msg, text, unixfrom=False):
2596 2597 2598
        eq = self.ndiffAssertEqual
        s = StringIO()
        g = Generator(s, maxheaderlen=0)
2599
        g.flatten(msg, unixfrom=unixfrom)
2600 2601 2602
        eq(text, s.getvalue())

    def test_parse_text_message(self):
2603
        eq = self.assertEqual
2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614
        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):
2615
        eq = self.assertEqual
2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685
        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)

2686 2687 2688 2689
    def test_message_delivery_status(self):
        msg, text = self._msgobj('msg_43.txt')
        self._idempotent(msg, text, unixfrom=True)

2690 2691 2692 2693
    def test_message_signed_idempotent(self):
        msg, text = self._msgobj('msg_45.txt')
        self._idempotent(msg, text)

2694
    def test_content_type(self):
2695
        eq = self.assertEqual
2696
        unless = self.assertTrue
2697 2698 2699 2700 2701 2702 2703 2704 2705
        # 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')
2706 2707
        eq(msg.preamble, 'This is a MIME-encapsulated message.' + self.linesep)
        eq(msg.epilogue, self.linesep)
2708 2709 2710 2711
        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')
2712
        eq(msg1.get_payload(), 'Yadda yadda yadda' + self.linesep)
2713 2714
        msg2 = msg.get_payload(1)
        eq(msg2.get_content_type(), 'text/plain')
2715
        eq(msg2.get_payload(), 'Yadda yadda yadda' + self.linesep)
2716 2717
        msg3 = msg.get_payload(2)
        eq(msg3.get_content_type(), 'message/rfc822')
2718
        self.assertTrue(isinstance(msg3, Message))
2719 2720 2721 2722 2723
        payload = msg3.get_payload()
        unless(isinstance(payload, list))
        eq(len(payload), 1)
        msg4 = payload[0]
        unless(isinstance(msg4, Message))
2724
        eq(msg4.get_payload(), 'Yadda yadda yadda' + self.linesep)
2725 2726

    def test_parser(self):
2727
        eq = self.assertEqual
2728
        unless = self.assertTrue
2729 2730 2731 2732 2733 2734 2735 2736 2737
        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]
2738
        self.assertTrue(isinstance(msg1, Message))
2739
        eq(msg1.get_content_type(), 'text/plain')
2740
        self.assertTrue(isinstance(msg1.get_payload(), str))
2741
        eq(msg1.get_payload(), self.linesep)
2742 2743


2744

2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770
# Test various other bits of the package's functionality
class TestMiscellaneous(TestEmailBase):
    def test_message_from_string(self):
        with openfile('msg_01.txt') as fp:
            text = fp.read()
        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):
        with openfile('msg_01.txt') as fp:
            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())

    def test_message_from_string_with_class(self):
2771
        unless = self.assertTrue
2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788
        with openfile('msg_01.txt') as fp:
            text = fp.read()

        # Create a subclass
        class MyMessage(Message):
            pass

        msg = email.message_from_string(text, MyMessage)
        unless(isinstance(msg, MyMessage))
        # Try something more complicated
        with openfile('msg_02.txt') as fp:
            text = fp.read()
        msg = email.message_from_string(text, MyMessage)
        for subpart in msg.walk():
            unless(isinstance(subpart, MyMessage))

    def test_message_from_file_with_class(self):
2789
        unless = self.assertTrue
2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802
        # Create a subclass
        class MyMessage(Message):
            pass

        with openfile('msg_01.txt') as fp:
            msg = email.message_from_file(fp, MyMessage)
        unless(isinstance(msg, MyMessage))
        # Try something more complicated
        with openfile('msg_02.txt') as fp:
            msg = email.message_from_file(fp, MyMessage)
        for subpart in msg.walk():
            unless(isinstance(subpart, MyMessage))

2803 2804 2805 2806 2807 2808 2809
    def test_custom_message_does_not_require_arguments(self):
        class MyMessage(Message):
            def __init__(self):
                super().__init__()
        msg = self._str_msg("Subject: test\n\ntest", MyMessage)
        self.assertTrue(isinstance(msg, MyMessage))

2810 2811
    def test__all__(self):
        module = __import__('email')
2812 2813 2814 2815 2816
        self.assertEqual(sorted(module.__all__), [
            'base64mime', 'charset', 'encoders', 'errors', 'feedparser',
            'generator', 'header', 'iterators', 'message',
            'message_from_binary_file', 'message_from_bytes',
            'message_from_file', 'message_from_string', 'mime', 'parser',
2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839
            '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)))

2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850
    # parsedate and parsedate_tz will become deprecated interfaces someday
    def test_parsedate_returns_None_for_invalid_strings(self):
        self.assertIsNone(utils.parsedate(''))
        self.assertIsNone(utils.parsedate_tz(''))
        self.assertIsNone(utils.parsedate('0'))
        self.assertIsNone(utils.parsedate_tz('0'))
        self.assertIsNone(utils.parsedate('A Complete Waste of Time'))
        self.assertIsNone(utils.parsedate_tz('A Complete Waste of Time'))
        # Not a part of the spec but, but this has historically worked:
        self.assertIsNone(utils.parsedate(None))
        self.assertIsNone(utils.parsedate_tz(None))
2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866

    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))

2867 2868 2869 2870 2871 2872 2873 2874 2875 2876
    def test_parsedate_no_space_before_positive_offset(self):
        self.assertEqual(utils.parsedate_tz('Wed, 3 Apr 2002 14:58:26+0800'),
           (2002, 4, 3, 14, 58, 26, 0, 1, -1, 28800))

    def test_parsedate_no_space_before_negative_offset(self):
        # Issue 1155362: we already handled '+' for this case.
        self.assertEqual(utils.parsedate_tz('Wed, 3 Apr 2002 14:58:26-0800'),
           (2002, 4, 3, 14, 58, 26, 0, 1, -1, -28800))


2877 2878 2879 2880 2881 2882 2883
    def test_parsedate_accepts_time_with_dots(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))
        eq(utils.parsedate_tz('5 Feb 2003 13.47 -0800'),
           (2003, 2, 5, 13, 47, 0, 0, 1, -1, -28800))

2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894
    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)

2895 2896 2897 2898 2899 2900
    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)

2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913
    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'))

2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925
    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', 'person@dom.ain')),
            'A Silly Person <person@dom.ain>')

    def test_escape_dump(self):
        self.assertEqual(
            utils.formataddr(('A (Very) Silly Person', 'person@dom.ain')),
2926 2927 2928 2929
            r'"A (Very) Silly Person" <person@dom.ain>')
        self.assertEqual(
            utils.parseaddr(r'"A \(Very\) Silly Person" <person@dom.ain>'),
            ('A (Very) Silly Person', 'person@dom.ain'))
2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941
        a = r'A \(Special\) Person'
        b = 'person@dom.ain'
        self.assertEqual(utils.parseaddr(utils.formataddr((a, b))), (a, b))

    def test_escape_backslashes(self):
        self.assertEqual(
            utils.formataddr(('Arthur \Backslash\ Foobar', 'person@dom.ain')),
            r'"Arthur \\Backslash\\ Foobar" <person@dom.ain>')
        a = r'Arthur \Backslash\ Foobar'
        b = 'person@dom.ain'
        self.assertEqual(utils.parseaddr(utils.formataddr((a, b))), (a, b))

2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981
    def test_quotes_unicode_names(self):
        # issue 1690608.  email.utils.formataddr() should be rfc2047 aware.
        name = "H\u00e4ns W\u00fcrst"
        addr = 'person@dom.ain'
        utf8_base64 = "=?utf-8?b?SMOkbnMgV8O8cnN0?= <person@dom.ain>"
        latin1_quopri = "=?iso-8859-1?q?H=E4ns_W=FCrst?= <person@dom.ain>"
        self.assertEqual(utils.formataddr((name, addr)), utf8_base64)
        self.assertEqual(utils.formataddr((name, addr), 'iso-8859-1'),
            latin1_quopri)

    def test_accepts_any_charset_like_object(self):
        # issue 1690608.  email.utils.formataddr() should be rfc2047 aware.
        name = "H\u00e4ns W\u00fcrst"
        addr = 'person@dom.ain'
        utf8_base64 = "=?utf-8?b?SMOkbnMgV8O8cnN0?= <person@dom.ain>"
        foobar = "FOOBAR"
        class CharsetMock:
            def header_encode(self, string):
                return foobar
        mock = CharsetMock()
        mock_expected = "%s <%s>" % (foobar, addr)
        self.assertEqual(utils.formataddr((name, addr), mock), mock_expected)
        self.assertEqual(utils.formataddr((name, addr), Charset('utf-8')),
            utf8_base64)

    def test_invalid_charset_like_object_raises_error(self):
        # issue 1690608.  email.utils.formataddr() should be rfc2047 aware.
        name = "H\u00e4ns W\u00fcrst"
        addr = 'person@dom.ain'
        # A object without a header_encode method:
        bad_charset = object()
        self.assertRaises(AttributeError, utils.formataddr, (name, addr),
            bad_charset)

    def test_unicode_address_raises_error(self):
        # issue 1690608.  email.utils.formataddr() should be rfc2047 aware.
        addr = 'pers\u00f6n@dom.in'
        self.assertRaises(UnicodeError, utils.formataddr, (None, addr))
        self.assertRaises(UnicodeError, utils.formataddr, ("Name", addr))

2982 2983 2984 2985 2986 2987 2988 2989 2990
    def test_name_with_dot(self):
        x = 'John X. Doe <jxd@example.com>'
        y = '"John X. Doe" <jxd@example.com>'
        a, b = ('John X. Doe', 'jxd@example.com')
        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)

2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008
    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'))

3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026
    def test_parseaddr_preserves_spaces_in_local_part(self):
        # issue 9286.  A normal RFC5322 local part should not contain any
        # folding white space, but legacy local parts can (they are a sequence
        # of atoms, not dotatoms).  On the other hand we strip whitespace from
        # before the @ and around dots, on the assumption that the whitespace
        # around the punctuation is a mistake in what would otherwise be
        # an RFC5322 local part.  Leading whitespace is, usual, stripped as well.
        self.assertEqual(('', "merwok wok@xample.com"),
            utils.parseaddr("merwok wok@xample.com"))
        self.assertEqual(('', "merwok  wok@xample.com"),
            utils.parseaddr("merwok  wok@xample.com"))
        self.assertEqual(('', "merwok  wok@xample.com"),
            utils.parseaddr(" merwok  wok  @xample.com"))
        self.assertEqual(('', 'merwok"wok"  wok@xample.com'),
            utils.parseaddr('merwok"wok"  wok@xample.com'))
        self.assertEqual(('', 'merwok.wok.wok@xample.com'),
            utils.parseaddr('merwok. wok .  wok@xample.com'))

3027 3028 3029 3030 3031 3032 3033 3034 3035
    def test_formataddr_does_not_quote_parens_in_quoted_string(self):
        addr = ("'foo@example.com' (foo@example.com)",
                'foo@example.com')
        addrstr = ('"\'foo@example.com\' '
                            '(foo@example.com)" <foo@example.com>')
        self.assertEqual(utils.parseaddr(addrstr), addr)
        self.assertEqual(utils.formataddr(addr), addrstr)


3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048
    def test_multiline_from_comment(self):
        x = """\
Foo
\tBar <foo@example.com>"""
        self.assertEqual(utils.parseaddr(x), ('Foo Bar', 'foo@example.com'))

    def test_quote_dump(self):
        self.assertEqual(
            utils.formataddr(('A Silly; Person', 'person@dom.ain')),
            r'"A Silly; Person" <person@dom.ain>')

    def test_charset_richcomparisons(self):
        eq = self.assertEqual
3049
        ne = self.assertNotEqual
3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110
        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(['aperson@dom.ain (Al Person)',
                               'Bud Person <bperson@dom.ain>']),
           [('Al Person', 'aperson@dom.ain'),
            ('Bud Person', 'bperson@dom.ain')])

    def test_getaddresses_nasty(self):
        eq = self.assertEqual
        eq(utils.getaddresses(['foo: ;']), [('', '')])
        eq(utils.getaddresses(
           ['[]*-- =~$']),
           [('', ''), ('', ''), ('', '*--')])
        eq(utils.getaddresses(
           ['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']),
           [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')])

    def test_getaddresses_embedded_comment(self):
        """Test proper handling of a nested comment"""
        eq = self.assertEqual
        addrs = utils.getaddresses(['User ((nested comment)) <foo@bar.com>'])
        eq(addrs[0][1], 'foo@bar.com')

    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')
3111
        msg.set_payload(b'hello world', charset=charset)
3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173
        eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n')
        eq(msg.get_payload(decode=True), b'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
""")

3174 3175 3176 3177
    def test_make_msgid_domain(self):
        self.assertEqual(
            email.utils.make_msgid(domain='testdomain-string')[-19:],
            '@testdomain-string>')
3178

3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212
    def test_Generator_linend(self):
        # Issue 14645.
        with openfile('msg_26.txt', newline='\n') as f:
            msgtxt = f.read()
        msgtxt_nl = msgtxt.replace('\r\n', '\n')
        msg = email.message_from_string(msgtxt)
        s = StringIO()
        g = email.generator.Generator(s)
        g.flatten(msg)
        self.assertEqual(s.getvalue(), msgtxt_nl)

    def test_BytesGenerator_linend(self):
        # Issue 14645.
        with openfile('msg_26.txt', newline='\n') as f:
            msgtxt = f.read()
        msgtxt_nl = msgtxt.replace('\r\n', '\n')
        msg = email.message_from_string(msgtxt_nl)
        s = BytesIO()
        g = email.generator.BytesGenerator(s)
        g.flatten(msg, linesep='\r\n')
        self.assertEqual(s.getvalue().decode('ascii'), msgtxt)

    def test_BytesGenerator_linend_with_non_ascii(self):
        # Issue 14645.
        with openfile('msg_26.txt', 'rb') as f:
            msgtxt = f.read()
        msgtxt = msgtxt.replace(b'with attachment', b'fo\xf6')
        msgtxt_nl = msgtxt.replace(b'\r\n', b'\n')
        msg = email.message_from_bytes(msgtxt_nl)
        s = BytesIO()
        g = email.generator.BytesGenerator(s)
        g.flatten(msg, linesep='\r\n')
        self.assertEqual(s.getvalue(), msgtxt)

3213

3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268
# 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)
        with openfile('msg_19.txt') as fp:
            neq(EMPTYSTRING.join(lines), fp.read())

    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
""")

3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301
    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))

3302

3303

3304
class TestParsers(TestEmailBase):
3305

3306 3307 3308 3309 3310 3311 3312 3313
    def test_header_parser(self):
        eq = self.assertEqual
        # Parse only the headers of a complex multipart MIME document
        with openfile('msg_02.txt') as fp:
            msg = HeaderParser().parse(fp)
        eq(msg['from'], 'ppp-request@zzz.org')
        eq(msg['to'], 'ppp@zzz.org')
        eq(msg.get_content_type(), 'multipart/mixed')
3314 3315
        self.assertFalse(msg.is_multipart())
        self.assertTrue(isinstance(msg.get_payload(), str))
3316

3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328
    def test_bytes_header_parser(self):
        eq = self.assertEqual
        # Parse only the headers of a complex multipart MIME document
        with openfile('msg_02.txt', 'rb') as fp:
            msg = email.parser.BytesHeaderParser().parse(fp)
        eq(msg['from'], 'ppp-request@zzz.org')
        eq(msg['to'], 'ppp@zzz.org')
        eq(msg.get_content_type(), 'multipart/mixed')
        self.assertFalse(msg.is_multipart())
        self.assertTrue(isinstance(msg.get_payload(), str))
        self.assertTrue(isinstance(msg.get_payload(decode=True), bytes))

3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366
    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: aperson@dom.ain
To: bperson@dom.ain
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: aperson@dom.ain
To: bperson@dom.ain
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
3367
        with openfile('msg_26.txt', newline='\n') as fp:
3368 3369 3370 3371 3372 3373 3374 3375
            msg = Parser().parse(fp)
        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')

3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387
    def test_crlf_flatten(self):
        # Using newline='\n' preserves the crlfs in this input file.
        with openfile('msg_26.txt', newline='\n') as fp:
            text = fp.read()
        msg = email.message_from_string(text)
        s = StringIO()
        g = Generator(s)
        g.flatten(msg, linesep='\r\n')
        self.assertEqual(s.getvalue(), text)

    maxDiff = None

3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460
    def test_multipart_digest_with_extra_mime_headers(self):
        eq = self.assertEqual
        neq = self.ndiffAssertEqual
        with openfile('msg_28.txt') as fp:
            msg = email.message_from_file(fp)
        # 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 <aperson@dom.ain',
                 'Subject: Test',
                 'Date: Tue, 20 Aug 2002 16:43:45 +1000']
        msg = email.message_from_string(NL.join(lines))
        self.assertEqual(msg['date'], 'Tue, 20 Aug 2002 16:43:45 +1000')

    def test_strip_line_feed_and_carriage_return_in_headers(self):
        eq = self.assertEqual
        # For [ 1002475 ] email message parser doesn't handle \r\n correctly
        value1 = 'text'
        value2 = 'more text'
        m = 'Header: %s\r\nNext-Header: %s\r\n\r\nBody\r\n\r\n' % (
            value1, value2)
        msg = email.message_from_string(m)
        eq(msg.get('Header'), value1)
        eq(msg.get('Next-Header'), value2)

    def test_rfc2822_header_syntax(self):
        eq = self.assertEqual
        m = '>From: foo\nFrom: bar\n!"#QUX;~: zoo\n\nbody'
        msg = email.message_from_string(m)
        eq(len(msg), 3)
        eq(sorted(field for field in msg), ['!"#QUX;~', '>From', 'From'])
        eq(msg.get_payload(), 'body')

    def test_rfc2822_space_not_allowed_in_header(self):
        eq = self.assertEqual
        m = '>From foo@example.com 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')

3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478
    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: foo@bar.com\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'))
3479

3480

3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513
class Test8BitBytesHandling(unittest.TestCase):
    # In Python3 all input is string, but that doesn't work if the actual input
    # uses an 8bit transfer encoding.  To hack around that, in email 5.1 we
    # decode byte streams using the surrogateescape error handler, and
    # reconvert to binary at appropriate places if we detect surrogates.  This
    # doesn't allow us to transform headers with 8bit bytes (they get munged),
    # but it does allow us to parse and preserve them, and to decode body
    # parts that use an 8bit CTE.

    bodytest_msg = textwrap.dedent("""\
        From: foo@bar.com
        To: baz
        Mime-Version: 1.0
        Content-Type: text/plain; charset={charset}
        Content-Transfer-Encoding: {cte}

        {bodyline}
        """)

    def test_known_8bit_CTE(self):
        m = self.bodytest_msg.format(charset='utf-8',
                                     cte='8bit',
                                     bodyline='pöstal').encode('utf-8')
        msg = email.message_from_bytes(m)
        self.assertEqual(msg.get_payload(), "pöstal\n")
        self.assertEqual(msg.get_payload(decode=True),
                         "pöstal\n".encode('utf-8'))

    def test_unknown_8bit_CTE(self):
        m = self.bodytest_msg.format(charset='notavalidcharset',
                                     cte='8bit',
                                     bodyline='pöstal').encode('utf-8')
        msg = email.message_from_bytes(m)
3514
        self.assertEqual(msg.get_payload(), "p\uFFFD\uFFFDstal\n")
3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546
        self.assertEqual(msg.get_payload(decode=True),
                         "pöstal\n".encode('utf-8'))

    def test_8bit_in_quopri_body(self):
        # This is non-RFC compliant data...without 'decode' the library code
        # decodes the body using the charset from the headers, and because the
        # source byte really is utf-8 this works.  This is likely to fail
        # against real dirty data (ie: produce mojibake), but the data is
        # invalid anyway so it is as good a guess as any.  But this means that
        # this test just confirms the current behavior; that behavior is not
        # necessarily the best possible behavior.  With 'decode' it is
        # returning the raw bytes, so that test should be of correct behavior,
        # or at least produce the same result that email4 did.
        m = self.bodytest_msg.format(charset='utf-8',
                                     cte='quoted-printable',
                                     bodyline='p=C3=B6stál').encode('utf-8')
        msg = email.message_from_bytes(m)
        self.assertEqual(msg.get_payload(), 'p=C3=B6stál\n')
        self.assertEqual(msg.get_payload(decode=True),
                         'pöstál\n'.encode('utf-8'))

    def test_invalid_8bit_in_non_8bit_cte_uses_replace(self):
        # This is similar to the previous test, but proves that if the 8bit
        # byte is undecodeable in the specified charset, it gets replaced
        # by the unicode 'unknown' character.  Again, this may or may not
        # be the ideal behavior.  Note that if decode=False none of the
        # decoders will get involved, so this is the only test we need
        # for this behavior.
        m = self.bodytest_msg.format(charset='ascii',
                                     cte='quoted-printable',
                                     bodyline='p=C3=B6stál').encode('utf-8')
        msg = email.message_from_bytes(m)
3547
        self.assertEqual(msg.get_payload(), 'p=C3=B6st\uFFFD\uFFFDl\n')
3548 3549 3550
        self.assertEqual(msg.get_payload(decode=True),
                        'pöstál\n'.encode('utf-8'))

3551
    # test_defect_handling:test_invalid_chars_in_base64_payload
3552
    def test_8bit_in_base64_body(self):
3553 3554 3555
        # If we get 8bit bytes in a base64 body, we can just ignore them
        # as being outside the base64 alphabet and decode anyway.  But
        # we register a defect.
3556 3557 3558 3559 3560
        m = self.bodytest_msg.format(charset='utf-8',
                                     cte='base64',
                                     bodyline='cMO2c3RhbAá=').encode('utf-8')
        msg = email.message_from_bytes(m)
        self.assertEqual(msg.get_payload(decode=True),
3561 3562 3563
                         'pöstal'.encode('utf-8'))
        self.assertIsInstance(msg.defects[0],
                              errors.InvalidBase64CharactersDefect)
3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575

    def test_8bit_in_uuencode_body(self):
        # Sticking an 8bit byte in a uuencode block makes it undecodable by
        # normal means, so the block is returned undecoded, but as bytes.
        m = self.bodytest_msg.format(charset='utf-8',
                                     cte='uuencode',
                                     bodyline='<,.V<W1A; á ').encode('utf-8')
        msg = email.message_from_bytes(m)
        self.assertEqual(msg.get_payload(decode=True),
                         '<,.V<W1A; á \n'.encode('utf-8'))


3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587
    headertest_headers = (
        ('From: foo@bar.com', ('From', 'foo@bar.com')),
        ('To: báz', ('To', '=?unknown-8bit?q?b=C3=A1z?=')),
        ('Subject: Maintenant je vous présente mon collègue, le pouf célèbre\n'
            '\tJean de Baddie',
            ('Subject', '=?unknown-8bit?q?Maintenant_je_vous_pr=C3=A9sente_mon_'
                'coll=C3=A8gue=2C_le_pouf_c=C3=A9l=C3=A8bre?=\n'
                ' =?unknown-8bit?q?_Jean_de_Baddie?=')),
        ('From: göst', ('From', '=?unknown-8bit?b?Z8O2c3Q=?=')),
        )
    headertest_msg = ('\n'.join([src for (src, _) in headertest_headers]) +
        '\nYes, they are flying.\n').encode('utf-8')
3588 3589 3590

    def test_get_8bit_header(self):
        msg = email.message_from_bytes(self.headertest_msg)
3591 3592
        self.assertEqual(str(msg.get('to')), 'b\uFFFD\uFFFDz')
        self.assertEqual(str(msg['to']), 'b\uFFFD\uFFFDz')
3593 3594 3595 3596

    def test_print_8bit_headers(self):
        msg = email.message_from_bytes(self.headertest_msg)
        self.assertEqual(str(msg),
3597 3598 3599 3600 3601 3602 3603 3604 3605
                         textwrap.dedent("""\
                            From: {}
                            To: {}
                            Subject: {}
                            From: {}

                            Yes, they are flying.
                            """).format(*[expected[1] for (_, expected) in
                                        self.headertest_headers]))
3606 3607 3608

    def test_values_with_8bit_headers(self):
        msg = email.message_from_bytes(self.headertest_msg)
3609
        self.assertListEqual([str(x) for x in msg.values()],
3610
                              ['foo@bar.com',
3611 3612 3613 3614
                               'b\uFFFD\uFFFDz',
                               'Maintenant je vous pr\uFFFD\uFFFDsente mon '
                                   'coll\uFFFD\uFFFDgue, le pouf '
                                   'c\uFFFD\uFFFDl\uFFFD\uFFFDbre\n'
3615
                                   '\tJean de Baddie',
3616
                               "g\uFFFD\uFFFDst"])
3617 3618 3619

    def test_items_with_8bit_headers(self):
        msg = email.message_from_bytes(self.headertest_msg)
3620
        self.assertListEqual([(str(x), str(y)) for (x, y) in msg.items()],
3621
                              [('From', 'foo@bar.com'),
3622 3623 3624 3625 3626 3627 3628
                               ('To', 'b\uFFFD\uFFFDz'),
                               ('Subject', 'Maintenant je vous '
                                  'pr\uFFFD\uFFFDsente '
                                  'mon coll\uFFFD\uFFFDgue, le pouf '
                                  'c\uFFFD\uFFFDl\uFFFD\uFFFDbre\n'
                                  '\tJean de Baddie'),
                               ('From', 'g\uFFFD\uFFFDst')])
3629 3630 3631

    def test_get_all_with_8bit_headers(self):
        msg = email.message_from_bytes(self.headertest_msg)
3632
        self.assertListEqual([str(x) for x in msg.get_all('from')],
3633
                              ['foo@bar.com',
3634
                               'g\uFFFD\uFFFDst'])
3635

3636 3637 3638 3639 3640 3641 3642 3643
    def test_get_content_type_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/pl\xA7in; charset=utf-8
            """).encode('latin-1'))
        self.assertEqual(msg.get_content_type(), "text/pl\uFFFDin")
        self.assertEqual(msg.get_content_maintype(), "text")
        self.assertEqual(msg.get_content_subtype(), "pl\uFFFDin")

3644
    # test_headerregistry.TestContentTypeHeader.non_ascii_in_params
3645 3646 3647 3648 3649 3650 3651 3652 3653
    def test_get_params_with_8bit(self):
        msg = email.message_from_bytes(
            'X-Header: foo=\xa7ne; b\xa7r=two; baz=three\n'.encode('latin-1'))
        self.assertEqual(msg.get_params(header='x-header'),
           [('foo', '\uFFFDne'), ('b\uFFFDr', 'two'), ('baz', 'three')])
        self.assertEqual(msg.get_param('Foo', header='x-header'), '\uFFFdne')
        # XXX: someday you might be able to get 'b\xa7r', for now you can't.
        self.assertEqual(msg.get_param('b\xa7r', header='x-header'), None)

3654
    # test_headerregistry.TestContentTypeHeader.non_ascii_in_rfc2231_value
3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689
    def test_get_rfc2231_params_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/plain; charset=us-ascii;
             title*=us-ascii'en'This%20is%20not%20f\xa7n"""
             ).encode('latin-1'))
        self.assertEqual(msg.get_param('title'),
            ('us-ascii', 'en', 'This is not f\uFFFDn'))

    def test_set_rfc2231_params_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/plain; charset=us-ascii;
             title*=us-ascii'en'This%20is%20not%20f\xa7n"""
             ).encode('latin-1'))
        msg.set_param('title', 'test')
        self.assertEqual(msg.get_param('title'), 'test')

    def test_del_rfc2231_params_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/plain; charset=us-ascii;
             title*=us-ascii'en'This%20is%20not%20f\xa7n"""
             ).encode('latin-1'))
        msg.del_param('title')
        self.assertEqual(msg.get_param('title'), None)
        self.assertEqual(msg.get_content_maintype(), 'text')

    def test_get_payload_with_8bit_cte_header(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Transfer-Encoding: b\xa7se64
            Content-Type: text/plain; charset=latin-1

            payload
            """).encode('latin-1'))
        self.assertEqual(msg.get_payload(), 'payload\n')
        self.assertEqual(msg.get_payload(decode=True), b'payload\n')

3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707
    non_latin_bin_msg = textwrap.dedent("""\
        From: foo@bar.com
        To: báz
        Subject: Maintenant je vous présente mon collègue, le pouf célèbre
        \tJean de Baddie
        Mime-Version: 1.0
        Content-Type: text/plain; charset="utf-8"
        Content-Transfer-Encoding: 8bit

        Да, они летят.
        """).encode('utf-8')

    def test_bytes_generator(self):
        msg = email.message_from_bytes(self.non_latin_bin_msg)
        out = BytesIO()
        email.generator.BytesGenerator(out).flatten(msg)
        self.assertEqual(out.getvalue(), self.non_latin_bin_msg)

3708 3709 3710 3711 3712 3713 3714
    def test_bytes_generator_handles_None_body(self):
        #Issue 11019
        msg = email.message.Message()
        out = BytesIO()
        email.generator.BytesGenerator(out).flatten(msg)
        self.assertEqual(out.getvalue(), b"\n")

3715
    non_latin_bin_msg_as7bit_wrapped = textwrap.dedent("""\
3716
        From: foo@bar.com
3717 3718 3719 3720
        To: =?unknown-8bit?q?b=C3=A1z?=
        Subject: =?unknown-8bit?q?Maintenant_je_vous_pr=C3=A9sente_mon_coll=C3=A8gue?=
         =?unknown-8bit?q?=2C_le_pouf_c=C3=A9l=C3=A8bre?=
         =?unknown-8bit?q?_Jean_de_Baddie?=
3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731
        Mime-Version: 1.0
        Content-Type: text/plain; charset="utf-8"
        Content-Transfer-Encoding: base64

        0JTQsCwg0L7QvdC4INC70LXRgtGP0YIuCg==
        """)

    def test_generator_handles_8bit(self):
        msg = email.message_from_bytes(self.non_latin_bin_msg)
        out = StringIO()
        email.generator.Generator(out).flatten(msg)
3732
        self.assertEqual(out.getvalue(), self.non_latin_bin_msg_as7bit_wrapped)
3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744

    def test_bytes_generator_with_unix_from(self):
        # The unixfrom contains a current date, so we can't check it
        # literally.  Just make sure the first word is 'From' and the
        # rest of the message matches the input.
        msg = email.message_from_bytes(self.non_latin_bin_msg)
        out = BytesIO()
        email.generator.BytesGenerator(out).flatten(msg, unixfrom=True)
        lines = out.getvalue().split(b'\n')
        self.assertEqual(lines[0].split()[0], b'From')
        self.assertEqual(b'\n'.join(lines[1:]), self.non_latin_bin_msg)

3745 3746 3747 3748 3749 3750
    non_latin_bin_msg_as7bit = non_latin_bin_msg_as7bit_wrapped.split('\n')
    non_latin_bin_msg_as7bit[2:4] = [
        'Subject: =?unknown-8bit?q?Maintenant_je_vous_pr=C3=A9sente_mon_'
         'coll=C3=A8gue=2C_le_pouf_c=C3=A9l=C3=A8bre?=']
    non_latin_bin_msg_as7bit = '\n'.join(non_latin_bin_msg_as7bit)

3751 3752 3753 3754 3755
    def test_message_from_binary_file(self):
        fn = 'test.msg'
        self.addCleanup(unlink, fn)
        with open(fn, 'wb') as testfile:
            testfile.write(self.non_latin_bin_msg)
3756 3757
        with open(fn, 'rb') as testfile:
            m = email.parser.BytesParser().parse(testfile)
3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802
        self.assertEqual(str(m), self.non_latin_bin_msg_as7bit)

    latin_bin_msg = textwrap.dedent("""\
        From: foo@bar.com
        To: Dinsdale
        Subject: Nudge nudge, wink, wink
        Mime-Version: 1.0
        Content-Type: text/plain; charset="latin-1"
        Content-Transfer-Encoding: 8bit

        oh là là, know what I mean, know what I mean?
        """).encode('latin-1')

    latin_bin_msg_as7bit = textwrap.dedent("""\
        From: foo@bar.com
        To: Dinsdale
        Subject: Nudge nudge, wink, wink
        Mime-Version: 1.0
        Content-Type: text/plain; charset="iso-8859-1"
        Content-Transfer-Encoding: quoted-printable

        oh l=E0 l=E0, know what I mean, know what I mean?
        """)

    def test_string_generator_reencodes_to_quopri_when_appropriate(self):
        m = email.message_from_bytes(self.latin_bin_msg)
        self.assertEqual(str(m), self.latin_bin_msg_as7bit)

    def test_decoded_generator_emits_unicode_body(self):
        m = email.message_from_bytes(self.latin_bin_msg)
        out = StringIO()
        email.generator.DecodedGenerator(out).flatten(m)
        #DecodedHeader output contains an extra blank line compared
        #to the input message.  RDM: not sure if this is a bug or not,
        #but it is not specific to the 8bit->7bit conversion.
        self.assertEqual(out.getvalue(),
            self.latin_bin_msg.decode('latin-1')+'\n')

    def test_bytes_feedparser(self):
        bfp = email.feedparser.BytesFeedParser()
        for i in range(0, len(self.latin_bin_msg), 10):
            bfp.feed(self.latin_bin_msg[i:i+10])
        m = bfp.close()
        self.assertEqual(str(m), self.latin_bin_msg_as7bit)

3803 3804 3805 3806 3807 3808 3809 3810
    def test_crlf_flatten(self):
        with openfile('msg_26.txt', 'rb') as fp:
            text = fp.read()
        msg = email.message_from_bytes(text)
        s = BytesIO()
        g = email.generator.BytesGenerator(s)
        g.flatten(msg, linesep='\r\n')
        self.assertEqual(s.getvalue(), text)
3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857

    def test_8bit_multipart(self):
        # Issue 11605
        source = textwrap.dedent("""\
            Date: Fri, 18 Mar 2011 17:15:43 +0100
            To: foo@example.com
            From: foodwatch-Newsletter <bar@example.com>
            Subject: Aktuelles zu Japan, Klonfleisch und Smiley-System
            Message-ID: <76a486bee62b0d200f33dc2ca08220ad@localhost.localdomain>
            MIME-Version: 1.0
            Content-Type: multipart/alternative;
                    boundary="b1_76a486bee62b0d200f33dc2ca08220ad"

            --b1_76a486bee62b0d200f33dc2ca08220ad
            Content-Type: text/plain; charset="utf-8"
            Content-Transfer-Encoding: 8bit

            Guten Tag, ,

            mit großer Betroffenheit verfolgen auch wir im foodwatch-Team die
            Nachrichten aus Japan.


            --b1_76a486bee62b0d200f33dc2ca08220ad
            Content-Type: text/html; charset="utf-8"
            Content-Transfer-Encoding: 8bit

            <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
                "http://www.w3.org/TR/html4/loose.dtd">
            <html lang="de">
            <head>
                    <title>foodwatch - Newsletter</title>
            </head>
            <body>
              <p>mit gro&szlig;er Betroffenheit verfolgen auch wir im foodwatch-Team
                 die Nachrichten aus Japan.</p>
            </body>
            </html>
            --b1_76a486bee62b0d200f33dc2ca08220ad--

            """).encode('utf-8')
        msg = email.message_from_bytes(source)
        s = BytesIO()
        g = email.generator.BytesGenerator(s)
        g.flatten(msg)
        self.assertEqual(s.getvalue(), source)

3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881
    def test_bytes_generator_b_encoding_linesep(self):
        # Issue 14062: b encoding was tacking on an extra \n.
        m = Message()
        # This has enough non-ascii that it should always end up b encoded.
        m['Subject'] = Header('žluťoučký kůň')
        s = BytesIO()
        g = email.generator.BytesGenerator(s)
        g.flatten(m, linesep='\r\n')
        self.assertEqual(
            s.getvalue(),
            b'Subject: =?utf-8?b?xb5sdcWlb3XEjWvDvSBrxa/FiA==?=\r\n\r\n')

    def test_generator_b_encoding_linesep(self):
        # Since this broke in ByteGenerator, test Generator for completeness.
        m = Message()
        # This has enough non-ascii that it should always end up b encoded.
        m['Subject'] = Header('žluťoučký kůň')
        s = StringIO()
        g = email.generator.Generator(s)
        g.flatten(m, linesep='\r\n')
        self.assertEqual(
            s.getvalue(),
            'Subject: =?utf-8?b?xb5sdcWlb3XEjWvDvSBrxa/FiA==?=\r\n\r\n')

3882 3883
    maxDiff = None

3884

3885
class BaseTestBytesGeneratorIdempotent:
3886

3887 3888
    maxDiff = None

3889 3890 3891
    def _msgobj(self, filename):
        with openfile(filename, 'rb') as fp:
            data = fp.read()
3892
        data = self.normalize_linesep_regex.sub(self.blinesep, data)
3893 3894 3895
        msg = email.message_from_bytes(data)
        return msg, data

3896
    def _idempotent(self, msg, data, unixfrom=False):
3897 3898
        b = BytesIO()
        g = email.generator.BytesGenerator(b, maxheaderlen=0)
3899
        g.flatten(msg, unixfrom=unixfrom, linesep=self.linesep)
3900
        self.assertEqual(data, b.getvalue())
3901 3902


3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915
class TestBytesGeneratorIdempotentNL(BaseTestBytesGeneratorIdempotent,
                                    TestIdempotent):
    linesep = '\n'
    blinesep = b'\n'
    normalize_linesep_regex = re.compile(br'\r\n')


class TestBytesGeneratorIdempotentCRLF(BaseTestBytesGeneratorIdempotent,
                                       TestIdempotent):
    linesep = '\r\n'
    blinesep = b'\r\n'
    normalize_linesep_regex = re.compile(br'(?<!\r)\n')

3916

3917 3918 3919
class TestBase64(unittest.TestCase):
    def test_len(self):
        eq = self.assertEqual
3920
        eq(base64mime.header_length('hello'),
3921
           len(base64mime.body_encode(b'hello', eol='')))
3922 3923 3924 3925 3926 3927 3928
        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
3929
            eq(base64mime.header_length('x' * size), bsize)
3930 3931 3932

    def test_decode(self):
        eq = self.assertEqual
3933
        eq(base64mime.decode(''), b'')
3934 3935 3936 3937
        eq(base64mime.decode('aGVsbG8='), b'hello')

    def test_encode(self):
        eq = self.assertEqual
3938 3939
        eq(base64mime.body_encode(b''), b'')
        eq(base64mime.body_encode(b'hello'), 'aGVsbG8=\n')
3940
        # Test the binary flag
3941
        eq(base64mime.body_encode(b'hello\n'), 'aGVsbG8K\n')
3942
        # Test the maxlinelen arg
3943
        eq(base64mime.body_encode(b'xxxx ' * 20, maxlinelen=40), """\
3944 3945 3946 3947 3948 3949
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg
eHh4eCB4eHh4IHh4eHggeHh4eCB4eHh4IHh4eHgg
eHh4eCB4eHh4IA==
""")
        # Test the eol argument
3950
        eq(base64mime.body_encode(b'xxxx ' * 20, maxlinelen=40, eol='\r\n'),
Barry Warsaw's avatar
Barry Warsaw committed
3951
           """\
3952 3953 3954 3955 3956 3957 3958 3959 3960 3961
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=?=')
3962 3963
        eq(he('hello\r\nworld'), '=?iso-8859-1?b?aGVsbG8NCndvcmxk?=')
        eq(he('hello\nworld'), '=?iso-8859-1?b?aGVsbG8Kd29ybGQ=?=')
3964 3965 3966 3967 3968
        # Test the charset option
        eq(he('hello', charset='iso-8859-2'), '=?iso-8859-2?b?aGVsbG8=?=')
        eq(he('hello\nworld'), '=?iso-8859-1?b?aGVsbG8Kd29ybGQ=?=')


3969

3970 3971 3972 3973 3974 3975 3976 3977
class TestQuopri(unittest.TestCase):
    def setUp(self):
        # Set of characters (as byte integers) that don't need to be encoded
        # in headers.
        self.hlit = list(chain(
            range(ord('a'), ord('z') + 1),
            range(ord('A'), ord('Z') + 1),
            range(ord('0'), ord('9') + 1),
3978
            (c for c in b'!*+-/')))
3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992
        # Set of characters (as byte integers) that do need to be encoded in
        # headers.
        self.hnon = [c for c in range(256) if c not in self.hlit]
        assert len(self.hlit) + len(self.hnon) == 256
        # Set of characters (as byte integers) that don't need to be encoded
        # in bodies.
        self.blit = list(range(ord(' '), ord('~') + 1))
        self.blit.append(ord('\t'))
        self.blit.remove(ord('='))
        # Set of characters (as byte integers) that do need to be encoded in
        # bodies.
        self.bnon = [c for c in range(256) if c not in self.blit]
        assert len(self.blit) + len(self.bnon) == 256

3993
    def test_quopri_header_check(self):
3994
        for c in self.hlit:
3995
            self.assertFalse(quoprimime.header_check(c),
3996
                        'Should not be header quopri encoded: %s' % chr(c))
3997
        for c in self.hnon:
3998
            self.assertTrue(quoprimime.header_check(c),
3999
                            'Should be header quopri encoded: %s' % chr(c))
4000

4001
    def test_quopri_body_check(self):
4002
        for c in self.blit:
4003
            self.assertFalse(quoprimime.body_check(c),
4004
                        'Should not be body quopri encoded: %s' % chr(c))
4005
        for c in self.bnon:
4006
            self.assertTrue(quoprimime.body_check(c),
4007
                            'Should be body quopri encoded: %s' % chr(c))
4008 4009 4010

    def test_header_quopri_len(self):
        eq = self.assertEqual
4011 4012
        eq(quoprimime.header_length(b'hello'), 5)
        # RFC 2047 chrome is not included in header_length().
4013
        eq(len(quoprimime.header_encode(b'hello', charset='xxx')),
4014
           quoprimime.header_length(b'hello') +
4015 4016
           # =?xxx?q?...?= means 10 extra characters
           10)
4017 4018
        eq(quoprimime.header_length(b'h@e@l@l@o@'), 20)
        # RFC 2047 chrome is not included in header_length().
4019
        eq(len(quoprimime.header_encode(b'h@e@l@l@o@', charset='xxx')),
4020
           quoprimime.header_length(b'h@e@l@l@o@') +
4021 4022 4023
           # =?xxx?q?...?= means 10 extra characters
           10)
        for c in self.hlit:
4024
            eq(quoprimime.header_length(bytes([c])), 1,
4025 4026
               'expected length 1 for %r' % chr(c))
        for c in self.hnon:
4027 4028 4029 4030
            # Space is special; it's encoded to _
            if c == ord(' '):
                continue
            eq(quoprimime.header_length(bytes([c])), 3,
4031
               'expected length 3 for %r' % chr(c))
4032
        eq(quoprimime.header_length(b' '), 1)
4033 4034 4035 4036

    def test_body_quopri_len(self):
        eq = self.assertEqual
        for c in self.blit:
4037
            eq(quoprimime.body_length(bytes([c])), 1)
4038
        for c in self.bnon:
4039
            eq(quoprimime.body_length(bytes([c])), 3)
4040 4041 4042 4043 4044 4045

    def test_quote_unquote_idempotent(self):
        for x in range(256):
            c = chr(x)
            self.assertEqual(quoprimime.unquote(quoprimime.quote(c)), c)

4046 4047 4048 4049 4050 4051
    def _test_header_encode(self, header, expected_encoded_header, charset=None):
        if charset is None:
            encoded_header = quoprimime.header_encode(header)
        else:
            encoded_header = quoprimime.header_encode(header, charset)
        self.assertEqual(encoded_header, expected_encoded_header)
4052

4053 4054 4055
    def test_header_encode_null(self):
        self._test_header_encode(b'', '')

4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086
    def test_header_encode_one_word(self):
        self._test_header_encode(b'hello', '=?iso-8859-1?q?hello?=')

    def test_header_encode_two_lines(self):
        self._test_header_encode(b'hello\nworld',
                                '=?iso-8859-1?q?hello=0Aworld?=')

    def test_header_encode_non_ascii(self):
        self._test_header_encode(b'hello\xc7there',
                                '=?iso-8859-1?q?hello=C7there?=')

    def test_header_encode_alt_charset(self):
        self._test_header_encode(b'hello', '=?iso-8859-2?q?hello?=',
                charset='iso-8859-2')

    def _test_header_decode(self, encoded_header, expected_decoded_header):
        decoded_header = quoprimime.header_decode(encoded_header)
        self.assertEqual(decoded_header, expected_decoded_header)

    def test_header_decode_null(self):
        self._test_header_decode('', '')

    def test_header_decode_one_word(self):
        self._test_header_decode('hello', 'hello')

    def test_header_decode_two_lines(self):
        self._test_header_decode('hello=0Aworld', 'hello\nworld')

    def test_header_decode_non_ascii(self):
        self._test_header_decode('hello=C7there', 'hello\xc7there')

4087 4088 4089 4090
    def test_header_decode_re_bug_18380(self):
        # Issue 18380: Call re.sub with a positional argument for flags in the wrong position
        self.assertEqual(quoprimime.header_decode('=30' * 257), '0' * 257)

4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115
    def _test_decode(self, encoded, expected_decoded, eol=None):
        if eol is None:
            decoded = quoprimime.decode(encoded)
        else:
            decoded = quoprimime.decode(encoded, eol=eol)
        self.assertEqual(decoded, expected_decoded)

    def test_decode_null_word(self):
        self._test_decode('', '')

    def test_decode_null_line_null_word(self):
        self._test_decode('\r\n', '\n')

    def test_decode_one_word(self):
        self._test_decode('hello', 'hello')

    def test_decode_one_word_eol(self):
        self._test_decode('hello', 'hello', eol='X')

    def test_decode_one_line(self):
        self._test_decode('hello\r\n', 'hello\n')

    def test_decode_one_line_lf(self):
        self._test_decode('hello\n', 'hello\n')

4116 4117 4118 4119 4120 4121 4122 4123 4124
    def test_decode_one_line_cr(self):
        self._test_decode('hello\r', 'hello\n')

    def test_decode_one_line_nl(self):
        self._test_decode('hello\n', 'helloX', eol='X')

    def test_decode_one_line_crnl(self):
        self._test_decode('hello\r\n', 'helloX', eol='X')

4125 4126 4127 4128 4129 4130 4131 4132 4133
    def test_decode_one_line_one_word(self):
        self._test_decode('hello\r\nworld', 'hello\nworld')

    def test_decode_one_line_one_word_eol(self):
        self._test_decode('hello\r\nworld', 'helloXworld', eol='X')

    def test_decode_two_lines(self):
        self._test_decode('hello\r\nworld\r\n', 'hello\nworld\n')

4134 4135 4136
    def test_decode_two_lines_eol(self):
        self._test_decode('hello\r\nworld\r\n', 'helloXworldX', eol='X')

4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207
    def test_decode_one_long_line(self):
        self._test_decode('Spam' * 250, 'Spam' * 250)

    def test_decode_one_space(self):
        self._test_decode(' ', '')

    def test_decode_multiple_spaces(self):
        self._test_decode(' ' * 5, '')

    def test_decode_one_line_trailing_spaces(self):
        self._test_decode('hello    \r\n', 'hello\n')

    def test_decode_two_lines_trailing_spaces(self):
        self._test_decode('hello    \r\nworld   \r\n', 'hello\nworld\n')

    def test_decode_quoted_word(self):
        self._test_decode('=22quoted=20words=22', '"quoted words"')

    def test_decode_uppercase_quoting(self):
        self._test_decode('ab=CD=EF', 'ab\xcd\xef')

    def test_decode_lowercase_quoting(self):
        self._test_decode('ab=cd=ef', 'ab\xcd\xef')

    def test_decode_soft_line_break(self):
        self._test_decode('soft line=\r\nbreak', 'soft linebreak')

    def test_decode_false_quoting(self):
        self._test_decode('A=1,B=A ==> A+B==2', 'A=1,B=A ==> A+B==2')

    def _test_encode(self, body, expected_encoded_body, maxlinelen=None, eol=None):
        kwargs = {}
        if maxlinelen is None:
            # Use body_encode's default.
            maxlinelen = 76
        else:
            kwargs['maxlinelen'] = maxlinelen
        if eol is None:
            # Use body_encode's default.
            eol = '\n'
        else:
            kwargs['eol'] = eol
        encoded_body = quoprimime.body_encode(body, **kwargs)
        self.assertEqual(encoded_body, expected_encoded_body)
        if eol == '\n' or eol == '\r\n':
            # We know how to split the result back into lines, so maxlinelen
            # can be checked.
            for line in encoded_body.splitlines():
                self.assertLessEqual(len(line), maxlinelen)

    def test_encode_null(self):
        self._test_encode('', '')

    def test_encode_null_lines(self):
        self._test_encode('\n\n', '\n\n')

    def test_encode_one_line(self):
        self._test_encode('hello\n', 'hello\n')

    def test_encode_one_line_crlf(self):
        self._test_encode('hello\r\n', 'hello\n')

    def test_encode_one_line_eol(self):
        self._test_encode('hello\n', 'hello\r\n', eol='\r\n')

    def test_encode_one_space(self):
        self._test_encode(' ', '=20')

    def test_encode_one_line_one_space(self):
        self._test_encode(' \n', '=20\n')

4208 4209 4210 4211 4212 4213 4214 4215
# XXX: body_encode() expect strings, but uses ord(char) from these strings
# to index into a 256-entry list.  For code points above 255, this will fail.
# Should there be a check for 8-bit only ord() values in body, or at least
# a comment about the expected input?

    def test_encode_two_lines_one_space(self):
        self._test_encode(' \n \n', '=20\n=20\n')

4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230
    def test_encode_one_word_trailing_spaces(self):
        self._test_encode('hello   ', 'hello  =20')

    def test_encode_one_line_trailing_spaces(self):
        self._test_encode('hello   \n', 'hello  =20\n')

    def test_encode_one_word_trailing_tab(self):
        self._test_encode('hello  \t', 'hello  =09')

    def test_encode_one_line_trailing_tab(self):
        self._test_encode('hello  \t\n', 'hello  =09\n')

    def test_encode_trailing_space_before_maxlinelen(self):
        self._test_encode('abcd \n1234', 'abcd =\n\n1234', maxlinelen=6)

4231 4232 4233
    def test_encode_trailing_space_at_maxlinelen(self):
        self._test_encode('abcd \n1234', 'abcd=\n=20\n1234', maxlinelen=5)

4234
    def test_encode_trailing_space_beyond_maxlinelen(self):
4235 4236 4237 4238
        self._test_encode('abcd \n1234', 'abc=\nd=20\n1234', maxlinelen=4)

    def test_encode_whitespace_lines(self):
        self._test_encode(' \n' * 5, '=20\n' * 5)
4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254

    def test_encode_quoted_equals(self):
        self._test_encode('a = b', 'a =3D b')

    def test_encode_one_long_string(self):
        self._test_encode('x' * 100, 'x' * 75 + '=\n' + 'x' * 25)

    def test_encode_one_long_line(self):
        self._test_encode('x' * 100 + '\n', 'x' * 75 + '=\n' + 'x' * 25 + '\n')

    def test_encode_one_very_long_line(self):
        self._test_encode('x' * 200 + '\n',
                2 * ('x' * 75 + '=\n') + 'x' * 50 + '\n')

    def test_encode_shortest_maxlinelen(self):
        self._test_encode('=' * 5, '=3D=\n' * 4 + '=3D', maxlinelen=4)
4255

4256 4257 4258
    def test_encode_maxlinelen_too_small(self):
        self.assertRaises(ValueError, self._test_encode, '', '', maxlinelen=3)

4259 4260
    def test_encode(self):
        eq = self.assertEqual
4261 4262
        eq(quoprimime.body_encode(''), '')
        eq(quoprimime.body_encode('hello'), 'hello')
4263
        # Test the binary flag
4264
        eq(quoprimime.body_encode('hello\r\nworld'), 'hello\nworld')
4265
        # Test the maxlinelen arg
4266
        eq(quoprimime.body_encode('xxxx ' * 20, maxlinelen=40), """\
4267 4268 4269 4270
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
4271 4272
        eq(quoprimime.body_encode('xxxx ' * 20, maxlinelen=40, eol='\r\n'),
           """\
4273 4274 4275
xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx=\r
 xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx=\r
x xxxx xxxx xxxx xxxx=20""")
4276
        eq(quoprimime.body_encode("""\
4277 4278 4279 4280 4281 4282 4283 4284
one line

two line"""), """\
one line

two line""")


4285

4286 4287 4288 4289 4290 4291 4292 4293 4294
# 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

4295
    def test_codec_encodeable(self):
4296 4297 4298
        eq = self.assertEqual
        # Make sure us-ascii = no Unicode conversion
        c = Charset('us-ascii')
4299 4300
        eq(c.header_encode('Hello World!'), 'Hello World!')
        # Test 8-bit idempotency with us-ascii
4301
        s = '\xa4\xa2\xa4\xa4\xa4\xa6\xa4\xa8\xa4\xaa'
4302 4303 4304
        self.assertRaises(UnicodeError, c.header_encode, s)
        c = Charset('utf-8')
        eq(c.header_encode(s), '=?utf-8?b?wqTCosKkwqTCpMKmwqTCqMKkwqo=?=')
4305 4306 4307 4308 4309

    def test_body_encode(self):
        eq = self.assertEqual
        # Try a charset with QP body encoding
        c = Charset('iso-8859-1')
Barry Warsaw's avatar
Barry Warsaw committed
4310
        eq('hello w=F6rld', c.body_encode('hello w\xf6rld'))
4311 4312
        # Try a charset with Base64 body encoding
        c = Charset('utf-8')
4313
        eq('aGVsbG8gd29ybGQ=\n', c.body_encode(b'hello world'))
4314 4315
        # Try a charset with None body encoding
        c = Charset('us-ascii')
Barry Warsaw's avatar
Barry Warsaw committed
4316
        eq('hello world', c.body_encode('hello world'))
4317 4318 4319
        # Try the convert argument, where input codec != output codec
        c = Charset('euc-jp')
        # With apologies to Tokio Kikuchi ;)
4320 4321 4322 4323 4324 4325 4326 4327 4328
        # XXX FIXME
##         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
4329 4330 4331 4332
        # 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
4333
        CharsetModule.add_charset('fake', CharsetModule.QP, None, 'utf-8')
4334
        c = Charset('fake')
4335
        eq('hello world', c.body_encode('hello world'))
4336 4337 4338 4339 4340 4341 4342

    def test_unicode_charset_name(self):
        charset = Charset('us-ascii')
        self.assertEqual(str(charset), 'us-ascii')
        self.assertRaises(errors.CharsetError, Charset, 'asc\xffii')


4343

4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367
# 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 '):
4368
            self.assertTrue(len(l) <= 76)
4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391

    def test_multilingual(self):
        eq = self.ndiffAssertEqual
        g = Charset("iso-8859-1")
        cz = Charset("iso-8859-2")
        utf8 = Charset("utf-8")
        g_head = (b'Die Mieter treten hier ein werden mit einem '
                  b'Foerderband komfortabel den Korridor entlang, '
                  b'an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, '
                  b'gegen die rotierenden Klingen bef\xf6rdert. ')
        cz_head = (b'Finan\xe8ni metropole se hroutily pod tlakem jejich '
                   b'd\xf9vtipu.. ')
        utf8_head = ('\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')
        h = Header(g_head, g)
        h.append(cz_head, cz)
        h.append(utf8_head, utf8)
4392
        enc = h.encode(maxlinelen=76)
4393
        eq(enc, """\
4394 4395 4396 4397
=?iso-8859-1?q?Die_Mieter_treten_hier_ein_werden_mit_einem_Foerderband_kom?=
 =?iso-8859-1?q?fortabel_den_Korridor_entlang=2C_an_s=FCdl=FCndischen_Wand?=
 =?iso-8859-1?q?gem=E4lden_vorbei=2C_gegen_die_rotierenden_Klingen_bef=F6r?=
 =?iso-8859-1?q?dert=2E_?= =?iso-8859-2?q?Finan=E8ni_metropole_se_hroutily?=
4398 4399 4400 4401
 =?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?=
4402 4403 4404 4405 4406 4407 4408 4409
 =?utf-8?b?IE51bnN0dWNrIGdpdCB1bmQgU2xvdGVybWV5ZXI/IEphISBCZWloZXJodW5k?=
 =?utf-8?b?IGRhcyBPZGVyIGRpZSBGbGlwcGVyd2FsZHQgZ2Vyc3B1dC7jgI3jgajoqIA=?=
 =?utf-8?b?44Gj44Gm44GE44G+44GZ44CC?=""")
        decoded = decode_header(enc)
        eq(len(decoded), 3)
        eq(decoded[0], (g_head, 'iso-8859-1'))
        eq(decoded[1], (cz_head, 'iso-8859-2'))
        eq(decoded[2], (utf8_head.encode('utf-8'), 'utf-8'))
4410
        ustr = str(h)
4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428
        eq(ustr,
           (b'Die Mieter treten hier ein werden mit einem Foerderband '
            b'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen '
            b'Wandgem\xc3\xa4lden vorbei, gegen die rotierenden Klingen '
            b'bef\xc3\xb6rdert. Finan\xc4\x8dni metropole se hroutily pod '
            b'tlakem jejich d\xc5\xafvtipu.. \xe6\xad\xa3\xe7\xa2\xba\xe3\x81'
            b'\xab\xe8\xa8\x80\xe3\x81\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3'
            b'\xe3\x81\xaf\xe3\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3'
            b'\x81\xbe\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
            b'\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8\xaa\x9e'
            b'\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81\xe3\x81\x82\xe3'
            b'\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81\x9f\xe3\x82\x89\xe3\x82'
            b'\x81\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\xe5\xae\x9f\xe9\x9a\x9b'
            b'\xe3\x81\xab\xe3\x81\xaf\xe3\x80\x8cWenn ist das Nunstuck git '
            b'und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt '
            b'gersput.\xe3\x80\x8d\xe3\x81\xa8\xe8\xa8\x80\xe3\x81\xa3\xe3\x81'
            b'\xa6\xe3\x81\x84\xe3\x81\xbe\xe3\x81\x99\xe3\x80\x82'
            ).decode('utf-8'))
4429 4430
        # Test make_header()
        newh = make_header(decode_header(enc))
4431
        eq(newh, h)
4432 4433 4434 4435

    def test_empty_header_encode(self):
        h = Header()
        self.assertEqual(h.encode(), '')
4436

4437 4438 4439 4440 4441
    def test_header_ctor_default_args(self):
        eq = self.ndiffAssertEqual
        h = Header()
        eq(h, '')
        h.append('foo', Charset('iso-8859-1'))
4442
        eq(h, 'foo')
4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462

    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''')
        eq(str(h), hstr)
        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''')
        eq(str(h), hstr)
        h = Header(hstr, maxlinelen=1024, header_name='Subject')
        eq(h.encode(), hstr)
        eq(str(h), hstr)

4463
    def test_quopri_splittable(self):
4464 4465
        eq = self.ndiffAssertEqual
        h = Header(charset='iso-8859-1', maxlinelen=20)
4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520
        x = 'xxxx ' * 20
        h.append(x)
        s = h.encode()
        eq(s, """\
=?iso-8859-1?q?xxx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_x?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?x_?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?xx?=
 =?iso-8859-1?q?_?=""")
        eq(x, str(make_header(decode_header(s))))
4521 4522
        h = Header(charset='iso-8859-1', maxlinelen=40)
        h.append('xxxx ' * 20)
4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584
        s = h.encode()
        eq(s, """\
=?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xxx?=
 =?iso-8859-1?q?x_xxxx_xxxx_xxxx_xxxx_?=
 =?iso-8859-1?q?xxxx_xxxx_xxxx_xxxx_xx?=
 =?iso-8859-1?q?xx_xxxx_xxxx_xxxx_xxxx?=
 =?iso-8859-1?q?_xxxx_xxxx_?=""")
        eq(x, str(make_header(decode_header(s))))

    def test_base64_splittable(self):
        eq = self.ndiffAssertEqual
        h = Header(charset='koi8-r', maxlinelen=20)
        x = 'xxxx ' * 20
        h.append(x)
        s = h.encode()
        eq(s, """\
=?koi8-r?b?eHh4?=
 =?koi8-r?b?eCB4?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?IHh4?=
 =?koi8-r?b?eHgg?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?eCB4?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?IHh4?=
 =?koi8-r?b?eHgg?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?eCB4?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?IHh4?=
 =?koi8-r?b?eHgg?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?eCB4?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?IHh4?=
 =?koi8-r?b?eHgg?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?eCB4?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?IHh4?=
 =?koi8-r?b?eHgg?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?eCB4?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?IHh4?=
 =?koi8-r?b?eHgg?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?eCB4?=
 =?koi8-r?b?eHh4?=
 =?koi8-r?b?IA==?=""")
        eq(x, str(make_header(decode_header(s))))
        h = Header(charset='koi8-r', maxlinelen=40)
        h.append(x)
        s = h.encode()
        eq(s, """\
=?koi8-r?b?eHh4eCB4eHh4IHh4eHggeHh4?=
 =?koi8-r?b?eCB4eHh4IHh4eHggeHh4eCB4?=
 =?koi8-r?b?eHh4IHh4eHggeHh4eCB4eHh4?=
 =?koi8-r?b?IHh4eHggeHh4eCB4eHh4IHh4?=
 =?koi8-r?b?eHggeHh4eCB4eHh4IHh4eHgg?=
 =?koi8-r?b?eHh4eCB4eHh4IA==?=""")
        eq(x, str(make_header(decode_header(s))))
4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597

    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')
4598
        eq(h, 'hello')
4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627

##    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('p\xf6stal', 'utf-8')
        eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=')
        h = Header('\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 = b'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big'
        raises(UnicodeError, Header, x)
        h = Header()
        raises(UnicodeError, h.append, x)
        e = x.decode('utf-8', 'replace')
        eq(str(Header(x, errors='replace')), e)
        h.append(x, errors='replace')
        eq(str(h), e)

4628 4629
    def test_escaped_8bit_header(self):
        x = b'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big'
4630 4631
        e = x.decode('ascii', 'surrogateescape')
        h = Header(e, charset=email.charset.UNKNOWN8BIT)
4632 4633 4634 4635
        self.assertEqual(str(h),
                        'Ynwp4dUEbay Auction Semiar- No Charge \uFFFD Earn Big')
        self.assertEqual(email.header.decode_header(h), [(x, 'unknown-8bit')])

4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650
    def test_header_handles_binary_unknown8bit(self):
        x = b'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big'
        h = Header(x, charset=email.charset.UNKNOWN8BIT)
        self.assertEqual(str(h),
                        'Ynwp4dUEbay Auction Semiar- No Charge \uFFFD Earn Big')
        self.assertEqual(email.header.decode_header(h), [(x, 'unknown-8bit')])

    def test_make_header_handles_binary_unknown8bit(self):
        x = b'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big'
        h = Header(x, charset=email.charset.UNKNOWN8BIT)
        h2 = email.header.make_header(email.header.decode_header(h))
        self.assertEqual(str(h2),
                        'Ynwp4dUEbay Auction Semiar- No Charge \uFFFD Earn Big')
        self.assertEqual(email.header.decode_header(h2), [(x, 'unknown-8bit')])

4651 4652 4653 4654 4655 4656
    def test_modify_returned_list_does_not_change_header(self):
        h = Header('test')
        chunks = email.header.decode_header(h)
        chunks.append(('ascii', 'test2'))
        self.assertEqual(str(h), 'test')

4657 4658 4659 4660 4661 4662 4663 4664 4665 4666
    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)

4667
    def test_whitespace_keeper(self):
4668 4669 4670
        eq = self.assertEqual
        s = 'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztk=?= =?koi8-r?q?=CA?= zz.'
        parts = decode_header(s)
4671
        eq(parts, [(b'Subject: ', None), (b'\xf0\xd2\xcf\xd7\xc5\xd2\xcb\xc1 \xce\xc1 \xc6\xc9\xce\xc1\xcc\xd8\xce\xd9\xca', 'koi8-r'), (b' zz.', None)])
4672 4673 4674 4675 4676 4677
        hdr = make_header(parts)
        eq(hdr.encode(),
           'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztnK?= zz.')

    def test_broken_base64_header(self):
        raises = self.assertRaises
4678
        s = 'Subject: =?EUC-KR?B?CSixpLDtKSC/7Liuvsax4iC6uLmwMcijIKHaILzSwd/H0SC8+LCjwLsgv7W/+Mj3I ?='
4679 4680
        raises(errors.HeaderParseError, decode_header, s)

4681 4682 4683 4684
    def test_shift_jis_charset(self):
        h = Header('文', charset='shift_jis')
        self.assertEqual(h.encode(), '=?iso-2022-jp?b?GyRCSjgbKEI=?=')

4685 4686 4687 4688 4689 4690 4691
    def test_flatten_header_with_no_value(self):
        # Issue 11401 (regression from email 4.x)  Note that the space after
        # the header doesn't reflect the input, but this is also the way
        # email 4.x behaved.  At some point it would be nice to fix that.
        msg = email.message_from_string("EmptyHeader:")
        self.assertEqual(str(msg), "EmptyHeader: \n\n")

4692 4693 4694 4695 4696
    def test_encode_preserves_leading_ws_on_value(self):
        msg = Message()
        msg['SomeHeader'] = '   value with leading ws'
        self.assertEqual(str(msg), "SomeHeader:    value with leading ws\n\n")

4697

4698

4699 4700
# Test RFC 2231 header parameters (en/de)coding
class TestRFC2231(TestEmailBase):
4701 4702 4703

    # test_headerregistry.TestContentTypeHeader.rfc2231_encoded_with_double_quotes
    # test_headerregistry.TestContentTypeHeader.rfc2231_single_quote_inside_double_quotes
4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738
    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.ndiffAssertEqual
        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')
        eq(msg.as_string(maxheaderlen=78), """\
Return-Path: <bbb@zzz.org>
Delivered-To: bbb@zzz.org
Received: by mail.zzz.org (Postfix, from userid 889)
\tid 27CEAD38CC; Fri,  4 May 2001 14:05:44 -0400 (EDT)
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Message-ID: <15090.61304.110929.45684@aaa.zzz.org>
From: bbb@ddd.com (John X. Doe)
To: bbb@zzz.org
Subject: This is a test message
Date: Fri, 4 May 2001 14:05:44 -0400
Content-Type: text/plain; charset=us-ascii;
4739
 title*=us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21
4740 4741 4742 4743 4744 4745 4746 4747 4748


Hi,

Do you like this message?

-Me
""")

4749 4750 4751 4752 4753 4754 4755 4756 4757 4758
    def test_set_param_requote(self):
        msg = Message()
        msg.set_param('title', 'foo')
        self.assertEqual(msg['content-type'], 'text/plain; title="foo"')
        msg.set_param('title', 'bar', requote=False)
        self.assertEqual(msg['content-type'], 'text/plain; title=bar')
        # tspecial is still quoted.
        msg.set_param('title', "(bar)bell", requote=False)
        self.assertEqual(msg['content-type'], 'text/plain; title="(bar)bell"')

4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778
    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(maxheaderlen=78), """\
Return-Path: <bbb@zzz.org>
Delivered-To: bbb@zzz.org
Received: by mail.zzz.org (Postfix, from userid 889)
\tid 27CEAD38CC; Fri,  4 May 2001 14:05:44 -0400 (EDT)
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Message-ID: <15090.61304.110929.45684@aaa.zzz.org>
From: bbb@ddd.com (John X. Doe)
To: bbb@zzz.org
Subject: This is a test message
Date: Fri, 4 May 2001 14:05:44 -0400
Content-Type: text/plain; charset="us-ascii";
4779
 title*=us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21
4780 4781 4782 4783 4784 4785 4786 4787 4788


Hi,

Do you like this message?

-Me
""")

4789 4790 4791
    # test_headerregistry.TestContentTypeHeader.rfc2231_encoded_charset
    # I changed the charset name, though, because the one in the file isn't
    # a legal charset name.  Should add a test for an illegal charset.
4792 4793 4794 4795 4796
    def test_rfc2231_get_content_charset(self):
        eq = self.assertEqual
        msg = self._msgobj('msg_32.txt')
        eq(msg.get_content_charset(), 'us-ascii')

4797
    # test_headerregistry.TestContentTypeHeader.rfc2231_encoded_no_double_quotes
4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810
    def test_rfc2231_parse_rfc_quoting(self):
        m = textwrap.dedent('''\
            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')
        self.assertEqual(m, msg.as_string())

4811
    # test_headerregistry.TestContentTypeHeader.rfc2231_encoded_with_double_quotes
4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824
    def test_rfc2231_parse_extra_quoting(self):
        m = textwrap.dedent('''\
            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')
        self.assertEqual(m, msg.as_string())

4825 4826 4827
    # test_headerregistry.TestContentTypeHeader.rfc2231_no_language_or_charset
    # but new test uses *0* because otherwise lang/charset is not valid.
    # test_headerregistry.TestContentTypeHeader.rfc2231_segmented_normal_values
4828 4829 4830 4831 4832 4833 4834 4835 4836
    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')
4837
        self.assertFalse(isinstance(param, tuple))
4838 4839 4840 4841
        self.assertEqual(
            param,
            'file____C__DOCUMENTS_20AND_20SETTINGS_FABIEN_LOCAL_20SETTINGS_TEMP_nsmail.htm')

4842
    # test_headerregistry.TestContentTypeHeader.rfc2231_encoded_no_charset
4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854
    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')

4855
    # Duplicate of previous test?
4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867
    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')

4868 4869
    # test_headerregistry.TestContentTypeHeader.rfc2231_partly_encoded,
    # but the test below is wrong (the first part should be decoded).
4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920
    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')

4921
    # test_headerregistry.TestContentTypeHeader.rfc2231_unknown_charset_treated_as_ascii
4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987
    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(),
                         '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")

4988
    # test_headerregistry.TestContentTypeHeader.rfc2231_single_quote_inside_double_quotes
4989 4990 4991 4992 4993 4994 4995
    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')
4996
        self.assertFalse(isinstance(param, tuple))
4997 4998
        self.assertEqual(param, "Frank's Document")

4999
    # test_headerregistry.TestContentTypeHeader.rfc2231_single_quote_in_value_with_charset_and_lang
5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012
    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")

5013
    # test_headerregistry.TestContentTypeHeader.rfc2231_single_quote_in_non_encoded_value
5014 5015 5016 5017 5018 5019 5020 5021
    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')
5022
        self.assertFalse(isinstance(param, tuple))
5023 5024
        self.assertEqual(param, "us-ascii'en-us'Frank's Document")

5025
    # test_headerregistry.TestContentTypeHeader.rfc2231_single_quotes_inside_quotes
5026 5027 5028 5029 5030 5031 5032 5033 5034
    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")

5035
    # test_headerregistry.TestContentTypeHeader.rfc2231_encoded_then_unencoded_segments
5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050
    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')

5051 5052
    # test_headerregistry.TestContentTypeHeader.rfc2231_unencoded_then_encoded_segments
    # test_headerregistry.TestContentTypeHeader.rfc2231_quoted_unencoded_then_encoded_segments
5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068
    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')


5069

5070 5071 5072 5073 5074 5075
# 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):
5076
        with openfile(filename) as fp:
5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106
            original = fp.read()
            msg = email.message_from_string(original)
        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_as_string_maxheaderlen(self):
        original, msg = self._msg_and_obj('msg_45.txt')
        result = msg.as_string(maxheaderlen=60)
        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)


5107

5108
if __name__ == '__main__':
5109
    unittest.main()