Class: LibXML::XML::Document

Inherits:
Object
  • Object
show all
Defined in:
ext/libxml/ruby_xml_document.c,
lib/libxml/document.rb,
ext/libxml/ruby_xml_document.c

Overview

The XML::Document class provides a tree based API for working with xml documents. You may directly create a document and manipulate it, or create a document from a data source by using an XML::Parser object.

To read a document from a file:

doc = XML::Document.file('my_file')

To use a parser to read a document:

parser = XML::Parser.file('my_file')
doc = parser.parse

To create a document from scratch:

doc = XML::Document.new()
doc.root = XML::Node.new('root_node')
doc.root << XML::Node.new('elem1')
doc.save(filename, :indent => true, :encoding => XML::Encoding::UTF_8)

To write a document to a file:

doc = XML::Document.new()
doc.root = XML::Node.new('root_node')
root = doc.root

root << elem1 = XML::Node.new('elem1')
elem1['attr1'] = 'val1'
elem1['attr2'] = 'val2'

root << elem2 = XML::Node.new('elem2')
elem2['attr1'] = 'val1'
elem2['attr2'] = 'val2'

root << elem3 = XML::Node.new('elem3')
elem3 << elem4 = XML::Node.new('elem4')
elem3 << elem5 = XML::Node.new('elem5')

elem5 << elem6 = XML::Node.new('elem6')
elem6 << 'Content for element 6'

elem3['attr'] = 'baz'

doc.save(filename, :indent => true, :encoding => XML::Encoding::UTF_8)

Constant Summary collapse

XML_C14N_1_0 =

Original C14N 1.0 spec

INT2NUM(XML_C14N_1_0)
XML_C14N_EXCLUSIVE_1_0 =

Exclusive C14N 1.0 spec

INT2NUM(XML_C14N_EXCLUSIVE_1_0)
XML_C14N_1_1 =

C14N 1.1 spec

INT2NUM(XML_C14N_1_1)

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#XML::Document.initialize(xml_version = 1.0) ⇒ Object

Initializes a new XML::Document, optionally specifying the XML version.



112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
# File 'ext/libxml/ruby_xml_document.c', line 112

static VALUE rxml_document_initialize(int argc, VALUE *argv, VALUE self)
{
  xmlDocPtr xdoc;
  VALUE xmlver;

  switch (argc)
  {
  case 0:
    xmlver = rb_str_new2("1.0");
    break;
  case 1:
    rb_scan_args(argc, argv, "01", &xmlver);
    break;
  default:
    rb_raise(rb_eArgError, "wrong number of arguments (need 0 or 1)");
  }

  Check_Type(xmlver, T_STRING);
  xdoc = xmlNewDoc((xmlChar*) StringValuePtr(xmlver));
  rxml_register_doc(xdoc, self);
  DATA_PTR(self) = xdoc;

  return self;
}

Class Method Details

.document(value) ⇒ Object

call-seq:

XML::Document.document(document) -> XML::Document

Creates a new document based on the specified document.

Parameters:

document - A preparsed document.


14
15
16
# File 'lib/libxml/document.rb', line 14

def self.document(value)
  Parser.document(value).parse
end

.file(value, options = {}) ⇒ Object

call-seq:

XML::Document.file(path) -> XML::Document
XML::Document.file(path, :encoding => XML::Encoding::UTF_8,
                         :options => XML::Parser::Options::NOENT) -> XML::Document

Creates a new document from the specified file or uri.

You may provide an optional hash table to control how the parsing is performed. Valid options are:

encoding - The document encoding, defaults to nil. Valid values
           are the encoding constants defined on XML::Encoding.
options - Parser options.  Valid values are the constants defined on
          XML::Parser::Options.  Mutliple options can be combined
          by using Bitwise OR (|).


33
34
35
# File 'lib/libxml/document.rb', line 33

def self.file(value, options = {})
  Parser.file(value, options).parse
end

.io(value, options = {}) ⇒ Object

call-seq:

XML::Document.io(io) -> XML::Document
XML::Document.io(io, :encoding => XML::Encoding::UTF_8,
                     :options => XML::Parser::Options::NOENT
                     :base_uri="http://libxml.org") -> XML::Document

Creates a new document from the specified io object.

Parameters:

io - io object that contains the xml to parser
base_uri - The base url for the parsed document.
encoding - The document encoding, defaults to nil. Valid values
           are the encoding constants defined on XML::Encoding.
options - Parser options.  Valid values are the constants defined on
          XML::Parser::Options.  Mutliple options can be combined
          by using Bitwise OR (|).


54
55
56
# File 'lib/libxml/document.rb', line 54

def self.io(value, options = {})
  Parser.io(value, options).parse
end

.string(value, options = {}) ⇒ Object

call-seq:

XML::Document.string(string) -> XML::Document
XML::Document.string(string, :encoding => XML::Encoding::UTF_8,
                           :options => XML::Parser::Options::NOENT
                           :base_uri="http://libxml.org") -> XML::Document

Creates a new document from the specified string.

You may provide an optional hash table to control how the parsing is performed. Valid options are:

base_uri - The base url for the parsed document.
encoding - The document encoding, defaults to nil. Valid values
           are the encoding constants defined on XML::Encoding.
options  - Parser options.  Valid values are the constants defined on
           XML::Parser::Options.  Mutliple options can be combined
           by using Bitwise OR (|).


75
76
77
# File 'lib/libxml/document.rb', line 75

def self.string(value, options = {})
  Parser.string(value, options).parse
end

Instance Method Details

#canonicalize(*args) ⇒ Object



187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
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
271
272
273
274
275
276
277
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
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
# File 'ext/libxml/ruby_xml_document.c', line 187

static VALUE
rxml_document_canonicalize(int argc, VALUE *argv, VALUE self)
{
  VALUE result = Qnil;
  xmlDocPtr xdoc;
  xmlChar *buffer = NULL;
  VALUE option_hash = Qnil;
  VALUE o_nodes = Qnil;

  // :comments option
  int comments = 0;
  // :mode option
  int c14n_mode = XML_C14N_1_0;
  // :inclusive_ns_prefixes option (ARRAY)

  xmlChar * inc_ns_prefixes_ptr[C14N_NS_LIMIT];

  // :nodes option (ARRAY)
  xmlNodePtr  node_ptr_array[C14N_NODESET_LIMIT];
  xmlNodeSet nodeset = {
    0, C14N_NODESET_LIMIT, NULL
  };

  /* At least one NULL value must be defined in the array or the extension will
   * segfault when using XML_C14N_EXCLUSIVE_1_0 mode.
   * API docs: "list of inclusive namespace prefixes ended with a NULL"
   */
  inc_ns_prefixes_ptr[0] = NULL;

  rb_scan_args(argc, argv, "01", &option_hash);
  // Do stuff if ruby hash passed as argument
  if (!NIL_P(option_hash)) 
  {
  VALUE o_comments = Qnil;
  VALUE o_mode = Qnil;
  VALUE o_i_ns_prefixes = Qnil;
    
    Check_Type(option_hash, T_HASH);

    o_comments = rb_hash_aref(option_hash, ID2SYM(rb_intern("comments")));
    comments = (RTEST(o_comments) ? 1 : 0);

    o_mode = rb_hash_aref(option_hash, ID2SYM(rb_intern("mode")));
    if (!NIL_P(o_mode)) 
  {
      Check_Type(o_mode, T_FIXNUM);
      c14n_mode = NUM2INT(o_mode);
      //TODO: clean this up
      //if (c14n_mode > 2) { c14n_mode = 0; }
      //mode_int = (NUM2INT(o_mode) > 2 ? 0 : NUM2INT(o_mode));
    }

    o_i_ns_prefixes = rb_hash_aref(option_hash, ID2SYM(rb_intern("inclusive_ns_prefixes")));
    if (!NIL_P(o_i_ns_prefixes)) 
  {
      int i;
      int p = 0; //pointer array index
      VALUE *list_in = NULL;
      long list_size = 0;

    Check_Type(o_i_ns_prefixes, T_ARRAY);
      list_in = RARRAY_PTR(o_i_ns_prefixes);
      list_size = RARRAY_LEN(o_i_ns_prefixes);

      if (list_size > 0) 
    {
        for(i=0; i < list_size; ++i) {
          if (p >= C14N_NS_LIMIT) { break; }

          if (RTEST(list_in[i])) 
      {
            if (TYPE(list_in[i]) == T_STRING) 
      {
              inc_ns_prefixes_ptr[p] = (xmlChar *)StringValueCStr(list_in[i]);
              p++;
            }
          }
        }
      }

      // ensure p is not out of bound
      p = (p >= C14N_NS_LIMIT ? (C14N_NS_LIMIT-1) : p);

      // API docs: "list of inclusive namespace prefixes ended with a NULL"
      // Set last element to NULL
      inc_ns_prefixes_ptr[p] = NULL;
    }
    //o_ns_prefixes will free at end of block

    o_nodes = rb_hash_aref(option_hash, ID2SYM(rb_intern("nodes")));
    if (!NIL_P(o_nodes)) 
  {
      int i;
      int p = 0; // index of pointer array
      VALUE * list_in = NULL;
      long node_list_size = 0;

    if (CLASS_OF(o_nodes) == cXMLXPathObject)
    {
      o_nodes = rb_funcall(o_nodes, rb_intern("to_a"), 0);
    }
    else
    {
      Check_Type(o_nodes, T_ARRAY);
    }
      list_in = RARRAY_PTR(o_nodes);
      node_list_size = RARRAY_LEN(o_nodes);

      for (i=0; i < node_list_size; ++i)
    {
        if (p >= C14N_NODESET_LIMIT) { break; }

        if (RTEST(list_in[i])) 
    {
          xmlNodePtr node_ptr;
          Data_Get_Struct(list_in[i], xmlNode, node_ptr);
          node_ptr_array[p] = node_ptr;
          p++;
        }
      }

      // Need to set values in nodeset struct
      nodeset.nodeNr = (node_list_size > C14N_NODESET_LIMIT ?

                        C14N_NODESET_LIMIT :
                        (int)node_list_size);
      nodeset.nodeTab = node_ptr_array;
    }
  }//option_hash

  Data_Get_Struct(self, xmlDoc, xdoc);
  xmlC14NDocDumpMemory(xdoc,
                       (nodeset.nodeNr == 0 ? NULL : &nodeset),
                       c14n_mode,
                       inc_ns_prefixes_ptr,
                       comments,
                       &buffer);

  if (buffer)
  {
    result = rxml_new_cstr( buffer, NULL);
    xmlFree(buffer);
  }

  return result;
}

#childObject

Get this document’s child node.



423
424
425
426
427
428
429
430
431
432
# File 'ext/libxml/ruby_xml_document.c', line 423

static VALUE rxml_document_child_get(VALUE self)
{
  xmlDocPtr xdoc;
  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->children == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->children);
}

#child?Boolean

Determine whether this document has a child node.

Returns:

  • (Boolean)


440
441
442
443
444
445
446
447
448
449
# File 'ext/libxml/ruby_xml_document.c', line 440

static VALUE rxml_document_child_q(VALUE self)
{
  xmlDocPtr xdoc;
  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->children == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

#compressionNumeric

Obtain this document’s compression mode identifier.

Returns:

  • (Numeric)


340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
# File 'ext/libxml/ruby_xml_document.c', line 340

static VALUE rxml_document_compression_get(VALUE self)
{
#ifdef HAVE_ZLIB_H

  xmlDocPtr xdoc;

  int compmode;
  Data_Get_Struct(self, xmlDoc, xdoc);

  compmode = xmlGetDocCompressMode(xdoc);
  if (compmode == -1)
  return(Qnil);
  else
  return(INT2NUM(compmode));
#else

  rb_warn("libxml not compiled with zlib support");
  return (Qfalse);
#endif

}

#compression=(num) ⇒ Object

Set this document’s compression mode.



365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
# File 'ext/libxml/ruby_xml_document.c', line 365

static VALUE rxml_document_compression_set(VALUE self, VALUE num)
{
#ifdef HAVE_ZLIB_H

  xmlDocPtr xdoc;

  int compmode;
  Check_Type(num, T_FIXNUM);
  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc == NULL)
  {
    return(Qnil);
  }
  else
  {
    xmlSetDocCompressMode(xdoc, NUM2INT(num));

    compmode = xmlGetDocCompressMode(xdoc);
    if (compmode == -1)
    return(Qnil);
    else
    return(INT2NUM(compmode));
  }
#else

  rb_warn("libxml compiled without zlib support");
  return (Qfalse);
#endif

}

#compression?Boolean

Determine whether this document is compressed.

Returns:

  • (Boolean)


400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
# File 'ext/libxml/ruby_xml_document.c', line 400

static VALUE rxml_document_compression_q(VALUE self)
{
#ifdef HAVE_ZLIB_H

  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->compression != -1)
  return(Qtrue);
  else
  return(Qfalse);
#else

  rb_warn("libxml compiled without zlib support");
  return (Qfalse);
#endif

}

#context(nslist = nil) ⇒ Object

Returns a new XML::XPathContext for the document.

call-seq:

document.context(namespaces=nil) -> XPath::Context

Namespaces is an optional array of XML::NS objects



85
86
87
88
89
90
91
# File 'lib/libxml/document.rb', line 85

def context(nslist = nil)
  context = XPath::Context.new(self)
  context.node = self.root
  context.register_namespaces_from_node(self.root)
  context.register_namespaces(nslist) if nslist
  context
end

#debugObject

Print libxml debugging information to stdout. Requires that libxml was compiled with debugging enabled.



459
460
461
462
463
464
465
466
467
468
469
470
# File 'ext/libxml/ruby_xml_document.c', line 459

static VALUE rxml_document_debug(VALUE self)
{
#ifdef LIBXML_DEBUG_ENABLED

  xmlDocPtr xdoc;
  Data_Get_Struct(self, xmlDoc, xdoc);
  xmlDebugDumpDocument(NULL, xdoc);
  return Qtrue;
#else

  rb_warn("libxml was compiled without debugging support.");
  return Qfalse;
#endif

}

#debug_dumpObject



173
174
175
176
# File 'lib/libxml/document.rb', line 173

def debug_dump
  warn('Document#debug_dump is deprecated.  Use Document#debug instead.')
  self.debug
end

#debug_dump_headObject



178
179
180
181
# File 'lib/libxml/document.rb', line 178

def debug_dump_head
  warn('Document#debug_dump_head is deprecated.  Use Document#debug instead.')
  self.debug
end

#debug_format_dumpObject



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

def debug_format_dump
  warn('Document#debug_format_dump is deprecated.  Use Document#to_s instead.')
  self.to_s
end

#docbook_doc?Boolean

Specifies if this is an docbook node

Returns:

  • (Boolean)


154
155
156
# File 'lib/libxml/document.rb', line 154

def docbook_doc?
  node_type == XML::Node::DOCB_DOCUMENT_NODE
end

#document?Boolean

Specifies if this is an document node

Returns:

  • (Boolean)


149
150
151
# File 'lib/libxml/document.rb', line 149

def document?
  node_type == XML::Node::DOCUMENT_NODE
end

#dumpObject



163
164
165
166
# File 'lib/libxml/document.rb', line 163

def dump
  warn('Document#dump is deprecated.  Use Document#to_s instead.')
  self.to_s
end

#encodingXML::Encoding::UTF_8

Returns the LibXML encoding constant specified by this document.



478
479
480
481
482
483
484
485
486
# File 'ext/libxml/ruby_xml_document.c', line 478

static VALUE rxml_document_encoding_get(VALUE self)
{
  xmlDocPtr xdoc;
  const char *xencoding;
  Data_Get_Struct(self, xmlDoc, xdoc);

  xencoding = (const char*)xdoc->encoding;
  return INT2NUM(xmlParseCharEncoding(xencoding));
}

#encoding=(XML) ⇒ Object

Set the encoding for this document.



514
515
516
517
518
519
520
521
522
523
524
525
526
# File 'ext/libxml/ruby_xml_document.c', line 514

static VALUE rxml_document_encoding_set(VALUE self, VALUE encoding)
{
  xmlDocPtr xdoc;
  const char* xencoding = xmlGetCharEncodingName((xmlCharEncoding)NUM2INT(encoding));

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->encoding != NULL)
    xmlFree((xmlChar *) xdoc->encoding);

  xdoc->encoding = xmlStrdup((xmlChar *)xencoding);
  return self;
}

#find(xpath, nslist = nil) ⇒ Object

Return the nodes matching the specified xpath expression, optionally using the specified namespace. For more information about working with namespaces, please refer to the XML::XPath documentation.

call-seq:

document.find(xpath, nslist=nil) -> XML::XPath::Object

Parameters:

  • xpath - The xpath expression as a string

  • namespaces - An optional list of namespaces (see XML::XPath for information).

document.find('/foo', 'xlink:http://www.w3.org/1999/xlink')

IMPORTANT - The returned XML::Node::Set must be freed before its associated document. In a running Ruby program this will happen automatically via Ruby’s mark and sweep garbage collector. However, if the program exits, Ruby does not guarantee the order in which objects are freed (see blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-core/17700). As a result, the associated document may be freed before the node list, which will cause a segmentation fault. To avoid this, use the following (non-ruby like) coding style:

nodes = doc.find('/header')
nodes.each do |node|
  ... do stuff ...
end

# nodes = nil # GC.start



122
123
124
# File 'lib/libxml/document.rb', line 122

def find(xpath, nslist = nil)
  self.context(nslist).find(xpath)
end

#find_first(xpath, nslist = nil) ⇒ Object

Return the first node matching the specified xpath expression. For more information, please refer to the documentation for XML::Document#find.



129
130
131
# File 'lib/libxml/document.rb', line 129

def find_first(xpath, nslist = nil)
  find(xpath, nslist).first
end

#format_dumpObject



168
169
170
171
# File 'lib/libxml/document.rb', line 168

def format_dump
  warn('Document#format_dump is deprecated.  Use Document#to_s instead.')
  self.to_s
end

#html_doc?Boolean

Specifies if this is an html node

Returns:

  • (Boolean)


159
160
161
# File 'lib/libxml/document.rb', line 159

def html_doc?
  node_type == XML::Node::HTML_DOCUMENT_NODE
end

#import(node) ⇒ XML::Node

Creates a copy of the node that can be inserted into the current document.

IMPORTANT - The returned node MUST be inserted into the document. This is because the returned node refereces internal LibXML data structures owned by the document. Therefore, if the document is is freed before the the node is freed a segmentation fault will occur.

Returns:



540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
# File 'ext/libxml/ruby_xml_document.c', line 540

static VALUE rxml_document_import(VALUE self, VALUE node)
{
  xmlDocPtr xdoc;
  xmlNodePtr xnode, xresult;

  Data_Get_Struct(self, xmlDoc, xdoc);
  Data_Get_Struct(node, xmlNode, xnode);

  xresult = xmlDocCopyNode(xnode, xdoc, 1);

  if (xresult == NULL)
    rxml_raise(&xmlLastError);

  return rxml_node_wrap(xresult);
}

#lastObject

Obtain the last node.



562
563
564
565
566
567
568
569
570
571
572
# File 'ext/libxml/ruby_xml_document.c', line 562

static VALUE rxml_document_last_get(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->last == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->last);
}

#last?Boolean

Determine whether there is a last node.

Returns:

  • (Boolean)


580
581
582
583
584
585
586
587
588
589
590
# File 'ext/libxml/ruby_xml_document.c', line 580

static VALUE rxml_document_last_q(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->last == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

#nextObject

Obtain the next node.



598
599
600
601
602
603
604
605
606
607
608
# File 'ext/libxml/ruby_xml_document.c', line 598

static VALUE rxml_document_next_get(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->next == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->next);
}

#next?Boolean

Determine whether there is a next node.

Returns:

  • (Boolean)


616
617
618
619
620
621
622
623
624
625
626
# File 'ext/libxml/ruby_xml_document.c', line 616

static VALUE rxml_document_next_q(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->next == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

#typeNumeric

Obtain this node’s type identifier.

Returns:

  • (Numeric)


634
635
636
637
638
639
# File 'ext/libxml/ruby_xml_document.c', line 634

static VALUE rxml_document_node_type(VALUE self)
{
  xmlNodePtr xnode;
  Data_Get_Struct(self, xmlNode, xnode);
  return (INT2NUM(xnode->type));
}

#node_type_nameObject

Returns this node’s type name



134
135
136
137
138
139
140
141
142
143
144
145
# File 'lib/libxml/document.rb', line 134

def node_type_name
  case node_type
  when XML::Node::DOCUMENT_NODE
    'document_xml'
  when XML::Node::DOCB_DOCUMENT_NODE
    'document_docbook'
  when XML::Node::HTML_DOCUMENT_NODE
    'document_html'
  else
    raise(UnknownType, "Unknown node type: %n", node.node_type);
  end
end

#order_elements!Object

Call this routine to speed up XPath computation on static documents. This stamps all the element nodes with the document order.



980
981
982
983
984
985
986
# File 'ext/libxml/ruby_xml_document.c', line 980

static VALUE rxml_document_order_elements(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);
  return LONG2FIX(xmlXPathOrderDocElems(xdoc));
}

#parentObject

Obtain the parent node.



647
648
649
650
651
652
653
654
655
656
657
# File 'ext/libxml/ruby_xml_document.c', line 647

static VALUE rxml_document_parent_get(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->parent == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->parent);
}

#parent?Boolean

Determine whether there is a parent node.

Returns:

  • (Boolean)


665
666
667
668
669
670
671
672
673
674
675
# File 'ext/libxml/ruby_xml_document.c', line 665

static VALUE rxml_document_parent_q(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->parent == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

#prevObject

Obtain the previous node.



683
684
685
686
687
688
689
690
691
692
693
# File 'ext/libxml/ruby_xml_document.c', line 683

static VALUE rxml_document_prev_get(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->prev == NULL)
    return (Qnil);

  return rxml_node_wrap(xdoc->prev);
}

#prev?Boolean

Determine whether there is a previous node.

Returns:

  • (Boolean)


701
702
703
704
705
706
707
708
709
710
711
# File 'ext/libxml/ruby_xml_document.c', line 701

static VALUE rxml_document_prev_q(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);

  if (xdoc->prev == NULL)
    return (Qfalse);
  else
    return (Qtrue);
}

#rb_encodingObject



497
498
499
500
501
502
503
504
505
# File 'ext/libxml/ruby_xml_document.c', line 497

static VALUE rxml_document_rb_encoding_get(VALUE self)
{
  xmlDocPtr xdoc;
  rb_encoding* rbencoding;
  Data_Get_Struct(self, xmlDoc, xdoc);

  rbencoding = rxml_xml_encoding_to_rb_encoding(mXMLEncoding, xmlParseCharEncoding((const char*)xdoc->encoding));
  return rb_enc_from_encoding(rbencoding);
}

#readerObject



188
189
190
191
# File 'lib/libxml/document.rb', line 188

def reader
  warn('Document#reader is deprecated.  Use XML::Reader.document(self) instead.')
  XML::Reader.document(self)
end

#rootObject

Obtain the root node.



719
720
721
722
723
724
725
726
727
728
729
730
731
# File 'ext/libxml/ruby_xml_document.c', line 719

static VALUE rxml_document_root_get(VALUE self)
{
  xmlDocPtr xdoc;
  xmlNodePtr root;

  Data_Get_Struct(self, xmlDoc, xdoc);
  root = xmlDocGetRootElement(xdoc);

  if (root == NULL)
    return (Qnil);

  return rxml_node_wrap(root);
}

#root=(node) ⇒ Object

Set the root node.



739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
# File 'ext/libxml/ruby_xml_document.c', line 739

static VALUE rxml_document_root_set(VALUE self, VALUE node)
{
  xmlDocPtr xdoc;
  xmlNodePtr xnode;

  if (rb_obj_is_kind_of(node, cXMLNode) == Qfalse)
    rb_raise(rb_eTypeError, "must pass an XML::Node type object");

  Data_Get_Struct(self, xmlDoc, xdoc);
  Data_Get_Struct(node, xmlNode, xnode);

  if (xnode->doc != NULL && xnode->doc != xdoc)
    rb_raise(eXMLError, "Nodes belong to different documents.  You must first import the node by calling XML::Document.import");

  xmlDocSetRootElement(xdoc, xnode);
  return node;
}

#save(filename) ⇒ Integer #save(filename, : indent) ⇒ true

Saves a document to a file. You may provide an optional hash table to control how the string is generated. Valid options are:

:indent - Specifies if the string should be indented. The default value is true. Note that indentation is only added if both :indent is true and XML.indent_tree_output is true. If :indent is set to false, then both indentation and line feeds are removed from the result.

:encoding - Specifies the output encoding of the string. It defaults to the original encoding of the document (see #encoding. To override the orginal encoding, use one of the XML::Encoding encoding constants.

Overloads:

  • #save(filename) ⇒ Integer

    Returns:

    • (Integer)
  • #save(filename, : indent) ⇒ true

    Returns:

    • (true)


774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
# File 'ext/libxml/ruby_xml_document.c', line 774

static VALUE rxml_document_save(int argc, VALUE *argv, VALUE self)
{
  VALUE options = Qnil;
  VALUE filename = Qnil;
  xmlDocPtr xdoc;
  int indent = 1;
  const char *xfilename;
  const xmlChar *xencoding;
  int length;

  rb_scan_args(argc, argv, "11", &filename, &options);

  Check_Type(filename, T_STRING);
  xfilename = StringValuePtr(filename);

  Data_Get_Struct(self, xmlDoc, xdoc);
  xencoding = xdoc->encoding;

  if (!NIL_P(options))
  {
    VALUE rencoding, rindent;
    Check_Type(options, T_HASH);
    rencoding = rb_hash_aref(options, ID2SYM(rb_intern("encoding")));
    rindent = rb_hash_aref(options, ID2SYM(rb_intern("indent")));

    if (rindent == Qfalse)
      indent = 0;

    if (rencoding != Qnil)
    {
      xencoding = (const xmlChar*)xmlGetCharEncodingName((xmlCharEncoding)NUM2INT(rencoding));
      if (!xencoding)
        rb_raise(rb_eArgError, "Unknown encoding value: %d", NUM2INT(rencoding));
    }
  }

  length = xmlSaveFormatFileEnc(xfilename, xdoc, (const char*)xencoding, indent);

  if (length == -1)
    rxml_raise(&xmlLastError);

  return (INT2NUM(length));
}

#standalone?Boolean

Determine whether this is a standalone document.

Returns:

  • (Boolean)


824
825
826
827
828
829
830
831
832
833
# File 'ext/libxml/ruby_xml_document.c', line 824

static VALUE rxml_document_standalone_q(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);
  if (xdoc->standalone)
    return (Qtrue);
  else
    return (Qfalse);
}

#to_sObject #to_s(: indent) ⇒ true

Converts a document, and all of its children, to a string representation. You may provide an optional hash table to control how the string is generated. Valid options are:

:indent - Specifies if the string should be indented. The default value is true. Note that indentation is only added if both :indent is true and XML.indent_tree_output is true. If :indent is set to false, then both indentation and line feeds are removed from the result.

:encoding - Specifies the output encoding of the string. It defaults to XML::Encoding::UTF8. To change it, use one of the XML::Encoding encoding constants.

Overloads:

  • #to_s(: indent) ⇒ true

    Returns:

    • (true)


852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
# File 'ext/libxml/ruby_xml_document.c', line 852

static VALUE rxml_document_to_s(int argc, VALUE *argv, VALUE self)
{
  VALUE result;
  VALUE options = Qnil;
  xmlDocPtr xdoc;
  int indent = 1;
  const xmlChar *xencoding = (const xmlChar*) "UTF-8";
  xmlChar *buffer;
  int length;

  rb_scan_args(argc, argv, "01", &options);

  if (!NIL_P(options))
  {
    VALUE rencoding, rindent;
    Check_Type(options, T_HASH);
    rencoding = rb_hash_aref(options, ID2SYM(rb_intern("encoding")));
    rindent = rb_hash_aref(options, ID2SYM(rb_intern("indent")));

    if (rindent == Qfalse)
      indent = 0;

    if (rencoding != Qnil)
    {
      xencoding = (const xmlChar*)xmlGetCharEncodingName((xmlCharEncoding)NUM2INT(rencoding));
      if (!xencoding)
        rb_raise(rb_eArgError, "Unknown encoding value: %d", NUM2INT(rencoding));
    }
  }

  Data_Get_Struct(self, xmlDoc, xdoc);
  xmlDocDumpFormatMemoryEnc(xdoc, &buffer, &length, (const char*)xencoding, indent);

  result = rxml_new_cstr(buffer, xencoding);
  xmlFree(buffer);
  return result;
}

#urlObject

Obtain this document’s source URL, if any.



896
897
898
899
900
901
902
903
904
905
# File 'ext/libxml/ruby_xml_document.c', line 896

static VALUE rxml_document_url_get(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);
  if (xdoc->URL == NULL)
    return (Qnil);
  else
    return (rxml_new_cstr( xdoc->URL, NULL));
}

#validate(dtd) ⇒ Object

Validate this document against the specified XML::DTD. If the document is valid the method returns true. Otherwise an exception is raised with validation information.



1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
# File 'ext/libxml/ruby_xml_document.c', line 1062

static VALUE rxml_document_validate_dtd(VALUE self, VALUE dtd)
{
  xmlValidCtxt ctxt;
  xmlDocPtr xdoc;
  xmlDtdPtr xdtd;

  Data_Get_Struct(self, xmlDoc, xdoc);
  Data_Get_Struct(dtd, xmlDtd, xdtd);

  /* Setup context */
  memset(&ctxt, 0, sizeof(xmlValidCtxt));

  if (xmlValidateDtd(&ctxt, xdoc, xdtd))
  {
    return Qtrue;
  }
  else
  {
    rxml_raise(&xmlLastError);
    return Qfalse;
  }
}

#validate_relaxng(relaxng) ⇒ Object

Validate this document against the specified XML::RelaxNG. If the document is valid the method returns true. Otherwise an exception is raised with validation information.



1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
# File 'ext/libxml/ruby_xml_document.c', line 1029

static VALUE rxml_document_validate_relaxng(VALUE self, VALUE relaxng)
{
  xmlRelaxNGValidCtxtPtr vptr;
  xmlDocPtr xdoc;
  xmlRelaxNGPtr xrelaxng;
  int is_invalid;

  Data_Get_Struct(self, xmlDoc, xdoc);
  Data_Get_Struct(relaxng, xmlRelaxNG, xrelaxng);

  vptr = xmlRelaxNGNewValidCtxt(xrelaxng);

  is_invalid = xmlRelaxNGValidateDoc(vptr, xdoc);
  xmlRelaxNGFreeValidCtxt(vptr);
  if (is_invalid)
  {
    rxml_raise(&xmlLastError);
    return Qfalse;
  }
  else
  {
    return Qtrue;
  }
}

#validate_schema(schema) ⇒ Object

Validate this document against the specified XML::Schema. If the document is valid the method returns true. Otherwise an exception is raised with validation information.



996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
# File 'ext/libxml/ruby_xml_document.c', line 996

static VALUE rxml_document_validate_schema(VALUE self, VALUE schema)
{
  xmlSchemaValidCtxtPtr vptr;
  xmlDocPtr xdoc;
  xmlSchemaPtr xschema;
  int is_invalid;

  Data_Get_Struct(self, xmlDoc, xdoc);
  Data_Get_Struct(schema, xmlSchema, xschema);

  vptr = xmlSchemaNewValidCtxt(xschema);

  is_invalid = xmlSchemaValidateDoc(vptr, xdoc);
  xmlSchemaFreeValidCtxt(vptr);
  if (is_invalid)
  {
    rxml_raise(&xmlLastError);
    return Qfalse;
  }
  else
  {
    return Qtrue;
  }
}

#versionObject

Obtain the XML version specified by this document.



913
914
915
916
917
918
919
920
921
922
# File 'ext/libxml/ruby_xml_document.c', line 913

static VALUE rxml_document_version_get(VALUE self)
{
  xmlDocPtr xdoc;

  Data_Get_Struct(self, xmlDoc, xdoc);
  if (xdoc->version == NULL)
    return (Qnil);
  else
    return (rxml_new_cstr( xdoc->version, NULL));
}

#xhtml?Boolean

Determine whether this is an XHTML document.

Returns:

  • (Boolean)


930
931
932
933
934
935
936
937
938
939
940
# File 'ext/libxml/ruby_xml_document.c', line 930

static VALUE rxml_document_xhtml_q(VALUE self)
{
  xmlDocPtr xdoc;
  xmlDtdPtr xdtd;
  Data_Get_Struct(self, xmlDoc, xdoc);
  xdtd = xmlGetIntSubset(xdoc);
  if (xdtd != NULL && xmlIsXHTML(xdtd->SystemID, xdtd->ExternalID) > 0)
    return (Qtrue);
  else
    return (Qfalse);
}

#xincludeNumeric

Process xinclude directives in this document.

Returns:

  • (Numeric)


948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
# File 'ext/libxml/ruby_xml_document.c', line 948

static VALUE rxml_document_xinclude(VALUE self)
{
#ifdef LIBXML_XINCLUDE_ENABLED

  xmlDocPtr xdoc;

  int ret;

  Data_Get_Struct(self, xmlDoc, xdoc);
  ret = xmlXIncludeProcess(xdoc);
  if (ret >= 0)
  {
    return(INT2NUM(ret));
  }
  else
  {
    rxml_raise(&xmlLastError);
    return Qnil;
  }
#else

  rb_warn(
      "libxml was compiled without XInclude support.  Please recompile libxml and ruby-libxml");
  return (Qfalse);
#endif

}