nokogiri 1.16.7-x64-mingw-ucrt → 1.17.0-x64-mingw-ucrt

Sign up to get free protection for your applications and to get access to all the features.
Files changed (112) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile +11 -21
  3. data/README.md +4 -0
  4. data/dependencies.yml +6 -6
  5. data/ext/nokogiri/extconf.rb +191 -137
  6. data/ext/nokogiri/gumbo.c +69 -53
  7. data/ext/nokogiri/html4_document.c +10 -4
  8. data/ext/nokogiri/html4_element_description.c +18 -18
  9. data/ext/nokogiri/html4_sax_parser.c +40 -0
  10. data/ext/nokogiri/html4_sax_parser_context.c +48 -58
  11. data/ext/nokogiri/html4_sax_push_parser.c +25 -24
  12. data/ext/nokogiri/include/libexslt/exsltconfig.h +3 -3
  13. data/ext/nokogiri/include/libxml2/libxml/HTMLparser.h +12 -19
  14. data/ext/nokogiri/include/libxml2/libxml/c14n.h +1 -12
  15. data/ext/nokogiri/include/libxml2/libxml/debugXML.h +1 -1
  16. data/ext/nokogiri/include/libxml2/libxml/encoding.h +9 -0
  17. data/ext/nokogiri/include/libxml2/libxml/entities.h +12 -1
  18. data/ext/nokogiri/include/libxml2/libxml/hash.h +19 -0
  19. data/ext/nokogiri/include/libxml2/libxml/list.h +2 -2
  20. data/ext/nokogiri/include/libxml2/libxml/nanohttp.h +17 -0
  21. data/ext/nokogiri/include/libxml2/libxml/parser.h +60 -54
  22. data/ext/nokogiri/include/libxml2/libxml/parserInternals.h +9 -1
  23. data/ext/nokogiri/include/libxml2/libxml/pattern.h +6 -0
  24. data/ext/nokogiri/include/libxml2/libxml/tree.h +32 -12
  25. data/ext/nokogiri/include/libxml2/libxml/uri.h +11 -0
  26. data/ext/nokogiri/include/libxml2/libxml/valid.h +29 -2
  27. data/ext/nokogiri/include/libxml2/libxml/xinclude.h +7 -0
  28. data/ext/nokogiri/include/libxml2/libxml/xmlIO.h +21 -4
  29. data/ext/nokogiri/include/libxml2/libxml/xmlerror.h +14 -0
  30. data/ext/nokogiri/include/libxml2/libxml/xmlexports.h +111 -15
  31. data/ext/nokogiri/include/libxml2/libxml/xmlmemory.h +8 -45
  32. data/ext/nokogiri/include/libxml2/libxml/xmlreader.h +2 -0
  33. data/ext/nokogiri/include/libxml2/libxml/xmlsave.h +5 -0
  34. data/ext/nokogiri/include/libxml2/libxml/xmlunicode.h +165 -1
  35. data/ext/nokogiri/include/libxml2/libxml/xmlversion.h +7 -171
  36. data/ext/nokogiri/include/libxml2/libxml/xmlwriter.h +1 -0
  37. data/ext/nokogiri/include/libxml2/libxml/xpath.h +4 -0
  38. data/ext/nokogiri/include/libxslt/xsltInternals.h +3 -0
  39. data/ext/nokogiri/include/libxslt/xsltconfig.h +4 -37
  40. data/ext/nokogiri/libxml2_polyfill.c +114 -0
  41. data/ext/nokogiri/nokogiri.c +9 -2
  42. data/ext/nokogiri/nokogiri.h +18 -33
  43. data/ext/nokogiri/xml_attr.c +1 -1
  44. data/ext/nokogiri/xml_cdata.c +2 -10
  45. data/ext/nokogiri/xml_comment.c +3 -8
  46. data/ext/nokogiri/xml_document.c +163 -156
  47. data/ext/nokogiri/xml_document_fragment.c +10 -25
  48. data/ext/nokogiri/xml_dtd.c +1 -1
  49. data/ext/nokogiri/xml_element_content.c +9 -9
  50. data/ext/nokogiri/xml_encoding_handler.c +4 -4
  51. data/ext/nokogiri/xml_namespace.c +6 -6
  52. data/ext/nokogiri/xml_node.c +137 -105
  53. data/ext/nokogiri/xml_node_set.c +46 -44
  54. data/ext/nokogiri/xml_reader.c +54 -58
  55. data/ext/nokogiri/xml_relax_ng.c +35 -56
  56. data/ext/nokogiri/xml_sax_parser.c +156 -88
  57. data/ext/nokogiri/xml_sax_parser_context.c +213 -131
  58. data/ext/nokogiri/xml_sax_push_parser.c +68 -49
  59. data/ext/nokogiri/xml_schema.c +50 -85
  60. data/ext/nokogiri/xml_syntax_error.c +19 -11
  61. data/ext/nokogiri/xml_text.c +2 -4
  62. data/ext/nokogiri/xml_xpath_context.c +2 -2
  63. data/ext/nokogiri/xslt_stylesheet.c +8 -8
  64. data/lib/nokogiri/3.1/nokogiri.so +0 -0
  65. data/lib/nokogiri/3.2/nokogiri.so +0 -0
  66. data/lib/nokogiri/3.3/nokogiri.so +0 -0
  67. data/lib/nokogiri/class_resolver.rb +1 -1
  68. data/lib/nokogiri/css/node.rb +6 -2
  69. data/lib/nokogiri/css/parser.rb +6 -4
  70. data/lib/nokogiri/css/parser.y +2 -2
  71. data/lib/nokogiri/css/parser_extras.rb +6 -66
  72. data/lib/nokogiri/css/selector_cache.rb +38 -0
  73. data/lib/nokogiri/css/tokenizer.rb +4 -4
  74. data/lib/nokogiri/css/tokenizer.rex +9 -8
  75. data/lib/nokogiri/css/xpath_visitor.rb +42 -6
  76. data/lib/nokogiri/css.rb +86 -20
  77. data/lib/nokogiri/decorators/slop.rb +3 -5
  78. data/lib/nokogiri/encoding_handler.rb +2 -2
  79. data/lib/nokogiri/html4/document.rb +44 -23
  80. data/lib/nokogiri/html4/document_fragment.rb +124 -12
  81. data/lib/nokogiri/html4/encoding_reader.rb +1 -1
  82. data/lib/nokogiri/html4/sax/parser.rb +23 -38
  83. data/lib/nokogiri/html4/sax/parser_context.rb +4 -9
  84. data/lib/nokogiri/html4.rb +9 -14
  85. data/lib/nokogiri/html5/builder.rb +40 -0
  86. data/lib/nokogiri/html5/document.rb +61 -30
  87. data/lib/nokogiri/html5/document_fragment.rb +130 -20
  88. data/lib/nokogiri/html5/node.rb +4 -4
  89. data/lib/nokogiri/html5.rb +114 -72
  90. data/lib/nokogiri/version/constant.rb +1 -1
  91. data/lib/nokogiri/xml/builder.rb +8 -1
  92. data/lib/nokogiri/xml/document.rb +70 -26
  93. data/lib/nokogiri/xml/document_fragment.rb +84 -13
  94. data/lib/nokogiri/xml/node.rb +82 -11
  95. data/lib/nokogiri/xml/node_set.rb +9 -7
  96. data/lib/nokogiri/xml/parse_options.rb +1 -1
  97. data/lib/nokogiri/xml/pp/node.rb +6 -1
  98. data/lib/nokogiri/xml/reader.rb +46 -13
  99. data/lib/nokogiri/xml/relax_ng.rb +57 -20
  100. data/lib/nokogiri/xml/sax/document.rb +174 -83
  101. data/lib/nokogiri/xml/sax/parser.rb +115 -41
  102. data/lib/nokogiri/xml/sax/parser_context.rb +116 -8
  103. data/lib/nokogiri/xml/sax/push_parser.rb +3 -0
  104. data/lib/nokogiri/xml/sax.rb +48 -0
  105. data/lib/nokogiri/xml/schema.rb +112 -45
  106. data/lib/nokogiri/xml/searchable.rb +6 -8
  107. data/lib/nokogiri/xml/syntax_error.rb +22 -0
  108. data/lib/nokogiri/xml.rb +13 -24
  109. data/lib/nokogiri/xslt.rb +3 -9
  110. data/lib/xsd/xmlparser/nokogiri.rb +3 -4
  111. metadata +8 -5
  112. data/ext/nokogiri/libxml2_backwards_compat.c +0 -121
@@ -25,27 +25,145 @@ module Nokogiri
25
25
  #
26
26
  # 💡 HTML5 functionality is not available when running JRuby.
27
27
  class DocumentFragment < Nokogiri::HTML4::DocumentFragment
28
+ class << self
29
+ # :call-seq:
30
+ # parse(input, **options) → HTML5::DocumentFragment
31
+ #
32
+ # Parse \HTML5 fragment input from a String, and return a new HTML5::DocumentFragment. This
33
+ # method creates a new, empty HTML5::Document to contain the fragment.
34
+ #
35
+ # [Parameters]
36
+ # - +input+ (String | IO) The HTML5 document fragment to parse.
37
+ #
38
+ # [Optional Keyword Arguments]
39
+ # - +encoding:+ (String | Encoding) The encoding, or name of the encoding, that should be
40
+ # used when processing the document. When not provided, the encoding will be determined
41
+ # based on the document content. Also see Nokogiri::HTML5 for a longer explanation of how
42
+ # encoding is handled by the parser.
43
+ #
44
+ # - +context:+ (String | Nokogiri::XML::Node) The node, or the name of an HTML5 element, "in
45
+ # context" of which to parse the document fragment. See below for more
46
+ # information. (default +"body"+)
47
+ #
48
+ # - +max_errors:+ (Integer) The maximum number of parse errors to record. (default
49
+ # +Nokogiri::Gumbo::DEFAULT_MAX_ERRORS+ which is currently 0)
50
+ #
51
+ # - +max_tree_depth:+ (Integer) The maximum depth of the parse tree. (default
52
+ # +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+)
53
+ #
54
+ # - +max_attributes:+ (Integer) The maximum number of attributes allowed on an
55
+ # element. (default +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+)
56
+ #
57
+ # - +parse_noscript_content_as_text:+ (Boolean) Whether to parse the content of +noscript+
58
+ # elements as text. (default +false+)
59
+ #
60
+ # See rdoc-ref:HTML5@Parsing+options for a complete description of these parsing options.
61
+ #
62
+ # [Returns] Nokogiri::HTML5::DocumentFragment
63
+ #
64
+ # === Context \Node
65
+ #
66
+ # If a context node is specified using +context:+, then the parser will behave as if that
67
+ # Node, or a hypothetical tag named as specified, is the parent of the fragment subtree.
68
+ #
69
+ def parse(
70
+ input,
71
+ encoding_ = nil, positional_options_hash = nil,
72
+ encoding: encoding_, **options
73
+ )
74
+ unless positional_options_hash.nil? || positional_options_hash.empty?
75
+ options.merge!(positional_options_hash)
76
+ end
77
+
78
+ context = options.delete(:context)
79
+
80
+ document = HTML5::Document.new
81
+ document.encoding = "UTF-8"
82
+ input = HTML5.read_and_encode(input, encoding)
83
+
84
+ new(document, input, context, options)
85
+ end
86
+ end
87
+
28
88
  attr_accessor :document
29
89
  attr_accessor :errors
30
90
 
31
91
  # Get the parser's quirks mode value. See HTML5::QuirksMode.
32
92
  #
33
- # This method returns `nil` if the parser was not invoked (e.g., `Nokogiri::HTML5::DocumentFragment.new(doc)`).
93
+ # This method returns `nil` if the parser was not invoked (e.g.,
94
+ # `Nokogiri::HTML5::DocumentFragment.new(doc)`).
34
95
  #
35
96
  # Since v1.14.0
36
97
  attr_reader :quirks_mode
37
98
 
38
- # Create a document fragment.
39
- def initialize(doc, tags = nil, ctx = nil, options = {}) # rubocop:disable Lint/MissingSuper
40
- self.document = doc
41
- self.errors = []
42
- return self unless tags
43
-
44
- max_attributes = options[:max_attributes] || Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES
45
- max_errors = options[:max_errors] || Nokogiri::Gumbo::DEFAULT_MAX_ERRORS
46
- max_depth = options[:max_tree_depth] || Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH
47
- tags = Nokogiri::HTML5.read_and_encode(tags, nil)
48
- Nokogiri::Gumbo.fragment(self, tags, ctx, max_attributes, max_errors, max_depth)
99
+ #
100
+ # :call-seq:
101
+ # new(document, input, **options) → HTML5::DocumentFragment
102
+ #
103
+ # Parse \HTML5 fragment input from a String, and return a new HTML5::DocumentFragment.
104
+ #
105
+ # 💡 It's recommended to use either HTML5::DocumentFragment.parse or HTML5::Node#fragment
106
+ # rather than call this method directly.
107
+ #
108
+ # [Required Parameters]
109
+ # - +document+ (HTML5::Document) The parent document to associate the returned fragment with.
110
+ #
111
+ # [Optional Parameters]
112
+ # - +input+ (String) The content to be parsed.
113
+ #
114
+ # [Optional Keyword Arguments]
115
+ # - +encoding:+ (String | Encoding) The encoding, or name of the encoding, that should be
116
+ # used when processing the document. When not provided, the encoding will be determined
117
+ # based on the document content. Also see Nokogiri::HTML5 for a longer explanation of how
118
+ # encoding is handled by the parser.
119
+ #
120
+ # - +context:+ (String | Nokogiri::XML::Node) The node, or the name of an HTML5 element, in
121
+ # which to parse the document fragment. (default +"body"+)
122
+ #
123
+ # - +max_errors:+ (Integer) The maximum number of parse errors to record. (default
124
+ # +Nokogiri::Gumbo::DEFAULT_MAX_ERRORS+ which is currently 0)
125
+ #
126
+ # - +max_tree_depth:+ (Integer) The maximum depth of the parse tree. (default
127
+ # +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+)
128
+ #
129
+ # - +max_attributes:+ (Integer) The maximum number of attributes allowed on an
130
+ # element. (default +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+)
131
+ #
132
+ # - +parse_noscript_content_as_text:+ (Boolean) Whether to parse the content of +noscript+
133
+ # elements as text. (default +false+)
134
+ #
135
+ # See rdoc-ref:HTML5@Parsing+options for a complete description of these parsing options.
136
+ #
137
+ # [Returns] HTML5::DocumentFragment
138
+ #
139
+ # === Context \Node
140
+ #
141
+ # If a context node is specified using +context:+, then the parser will behave as if that
142
+ # Node, or a hypothetical tag named as specified, is the parent of the fragment subtree.
143
+ #
144
+ def initialize(
145
+ doc, input = nil,
146
+ context_ = nil, positional_options_hash = nil,
147
+ context: context_,
148
+ **options
149
+ ) # rubocop:disable Lint/MissingSuper
150
+ unless positional_options_hash.nil? || positional_options_hash.empty?
151
+ options.merge!(positional_options_hash)
152
+ end
153
+
154
+ @document = doc
155
+ @errors = []
156
+ return self unless input
157
+
158
+ input = Nokogiri::HTML5.read_and_encode(input, nil)
159
+
160
+ context = options.delete(:context) if options.key?(:context)
161
+
162
+ options[:max_attributes] ||= Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES
163
+ options[:max_errors] ||= options.delete(:max_parse_errors) || Nokogiri::Gumbo::DEFAULT_MAX_ERRORS
164
+ options[:max_tree_depth] ||= Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH
165
+
166
+ Nokogiri::Gumbo.fragment(self, input, context, **options)
49
167
  end
50
168
 
51
169
  def serialize(options = {}, &block) # :nodoc:
@@ -54,14 +172,6 @@ module Nokogiri
54
172
  XML::Node.instance_method(:serialize).bind_call(self, options, &block)
55
173
  end
56
174
 
57
- # Parse a document fragment from +tags+, returning a Nodeset.
58
- def self.parse(tags, encoding = nil, options = {})
59
- doc = HTML5::Document.new
60
- tags = HTML5.read_and_encode(tags, encoding)
61
- doc.encoding = "UTF-8"
62
- new(doc, tags, nil, options)
63
- end
64
-
65
175
  def extract_params(params) # :nodoc:
66
176
  handler = params.find do |param|
67
177
  ![Hash, String, Symbol].include?(param.class)
@@ -29,7 +29,7 @@ module Nokogiri
29
29
  # 💡 HTML5 functionality is not available when running JRuby.
30
30
  module Node
31
31
  def inner_html(options = {})
32
- return super(options) unless document.is_a?(HTML5::Document)
32
+ return super unless document.is_a?(HTML5::Document)
33
33
 
34
34
  result = options[:preserve_newline] && prepend_newline? ? +"\n" : +""
35
35
  result << children.map { |child| child.to_html(options) }.join
@@ -37,7 +37,7 @@ module Nokogiri
37
37
  end
38
38
 
39
39
  def write_to(io, *options)
40
- return super(io, *options) unless document.is_a?(HTML5::Document)
40
+ return super unless document.is_a?(HTML5::Document)
41
41
 
42
42
  options = options.first.is_a?(Hash) ? options.shift : {}
43
43
  encoding = options[:encoding] || options[0]
@@ -68,7 +68,7 @@ module Nokogiri
68
68
  end
69
69
 
70
70
  def fragment(tags)
71
- return super(tags) unless document.is_a?(HTML5::Document)
71
+ return super unless document.is_a?(HTML5::Document)
72
72
 
73
73
  DocumentFragment.new(document, tags, self)
74
74
  end
@@ -81,7 +81,7 @@ module Nokogiri
81
81
  # annoying with attribute names like xml:lang since libxml2 will
82
82
  # actually create the xml namespace if it doesn't exist already.
83
83
  def add_child_node_and_reparent_attrs(node)
84
- return super(node) unless document.is_a?(HTML5::Document)
84
+ return super unless document.is_a?(HTML5::Document)
85
85
 
86
86
  # I'm not sure what this method is supposed to do. Reparenting
87
87
  # namespaces is handled by libxml2, including child namespaces which
@@ -1,66 +1,71 @@
1
1
  # coding: utf-8
2
2
  # frozen_string_literal: true
3
3
 
4
+ # This file includes code from the Nokogumbo project, whose license follows.
4
5
  #
5
- # Copyright 2013-2021 Sam Ruby, Stephen Checkoway
6
+ # Copyright 2013-2021 Sam Ruby, Stephen Checkoway
6
7
  #
7
- # Licensed under the Apache License, Version 2.0 (the "License");
8
- # you may not use this file except in compliance with the License.
9
- # You may obtain a copy of the License at
8
+ # Licensed under the Apache License, Version 2.0 (the "License");
9
+ # you may not use this file except in compliance with the License.
10
+ # You may obtain a copy of the License at
10
11
  #
11
- # http://www.apache.org/licenses/LICENSE-2.0
12
+ # http://www.apache.org/licenses/LICENSE-2.0
12
13
  #
13
- # Unless required by applicable law or agreed to in writing, software
14
- # distributed under the License is distributed on an "AS IS" BASIS,
15
- # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16
- # See the License for the specific language governing permissions and
17
- # limitations under the License.
14
+ # Unless required by applicable law or agreed to in writing, software
15
+ # distributed under the License is distributed on an "AS IS" BASIS,
16
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17
+ # See the License for the specific language governing permissions and
18
+ # limitations under the License.
18
19
  #
19
20
 
20
21
  require_relative "html5/document"
21
22
  require_relative "html5/document_fragment"
22
23
  require_relative "html5/node"
24
+ require_relative "html5/builder"
23
25
 
24
26
  module Nokogiri
25
- # Since v1.12.0
26
- #
27
- # ⚠ HTML5 functionality is not available when running JRuby.
28
- #
29
- # Parse an HTML5 document. Convenience method for {Nokogiri::HTML5::Document.parse}
30
- def self.HTML5(input, url = nil, encoding = nil, **options, &block)
31
- Nokogiri::HTML5::Document.parse(input, url, encoding, **options, &block)
27
+ # Convenience method for Nokogiri::HTML5::Document.parse
28
+ def self.HTML5(...)
29
+ Nokogiri::HTML5::Document.parse(...)
32
30
  end
33
31
 
34
32
  # == Usage
35
33
  #
36
- # ⚠ HTML5 functionality is not available when running JRuby.
37
- #
38
34
  # Parse an HTML5 document:
39
35
  #
40
- # doc = Nokogiri.HTML5(string)
36
+ # doc = Nokogiri.HTML5(input)
41
37
  #
42
38
  # Parse an HTML5 fragment:
43
39
  #
44
- # fragment = Nokogiri::HTML5.fragment(string)
40
+ # fragment = Nokogiri::HTML5.fragment(input)
41
+ #
42
+ # ⚠ HTML5 functionality is not available when running JRuby.
45
43
  #
46
44
  # == Parsing options
47
45
  #
48
- # The document and fragment parsing methods support options that are different from Nokogiri's.
46
+ # The document and fragment parsing methods support options that are different from
47
+ # Nokogiri::HTML4::Document or Nokogiri::XML::Document.
48
+ #
49
+ # - <tt>Nokogiri.HTML5(input, url:, encoding:, **parse_options)</tt>
50
+ # - <tt>Nokogiri::HTML5.parse(input, url:, encoding:, **parse_options)</tt>
51
+ # - <tt>Nokogiri::HTML5::Document.parse(input, url:, encoding:, **parse_options)</tt>
52
+ # - <tt>Nokogiri::HTML5.fragment(input, encoding:, **parse_options)</tt>
53
+ # - <tt>Nokogiri::HTML5::DocumentFragment.parse(input, encoding:, **parse_options)</tt>
49
54
  #
50
- # - <tt>Nokogiri.HTML5(html, url = nil, encoding = nil, options = {})</tt>
51
- # - <tt>Nokogiri::HTML5.parse(html, url = nil, encoding = nil, options = {})</tt>
52
- # - <tt>Nokogiri::HTML5::Document.parse(html, url = nil, encoding = nil, options = {})</tt>
53
- # - <tt>Nokogiri::HTML5.fragment(html, encoding = nil, options = {})</tt>
54
- # - <tt>Nokogiri::HTML5::DocumentFragment.parse(html, encoding = nil, options = {})</tt>
55
+ # The four currently supported parse options are
55
56
  #
56
- # The three currently supported options are +:max_errors+, +:max_tree_depth+ and
57
- # +:max_attributes+, described below.
57
+ # - +max_errors:+ (Integer, default 0) Maximum number of parse errors to report in HTML5::Document#errors.
58
+ # - +max_tree_depth:+ (Integer, default +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+) Maximum tree depth to parse.
59
+ # - +max_attributes:+ (Integer, default +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+) Maximum number of attributes to parse per element.
60
+ # - +parse_noscript_content_as_text:+ (Boolean, default false) When enabled, parse +noscript+ tag content as text, mimicking the behavior of web browsers.
58
61
  #
59
- # === Error reporting
62
+ # These options are explained in the following sections.
63
+ #
64
+ # === Error reporting: +max_errors:+
60
65
  #
61
66
  # Nokogiri contains an experimental HTML5 parse error reporting facility. By default, no parse
62
67
  # errors are reported but this can be configured by passing the +:max_errors+ option to
63
- # {HTML5.parse} or {HTML5.fragment}.
68
+ # HTML5.parse or HTML5.fragment.
64
69
  #
65
70
  # For example, this script:
66
71
  #
@@ -86,20 +91,21 @@ module Nokogiri
86
91
  #
87
92
  # Using <tt>max_errors: -1</tt> results in an unlimited number of errors being returned.
88
93
  #
89
- # The errors returned by {HTML5::Document#errors} are instances of {Nokogiri::XML::SyntaxError}.
94
+ # The errors returned by HTML5::Document#errors are instances of Nokogiri::XML::SyntaxError.
90
95
  #
91
- # The {https://html.spec.whatwg.org/multipage/parsing.html#parse-errors HTML standard} defines a
96
+ # The {HTML standard}[https://html.spec.whatwg.org/multipage/parsing.html#parse-errors] defines a
92
97
  # number of standard parse error codes. These error codes only cover the "tokenization" stage of
93
98
  # parsing HTML. The parse errors in the "tree construction" stage do not have standardized error
94
99
  # codes (yet).
95
100
  #
96
- # As a convenience to Nokogiri users, the defined error codes are available via
97
- # {Nokogiri::XML::SyntaxError#str1} method.
101
+ # As a convenience to Nokogiri users, the defined error codes are available
102
+ # via Nokogiri::XML::SyntaxError#str1 method.
98
103
  #
99
104
  # doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />', max_errors: 10)
100
105
  # doc.errors.each do |err|
101
106
  # puts("#{err.line}:#{err.column}: #{err.str1}")
102
107
  # end
108
+ # doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />',
103
109
  # # => 1:1: generic-parser
104
110
  # # 1:1: non-void-html-element-start-tag-with-trailing-solidus
105
111
  # # 1:17: end-tag-with-trailing-solidus
@@ -112,40 +118,75 @@ module Nokogiri
112
118
  # are not part of Nokogiri's public API. That is, these are subject to change without Nokogiri's
113
119
  # major version number changing. These may be stabilized in the future.
114
120
  #
115
- # === Maximum tree depth
121
+ # === Maximum tree depth: +max_tree_depth:+
116
122
  #
117
123
  # The maximum depth of the DOM tree parsed by the various parsing methods is configurable by the
118
124
  # +:max_tree_depth+ option. If the depth of the tree would exceed this limit, then an
119
- # {::ArgumentError} is thrown.
125
+ # +ArgumentError+ is thrown.
120
126
  #
121
- # This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH = 400</tt>) can be
122
- # removed by giving the option <tt>max_tree_depth: -1</tt>.
127
+ # This limit (which defaults to +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+) can be removed by
128
+ # giving the option <tt>max_tree_depth: -1</tt>.
123
129
  #
124
130
  # html = '<!DOCTYPE html>' + '<div>' * 1000
125
131
  # doc = Nokogiri.HTML5(html)
126
132
  # # raises ArgumentError: Document tree depth limit exceeded
127
133
  # doc = Nokogiri.HTML5(html, max_tree_depth: -1)
128
134
  #
129
- # === Attribute limit per element
135
+ # === Attribute limit per element: +max_attributes:+
130
136
  #
131
137
  # The maximum number of attributes per DOM element is configurable by the +:max_attributes+
132
- # option. If a given element would exceed this limit, then an {::ArgumentError} is thrown.
138
+ # option. If a given element would exceed this limit, then an +ArgumentError+ is thrown.
133
139
  #
134
- # This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES = 400</tt>) can be
135
- # removed by giving the option <tt>max_attributes: -1</tt>.
140
+ # This limit (which defaults to +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+) can be removed by
141
+ # giving the option <tt>max_attributes: -1</tt>.
136
142
  #
137
- # html = '<!DOCTYPE html><div ' + (1..1000).map { |x| "attr-#{x}" }.join(' ') + '>'
143
+ # html = '<!DOCTYPE html><div ' + (1..1000).map { |x| "attr-#{x}" }.join(' # ') + '>'
138
144
  # # "<!DOCTYPE html><div attr-1 attr-2 attr-3 ... attr-1000>"
139
145
  # doc = Nokogiri.HTML5(html)
140
146
  # # raises ArgumentError: Attributes per element limit exceeded
147
+ #
141
148
  # doc = Nokogiri.HTML5(html, max_attributes: -1)
149
+ # # parses successfully
150
+ #
151
+ # === Parse +noscript+ elements' content as text: +parse_noscript_content_as_text:+
152
+ #
153
+ # By default, the content of +noscript+ elements is parsed as HTML elements. Browsers that
154
+ # support scripting parse the content of +noscript+ elements as raw text.
155
+ #
156
+ # The +:parse_noscript_content_as_text+ option causes Nokogiri to parse the content of +noscript+
157
+ # elements as a single text node.
158
+ #
159
+ # html = "<!DOCTYPE html><noscript><meta charset='UTF-8'><link rel=stylesheet href=!></noscript>"
160
+ # doc = Nokogiri::HTML5.parse(html, parse_noscript_content_as_text: true)
161
+ # pp doc.at_xpath("/html/head/noscript")
162
+ # # => #(Element:0x878c {
163
+ # # name = "noscript",
164
+ # # children = [ #(Text "<meta charset='UTF-8'><link rel=stylesheet href=!>")]
165
+ # # })
166
+ #
167
+ # In contrast, <tt>parse_noscript_content_as_text: false</tt> (the default) causes the +noscript+
168
+ # element in the previous example to have two children, a +meta+ element and a +link+ element.
169
+ #
170
+ # doc = Nokogiri::HTML5.parse(html)
171
+ # puts doc.at_xpath("/html/head/noscript")
172
+ # # => #(Element:0x96b4 {
173
+ # # name = "noscript",
174
+ # # children = [
175
+ # # #(Element:0x97e0 { name = "meta", attribute_nodes = [ #(Attr:0x990c { name = "charset", value = "UTF-8" })] }),
176
+ # # #(Element:0x9b00 {
177
+ # # name = "link",
178
+ # # attribute_nodes = [
179
+ # # #(Attr:0x9c2c { name = "rel", value = "stylesheet" }),
180
+ # # #(Attr:0x9dd0 { name = "href", value = "!" })]
181
+ # # })]
182
+ # # })
142
183
  #
143
184
  # == HTML Serialization
144
185
  #
145
- # After parsing HTML, it may be serialized using any of the {Nokogiri::XML::Node} serialization
146
- # methods. In particular, {XML::Node#serialize}, {XML::Node#to_html}, and {XML::Node#to_s} will
186
+ # After parsing HTML, it may be serialized using any of the Nokogiri::XML::Node serialization
187
+ # methods. In particular, XML::Node#serialize, XML::Node#to_html, and XML::Node#to_s will
147
188
  # serialize a given node and its children. (This is the equivalent of JavaScript's
148
- # +Element.outerHTML+.) Similarly, {XML::Node#inner_html} will serialize the children of a given
189
+ # +Element.outerHTML+.) Similarly, XML::Node#inner_html will serialize the children of a given
149
190
  # node. (This is the equivalent of JavaScript's +Element.innerHTML+.)
150
191
  #
151
192
  # doc = Nokogiri::HTML5("<!DOCTYPE html><span>Hello world!</span>")
@@ -153,12 +194,12 @@ module Nokogiri
153
194
  # # => <!DOCTYPE html><html><head></head><body><span>Hello world!</span></body></html>
154
195
  #
155
196
  # Due to quirks in how HTML is parsed and serialized, it's possible for a DOM tree to be
156
- # serialized and then re-parsed, resulting in a different DOM. Mostly, this happens with DOMs
197
+ # serialized and then re-parsed, resulting in a different DOM. Mostly, this happens with DOMs
157
198
  # produced from invalid HTML. Unfortunately, even valid HTML may not survive serialization and
158
199
  # re-parsing.
159
200
  #
160
- # In particular, a newline at the start of +pre+, +listing+, and +textarea+ elements is ignored by
161
- # the parser.
201
+ # In particular, a newline at the start of +pre+, +listing+, and +textarea+
202
+ # elements is ignored by the parser.
162
203
  #
163
204
  # doc = Nokogiri::HTML5(<<-EOF)
164
205
  # <!DOCTYPE html>
@@ -187,56 +228,57 @@ module Nokogiri
187
228
  #
188
229
  # == Encodings
189
230
  #
190
- # Nokogiri always parses HTML5 using {https://en.wikipedia.org/wiki/UTF-8 UTF-8}; however, the
231
+ # Nokogiri always parses HTML5 using {UTF-8}[https://en.wikipedia.org/wiki/UTF-8]; however, the
191
232
  # encoding of the input can be explicitly selected via the optional +encoding+ parameter. This is
192
233
  # most useful when the input comes not from a string but from an IO object.
193
234
  #
194
235
  # When serializing a document or node, the encoding of the output string can be specified via the
195
236
  # +:encoding+ options. Characters that cannot be encoded in the selected encoding will be encoded
196
- # as {https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references HTML numeric
197
- # entities}.
237
+ # as {HTML numeric
238
+ # entities}[https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references].
198
239
  #
199
240
  # frag = Nokogiri::HTML5.fragment('<span>아는 길도 물어가라</span>')
200
241
  # html = frag.serialize(encoding: 'US-ASCII')
201
242
  # puts html
202
243
  # # => <span>&#xc544;&#xb294; &#xae38;&#xb3c4; &#xbb3c;&#xc5b4;&#xac00;&#xb77c;</span>
244
+ #
203
245
  # frag = Nokogiri::HTML5.fragment(html)
204
246
  # puts frag.serialize
205
247
  # # => <span>아는 길도 물어가라</span>
206
248
  #
207
- # (There's a {https://bugs.ruby-lang.org/issues/15033 bug} in all current versions of Ruby that
249
+ # (There's a {bug}[https://bugs.ruby-lang.org/issues/15033] in all current versions of Ruby that
208
250
  # can cause the entity encoding to fail. Of the mandated supported encodings for HTML, the only
209
251
  # encoding I'm aware of that has this bug is <tt>'ISO-2022-JP'</tt>. We recommend avoiding this
210
252
  # encoding.)
211
253
  #
212
254
  # == Notes
213
255
  #
214
- # * The {Nokogiri::HTML5.fragment} function takes a string and parses it
215
- # as a HTML5 document. The +<html>+, +<head>+, and +<body>+ elements are
216
- # removed from this document, and any children of these elements that remain
217
- # are returned as a {Nokogiri::HTML5::DocumentFragment}.
256
+ # * The Nokogiri::HTML5.fragment function takes a String or IO and parses it as a HTML5 document
257
+ # in a +body+ context. As a result, the +html+, +head+, and +body+ elements are removed from
258
+ # this document, and any children of these elements that remain are returned as a
259
+ # Nokogiri::HTML5::DocumentFragment; but you can pass in a different context (e.g., "html" to
260
+ # get +head+ and +body+ tags in the result).
218
261
  #
219
- # * The {Nokogiri::HTML5.parse} function takes a string and passes it to the
220
- # <code>gumbo_parse_with_options</code> method, using the default options.
221
- # The resulting Gumbo parse tree is then walked.
262
+ # * The Nokogiri::HTML5.parse function takes a String or IO and passes it to the
263
+ # <code>gumbo_parse_with_options</code> method, using the default options. The resulting Gumbo
264
+ # parse tree is then walked.
222
265
  #
223
266
  # * Instead of uppercase element names, lowercase element names are produced.
224
267
  #
225
- # * Instead of returning +unknown+ as the element name for unknown tags, the
226
- # original tag name is returned verbatim.
268
+ # * Instead of returning +unknown+ as the element name for unknown tags, the original tag name is
269
+ # returned verbatim.
227
270
  #
228
271
  # Since v1.12.0
229
272
  module HTML5
230
273
  class << self
231
- # Parse an HTML 5 document. Convenience method for {Nokogiri::HTML5::Document.parse}
232
- def parse(string, url = nil, encoding = nil, **options, &block)
233
- Document.parse(string, url, encoding, **options, &block)
274
+ # Convenience method for Nokogiri::HTML5::Document.parse
275
+ def parse(...)
276
+ Document.parse(...)
234
277
  end
235
278
 
236
- # Parse a fragment from +string+. Convenience method for
237
- # {Nokogiri::HTML5::DocumentFragment.parse}.
238
- def fragment(string, encoding = nil, **options)
239
- DocumentFragment.parse(string, encoding, options)
279
+ # Convenience method for Nokogiri::HTML5::DocumentFragment.parse
280
+ def fragment(...)
281
+ DocumentFragment.parse(...)
240
282
  end
241
283
 
242
284
  # :nodoc:
@@ -267,11 +309,11 @@ module Nokogiri
267
309
  private
268
310
 
269
311
  # Charset sniffing is a complex and controversial topic that understandably isn't done _by
270
- # default_ by the Ruby Net::HTTP library. This being said, it is a very real problem for
312
+ # default_ by the Ruby Net::HTTP library. This being said, it is a very real problem for
271
313
  # consumers of HTML as the default for HTML is iso-8859-1, most "good" producers use utf-8, and
272
314
  # the Gumbo parser *only* supports utf-8.
273
315
  #
274
- # Accordingly, Nokogiri::HTML4::Document.parse provides limited encoding detection. Following
316
+ # Accordingly, Nokogiri::HTML4::Document.parse provides limited encoding detection. Following
275
317
  # this lead, Nokogiri::HTML5 attempts to do likewise, while attempting to more closely follow
276
318
  # the HTML5 standard.
277
319
  #
@@ -2,5 +2,5 @@
2
2
 
3
3
  module Nokogiri
4
4
  # The version of Nokogiri you are using
5
- VERSION = "1.16.7"
5
+ VERSION = "1.17.0"
6
6
  end
@@ -475,7 +475,14 @@ module Nokogiri
475
475
  if block
476
476
  old_parent = @doc_builder.parent
477
477
  @doc_builder.parent = @node
478
- value = @doc_builder.instance_eval(&block)
478
+
479
+ arity = @doc_builder.arity || block.arity
480
+ value = if arity <= 0
481
+ @doc_builder.instance_eval(&block)
482
+ else
483
+ yield(@doc_builder)
484
+ end
485
+
479
486
  @doc_builder.parent = old_parent
480
487
  return value
481
488
  end