Class: Canon::Xml::DataModel
- Defined in:
- lib/canon/xml/data_model.rb
Class Method Summary collapse
- .build_attribute_nodes(nokogiri_element, element) ⇒ Object
- .build_comment_node(nokogiri_comment) ⇒ Object
- .build_element_node(nokogiri_element, preserve_whitespace: false) ⇒ Object
- .build_from_moxml(moxml_doc, preserve_whitespace: false) ⇒ Object
- .build_from_nokogiri(nokogiri_doc, preserve_whitespace: false) ⇒ Object
- .build_moxml_attribute_nodes(moxml_element, element) ⇒ Object
- .build_moxml_comment_node(moxml_comment) ⇒ Object
- .build_moxml_element_node(moxml_element, preserve_whitespace: false) ⇒ Object
- .build_moxml_namespace_nodes(moxml_element, element) ⇒ Object
- .build_moxml_node(node, preserve_whitespace: false) ⇒ Object
- .build_moxml_pi_node(moxml_pi) ⇒ Object
- .build_moxml_text_node(moxml_text, preserve_whitespace: false) ⇒ Object
- .build_namespace_nodes(nokogiri_element, element) ⇒ Object
- .build_node_from_nokogiri(nokogiri_node, preserve_whitespace: false) ⇒ Object
- .build_pi_node(nokogiri_pi) ⇒ Object
- .build_text_node(nokogiri_text, preserve_whitespace: false) ⇒ Object
- .check_for_relative_namespace_uris(doc) ⇒ Object
- .collect_in_scope_namespaces(nokogiri_element) ⇒ Object
- .extract_xml_encoding(xml_string) ⇒ Object
-
.from_moxml_xml(xml_string, preserve_whitespace:) ⇒ Object
— Moxml path —.
-
.from_nokogiri_xml(xml_string, preserve_whitespace:) ⇒ Object
— Nokogiri path —.
- .from_xml(xml_string, preserve_whitespace: false) ⇒ Object
- .normalize_encoding(xml_string) ⇒ Object
- .parse(xml_string) ⇒ Object
- .relative_uri?(uri) ⇒ Boolean
- .serialize(node) ⇒ Object
- .transcode_to_utf8(xml_string, source_encoding) ⇒ Object
- .try_utf8_reinterpretation(xml_string) ⇒ Object
- .update_xml_declaration(xml_string, new_encoding) ⇒ Object
Class Method Details
.build_attribute_nodes(nokogiri_element, element) ⇒ Object
234 235 236 237 238 239 240 241 242 243 244 |
# File 'lib/canon/xml/data_model.rb', line 234 def self.build_attribute_nodes(nokogiri_element, element) nokogiri_element.attributes.each_value do |attr| attr_node = Nodes::AttributeNode.new( name: attr.name, value: attr.value, namespace_uri: attr.namespace&.href, prefix: attr.namespace&.prefix, ) element.add_attribute(attr_node) end end |
.build_comment_node(nokogiri_comment) ⇒ Object
257 258 259 |
# File 'lib/canon/xml/data_model.rb', line 257 def self.build_comment_node(nokogiri_comment) Nodes::CommentNode.new(value: nokogiri_comment.content) end |
.build_element_node(nokogiri_element, preserve_whitespace: false) ⇒ Object
182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 |
# File 'lib/canon/xml/data_model.rb', line 182 def self.build_element_node(nokogiri_element, preserve_whitespace: false) element = Nodes::ElementNode.new( name: nokogiri_element.name, namespace_uri: nokogiri_element.namespace&.href, prefix: nokogiri_element.namespace&.prefix, ) build_namespace_nodes(nokogiri_element, element) build_attribute_nodes(nokogiri_element, element) nokogiri_element.children.each do |child| node = build_node_from_nokogiri(child, preserve_whitespace: preserve_whitespace) element.add_child(node) if node end element end |
.build_from_moxml(moxml_doc, preserve_whitespace: false) ⇒ Object
275 276 277 278 279 280 281 282 283 284 |
# File 'lib/canon/xml/data_model.rb', line 275 def self.build_from_moxml(moxml_doc, preserve_whitespace: false) root = Nodes::RootNode.new if moxml_doc.respond_to?(:root) && moxml_doc.root root.add_child(build_moxml_element_node(moxml_doc.root, preserve_whitespace: preserve_whitespace)) end root end |
.build_from_nokogiri(nokogiri_doc, preserve_whitespace: false) ⇒ Object
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 |
# File 'lib/canon/xml/data_model.rb', line 139 def self.build_from_nokogiri(nokogiri_doc, preserve_whitespace: false) root = Nodes::RootNode.new if nokogiri_doc.respond_to?(:root) && nokogiri_doc.root root.add_child(build_element_node(nokogiri_doc.root, preserve_whitespace: preserve_whitespace)) nokogiri_doc.children.each do |child| next if child == nokogiri_doc.root next if child.is_a?(Nokogiri::XML::DTD) node = build_node_from_nokogiri(child, preserve_whitespace: preserve_whitespace) root.add_child(node) if node end else nokogiri_doc.children.each do |child| next if child.is_a?(Nokogiri::XML::DTD) node = build_node_from_nokogiri(child, preserve_whitespace: preserve_whitespace) root.add_child(node) if node end end root end |
.build_moxml_attribute_nodes(moxml_element, element) ⇒ Object
340 341 342 343 344 345 346 347 348 |
# File 'lib/canon/xml/data_model.rb', line 340 def self.build_moxml_attribute_nodes(moxml_element, element) moxml_element.attributes.each do |attr| attr_node = Nodes::AttributeNode.new( name: attr.name, value: attr.value, ) element.add_attribute(attr_node) end end |
.build_moxml_comment_node(moxml_comment) ⇒ Object
360 361 362 |
# File 'lib/canon/xml/data_model.rb', line 360 def self.build_moxml_comment_node(moxml_comment) Nodes::CommentNode.new(value: moxml_comment.text) end |
.build_moxml_element_node(moxml_element, preserve_whitespace: false) ⇒ Object
300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 |
# File 'lib/canon/xml/data_model.rb', line 300 def self.build_moxml_element_node(moxml_element, preserve_whitespace: false) ns = moxml_element.namespace element = Nodes::ElementNode.new( name: moxml_element.name, namespace_uri: ns&.uri, prefix: ns&.prefix, ) build_moxml_namespace_nodes(moxml_element, element) build_moxml_attribute_nodes(moxml_element, element) moxml_element.children.each do |child| node = build_moxml_node(child, preserve_whitespace: preserve_whitespace) element.add_child(node) if node end element end |
.build_moxml_namespace_nodes(moxml_element, element) ⇒ Object
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 |
# File 'lib/canon/xml/data_model.rb', line 321 def self.build_moxml_namespace_nodes(moxml_element, element) moxml_element.namespace_definitions.each do |ns| ns_node = Nodes::NamespaceNode.new( prefix: ns.prefix || "", uri: ns.uri, ) element.add_namespace(ns_node) end unless element.namespaces.any? do |n| n.prefix == "xml" end element.add_namespace(Nodes::NamespaceNode.new( prefix: "xml", uri: "http://www.w3.org/XML/1998/namespace", )) end end |
.build_moxml_node(node, preserve_whitespace: false) ⇒ Object
286 287 288 289 290 291 292 293 294 295 296 297 298 |
# File 'lib/canon/xml/data_model.rb', line 286 def self.build_moxml_node(node, preserve_whitespace: false) case node when Moxml::Element build_moxml_element_node(node, preserve_whitespace: preserve_whitespace) when Moxml::Text build_moxml_text_node(node, preserve_whitespace: preserve_whitespace) when Moxml::Comment build_moxml_comment_node(node) when Moxml::ProcessingInstruction build_moxml_pi_node(node) end end |
.build_moxml_pi_node(moxml_pi) ⇒ Object
364 365 366 367 368 369 |
# File 'lib/canon/xml/data_model.rb', line 364 def self.build_moxml_pi_node(moxml_pi) Nodes::ProcessingInstructionNode.new( target: moxml_pi.target, data: moxml_pi.data, ) end |
.build_moxml_text_node(moxml_text, preserve_whitespace: false) ⇒ Object
350 351 352 353 354 355 356 357 358 |
# File 'lib/canon/xml/data_model.rb', line 350 def self.build_moxml_text_node(moxml_text, preserve_whitespace: false) content = moxml_text.text if !preserve_whitespace && content.strip.empty? && moxml_text.parent.is_a?(Moxml::Element) return nil end Nodes::TextNode.new(value: content, original: content) end |
.build_namespace_nodes(nokogiri_element, element) ⇒ Object
201 202 203 204 205 206 207 208 209 210 211 |
# File 'lib/canon/xml/data_model.rb', line 201 def self.build_namespace_nodes(nokogiri_element, element) namespaces = collect_in_scope_namespaces(nokogiri_element) namespaces.each do |prefix, uri| ns_node = Nodes::NamespaceNode.new( prefix: prefix, uri: uri, ) element.add_namespace(ns_node) end end |
.build_node_from_nokogiri(nokogiri_node, preserve_whitespace: false) ⇒ Object
166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 |
# File 'lib/canon/xml/data_model.rb', line 166 def self.build_node_from_nokogiri(nokogiri_node, preserve_whitespace: false) case nokogiri_node when Nokogiri::XML::Element build_element_node(nokogiri_node, preserve_whitespace: preserve_whitespace) when Nokogiri::XML::Text build_text_node(nokogiri_node, preserve_whitespace: preserve_whitespace) when Nokogiri::XML::Comment build_comment_node(nokogiri_node) when Nokogiri::XML::ProcessingInstruction build_pi_node(nokogiri_node) end end |
.build_pi_node(nokogiri_pi) ⇒ Object
261 262 263 264 265 266 |
# File 'lib/canon/xml/data_model.rb', line 261 def self.build_pi_node(nokogiri_pi) Nodes::ProcessingInstructionNode.new( target: nokogiri_pi.name, data: nokogiri_pi.content, ) end |
.build_text_node(nokogiri_text, preserve_whitespace: false) ⇒ Object
246 247 248 249 250 251 252 253 254 255 |
# File 'lib/canon/xml/data_model.rb', line 246 def self.build_text_node(nokogiri_text, preserve_whitespace: false) content = nokogiri_text.content if !preserve_whitespace && content.strip.empty? && nokogiri_text.parent.is_a?(Nokogiri::XML::Element) return nil end original = nokogiri_text.to_xml Nodes::TextNode.new(value: content, original: original) end |
.check_for_relative_namespace_uris(doc) ⇒ Object
125 126 127 128 129 130 131 132 133 134 135 136 137 |
# File 'lib/canon/xml/data_model.rb', line 125 def self.check_for_relative_namespace_uris(doc) doc.traverse do |node| next unless node.is_a?(Nokogiri::XML::Element) node.namespace_definitions.each do |ns| next if ns.href.nil? || ns.href.empty? if relative_uri?(ns.href) raise Canon::Error, "Relative namespace URI not allowed: #{ns.href}" end end end end |
.collect_in_scope_namespaces(nokogiri_element) ⇒ Object
213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 |
# File 'lib/canon/xml/data_model.rb', line 213 def self.collect_in_scope_namespaces(nokogiri_element) namespaces = {} current = nokogiri_element while current && !current.is_a?(Nokogiri::XML::Document) if current.is_a?(Nokogiri::XML::Element) current.namespace_definitions.each do |ns| prefix = ns.prefix || "" unless namespaces.key?(prefix) namespaces[prefix] = ns.href end end end current = current.parent end namespaces["xml"] ||= "http://www.w3.org/XML/1998/namespace" namespaces end |
.extract_xml_encoding(xml_string) ⇒ Object
92 93 94 95 96 97 98 99 |
# File 'lib/canon/xml/data_model.rb', line 92 def self.extract_xml_encoding(xml_string) binary_string = xml_string.dup.force_encoding("BINARY") if binary_string =~ /\A\s*<\?xml[^>]*\bencoding\s*=\s*["']([^"']+)["'][^>]*\?>/i return Regexp.last_match(1) end nil end |
.from_moxml_xml(xml_string, preserve_whitespace:) ⇒ Object
— Moxml path —
270 271 272 273 |
# File 'lib/canon/xml/data_model.rb', line 270 def self.from_moxml_xml(xml_string, preserve_whitespace:) doc = Canon::XmlParsing.parse(xml_string) build_from_moxml(doc, preserve_whitespace: preserve_whitespace) end |
.from_nokogiri_xml(xml_string, preserve_whitespace:) ⇒ Object
— Nokogiri path —
115 116 117 118 119 120 121 122 123 |
# File 'lib/canon/xml/data_model.rb', line 115 def self.from_nokogiri_xml(xml_string, preserve_whitespace:) doc = Nokogiri::XML(xml_string, &:nonet) check_for_relative_namespace_uris(doc) result = build_from_nokogiri(doc, preserve_whitespace: preserve_whitespace) errors = Array(doc.errors).map(&:to_s) result.parse_errors = errors if errors.any? result end |
.from_xml(xml_string, preserve_whitespace: false) ⇒ Object
19 20 21 22 23 24 25 26 27 28 29 |
# File 'lib/canon/xml/data_model.rb', line 19 def self.from_xml(xml_string, preserve_whitespace: false) normalized_xml = normalize_encoding(xml_string) if Canon::XmlBackend.nokogiri? from_nokogiri_xml(normalized_xml, preserve_whitespace: preserve_whitespace) else from_moxml_xml(normalized_xml, preserve_whitespace: preserve_whitespace) end end |
.normalize_encoding(xml_string) ⇒ Object
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
# File 'lib/canon/xml/data_model.rb', line 31 def self.normalize_encoding(xml_string) return xml_string unless xml_string.is_a?(String) declared_encoding = extract_xml_encoding(xml_string) if declared_encoding if declared_encoding.upcase != "UTF-8" utf8_reinterpreted = try_utf8_reinterpretation(xml_string) if utf8_reinterpreted return update_xml_declaration(xml_string, "UTF-8") end return transcode_to_utf8(xml_string, declared_encoding) end elsif xml_string.encoding.name != "UTF-8" reinterpreted = try_utf8_reinterpretation(xml_string) return reinterpreted if reinterpreted return transcode_to_utf8(xml_string, xml_string.encoding.name) end xml_string end |
.parse(xml_string) ⇒ Object
101 102 103 |
# File 'lib/canon/xml/data_model.rb', line 101 def self.parse(xml_string) from_xml(xml_string) end |
.relative_uri?(uri) ⇒ Boolean
109 110 111 |
# File 'lib/canon/xml/data_model.rb', line 109 def self.relative_uri?(uri) uri !~ %r{^[a-zA-Z][a-zA-Z0-9+.-]*:} end |
.serialize(node) ⇒ Object
105 106 107 |
# File 'lib/canon/xml/data_model.rb', line 105 def self.serialize(node) node.to_s end |
.transcode_to_utf8(xml_string, source_encoding) ⇒ Object
62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
# File 'lib/canon/xml/data_model.rb', line 62 def self.transcode_to_utf8(xml_string, source_encoding) if source_encoding != "UTF-8" forced = xml_string.dup.force_encoding(source_encoding) if forced.valid_encoding? utf8_check = xml_string.dup.force_encoding("UTF-8") if utf8_check.valid_encoding? return xml_string.dup.force_encoding("UTF-8") end return forced.encode("UTF-8", source_encoding, invalid: :replace, undef: :replace, replace: "?") end end xml_string.dup.force_encoding("UTF-8") rescue EncodingError xml_string end |
.try_utf8_reinterpretation(xml_string) ⇒ Object
83 84 85 86 87 88 89 90 |
# File 'lib/canon/xml/data_model.rb', line 83 def self.try_utf8_reinterpretation(xml_string) return xml_string if xml_string.encoding.name == "UTF-8" forced = xml_string.dup.force_encoding("UTF-8") return forced if forced.valid_encoding? nil end |
.update_xml_declaration(xml_string, new_encoding) ⇒ Object
56 57 58 59 60 |
# File 'lib/canon/xml/data_model.rb', line 56 def self.update_xml_declaration(xml_string, new_encoding) xml_string.sub(/\bencoding\s*=\s*["'][^"']+["']/i) do |_match| %(encoding="#{new_encoding}") end end |