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
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
|
# -*- coding: utf-8 -*-
"""Tests of Beautiful Soup as a whole."""
import unittest
from bs4.element import SoupStrainer
from bs4.dammit import EntitySubstitution, UnicodeDammit
from bs4.testing import SoupTest
class TestSelectiveParsing(SoupTest):
def test_parse_with_soupstrainer(self):
markup = "No<b>Yes</b><a>No<b>Yes <c>Yes</c></b>"
strainer = SoupStrainer("b")
soup = self.soup(markup, parse_only=strainer)
self.assertEquals(soup.encode(), "<b>Yes</b><b>Yes <c>Yes</c></b>")
class TestEntitySubstitution(unittest.TestCase):
"""Standalone tests of the EntitySubstitution class."""
def setUp(self):
self.sub = EntitySubstitution
def test_simple_html_substitution(self):
# Unicode characters corresponding to named HTML entites
# are substituted, and no others.
s = u"foo\u2200\N{SNOWMAN}\u00f5bar"
self.assertEquals(self.sub.substitute_html(s),
u"foo∀\N{SNOWMAN}õbar")
def test_smart_quote_substitution(self):
# MS smart quotes are a common source of frustration, so we
# give them a special test.
quotes = "\x91\x92foo\x93\x94"
dammit = UnicodeDammit(quotes)
self.assertEquals(self.sub.substitute_html(dammit.markup),
"‘’foo“”")
def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
s = 'Welcome to "my bar"'
self.assertEquals(self.sub.substitute_xml(s, False), s)
def test_xml_attribute_quoting_normally_uses_double_quotes(self):
self.assertEquals(self.sub.substitute_xml("Welcome", True),
'"Welcome"')
self.assertEquals(self.sub.substitute_xml("Bob's Bar", True),
'"Bob\'s Bar"')
def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
s = 'Welcome to "my bar"'
self.assertEquals(self.sub.substitute_xml(s, True),
"'Welcome to \"my bar\"'")
def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
s = 'Welcome to "Bob\'s Bar"'
self.assertEquals(
self.sub.substitute_xml(s, True),
'"Welcome to "Bob\'s Bar""')
def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
quoted = 'Welcome to "Bob\'s Bar"'
self.assertEquals(self.sub.substitute_xml(quoted), quoted)
def test_xml_quoting_handles_angle_brackets(self):
self.assertEquals(
self.sub.substitute_xml("foo<bar>"),
"foo<bar>")
def test_xml_quoting_handles_ampersands(self):
self.assertEquals(self.sub.substitute_xml("AT&T"), "AT&T")
def test_xml_quoting_ignores_ampersands_when_they_are_part_of_an_entity(self):
self.assertEquals(
self.sub.substitute_xml("ÁT&T"),
"ÁT&T")
def test_quotes_not_html_substituted(self):
"""There's no need to do this except inside attribute values."""
text = 'Bob\'s "bar"'
self.assertEquals(self.sub.substitute_html(text), text)
class TestUnicodeDammit(unittest.TestCase):
"""Standalone tests of Unicode, Dammit."""
def test_smart_quotes_to_unicode(self):
markup = "<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup)
self.assertEquals(
dammit.unicode, u"<foo>\u2018\u2019\u201c\u201d</foo>")
def test_smart_quotes_to_xml_entities(self):
markup = "<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="xml")
self.assertEquals(
dammit.unicode, "<foo>‘’“”</foo>")
def test_smart_quotes_to_html_entities(self):
markup = "<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="html")
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.original_encoding, 'utf-8')
def test_convert_hebrew(self):
hebrew = "\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
self.assertEquals(dammit.original_encoding, '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.original_encoding, '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-8859-8"])
self.assertEquals(dammit.original_encoding, '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.original_encoding, 'utf-8')
|
