1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
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
|
# -*- coding: utf-8 -*-
"""Tests of Beautiful Soup as a whole."""
import unittest
from helpers import SoupTest
from beautifulsoup.dammit import UnicodeDammit
class TestEncodingConversion(SoupTest):
# Test Beautiful Soup's ability to decode and encode from various
# encodings.
def setUp(self):
super(TestEncodingConversion, self).setUp()
self.unicode_data = u"<html><body><foo>\xe9</foo></body></html>"
self.utf8_data = self.unicode_data.encode("utf-8")
self.assertEqual(
self.utf8_data, "<html><body><foo>\xc3\xa9</foo></body></html>")
def test_ascii_in_unicode_out(self):
# ASCII input is converted to Unicode. The originalEncoding
# attribute is set.
ascii = "<foo>a</foo>"
soup_from_ascii = self.soup(ascii)
unicode_output = soup_from_ascii.decode()
self.assertTrue(isinstance(unicode_output, unicode))
self.assertEquals(unicode_output, self.document_for(ascii))
self.assertEquals(soup_from_ascii.originalEncoding, "ascii")
def test_unicode_in_unicode_out(self):
# Unicode input is left alone. The originalEncoding attribute
# is not set.
soup_from_unicode = self.soup(self.unicode_data)
self.assertEquals(soup_from_unicode.decode(), self.unicode_data)
self.assertEquals(soup_from_unicode.foo.string, u'\xe9')
self.assertEquals(soup_from_unicode.originalEncoding, None)
def test_utf8_in_unicode_out(self):
# UTF-8 input is converted to Unicode. The originalEncoding
# attribute is set.
soup_from_utf8 = self.soup(self.utf8_data)
self.assertEquals(soup_from_utf8.decode(), self.unicode_data)
self.assertEquals(soup_from_utf8.foo.string, u'\xe9')
def test_utf8_out(self):
# The internal data structures can be encoded as UTF-8.
soup_from_unicode = self.soup(self.unicode_data)
self.assertEquals(soup_from_unicode.encode('utf-8'), self.utf8_data)
class TestUnicodeDammit(unittest.TestCase):
"""Standalone tests of Unicode, Dammit."""
def test_smart_quote_replacement(self):
markup = "<foo>\x92</foo>"
dammit = UnicodeDammit(markup)
self.assertEquals(dammit.unicode, "<foo>’</foo>")
def test_detect_utf8(self):
utf8 = "\xc3\xa9"
dammit = UnicodeDammit(utf8)
self.assertEquals(dammit.unicode, u'\xe9')
self.assertEquals(dammit.originalEncoding, 'utf-8')
def test_convert_hebrew(self):
hebrew = "\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
self.assertEquals(dammit.originalEncoding, 'iso-8859-8')
self.assertEquals(dammit.unicode, u'\u05dd\u05d5\u05dc\u05e9')
def test_dont_see_smart_quotes_where_there_are_none(self):
utf_8 = "\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
dammit = UnicodeDammit(utf_8)
self.assertEquals(dammit.originalEncoding, 'utf-8')
self.assertEquals(dammit.unicode.encode("utf-8"), utf_8)
def test_ignore_inappropriate_codecs(self):
utf8_data = u"Räksmörgås".encode("utf-8")
dammit = UnicodeDammit(utf8_data, ["iso-8859-1"])
self.assertEquals(dammit.originalEncoding, 'utf-8')
def test_ignore_invalid_codecs(self):
utf8_data = u"Räksmörgås".encode("utf-8")
for bad_encoding in ['.utf8', '...', 'utF---16.!']:
dammit = UnicodeDammit(utf8_data, [bad_encoding])
self.assertEquals(dammit.originalEncoding, 'utf-8')
|
