Class: Nokogiri::XML::Reader

Inherits:
Object
  • Object
show all
Includes:
Enumerable
Defined in:
lib/nokogiri/xml/reader.rb,
ext/nokogiri/xml_reader.c

Overview

Nokogiri::XML::Reader parses an XML document similar to the way a cursor would move. The Reader is given an XML document, and yields nodes to an each block.

Here is an example of usage:

reader = Nokogiri::XML::Reader(<<-eoxml)
  <x xmlns:tenderlove='http://tenderlovemaking.com/'>
    <tenderlove:foo awesome='true'>snuggles!</tenderlove:foo>
  </x>
eoxml

reader.each do |node|

  # node is an instance of Nokogiri::XML::Reader
  puts node.name

end

Note that Nokogiri::XML::Reader#each can only be called once!! Once the cursor moves through the entire document, you must parse the document again. So make sure that you capture any information you need during the first iteration.

The Reader parser is good for when you need the speed of a SAX parser, but do not want to write a Document handler.

Constant Summary collapse

TYPE_NONE = 
0
TYPE_ELEMENT =

Element node type

1
TYPE_ATTRIBUTE =

Attribute node type

2
TYPE_TEXT =

Text node type

3
TYPE_CDATA =

CDATA node type

4
TYPE_ENTITY_REFERENCE =

Entity Reference node type

5
TYPE_ENTITY =

Entity node type

6
TYPE_PROCESSING_INSTRUCTION =

PI node type

7
TYPE_COMMENT =

Comment node type

8
TYPE_DOCUMENT =

Document node type

9
TYPE_DOCUMENT_TYPE =

Document Type node type

10
TYPE_DOCUMENT_FRAGMENT =

Document Fragment node type

11
TYPE_NOTATION =

Notation node type

12
TYPE_WHITESPACE =

Whitespace node type

13
TYPE_SIGNIFICANT_WHITESPACE =

Significant Whitespace node type

14
TYPE_END_ELEMENT =

Element end node type

15
TYPE_END_ENTITY =

Entity end node type

16
TYPE_XML_DECLARATION =

XML Declaration node type

17

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Instance Attribute Details

#encoding ⇒ Object (readonly)

The encoding for the document



73
74
75
 
# File 'lib/nokogiri/xml/reader.rb', line 73

def encoding
  @encoding
end

#errors ⇒ Object

A list of errors encountered while parsing



70
71
72
 
# File 'lib/nokogiri/xml/reader.rb', line 70

def errors
  @errors
end

#source ⇒ Object (readonly)

The XML source



76
77
78
 
# File 'lib/nokogiri/xml/reader.rb', line 76

def source
  @source
end

Class Method Details

.from_io(io, url = nil, encoding = nil, options = 0) ⇒ Object

Create a new reader that parses io



584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
 
# File 'ext/nokogiri/xml_reader.c', line 584

static VALUE from_io(int argc, VALUE *argv, VALUE klass)
{
  VALUE rb_io, rb_url, encoding, rb_options;
  xmlTextReaderPtr reader;
  const char * c_url      = NULL;
  const char * c_encoding = NULL;
  int c_options           = 0;
  VALUE rb_reader, args[3];

  rb_scan_args(argc, argv, "13", &rb_io, &rb_url, &encoding, &rb_options);

  if (!RTEST(rb_io)) rb_raise(rb_eArgError, "io cannot be nil");
  if (RTEST(rb_url)) c_url = StringValuePtr(rb_url);
  if (RTEST(encoding)) c_encoding = StringValuePtr(encoding);
  if (RTEST(rb_options)) c_options = (int)NUM2INT(rb_options);

  reader = xmlReaderForIO(
      (xmlInputReadCallback)io_read_callback,
      (xmlInputCloseCallback)io_close_callback,
      (void *)rb_io,
      c_url,
      c_encoding,
      c_options
  );

  if(reader == NULL) {
    xmlFreeTextReader(reader);
    rb_raise(rb_eRuntimeError, "couldn't create a parser");
  }

  rb_reader = Data_Wrap_Struct(klass, NULL, dealloc, reader);
  args[0] = rb_io;
  args[1] = rb_url;
  args[2] = encoding;
  rb_obj_call_init(rb_reader, 3, args);

  return rb_reader;
}

.from_memory(string, url = nil, encoding = nil, options = 0) ⇒ Object

Create a new reader that parses string



540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
 
# File 'ext/nokogiri/xml_reader.c', line 540

static VALUE from_memory(int argc, VALUE *argv, VALUE klass)
{
  VALUE rb_buffer, rb_url, encoding, rb_options;
  xmlTextReaderPtr reader;
  const char * c_url      = NULL;
  const char * c_encoding = NULL;
  int c_options           = 0;
  VALUE rb_reader, args[3];

  rb_scan_args(argc, argv, "13", &rb_buffer, &rb_url, &encoding, &rb_options);

  if (!RTEST(rb_buffer)) rb_raise(rb_eArgError, "string cannot be nil");
  if (RTEST(rb_url)) c_url = StringValuePtr(rb_url);
  if (RTEST(encoding)) c_encoding = StringValuePtr(encoding);
  if (RTEST(rb_options)) c_options = (int)NUM2INT(rb_options);

  reader = xmlReaderForMemory(
      StringValuePtr(rb_buffer),
      (int)RSTRING_LEN(rb_buffer),
      c_url,
      c_encoding,
      c_options
  );

  if(reader == NULL) {
    xmlFreeTextReader(reader);
    rb_raise(rb_eRuntimeError, "couldn't create a parser");
  }

  rb_reader = Data_Wrap_Struct(klass, NULL, dealloc, reader);
  args[0] = rb_buffer;
  args[1] = rb_url;
  args[2] = encoding;
  rb_obj_call_init(rb_reader, 3, args);

  return rb_reader;
}

Instance Method Details

#attribute(name) ⇒ Object

Get the value of attribute named name



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
 
# File 'ext/nokogiri/xml_reader.c', line 213

static VALUE reader_attribute(VALUE self, VALUE name)
{
  xmlTextReaderPtr reader;
  xmlChar *value ;
  VALUE rb_value;

  Data_Get_Struct(self, xmlTextReader, reader);

  if(NIL_P(name)) return Qnil;
  name = StringValue(name) ;

  value = xmlTextReaderGetAttribute(reader, (xmlChar*)StringValuePtr(name));
  if(value == NULL) {
    /* this section is an attempt to workaround older versions of libxml that
       don't handle namespaces properly in all attribute-and-friends functions */
    xmlChar *prefix = NULL ;
    xmlChar *localname = xmlSplitQName2((xmlChar*)StringValuePtr(name), &prefix);
    if (localname != NULL) {
      value = xmlTextReaderLookupNamespace(reader, localname);
      xmlFree(localname) ;
    } else {
      value = xmlTextReaderLookupNamespace(reader, prefix);
    }
    xmlFree(prefix);
  }
  if(value == NULL) return Qnil;

  rb_value = NOKOGIRI_STR_NEW2(value);
  xmlFree(value);
  return rb_value;
}

#attribute_at(index) ⇒ Object

Get the value of attribute at index



185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
 
# File 'ext/nokogiri/xml_reader.c', line 185

static VALUE attribute_at(VALUE self, VALUE index)
{
  xmlTextReaderPtr reader;
  xmlChar *value;
  VALUE rb_value;

  Data_Get_Struct(self, xmlTextReader, reader);

  if(NIL_P(index)) return Qnil;
  index = rb_Integer(index);

  value = xmlTextReaderGetAttributeNo(
      reader,
      (int)NUM2INT(index)
  );
  if(value == NULL) return Qnil;

  rb_value = NOKOGIRI_STR_NEW2(value);
  xmlFree(value);
  return rb_value;
}

#attribute_count ⇒ Object

Get the number of attributes for the current node



251
252
253
254
255
256
257
258
259
260
261
 
# File 'ext/nokogiri/xml_reader.c', line 251

static VALUE attribute_count(VALUE self)
{
  xmlTextReaderPtr reader;
  int count;

  Data_Get_Struct(self, xmlTextReader, reader);
  count = xmlTextReaderAttributeCount(reader);
  if(count == -1) return Qnil;

  return INT2NUM((long)count);
}

#attribute_nodes ⇒ Object

Get a list of attributes for the current node



97
98
99
100
101
 
# File 'lib/nokogiri/xml/reader.rb', line 97

def attribute_nodes
  nodes = attr_nodes
  nodes.each { |v| v.instance_variable_set(:@_r, self) }
  nodes
end

#attributes ⇒ Object

Get a list of attributes for the current node.



89
90
91
92
93
 
# File 'lib/nokogiri/xml/reader.rb', line 89

def attributes
  Hash[attribute_nodes.map { |node|
    [node.name, node.to_s]
  }].merge(namespaces || {})
end

#attributes? ⇒ Boolean

Does this node have attributes?

Returns:

  • (Boolean) 


112
113
114
115
116
117
118
119
120
121
122
123
 
# File 'ext/nokogiri/xml_reader.c', line 112

static VALUE attributes_eh(VALUE self)
{
  xmlTextReaderPtr reader;
  int eh;

  Data_Get_Struct(self, xmlTextReader, reader);
  eh = has_attributes(reader);
  if(eh == 0) return Qfalse;
  if(eh == 1) return Qtrue;

  return Qnil;
}

#base_uri ⇒ Object

base_uri

Get the xml:base of the node



413
414
415
416
417
418
419
420
421
422
423
 
# File 'ext/nokogiri/xml_reader.c', line 413

static VALUE base_uri(VALUE self)
{
  xmlTextReaderPtr reader;
  const char * base_uri;

  Data_Get_Struct(self, xmlTextReader, reader);
  base_uri = (const char *)xmlTextReaderBaseUri(reader);
  if (base_uri == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(base_uri);
}

#default? ⇒ Boolean

Was an attribute generated from the default value in the DTD or schema?

Returns:

  • (Boolean) 


74
75
76
77
78
79
80
81
82
83
84
85
 
# File 'ext/nokogiri/xml_reader.c', line 74

static VALUE default_eh(VALUE self)
{
  xmlTextReaderPtr reader;
  int eh;

  Data_Get_Struct(self, xmlTextReader, reader);
  eh = xmlTextReaderIsDefault(reader);
  if(eh == 0) return Qfalse;
  if(eh == 1) return Qtrue;

  return Qnil;
}

#depth ⇒ Object

Get the depth of the node



269
270
271
272
273
274
275
276
277
278
279
 
# File 'ext/nokogiri/xml_reader.c', line 269

static VALUE depth(VALUE self)
{
  xmlTextReaderPtr reader;
  int depth;

  Data_Get_Struct(self, xmlTextReader, reader);
  depth = xmlTextReaderDepth(reader);
  if(depth == -1) return Qnil;

  return INT2NUM((long)depth);
}

#each ⇒ Object

Move the cursor through the document yielding the cursor to the block



105
106
107
108
109
 
# File 'lib/nokogiri/xml/reader.rb', line 105

def each
  while cursor = self.read
    yield cursor
  end
end

#empty_element?(#) ⇒ Boolean Also known as: self_closing?

Returns true if the current node is empty, otherwise false.

Returns:

  • (Boolean) 


629
630
631
632
633
634
635
636
637
638
639
 
# File 'ext/nokogiri/xml_reader.c', line 629

static VALUE empty_element_p(VALUE self)
{
  xmlTextReaderPtr reader;

  Data_Get_Struct(self, xmlTextReader, reader);

  if(xmlTextReaderIsEmptyElement(reader))
    return Qtrue;

  return Qfalse;
}

#inner_xml ⇒ Object

Read the contents of the current node, including child nodes and markup. Returns a utf-8 encoded string.



491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
 
# File 'ext/nokogiri/xml_reader.c', line 491

static VALUE inner_xml(VALUE self)
{
  xmlTextReaderPtr reader;
  xmlChar* value;
  VALUE str;

  Data_Get_Struct(self, xmlTextReader, reader);

  value = xmlTextReaderReadInnerXml(reader);

  str = Qnil;
  if(value) {
    str = NOKOGIRI_STR_NEW2((char*)value);
    xmlFree(value);
  }

  return str;
}

#lang ⇒ Object

Get the xml:lang scope within which the node resides.



305
306
307
308
309
310
311
312
313
314
315
 
# File 'ext/nokogiri/xml_reader.c', line 305

static VALUE lang(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *lang;

  Data_Get_Struct(self, xmlTextReader, reader);
  lang = (const char *)xmlTextReaderConstXmlLang(reader);
  if(lang == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(lang);
}

#local_name ⇒ Object

Get the local name of the node



377
378
379
380
381
382
383
384
385
386
387
 
# File 'ext/nokogiri/xml_reader.c', line 377

static VALUE local_name(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *name;

  Data_Get_Struct(self, xmlTextReader, reader);
  name = (const char *)xmlTextReaderConstLocalName(reader);
  if(name == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(name);
}

#name ⇒ Object

Get the name of the node. Returns a utf-8 encoded string.



395
396
397
398
399
400
401
402
403
404
405
 
# File 'ext/nokogiri/xml_reader.c', line 395

static VALUE name(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *name;

  Data_Get_Struct(self, xmlTextReader, reader);
  name = (const char *)xmlTextReaderConstName(reader);
  if(name == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(name);
}

#namespace_uri ⇒ Object

Get the URI defining the namespace associated with the node



359
360
361
362
363
364
365
366
367
368
369
 
# File 'ext/nokogiri/xml_reader.c', line 359

static VALUE namespace_uri(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *uri;

  Data_Get_Struct(self, xmlTextReader, reader);
  uri = (const char *)xmlTextReaderConstNamespaceUri(reader);
  if(uri == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(uri);
}

#namespaces ⇒ Object

Get a hash of namespaces for this Node



131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
 
# File 'ext/nokogiri/xml_reader.c', line 131

static VALUE namespaces(VALUE self)
{
  xmlTextReaderPtr reader;
  xmlNodePtr ptr;
  VALUE attr ;

  Data_Get_Struct(self, xmlTextReader, reader);

  attr = rb_hash_new() ;

  if (! has_attributes(reader))
    return attr ;

  ptr = xmlTextReaderExpand(reader);
  if(ptr == NULL) return Qnil;

  Nokogiri_xml_node_namespaces(ptr, attr);

  return attr ;
}

#node_type ⇒ Object

Get the type of readers current node



444
445
446
447
448
449
 
# File 'ext/nokogiri/xml_reader.c', line 444

static VALUE node_type(VALUE self)
{
  xmlTextReaderPtr reader;
  Data_Get_Struct(self, xmlTextReader, reader);
  return INT2NUM((long)xmlTextReaderNodeType(reader));
}

#outer_xml ⇒ Object

Read the current node and its contents, including child nodes and markup. Returns a utf-8 encoded string.



517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
 
# File 'ext/nokogiri/xml_reader.c', line 517

static VALUE outer_xml(VALUE self)
{
  xmlTextReaderPtr reader;
  xmlChar *value;
  VALUE str = Qnil;

  Data_Get_Struct(self, xmlTextReader, reader);

  value = xmlTextReaderReadOuterXml(reader);

  if(value) {
    str = NOKOGIRI_STR_NEW2((char*)value);
    xmlFree(value);
  }
  return str;
}

#prefix ⇒ Object

Get the shorthand reference to the namespace associated with the node.



341
342
343
344
345
346
347
348
349
350
351
 
# File 'ext/nokogiri/xml_reader.c', line 341

static VALUE prefix(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *prefix;

  Data_Get_Struct(self, xmlTextReader, reader);
  prefix = (const char *)xmlTextReaderConstPrefix(reader);
  if(prefix == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(prefix);
}

#read ⇒ Object

Move the Reader forward through the XML document.



457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
 
# File 'ext/nokogiri/xml_reader.c', line 457

static VALUE read_more(VALUE self)
{
  xmlTextReaderPtr reader;
  xmlErrorPtr error;
  VALUE error_list;
  int ret;

  Data_Get_Struct(self, xmlTextReader, reader);

  error_list = rb_funcall(self, rb_intern("errors"), 0);

  xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher);
  ret = xmlTextReaderRead(reader);
  xmlSetStructuredErrorFunc(NULL, NULL);

  if(ret == 1) return self;
  if(ret == 0) return Qnil;

  error = xmlGetLastError();
  if(error)
    rb_exc_raise(Nokogiri_wrap_xml_syntax_error( Qnil , error));
  else
    rb_raise(rb_eRuntimeError, "Error pulling: %d", ret);

  return Qnil;
}

#state ⇒ Object

Get the state of the reader



431
432
433
434
435
436
 
# File 'ext/nokogiri/xml_reader.c', line 431

static VALUE state(VALUE self)
{
  xmlTextReaderPtr reader;
  Data_Get_Struct(self, xmlTextReader, reader);
  return INT2NUM((long)xmlTextReaderReadState(reader));
}

#value ⇒ Object

Get the text value of the node if present. Returns a utf-8 encoded string.



323
324
325
326
327
328
329
330
331
332
333
 
# File 'ext/nokogiri/xml_reader.c', line 323

static VALUE value(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *value;

  Data_Get_Struct(self, xmlTextReader, reader);
  value = (const char *)xmlTextReaderConstValue(reader);
  if(value == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(value);
}

#value? ⇒ Boolean

Does this node have a text value?

Returns:

  • (Boolean) 


93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'ext/nokogiri/xml_reader.c', line 93

static VALUE value_eh(VALUE self)
{
  xmlTextReaderPtr reader;
  int eh;

  Data_Get_Struct(self, xmlTextReader, reader);
  eh = xmlTextReaderHasValue(reader);
  if(eh == 0) return Qfalse;
  if(eh == 1) return Qtrue;

  return Qnil;
}

#xml_version ⇒ Object

Get the XML version of the document being read



287
288
289
290
291
292
293
294
295
296
297
 
# File 'ext/nokogiri/xml_reader.c', line 287

static VALUE xml_version(VALUE self)
{
  xmlTextReaderPtr reader;
  const char *version;

  Data_Get_Struct(self, xmlTextReader, reader);
  version = (const char *)xmlTextReaderConstXmlVersion(reader);
  if(version == NULL) return Qnil;

  return NOKOGIRI_STR_NEW2(version);
}