File: test_document.rb

package info (click to toggle)
ruby-nokogiri 1.11.1%2Bdfsg-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 5,576 kB
  • sloc: xml: 28,086; ruby: 18,456; java: 13,067; ansic: 5,138; yacc: 265; sh: 208; makefile: 27
file content (809 lines) | stat: -rw-r--r-- 24,894 bytes parent folder | download
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
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
# frozen_string_literal: true
require "helper"

module Nokogiri
  module HTML
    class TestDocument < Nokogiri::TestCase
      let(:html) { Nokogiri::HTML.parse(File.read(HTML_FILE)) }

      def test_nil_css
        # Behavior is undefined but shouldn't break
        assert(html.css(nil))
        assert(html.xpath(nil))
      end

      def test_does_not_fail_with_illformatted_html
        doc = Nokogiri::HTML('"</html>";'.dup.force_encoding(Encoding::BINARY))
        assert_not_nil(doc)
      end

      def test_exceptions_remove_newlines
        errors = html.errors
        assert(errors.length > 0, "has errors")
        errors.each do |error|
          assert_equal(error.to_s.chomp, error.to_s)
        end
      end

      def test_fragment
        fragment = html.fragment
        assert_equal(0, fragment.children.length)
      end

      def test_document_takes_config_block
        options = nil
        Nokogiri::HTML(File.read(HTML_FILE), HTML_FILE) do |cfg|
          options = cfg
          options.nonet.nowarning.dtdattr
        end
        assert(options.nonet?)
        assert(options.nowarning?)
        assert(options.dtdattr?)
      end

      def test_parse_takes_config_block
        options = nil
        Nokogiri::HTML.parse(File.read(HTML_FILE), HTML_FILE) do |cfg|
          options = cfg
          options.nonet.nowarning.dtdattr
        end
        assert(options.nonet?)
        assert(options.nowarning?)
        assert(options.dtdattr?)
      end

      def test_subclass
        klass = Class.new(Nokogiri::HTML::Document)
        doc = klass.new
        assert_instance_of(klass, doc)
      end

      def test_subclass_initialize
        klass = Class.new(Nokogiri::HTML::Document) do
          attr_accessor :initialized_with

          def initialize(*args)
            @initialized_with = args
          end
        end
        doc = klass.new("uri", "external_id", 1)
        assert_equal(["uri", "external_id", 1], doc.initialized_with)
      end

      def test_subclass_dup
        klass = Class.new(Nokogiri::HTML::Document)
        doc = klass.new.dup
        assert_instance_of(klass, doc)
      end

      def test_subclass_parse
        klass = Class.new(Nokogiri::HTML::Document)
        doc = klass.parse(File.read(HTML_FILE))
        assert_equal(html.to_s, doc.to_s)
        assert_instance_of(klass, doc)
      end

      def test_document_parse_method
        html = Nokogiri::HTML::Document.parse(File.read(HTML_FILE))
        assert_equal(html.to_s, html.to_s)
      end

      def test_document_parse_method_with_url
        doc = Nokogiri::HTML("<html></html>", "http://foobar.example.com/", "UTF-8")
        refute_empty(doc.to_s, "Document should not be empty")
        assert_equal("http://foobar.example.com/", doc.url)
      end

      ###
      # Nokogiri::HTML returns an empty Document when given a blank string GH#11
      def test_empty_string_returns_empty_doc
        doc = Nokogiri::HTML("")
        assert_instance_of(Nokogiri::HTML::Document, doc)
        assert_nil(doc.root)
      end

      unless Nokogiri.uses_libxml?("~> 2.6.0")
        def test_to_xhtml_with_indent
          doc = Nokogiri::HTML("<html><body><a>foo</a></body></html>")
          doc = Nokogiri::HTML(doc.to_xhtml(indent: 2))
          assert_indent(2, doc)
        end

        def test_write_to_xhtml_with_indent
          io = StringIO.new
          doc = Nokogiri::HTML("<html><body><a>foo</a></body></html>")
          doc.write_xhtml_to(io, indent: 5)
          io.rewind
          doc = Nokogiri::HTML(io.read)
          assert_indent(5, doc)
        end
      end

      def test_swap_should_not_exist
        assert_raises(NoMethodError) do
          html.swap
        end
      end

      def test_namespace_should_not_exist
        assert_raises(NoMethodError) do
          html.namespace
        end
      end

      def test_meta_encoding
        assert_equal("UTF-8", html.meta_encoding)
      end

      def test_meta_encoding_is_strict_about_http_equiv
        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <meta http-equiv="X-Content-Type" content="text/html; charset=Shift_JIS">
            </head>
            <body>
              foo
            </body>
          </html>
        EOHTML
        assert_nil(doc.meta_encoding)
      end

      def test_meta_encoding_handles_malformed_content_charset
        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <meta http-equiv="Content-type" content="text/html; utf-8" />
            </head>
            <body>
              foo
            </body>
          </html>
        EOHTML
        assert_nil(doc.meta_encoding)
      end

      def test_meta_encoding_checks_charset
        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <meta charset="UTF-8">
            </head>
            <body>
              foo
            </body>
          </html>
        EOHTML
        assert_equal("UTF-8", doc.meta_encoding)
      end

      def test_meta_encoding=
        html.meta_encoding = "EUC-JP"
        assert_equal("EUC-JP", html.meta_encoding)
      end

      def test_title
        assert_equal("Tender Lovemaking  ", html.title)
        doc = Nokogiri::HTML("<html><body>foo</body></html>")
        assert_nil(doc.title)
      end

      def test_title=
        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <title>old</title>
            </head>
            <body>
              foo
            </body>
          </html>
        EOHTML
        doc.title = "new"
        assert_equal(1, doc.css("title").size)
        assert_equal("new", doc.title)

        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
            </head>
            <body>
              foo
            </body>
          </html>
        EOHTML
        doc.title = "new"
        assert_equal("new", doc.title)
        title = doc.at("/html/head/title")
        assert_not_nil(title)
        assert_equal("new", title.text)
        assert_equal(-1, doc.at("meta[@http-equiv]") <=> title)

        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              foo
            </body>
          </html>
        EOHTML
        doc.title = "new"
        assert_equal("new", doc.title)
        # <head> may or may not be added
        title = doc.at("/html//title")
        assert_not_nil(title)
        assert_equal("new", title.text)
        assert_equal(-1, title <=> doc.at("body"))

        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <meta charset="UTF-8">
            <body>
              foo
            </body>
          </html>
        EOHTML
        doc.title = "new"
        assert_equal("new", doc.title)
        assert_equal(-1, doc.at("meta[@charset]") <=> doc.at("title"))
        assert_equal(-1, doc.at("title") <=> doc.at("body"))

        doc = Nokogiri::HTML("<!DOCTYPE html><p>hello")
        doc.title = "new"
        assert_equal("new", doc.title)
        assert_instance_of(Nokogiri::XML::DTD, doc.children.first)
        assert_equal(-1, doc.at("title") <=> doc.at("p"))

        doc = Nokogiri::HTML("")
        doc.title = "new"
        assert_equal("new", doc.title)
        assert_equal("new", doc.at("/html/head/title/text()").to_s)
      end

      def test_meta_encoding_without_head
        encoding = "EUC-JP"
        html = Nokogiri::HTML("<html><body>foo</body></html>", nil, encoding)

        assert_nil(html.meta_encoding)

        html.meta_encoding = encoding
        assert_equal(encoding, html.meta_encoding)

        meta = html.at("/html/head/meta[@http-equiv and boolean(@content)]")
        assert(meta, "meta is in head")

        assert(meta.at("./parent::head/following-sibling::body"), "meta is before body")
      end

      def test_html5_meta_encoding_without_head
        encoding = "EUC-JP"
        html = Nokogiri::HTML("<!DOCTYPE html><html><body>foo</body></html>", nil, encoding)

        assert_nil(html.meta_encoding)

        html.meta_encoding = encoding
        assert_equal(encoding, html.meta_encoding)

        meta = html.at("/html/head/meta[@charset]")
        assert(meta, "meta is in head")

        assert(meta.at("./parent::head/following-sibling::body"), "meta is before body")
      end

      def test_meta_encoding_with_empty_content_type
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <meta http-equiv="Content-Type" content="">
            </head>
            <body>
              foo
            </body>
          </html>
        EOHTML
        assert_nil(html.meta_encoding)

        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <meta http-equiv="Content-Type">
            </head>
            <body>
              foo
            </body>
          </html>
        EOHTML
        assert_nil(html.meta_encoding)
      end

      def test_root_node_parent_is_document
        parent = html.root.parent
        assert_equal(html, parent)
        assert_instance_of(Nokogiri::HTML::Document, parent)
      end

      def test_parse_handles_nil_gracefully
        @doc = Nokogiri::HTML::Document.parse(nil)
        assert_instance_of(Nokogiri::HTML::Document, @doc)
      end

      def test_parse_empty_document
        doc = Nokogiri::HTML("\n")
        assert_equal(0, doc.css("a").length)
        assert_equal(0, doc.xpath("//a").length)
        assert_equal(0, doc.search("//a").length)
      end

      def test_HTML_function
        html = Nokogiri::HTML(File.read(HTML_FILE))
        assert(html.html?)
      end

      def test_parse_works_with_an_object_that_responds_to_read
        klass = Class.new do
          def initialize
            @contents = StringIO.new("<div>foo</div>")
          end

          def read(*args)
            @contents.read(*args)
          end
        end

        doc = Nokogiri::HTML.parse(klass.new)
        assert_equal("foo", doc.at_css("div").content)
      end

      def test_parse_temp_file
        temp_html_file = Tempfile.new("TEMP_HTML_FILE")
        File.open(HTML_FILE, "rb") { |f| temp_html_file.write(f.read) }
        temp_html_file.close
        temp_html_file.open
        assert_equal(Nokogiri::HTML.parse(File.read(HTML_FILE)).xpath("//div/a").length,
          Nokogiri::HTML.parse(temp_html_file).xpath("//div/a").length)
      end

      def test_to_xhtml
        assert_match("XHTML", html.to_xhtml)
        assert_match("XHTML", html.to_xhtml(encoding: "UTF-8"))
        assert_match("UTF-8", html.to_xhtml(encoding: "UTF-8"))
      end

      def test_no_xml_header
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
          </html>
        EOHTML
        assert(html.to_html.length > 0, "html length is too short")
        assert_no_match(/^<\?xml/, html.to_html)
      end

      def test_document_has_error
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              <div awesome="asdf>
                <p>inside div tag</p>
              </div>
              <p>outside div tag</p>
            </body>
          </html>
        EOHTML
        assert(html.errors.length > 0)
      end

      def test_relative_css
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              <div>
                <p>inside div tag</p>
              </div>
              <p>outside div tag</p>
            </body>
          </html>
        EOHTML
        set = html.search("div").search("p")
        assert_equal(1, set.length)
        assert_equal("inside div tag", set.first.inner_text)
      end

      def test_multi_css
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              <div>
                <p>p tag</p>
                <a>a tag</a>
              </div>
            </body>
          </html>
        EOHTML
        set = html.css("p, a")
        assert_equal(2, set.length)
        assert_equal(["a tag", "p tag"].sort, set.map(&:content).sort)
      end

      def test_inner_text
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              <div>
                <p>
                  Hello world!
                </p>
              </div>
            </body>
          </html>
        EOHTML
        node = html.xpath("//div").first
        assert_equal("Hello world!", node.inner_text.strip)
      end

      def test_doc_type
        html = Nokogiri::HTML(<<~EOHTML)
          <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
          <html xmlns="http://www.w3.org/1999/xhtml">
            <body>
              <p>Rainbow Dash</p>
            </body>
          </html>
        EOHTML
        assert_equal("html", html.internal_subset.name)
        assert_equal("-//W3C//DTD XHTML 1.1//EN", html.internal_subset.external_id)
        assert_equal("http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd", html.internal_subset.system_id)
        assert_equal("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\" \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">", html.to_s[0, 97])
      end

      def test_content_size
        html = Nokogiri::HTML("<div>\n</div>")
        assert_equal(1, html.content.size)
        assert_equal(1, html.content.split("").size)
        assert_equal("\n", html.content)
      end

      def test_find_by_xpath
        found = html.xpath("//div/a")
        assert_equal(3, found.length)
      end

      def test_find_by_css
        found = html.css("div > a")
        assert_equal(3, found.length)
      end

      def test_find_by_css_with_square_brackets
        found = html.css("div[@id='header'] > h1")
        found = html.css("div[@id='header'] h1") # this blows up on commit 6fa0f6d329d9dbf1cc21c0ac72f7e627bb4c05fc
        assert_equal(1, found.length)
      end

      def test_find_by_css_with_escaped_characters
        found_without_escape = html.css("div[@id='abc.123']")
        found_by_id = html.css('#abc\.123')
        found_by_class = html.css('.special\.character')
        assert_equal(1, found_without_escape.length)
        assert_equal(found_by_id, found_without_escape)
        assert_equal(found_by_class, found_without_escape)
      end

      def test_find_with_function
        assert(html.css("div:awesome() h1", Class.new do
          def awesome(divs)
            [divs.first]
          end
        end.new))
      end

      def test_dup_shallow
        found = html.search("//div/a").first
        dup = found.dup(0)
        assert(dup)
        assert_equal("", dup.content)
      end

      def test_search_can_handle_xpath_and_css
        found = html.search("//div/a", "div > p")
        length = html.xpath("//div/a").length +
                 html.css("div > p").length
        assert_equal(length, found.length)
      end

      def test_dup_document
        assert(dup = html.dup)
        assert_not_equal(dup, html)
        assert(html.html?)
        assert_instance_of(Nokogiri::HTML::Document, dup)
        assert(dup.html?, "duplicate should be html")
        assert_equal(html.to_s, dup.to_s)
      end

      def test_dup_document_shallow
        assert(dup = html.dup(0))
        assert_not_equal(dup, html)
      end

      def test_dup
        found = html.search("//div/a").first
        dup = found.dup
        assert(dup)
        assert_equal(found.content, dup.content)
        assert_equal(found.document, dup.document)
      end

      # issue 1060
      def test_node_ownership_after_dup
        html = "<html><head></head><body><div>replace me</div></body></html>"
        doc = Nokogiri::HTML::Document.parse(html)
        dup = doc.dup
        assert_same(dup, dup.at_css("div").document)

        # should not raise an exception
        dup.at_css("div").parse("<div>replaced</div>")
      end

      def test_inner_html
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              <div>
                <p>
                  Hello world!
                </p>
              </div>
            </body>
          </html>
        EOHTML
        node = html.xpath("//div").first
        assert_equal("<p>Helloworld!</p>", node.inner_html.gsub(/\s/, ""))
      end

      def test_round_trip
        doc = Nokogiri::HTML(html.inner_html)
        assert_equal(html.root.to_html, doc.root.to_html)
      end

      def test_fragment_contains_text_node
        fragment = Nokogiri::HTML.fragment("fooo")
        assert_equal(1, fragment.children.length)
        assert_equal("fooo", fragment.inner_text)
      end

      def test_fragment_includes_two_tags
        assert_equal(2, Nokogiri::HTML.fragment("<br/><hr/>").children.length)
      end

      def test_relative_css_finder
        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              <div class="red">
                <p>
                  inside red
                </p>
              </div>
              <div class="green">
                <p>
                  inside green
                </p>
              </div>
            </body>
          </html>
        EOHTML
        red_divs = doc.css("div.red")
        assert_equal(1, red_divs.length)
        p_tags = red_divs.first.css("p")
        assert_equal(1, p_tags.length)
        assert_equal("inside red", p_tags.first.text.strip)
      end

      def test_find_classes
        doc = Nokogiri::HTML(<<~EOHTML)
          <html>
            <body>
              <p class="red">RED</p>
              <p class="awesome red">RED</p>
              <p class="notred">GREEN</p>
              <p class="green notred">GREEN</p>
            </body>
          </html>
        EOHTML
        list = doc.css(".red")
        assert_equal(2, list.length)
        assert_equal(%w{RED RED}, list.map(&:text))
      end

      def test_parse_can_take_io
        html = nil
        File.open(HTML_FILE, "rb") do |f|
          html = Nokogiri::HTML(f)
        end
        assert(html.html?)
        assert_equal(HTML_FILE, html.url)
      end

      def test_parse_works_with_an_object_that_responds_to_path
        html = String.new("<html><body>hello</body></html>")
        def html.path
          "/i/should/be/the/document/url"
        end

        doc = Nokogiri::HTML.parse(html)

        assert_equal("/i/should/be/the/document/url", doc.url)
      end

      # issue #1821, #2110
      def test_parse_can_take_pathnames
        assert(File.size(HTML_FILE) > 4096) # file must be big enough to trip the read callback more than once

        doc = Nokogiri::HTML.parse(Pathname.new(HTML_FILE))

        # an arbitrary assertion on the structure of the document
        assert_equal(166, doc.css("a").length)
        assert_equal(HTML_FILE, doc.url)
      end

      def test_html?
        assert(!html.xml?)
        assert(html.html?)
      end

      def test_serialize
        assert(html.serialize)
        assert(html.to_html)
      end

      def test_empty_document
        # empty document should return "" #699
        assert_equal("", Nokogiri::HTML.parse(nil).text)
        assert_equal("", Nokogiri::HTML.parse("").text)
      end

      def test_capturing_nonparse_errors_during_document_clone
        # see https://github.com/sparklemotion/nokogiri/issues/1196 for background
        original = Nokogiri::HTML.parse("<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_docs
        # Errors should be emitted while parsing only, and should not change when moving nodes.
        doc1 = Nokogiri::HTML("<html><body><diva id='unique'>one</diva></body></html>")
        doc2 = Nokogiri::HTML("<html><body><dive id='unique'>two</dive></body></html>")
        node1 = doc1.at_css("#unique")
        node2 = doc2.at_css("#unique")
        original_errors1 = doc1.errors.dup
        original_errors2 = doc2.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, doc1.errors)
        assert_equal(original_errors2, doc2.errors)
      end

      def test_silencing_nonparse_errors_during_attribute_insertion_1262
        # see https://github.com/sparklemotion/nokogiri/issues/1262
        #
        # libxml2 emits a warning when this happens; the JRuby
        # implementation does not. so rather than capture the error in
        # doc.errors in a platform-dependent way, I'm opting to have
        # the error silenced.
        #
        # So this test doesn't look meaningful, but we want to avoid
        # having `ID unique-issue-1262 already defined` emitted to
        # stderr when running the test suite.
        #
        doc = Nokogiri::HTML::Document.new
        Nokogiri::XML::Element.new("div", doc).set_attribute("id", "unique-issue-1262")
        Nokogiri::XML::Element.new("div", doc).set_attribute("id", "unique-issue-1262")
        assert_equal(0, doc.errors.length)
      end

      it "skips encoding for script tags" do
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <script>var isGreater = 4 > 5;</script>
            </head>
            <body></body>
          </html>
        EOHTML
        node = html.xpath("//script").first
        assert_equal("var isGreater = 4 > 5;", node.inner_html)
      end

      it "skips encoding for style tags" do
        html = Nokogiri::HTML(<<~EOHTML)
          <html>
            <head>
              <style>tr > div { display:block; }</style>
            </head>
            <body></body>
          </html>
        EOHTML
        node = html.xpath("//style").first
        assert_equal("tr > div { display:block; }", node.inner_html)
      end

      it "does not fail when converting to_html using explicit encoding" do
        html_fragment = <<~EOHTML
          <img width="16" height="16" src="images/icon.gif" border="0" alt="Inactive hide details for &quot;User&quot; ---19/05/2015 12:55:29---Provvediamo subito nell&#8217;integrare">
        EOHTML
        doc = Nokogiri::HTML(html_fragment, nil, "ISO-8859-1")
        html = doc.to_html
        assert html.index("src=\"images/icon.gif\"")
        assert_equal "ISO-8859-1", html.encoding.name
      end

      def test_leaking_dtd_nodes_after_internal_subset_removal
        # see https://github.com/sparklemotion/nokogiri/issues/1784
        #
        # just checking that this doesn't raise a valgrind error. we
        # don't otherwise have any test coverage for removing DTDs.
        #
        100.times do |i|
          Nokogiri::HTML::Document.new.internal_subset.remove
        end
      end

      describe "HTML::Document.parse" do
        let(:html_strict) do
          Nokogiri::XML::ParseOptions.new(Nokogiri::XML::ParseOptions::DEFAULT_HTML).norecover
        end

        it "sets the test up correctly" do
          assert(html_strict.strict?)
        end

        describe "read memory" do
          let(:input) { "<html><body><div" }

          describe "strict parsing" do
            let(:parse_options) { html_strict }

            it "raises exception on parse error" do
              exception = assert_raises Nokogiri::SyntaxError do
                Nokogiri::HTML.parse(input, nil, nil, parse_options)
              end
              assert_match(/Parser without recover option encountered error or warning/, exception.to_s)
            end
          end

          describe "default options" do
            it "does not raise exception on parse error" do
              doc = Nokogiri::HTML.parse(input)
              assert_operator(doc.errors.length, :>, 0)
            end
          end
        end

        describe "read io" do
          let(:input) { StringIO.new("<html><body><div") }

          describe "strict parsing" do
            let(:parse_options) { html_strict }

            it "raises exception on parse error" do
              exception = assert_raises Nokogiri::SyntaxError do
                Nokogiri::HTML.parse(input, nil, "UTF-8", parse_options)
              end
              assert_match(/Parser without recover option encountered error or warning/, exception.to_s)
            end
          end

          describe "default options" do
            it "does not raise exception on parse error" do
              doc = Nokogiri::HTML.parse(input, nil, "UTF-8")
              assert_operator(doc.errors.length, :>, 0)
            end
          end
        end
      end
    end
  end
end