Files

Class/Module Index [+]

Quicksearch

Nokogiri::XML::Document

Nokogiri::XML::Document is the main entry point for dealing with XML documents. The Document is created by parsing an XML document. See Nokogiri.XML()

For searching a Document, see Nokogiri::XML::Node#css and Nokogiri::XML::Node#xpath

Attributes

errors[RW]

A list of Nokogiri::XML::SyntaxError found when parsing a document

Public Class Methods

new(version = default) click to toggle source

Create a new document with version (defaults to "1.0")

static VALUE new(int argc, VALUE *argv, VALUE klass)
{
  xmlDocPtr doc;
  VALUE version, rest, rb_doc ;

  rb_scan_args(argc, argv, "0*", &rest);
  version = rb_ary_entry(rest, (long)0);
  if (NIL_P(version)) version = rb_str_new2("1.0");

  doc = xmlNewDoc((xmlChar *)StringValuePtr(version));
  rb_doc = Nokogiri_wrap_xml_document(klass, doc);
  rb_obj_call_init(rb_doc, argc, argv);
  return rb_doc ;
}
parse(string_or_io, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML, &block) click to toggle source

Parse an XML file. string_or_io may be a String, or any object that responds to read and close such as an IO, or StringIO. url is resource where this document is located. encoding is the encoding that should be used when processing the document. options is a number that sets options in the parser, such as Nokogiri::XML::ParseOptions::RECOVER. See the constants in Nokogiri::XML::ParseOptions.

# File lib/nokogiri/xml/document.rb, line 19
def self.parse string_or_io, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML, &block

  options = Nokogiri::XML::ParseOptions.new(options) if Fixnum === options
  # Give the options to the user
  yield options if block_given?

  if string_or_io.respond_to?(:read)
    url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil
    return read_io(string_or_io, url, encoding, options.to_i)
  end

  # read_memory pukes on empty docs
  return new if string_or_io.nil? or string_or_io.empty?

  read_memory(string_or_io, url, encoding, options.to_i)
end
read_io(io, url, encoding, options) click to toggle source

Create a new document from an IO object

static VALUE read_io( VALUE klass,
                      VALUE io,
                      VALUE url,
                      VALUE encoding,
                      VALUE options )
{
  const char * c_url    = NIL_P(url)      ? NULL : StringValuePtr(url);
  const char * c_enc    = NIL_P(encoding) ? NULL : StringValuePtr(encoding);
  VALUE error_list      = rb_ary_new();
  VALUE document;
  xmlDocPtr doc;

  xmlResetLastError();
  xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher);

  doc = xmlReadIO(
      (xmlInputReadCallback)io_read_callback,
      (xmlInputCloseCallback)io_close_callback,
      (void *)io,
      c_url,
      c_enc,
      (int)NUM2INT(options)
  );
  xmlSetStructuredErrorFunc(NULL, NULL);

  if(doc == NULL) {
    xmlErrorPtr error;

    xmlFreeDoc(doc);

    error = xmlGetLastError();
    if(error)
      rb_exc_raise(Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error));
    else
      rb_raise(rb_eRuntimeError, "Could not parse document");

    return Qnil;
  }

  document = Nokogiri_wrap_xml_document(klass, doc);
  rb_iv_set(document, "@errors", error_list);
  return document;
}
read_memory(string, url, encoding, options) click to toggle source

Create a new document from a String

static VALUE read_memory( VALUE klass,
                          VALUE string,
                          VALUE url,
                          VALUE encoding,
                          VALUE options )
{
  const char * c_buffer = StringValuePtr(string);
  const char * c_url    = NIL_P(url)      ? NULL : StringValuePtr(url);
  const char * c_enc    = NIL_P(encoding) ? NULL : StringValuePtr(encoding);
  int len               = (int)RSTRING_LEN(string);
  VALUE error_list      = rb_ary_new();
  VALUE document;
  xmlDocPtr doc;

  xmlResetLastError();
  xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher);
  doc = xmlReadMemory(c_buffer, len, c_url, c_enc, (int)NUM2INT(options));
  xmlSetStructuredErrorFunc(NULL, NULL);

  if(doc == NULL) {
    xmlErrorPtr error;

    xmlFreeDoc(doc);

    error = xmlGetLastError();
    if(error)
      rb_exc_raise(Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error));
    else
      rb_raise(rb_eRuntimeError, "Could not parse document");

    return Qnil;
  }

  document = Nokogiri_wrap_xml_document(klass, doc);
  rb_iv_set(document, "@errors", error_list);
  return document;
}
wrap(document) click to toggle source

JRuby Wraps Java's org.w3c.dom.document and returns Nokogiri::XML::Document

# File lib/nokogiri/xml/document.rb, line 211
def self.wrap document
  raise "JRuby only method" unless Nokogiri.jruby?
  return wrapJavaDocument(document)
end

Public Instance Methods

<<(child) click to toggle source
Alias for: add_child
add_child(child) click to toggle source
# File lib/nokogiri/xml/document.rb, line 197
def add_child child
  raise "Document already has a root node" if root
  if child.type == Node::DOCUMENT_FRAG_NODE
    raise "Document cannot have multiple root nodes" if child.children.size > 1
    super(child.children.first)
  else
    super
  end
end
Also aliased as: <<
clone(p1 = v1) click to toggle source
Alias for: dup
collect_namespaces() click to toggle source

Recursively get all namespaces from this node and its subtree and return them as a hash.

For example, given this document:

<root xmlns:foo="bar">
  <bar xmlns:hello="world" />
</root>

This method will return:

{ 'xmlns:foo' => 'bar', 'xmlns:hello' => 'world' }

WARNING: this method will clobber duplicate names in the keys. For example, given this document:

<root xmlns:foo="bar">
  <bar xmlns:foo="baz" />
</root>

The hash returned will look like this: { 'xmlns:foo' => 'bar' }

Non-prefixed default namespaces (as in "xmlns=") are not included in the hash.

Note this is a very expensive operation in current implementation, as it traverses the entire graph, and also has to bring each node accross the libxml bridge into a ruby object.

# File lib/nokogiri/xml/document.rb, line 123
def collect_namespaces
  ns = {}
  traverse { |j| ns.merge!(j.namespaces) }
  ns
end
create_cdata(text) click to toggle source

Create a CDATA element containing text

# File lib/nokogiri/xml/document.rb, line 80
def create_cdata text
  Nokogiri::XML::CDATA.new(self, text.to_s)
end
create_element(name, *args, &block) click to toggle source

Create an element with name, and optionally setting the content and attributes.

doc.create_element "div" # <div></div>
doc.create_element "div", :class => "container" # <div class='container'></div>
doc.create_element "div", "contents" # <div>contents</div>
doc.create_element "div", "contents", :class => "container" # <div class='container'>contents</div>
doc.create_element "div" { |node| node['class'] = "container" } # <div class='container'></div>
# File lib/nokogiri/xml/document.rb, line 53
def create_element name, *args, &block
  elm = Nokogiri::XML::Element.new(name, self, &block)
  args.each do |arg|
    case arg
    when Hash
      arg.each { |k,v|
        key = k.to_s
        if key =~ /^xmlns(:\w+)?$/
          ns_name = key.split(":", 2)[1]
          elm.add_namespace_definition ns_name, v
          next
        end
        elm[k.to_s] = v.to_s
      }
    else
      elm.content = arg
    end
  end
  elm
end
create_entity(name, type, external_id, system_id, content) click to toggle source

Create a new entity named name.

type is an integer representing the type of entity to be created, and it defaults to Nokogiri::XML::EntityDecl::INTERNAL_GENERAL. See the constants on Nokogiri::XML::EntityDecl for more information.

external_id, system_id, and content set the External ID, System ID, and content respectively. All of these parameters are optional.

static VALUE create_entity(int argc, VALUE *argv, VALUE self)
{
  VALUE name;
  VALUE type;
  VALUE external_id;
  VALUE system_id;
  VALUE content;
  xmlEntityPtr ptr;
  xmlDocPtr doc ;

  Data_Get_Struct(self, xmlDoc, doc);

  rb_scan_args(argc, argv, "14", &name, &type, &external_id, &system_id,
      &content);

  xmlResetLastError();
  ptr = xmlAddDocEntity(
      doc,
      (xmlChar *)(NIL_P(name)        ? NULL                        : StringValuePtr(name)),
      (int)      (NIL_P(type)        ? XML_INTERNAL_GENERAL_ENTITY : NUM2INT(type)),
      (xmlChar *)(NIL_P(external_id) ? NULL                        : StringValuePtr(external_id)),
      (xmlChar *)(NIL_P(system_id)   ? NULL                        : StringValuePtr(system_id)),
      (xmlChar *)(NIL_P(content)     ? NULL                        : StringValuePtr(content))
    );

  if(NULL == ptr) {
    xmlErrorPtr error = xmlGetLastError();
    if(error)
      rb_exc_raise(Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error));
    else
      rb_raise(rb_eRuntimeError, "Could not create entity");

    return Qnil;
  }

  return Nokogiri_wrap_xml_node(cNokogiriXmlEntityDecl, (xmlNodePtr)ptr);
}
create_text_node(text, &block) click to toggle source

Create a text node with text

# File lib/nokogiri/xml/document.rb, line 75
def create_text_node text, &block
  Nokogiri::XML::Text.new(text.to_s, self, &block)
end
decorate(node) click to toggle source

Apply any decorators to node

# File lib/nokogiri/xml/document.rb, line 170
def decorate node
  return unless @decorators
  @decorators.each { |klass,list|
    next unless node.is_a?(klass)
    list.each { |moodule| node.extend(moodule) }
  }
end
decorators(key) click to toggle source

Get the list of decorators given key

# File lib/nokogiri/xml/document.rb, line 130
def decorators key
  @decorators ||= Hash.new
  @decorators[key] ||= []
end
document() click to toggle source

A reference to self

# File lib/nokogiri/xml/document.rb, line 90
def document
  self
end
dup click to toggle source

Copy this Document. An optional depth may be passed in, but it defaults to a deep copy. 0 is a shallow copy, 1 is a deep copy.

static VALUE duplicate_node(int argc, VALUE *argv, VALUE self)
{
  xmlDocPtr doc, dup;
  VALUE level;

  if(rb_scan_args(argc, argv, "01", &level) == 0)
    level = INT2NUM((long)1);

  Data_Get_Struct(self, xmlDoc, doc);

  dup = xmlCopyDoc(doc, (int)NUM2INT(level));
  if(dup == NULL) return Qnil;

  dup->type = doc->type;
  return Nokogiri_wrap_xml_document(rb_obj_class(self), dup);
}
Also aliased as: clone
encoding click to toggle source

Get the encoding for this Document

static VALUE encoding(VALUE self)
{
  xmlDocPtr doc;
  Data_Get_Struct(self, xmlDoc, doc);

  if(!doc->encoding) return Qnil;
  return NOKOGIRI_STR_NEW2(doc->encoding);
}
encoding= encoding click to toggle source

Set the encoding string for this Document

static VALUE set_encoding(VALUE self, VALUE encoding)
{
  xmlDocPtr doc;
  Data_Get_Struct(self, xmlDoc, doc);

  doc->encoding = xmlStrdup((xmlChar *)StringValuePtr(encoding));

  return encoding;
}
fragment(tags = nil) click to toggle source

Create a Nokogiri::XML::DocumentFragment from tags Returns an empty fragment if tags is nil.

# File lib/nokogiri/xml/document.rb, line 189
def fragment tags = nil
  DocumentFragment.new(self, tags, self.root)
end
name() click to toggle source

The name of this document. Always returns "document"

# File lib/nokogiri/xml/document.rb, line 85
def name
  'document'
end
namespaces() click to toggle source

Get the hash of namespaces on the root Nokogiri::XML::Node

# File lib/nokogiri/xml/document.rb, line 182
def namespaces
  root ? root.namespaces : {}
end
remove_namespaces! click to toggle source

Remove all namespaces from all nodes in the document.

This could be useful for developers who either don't understand namespaces or don't care about them.

The following example shows a use case, and you can decide for yourself whether this is a good thing or not:

doc = Nokogiri::XML <<-EOXML
   <root>
     <car xmlns:part="http://general-motors.com/">
       <part:tire>Michelin Model XGV</part:tire>
     </car>
     <bicycle xmlns:part="http://schwinn.com/">
       <part:tire>I'm a bicycle tire!</part:tire>
     </bicycle>
   </root>
   EOXML

doc.xpath("//tire").to_s # => ""
doc.xpath("//part:tire", "part" => "http://general-motors.com/").to_s # => "<part:tire>Michelin Model XGV</part:tire>"
doc.xpath("//part:tire", "part" => "http://schwinn.com/").to_s # => "<part:tire>I'm a bicycle tire!</part:tire>"

doc.remove_namespaces!

doc.xpath("//tire").to_s # => "<tire>Michelin Model XGV</tire><tire>I'm a bicycle tire!</tire>"
doc.xpath("//part:tire", "part" => "http://general-motors.com/").to_s # => ""
doc.xpath("//part:tire", "part" => "http://schwinn.com/").to_s # => ""

For more information on why this probably is not a good thing in general, please direct your browser to tenderlovemaking.com/2009/04/23/namespaces-in-xml/

VALUE remove_namespaces_bang(VALUE self)
{
  xmlDocPtr doc ;
  Data_Get_Struct(self, xmlDoc, doc);

  recursively_remove_namespaces_from_node((xmlNodePtr)doc);
  return self;
}
root click to toggle source

Get the root node for this document.

static VALUE root(VALUE self)
{
  xmlDocPtr doc;
  xmlNodePtr root;

  Data_Get_Struct(self, xmlDoc, doc);

  root = xmlDocGetRootElement(doc);

  if(!root) return Qnil;
  return Nokogiri_wrap_xml_node(Qnil, root) ;
}
root= click to toggle source

Set the root element on this document

static VALUE set_root(VALUE self, VALUE root)
{
  xmlDocPtr doc;
  xmlNodePtr new_root;
  xmlNodePtr old_root;

  Data_Get_Struct(self, xmlDoc, doc);

  old_root = NULL;

  if(NIL_P(root)) {
    old_root = xmlDocGetRootElement(doc);

    if(old_root) {
      xmlUnlinkNode(old_root);
      NOKOGIRI_ROOT_NODE(old_root);
    }

    return root;
  }

  Data_Get_Struct(root, xmlNode, new_root);


  /* If the new root's document is not the same as the current document,
   * then we need to dup the node in to this document. */
  if(new_root->doc != doc) {
    old_root = xmlDocGetRootElement(doc);
    if (!(new_root = xmlDocCopyNode(new_root, doc, 1))) {
      rb_raise(rb_eRuntimeError, "Could not reparent node (xmlDocCopyNode)");
    }
  }

  xmlDocSetRootElement(doc, new_root);
  if(old_root) NOKOGIRI_ROOT_NODE(old_root);
  return root;
}
slop!() click to toggle source

Explore a document with shortcut methods. See Nokogiri::Slop for details.

Note that any nodes that have been instantiated before slop! is called will not be decorated with sloppy behavior. So, if you're in irb, the preferred idiom is:

irb> doc = Nokogiri::Slop my_markup

and not

irb> doc = Nokogiri::HTML my_markup
... followed by irb's implicit inspect (and therefore instantiation of every node) ...
irb> doc.slop!
... which does absolutely nothing.
# File lib/nokogiri/xml/document.rb, line 159
def slop!
  unless decorators(XML::Node).include? Nokogiri::Decorators::Slop
    decorators(XML::Node) << Nokogiri::Decorators::Slop
    decorate!
  end

  self
end
to_java() click to toggle source

JRuby Returns Java's org.w3c.dom.document of this Document.

# File lib/nokogiri/xml/document.rb, line 219
def to_java
  raise "JRuby only method" unless Nokogiri.jruby?
  return toJavaDocument()
end
url click to toggle source

Get the url name for this document.

static VALUE url(VALUE self)
{
  xmlDocPtr doc;
  Data_Get_Struct(self, xmlDoc, doc);

  if(doc->URL) return NOKOGIRI_STR_NEW2(doc->URL);

  return Qnil;
}
validate() click to toggle source

Validate this Document against it's DTD. Returns a list of errors on the document or nil when there is no DTD.

# File lib/nokogiri/xml/document.rb, line 138
def validate
  return nil unless internal_subset
  internal_subset.validate self
end
version click to toggle source

Get the XML version for this Document

static VALUE version(VALUE self)
{
  xmlDocPtr doc;
  Data_Get_Struct(self, xmlDoc, doc);

  if(!doc->version) return Qnil;
  return NOKOGIRI_STR_NEW2(doc->version);
}

[Validate]

Generated with the Darkfish Rdoc Generator 2.