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

#errors ⇒ Object

A list of errors encountered while parsing



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

def errors
  @errors
end

#source ⇒ Object (readonly)

The XML source



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

def source
  @source
end

Class Method Details

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

Create a new reader that parses io



652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
 
# File 'ext/nokogiri/xml_reader.c', line 652

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 = StringValueCStr(rb_url); }
  if (RTEST(encoding)) { c_encoding = StringValueCStr(encoding); }
  if (RTEST(rb_options)) { c_options = (int)NUM2INT(rb_options); }

  reader = xmlReaderForIO(
             (xmlInputReadCallback)noko_io_read,
             (xmlInputCloseCallback)noko_io_close,
             (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



607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
 
# File 'ext/nokogiri/xml_reader.c', line 607

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 = StringValueCStr(rb_url); }
  if (RTEST(encoding)) { c_encoding = StringValueCStr(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



269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
 
# File 'ext/nokogiri/xml_reader.c', line 269

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 *)StringValueCStr(name));
  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



240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
 
# File 'ext/nokogiri/xml_reader.c', line 240

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



295
296
297
298
299
300
301
302
303
304
305
306
 
# File 'ext/nokogiri/xml_reader.c', line 295

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_hash ⇒ Object

:call-seq: attribute_hash() → Hash<String ⇒ String>

Get the attributes of the current node as a Hash of names and values.

See related: #attributes and #namespaces



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
 
# File 'ext/nokogiri/xml_reader.c', line 200

static VALUE
rb_xml_reader_attribute_hash(VALUE rb_reader)
{
  VALUE rb_attributes = rb_hash_new();
  xmlTextReaderPtr c_reader;
  xmlNodePtr c_node;
  xmlAttrPtr c_property;

  Data_Get_Struct(rb_reader, xmlTextReader, c_reader);

  if (!has_attributes(c_reader)) {
    return rb_attributes;
  }

  c_node = xmlTextReaderExpand(c_reader);
  c_property = c_node->properties;
  while (c_property != NULL) {
    VALUE rb_name = NOKOGIRI_STR_NEW2(c_property->name);
    VALUE rb_value = Qnil;
    xmlChar *c_value = xmlNodeGetContent((xmlNode *)c_property);

    if (c_value) {
      rb_value = NOKOGIRI_STR_NEW2(c_value);
      xmlFree(c_value);
    }

    rb_hash_aset(rb_attributes, rb_name, rb_value);

    c_property = c_property->next;
  }

  return rb_attributes;
}

#attribute_nodes ⇒ Object

:call-seq: attribute_nodes() → Array<Nokogiri::XML::Attr>

Get the attributes of the current node as an Array of XML:Attr

⚠ This method is deprecated and unsafe to use. It will be removed in a future version of Nokogiri.

See related: #attribute_hash, #attributes



160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
 
# File 'ext/nokogiri/xml_reader.c', line 160

static VALUE
rb_xml_reader_attribute_nodes(VALUE rb_reader)
{
  xmlTextReaderPtr c_reader;
  xmlNodePtr c_node;
  VALUE attr_nodes;
  int j;

  // TODO: deprecated, remove in Nokogiri v1.15, see https://github.com/sparklemotion/nokogiri/issues/2598
  // After removal, we can also remove all the "node_has_a_document" special handling from xml_node.c
  NOKO_WARN_DEPRECATION("Reader#attribute_nodes is deprecated and will be removed in a future version of Nokogiri. Please use Reader#attribute_hash instead.");

  Data_Get_Struct(rb_reader, xmlTextReader, c_reader);

  if (! has_attributes(c_reader)) {
    return rb_ary_new() ;
  }

  c_node = xmlTextReaderExpand(c_reader);
  if (c_node == NULL) {
    return Qnil;
  }

  attr_nodes = noko_xml_node_attrs(c_node);

  /* ensure that the Reader won't be GCed as long as a node is referenced */
  for (j = 0 ; j < RARRAY_LEN(attr_nodes) ; j++) {
    rb_iv_set(rb_ary_entry(attr_nodes, j), "@reader", rb_reader);
  }

  return attr_nodes;
}

#attributes ⇒ Object

Get the attributes and namespaces of the current node as a Hash.

This is the union of Reader#attribute_hash and Reader#namespaces

Returns

(Hash<String, String>) Attribute names and values, and namespace prefixes and hrefs.



92
93
94
 
# File 'lib/nokogiri/xml/reader.rb', line 92

def attributes
  attribute_hash.merge(namespaces)
end

#attributes? ⇒ Boolean

Does this node have attributes?

Returns:

  • (Boolean) 


108
109
110
111
112
113
114
115
116
117
118
119
120
 
# File 'ext/nokogiri/xml_reader.c', line 108

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



466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
 
# File 'ext/nokogiri/xml_reader.c', line 466

static VALUE
rb_xml_reader_base_uri(VALUE rb_reader)
{
  VALUE rb_base_uri;
  xmlTextReaderPtr c_reader;
  xmlChar *c_base_uri;

  Data_Get_Struct(rb_reader, xmlTextReader, c_reader);

  c_base_uri = xmlTextReaderBaseUri(c_reader);
  if (c_base_uri == NULL) {
    return Qnil;
  }

  rb_base_uri = NOKOGIRI_STR_NEW2(c_base_uri);
  xmlFree(c_base_uri);

  return rb_base_uri;
}

#default? ⇒ Boolean

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

Returns:

  • (Boolean) 


68
69
70
71
72
73
74
75
76
77
78
79
80
 
# File 'ext/nokogiri/xml_reader.c', line 68

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



314
315
316
317
318
319
320
321
322
323
324
325
 
# File 'ext/nokogiri/xml_reader.c', line 314

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



98
99
100
101
102
 
# File 'lib/nokogiri/xml/reader.rb', line 98

def each
  while (cursor = 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) 


698
699
700
701
702
703
704
705
706
707
708
709
710
 
# File 'ext/nokogiri/xml_reader.c', line 698

static VALUE
empty_element_p(VALUE self)
{
  xmlTextReaderPtr reader;

  Data_Get_Struct(self, xmlTextReader, reader);

  if (xmlTextReaderIsEmptyElement(reader)) {
    return Qtrue;
  }

  return Qfalse;
}

#encoding ⇒ Object 



712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
 
# File 'ext/nokogiri/xml_reader.c', line 712

static VALUE
rb_xml_reader_encoding(VALUE rb_reader)
{
  xmlTextReaderPtr c_reader;
  const char *parser_encoding;
  VALUE constructor_encoding;

  constructor_encoding = rb_iv_get(rb_reader, "@encoding");
  if (RTEST(constructor_encoding)) {
    return constructor_encoding;
  }

  Data_Get_Struct(rb_reader, xmlTextReader, c_reader);
  parser_encoding = (const char *)xmlTextReaderConstEncoding(c_reader);
  if (parser_encoding == NULL) { return Qnil; }
  return NOKOGIRI_STR_NEW2(parser_encoding);
}

#inner_xml ⇒ Object

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



556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
 
# File 'ext/nokogiri/xml_reader.c', line 556

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.



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

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



428
429
430
431
432
433
434
435
436
437
438
439
 
# File 'ext/nokogiri/xml_reader.c', line 428

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.



447
448
449
450
451
452
453
454
455
456
457
458
 
# File 'ext/nokogiri/xml_reader.c', line 447

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



409
410
411
412
413
414
415
416
417
418
419
420
 
# File 'ext/nokogiri/xml_reader.c', line 409

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



128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
 
# File 'ext/nokogiri/xml_reader.c', line 128

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



506
507
508
509
510
511
512
 
# File 'ext/nokogiri/xml_reader.c', line 506

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.



583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
 
# File 'ext/nokogiri/xml_reader.c', line 583

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.



390
391
392
393
394
395
396
397
398
399
400
401
 
# File 'ext/nokogiri/xml_reader.c', line 390

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.



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
 
# File 'ext/nokogiri/xml_reader.c', line 520

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(error));
  } else {
    rb_raise(rb_eRuntimeError, "Error pulling: %d", ret);
  }

  return Qnil;
}

#state ⇒ Object

Get the state of the reader



492
493
494
495
496
497
498
 
# File 'ext/nokogiri/xml_reader.c', line 492

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.



371
372
373
374
375
376
377
378
379
380
381
382
 
# File 'ext/nokogiri/xml_reader.c', line 371

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) 


88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'ext/nokogiri/xml_reader.c', line 88

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



333
334
335
336
337
338
339
340
341
342
343
344
 
# File 'ext/nokogiri/xml_reader.c', line 333

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);
}