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
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
|
# -*- coding: utf-8 -*-
# frozen_string_literal: true
require "helper"
class TestNokogiriHtmlDocument < Nokogiri::TestCase
describe "Nokogiri::HTML::Document" do
describe "Encoding" do
def test_encoding
doc = Nokogiri::HTML(File.open(SHIFT_JIS_HTML, "rb"))
hello = "こんにちは"
assert_match(doc.encoding, doc.to_html)
assert_match(hello.encode("Shift_JIS"), doc.to_html)
assert_equal("Shift_JIS", doc.to_html.encoding.name)
assert_match(hello, doc.to_html(encoding: "UTF-8"))
assert_match("UTF-8", doc.to_html(encoding: "UTF-8"))
assert_match("UTF-8", doc.to_html(encoding: "UTF-8").encoding.name)
end
def test_encoding_without_charset
doc = Nokogiri::HTML(File.open(SHIFT_JIS_NO_CHARSET, "r:Shift_JIS:Shift_JIS").read)
hello = "こんにちは"
assert_match(hello, doc.content)
assert_match(hello, doc.to_html(encoding: "UTF-8"))
assert_match("UTF-8", doc.to_html(encoding: "UTF-8").encoding.name)
end
def test_default_to_encoding_from_string
bad_charset = <<~eohtml
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=charset=UTF-8">
</head>
<body>
<a href="http://tenderlovemaking.com/">blah!</a>
</body>
</html>
eohtml
doc = Nokogiri::HTML(bad_charset)
assert_equal(bad_charset.encoding.name, doc.encoding)
doc = Nokogiri.parse(bad_charset)
assert_equal(bad_charset.encoding.name, doc.encoding)
end
def test_encoding_non_utf8
orig = "日本語が上手です"
bin = Encoding::ASCII_8BIT
[Encoding::Shift_JIS, Encoding::EUC_JP].each do |enc|
html = <<~eohtml.encode(enc)
<html>
<meta http-equiv="Content-Type" content="text/html; charset=#{enc.name}">
<title xml:lang="ja">#{orig}</title></html>
eohtml
text = Nokogiri::HTML.parse(html).at("title").inner_text
assert_equal(
orig.encode(enc).force_encoding(bin),
text.encode(enc).force_encoding(bin)
)
end
end
def test_encoding_with_a_bad_name
bad_charset = <<~eohtml
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=charset=UTF-8">
</head>
<body>
<a href="http://tenderlovemaking.com/">blah!</a>
</body>
</html>
eohtml
doc = Nokogiri::HTML(bad_charset, nil, "askldjfhalsdfjhlkasdfjh")
assert_equal(["http://tenderlovemaking.com/"],
doc.css("a").map { |a| a["href"] })
end
def test_empty_doc_encoding
encoding = "US-ASCII"
assert_equal(encoding, Nokogiri::HTML.parse(nil, nil, encoding).encoding)
end
describe "Detection" do
def binread(file)
File.binread(file)
end
def binopen(file)
File.open(file, "rb")
end
it "handles both memory and IO" do
from_stream = Nokogiri::HTML(binopen(NOENCODING_FILE))
from_string = Nokogiri::HTML(binread(NOENCODING_FILE))
assert_equal(from_string.to_s.size, from_stream.to_s.size)
assert_operator(from_string.to_s.size, :>, 0)
end
it "uses meta charset encoding when present" do
html = Nokogiri::HTML(binopen(METACHARSET_FILE))
assert_equal("iso-2022-jp", html.encoding)
assert_equal("たこ焼き仮面", html.title)
end
{ "xhtml" => ENCODING_XHTML_FILE, "html" => ENCODING_HTML_FILE }.each do |flavor, file|
it "detects #{flavor} document encoding" do
doc_from_string_enc = Nokogiri::HTML(binread(file), nil, "Shift_JIS")
ary_from_string_enc = doc_from_string_enc.xpath("//p/text()").map(&:text)
doc_from_string = Nokogiri::HTML(binread(file))
ary_from_string = doc_from_string.xpath("//p/text()").map(&:text)
doc_from_file_enc = Nokogiri::HTML(binopen(file), nil, "Shift_JIS")
ary_from_file_enc = doc_from_file_enc.xpath("//p/text()").map(&:text)
doc_from_file = Nokogiri::HTML(binopen(file))
ary_from_file = doc_from_file.xpath("//p/text()").map(&:text)
title = "たこ焼き仮面"
assert_equal(title, doc_from_string_enc.at("//title/text()").text)
assert_equal(title, doc_from_string.at("//title/text()").text)
assert_equal(title, doc_from_file_enc.at("//title/text()").text)
assert_equal(title, doc_from_file.at("//title/text()").text)
evil = (0..72).map { |i| "超" * i + "悪い事を構想中。" }
assert_equal(evil, ary_from_string_enc)
assert_equal(evil, ary_from_string)
next unless !Nokogiri.uses_libxml? || Nokogiri::VersionInfo.instance.libxml2_has_iconv?
# libxml2 without iconv does not pass this test
assert_equal(evil, ary_from_file_enc)
assert_equal(evil, ary_from_file)
end
end
describe "error handling" do
RAW = "<html><body><div"
{ "read_memory" => RAW, "read_io" => StringIO.new(RAW) }.each do |flavor, input|
it "#{flavor} should handle errors" do
doc = Nokogiri::HTML.parse(input)
assert_operator(doc.errors.length, :>, 0)
end
end
end
it "does not start backtracking during detection of XHTML encoding" do
# this test is a quick and dirty version
# of the more complete perf test that is on main.
n = 40_000
redos_string = "<?xml " + (" " * n)
redos_string.encode!("ASCII-8BIT")
start_time = Time.now
Nokogiri::HTML4(redos_string)
elapsed_time = Time.now - start_time
assert_operator(elapsed_time, :<, 1)
end
end
end
end
end
|
