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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
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
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
|
# -*- coding: utf-8 -*-
require "helper"
module Nokogiri
module HTML
class TestDocumentFragment < Nokogiri::TestCase
def setup
super
@html = Nokogiri::HTML.parse(File.read(HTML_FILE), HTML_FILE)
end
def test_ascii_8bit_encoding
s = String.new 'hello'
s.force_encoding ::Encoding::ASCII_8BIT
assert_equal "hello", Nokogiri::HTML::DocumentFragment.parse(s).to_html
end
def test_inspect_encoding
fragment = "<div>こんにちは！</div>".encode('EUC-JP')
f = Nokogiri::HTML::DocumentFragment.parse fragment
assert_equal "こんにちは！", f.content
end
def test_html_parse_encoding
fragment = "<div>こんにちは！</div>".encode 'EUC-JP'
f = Nokogiri::HTML.fragment fragment
assert_equal 'EUC-JP', f.document.encoding
assert_equal "こんにちは！", f.content
end
def test_unlink_empty_document
frag = Nokogiri::HTML::DocumentFragment.parse('').unlink # must_not_raise
assert_nil frag.parent
end
def test_colons_are_not_removed
doc = Nokogiri::HTML::DocumentFragment.parse("<span>3:30pm</span>")
assert_match(/3:30/, doc.to_s)
end
def test_parse_encoding
fragment = "<div>hello world</div>"
f = Nokogiri::HTML::DocumentFragment.parse fragment, 'ISO-8859-1'
assert_equal 'ISO-8859-1', f.document.encoding
assert_equal "hello world", f.content
end
def test_html_parse_with_encoding
fragment = "<div>hello world</div>"
f = Nokogiri::HTML.fragment fragment, 'ISO-8859-1'
assert_equal 'ISO-8859-1', f.document.encoding
assert_equal "hello world", f.content
end
def test_parse_in_context
assert_equal('<br>', @html.root.parse('<br />').to_s)
end
def test_inner_html=
fragment = Nokogiri::HTML.fragment '<hr />'
fragment.inner_html = "hello"
assert_equal 'hello', fragment.inner_html
end
def test_ancestors_search
html = %q{
<div>
<ul>
<li>foo</li>
</ul>
</div>
}
fragment = Nokogiri::HTML.fragment html
li = fragment.at('li')
assert li.matches?('li')
end
def test_fun_encoding
string = %Q(<body>こんにちは</body>)
html = Nokogiri::HTML::DocumentFragment.parse(
string
).to_html(:encoding => 'UTF-8')
assert_equal string, html
end
def test_new
assert Nokogiri::HTML::DocumentFragment.new(@html)
end
def test_body_fragment_should_contain_body
fragment = Nokogiri::HTML::DocumentFragment.parse(" <body><div>foo</div></body>")
assert_match(/^<body>/, fragment.to_s)
end
def test_nonbody_fragment_should_not_contain_body
fragment = Nokogiri::HTML::DocumentFragment.parse("<div>foo</div>")
assert_match(/^<div>/, fragment.to_s)
end
def test_fragment_should_have_document
fragment = Nokogiri::HTML::DocumentFragment.new(@html)
assert_equal @html, fragment.document
end
def test_empty_fragment_should_be_searchable_by_css
fragment = Nokogiri::HTML.fragment("")
assert_equal 0, fragment.css("a").size
end
def test_empty_fragment_should_be_searchable
fragment = Nokogiri::HTML.fragment("")
assert_equal 0, fragment.search("//a").size
end
def test_name
fragment = Nokogiri::HTML::DocumentFragment.new(@html)
assert_equal '#document-fragment', fragment.name
end
def test_static_method
fragment = Nokogiri::HTML::DocumentFragment.parse("<div>a</div>")
assert_instance_of Nokogiri::HTML::DocumentFragment, fragment
end
def test_many_fragments
100.times { Nokogiri::HTML::DocumentFragment.new(@html) }
end
def test_subclass
klass = Class.new(Nokogiri::HTML::DocumentFragment)
fragment = klass.new(@html, "<div>a</div>")
assert_instance_of klass, fragment
end
def test_subclass_parse
klass = Class.new(Nokogiri::HTML::DocumentFragment)
doc = klass.parse("<div>a</div>")
assert_instance_of klass, doc
end
def test_html_fragment
fragment = Nokogiri::HTML.fragment("<div>a</div>")
assert_equal "<div>a</div>", fragment.to_s
end
def test_html_fragment_has_outer_text
doc = "a<div>b</div>c"
fragment = Nokogiri::HTML::Document.new.fragment(doc)
if Nokogiri.uses_libxml?("<= 2.6.16")
assert_equal "a<div>b</div><p>c</p>", fragment.to_s
else
assert_equal "a<div>b</div>c", fragment.to_s
end
end
def test_html_fragment_case_insensitivity
doc = "<Div>b</Div>"
fragment = Nokogiri::HTML::Document.new.fragment(doc)
assert_equal "<div>b</div>", fragment.to_s
end
def test_html_fragment_with_leading_whitespace
doc = " <div>b</div> "
fragment = Nokogiri::HTML::Document.new.fragment(doc)
assert_match %r% <div>b</div> *%, fragment.to_s
end
def test_html_fragment_with_leading_whitespace_and_newline
doc = " \n<div>b</div> "
fragment = Nokogiri::HTML::Document.new.fragment(doc)
assert_match %r% \n<div>b</div> *%, fragment.to_s
end
def test_html_fragment_with_input_and_intermediate_whitespace
doc = "<label>Label</label><input type=\"text\"> <span>span</span>"
fragment = Nokogiri::HTML::Document.new.fragment(doc)
assert_equal "<label>Label</label><input type=\"text\"> <span>span</span>", fragment.to_s
end
def test_html_fragment_with_leading_text_and_newline
fragment = HTML::Document.new.fragment("First line\nSecond line<br>Broken line")
assert_equal fragment.to_s, "First line\nSecond line<br>Broken line"
end
def test_html_fragment_with_leading_whitespace_and_text_and_newline
fragment = HTML::Document.new.fragment(" First line\nSecond line<br>Broken line")
assert_equal " First line\nSecond line<br>Broken line", fragment.to_s
end
def test_html_fragment_with_leading_entity
failed = ""test<br/>test""
fragment = Nokogiri::HTML::DocumentFragment.parse(failed)
assert_equal '"test<br>test"', fragment.to_html
end
def test_to_s
doc = "<span>foo<br></span><span>bar</span>"
fragment = Nokogiri::HTML::Document.new.fragment(doc)
assert_equal "<span>foo<br></span><span>bar</span>", fragment.to_s
end
def test_to_html
doc = "<span>foo<br></span><span>bar</span>"
fragment = Nokogiri::HTML::Document.new.fragment(doc)
assert_equal "<span>foo<br></span><span>bar</span>", fragment.to_html
end
def test_to_xhtml
doc = "<span>foo<br></span><span>bar</span><p></p>"
fragment = Nokogiri::HTML::Document.new.fragment(doc)
if Nokogiri.jruby? || Nokogiri.uses_libxml?(">= 2.7.0")
assert_equal "<span>foo<br /></span><span>bar</span><p></p>", fragment.to_xhtml
else
# FIXME: why are we doing this ? this violates the spec,
# see http://www.w3.org/TR/xhtml1/#C_2
assert_equal "<span>foo<br></span><span>bar</span><p></p>", fragment.to_xhtml
end
end
def test_to_xml
doc = "<span>foo<br></span><span>bar</span>"
fragment = Nokogiri::HTML::Document.new.fragment(doc)
assert_equal "<span>foo<br/></span><span>bar</span>", fragment.to_xml
end
def test_fragment_script_tag_with_cdata
doc = HTML::Document.new
fragment = doc.fragment("<script>var foo = 'bar';</script>")
assert_equal("<script>var foo = 'bar';</script>",
fragment.to_s)
end
def test_fragment_with_comment
doc = HTML::Document.new
fragment = doc.fragment("<p>hello<!-- your ad here --></p>")
assert_equal("<p>hello<!-- your ad here --></p>",
fragment.to_s)
end
def test_element_children_counts
if Nokogiri.uses_libxml?("<= 2.9.1")
skip "#elements doesn't work in 2.9.1, see 1793a5a for history"
end
doc = Nokogiri::HTML::DocumentFragment.parse(" <div> </div>\n ")
assert_equal 1, doc.element_children.count
end
def test_malformed_fragment_is_corrected
fragment = HTML::DocumentFragment.parse("<div </div>")
assert_equal "<div></div>", fragment.to_s
end
def test_unclosed_script_tag
# see GH#315
fragment = HTML::DocumentFragment.parse("foo <script>bar")
assert_equal "foo <script>bar</script>", fragment.to_html
end
def test_error_propagation_on_fragment_parse
frag = Nokogiri::HTML::DocumentFragment.parse "<hello>oh, hello there.</hello>"
assert frag.errors.any?{|err| err.to_s =~ /Tag hello invalid/}, "errors should be copied to the fragment"
end
def test_error_propagation_on_fragment_parse_in_node_context
doc = Nokogiri::HTML::Document.parse "<html><body><div></div></body></html>"
context_node = doc.at_css "div"
frag = Nokogiri::HTML::DocumentFragment.new doc, "<hello>oh, hello there.</hello>", context_node
assert frag.errors.any?{|err| err.to_s =~ /Tag hello invalid/}, "errors should be on the context node's document"
end
def test_error_propagation_on_fragment_parse_in_node_context_should_not_include_preexisting_errors
doc = Nokogiri::HTML::Document.parse "<html><body><div></div><jimmy></jimmy></body></html>"
assert doc.errors.any?{|err| err.to_s =~ /jimmy/}, "assert on setup"
context_node = doc.at_css "div"
frag = Nokogiri::HTML::DocumentFragment.new doc, "<hello>oh, hello there.</hello>", context_node
assert frag.errors.any?{|err| err.to_s =~ /Tag hello invalid/}, "errors should be on the context node's document"
assert frag.errors.none?{|err| err.to_s =~ /jimmy/}, "errors should not include pre-existing document errors"
end
def test_capturing_nonparse_errors_during_fragment_clone
# see https://github.com/sparklemotion/nokogiri/issues/1196 for background
original = Nokogiri::HTML.fragment("<div id='unique'></div><div id='unique'></div>")
original_errors = original.errors.dup
copy = original.dup
assert_equal original_errors, copy.errors
end
def test_capturing_nonparse_errors_during_node_copy_between_fragments
# Errors should be emitted while parsing only, and should not change when moving nodes.
frag1 = Nokogiri::HTML.fragment("<diva id='unique'>one</diva>")
frag2 = Nokogiri::HTML.fragment("<dive id='unique'>two</dive>")
node1 = frag1.at_css("#unique")
node2 = frag2.at_css("#unique")
original_errors1 = frag1.errors.dup
original_errors2 = frag2.errors.dup
assert original_errors1.any?{|e| e.to_s =~ /Tag diva invalid/ }, "it should complain about the tag name"
assert original_errors2.any?{|e| e.to_s =~ /Tag dive invalid/ }, "it should complain about the tag name"
node1.add_child node2
assert_equal original_errors1, frag1.errors
assert_equal original_errors2, frag2.errors
end
def test_dup_should_create_an_html_document_fragment
# https://github.com/sparklemotion/nokogiri/issues/1846
original = Nokogiri::HTML::DocumentFragment.parse("<div><p>hello</p></div>")
duplicate = original.dup
assert_instance_of Nokogiri::HTML::DocumentFragment, duplicate
end
end
end
end
|
