class Nokogiri::XML::Document
Nokogiri::XML::Searchable#xpath
For searching a Document, see Nokogiri::XML::Searchable#css and
See Nokogiri::XML::Document.parse() for more information on parsing.
XML documents. The Document is created by parsing an XML document.
Nokogiri::XML::Document is the main entry point for dealing with
#
def self.empty_doc? string_or_io
def self.empty_doc? string_or_io string_or_io.nil? || (string_or_io.respond_to?(:empty?) && string_or_io.empty?) || (string_or_io.respond_to?(:eof?) && string_or_io.eof?) end
def self.parse string_or_io, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML
Nokogiri.XML() is a convenience method which will call this method.
set) by default.
and that module's DEFAULT_XML constant for what's set (and not
Nokogiri::XML::ParseOptions for a complete list of options;
does not attempt to load DTDs or access the network. See
By default, Nokogiri treats documents as untrusted, and so
parse options may be set.
+block+ (optional) is passed a configuration object on which
Nokogiri::XML::ParseOptions for more information.
parsing, such as Nokogiri::XML::ParseOptions::RECOVER. See the
+options+ (optional) is a configuration object that sets options during
the document.
+encoding+ (optional) is the encoding that should be used when processing
+url+ (optional) is the URI where this document is located.
_read_ and _close_ such as an IO, or StringIO.
+string_or_io+ may be a String, or any object that responds to
Parse an XML file.
#
def self.parse string_or_io, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML options = Nokogiri::XML::ParseOptions.new(options) if Integer === options yield options if block_given? url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil if empty_doc?(string_or_io) if options.strict? raise Nokogiri::XML::SyntaxError.new("Empty document") else return encoding ? new.tap { |i| i.encoding = encoding } : new end end doc = if string_or_io.respond_to?(:read) if string_or_io.is_a?(Pathname) # resolve the Pathname to the file and open it as an IO object, see #2110 string_or_io = string_or_io.expand_path.open url ||= string_or_io.path end read_io(string_or_io, url, encoding, options.to_i) else # read_memory pukes on empty docs read_memory(string_or_io, url, encoding, options.to_i) end # do xinclude processing doc.do_xinclude(options) if options.xinclude? return doc end
def add_child node_or_tags
def add_child node_or_tags raise "A document may not have multiple root nodes." if (root && root.name != 'nokogiri_text_wrapper') && !(node_or_tags.comment? || node_or_tags.processing_instruction?) node_or_tags = coerce(node_or_tags) if node_or_tags.is_a?(XML::NodeSet) raise "A document may not have multiple root nodes." if node_or_tags.size > 1 super(node_or_tags.first) else super end end
def collect_namespaces
implementation of the underlying XML library.
namespaces, and as a result the order may be dependent on the
Note that this method does an xpath lookup for nodes with
in the hash.
Non-prefixed default namespaces (as in "xmlns=") are not included
The hash returned will look like this: { 'xmlns:foo' => 'bar' }
For example, given this document:
WARNING: this method will clobber duplicate names in the keys.
{ 'xmlns:foo' => 'bar', 'xmlns:hello' => 'world' }
This method will return:
For example, given this document:
return them as a hash.
Recursively get all namespaces from this node and its subtree and
#
def collect_namespaces xpath("//namespace::*").inject({}) do |hash, ns| hash[["xmlns",ns.prefix].compact.join(":")] = ns.href if ns.prefix != "xml" hash end end
def create_cdata string, &block
def create_cdata string, &block Nokogiri::XML::CDATA.new self, string.to_s, &block end
def create_comment string, &block
def create_comment string, &block Nokogiri::XML::Comment.new self, string.to_s, &block end
def create_element(name, *contents_or_attrs, &block)
- Example: Passing a block to mutate the element -
Example: An element with contents and attributes -
Example: An element with attributes -
Example: An element with contents -
Example: An empty element without attributes -
Returns:
-
(Nokogiri::XML::Element)
-
Other tags:
- Yieldparam: node -
Parameters:
-
contents_or_attrs
(#to_s, Hash
) -- -
name
(String
) --
def create_element(name, *contents_or_attrs, &block) elm = Nokogiri::XML::Element.new(name, self, &block) contents_or_attrs.each do |arg| case arg when Hash arg.each do |k, v| key = k.to_s if key =~ NCNAME_RE ns_name = Regexp.last_match(1) elm.add_namespace_definition(ns_name, v) else elm[k.to_s] = v.to_s end end else elm.content = arg end end if ns = elm.namespace_definitions.find { |n| n.prefix.nil? || (n.prefix == '') } elm.namespace = ns end elm end
def create_text_node string, &block
def create_text_node string, &block Nokogiri::XML::Text.new string.to_s, self, &block end
def decorate node
#
def decorate node return unless @decorators @decorators.each { |klass,list| next unless node.is_a?(klass) list.each { |moodule| node.extend(moodule) } } end
def decorators key
def decorators key @decorators ||= Hash.new @decorators[key] ||= [] end
def document
def document self end
def fragment tags = nil
Create a Nokogiri::XML::DocumentFragment from +tags+
#
def fragment tags = nil DocumentFragment.new(self, tags, self.root) end
def initialize *args # :nodoc:
def initialize *args # :nodoc: @errors = [] @decorators = nil end
def inspect_attributes
def inspect_attributes [:name, :children] end
def name
def name 'document' end
def namespaces
def namespaces root ? root.namespaces : {} end
def slop!
... which does absolutely nothing.
irb> doc.slop!
... followed by irb's implicit inspect (and therefore instantiation of every node) ...
irb> doc = Nokogiri::HTML my_markup
and not
irb> doc = Nokogiri::Slop my_markup
irb, the preferred idiom is:
is called will not be decorated with sloppy behavior. So, if you're in
Note that any nodes that have been instantiated before #slop!
Explore a document with shortcut methods. See Nokogiri::Slop for details.
#
def slop! unless decorators(XML::Node).include? Nokogiri::Decorators::Slop decorators(XML::Node) << Nokogiri::Decorators::Slop decorate! end self end
def validate
Validate this Document against it's DTD. Returns a list of errors on
#
def validate return nil unless internal_subset internal_subset.validate self end