nokogiri 1.13.0-x64-mingw-ucrt

Sign up to get free protection for your applications and to get access to all the features.

Potentially problematic release.


This version of nokogiri might be problematic. Click here for more details.

Files changed (195) hide show
  1. checksums.yaml +7 -0
  2. data/Gemfile +5 -0
  3. data/LICENSE-DEPENDENCIES.md +1903 -0
  4. data/LICENSE.md +9 -0
  5. data/README.md +280 -0
  6. data/bin/nokogiri +131 -0
  7. data/dependencies.yml +73 -0
  8. data/ext/nokogiri/depend +38 -0
  9. data/ext/nokogiri/extconf.rb +1000 -0
  10. data/ext/nokogiri/gumbo.c +584 -0
  11. data/ext/nokogiri/html4_document.c +166 -0
  12. data/ext/nokogiri/html4_element_description.c +294 -0
  13. data/ext/nokogiri/html4_entity_lookup.c +37 -0
  14. data/ext/nokogiri/html4_sax_parser_context.c +120 -0
  15. data/ext/nokogiri/html4_sax_push_parser.c +95 -0
  16. data/ext/nokogiri/include/libexslt/exslt.h +102 -0
  17. data/ext/nokogiri/include/libexslt/exsltconfig.h +70 -0
  18. data/ext/nokogiri/include/libexslt/exsltexports.h +140 -0
  19. data/ext/nokogiri/include/libxml2/libxml/DOCBparser.h +96 -0
  20. data/ext/nokogiri/include/libxml2/libxml/HTMLparser.h +306 -0
  21. data/ext/nokogiri/include/libxml2/libxml/HTMLtree.h +147 -0
  22. data/ext/nokogiri/include/libxml2/libxml/SAX.h +173 -0
  23. data/ext/nokogiri/include/libxml2/libxml/SAX2.h +178 -0
  24. data/ext/nokogiri/include/libxml2/libxml/c14n.h +128 -0
  25. data/ext/nokogiri/include/libxml2/libxml/catalog.h +182 -0
  26. data/ext/nokogiri/include/libxml2/libxml/chvalid.h +230 -0
  27. data/ext/nokogiri/include/libxml2/libxml/debugXML.h +217 -0
  28. data/ext/nokogiri/include/libxml2/libxml/dict.h +79 -0
  29. data/ext/nokogiri/include/libxml2/libxml/encoding.h +245 -0
  30. data/ext/nokogiri/include/libxml2/libxml/entities.h +151 -0
  31. data/ext/nokogiri/include/libxml2/libxml/globals.h +508 -0
  32. data/ext/nokogiri/include/libxml2/libxml/hash.h +236 -0
  33. data/ext/nokogiri/include/libxml2/libxml/list.h +137 -0
  34. data/ext/nokogiri/include/libxml2/libxml/nanoftp.h +163 -0
  35. data/ext/nokogiri/include/libxml2/libxml/nanohttp.h +81 -0
  36. data/ext/nokogiri/include/libxml2/libxml/parser.h +1243 -0
  37. data/ext/nokogiri/include/libxml2/libxml/parserInternals.h +644 -0
  38. data/ext/nokogiri/include/libxml2/libxml/pattern.h +100 -0
  39. data/ext/nokogiri/include/libxml2/libxml/relaxng.h +217 -0
  40. data/ext/nokogiri/include/libxml2/libxml/schemasInternals.h +958 -0
  41. data/ext/nokogiri/include/libxml2/libxml/schematron.h +142 -0
  42. data/ext/nokogiri/include/libxml2/libxml/threads.h +89 -0
  43. data/ext/nokogiri/include/libxml2/libxml/tree.h +1311 -0
  44. data/ext/nokogiri/include/libxml2/libxml/uri.h +94 -0
  45. data/ext/nokogiri/include/libxml2/libxml/valid.h +458 -0
  46. data/ext/nokogiri/include/libxml2/libxml/xinclude.h +129 -0
  47. data/ext/nokogiri/include/libxml2/libxml/xlink.h +189 -0
  48. data/ext/nokogiri/include/libxml2/libxml/xmlIO.h +368 -0
  49. data/ext/nokogiri/include/libxml2/libxml/xmlautomata.h +146 -0
  50. data/ext/nokogiri/include/libxml2/libxml/xmlerror.h +946 -0
  51. data/ext/nokogiri/include/libxml2/libxml/xmlexports.h +77 -0
  52. data/ext/nokogiri/include/libxml2/libxml/xmlmemory.h +224 -0
  53. data/ext/nokogiri/include/libxml2/libxml/xmlmodule.h +57 -0
  54. data/ext/nokogiri/include/libxml2/libxml/xmlreader.h +428 -0
  55. data/ext/nokogiri/include/libxml2/libxml/xmlregexp.h +222 -0
  56. data/ext/nokogiri/include/libxml2/libxml/xmlsave.h +88 -0
  57. data/ext/nokogiri/include/libxml2/libxml/xmlschemas.h +246 -0
  58. data/ext/nokogiri/include/libxml2/libxml/xmlschemastypes.h +151 -0
  59. data/ext/nokogiri/include/libxml2/libxml/xmlstring.h +140 -0
  60. data/ext/nokogiri/include/libxml2/libxml/xmlunicode.h +202 -0
  61. data/ext/nokogiri/include/libxml2/libxml/xmlversion.h +485 -0
  62. data/ext/nokogiri/include/libxml2/libxml/xmlwriter.h +488 -0
  63. data/ext/nokogiri/include/libxml2/libxml/xpath.h +564 -0
  64. data/ext/nokogiri/include/libxml2/libxml/xpathInternals.h +632 -0
  65. data/ext/nokogiri/include/libxml2/libxml/xpointer.h +114 -0
  66. data/ext/nokogiri/include/libxslt/attributes.h +38 -0
  67. data/ext/nokogiri/include/libxslt/documents.h +93 -0
  68. data/ext/nokogiri/include/libxslt/extensions.h +262 -0
  69. data/ext/nokogiri/include/libxslt/extra.h +72 -0
  70. data/ext/nokogiri/include/libxslt/functions.h +78 -0
  71. data/ext/nokogiri/include/libxslt/imports.h +75 -0
  72. data/ext/nokogiri/include/libxslt/keys.h +53 -0
  73. data/ext/nokogiri/include/libxslt/namespaces.h +68 -0
  74. data/ext/nokogiri/include/libxslt/numbersInternals.h +73 -0
  75. data/ext/nokogiri/include/libxslt/pattern.h +84 -0
  76. data/ext/nokogiri/include/libxslt/preproc.h +43 -0
  77. data/ext/nokogiri/include/libxslt/security.h +104 -0
  78. data/ext/nokogiri/include/libxslt/templates.h +77 -0
  79. data/ext/nokogiri/include/libxslt/transform.h +207 -0
  80. data/ext/nokogiri/include/libxslt/variables.h +118 -0
  81. data/ext/nokogiri/include/libxslt/xslt.h +110 -0
  82. data/ext/nokogiri/include/libxslt/xsltInternals.h +1978 -0
  83. data/ext/nokogiri/include/libxslt/xsltconfig.h +180 -0
  84. data/ext/nokogiri/include/libxslt/xsltexports.h +142 -0
  85. data/ext/nokogiri/include/libxslt/xsltlocale.h +76 -0
  86. data/ext/nokogiri/include/libxslt/xsltutils.h +313 -0
  87. data/ext/nokogiri/libxml2_backwards_compat.c +121 -0
  88. data/ext/nokogiri/nokogiri.c +278 -0
  89. data/ext/nokogiri/nokogiri.h +223 -0
  90. data/ext/nokogiri/test_global_handlers.c +40 -0
  91. data/ext/nokogiri/xml_attr.c +103 -0
  92. data/ext/nokogiri/xml_attribute_decl.c +70 -0
  93. data/ext/nokogiri/xml_cdata.c +57 -0
  94. data/ext/nokogiri/xml_comment.c +62 -0
  95. data/ext/nokogiri/xml_document.c +680 -0
  96. data/ext/nokogiri/xml_document_fragment.c +44 -0
  97. data/ext/nokogiri/xml_dtd.c +208 -0
  98. data/ext/nokogiri/xml_element_content.c +128 -0
  99. data/ext/nokogiri/xml_element_decl.c +69 -0
  100. data/ext/nokogiri/xml_encoding_handler.c +104 -0
  101. data/ext/nokogiri/xml_entity_decl.c +112 -0
  102. data/ext/nokogiri/xml_entity_reference.c +50 -0
  103. data/ext/nokogiri/xml_namespace.c +120 -0
  104. data/ext/nokogiri/xml_node.c +2144 -0
  105. data/ext/nokogiri/xml_node_set.c +498 -0
  106. data/ext/nokogiri/xml_processing_instruction.c +54 -0
  107. data/ext/nokogiri/xml_reader.c +719 -0
  108. data/ext/nokogiri/xml_relax_ng.c +185 -0
  109. data/ext/nokogiri/xml_sax_parser.c +310 -0
  110. data/ext/nokogiri/xml_sax_parser_context.c +281 -0
  111. data/ext/nokogiri/xml_sax_push_parser.c +168 -0
  112. data/ext/nokogiri/xml_schema.c +284 -0
  113. data/ext/nokogiri/xml_syntax_error.c +85 -0
  114. data/ext/nokogiri/xml_text.c +48 -0
  115. data/ext/nokogiri/xml_xpath_context.c +406 -0
  116. data/ext/nokogiri/xslt_stylesheet.c +264 -0
  117. data/gumbo-parser/CHANGES.md +63 -0
  118. data/gumbo-parser/Makefile +101 -0
  119. data/gumbo-parser/THANKS +27 -0
  120. data/lib/nokogiri/3.1/nokogiri.so +0 -0
  121. data/lib/nokogiri/class_resolver.rb +67 -0
  122. data/lib/nokogiri/css/node.rb +54 -0
  123. data/lib/nokogiri/css/parser.rb +759 -0
  124. data/lib/nokogiri/css/parser.y +280 -0
  125. data/lib/nokogiri/css/parser_extras.rb +94 -0
  126. data/lib/nokogiri/css/syntax_error.rb +9 -0
  127. data/lib/nokogiri/css/tokenizer.rb +155 -0
  128. data/lib/nokogiri/css/tokenizer.rex +56 -0
  129. data/lib/nokogiri/css/xpath_visitor.rb +359 -0
  130. data/lib/nokogiri/css.rb +60 -0
  131. data/lib/nokogiri/decorators/slop.rb +44 -0
  132. data/lib/nokogiri/extension.rb +31 -0
  133. data/lib/nokogiri/gumbo.rb +15 -0
  134. data/lib/nokogiri/html.rb +48 -0
  135. data/lib/nokogiri/html4/builder.rb +37 -0
  136. data/lib/nokogiri/html4/document.rb +331 -0
  137. data/lib/nokogiri/html4/document_fragment.rb +54 -0
  138. data/lib/nokogiri/html4/element_description.rb +25 -0
  139. data/lib/nokogiri/html4/element_description_defaults.rb +578 -0
  140. data/lib/nokogiri/html4/entity_lookup.rb +15 -0
  141. data/lib/nokogiri/html4/sax/parser.rb +61 -0
  142. data/lib/nokogiri/html4/sax/parser_context.rb +20 -0
  143. data/lib/nokogiri/html4/sax/push_parser.rb +37 -0
  144. data/lib/nokogiri/html4.rb +46 -0
  145. data/lib/nokogiri/html5/document.rb +88 -0
  146. data/lib/nokogiri/html5/document_fragment.rb +83 -0
  147. data/lib/nokogiri/html5/node.rb +96 -0
  148. data/lib/nokogiri/html5.rb +477 -0
  149. data/lib/nokogiri/jruby/dependencies.rb +21 -0
  150. data/lib/nokogiri/syntax_error.rb +6 -0
  151. data/lib/nokogiri/version/constant.rb +6 -0
  152. data/lib/nokogiri/version/info.rb +221 -0
  153. data/lib/nokogiri/version.rb +4 -0
  154. data/lib/nokogiri/xml/attr.rb +17 -0
  155. data/lib/nokogiri/xml/attribute_decl.rb +20 -0
  156. data/lib/nokogiri/xml/builder.rb +485 -0
  157. data/lib/nokogiri/xml/cdata.rb +13 -0
  158. data/lib/nokogiri/xml/character_data.rb +9 -0
  159. data/lib/nokogiri/xml/document.rb +418 -0
  160. data/lib/nokogiri/xml/document_fragment.rb +162 -0
  161. data/lib/nokogiri/xml/dtd.rb +34 -0
  162. data/lib/nokogiri/xml/element_content.rb +38 -0
  163. data/lib/nokogiri/xml/element_decl.rb +15 -0
  164. data/lib/nokogiri/xml/entity_decl.rb +21 -0
  165. data/lib/nokogiri/xml/entity_reference.rb +20 -0
  166. data/lib/nokogiri/xml/namespace.rb +16 -0
  167. data/lib/nokogiri/xml/node/save_options.rb +65 -0
  168. data/lib/nokogiri/xml/node.rb +1402 -0
  169. data/lib/nokogiri/xml/node_set.rb +364 -0
  170. data/lib/nokogiri/xml/notation.rb +19 -0
  171. data/lib/nokogiri/xml/parse_options.rb +133 -0
  172. data/lib/nokogiri/xml/pp/character_data.rb +21 -0
  173. data/lib/nokogiri/xml/pp/node.rb +55 -0
  174. data/lib/nokogiri/xml/pp.rb +4 -0
  175. data/lib/nokogiri/xml/processing_instruction.rb +10 -0
  176. data/lib/nokogiri/xml/reader.rb +107 -0
  177. data/lib/nokogiri/xml/relax_ng.rb +38 -0
  178. data/lib/nokogiri/xml/sax/document.rb +167 -0
  179. data/lib/nokogiri/xml/sax/parser.rb +125 -0
  180. data/lib/nokogiri/xml/sax/parser_context.rb +21 -0
  181. data/lib/nokogiri/xml/sax/push_parser.rb +61 -0
  182. data/lib/nokogiri/xml/sax.rb +6 -0
  183. data/lib/nokogiri/xml/schema.rb +73 -0
  184. data/lib/nokogiri/xml/searchable.rb +259 -0
  185. data/lib/nokogiri/xml/syntax_error.rb +71 -0
  186. data/lib/nokogiri/xml/text.rb +11 -0
  187. data/lib/nokogiri/xml/xpath/syntax_error.rb +13 -0
  188. data/lib/nokogiri/xml/xpath.rb +21 -0
  189. data/lib/nokogiri/xml/xpath_context.rb +16 -0
  190. data/lib/nokogiri/xml.rb +75 -0
  191. data/lib/nokogiri/xslt/stylesheet.rb +27 -0
  192. data/lib/nokogiri/xslt.rb +58 -0
  193. data/lib/nokogiri.rb +128 -0
  194. data/lib/xsd/xmlparser/nokogiri.rb +104 -0
  195. metadata +536 -0
@@ -0,0 +1,1402 @@
1
+ # encoding: utf-8
2
+ # frozen_string_literal: true
3
+
4
+ require "stringio"
5
+
6
+ module Nokogiri
7
+ module XML
8
+ # Nokogiri::XML::Node is the primary API you'll use to interact with your Document.
9
+ #
10
+ # == Attributes
11
+ #
12
+ # A Nokogiri::XML::Node may be treated similarly to a hash with regard to attributes. For
13
+ # example:
14
+ #
15
+ # node = Nokogiri::XML::DocumentFragment.parse("<a href='#foo' id='link'>link</a>").at_css("a")
16
+ # node.to_html # => "<a href=\"#foo\" id=\"link\">link</a>"
17
+ # node['href'] # => "#foo"
18
+ # node.keys # => ["href", "id"]
19
+ # node.values # => ["#foo", "link"]
20
+ # node['class'] = 'green' # => "green"
21
+ # node.to_html # => "<a href=\"#foo\" id=\"link\" class=\"green\">link</a>"
22
+ #
23
+ # See the method group entitled Node@Working+With+Node+Attributes for the full set of methods.
24
+ #
25
+ # == Navigation
26
+ #
27
+ # Nokogiri::XML::Node also has methods that let you move around your tree:
28
+ #
29
+ # [#parent, #children, #next, #previous]
30
+ # Navigate up, down, or through siblings.
31
+ #
32
+ # See the method group entitled Node@Traversing+Document+Structure for the full set of methods.
33
+ #
34
+ # == Serialization
35
+ #
36
+ # When printing or otherwise emitting a document or a node (and its subtree), there are a few
37
+ # methods you might want to use:
38
+ #
39
+ # [#content, #text, #inner_text, #to_str]
40
+ # These methods will all **emit plaintext**,
41
+ # meaning that entities will be replaced (e.g., +&lt;+ will be replaced with +<+), meaning
42
+ # that any sanitizing will likely be un-done in the output.
43
+ #
44
+ # [#to_s, #to_xml, #to_html, #inner_html]
45
+ # These methods will all **emit properly-escaped markup**, meaning that it's suitable for
46
+ # consumption by browsers, parsers, etc.
47
+ #
48
+ # See the method group entitled Node@Serialization+and+Generating+Output for the full set of methods.
49
+ #
50
+ # == Searching
51
+ #
52
+ # You may search this node's subtree using methods like #xpath and #css.
53
+ #
54
+ # See the method group entitled Node@Searching+via+XPath+or+CSS+Queries for the full set of methods.
55
+ #
56
+ class Node
57
+ include Nokogiri::XML::PP::Node
58
+ include Nokogiri::XML::Searchable
59
+ include Nokogiri::ClassResolver
60
+ include Enumerable
61
+
62
+ # Element node type, see Nokogiri::XML::Node#element?
63
+ ELEMENT_NODE = 1
64
+ # Attribute node type
65
+ ATTRIBUTE_NODE = 2
66
+ # Text node type, see Nokogiri::XML::Node#text?
67
+ TEXT_NODE = 3
68
+ # CDATA node type, see Nokogiri::XML::Node#cdata?
69
+ CDATA_SECTION_NODE = 4
70
+ # Entity reference node type
71
+ ENTITY_REF_NODE = 5
72
+ # Entity node type
73
+ ENTITY_NODE = 6
74
+ # PI node type
75
+ PI_NODE = 7
76
+ # Comment node type, see Nokogiri::XML::Node#comment?
77
+ COMMENT_NODE = 8
78
+ # Document node type, see Nokogiri::XML::Node#xml?
79
+ DOCUMENT_NODE = 9
80
+ # Document type node type
81
+ DOCUMENT_TYPE_NODE = 10
82
+ # Document fragment node type
83
+ DOCUMENT_FRAG_NODE = 11
84
+ # Notation node type
85
+ NOTATION_NODE = 12
86
+ # HTML document node type, see Nokogiri::XML::Node#html?
87
+ HTML_DOCUMENT_NODE = 13
88
+ # DTD node type
89
+ DTD_NODE = 14
90
+ # Element declaration type
91
+ ELEMENT_DECL = 15
92
+ # Attribute declaration type
93
+ ATTRIBUTE_DECL = 16
94
+ # Entity declaration type
95
+ ENTITY_DECL = 17
96
+ # Namespace declaration type
97
+ NAMESPACE_DECL = 18
98
+ # XInclude start type
99
+ XINCLUDE_START = 19
100
+ # XInclude end type
101
+ XINCLUDE_END = 20
102
+ # DOCB document node type
103
+ DOCB_DOCUMENT_NODE = 21
104
+
105
+ #
106
+ # :call-seq:
107
+ # new(name, document) -> Nokogiri::XML::Node
108
+ # new(name, document) { |node| ... } -> Nokogiri::XML::Node
109
+ #
110
+ # Create a new node with +name+ that belongs to +document+.
111
+ #
112
+ # If you intend to add a node to a document tree, it's likely that you will prefer one of the
113
+ # Nokogiri::XML::Node methods like #add_child, #add_next_sibling, #replace, etc. which will
114
+ # both create an element (or subtree) and place it in the document tree.
115
+ #
116
+ # Another alternative, if you are concerned about performance, is
117
+ # Nokogiri::XML::Document#create_element which accepts additional arguments for contents or
118
+ # attributes but (like this method) avoids parsing markup.
119
+ #
120
+ # [Parameters]
121
+ # - +name+ (String)
122
+ # - +document+ (Nokogiri::XML::Document) The document to which the the returned node will belong.
123
+ # [Yields] Nokogiri::XML::Node
124
+ # [Returns] Nokogiri::XML::Node
125
+ #
126
+ def initialize(name, document)
127
+ # This is intentionally empty.
128
+ end
129
+
130
+ ###
131
+ # Decorate this node with the decorators set up in this node's Document
132
+ def decorate!
133
+ document.decorate(self)
134
+ end
135
+
136
+ # :section: Manipulating Document Structure
137
+
138
+ ###
139
+ # Add +node_or_tags+ as a child of this Node.
140
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
141
+ #
142
+ # Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is a DocumentFragment, NodeSet, or string).
143
+ #
144
+ # Also see related method +<<+.
145
+ def add_child(node_or_tags)
146
+ node_or_tags = coerce(node_or_tags)
147
+ if node_or_tags.is_a?(XML::NodeSet)
148
+ node_or_tags.each { |n| add_child_node_and_reparent_attrs(n) }
149
+ else
150
+ add_child_node_and_reparent_attrs(node_or_tags)
151
+ end
152
+ node_or_tags
153
+ end
154
+
155
+ ###
156
+ # Add +node_or_tags+ as the first child of this Node.
157
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
158
+ #
159
+ # Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is a DocumentFragment, NodeSet, or string).
160
+ #
161
+ # Also see related method +add_child+.
162
+ def prepend_child(node_or_tags)
163
+ if (first = children.first)
164
+ # Mimic the error add_child would raise.
165
+ raise "Document already has a root node" if document? && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
166
+ first.__send__(:add_sibling, :previous, node_or_tags)
167
+ else
168
+ add_child(node_or_tags)
169
+ end
170
+ end
171
+
172
+ ###
173
+ # Add html around this node
174
+ #
175
+ # Returns self
176
+ def wrap(html)
177
+ new_parent = document.parse(html).first
178
+ add_next_sibling(new_parent)
179
+ new_parent.add_child(self)
180
+ self
181
+ end
182
+
183
+ ###
184
+ # Add +node_or_tags+ as a child of this Node.
185
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
186
+ #
187
+ # Returns self, to support chaining of calls (e.g., root << child1 << child2)
188
+ #
189
+ # Also see related method +add_child+.
190
+ def <<(node_or_tags)
191
+ add_child(node_or_tags)
192
+ self
193
+ end
194
+
195
+ ###
196
+ # Insert +node_or_tags+ before this Node (as a sibling).
197
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
198
+ #
199
+ # Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is a DocumentFragment, NodeSet, or string).
200
+ #
201
+ # Also see related method +before+.
202
+ def add_previous_sibling(node_or_tags)
203
+ raise ArgumentError,
204
+ "A document may not have multiple root nodes." if parent&.document? && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
205
+
206
+ add_sibling(:previous, node_or_tags)
207
+ end
208
+
209
+ ###
210
+ # Insert +node_or_tags+ after this Node (as a sibling).
211
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
212
+ #
213
+ # Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is a DocumentFragment, NodeSet, or string).
214
+ #
215
+ # Also see related method +after+.
216
+ def add_next_sibling(node_or_tags)
217
+ raise ArgumentError,
218
+ "A document may not have multiple root nodes." if parent&.document? && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
219
+
220
+ add_sibling(:next, node_or_tags)
221
+ end
222
+
223
+ ####
224
+ # Insert +node_or_tags+ before this node (as a sibling).
225
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
226
+ #
227
+ # Returns self, to support chaining of calls.
228
+ #
229
+ # Also see related method +add_previous_sibling+.
230
+ def before(node_or_tags)
231
+ add_previous_sibling(node_or_tags)
232
+ self
233
+ end
234
+
235
+ ####
236
+ # Insert +node_or_tags+ after this node (as a sibling).
237
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a string containing markup.
238
+ #
239
+ # Returns self, to support chaining of calls.
240
+ #
241
+ # Also see related method +add_next_sibling+.
242
+ def after(node_or_tags)
243
+ add_next_sibling(node_or_tags)
244
+ self
245
+ end
246
+
247
+ ####
248
+ # Set the inner html for this Node to +node_or_tags+
249
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a string containing markup.
250
+ #
251
+ # Also see related method +children=+
252
+ def inner_html=(node_or_tags)
253
+ self.children = node_or_tags
254
+ end
255
+
256
+ ####
257
+ # Set the inner html for this Node +node_or_tags+
258
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a string containing markup.
259
+ #
260
+ # Also see related method +inner_html=+
261
+ def children=(node_or_tags)
262
+ node_or_tags = coerce(node_or_tags)
263
+ children.unlink
264
+ if node_or_tags.is_a?(XML::NodeSet)
265
+ node_or_tags.each { |n| add_child_node_and_reparent_attrs(n) }
266
+ else
267
+ add_child_node_and_reparent_attrs(node_or_tags)
268
+ end
269
+ end
270
+
271
+ ####
272
+ # Replace this Node with +node_or_tags+.
273
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
274
+ #
275
+ # Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is a DocumentFragment, NodeSet, or string).
276
+ #
277
+ # Also see related method +swap+.
278
+ def replace(node_or_tags)
279
+ raise("Cannot replace a node with no parent") unless parent
280
+
281
+ # We cannot replace a text node directly, otherwise libxml will return
282
+ # an internal error at parser.c:13031, I don't know exactly why
283
+ # libxml is trying to find a parent node that is an element or document
284
+ # so I can't tell if this is bug in libxml or not. issue #775.
285
+ if text?
286
+ replacee = Nokogiri::XML::Node.new("dummy", document)
287
+ add_previous_sibling_node(replacee)
288
+ unlink
289
+ return replacee.replace(node_or_tags)
290
+ end
291
+
292
+ node_or_tags = parent.coerce(node_or_tags)
293
+
294
+ if node_or_tags.is_a?(XML::NodeSet)
295
+ node_or_tags.each { |n| add_previous_sibling(n) }
296
+ unlink
297
+ else
298
+ replace_node(node_or_tags)
299
+ end
300
+ node_or_tags
301
+ end
302
+
303
+ ####
304
+ # Swap this Node for +node_or_tags+
305
+ # +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
306
+ #
307
+ # Returns self, to support chaining of calls.
308
+ #
309
+ # Also see related method +replace+.
310
+ def swap(node_or_tags)
311
+ replace(node_or_tags)
312
+ self
313
+ end
314
+
315
+ ####
316
+ # Set the Node's content to a Text node containing +string+. The string gets XML escaped, not interpreted as markup.
317
+ def content=(string)
318
+ self.native_content = encode_special_chars(string.to_s)
319
+ end
320
+
321
+ ###
322
+ # Set the parent Node for this Node
323
+ def parent=(parent_node)
324
+ parent_node.add_child(self)
325
+ end
326
+
327
+ ###
328
+ # Adds a default namespace supplied as a string +url+ href, to self.
329
+ # The consequence is as an xmlns attribute with supplied argument were
330
+ # present in parsed XML. A default namespace set with this method will
331
+ # now show up in #attributes, but when this node is serialized to XML an
332
+ # "xmlns" attribute will appear. See also #namespace and #namespace=
333
+ def default_namespace=(url)
334
+ add_namespace_definition(nil, url)
335
+ end
336
+
337
+ ###
338
+ # Set the default namespace on this node (as would be defined with an
339
+ # "xmlns=" attribute in XML source), as a Namespace object +ns+. Note that
340
+ # a Namespace added this way will NOT be serialized as an xmlns attribute
341
+ # for this node. You probably want #default_namespace= instead, or perhaps
342
+ # #add_namespace_definition with a nil prefix argument.
343
+ def namespace=(ns)
344
+ return set_namespace(ns) unless ns
345
+
346
+ unless Nokogiri::XML::Namespace === ns
347
+ raise TypeError, "#{ns.class} can't be coerced into Nokogiri::XML::Namespace"
348
+ end
349
+ if ns.document != document
350
+ raise ArgumentError, "namespace must be declared on the same document"
351
+ end
352
+
353
+ set_namespace(ns)
354
+ end
355
+
356
+ ###
357
+ # Do xinclude substitution on the subtree below node. If given a block, a
358
+ # Nokogiri::XML::ParseOptions object initialized from +options+, will be
359
+ # passed to it, allowing more convenient modification of the parser options.
360
+ def do_xinclude(options = XML::ParseOptions::DEFAULT_XML)
361
+ options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
362
+ yield options if block_given?
363
+
364
+ # call c extension
365
+ process_xincludes(options.to_i)
366
+ end
367
+
368
+ alias_method :next, :next_sibling
369
+ alias_method :previous, :previous_sibling
370
+ alias_method :next=, :add_next_sibling
371
+ alias_method :previous=, :add_previous_sibling
372
+ alias_method :remove, :unlink
373
+ alias_method :name=, :node_name=
374
+ alias_method :add_namespace, :add_namespace_definition
375
+
376
+ # :section:
377
+
378
+ alias_method :inner_text, :content
379
+ alias_method :text, :content
380
+ alias_method :to_str, :content
381
+ alias_method :name, :node_name
382
+ alias_method :type, :node_type
383
+ alias_method :clone, :dup
384
+ alias_method :elements, :element_children
385
+
386
+ # :section: Working With Node Attributes
387
+
388
+ # :call-seq: [](name) → (String, nil)
389
+ #
390
+ # Fetch an attribute from this node.
391
+ #
392
+ # ⚠ Note that attributes with namespaces cannot be accessed with this method. To access
393
+ # namespaced attributes, use #attribute_with_ns.
394
+ #
395
+ # [Returns] (String, nil) value of the attribute +name+, or +nil+ if no matching attribute exists
396
+ #
397
+ # *Example*
398
+ #
399
+ # doc = Nokogiri::XML("<root><child size='large' class='big wide tall'/></root>")
400
+ # child = doc.at_css("child")
401
+ # child["size"] # => "large"
402
+ # child["class"] # => "big wide tall"
403
+ #
404
+ # *Example:* Namespaced attributes will not be returned.
405
+ #
406
+ # ⚠ Note namespaced attributes may be accessed with #attribute or #attribute_with_ns
407
+ #
408
+ # doc = Nokogiri::XML(<<~EOF)
409
+ # <root xmlns:width='http://example.com/widths'>
410
+ # <child width:size='broad'/>
411
+ # </root>
412
+ # EOF
413
+ # doc.at_css("child")["size"] # => nil
414
+ # doc.at_css("child").attribute("size").value # => "broad"
415
+ # doc.at_css("child").attribute_with_ns("size", "http://example.com/widths").value
416
+ # # => "broad"
417
+ #
418
+ def [](name)
419
+ get(name.to_s)
420
+ end
421
+
422
+ # :call-seq: []=(name, value) → value
423
+ #
424
+ # Update the attribute +name+ to +value+, or create the attribute if it does not exist.
425
+ #
426
+ # ⚠ Note that attributes with namespaces cannot be accessed with this method. To access
427
+ # namespaced attributes for update, use #attribute_with_ns. To add a namespaced attribute,
428
+ # see the example below.
429
+ #
430
+ # [Returns] +value+
431
+ #
432
+ # *Example*
433
+ #
434
+ # doc = Nokogiri::XML("<root><child/></root>")
435
+ # child = doc.at_css("child")
436
+ # child["size"] = "broad"
437
+ # child.to_html
438
+ # # => "<child size=\"broad\"></child>"
439
+ #
440
+ # *Example:* Add a namespaced attribute.
441
+ #
442
+ # doc = Nokogiri::XML(<<~EOF)
443
+ # <root xmlns:width='http://example.com/widths'>
444
+ # <child/>
445
+ # </root>
446
+ # EOF
447
+ # child = doc.at_css("child")
448
+ # child["size"] = "broad"
449
+ # ns = doc.root.namespace_definitions.find { |ns| ns.prefix == "width" }
450
+ # child.attribute("size").namespace = ns
451
+ # doc.to_html
452
+ # # => "<root xmlns:width=\"http://example.com/widths\">\n" +
453
+ # # " <child width:size=\"broad\"></child>\n" +
454
+ # # "</root>\n"
455
+ #
456
+ def []=(name, value)
457
+ set(name.to_s, value.to_s)
458
+ end
459
+
460
+ #
461
+ # :call-seq: attributes() → Hash<String ⇒ Nokogiri::XML::Attr>
462
+ #
463
+ # Fetch this node's attributes.
464
+ #
465
+ # ⚠ Because the keys do not include any namespace information for the attribute, in case of a
466
+ # simple name collision, not all attributes will be returned. In this case, you will need to
467
+ # use #attribute_nodes.
468
+ #
469
+ # [Returns]
470
+ # Hash containing attributes belonging to +self+. The hash keys are String attribute
471
+ # names (without the namespace), and the hash values are Nokogiri::XML::Attr.
472
+ #
473
+ # *Example* with no namespaces:
474
+ #
475
+ # doc = Nokogiri::XML("<root><child size='large' class='big wide tall'/></root>")
476
+ # doc.at_css("child").attributes
477
+ # # => {"size"=>#(Attr:0x550 { name = "size", value = "large" }),
478
+ # # "class"=>#(Attr:0x564 { name = "class", value = "big wide tall" })}
479
+ #
480
+ # *Example* with a namespace:
481
+ #
482
+ # doc = Nokogiri::XML("<root xmlns:desc='http://example.com/sizes'><child desc:size='large'/></root>")
483
+ # doc.at_css("child").attributes
484
+ # # => {"size"=>
485
+ # # #(Attr:0x550 {
486
+ # # name = "size",
487
+ # # namespace = #(Namespace:0x564 {
488
+ # # prefix = "desc",
489
+ # # href = "http://example.com/sizes"
490
+ # # }),
491
+ # # value = "large"
492
+ # # })}
493
+ #
494
+ # *Example* with an attribute name collision:
495
+ #
496
+ # ⚠ Note that only one of the attributes is returned in the Hash.
497
+ #
498
+ # doc = Nokogiri::XML(<<~EOF)
499
+ # <root xmlns:width='http://example.com/widths'
500
+ # xmlns:height='http://example.com/heights'>
501
+ # <child width:size='broad' height:size='tall'/>
502
+ # </root>
503
+ # EOF
504
+ # doc.at_css("child").attributes
505
+ # # => {"size"=>
506
+ # # #(Attr:0x550 {
507
+ # # name = "size",
508
+ # # namespace = #(Namespace:0x564 {
509
+ # # prefix = "height",
510
+ # # href = "http://example.com/heights"
511
+ # # }),
512
+ # # value = "tall"
513
+ # # })}
514
+ #
515
+ def attributes
516
+ attribute_nodes.each_with_object({}) do |node, hash|
517
+ hash[node.node_name] = node
518
+ end
519
+ end
520
+
521
+ ###
522
+ # Get the attribute values for this Node.
523
+ def values
524
+ attribute_nodes.map(&:value)
525
+ end
526
+
527
+ ###
528
+ # Does this Node's attributes include <value>
529
+ def value?(value)
530
+ values.include?(value)
531
+ end
532
+
533
+ ###
534
+ # Get the attribute names for this Node.
535
+ def keys
536
+ attribute_nodes.map(&:node_name)
537
+ end
538
+
539
+ ###
540
+ # Iterate over each attribute name and value pair for this Node.
541
+ def each
542
+ attribute_nodes.each do |node|
543
+ yield [node.node_name, node.value]
544
+ end
545
+ end
546
+
547
+ ###
548
+ # Remove the attribute named +name+
549
+ def remove_attribute(name)
550
+ attr = attributes[name].remove if key?(name)
551
+ clear_xpath_context if Nokogiri.jruby?
552
+ attr
553
+ end
554
+
555
+ #
556
+ # :call-seq: classes() → Array<String>
557
+ #
558
+ # Fetch CSS class names of a Node.
559
+ #
560
+ # This is a convenience function and is equivalent to:
561
+ #
562
+ # node.kwattr_values("class")
563
+ #
564
+ # See related: #kwattr_values, #add_class, #append_class, #remove_class
565
+ #
566
+ # [Returns]
567
+ # The CSS classes (Array of String) present in the Node's "class" attribute. If the
568
+ # attribute is empty or non-existent, the return value is an empty array.
569
+ #
570
+ # *Example*
571
+ #
572
+ # node # => <div class="section title header"></div>
573
+ # node.classes # => ["section", "title", "header"]
574
+ #
575
+ def classes
576
+ kwattr_values("class")
577
+ end
578
+
579
+ #
580
+ # :call-seq: add_class(names) → self
581
+ #
582
+ # Ensure HTML CSS classes are present on +self+. Any CSS classes in +names+ that already exist
583
+ # in the "class" attribute are _not_ added. Note that any existing duplicates in the
584
+ # "class" attribute are not removed. Compare with #append_class.
585
+ #
586
+ # This is a convenience function and is equivalent to:
587
+ #
588
+ # node.kwattr_add("class", names)
589
+ #
590
+ # See related: #kwattr_add, #classes, #append_class, #remove_class
591
+ #
592
+ # [Parameters]
593
+ # - +names+ (String, Array<String>)
594
+ #
595
+ # CSS class names to be added to the Node's "class" attribute. May be a string containing
596
+ # whitespace-delimited names, or an Array of String names. Any class names already present
597
+ # will not be added. Any class names not present will be added. If no "class" attribute
598
+ # exists, one is created.
599
+ #
600
+ # [Returns] +self+ (Node) for ease of chaining method calls.
601
+ #
602
+ # *Example:* Ensure that the node has CSS class "section"
603
+ #
604
+ # node # => <div></div>
605
+ # node.add_class("section") # => <div class="section"></div>
606
+ # node.add_class("section") # => <div class="section"></div> # duplicate not added
607
+ #
608
+ # *Example:* Ensure that the node has CSS classes "section" and "header", via a String argument
609
+ #
610
+ # Note that the CSS class "section" is not added because it is already present.
611
+ # Note also that the pre-existing duplicate CSS class "section" is not removed.
612
+ #
613
+ # node # => <div class="section section"></div>
614
+ # node.add_class("section header") # => <div class="section section header"></div>
615
+ #
616
+ # *Example:* Ensure that the node has CSS classes "section" and "header", via an Array argument
617
+ #
618
+ # node # => <div></div>
619
+ # node.add_class(["section", "header"]) # => <div class="section header"></div>
620
+ #
621
+ def add_class(names)
622
+ kwattr_add("class", names)
623
+ end
624
+
625
+ #
626
+ # :call-seq: append_class(names) → self
627
+ #
628
+ # Add HTML CSS classes to +self+, regardless of duplication. Compare with #add_class.
629
+ #
630
+ # This is a convenience function and is equivalent to:
631
+ #
632
+ # node.kwattr_append("class", names)
633
+ #
634
+ # See related: #kwattr_append, #classes, #add_class, #remove_class
635
+ #
636
+ # [Parameters]
637
+ # - +names+ (String, Array<String>)
638
+ #
639
+ # CSS class names to be appended to the Node's "class" attribute. May be a string containing
640
+ # whitespace-delimited names, or an Array of String names. All class names passed in will be
641
+ # appended to the "class" attribute even if they are already present in the attribute
642
+ # value. If no "class" attribute exists, one is created.
643
+ #
644
+ # [Returns] +self+ (Node) for ease of chaining method calls.
645
+ #
646
+ # *Example:* Append "section" to the node's CSS "class" attribute
647
+ #
648
+ # node # => <div></div>
649
+ # node.append_class("section") # => <div class="section"></div>
650
+ # node.append_class("section") # => <div class="section section"></div> # duplicate added!
651
+ #
652
+ # *Example:* Append "section" and "header" to the noded's CSS "class" attribute, via a String argument
653
+ #
654
+ # Note that the CSS class "section" is appended even though it is already present
655
+ #
656
+ # node # => <div class="section section"></div>
657
+ # node.append_class("section header") # => <div class="section section section header"></div>
658
+ #
659
+ # *Example:* Append "section" and "header" to the node's CSS "class" attribute, via an Array argument
660
+ #
661
+ # node # => <div></div>
662
+ # node.append_class(["section", "header"]) # => <div class="section header"></div>
663
+ # node.append_class(["section", "header"]) # => <div class="section header section header"></div>
664
+ #
665
+ def append_class(names)
666
+ kwattr_append("class", names)
667
+ end
668
+
669
+ # :call-seq:
670
+ # remove_class(css_classes) → self
671
+ #
672
+ # Remove HTML CSS classes from this node. Any CSS class names in +css_classes+ that exist in
673
+ # this node's "class" attribute are removed, including any multiple entries.
674
+ #
675
+ # If no CSS classes remain after this operation, or if +css_classes+ is +nil+, the "class"
676
+ # attribute is deleted from the node.
677
+ #
678
+ # This is a convenience function and is equivalent to:
679
+ #
680
+ # node.kwattr_remove("class", css_classes)
681
+ #
682
+ # Also see #kwattr_remove, #classes, #add_class, #append_class
683
+ #
684
+ # [Parameters]
685
+ # - +css_classes+ (String, Array<String>)
686
+ #
687
+ # CSS class names to be removed from the Node's
688
+ # "class" attribute. May be a string containing whitespace-delimited names, or an Array of
689
+ # String names. Any class names already present will be removed. If no CSS classes remain,
690
+ # the "class" attribute is deleted.
691
+ #
692
+ # [Returns] +self+ (Nokogiri::XML::Node) for ease of chaining method calls.
693
+ #
694
+ # *Example*: Deleting a CSS class
695
+ #
696
+ # Note that all instances of the class "section" are removed from the "class" attribute.
697
+ #
698
+ # node # => <div class="section header section"></div>
699
+ # node.remove_class("section") # => <div class="header"></div>
700
+ #
701
+ # *Example*: Deleting the only remaining CSS class
702
+ #
703
+ # Note that the attribute is removed once there are no remaining classes.
704
+ #
705
+ # node # => <div class="section"></div>
706
+ # node.remove_class("section") # => <div></div>
707
+ #
708
+ # *Example*: Deleting multiple CSS classes
709
+ #
710
+ # Note that the "class" attribute is deleted once it's empty.
711
+ #
712
+ # node # => <div class="section header float"></div>
713
+ # node.remove_class(["section", "float"]) # => <div class="header"></div>
714
+ #
715
+ def remove_class(names = nil)
716
+ kwattr_remove("class", names)
717
+ end
718
+
719
+ # :call-seq:
720
+ # kwattr_values(attribute_name) → Array<String>
721
+ #
722
+ # Fetch values from a keyword attribute of a Node.
723
+ #
724
+ # A "keyword attribute" is a node attribute that contains a set of space-delimited
725
+ # values. Perhaps the most familiar example of this is the HTML "class" attribute used to
726
+ # contain CSS classes. But other keyword attributes exist, for instance
727
+ # {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
728
+ #
729
+ # See also #classes, #kwattr_add, #kwattr_append, #kwattr_remove
730
+ #
731
+ # [Parameters]
732
+ # - +attribute_name+ (String) The name of the keyword attribute to be inspected.
733
+ #
734
+ # [Returns]
735
+ # (Array<String>) The values present in the Node's +attribute_name+ attribute. If the
736
+ # attribute is empty or non-existent, the return value is an empty array.
737
+ #
738
+ # *Example:*
739
+ #
740
+ # node # => <a rel="nofollow noopener external">link</a>
741
+ # node.kwattr_values("rel") # => ["nofollow", "noopener", "external"]
742
+ #
743
+ # Since v1.11.0
744
+ def kwattr_values(attribute_name)
745
+ keywordify(get_attribute(attribute_name) || [])
746
+ end
747
+
748
+ # :call-seq:
749
+ # kwattr_add(attribute_name, keywords) → self
750
+ #
751
+ # Ensure that values are present in a keyword attribute.
752
+ #
753
+ # Any values in +keywords+ that already exist in the Node's attribute values are _not_
754
+ # added. Note that any existing duplicates in the attribute values are not removed. Compare
755
+ # with #kwattr_append.
756
+ #
757
+ # A "keyword attribute" is a node attribute that contains a set of space-delimited
758
+ # values. Perhaps the most familiar example of this is the HTML "class" attribute used to
759
+ # contain CSS classes. But other keyword attributes exist, for instance
760
+ # {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
761
+ #
762
+ # See also #add_class, #kwattr_values, #kwattr_append, #kwattr_remove
763
+ #
764
+ # [Parameters]
765
+ # - +attribute_name+ (String) The name of the keyword attribute to be modified.
766
+ # - +keywords+ (String, Array<String>)
767
+ # Keywords to be added to the attribute named +attribute_name+. May be a string containing
768
+ # whitespace-delimited values, or an Array of String values. Any values already present will
769
+ # not be added. Any values not present will be added. If the named attribute does not exist,
770
+ # it is created.
771
+ #
772
+ # [Returns] +self+ (Nokogiri::XML::Node) for ease of chaining method calls.
773
+ #
774
+ # *Example:* Ensure that a +Node+ has "nofollow" in its +rel+ attribute.
775
+ #
776
+ # Note that duplicates are not added.
777
+ #
778
+ # node # => <a></a>
779
+ # node.kwattr_add("rel", "nofollow") # => <a rel="nofollow"></a>
780
+ # node.kwattr_add("rel", "nofollow") # => <a rel="nofollow"></a>
781
+ #
782
+ # *Example:* Ensure that a +Node+ has "nofollow" and "noreferrer" in its +rel+ attribute, via a
783
+ # String argument.
784
+ #
785
+ # Note that "nofollow" is not added because it is already present. Note also that the
786
+ # pre-existing duplicate "nofollow" is not removed.
787
+ #
788
+ # node # => <a rel="nofollow nofollow"></a>
789
+ # node.kwattr_add("rel", "nofollow noreferrer") # => <a rel="nofollow nofollow noreferrer"></a>
790
+ #
791
+ # *Example:* Ensure that a +Node+ has "nofollow" and "noreferrer" in its +rel+ attribute, via
792
+ # an Array argument.
793
+ #
794
+ # node # => <a></a>
795
+ # node.kwattr_add("rel", ["nofollow", "noreferrer"]) # => <a rel="nofollow noreferrer"></a>
796
+ #
797
+ # Since v1.11.0
798
+ def kwattr_add(attribute_name, keywords)
799
+ keywords = keywordify(keywords)
800
+ current_kws = kwattr_values(attribute_name)
801
+ new_kws = (current_kws + (keywords - current_kws)).join(" ")
802
+ set_attribute(attribute_name, new_kws)
803
+ self
804
+ end
805
+
806
+ # :call-seq:
807
+ # kwattr_append(attribute_name, keywords) → self
808
+ #
809
+ # Add keywords to a Node's keyword attribute, regardless of duplication. Compare with
810
+ # #kwattr_add.
811
+ #
812
+ # A "keyword attribute" is a node attribute that contains a set of space-delimited
813
+ # values. Perhaps the most familiar example of this is the HTML "class" attribute used to
814
+ # contain CSS classes. But other keyword attributes exist, for instance
815
+ # {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
816
+ #
817
+ # See also #append_class, #kwattr_values, #kwattr_add, #kwattr_remove
818
+ #
819
+ # [Parameters]
820
+ # - +attribute_name+ (String) The name of the keyword attribute to be modified.
821
+ # - +keywords+ (String, Array<String>)
822
+ # Keywords to be added to the attribute named +attribute_name+. May be a string containing
823
+ # whitespace-delimited values, or an Array of String values. All values passed in will be
824
+ # appended to the named attribute even if they are already present in the attribute. If the
825
+ # named attribute does not exist, it is created.
826
+ #
827
+ # [Returns] +self+ (Node) for ease of chaining method calls.
828
+ #
829
+ # *Example:* Append "nofollow" to the +rel+ attribute.
830
+ #
831
+ # Note that duplicates are added.
832
+ #
833
+ # node # => <a></a>
834
+ # node.kwattr_append("rel", "nofollow") # => <a rel="nofollow"></a>
835
+ # node.kwattr_append("rel", "nofollow") # => <a rel="nofollow nofollow"></a>
836
+ #
837
+ # *Example:* Append "nofollow" and "noreferrer" to the +rel+ attribute, via a String argument.
838
+ #
839
+ # Note that "nofollow" is appended even though it is already present.
840
+ #
841
+ # node # => <a rel="nofollow"></a>
842
+ # node.kwattr_append("rel", "nofollow noreferrer") # => <a rel="nofollow nofollow noreferrer"></a>
843
+ #
844
+ #
845
+ # *Example:* Append "nofollow" and "noreferrer" to the +rel+ attribute, via an Array argument.
846
+ #
847
+ # node # => <a></a>
848
+ # node.kwattr_append("rel", ["nofollow", "noreferrer"]) # => <a rel="nofollow noreferrer"></a>
849
+ #
850
+ # Since v1.11.0
851
+ def kwattr_append(attribute_name, keywords)
852
+ keywords = keywordify(keywords)
853
+ current_kws = kwattr_values(attribute_name)
854
+ new_kws = (current_kws + keywords).join(" ")
855
+ set_attribute(attribute_name, new_kws)
856
+ self
857
+ end
858
+
859
+ # :call-seq:
860
+ # kwattr_remove(attribute_name, keywords) → self
861
+ #
862
+ # Remove keywords from a keyword attribute. Any matching keywords that exist in the named
863
+ # attribute are removed, including any multiple entries.
864
+ #
865
+ # If no keywords remain after this operation, or if +keywords+ is +nil+, the attribute is
866
+ # deleted from the node.
867
+ #
868
+ # A "keyword attribute" is a node attribute that contains a set of space-delimited
869
+ # values. Perhaps the most familiar example of this is the HTML "class" attribute used to
870
+ # contain CSS classes. But other keyword attributes exist, for instance
871
+ # {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
872
+ #
873
+ # See also #remove_class, #kwattr_values, #kwattr_add, #kwattr_append
874
+ #
875
+ # [Parameters]
876
+ # - +attribute_name+ (String) The name of the keyword attribute to be modified.
877
+ # - +keywords+ (String, Array<String>)
878
+ # Keywords to be removed from the attribute named +attribute_name+. May be a string
879
+ # containing whitespace-delimited values, or an Array of String values. Any keywords present
880
+ # in the named attribute will be removed. If no keywords remain, or if +keywords+ is nil,
881
+ # the attribute is deleted.
882
+ #
883
+ # [Returns] +self+ (Node) for ease of chaining method calls.
884
+ #
885
+ # *Example:*
886
+ #
887
+ # Note that the +rel+ attribute is deleted when empty.
888
+ #
889
+ # node # => <a rel="nofollow noreferrer">link</a>
890
+ # node.kwattr_remove("rel", "nofollow") # => <a rel="noreferrer">link</a>
891
+ # node.kwattr_remove("rel", "noreferrer") # => <a>link</a>
892
+ #
893
+ # Since v1.11.0
894
+ def kwattr_remove(attribute_name, keywords)
895
+ if keywords.nil?
896
+ remove_attribute(attribute_name)
897
+ return self
898
+ end
899
+
900
+ keywords = keywordify(keywords)
901
+ current_kws = kwattr_values(attribute_name)
902
+ new_kws = current_kws - keywords
903
+ if new_kws.empty?
904
+ remove_attribute(attribute_name)
905
+ else
906
+ set_attribute(attribute_name, new_kws.join(" "))
907
+ end
908
+ self
909
+ end
910
+
911
+ alias_method :delete, :remove_attribute
912
+ alias_method :get_attribute, :[]
913
+ alias_method :attr, :[]
914
+ alias_method :set_attribute, :[]=
915
+ alias_method :has_attribute?, :key?
916
+
917
+ # :section:
918
+
919
+ ###
920
+ # Returns true if this Node matches +selector+
921
+ def matches?(selector)
922
+ ancestors.last.search(selector).include?(self)
923
+ end
924
+
925
+ ###
926
+ # Create a DocumentFragment containing +tags+ that is relative to _this_
927
+ # context node.
928
+ def fragment(tags)
929
+ document.related_class("DocumentFragment").new(document, tags, self)
930
+ end
931
+
932
+ ###
933
+ # Parse +string_or_io+ as a document fragment within the context of
934
+ # *this* node. Returns a XML::NodeSet containing the nodes parsed from
935
+ # +string_or_io+.
936
+ def parse(string_or_io, options = nil)
937
+ ##
938
+ # When the current node is unparented and not an element node, use the
939
+ # document as the parsing context instead. Otherwise, the in-context
940
+ # parser cannot find an element or a document node.
941
+ # Document Fragments are also not usable by the in-context parser.
942
+ if !element? && !document? && (!parent || parent.fragment?)
943
+ return document.parse(string_or_io, options)
944
+ end
945
+
946
+ options ||= (document.html? ? ParseOptions::DEFAULT_HTML : ParseOptions::DEFAULT_XML)
947
+ options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
948
+ yield options if block_given?
949
+
950
+ contents = if string_or_io.respond_to?(:read)
951
+ string_or_io.read
952
+ else
953
+ string_or_io
954
+ end
955
+
956
+ return Nokogiri::XML::NodeSet.new(document) if contents.empty?
957
+
958
+ # libxml2 does not obey the +recover+ option after encountering errors during +in_context+
959
+ # parsing, and so this horrible hack is here to try to emulate recovery behavior.
960
+ #
961
+ # Unfortunately, this means we're no longer parsing "in context" and so namespaces that
962
+ # would have been inherited from the context node won't be handled correctly. This hack was
963
+ # written in 2010, and I regret it, because it's silently degrading functionality in a way
964
+ # that's not easily prevented (or even detected).
965
+ #
966
+ # I think preferable behavior would be to either:
967
+ #
968
+ # a. add an error noting that we "fell back" and pointing the user to turning off the +recover+ option
969
+ # b. don't recover, but raise a sensible exception
970
+ #
971
+ # For context and background: https://github.com/sparklemotion/nokogiri/issues/313
972
+ # FIXME bug report: https://github.com/sparklemotion/nokogiri/issues/2092
973
+ error_count = document.errors.length
974
+ node_set = in_context(contents, options.to_i)
975
+ if node_set.empty? && (document.errors.length > error_count)
976
+ if options.recover?
977
+ fragment = document.related_class("DocumentFragment").parse(contents)
978
+ node_set = fragment.children
979
+ else
980
+ raise document.errors[error_count]
981
+ end
982
+ end
983
+ node_set
984
+ end
985
+
986
+ # :call-seq:
987
+ # namespaces() → Hash<String(Namespace#prefix) ⇒ String(Namespace#href)>
988
+ #
989
+ # Fetch all the namespaces on this node and its ancestors.
990
+ #
991
+ # Note that the keys in this hash XML attributes that would be used to define this namespace,
992
+ # such as "xmlns:prefix", not just the prefix.
993
+ #
994
+ # The default namespace for this node will be included with key "xmlns".
995
+ #
996
+ # See also #namespace_scopes
997
+ #
998
+ # [Returns]
999
+ # Hash containing all the namespaces on this node and its ancestors. The hash keys are the
1000
+ # namespace prefix, and the hash value for each key is the namespace URI.
1001
+ #
1002
+ # *Example:*
1003
+ #
1004
+ # doc = Nokogiri::XML(<<~EOF)
1005
+ # <root xmlns="http://example.com/root" xmlns:in_scope="http://example.com/in_scope">
1006
+ # <first/>
1007
+ # <second xmlns="http://example.com/child"/>
1008
+ # <third xmlns:foo="http://example.com/foo"/>
1009
+ # </root>
1010
+ # EOF
1011
+ # doc.at_xpath("//root:first", "root" => "http://example.com/root").namespaces
1012
+ # # => {"xmlns"=>"http://example.com/root",
1013
+ # # "xmlns:in_scope"=>"http://example.com/in_scope"}
1014
+ # doc.at_xpath("//child:second", "child" => "http://example.com/child").namespaces
1015
+ # # => {"xmlns"=>"http://example.com/child",
1016
+ # # "xmlns:in_scope"=>"http://example.com/in_scope"}
1017
+ # doc.at_xpath("//root:third", "root" => "http://example.com/root").namespaces
1018
+ # # => {"xmlns:foo"=>"http://example.com/foo",
1019
+ # # "xmlns"=>"http://example.com/root",
1020
+ # # "xmlns:in_scope"=>"http://example.com/in_scope"}
1021
+ #
1022
+ def namespaces
1023
+ namespace_scopes.each_with_object({}) do |ns, hash|
1024
+ prefix = ns.prefix
1025
+ key = prefix ? "xmlns:#{prefix}" : "xmlns"
1026
+ hash[key] = ns.href
1027
+ end
1028
+ end
1029
+
1030
+ # Returns true if this is a Comment
1031
+ def comment?
1032
+ type == COMMENT_NODE
1033
+ end
1034
+
1035
+ # Returns true if this is a CDATA
1036
+ def cdata?
1037
+ type == CDATA_SECTION_NODE
1038
+ end
1039
+
1040
+ # Returns true if this is an XML::Document node
1041
+ def xml?
1042
+ type == DOCUMENT_NODE
1043
+ end
1044
+
1045
+ # Returns true if this is an HTML4::Document or HTML5::Document node
1046
+ def html?
1047
+ type == HTML_DOCUMENT_NODE
1048
+ end
1049
+
1050
+ # Returns true if this is a Document
1051
+ def document?
1052
+ is_a?(XML::Document)
1053
+ end
1054
+
1055
+ # Returns true if this is a ProcessingInstruction node
1056
+ def processing_instruction?
1057
+ type == PI_NODE
1058
+ end
1059
+
1060
+ # Returns true if this is a Text node
1061
+ def text?
1062
+ type == TEXT_NODE
1063
+ end
1064
+
1065
+ # Returns true if this is a DocumentFragment
1066
+ def fragment?
1067
+ type == DOCUMENT_FRAG_NODE
1068
+ end
1069
+
1070
+ ###
1071
+ # Fetch the Nokogiri::HTML4::ElementDescription for this node. Returns
1072
+ # nil on XML documents and on unknown tags.
1073
+ def description
1074
+ return nil if document.xml?
1075
+ Nokogiri::HTML4::ElementDescription[name]
1076
+ end
1077
+
1078
+ ###
1079
+ # Is this a read only node?
1080
+ def read_only?
1081
+ # According to gdome2, these are read-only node types
1082
+ [NOTATION_NODE, ENTITY_NODE, ENTITY_DECL].include?(type)
1083
+ end
1084
+
1085
+ # Returns true if this is an Element node
1086
+ def element?
1087
+ type == ELEMENT_NODE
1088
+ end
1089
+
1090
+ alias_method :elem?, :element?
1091
+
1092
+ ###
1093
+ # Turn this node in to a string. If the document is HTML, this method
1094
+ # returns html. If the document is XML, this method returns XML.
1095
+ def to_s
1096
+ document.xml? ? to_xml : to_html
1097
+ end
1098
+
1099
+ # Get the inner_html for this node's Node#children
1100
+ def inner_html(*args)
1101
+ children.map { |x| x.to_html(*args) }.join
1102
+ end
1103
+
1104
+ # Get the path to this node as a CSS expression
1105
+ def css_path
1106
+ path.split(%r{/}).map do |part|
1107
+ part.empty? ? nil : part.gsub(/\[(\d+)\]/, ':nth-of-type(\1)')
1108
+ end.compact.join(" > ")
1109
+ end
1110
+
1111
+ ###
1112
+ # Get a list of ancestor Node for this Node. If +selector+ is given,
1113
+ # the ancestors must match +selector+
1114
+ def ancestors(selector = nil)
1115
+ return NodeSet.new(document) unless respond_to?(:parent)
1116
+ return NodeSet.new(document) unless parent
1117
+
1118
+ parents = [parent]
1119
+
1120
+ while parents.last.respond_to?(:parent)
1121
+ break unless (ctx_parent = parents.last.parent)
1122
+ parents << ctx_parent
1123
+ end
1124
+
1125
+ return NodeSet.new(document, parents) unless selector
1126
+
1127
+ root = parents.last
1128
+ search_results = root.search(selector)
1129
+
1130
+ NodeSet.new(document, parents.find_all do |parent|
1131
+ search_results.include?(parent)
1132
+ end)
1133
+ end
1134
+
1135
+ ####
1136
+ # Yields self and all children to +block+ recursively.
1137
+ def traverse(&block)
1138
+ children.each { |j| j.traverse(&block) }
1139
+ yield(self)
1140
+ end
1141
+
1142
+ ###
1143
+ # Accept a visitor. This method calls "visit" on +visitor+ with self.
1144
+ def accept(visitor)
1145
+ visitor.visit(self)
1146
+ end
1147
+
1148
+ ###
1149
+ # Test to see if this Node is equal to +other+
1150
+ def ==(other)
1151
+ return false unless other
1152
+ return false unless other.respond_to?(:pointer_id)
1153
+ pointer_id == other.pointer_id
1154
+ end
1155
+
1156
+ ###
1157
+ # Compare two Node objects with respect to their Document. Nodes from
1158
+ # different documents cannot be compared.
1159
+ def <=>(other)
1160
+ return nil unless other.is_a?(Nokogiri::XML::Node)
1161
+ return nil unless document == other.document
1162
+ compare(other)
1163
+ end
1164
+
1165
+ # :section: Serialization and Generating Output
1166
+
1167
+ ###
1168
+ # Serialize Node using +options+. Save options can also be set using a
1169
+ # block. See SaveOptions.
1170
+ #
1171
+ # These two statements are equivalent:
1172
+ #
1173
+ # node.serialize(:encoding => 'UTF-8', :save_with => FORMAT | AS_XML)
1174
+ #
1175
+ # or
1176
+ #
1177
+ # node.serialize(:encoding => 'UTF-8') do |config|
1178
+ # config.format.as_xml
1179
+ # end
1180
+ #
1181
+ def serialize(*args, &block)
1182
+ options = if args.first.is_a?(Hash)
1183
+ args.shift
1184
+ else
1185
+ {
1186
+ encoding: args[0],
1187
+ save_with: args[1],
1188
+ }
1189
+ end
1190
+
1191
+ encoding = options[:encoding] || document.encoding
1192
+ options[:encoding] = encoding
1193
+
1194
+ outstring = +""
1195
+ outstring.force_encoding(Encoding.find(encoding || "utf-8"))
1196
+ io = StringIO.new(outstring)
1197
+ write_to(io, options, &block)
1198
+ io.string
1199
+ end
1200
+
1201
+ ###
1202
+ # Serialize this Node to HTML
1203
+ #
1204
+ # doc.to_html
1205
+ #
1206
+ # See Node#write_to for a list of +options+. For formatted output,
1207
+ # use Node#to_xhtml instead.
1208
+ def to_html(options = {})
1209
+ to_format(SaveOptions::DEFAULT_HTML, options)
1210
+ end
1211
+
1212
+ ###
1213
+ # Serialize this Node to XML using +options+
1214
+ #
1215
+ # doc.to_xml(:indent => 5, :encoding => 'UTF-8')
1216
+ #
1217
+ # See Node#write_to for a list of +options+
1218
+ def to_xml(options = {})
1219
+ options[:save_with] ||= SaveOptions::DEFAULT_XML
1220
+ serialize(options)
1221
+ end
1222
+
1223
+ ###
1224
+ # Serialize this Node to XHTML using +options+
1225
+ #
1226
+ # doc.to_xhtml(:indent => 5, :encoding => 'UTF-8')
1227
+ #
1228
+ # See Node#write_to for a list of +options+
1229
+ def to_xhtml(options = {})
1230
+ to_format(SaveOptions::DEFAULT_XHTML, options)
1231
+ end
1232
+
1233
+ ###
1234
+ # Write Node to +io+ with +options+. +options+ modify the output of
1235
+ # this method. Valid options are:
1236
+ #
1237
+ # * +:encoding+ for changing the encoding
1238
+ # * +:indent_text+ the indentation text, defaults to one space
1239
+ # * +:indent+ the number of +:indent_text+ to use, defaults to 2
1240
+ # * +:save_with+ a combination of SaveOptions constants.
1241
+ #
1242
+ # To save with UTF-8 indented twice:
1243
+ #
1244
+ # node.write_to(io, :encoding => 'UTF-8', :indent => 2)
1245
+ #
1246
+ # To save indented with two dashes:
1247
+ #
1248
+ # node.write_to(io, :indent_text => '-', :indent => 2)
1249
+ #
1250
+ def write_to(io, *options)
1251
+ options = options.first.is_a?(Hash) ? options.shift : {}
1252
+ encoding = options[:encoding] || options[0]
1253
+ if Nokogiri.jruby?
1254
+ save_options = options[:save_with] || options[1]
1255
+ indent_times = options[:indent] || 0
1256
+ else
1257
+ save_options = options[:save_with] || options[1] || SaveOptions::FORMAT
1258
+ indent_times = options[:indent] || 2
1259
+ end
1260
+ indent_text = options[:indent_text] || " "
1261
+
1262
+ # Any string times 0 returns an empty string. Therefore, use the same
1263
+ # string instead of generating a new empty string for every node with
1264
+ # zero indentation.
1265
+ indentation = indent_times.zero? ? "" : (indent_text * indent_times)
1266
+
1267
+ config = SaveOptions.new(save_options.to_i)
1268
+ yield config if block_given?
1269
+
1270
+ native_write_to(io, encoding, indentation, config.options)
1271
+ end
1272
+
1273
+ ###
1274
+ # Write Node as HTML to +io+ with +options+
1275
+ #
1276
+ # See Node#write_to for a list of +options+
1277
+ def write_html_to(io, options = {})
1278
+ write_format_to(SaveOptions::DEFAULT_HTML, io, options)
1279
+ end
1280
+
1281
+ ###
1282
+ # Write Node as XHTML to +io+ with +options+
1283
+ #
1284
+ # See Node#write_to for a list of +options+
1285
+ def write_xhtml_to(io, options = {})
1286
+ write_format_to(SaveOptions::DEFAULT_XHTML, io, options)
1287
+ end
1288
+
1289
+ ###
1290
+ # Write Node as XML to +io+ with +options+
1291
+ #
1292
+ # doc.write_xml_to io, :encoding => 'UTF-8'
1293
+ #
1294
+ # See Node#write_to for a list of options
1295
+ def write_xml_to(io, options = {})
1296
+ options[:save_with] ||= SaveOptions::DEFAULT_XML
1297
+ write_to(io, options)
1298
+ end
1299
+
1300
+ def canonicalize(mode = XML::XML_C14N_1_0, inclusive_namespaces = nil, with_comments = false)
1301
+ c14n_root = self
1302
+ document.canonicalize(mode, inclusive_namespaces, with_comments) do |node, parent|
1303
+ tn = node.is_a?(XML::Node) ? node : parent
1304
+ tn == c14n_root || tn.ancestors.include?(c14n_root)
1305
+ end
1306
+ end
1307
+
1308
+ # :section:
1309
+
1310
+ protected
1311
+
1312
+ def coerce(data)
1313
+ case data
1314
+ when XML::NodeSet
1315
+ return data
1316
+ when XML::DocumentFragment
1317
+ return data.children
1318
+ when String
1319
+ return fragment(data).children
1320
+ when Document, XML::Attr
1321
+ # unacceptable
1322
+ when XML::Node
1323
+ return data
1324
+ end
1325
+
1326
+ raise ArgumentError, <<~EOERR
1327
+ Requires a Node, NodeSet or String argument, and cannot accept a #{data.class}.
1328
+ (You probably want to select a node from the Document with at() or search(), or create a new Node via Node.new().)
1329
+ EOERR
1330
+ end
1331
+
1332
+ private
1333
+
1334
+ def keywordify(keywords)
1335
+ case keywords
1336
+ when Enumerable
1337
+ keywords
1338
+ when String
1339
+ keywords.scan(/\S+/)
1340
+ else
1341
+ raise ArgumentError,
1342
+ "Keyword attributes must be passed as either a String or an Enumerable, but received #{keywords.class}"
1343
+ end
1344
+ end
1345
+
1346
+ def add_sibling(next_or_previous, node_or_tags)
1347
+ raise("Cannot add sibling to a node with no parent") unless parent
1348
+
1349
+ impl = next_or_previous == :next ? :add_next_sibling_node : :add_previous_sibling_node
1350
+ iter = next_or_previous == :next ? :reverse_each : :each
1351
+
1352
+ node_or_tags = parent.coerce(node_or_tags)
1353
+ if node_or_tags.is_a?(XML::NodeSet)
1354
+ if text?
1355
+ pivot = Nokogiri::XML::Node.new("dummy", document)
1356
+ send(impl, pivot)
1357
+ else
1358
+ pivot = self
1359
+ end
1360
+ node_or_tags.send(iter) { |n| pivot.send(impl, n) }
1361
+ pivot.unlink if text?
1362
+ else
1363
+ send(impl, node_or_tags)
1364
+ end
1365
+ node_or_tags
1366
+ end
1367
+
1368
+ USING_LIBXML_WITH_BROKEN_SERIALIZATION = Nokogiri.uses_libxml?("~> 2.6.0").freeze
1369
+ private_constant :USING_LIBXML_WITH_BROKEN_SERIALIZATION
1370
+
1371
+ def to_format(save_option, options)
1372
+ return dump_html if USING_LIBXML_WITH_BROKEN_SERIALIZATION
1373
+
1374
+ options[:save_with] = save_option unless options[:save_with]
1375
+ serialize(options)
1376
+ end
1377
+
1378
+ def write_format_to(save_option, io, options)
1379
+ return (io << dump_html) if USING_LIBXML_WITH_BROKEN_SERIALIZATION
1380
+
1381
+ options[:save_with] ||= save_option
1382
+ write_to(io, options)
1383
+ end
1384
+
1385
+ def inspect_attributes
1386
+ [:name, :namespace, :attribute_nodes, :children]
1387
+ end
1388
+
1389
+ IMPLIED_XPATH_CONTEXTS = [".//"].freeze
1390
+
1391
+ def add_child_node_and_reparent_attrs(node)
1392
+ add_child_node(node)
1393
+ node.attribute_nodes.find_all { |a| a.name.include?(":") }.each do |attr_node|
1394
+ attr_node.remove
1395
+ node[attr_node.name] = attr_node.value
1396
+ end
1397
+ end
1398
+ end
1399
+ end
1400
+ end
1401
+
1402
+ require_relative "node/save_options"