Nokogiri_precompiled_aarch64_dedshit 1.14.5

Sign up to get free protection for your applications and to get access to all the features.
Files changed (263) hide show
  1. checksums.yaml +7 -0
  2. data/Gemfile +44 -0
  3. data/LICENSE-DEPENDENCIES.md +2224 -0
  4. data/LICENSE.md +9 -0
  5. data/README.md +287 -0
  6. data/bin/nokogiri +131 -0
  7. data/dependencies.yml +41 -0
  8. data/ext/java/nokogiri/Html4Document.java +157 -0
  9. data/ext/java/nokogiri/Html4ElementDescription.java +133 -0
  10. data/ext/java/nokogiri/Html4EntityLookup.java +63 -0
  11. data/ext/java/nokogiri/Html4SaxParserContext.java +289 -0
  12. data/ext/java/nokogiri/Html4SaxPushParser.java +213 -0
  13. data/ext/java/nokogiri/NokogiriService.java +613 -0
  14. data/ext/java/nokogiri/XmlAttr.java +154 -0
  15. data/ext/java/nokogiri/XmlAttributeDecl.java +119 -0
  16. data/ext/java/nokogiri/XmlCdata.java +60 -0
  17. data/ext/java/nokogiri/XmlComment.java +77 -0
  18. data/ext/java/nokogiri/XmlDocument.java +705 -0
  19. data/ext/java/nokogiri/XmlDocumentFragment.java +163 -0
  20. data/ext/java/nokogiri/XmlDtd.java +516 -0
  21. data/ext/java/nokogiri/XmlElement.java +44 -0
  22. data/ext/java/nokogiri/XmlElementContent.java +412 -0
  23. data/ext/java/nokogiri/XmlElementDecl.java +148 -0
  24. data/ext/java/nokogiri/XmlEntityDecl.java +151 -0
  25. data/ext/java/nokogiri/XmlEntityReference.java +79 -0
  26. data/ext/java/nokogiri/XmlNamespace.java +193 -0
  27. data/ext/java/nokogiri/XmlNode.java +1938 -0
  28. data/ext/java/nokogiri/XmlNodeSet.java +463 -0
  29. data/ext/java/nokogiri/XmlProcessingInstruction.java +79 -0
  30. data/ext/java/nokogiri/XmlReader.java +615 -0
  31. data/ext/java/nokogiri/XmlRelaxng.java +133 -0
  32. data/ext/java/nokogiri/XmlSaxParserContext.java +329 -0
  33. data/ext/java/nokogiri/XmlSaxPushParser.java +288 -0
  34. data/ext/java/nokogiri/XmlSchema.java +423 -0
  35. data/ext/java/nokogiri/XmlSyntaxError.java +137 -0
  36. data/ext/java/nokogiri/XmlText.java +90 -0
  37. data/ext/java/nokogiri/XmlXpathContext.java +305 -0
  38. data/ext/java/nokogiri/XsltStylesheet.java +368 -0
  39. data/ext/java/nokogiri/internals/ClosedStreamException.java +13 -0
  40. data/ext/java/nokogiri/internals/HtmlDomParserContext.java +252 -0
  41. data/ext/java/nokogiri/internals/IgnoreSchemaErrorsErrorHandler.java +27 -0
  42. data/ext/java/nokogiri/internals/NokogiriBlockingQueueInputStream.java +178 -0
  43. data/ext/java/nokogiri/internals/NokogiriDomParser.java +99 -0
  44. data/ext/java/nokogiri/internals/NokogiriEntityResolver.java +140 -0
  45. data/ext/java/nokogiri/internals/NokogiriErrorHandler.java +65 -0
  46. data/ext/java/nokogiri/internals/NokogiriHandler.java +339 -0
  47. data/ext/java/nokogiri/internals/NokogiriHelpers.java +817 -0
  48. data/ext/java/nokogiri/internals/NokogiriNamespaceCache.java +228 -0
  49. data/ext/java/nokogiri/internals/NokogiriNamespaceContext.java +110 -0
  50. data/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java +86 -0
  51. data/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java +107 -0
  52. data/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java +62 -0
  53. data/ext/java/nokogiri/internals/NokogiriXPathFunction.java +165 -0
  54. data/ext/java/nokogiri/internals/NokogiriXPathFunctionResolver.java +50 -0
  55. data/ext/java/nokogiri/internals/NokogiriXPathVariableResolver.java +37 -0
  56. data/ext/java/nokogiri/internals/NokogiriXsltErrorListener.java +70 -0
  57. data/ext/java/nokogiri/internals/ParserContext.java +262 -0
  58. data/ext/java/nokogiri/internals/ReaderNode.java +564 -0
  59. data/ext/java/nokogiri/internals/SaveContextVisitor.java +865 -0
  60. data/ext/java/nokogiri/internals/SchemaErrorHandler.java +50 -0
  61. data/ext/java/nokogiri/internals/XalanDTMManagerPatch.java +174 -0
  62. data/ext/java/nokogiri/internals/XmlDeclHandler.java +11 -0
  63. data/ext/java/nokogiri/internals/XmlDomParserContext.java +265 -0
  64. data/ext/java/nokogiri/internals/XmlSaxParser.java +40 -0
  65. data/ext/java/nokogiri/internals/c14n/AttrCompare.java +122 -0
  66. data/ext/java/nokogiri/internals/c14n/C14nHelper.java +178 -0
  67. data/ext/java/nokogiri/internals/c14n/CanonicalFilter.java +43 -0
  68. data/ext/java/nokogiri/internals/c14n/CanonicalizationException.java +106 -0
  69. data/ext/java/nokogiri/internals/c14n/Canonicalizer.java +278 -0
  70. data/ext/java/nokogiri/internals/c14n/Canonicalizer11.java +664 -0
  71. data/ext/java/nokogiri/internals/c14n/Canonicalizer11_OmitComments.java +45 -0
  72. data/ext/java/nokogiri/internals/c14n/Canonicalizer11_WithComments.java +45 -0
  73. data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315.java +388 -0
  74. data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315Excl.java +308 -0
  75. data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315ExclOmitComments.java +47 -0
  76. data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315ExclWithComments.java +51 -0
  77. data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315OmitComments.java +51 -0
  78. data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315WithComments.java +50 -0
  79. data/ext/java/nokogiri/internals/c14n/CanonicalizerBase.java +660 -0
  80. data/ext/java/nokogiri/internals/c14n/CanonicalizerPhysical.java +194 -0
  81. data/ext/java/nokogiri/internals/c14n/CanonicalizerSpi.java +77 -0
  82. data/ext/java/nokogiri/internals/c14n/Constants.java +45 -0
  83. data/ext/java/nokogiri/internals/c14n/ElementProxy.java +325 -0
  84. data/ext/java/nokogiri/internals/c14n/HelperNodeList.java +106 -0
  85. data/ext/java/nokogiri/internals/c14n/IgnoreAllErrorHandler.java +86 -0
  86. data/ext/java/nokogiri/internals/c14n/InclusiveNamespaces.java +181 -0
  87. data/ext/java/nokogiri/internals/c14n/InvalidCanonicalizerException.java +87 -0
  88. data/ext/java/nokogiri/internals/c14n/NameSpaceSymbTable.java +452 -0
  89. data/ext/java/nokogiri/internals/c14n/NodeFilter.java +52 -0
  90. data/ext/java/nokogiri/internals/c14n/UtfHelpper.java +190 -0
  91. data/ext/java/nokogiri/internals/c14n/XMLUtils.java +540 -0
  92. data/ext/java/nokogiri/internals/dom2dtm/DOM2DTM.java +1712 -0
  93. data/ext/java/nokogiri/internals/dom2dtm/DOM2DTMdefaultNamespaceDeclarationNode.java +737 -0
  94. data/ext/nokogiri/depend +38 -0
  95. data/ext/nokogiri/extconf.rb +1086 -0
  96. data/ext/nokogiri/gumbo.c +594 -0
  97. data/ext/nokogiri/html4_document.c +167 -0
  98. data/ext/nokogiri/html4_element_description.c +294 -0
  99. data/ext/nokogiri/html4_entity_lookup.c +37 -0
  100. data/ext/nokogiri/html4_sax_parser_context.c +116 -0
  101. data/ext/nokogiri/html4_sax_push_parser.c +95 -0
  102. data/ext/nokogiri/libxml2_backwards_compat.c +121 -0
  103. data/ext/nokogiri/nokogiri.c +265 -0
  104. data/ext/nokogiri/nokogiri.h +235 -0
  105. data/ext/nokogiri/test_global_handlers.c +42 -0
  106. data/ext/nokogiri/xml_attr.c +103 -0
  107. data/ext/nokogiri/xml_attribute_decl.c +70 -0
  108. data/ext/nokogiri/xml_cdata.c +57 -0
  109. data/ext/nokogiri/xml_comment.c +62 -0
  110. data/ext/nokogiri/xml_document.c +689 -0
  111. data/ext/nokogiri/xml_document_fragment.c +44 -0
  112. data/ext/nokogiri/xml_dtd.c +210 -0
  113. data/ext/nokogiri/xml_element_content.c +128 -0
  114. data/ext/nokogiri/xml_element_decl.c +69 -0
  115. data/ext/nokogiri/xml_encoding_handler.c +104 -0
  116. data/ext/nokogiri/xml_entity_decl.c +112 -0
  117. data/ext/nokogiri/xml_entity_reference.c +50 -0
  118. data/ext/nokogiri/xml_namespace.c +186 -0
  119. data/ext/nokogiri/xml_node.c +2426 -0
  120. data/ext/nokogiri/xml_node_set.c +496 -0
  121. data/ext/nokogiri/xml_processing_instruction.c +54 -0
  122. data/ext/nokogiri/xml_reader.c +794 -0
  123. data/ext/nokogiri/xml_relax_ng.c +164 -0
  124. data/ext/nokogiri/xml_sax_parser.c +316 -0
  125. data/ext/nokogiri/xml_sax_parser_context.c +283 -0
  126. data/ext/nokogiri/xml_sax_push_parser.c +166 -0
  127. data/ext/nokogiri/xml_schema.c +260 -0
  128. data/ext/nokogiri/xml_syntax_error.c +85 -0
  129. data/ext/nokogiri/xml_text.c +48 -0
  130. data/ext/nokogiri/xml_xpath_context.c +415 -0
  131. data/ext/nokogiri/xslt_stylesheet.c +363 -0
  132. data/gumbo-parser/CHANGES.md +63 -0
  133. data/gumbo-parser/Makefile +111 -0
  134. data/gumbo-parser/THANKS +27 -0
  135. data/gumbo-parser/src/Makefile +34 -0
  136. data/gumbo-parser/src/README.md +41 -0
  137. data/gumbo-parser/src/ascii.c +75 -0
  138. data/gumbo-parser/src/ascii.h +115 -0
  139. data/gumbo-parser/src/attribute.c +42 -0
  140. data/gumbo-parser/src/attribute.h +17 -0
  141. data/gumbo-parser/src/char_ref.c +22225 -0
  142. data/gumbo-parser/src/char_ref.h +29 -0
  143. data/gumbo-parser/src/char_ref.rl +2154 -0
  144. data/gumbo-parser/src/error.c +626 -0
  145. data/gumbo-parser/src/error.h +148 -0
  146. data/gumbo-parser/src/foreign_attrs.c +104 -0
  147. data/gumbo-parser/src/foreign_attrs.gperf +27 -0
  148. data/gumbo-parser/src/insertion_mode.h +33 -0
  149. data/gumbo-parser/src/macros.h +91 -0
  150. data/gumbo-parser/src/nokogiri_gumbo.h +944 -0
  151. data/gumbo-parser/src/parser.c +4878 -0
  152. data/gumbo-parser/src/parser.h +41 -0
  153. data/gumbo-parser/src/replacement.h +33 -0
  154. data/gumbo-parser/src/string_buffer.c +103 -0
  155. data/gumbo-parser/src/string_buffer.h +68 -0
  156. data/gumbo-parser/src/string_piece.c +48 -0
  157. data/gumbo-parser/src/svg_attrs.c +174 -0
  158. data/gumbo-parser/src/svg_attrs.gperf +77 -0
  159. data/gumbo-parser/src/svg_tags.c +137 -0
  160. data/gumbo-parser/src/svg_tags.gperf +55 -0
  161. data/gumbo-parser/src/tag.c +223 -0
  162. data/gumbo-parser/src/tag_lookup.c +382 -0
  163. data/gumbo-parser/src/tag_lookup.gperf +170 -0
  164. data/gumbo-parser/src/tag_lookup.h +13 -0
  165. data/gumbo-parser/src/token_buffer.c +79 -0
  166. data/gumbo-parser/src/token_buffer.h +71 -0
  167. data/gumbo-parser/src/token_type.h +17 -0
  168. data/gumbo-parser/src/tokenizer.c +3463 -0
  169. data/gumbo-parser/src/tokenizer.h +112 -0
  170. data/gumbo-parser/src/tokenizer_states.h +339 -0
  171. data/gumbo-parser/src/utf8.c +245 -0
  172. data/gumbo-parser/src/utf8.h +164 -0
  173. data/gumbo-parser/src/util.c +66 -0
  174. data/gumbo-parser/src/util.h +34 -0
  175. data/gumbo-parser/src/vector.c +111 -0
  176. data/gumbo-parser/src/vector.h +45 -0
  177. data/lib/nokogiri/class_resolver.rb +67 -0
  178. data/lib/nokogiri/css/node.rb +54 -0
  179. data/lib/nokogiri/css/parser.rb +770 -0
  180. data/lib/nokogiri/css/parser.y +277 -0
  181. data/lib/nokogiri/css/parser_extras.rb +96 -0
  182. data/lib/nokogiri/css/syntax_error.rb +9 -0
  183. data/lib/nokogiri/css/tokenizer.rb +155 -0
  184. data/lib/nokogiri/css/tokenizer.rex +56 -0
  185. data/lib/nokogiri/css/xpath_visitor.rb +359 -0
  186. data/lib/nokogiri/css.rb +66 -0
  187. data/lib/nokogiri/decorators/slop.rb +44 -0
  188. data/lib/nokogiri/encoding_handler.rb +57 -0
  189. data/lib/nokogiri/extension.rb +32 -0
  190. data/lib/nokogiri/gumbo.rb +15 -0
  191. data/lib/nokogiri/html.rb +48 -0
  192. data/lib/nokogiri/html4/builder.rb +37 -0
  193. data/lib/nokogiri/html4/document.rb +214 -0
  194. data/lib/nokogiri/html4/document_fragment.rb +54 -0
  195. data/lib/nokogiri/html4/element_description.rb +25 -0
  196. data/lib/nokogiri/html4/element_description_defaults.rb +572 -0
  197. data/lib/nokogiri/html4/encoding_reader.rb +121 -0
  198. data/lib/nokogiri/html4/entity_lookup.rb +15 -0
  199. data/lib/nokogiri/html4/sax/parser.rb +63 -0
  200. data/lib/nokogiri/html4/sax/parser_context.rb +20 -0
  201. data/lib/nokogiri/html4/sax/push_parser.rb +37 -0
  202. data/lib/nokogiri/html4.rb +47 -0
  203. data/lib/nokogiri/html5/document.rb +168 -0
  204. data/lib/nokogiri/html5/document_fragment.rb +90 -0
  205. data/lib/nokogiri/html5/node.rb +98 -0
  206. data/lib/nokogiri/html5.rb +389 -0
  207. data/lib/nokogiri/jruby/dependencies.rb +3 -0
  208. data/lib/nokogiri/jruby/isorelax/isorelax/20030108/isorelax-20030108.jar +0 -0
  209. data/lib/nokogiri/jruby/net/sf/saxon/Saxon-HE/9.6.0-4/Saxon-HE-9.6.0-4.jar +0 -0
  210. data/lib/nokogiri/jruby/net/sourceforge/htmlunit/neko-htmlunit/2.63.0/neko-htmlunit-2.63.0.jar +0 -0
  211. data/lib/nokogiri/jruby/nokogiri_jars.rb +43 -0
  212. data/lib/nokogiri/jruby/nu/validator/jing/20200702VNU/jing-20200702VNU.jar +0 -0
  213. data/lib/nokogiri/jruby/org/nokogiri/nekodtd/0.1.11.noko2/nekodtd-0.1.11.noko2.jar +0 -0
  214. data/lib/nokogiri/jruby/xalan/serializer/2.7.3/serializer-2.7.3.jar +0 -0
  215. data/lib/nokogiri/jruby/xalan/xalan/2.7.3/xalan-2.7.3.jar +0 -0
  216. data/lib/nokogiri/jruby/xerces/xercesImpl/2.12.2/xercesImpl-2.12.2.jar +0 -0
  217. data/lib/nokogiri/jruby/xml-apis/xml-apis/1.4.01/xml-apis-1.4.01.jar +0 -0
  218. data/lib/nokogiri/syntax_error.rb +6 -0
  219. data/lib/nokogiri/version/constant.rb +6 -0
  220. data/lib/nokogiri/version/info.rb +223 -0
  221. data/lib/nokogiri/version.rb +4 -0
  222. data/lib/nokogiri/xml/attr.rb +66 -0
  223. data/lib/nokogiri/xml/attribute_decl.rb +20 -0
  224. data/lib/nokogiri/xml/builder.rb +487 -0
  225. data/lib/nokogiri/xml/cdata.rb +13 -0
  226. data/lib/nokogiri/xml/character_data.rb +9 -0
  227. data/lib/nokogiri/xml/document.rb +471 -0
  228. data/lib/nokogiri/xml/document_fragment.rb +205 -0
  229. data/lib/nokogiri/xml/dtd.rb +34 -0
  230. data/lib/nokogiri/xml/element_content.rb +38 -0
  231. data/lib/nokogiri/xml/element_decl.rb +15 -0
  232. data/lib/nokogiri/xml/entity_decl.rb +21 -0
  233. data/lib/nokogiri/xml/entity_reference.rb +20 -0
  234. data/lib/nokogiri/xml/namespace.rb +58 -0
  235. data/lib/nokogiri/xml/node/save_options.rb +68 -0
  236. data/lib/nokogiri/xml/node.rb +1563 -0
  237. data/lib/nokogiri/xml/node_set.rb +447 -0
  238. data/lib/nokogiri/xml/notation.rb +19 -0
  239. data/lib/nokogiri/xml/parse_options.rb +213 -0
  240. data/lib/nokogiri/xml/pp/character_data.rb +21 -0
  241. data/lib/nokogiri/xml/pp/node.rb +57 -0
  242. data/lib/nokogiri/xml/pp.rb +4 -0
  243. data/lib/nokogiri/xml/processing_instruction.rb +11 -0
  244. data/lib/nokogiri/xml/reader.rb +105 -0
  245. data/lib/nokogiri/xml/relax_ng.rb +38 -0
  246. data/lib/nokogiri/xml/sax/document.rb +167 -0
  247. data/lib/nokogiri/xml/sax/parser.rb +125 -0
  248. data/lib/nokogiri/xml/sax/parser_context.rb +21 -0
  249. data/lib/nokogiri/xml/sax/push_parser.rb +61 -0
  250. data/lib/nokogiri/xml/sax.rb +6 -0
  251. data/lib/nokogiri/xml/schema.rb +73 -0
  252. data/lib/nokogiri/xml/searchable.rb +270 -0
  253. data/lib/nokogiri/xml/syntax_error.rb +72 -0
  254. data/lib/nokogiri/xml/text.rb +11 -0
  255. data/lib/nokogiri/xml/xpath/syntax_error.rb +13 -0
  256. data/lib/nokogiri/xml/xpath.rb +21 -0
  257. data/lib/nokogiri/xml/xpath_context.rb +16 -0
  258. data/lib/nokogiri/xml.rb +76 -0
  259. data/lib/nokogiri/xslt/stylesheet.rb +27 -0
  260. data/lib/nokogiri/xslt.rb +65 -0
  261. data/lib/nokogiri.rb +120 -0
  262. data/lib/xsd/xmlparser/nokogiri.rb +106 -0
  263. metadata +391 -0
@@ -0,0 +1,270 @@
1
+ # coding: utf-8
2
+ # frozen_string_literal: true
3
+
4
+ module Nokogiri
5
+ module XML
6
+ #
7
+ # The Searchable module declares the interface used for searching your DOM.
8
+ #
9
+ # It implements the public methods #search, #css, and #xpath,
10
+ # as well as allowing specific implementations to specialize some
11
+ # of the important behaviors.
12
+ #
13
+ module Searchable
14
+ # Regular expression used by Searchable#search to determine if a query
15
+ # string is CSS or XPath
16
+ LOOKS_LIKE_XPATH = %r{^(\./|/|\.\.|\.$)}
17
+
18
+ # :section: Searching via XPath or CSS Queries
19
+
20
+ ###
21
+ # call-seq:
22
+ # search(*paths, [namespace-bindings, xpath-variable-bindings, custom-handler-class])
23
+ #
24
+ # Search this object for +paths+. +paths+ must be one or more XPath or CSS queries:
25
+ #
26
+ # node.search("div.employee", ".//title")
27
+ #
28
+ # A hash of namespace bindings may be appended:
29
+ #
30
+ # node.search('.//bike:tire', {'bike' => 'http://schwinn.com/'})
31
+ # node.search('bike|tire', {'bike' => 'http://schwinn.com/'})
32
+ #
33
+ # For XPath queries, a hash of variable bindings may also be appended to the namespace
34
+ # bindings. For example:
35
+ #
36
+ # node.search('.//address[@domestic=$value]', nil, {:value => 'Yes'})
37
+ #
38
+ # 💡 Custom XPath functions and CSS pseudo-selectors may also be defined. To define custom
39
+ # functions create a class and implement the function you want to define. The first argument
40
+ # to the method will be the current matching NodeSet. Any other arguments are ones that you
41
+ # pass in. Note that this class may appear anywhere in the argument list. For example:
42
+ #
43
+ # handler = Class.new {
44
+ # def regex node_set, regex
45
+ # node_set.find_all { |node| node['some_attribute'] =~ /#{regex}/ }
46
+ # end
47
+ # }.new
48
+ # node.search('.//title[regex(., "\w+")]', 'div.employee:regex("[0-9]+")', handler)
49
+ #
50
+ # See Searchable#xpath and Searchable#css for further usage help.
51
+ def search(*args)
52
+ paths, handler, ns, binds = extract_params(args)
53
+
54
+ xpaths = paths.map(&:to_s).map do |path|
55
+ LOOKS_LIKE_XPATH.match?(path) ? path : xpath_query_from_css_rule(path, ns)
56
+ end.flatten.uniq
57
+
58
+ xpath(*(xpaths + [ns, handler, binds].compact))
59
+ end
60
+
61
+ alias_method :/, :search
62
+
63
+ ###
64
+ # call-seq:
65
+ # at(*paths, [namespace-bindings, xpath-variable-bindings, custom-handler-class])
66
+ #
67
+ # Search this object for +paths+, and return only the first
68
+ # result. +paths+ must be one or more XPath or CSS queries.
69
+ #
70
+ # See Searchable#search for more information.
71
+ def at(*args)
72
+ search(*args).first
73
+ end
74
+
75
+ alias_method :%, :at
76
+
77
+ ###
78
+ # call-seq:
79
+ # css(*rules, [namespace-bindings, custom-pseudo-class])
80
+ #
81
+ # Search this object for CSS +rules+. +rules+ must be one or more CSS
82
+ # selectors. For example:
83
+ #
84
+ # node.css('title')
85
+ # node.css('body h1.bold')
86
+ # node.css('div + p.green', 'div#one')
87
+ #
88
+ # A hash of namespace bindings may be appended. For example:
89
+ #
90
+ # node.css('bike|tire', {'bike' => 'http://schwinn.com/'})
91
+ #
92
+ # 💡 Custom CSS pseudo classes may also be defined which are mapped to a custom XPath
93
+ # function. To define custom pseudo classes, create a class and implement the custom pseudo
94
+ # class you want defined. The first argument to the method will be the matching context
95
+ # NodeSet. Any other arguments are ones that you pass in. For example:
96
+ #
97
+ # handler = Class.new {
98
+ # def regex(node_set, regex)
99
+ # node_set.find_all { |node| node['some_attribute'] =~ /#{regex}/ }
100
+ # end
101
+ # }.new
102
+ # node.css('title:regex("\w+")', handler)
103
+ #
104
+ # 💡 Some XPath syntax is supported in CSS queries. For example, to query for an attribute:
105
+ #
106
+ # node.css('img > @href') # returns all +href+ attributes on an +img+ element
107
+ # node.css('img / @href') # same
108
+ #
109
+ # # ⚠ this returns +class+ attributes from all +div+ elements AND THEIR CHILDREN!
110
+ # node.css('div @class')
111
+ #
112
+ # node.css
113
+ #
114
+ # 💡 Array-like syntax is supported in CSS queries as an alternative to using +:nth-child()+.
115
+ #
116
+ # ⚠ NOTE that indices are 1-based like +:nth-child+ and not 0-based like Ruby Arrays. For
117
+ # example:
118
+ #
119
+ # # equivalent to 'li:nth-child(2)'
120
+ # node.css('li[2]') # retrieve the second li element in a list
121
+ #
122
+ # ⚠ NOTE that the CSS query string is case-sensitive with regards to your document type. HTML
123
+ # tags will match only lowercase CSS queries, so if you search for "H1" in an HTML document,
124
+ # you'll never find anything. However, "H1" might be found in an XML document, where tags
125
+ # names are case-sensitive (e.g., "H1" is distinct from "h1").
126
+ def css(*args)
127
+ rules, handler, ns, _ = extract_params(args)
128
+
129
+ css_internal(self, rules, handler, ns)
130
+ end
131
+
132
+ ##
133
+ # call-seq:
134
+ # at_css(*rules, [namespace-bindings, custom-pseudo-class])
135
+ #
136
+ # Search this object for CSS +rules+, and return only the first
137
+ # match. +rules+ must be one or more CSS selectors.
138
+ #
139
+ # See Searchable#css for more information.
140
+ def at_css(*args)
141
+ css(*args).first
142
+ end
143
+
144
+ ###
145
+ # call-seq:
146
+ # xpath(*paths, [namespace-bindings, variable-bindings, custom-handler-class])
147
+ #
148
+ # Search this node for XPath +paths+. +paths+ must be one or more XPath
149
+ # queries.
150
+ #
151
+ # node.xpath('.//title')
152
+ #
153
+ # A hash of namespace bindings may be appended. For example:
154
+ #
155
+ # node.xpath('.//foo:name', {'foo' => 'http://example.org/'})
156
+ # node.xpath('.//xmlns:name', node.root.namespaces)
157
+ #
158
+ # A hash of variable bindings may also be appended to the namespace bindings. For example:
159
+ #
160
+ # node.xpath('.//address[@domestic=$value]', nil, {:value => 'Yes'})
161
+ #
162
+ # 💡 Custom XPath functions may also be defined. To define custom functions create a class and
163
+ # implement the function you want to define. The first argument to the method will be the
164
+ # current matching NodeSet. Any other arguments are ones that you pass in. Note that this
165
+ # class may appear anywhere in the argument list. For example:
166
+ #
167
+ # handler = Class.new {
168
+ # def regex(node_set, regex)
169
+ # node_set.find_all { |node| node['some_attribute'] =~ /#{regex}/ }
170
+ # end
171
+ # }.new
172
+ # node.xpath('.//title[regex(., "\w+")]', handler)
173
+ #
174
+ def xpath(*args)
175
+ paths, handler, ns, binds = extract_params(args)
176
+
177
+ xpath_internal(self, paths, handler, ns, binds)
178
+ end
179
+
180
+ ##
181
+ # call-seq:
182
+ # at_xpath(*paths, [namespace-bindings, variable-bindings, custom-handler-class])
183
+ #
184
+ # Search this node for XPath +paths+, and return only the first
185
+ # match. +paths+ must be one or more XPath queries.
186
+ #
187
+ # See Searchable#xpath for more information.
188
+ def at_xpath(*args)
189
+ xpath(*args).first
190
+ end
191
+
192
+ # :call-seq:
193
+ # >(selector) → NodeSet
194
+ #
195
+ # Search this node's immediate children using CSS selector +selector+
196
+ def >(selector) # rubocop:disable Naming/BinaryOperatorParameterName
197
+ ns = (document.root&.namespaces || {})
198
+ xpath(CSS.xpath_for(selector, prefix: "./", ns: ns).first)
199
+ end
200
+
201
+ # :section:
202
+
203
+ private
204
+
205
+ def css_internal(node, rules, handler, ns)
206
+ xpath_internal(node, css_rules_to_xpath(rules, ns), handler, ns, nil)
207
+ end
208
+
209
+ def xpath_internal(node, paths, handler, ns, binds)
210
+ document = node.document
211
+ return NodeSet.new(document) unless document
212
+
213
+ if paths.length == 1
214
+ return xpath_impl(node, paths.first, handler, ns, binds)
215
+ end
216
+
217
+ NodeSet.new(document) do |combined|
218
+ paths.each do |path|
219
+ xpath_impl(node, path, handler, ns, binds).each { |set| combined << set }
220
+ end
221
+ end
222
+ end
223
+
224
+ def xpath_impl(node, path, handler, ns, binds)
225
+ ctx = XPathContext.new(node)
226
+ ctx.register_namespaces(ns)
227
+ path = path.gsub(/xmlns:/, " :") unless Nokogiri.uses_libxml?
228
+
229
+ binds&.each do |key, value|
230
+ ctx.register_variable(key.to_s, value)
231
+ end
232
+
233
+ ctx.evaluate(path, handler)
234
+ end
235
+
236
+ def css_rules_to_xpath(rules, ns)
237
+ rules.map { |rule| xpath_query_from_css_rule(rule, ns) }
238
+ end
239
+
240
+ def xpath_query_from_css_rule(rule, ns)
241
+ visitor = Nokogiri::CSS::XPathVisitor.new(
242
+ builtins: Nokogiri::CSS::XPathVisitor::BuiltinsConfig::OPTIMAL,
243
+ doctype: document.xpath_doctype,
244
+ )
245
+ self.class::IMPLIED_XPATH_CONTEXTS.map do |implied_xpath_context|
246
+ CSS.xpath_for(rule.to_s, { prefix: implied_xpath_context, ns: ns,
247
+ visitor: visitor, })
248
+ end.join(" | ")
249
+ end
250
+
251
+ def extract_params(params) # :nodoc:
252
+ handler = params.find do |param|
253
+ ![Hash, String, Symbol].include?(param.class)
254
+ end
255
+ params -= [handler] if handler
256
+
257
+ hashes = []
258
+ while Hash === params.last || params.last.nil?
259
+ hashes << params.pop
260
+ break if params.empty?
261
+ end
262
+ ns, binds = hashes.reverse
263
+
264
+ ns ||= (document.root&.namespaces || {})
265
+
266
+ [params, handler, ns, binds]
267
+ end
268
+ end
269
+ end
270
+ end
@@ -0,0 +1,72 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Nokogiri
4
+ module XML
5
+ ###
6
+ # This class provides information about XML SyntaxErrors. These
7
+ # exceptions are typically stored on Nokogiri::XML::Document#errors.
8
+ class SyntaxError < ::Nokogiri::SyntaxError
9
+ attr_reader :domain
10
+ attr_reader :code
11
+ attr_reader :level
12
+ attr_reader :file
13
+ attr_reader :line
14
+ attr_reader :str1
15
+ attr_reader :str2
16
+ attr_reader :str3
17
+ attr_reader :int1
18
+ attr_reader :column
19
+
20
+ ###
21
+ # return true if this is a non error
22
+ def none?
23
+ level == 0
24
+ end
25
+
26
+ ###
27
+ # return true if this is a warning
28
+ def warning?
29
+ level == 1
30
+ end
31
+
32
+ ###
33
+ # return true if this is an error
34
+ def error?
35
+ level == 2
36
+ end
37
+
38
+ ###
39
+ # return true if this error is fatal
40
+ def fatal?
41
+ level == 3
42
+ end
43
+
44
+ def to_s
45
+ message = super.chomp
46
+ [location_to_s, level_to_s, message]
47
+ .compact.join(": ")
48
+ .force_encoding(message.encoding)
49
+ end
50
+
51
+ private
52
+
53
+ def level_to_s
54
+ case level
55
+ when 3 then "FATAL"
56
+ when 2 then "ERROR"
57
+ when 1 then "WARNING"
58
+ end
59
+ end
60
+
61
+ def nil_or_zero?(attribute)
62
+ attribute.nil? || attribute.zero?
63
+ end
64
+
65
+ def location_to_s
66
+ return nil if nil_or_zero?(line) && nil_or_zero?(column)
67
+
68
+ "#{line}:#{column}"
69
+ end
70
+ end
71
+ end
72
+ end
@@ -0,0 +1,11 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Nokogiri
4
+ module XML
5
+ class Text < Nokogiri::XML::CharacterData
6
+ def content=(string)
7
+ self.native_content = string.to_s
8
+ end
9
+ end
10
+ end
11
+ end
@@ -0,0 +1,13 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Nokogiri
4
+ module XML
5
+ module XPath
6
+ class SyntaxError < XML::SyntaxError
7
+ def to_s
8
+ [super.chomp, str1].compact.join(": ")
9
+ end
10
+ end
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,21 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Nokogiri
4
+ module XML
5
+ module XPath
6
+ # The XPath search prefix to search globally, +//+
7
+ GLOBAL_SEARCH_PREFIX = "//"
8
+
9
+ # The XPath search prefix to search direct descendants of the root element, +/+
10
+ ROOT_SEARCH_PREFIX = "/"
11
+
12
+ # The XPath search prefix to search direct descendants of the current element, +./+
13
+ CURRENT_SEARCH_PREFIX = "./"
14
+
15
+ # The XPath search prefix to search anywhere in the current element's subtree, +.//+
16
+ SUBTREE_SEARCH_PREFIX = ".//"
17
+ end
18
+ end
19
+ end
20
+
21
+ require_relative "xpath/syntax_error"
@@ -0,0 +1,16 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Nokogiri
4
+ module XML
5
+ class XPathContext
6
+ ###
7
+ # Register namespaces in +namespaces+
8
+ def register_namespaces(namespaces)
9
+ namespaces.each do |k, v|
10
+ k = k.to_s.gsub(/.*:/, "") # strip off 'xmlns:' or 'xml:'
11
+ register_ns(k, v)
12
+ end
13
+ end
14
+ end
15
+ end
16
+ end
@@ -0,0 +1,76 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Nokogiri
4
+ class << self
5
+ ###
6
+ # Parse XML. Convenience method for Nokogiri::XML::Document.parse
7
+ def XML(thing, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_XML, &block)
8
+ Nokogiri::XML::Document.parse(thing, url, encoding, options, &block)
9
+ end
10
+ end
11
+
12
+ module XML
13
+ # Original C14N 1.0 spec canonicalization
14
+ XML_C14N_1_0 = 0
15
+ # Exclusive C14N 1.0 spec canonicalization
16
+ XML_C14N_EXCLUSIVE_1_0 = 1
17
+ # C14N 1.1 spec canonicalization
18
+ XML_C14N_1_1 = 2
19
+ class << self
20
+ ###
21
+ # Parse an XML document using the Nokogiri::XML::Reader API. See
22
+ # Nokogiri::XML::Reader for mor information
23
+ def Reader(string_or_io, url = nil, encoding = nil, options = ParseOptions::STRICT)
24
+ options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
25
+ yield options if block_given?
26
+
27
+ if string_or_io.respond_to?(:read)
28
+ return Reader.from_io(string_or_io, url, encoding, options.to_i)
29
+ end
30
+
31
+ Reader.from_memory(string_or_io, url, encoding, options.to_i)
32
+ end
33
+
34
+ ###
35
+ # Parse XML. Convenience method for Nokogiri::XML::Document.parse
36
+ def parse(thing, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML, &block)
37
+ Document.parse(thing, url, encoding, options, &block)
38
+ end
39
+
40
+ ####
41
+ # Parse a fragment from +string+ in to a NodeSet.
42
+ def fragment(string, options = ParseOptions::DEFAULT_XML, &block)
43
+ XML::DocumentFragment.parse(string, options, &block)
44
+ end
45
+ end
46
+ end
47
+ end
48
+
49
+ require_relative "xml/pp"
50
+ require_relative "xml/parse_options"
51
+ require_relative "xml/sax"
52
+ require_relative "xml/searchable"
53
+ require_relative "xml/node"
54
+ require_relative "xml/attribute_decl"
55
+ require_relative "xml/element_decl"
56
+ require_relative "xml/element_content"
57
+ require_relative "xml/character_data"
58
+ require_relative "xml/namespace"
59
+ require_relative "xml/attr"
60
+ require_relative "xml/dtd"
61
+ require_relative "xml/cdata"
62
+ require_relative "xml/text"
63
+ require_relative "xml/document"
64
+ require_relative "xml/document_fragment"
65
+ require_relative "xml/processing_instruction"
66
+ require_relative "xml/node_set"
67
+ require_relative "xml/syntax_error"
68
+ require_relative "xml/xpath"
69
+ require_relative "xml/xpath_context"
70
+ require_relative "xml/builder"
71
+ require_relative "xml/reader"
72
+ require_relative "xml/notation"
73
+ require_relative "xml/entity_decl"
74
+ require_relative "xml/entity_reference"
75
+ require_relative "xml/schema"
76
+ require_relative "xml/relax_ng"
@@ -0,0 +1,27 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Nokogiri
4
+ module XSLT
5
+ ###
6
+ # A Stylesheet represents an XSLT Stylesheet object. Stylesheet creation
7
+ # is done through Nokogiri.XSLT. Here is an example of transforming
8
+ # an XML::Document with a Stylesheet:
9
+ #
10
+ # doc = Nokogiri::XML(File.read('some_file.xml'))
11
+ # xslt = Nokogiri::XSLT(File.read('some_transformer.xslt'))
12
+ #
13
+ # puts xslt.transform(doc)
14
+ #
15
+ # See Nokogiri::XSLT::Stylesheet#transform for more transformation
16
+ # information.
17
+ class Stylesheet
18
+ ###
19
+ # Apply an XSLT stylesheet to an XML::Document.
20
+ # +params+ is an array of strings used as XSLT parameters.
21
+ # returns serialized document
22
+ def apply_to(document, params = [])
23
+ serialize(transform(document, params))
24
+ end
25
+ end
26
+ end
27
+ end
@@ -0,0 +1,65 @@
1
+ # coding: utf-8
2
+ # frozen_string_literal: true
3
+
4
+ module Nokogiri
5
+ class << self
6
+ ###
7
+ # Create a Nokogiri::XSLT::Stylesheet with +stylesheet+.
8
+ #
9
+ # Example:
10
+ #
11
+ # xslt = Nokogiri::XSLT(File.read(ARGV[0]))
12
+ #
13
+ def XSLT(stylesheet, modules = {})
14
+ XSLT.parse(stylesheet, modules)
15
+ end
16
+ end
17
+
18
+ ###
19
+ # See Nokogiri::XSLT::Stylesheet for creating and manipulating
20
+ # Stylesheet object.
21
+ module XSLT
22
+ class << self
23
+ ###
24
+ # Parse the stylesheet in +string+, register any +modules+
25
+ def parse(string, modules = {})
26
+ modules.each do |url, klass|
27
+ XSLT.register(url, klass)
28
+ end
29
+
30
+ doc = XML::Document.parse(string, nil, nil, XML::ParseOptions::DEFAULT_XSLT)
31
+ if Nokogiri.jruby?
32
+ Stylesheet.parse_stylesheet_doc(doc, string)
33
+ else
34
+ Stylesheet.parse_stylesheet_doc(doc)
35
+ end
36
+ end
37
+
38
+ # :call-seq:
39
+ # quote_params(params) → Array
40
+ #
41
+ # Quote parameters in +params+ for stylesheet safety.
42
+ # See Nokogiri::XSLT::Stylesheet.transform for example usage.
43
+ #
44
+ # [Parameters]
45
+ # - +params+ (Hash, Array) XSLT parameters (key->value, or tuples of [key, value])
46
+ #
47
+ # [Returns] Array of string parameters, with quotes correctly escaped for use with XSLT::Stylesheet.transform
48
+ #
49
+ def quote_params(params)
50
+ params.flatten.each_slice(2).with_object([]) do |kv, quoted_params|
51
+ key, value = kv.map(&:to_s)
52
+ value = if /'/.match?(value)
53
+ "concat('#{value.gsub(/'/, %q{', "'", '})}')"
54
+ else
55
+ "'#{value}'"
56
+ end
57
+ quoted_params << key
58
+ quoted_params << value
59
+ end
60
+ end
61
+ end
62
+ end
63
+ end
64
+
65
+ require_relative "xslt/stylesheet"
data/lib/nokogiri.rb ADDED
@@ -0,0 +1,120 @@
1
+ # coding: utf-8
2
+ # frozen_string_literal: true
3
+
4
+ if defined?(RUBY_ENGINE) && RUBY_ENGINE == "jruby"
5
+ require_relative "nokogiri/jruby/dependencies"
6
+ end
7
+
8
+ require_relative "nokogiri/extension"
9
+
10
+ # Nokogiri parses and searches XML/HTML very quickly, and also has
11
+ # correctly implemented CSS3 selector support as well as XPath 1.0
12
+ # support.
13
+ #
14
+ # Parsing a document returns either a Nokogiri::XML::Document, or a
15
+ # Nokogiri::HTML4::Document depending on the kind of document you parse.
16
+ #
17
+ # Here is an example:
18
+ #
19
+ # require 'nokogiri'
20
+ # require 'open-uri'
21
+ #
22
+ # # Get a Nokogiri::HTML4::Document for the page we’re interested in...
23
+ #
24
+ # doc = Nokogiri::HTML4(URI.open('http://www.google.com/search?q=tenderlove'))
25
+ #
26
+ # # Do funky things with it using Nokogiri::XML::Node methods...
27
+ #
28
+ # ####
29
+ # # Search for nodes by css
30
+ # doc.css('h3.r a.l').each do |link|
31
+ # puts link.content
32
+ # end
33
+ #
34
+ # See also:
35
+ #
36
+ # - Nokogiri::XML::Searchable#css for more information about CSS searching
37
+ # - Nokogiri::XML::Searchable#xpath for more information about XPath searching
38
+ module Nokogiri
39
+ class << self
40
+ ###
41
+ # Parse an HTML or XML document. +string+ contains the document.
42
+ def parse(string, url = nil, encoding = nil, options = nil)
43
+ if string.respond_to?(:read) ||
44
+ /^\s*<(?:!DOCTYPE\s+)?html[\s>]/i.match?(string[0, 512])
45
+ # Expect an HTML indicator to appear within the first 512
46
+ # characters of a document. (<?xml ?> + <?xml-stylesheet ?>
47
+ # shouldn't be that long)
48
+ Nokogiri.HTML4(string, url, encoding,
49
+ options || XML::ParseOptions::DEFAULT_HTML)
50
+ else
51
+ Nokogiri.XML(string, url, encoding,
52
+ options || XML::ParseOptions::DEFAULT_XML)
53
+ end.tap do |doc|
54
+ yield doc if block_given?
55
+ end
56
+ end
57
+
58
+ ###
59
+ # Create a new Nokogiri::XML::DocumentFragment
60
+ def make(input = nil, opts = {}, &blk)
61
+ if input
62
+ Nokogiri::HTML4.fragment(input).children.first
63
+ else
64
+ Nokogiri(&blk)
65
+ end
66
+ end
67
+
68
+ ###
69
+ # Parse a document and add the Slop decorator. The Slop decorator
70
+ # implements method_missing such that methods may be used instead of CSS
71
+ # or XPath. For example:
72
+ #
73
+ # doc = Nokogiri::Slop(<<-eohtml)
74
+ # <html>
75
+ # <body>
76
+ # <p>first</p>
77
+ # <p>second</p>
78
+ # </body>
79
+ # </html>
80
+ # eohtml
81
+ # assert_equal('second', doc.html.body.p[1].text)
82
+ #
83
+ def Slop(*args, &block)
84
+ Nokogiri(*args, &block).slop!
85
+ end
86
+
87
+ # :nodoc:
88
+ def install_default_aliases
89
+ warn("Nokogiri.install_default_aliases is deprecated and will be removed in a future version of Nokogiri. Please call Nokogiri::EncodingHandler.install_default_aliases instead.")
90
+ Nokogiri::EncodingHandler.install_default_aliases
91
+ end
92
+ end
93
+ end
94
+
95
+ ###
96
+ # Parse a document contained in +args+. Nokogiri will try to guess what type of document you are
97
+ # attempting to parse. For more information, see Nokogiri.parse
98
+ #
99
+ # To specify the type of document, use {Nokogiri.XML}, {Nokogiri.HTML4}, or {Nokogiri.HTML5}.
100
+ def Nokogiri(*args, &block)
101
+ if block
102
+ Nokogiri::HTML4::Builder.new(&block).doc.root
103
+ else
104
+ Nokogiri.parse(*args)
105
+ end
106
+ end
107
+
108
+ require_relative "nokogiri/version"
109
+ require_relative "nokogiri/class_resolver"
110
+ require_relative "nokogiri/syntax_error"
111
+ require_relative "nokogiri/xml"
112
+ require_relative "nokogiri/xslt"
113
+ require_relative "nokogiri/html4"
114
+ require_relative "nokogiri/html"
115
+ require_relative "nokogiri/decorators/slop"
116
+ require_relative "nokogiri/css"
117
+ require_relative "nokogiri/html4/builder"
118
+ require_relative "nokogiri/encoding_handler"
119
+
120
+ require_relative "nokogiri/html5" if Nokogiri.uses_gumbo?