Class: Nokogiri::XML::Document

Inherits:
Node
  • Object
show all
Defined in:
lib/nokogiri/xml/document.rb,
ext/nokogiri/xml_document.c,
ext/nokogiri/html_document.c

Overview

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::Document.parse() for more information on parsing.

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

Direct Known Subclasses

HTML::Document

Constant Summary collapse

NCNAME_START_CHAR =

I’m ignoring unicode characters here. See www.w3.org/TR/REC-xml-names/#ns-decl for more details.

"A-Za-z_"
NCNAME_CHAR = 
NCNAME_START_CHAR + "\\-.0-9"
NCNAME_RE = 
/^xmlns(:[#{NCNAME_START_CHAR}][#{NCNAME_CHAR}]*)?$/

Constants inherited from Node

Node::ATTRIBUTE_DECL, Node::ATTRIBUTE_NODE, Node::CDATA_SECTION_NODE, Node::COMMENT_NODE, Node::DOCB_DOCUMENT_NODE, Node::DOCUMENT_FRAG_NODE, Node::DOCUMENT_NODE, Node::DOCUMENT_TYPE_NODE, Node::DTD_NODE, Node::ELEMENT_DECL, Node::ELEMENT_NODE, Node::ENTITY_DECL, Node::ENTITY_NODE, Node::ENTITY_REF_NODE, Node::HTML_DOCUMENT_NODE, Node::NAMESPACE_DECL, Node::NOTATION_NODE, Node::PI_NODE, Node::TEXT_NODE, Node::XINCLUDE_END, Node::XINCLUDE_START

Constants included from Searchable

Searchable::LOOKS_LIKE_XPATH

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from Node

#<=>, #==, #>, #[], #[]=, #accept, #add_class, #add_namespace_definition, #add_next_sibling, #add_previous_sibling, #after, #ancestors, #append_class, #attribute, #attribute_nodes, #attribute_with_ns, #attributes, #before, #blank?, #cdata?, #child, #children, #children=, #classes, #comment?, #content, #content=, #create_external_subset, #create_internal_subset, #css_path, #decorate!, #default_namespace=, #description, #do_xinclude, #document?, #each, #element?, #element_children, #encode_special_chars, #external_subset, #first_element_child, #fragment?, #html?, #inner_html, #inner_html=, #internal_subset, #key?, #keys, #lang, #lang=, #last_element_child, #line, #matches?, #namespace, #namespace=, #namespace_definitions, #namespace_scopes, #namespaced_key?, #native_content=, #next_element, #next_sibling, #node_name, #node_name=, #node_type, #parent, #parent=, #parse, #path, #pointer_id, #prepend_child, #previous_element, #previous_sibling, #processing_instruction?, #read_only?, #remove_attribute, #remove_class, #replace, #serialize, #swap, #text?, #to_html, #to_s, #to_xhtml, #traverse, #unlink, #values, #wrap, #write_html_to, #write_to, #write_xhtml_to, #write_xml_to, #xml?

Methods included from Searchable

#at, #at_css, #at_xpath, #css, #search, #xpath

Methods included from PP::Node

#inspect, #pretty_print

Constructor Details

#initialize(*args) ⇒ Document

:nodoc:



74
75
76
77
 
# File 'lib/nokogiri/xml/document.rb', line 74

def initialize *args # :nodoc:
  @errors     = []
  @decorators = nil
end

Instance Attribute Details

#errors ⇒ Object

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



72
73
74
 
# File 'lib/nokogiri/xml/document.rb', line 72

def errors
  @errors
end

Class Method Details

.new(version = default) ⇒ Object

Create a new document with version (defaults to “1.0”)



352
353
354
355
356
357
358
359
360
361
362
363
364
365
 
# File 'ext/nokogiri/xml_document.c', line 352

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 *)StringValueCStr(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) {|options| ... } ⇒ Object

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 (optional) is the URI where this document is located.

encoding (optional) is the encoding that should be used when processing the document.

options (optional) is a configuration object that sets options during parsing, such as Nokogiri::XML::ParseOptions::RECOVER. See the Nokogiri::XML::ParseOptions for more information.

block (optional) is passed a configuration object on which parse options may be set.

By default, Nokogiri treats documents as untrusted, and so does not attempt to load DTDs or access the network. See Nokogiri::XML::ParseOptions for a complete list of options; and that module’s DEFAULT_XML constant for what’s set (and not set) by default.

Nokogiri.XML() is a convenience method which will call this method.

Yields:

  • (options) 


44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
 
# File 'lib/nokogiri/xml/document.rb', line 44

def self.parse string_or_io, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML
  options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
  # Give the options to the user
  yield options if block_given?

  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)
    url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil
    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

.read_io(io, url, encoding, options) ⇒ Object

Create a new document from an IO object



228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
 
# File 'ext/nokogiri/xml_document.c', line 228

static VALUE read_io( VALUE klass,
                      VALUE io,
                      VALUE url,
                      VALUE encoding,
                      VALUE options )
{
  const char * c_url    = NIL_P(url)      ? NULL : StringValueCStr(url);
  const char * c_enc    = NIL_P(encoding) ? NULL : StringValueCStr(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(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) ⇒ Object

Create a new document from a String



278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
 
# File 'ext/nokogiri/xml_document.c', line 278

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 : StringValueCStr(url);
  const char * c_enc    = NIL_P(encoding) ? NULL : StringValueCStr(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(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) ⇒ Object

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



257
258
259
260
 
# File 'lib/nokogiri/xml/document.rb', line 257

def self.wrap document
  raise "JRuby only method" unless Nokogiri.jruby?
  return wrapJavaDocument(document)
end

Instance Method Details

#add_child(node_or_tags) ⇒ Object Also known as: << 



242
243
244
245
246
247
248
249
250
251
 
# File 'lib/nokogiri/xml/document.rb', line 242

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

#canonicalize(mode = XML_C14N_1_0, inclusive_namespaces = nil, with_comments = false) ⇒ Object #canonicalize {|obj, parent| ... } ⇒ Object

Canonicalize a document and return the results. Takes an optional block that takes two parameters: the obj and that node’s parent. The obj will be either a Nokogiri::XML::Node, or a Nokogiri::XML::Namespace The block must return a non-nil, non-false value if the obj passed in should be included in the canonicalized document.

Overloads:

  • #canonicalize {|obj, parent| ... } ⇒ Object

    Yields:



495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
 
# File 'ext/nokogiri/xml_document.c', line 495

static VALUE canonicalize(int argc, VALUE* argv, VALUE self)
{
  VALUE mode;
  VALUE incl_ns;
  VALUE with_comments;
  xmlChar **ns;
  long ns_len, i;

  xmlDocPtr doc;
  xmlOutputBufferPtr buf;
  xmlC14NIsVisibleCallback cb = NULL;
  void * ctx = NULL;

  VALUE rb_cStringIO;
  VALUE io;

  rb_scan_args(argc, argv, "03", &mode, &incl_ns, &with_comments);

  Data_Get_Struct(self, xmlDoc, doc);

  rb_cStringIO = rb_const_get_at(rb_cObject, rb_intern("StringIO"));
  io           = rb_class_new_instance(0, 0, rb_cStringIO);
  buf          = xmlAllocOutputBuffer(NULL);

  buf->writecallback = (xmlOutputWriteCallback)io_write_callback;
  buf->closecallback = (xmlOutputCloseCallback)io_close_callback;
  buf->context       = (void *)io;

  if(rb_block_given_p()) {
    cb = block_caller;
    ctx = (void *)rb_block_proc();
  }

  if(NIL_P(incl_ns)){
    ns = NULL;
  }
  else{
    Check_Type(incl_ns, T_ARRAY);
    ns_len = RARRAY_LEN(incl_ns);
    ns = calloc((size_t)ns_len+1, sizeof(xmlChar *));
    for (i = 0 ; i < ns_len ; i++) {
      VALUE entry = rb_ary_entry(incl_ns, i);
      ns[i] = (xmlChar*)StringValueCStr(entry);
    }
  }


  xmlC14NExecute(doc, cb, ctx,
    (int)      (NIL_P(mode)        ? 0 : NUM2INT(mode)),
    ns,
    (int)      RTEST(with_comments),
    buf);

  xmlOutputBufferClose(buf);

  return rb_funcall(io, rb_intern("string"), 0);
}

#collect_namespaces ⇒ Object

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 that this method does an xpath lookup for nodes with namespaces, and as a result the order may be dependent on the implementation of the underlying XML library.



167
168
169
170
171
172
 
# File 'lib/nokogiri/xml/document.rb', line 167

def collect_namespaces
  xpath("//namespace::*").inject({}) do |hash, ns|
    hash[["xmlns",ns.prefix].compact.join(":")] = ns.href if ns.prefix != "xml"
    hash
  end
end

#create_cdata(string, &block) ⇒ Object

Create a CDATA Node containing string



118
119
120
 
# File 'lib/nokogiri/xml/document.rb', line 118

def create_cdata string, &block
  Nokogiri::XML::CDATA.new self, string.to_s, &block
end

#create_comment(string, &block) ⇒ Object

Create a Comment Node containing string



123
124
125
 
# File 'lib/nokogiri/xml/document.rb', line 123

def create_comment string, &block
  Nokogiri::XML::Comment.new self, string.to_s, &block
end

#create_element(name, *args, &block) ⇒ Object

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>



88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
 
# File 'lib/nokogiri/xml/document.rb', line 88

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 =~ NCNAME_RE
          ns_name = key.split(":", 2)[1]
          elm.add_namespace_definition ns_name, v
        else
          elm[k.to_s] = v.to_s
        end
      }
    else
      elm.content = arg
    end
  end
  if ns = elm.namespace_definitions.find { |n| n.prefix.nil? or n.prefix == '' }
    elm.namespace = ns
  end
  elm
end

#create_entity(name, type, external_id, system_id, content) ⇒ Object

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.



424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
 
# File 'ext/nokogiri/xml_document.c', line 424

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                        : StringValueCStr(name)),
      (int)      (NIL_P(type)        ? XML_INTERNAL_GENERAL_ENTITY : NUM2INT(type)),
      (xmlChar *)(NIL_P(external_id) ? NULL                        : StringValueCStr(external_id)),
      (xmlChar *)(NIL_P(system_id)   ? NULL                        : StringValueCStr(system_id)),
      (xmlChar *)(NIL_P(content)     ? NULL                        : StringValueCStr(content))
    );

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

    return Qnil;
  }

  return Nokogiri_wrap_xml_node(cNokogiriXmlEntityDecl, (xmlNodePtr)ptr);
}

#create_text_node(string, &block) ⇒ Object

Create a Text Node with string



113
114
115
 
# File 'lib/nokogiri/xml/document.rb', line 113

def create_text_node string, &block
  Nokogiri::XML::Text.new string.to_s, self, &block
end

#decorate(node) ⇒ Object

Apply any decorators to node



215
216
217
218
219
220
221
 
# File 'lib/nokogiri/xml/document.rb', line 215

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) ⇒ Object

Get the list of decorators given key



175
176
177
178
 
# File 'lib/nokogiri/xml/document.rb', line 175

def decorators key
  @decorators ||= Hash.new
  @decorators[key] ||= []
end

#document ⇒ Object

A reference to self



133
134
135
 
# File 'lib/nokogiri/xml/document.rb', line 133

def document
  self
end

#dup ⇒ Object Also known as: clone

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.



323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
 
# File 'ext/nokogiri/xml_document.c', line 323

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

  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;
  copy = Nokogiri_wrap_xml_document(rb_obj_class(self), dup);
  error_list = rb_iv_get(self, "@errors");
  rb_iv_set(copy, "@errors", error_list);
  return copy ;
}

#encoding ⇒ Object

Get the encoding for this Document



198
199
200
201
202
203
204
205
 
# File 'ext/nokogiri/xml_document.c', line 198

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) ⇒ Object

Set the encoding string for this Document



179
180
181
182
183
184
185
186
187
188
189
190
 
# File 'ext/nokogiri/xml_document.c', line 179

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

  if (doc->encoding)
      free((char *)(uintptr_t) doc->encoding); /* avoid gcc cast warning */

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

  return encoding;
}

#fragment(tags = nil) ⇒ Object

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



234
235
236
 
# File 'lib/nokogiri/xml/document.rb', line 234

def fragment tags = nil
  DocumentFragment.new(self, tags, self.root)
end

#name ⇒ Object

The name of this document. Always returns “document”



128
129
130
 
# File 'lib/nokogiri/xml/document.rb', line 128

def name
  'document'
end

#namespaces ⇒ Object

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



227
228
229
 
# File 'lib/nokogiri/xml/document.rb', line 227

def namespaces
  root ? root.namespaces : {}
end

#remove_namespaces! ⇒ Object

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.html



404
405
406
407
408
409
410
411
 
# File 'ext/nokogiri/xml_document.c', line 404

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

  recursively_remove_namespaces_from_node((xmlNodePtr)doc);
  return self;
}

#root ⇒ Object

Get the root node for this document.



160
161
162
163
164
165
166
167
168
169
170
171
 
# File 'ext/nokogiri/xml_document.c', line 160

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= ⇒ Object

Set the root element on this document



116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
# File 'ext/nokogiri/xml_document.c', line 116

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! ⇒ Object

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.



204
205
206
207
208
209
210
211
 
# File 'lib/nokogiri/xml/document.rb', line 204

def slop!
  unless decorators(XML::Node).include? Nokogiri::Decorators::Slop
    decorators(XML::Node) << Nokogiri::Decorators::Slop
    decorate!
  end

  self
end

#to_java ⇒ Object

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



265
266
267
268
 
# File 'lib/nokogiri/xml/document.rb', line 265

def to_java
  raise "JRuby only method" unless Nokogiri.jruby?
  return toJavaDocument()
end

#url ⇒ Object

Get the url name for this document.



100
101
102
103
104
105
106
107
108
 
# File 'ext/nokogiri/xml_document.c', line 100

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 ⇒ Object

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



183
184
185
186
 
# File 'lib/nokogiri/xml/document.rb', line 183

def validate
  return nil unless internal_subset
  internal_subset.validate self
end

#version ⇒ Object

Get the XML version for this Document



213
214
215
216
217
218
219
220
 
# File 'ext/nokogiri/xml_document.c', line 213

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

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