| 1 |
import unittest |
| 2 |
from email import _encoded_words as _ew |
| 3 |
from email import errors |
| 4 |
from test.test_email import TestEmailBase |
| 5 |
|
| 6 |
|
| 7 |
class TestDecodeQ(TestEmailBase): |
| 8 |
|
| 9 |
def _test(self, source, ex_result, ex_defects=[]): |
| 10 |
result, defects = _ew.decode_q(source) |
| 11 |
self.assertEqual(result, ex_result) |
| 12 |
self.assertDefectsEqual(defects, ex_defects) |
| 13 |
|
| 14 |
def test_no_encoded(self): |
| 15 |
self._test(b'foobar', b'foobar') |
| 16 |
|
| 17 |
def test_spaces(self): |
| 18 |
self._test(b'foo=20bar=20', b'foo bar ') |
| 19 |
self._test(b'foo_bar_', b'foo bar ') |
| 20 |
|
| 21 |
def test_run_of_encoded(self): |
| 22 |
self._test(b'foo=20=20=21=2Cbar', b'foo !,bar') |
| 23 |
|
| 24 |
|
| 25 |
class TestDecodeB(TestEmailBase): |
| 26 |
|
| 27 |
def _test(self, source, ex_result, ex_defects=[]): |
| 28 |
result, defects = _ew.decode_b(source) |
| 29 |
self.assertEqual(result, ex_result) |
| 30 |
self.assertDefectsEqual(defects, ex_defects) |
| 31 |
|
| 32 |
def test_simple(self): |
| 33 |
self._test(b'Zm9v', b'foo') |
| 34 |
|
| 35 |
def test_missing_padding(self): |
| 36 |
# 1 missing padding character |
| 37 |
self._test(b'dmk', b'vi', [errors.InvalidBase64PaddingDefect]) |
| 38 |
# 2 missing padding characters |
| 39 |
self._test(b'dg', b'v', [errors.InvalidBase64PaddingDefect]) |
| 40 |
|
| 41 |
def test_invalid_character(self): |
| 42 |
self._test(b'dm\x01k===', b'vi', [errors.InvalidBase64CharactersDefect]) |
| 43 |
|
| 44 |
def test_invalid_character_and_bad_padding(self): |
| 45 |
self._test(b'dm\x01k', b'vi', [errors.InvalidBase64CharactersDefect, |
| 46 |
errors.InvalidBase64PaddingDefect]) |
| 47 |
|
| 48 |
def test_invalid_length(self): |
| 49 |
self._test(b'abcde', b'abcde', [errors.InvalidBase64LengthDefect]) |
| 50 |
|
| 51 |
|
| 52 |
class TestDecode(TestEmailBase): |
| 53 |
|
| 54 |
def test_wrong_format_input_raises(self): |
| 55 |
with self.assertRaises(ValueError): |
| 56 |
_ew.decode('=?badone?=') |
| 57 |
with self.assertRaises(ValueError): |
| 58 |
_ew.decode('=?') |
| 59 |
with self.assertRaises(ValueError): |
| 60 |
_ew.decode('') |
| 61 |
with self.assertRaises(KeyError): |
| 62 |
_ew.decode('=?utf-8?X?somevalue?=') |
| 63 |
|
| 64 |
def _test(self, source, result, charset='us-ascii', lang='', defects=[]): |
| 65 |
res, char, l, d = _ew.decode(source) |
| 66 |
self.assertEqual(res, result) |
| 67 |
self.assertEqual(char, charset) |
| 68 |
self.assertEqual(l, lang) |
| 69 |
self.assertDefectsEqual(d, defects) |
| 70 |
|
| 71 |
def test_simple_q(self): |
| 72 |
self._test('=?us-ascii?q?foo?=', 'foo') |
| 73 |
|
| 74 |
def test_simple_b(self): |
| 75 |
self._test('=?us-ascii?b?dmk=?=', 'vi') |
| 76 |
|
| 77 |
def test_q_case_ignored(self): |
| 78 |
self._test('=?us-ascii?Q?foo?=', 'foo') |
| 79 |
|
| 80 |
def test_b_case_ignored(self): |
| 81 |
self._test('=?us-ascii?B?dmk=?=', 'vi') |
| 82 |
|
| 83 |
def test_non_trivial_q(self): |
| 84 |
self._test('=?latin-1?q?=20F=fcr=20Elise=20?=', ' Für Elise ', 'latin-1') |
| 85 |
|
| 86 |
def test_q_escaped_bytes_preserved(self): |
| 87 |
self._test(b'=?us-ascii?q?=20\xACfoo?='.decode('us-ascii', |
| 88 |
'surrogateescape'), |
| 89 |
' \uDCACfoo', |
| 90 |
defects = [errors.UndecodableBytesDefect]) |
| 91 |
|
| 92 |
def test_b_undecodable_bytes_ignored_with_defect(self): |
| 93 |
self._test(b'=?us-ascii?b?dm\xACk?='.decode('us-ascii', |
| 94 |
'surrogateescape'), |
| 95 |
'vi', |
| 96 |
defects = [ |
| 97 |
errors.InvalidBase64CharactersDefect, |
| 98 |
errors.InvalidBase64PaddingDefect]) |
| 99 |
|
| 100 |
def test_b_invalid_bytes_ignored_with_defect(self): |
| 101 |
self._test('=?us-ascii?b?dm\x01k===?=', |
| 102 |
'vi', |
| 103 |
defects = [errors.InvalidBase64CharactersDefect]) |
| 104 |
|
| 105 |
def test_b_invalid_bytes_incorrect_padding(self): |
| 106 |
self._test('=?us-ascii?b?dm\x01k?=', |
| 107 |
'vi', |
| 108 |
defects = [ |
| 109 |
errors.InvalidBase64CharactersDefect, |
| 110 |
errors.InvalidBase64PaddingDefect]) |
| 111 |
|
| 112 |
def test_b_padding_defect(self): |
| 113 |
self._test('=?us-ascii?b?dmk?=', |
| 114 |
'vi', |
| 115 |
defects = [errors.InvalidBase64PaddingDefect]) |
| 116 |
|
| 117 |
def test_nonnull_lang(self): |
| 118 |
self._test('=?us-ascii*jive?q?test?=', 'test', lang='jive') |
| 119 |
|
| 120 |
def test_unknown_8bit_charset(self): |
| 121 |
self._test('=?unknown-8bit?q?foo=ACbar?=', |
| 122 |
b'foo\xacbar'.decode('ascii', 'surrogateescape'), |
| 123 |
charset = 'unknown-8bit', |
| 124 |
defects = []) |
| 125 |
|
| 126 |
def test_unknown_charset(self): |
| 127 |
self._test('=?foobar?q?foo=ACbar?=', |
| 128 |
b'foo\xacbar'.decode('ascii', 'surrogateescape'), |
| 129 |
charset = 'foobar', |
| 130 |
# XXX Should this be a new Defect instead? |
| 131 |
defects = [errors.CharsetError]) |
| 132 |
|
| 133 |
def test_invalid_character_in_charset(self): |
| 134 |
self._test('=?utf-8\udce2\udc80\udc9d?q?foo=ACbar?=', |
| 135 |
b'foo\xacbar'.decode('ascii', 'surrogateescape'), |
| 136 |
charset = 'utf-8\udce2\udc80\udc9d', |
| 137 |
# XXX Should this be a new Defect instead? |
| 138 |
defects = [errors.CharsetError]) |
| 139 |
|
| 140 |
def test_q_nonascii(self): |
| 141 |
self._test('=?utf-8?q?=C3=89ric?=', |
| 142 |
'Éric', |
| 143 |
charset='utf-8') |
| 144 |
|
| 145 |
|
| 146 |
class TestEncodeQ(TestEmailBase): |
| 147 |
|
| 148 |
def _test(self, src, expected): |
| 149 |
self.assertEqual(_ew.encode_q(src), expected) |
| 150 |
|
| 151 |
def test_all_safe(self): |
| 152 |
self._test(b'foobar', 'foobar') |
| 153 |
|
| 154 |
def test_spaces(self): |
| 155 |
self._test(b'foo bar ', 'foo_bar_') |
| 156 |
|
| 157 |
def test_run_of_encodables(self): |
| 158 |
self._test(b'foo ,,bar', 'foo__=2C=2Cbar') |
| 159 |
|
| 160 |
|
| 161 |
class TestEncodeB(TestEmailBase): |
| 162 |
|
| 163 |
def test_simple(self): |
| 164 |
self.assertEqual(_ew.encode_b(b'foo'), 'Zm9v') |
| 165 |
|
| 166 |
def test_padding(self): |
| 167 |
self.assertEqual(_ew.encode_b(b'vi'), 'dmk=') |
| 168 |
|
| 169 |
|
| 170 |
class TestEncode(TestEmailBase): |
| 171 |
|
| 172 |
def test_q(self): |
| 173 |
self.assertEqual(_ew.encode('foo', 'utf-8', 'q'), '=?utf-8?q?foo?=') |
| 174 |
|
| 175 |
def test_b(self): |
| 176 |
self.assertEqual(_ew.encode('foo', 'utf-8', 'b'), '=?utf-8?b?Zm9v?=') |
| 177 |
|
| 178 |
def test_auto_q(self): |
| 179 |
self.assertEqual(_ew.encode('foo', 'utf-8'), '=?utf-8?q?foo?=') |
| 180 |
|
| 181 |
def test_auto_q_if_short_mostly_safe(self): |
| 182 |
self.assertEqual(_ew.encode('vi.', 'utf-8'), '=?utf-8?q?vi=2E?=') |
| 183 |
|
| 184 |
def test_auto_b_if_enough_unsafe(self): |
| 185 |
self.assertEqual(_ew.encode('.....', 'utf-8'), '=?utf-8?b?Li4uLi4=?=') |
| 186 |
|
| 187 |
def test_auto_b_if_long_unsafe(self): |
| 188 |
self.assertEqual(_ew.encode('vi.vi.vi.vi.vi.', 'utf-8'), |
| 189 |
'=?utf-8?b?dmkudmkudmkudmkudmku?=') |
| 190 |
|
| 191 |
def test_auto_q_if_long_mostly_safe(self): |
| 192 |
self.assertEqual(_ew.encode('vi vi vi.vi ', 'utf-8'), |
| 193 |
'=?utf-8?q?vi_vi_vi=2Evi_?=') |
| 194 |
|
| 195 |
def test_utf8_default(self): |
| 196 |
self.assertEqual(_ew.encode('foo'), '=?utf-8?q?foo?=') |
| 197 |
|
| 198 |
def test_lang(self): |
| 199 |
self.assertEqual(_ew.encode('foo', lang='jive'), '=?utf-8*jive?q?foo?=') |
| 200 |
|
| 201 |
def test_unknown_8bit(self): |
| 202 |
self.assertEqual(_ew.encode('foo\uDCACbar', charset='unknown-8bit'), |
| 203 |
'=?unknown-8bit?q?foo=ACbar?=') |
| 204 |
|
| 205 |
|
| 206 |
if __name__ == '__main__': |
| 207 |
unittest.main() |