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(*args) click to toggle source

(Not documented)

# File lib/nokogiri/xml/document.rb, line 14
      def initialize *args
        @decorators = nil
      end

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)
{
  VALUE version, rest, rb_doc ;

  rb_scan_args(argc, argv, "0*", &rest);
  version = rb_ary_entry(rest, 0);
  if (version == Qnil) {
    version = rb_str_new2("1.0");
  }

  xmlDocPtr doc = xmlNewDoc((xmlChar *)StringValuePtr(version));
  rb_doc = Nokogiri_wrap_xml_document(klass, doc);
  rb_funcall2(rb_doc, rb_intern("initialize"), 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. thing 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 90
        def 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 self.read_io(string_or_io, url, encoding, options.to_i)
          end

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

          self.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    = (url == Qnil) ? NULL : StringValuePtr(url);
  const char * c_enc    = (encoding == Qnil) ? NULL : StringValuePtr(encoding);
  VALUE error_list      = rb_ary_new();

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

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

  if(doc == NULL) {
    xmlFreeDoc(doc);

    xmlErrorPtr error = xmlGetLastError();
    if(error)
      rb_funcall(rb_mKernel, rb_intern("raise"), 1,
          Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error)
      );
    else
      rb_raise(rb_eRuntimeError, "Could not parse document");

    return Qnil;
  }

  VALUE document = Nokogiri_wrap_xml_document(klass, doc);
  rb_funcall(document, rb_intern("errors="), 1, 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    = (url == Qnil) ? NULL : StringValuePtr(url);
  const char * c_enc    = (encoding == Qnil) ? NULL : StringValuePtr(encoding);
  int len               = RSTRING_LEN(string);
  VALUE error_list      = rb_ary_new();

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

  if(doc == NULL) {
    xmlFreeDoc(doc);

    xmlErrorPtr error = xmlGetLastError();
    if(error)
      rb_funcall(rb_mKernel, rb_intern("raise"), 1,
          Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error)
      );
    else
      rb_raise(rb_eRuntimeError, "Could not parse document");

    return Qnil;
  }

  VALUE document = Nokogiri_wrap_xml_document(klass, doc);
  rb_funcall(document, rb_intern("errors="), 1, error_list);
  return document;
}

Public Instance Methods

clone(...) click to toggle source

Alias for dup

decorate(node) click to toggle source

Apply any decorators to node

# File lib/nokogiri/xml/document.rb, line 55
      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 29
      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 24
      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)
{
  VALUE level;

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

  xmlDocPtr doc, dup;
  Data_Get_Struct(self, xmlDoc, doc);

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

  dup->type = doc->type;
  return Nokogiri_wrap_xml_document(RBASIC(self)->klass, 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, 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) click to toggle source

Create a Nokogiri::XML::DocumentFragment from tags

# File lib/nokogiri/xml/document.rb, line 74
      def fragment tags
        DocumentFragment.new(self, tags)
      end

name() click to toggle source

The name of this document. Always returns “document“

# File lib/nokogiri/xml/document.rb, line 19
      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 68
      def namespaces
        root ? root.collect_namespaces : {}
      end

root click to toggle source

Get the root node for this document.

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

  xmlNodePtr 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;

  Data_Get_Struct(self, xmlDoc, doc);
  Data_Get_Struct(root, xmlNode, new_root);

  xmlDocSetRootElement(doc, new_root);
  return root;
}

slop!() click to toggle source

Explore a document with shortcut methods.

# File lib/nokogiri/xml/document.rb, line 44
      def slop!
        unless decorators(XML::Node).include? Nokogiri::Decorators::Slop
          decorators(XML::Node) << Nokogiri::Decorators::Slop
          decorate!
        end

        self
      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, doc->encoding);

  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 37
      def validate
        return nil unless internal_subset
        internal_subset.validate self
      end

In Files

Parent

Methods

Files

Class Index

Nokogiri::XML::Document

Attributes

Public Class Methods

Public Instance Methods