Class: LibXML::XML::Reader

Inherits:
Object
  • Object
show all
Defined in:
ext/libxml/ruby_xml_reader.c,
ext/libxml/ruby_xml_reader.c

Overview

The XML::Reader class provides a simpler, alternative way of parsing an XML document in contrast to XML::Parser or XML::SaxParser. A XML::Reader instance acts like a cursor going forward in a document stream, stopping at each node it encounters. To advance to the next node, simply cadd XML::Reader#read.

The XML::Reader API closely matches the DOM Core specification and supports namespaces, xml:base, entity handling and DTDs.

To summarize, XML::Reader provides a far simpler API to use versus XML::SaxParser and is more memory efficient than using XML::Parser to create a DOM tree.

Example:

reader = XML::Reader.string("<foo><bar>1</bar><bar>2</bar><bar>3</bar></foo>")
reader.read
assert_equal('foo', reader.name)
assert_nil(reader.value)

3.times do |i|
  reader.read
  assert_equal(XML::Reader::TYPE_ELEMENT, reader.node_type)
  assert_equal('bar', reader.name)
  reader.read
  assert_equal(XML::Reader::TYPE_TEXT, reader.node_type)
  assert_equal((i + 1).to_s, reader.value)
  reader.read
  assert_equal(XML::Reader::TYPE_END_ELEMENT, reader.node_type)
end

You can also parse documents (see XML::Reader.document), strings (see XML::Parser.string) and io objects (see XML::Parser.io).

For a more in depth tutorial, albeit in C, see xmlsoft.org/xmlreader.html.

Constant Summary collapse

LOADDTD =

Constants

INT2FIX(XML_PARSER_LOADDTD)
DEFAULTATTRS = 
INT2FIX(XML_PARSER_DEFAULTATTRS)
VALIDATE = 
INT2FIX(XML_PARSER_VALIDATE)
SUBST_ENTITIES = 
INT2FIX(XML_PARSER_SUBST_ENTITIES)
SEVERITY_VALIDITY_WARNING = 
INT2FIX(XML_PARSER_SEVERITY_VALIDITY_WARNING)
SEVERITY_VALIDITY_ERROR = 
INT2FIX(XML_PARSER_SEVERITY_VALIDITY_ERROR)
SEVERITY_WARNING = 
INT2FIX(XML_PARSER_SEVERITY_WARNING)
SEVERITY_ERROR = 
INT2FIX(XML_PARSER_SEVERITY_ERROR)
TYPE_NONE = 
INT2FIX(XML_READER_TYPE_NONE)
TYPE_ELEMENT = 
INT2FIX(XML_READER_TYPE_ELEMENT)
TYPE_ATTRIBUTE = 
INT2FIX(XML_READER_TYPE_ATTRIBUTE)
TYPE_TEXT = 
INT2FIX(XML_READER_TYPE_TEXT)
TYPE_CDATA = 
INT2FIX(XML_READER_TYPE_CDATA)
TYPE_ENTITY_REFERENCE = 
INT2FIX(XML_READER_TYPE_ENTITY_REFERENCE)
TYPE_ENTITY = 
INT2FIX(XML_READER_TYPE_ENTITY)
TYPE_PROCESSING_INSTRUCTION = 
INT2FIX(XML_READER_TYPE_PROCESSING_INSTRUCTION)
TYPE_COMMENT = 
INT2FIX(XML_READER_TYPE_COMMENT)
TYPE_DOCUMENT = 
INT2FIX(XML_READER_TYPE_DOCUMENT)
TYPE_DOCUMENT_TYPE = 
INT2FIX(XML_READER_TYPE_DOCUMENT_TYPE)
TYPE_DOCUMENT_FRAGMENT = 
INT2FIX(XML_READER_TYPE_DOCUMENT_FRAGMENT)
TYPE_NOTATION = 
INT2FIX(XML_READER_TYPE_NOTATION)
TYPE_WHITESPACE = 
INT2FIX(XML_READER_TYPE_WHITESPACE)
TYPE_SIGNIFICANT_WHITESPACE = 
INT2FIX(XML_READER_TYPE_SIGNIFICANT_WHITESPACE)
TYPE_END_ELEMENT = 
INT2FIX(XML_READER_TYPE_END_ELEMENT)
TYPE_END_ENTITY = 
INT2FIX(XML_READER_TYPE_END_ENTITY)
TYPE_XML_DECLARATION = 
INT2FIX(XML_READER_TYPE_XML_DECLARATION)
MODE_INITIAL =

Read states

INT2FIX(XML_TEXTREADER_MODE_INITIAL)
MODE_INTERACTIVE = 
INT2FIX(XML_TEXTREADER_MODE_INTERACTIVE)
MODE_ERROR = 
INT2FIX(XML_TEXTREADER_MODE_ERROR)
MODE_EOF = 
INT2FIX(XML_TEXTREADER_MODE_EOF)
MODE_CLOSED = 
INT2FIX(XML_TEXTREADER_MODE_CLOSED)
MODE_READING = 
INT2FIX(XML_TEXTREADER_MODE_READING)

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.XML::Reader.document(doc) ⇒ XML::Reader

Create an new reader for the specified document.

Returns:



88
89
90
91
92
93
94
95
96
97
98
99
100
101
 
# File 'ext/libxml/ruby_xml_reader.c', line 88

VALUE rxml_reader_document(VALUE klass, VALUE doc)
{
  xmlDocPtr xdoc;
  xmlTextReaderPtr xreader;

  Data_Get_Struct(doc, xmlDoc, xdoc);

  xreader = xmlReaderWalker(xdoc);

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

  return rxml_reader_wrap(xreader);
}

.XML::Reader.file(path) ⇒ XML::Reader .XML::Reader.file(path, : encoding) ⇒ XML::Encoding::UTF_8

Creates a new reader by parsing 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 - Controls the execution of the parser, defaults to 0.
          Valid values are the constants defined on
          XML::Parser::Options.  Mutliple options can be combined
          by using Bitwise OR (|).

Overloads:



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/libxml/ruby_xml_reader.c', line 120

static VALUE rxml_reader_file(int argc, VALUE *argv, VALUE klass)
{
  xmlTextReaderPtr xreader;
  VALUE path;
  VALUE options;

  const char *xencoding = NULL;
  int xoptions = 0;

  rb_scan_args(argc, argv, "11", &path, &options);
  Check_Type(path, T_STRING);

  if (!NIL_P(options))
  {
    VALUE encoding = Qnil;
    VALUE parserOptions = Qnil;

    Check_Type(options, T_HASH);

    encoding = rb_hash_aref(options, BASE_URI_SYMBOL);
    xencoding = NIL_P(encoding) ? NULL : xmlGetCharEncodingName(NUM2INT(encoding));

    parserOptions = rb_hash_aref(options, OPTIONS_SYMBOL);
    xoptions = NIL_P(parserOptions) ? 0 : NUM2INT(parserOptions);
  }

  xreader = xmlReaderForFile(StringValueCStr(path), xencoding, xoptions);

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

  return rxml_reader_wrap(xreader);
}

.XML::Reader.io(io) ⇒ XML::Reader .XML::Reader.io(io, : encoding) ⇒ XML::Encoding::UTF_8

Creates a new reader by parsing the specified io object.

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 - Controls the execution of the parser, defaults to 0.
          Valid values are the constants defined on
          XML::Parser::Options.  Mutliple options can be combined
          by using Bitwise OR (|).

Overloads:



172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
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
 
# File 'ext/libxml/ruby_xml_reader.c', line 172

static VALUE rxml_reader_io(int argc, VALUE *argv, VALUE klass)
{
  xmlTextReaderPtr xreader;
  VALUE result;
  VALUE io;
  VALUE options;
  char *xbaseurl = NULL;
  const char *xencoding = NULL;
  int xoptions = 0;

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

  if (!NIL_P(options))
  {
    VALUE baseurl = Qnil;
    VALUE encoding = Qnil;
    VALUE parserOptions = Qnil;

    Check_Type(options, T_HASH);

    baseurl = rb_hash_aref(options, BASE_URI_SYMBOL);
    xbaseurl = NIL_P(baseurl) ? NULL : StringValueCStr(baseurl);

    encoding = rb_hash_aref(options, ENCODING_SYMBOL);
    xencoding = NIL_P(encoding) ? NULL : xmlGetCharEncodingName(NUM2INT(encoding));

    parserOptions = rb_hash_aref(options, OPTIONS_SYMBOL);
    xoptions = NIL_P(parserOptions) ? 0 : NUM2INT(parserOptions);
  }
  
  xreader = xmlReaderForIO((xmlInputReadCallback) rxml_read_callback, NULL,
                           (void *) io, 
                           xbaseurl, xencoding, xoptions);

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

  result = rxml_reader_wrap(xreader);

  /* Attach io object to parser so it won't get freed.*/
  rb_ivar_set(result, IO_ATTR, io);

  return result;
}

.XML::Reader.string(io) ⇒ XML::Reader .XML::Reader.string(io, : encoding) ⇒ XML::Encoding::UTF_8

Creates a new reader by parsing 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 - Controls the execution of the parser, defaults to 0.
          Valid values are the constants defined on
          XML::Parser::Options.  Mutliple options can be combined
          by using Bitwise OR (|).

Overloads:



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
 
# File 'ext/libxml/ruby_xml_reader.c', line 235

static VALUE rxml_reader_string(int argc, VALUE *argv, VALUE klass)
{
  xmlTextReaderPtr xreader;
  VALUE string;
  VALUE options;
  char *xbaseurl = NULL;
  const char *xencoding = NULL;
  int xoptions = 0;

  rb_scan_args(argc, argv, "11", &string, &options);
  Check_Type(string, T_STRING);

  if (!NIL_P(options))
  {
    VALUE baseurl = Qnil;
    VALUE encoding = Qnil;
    VALUE parserOptions = Qnil;

    Check_Type(options, T_HASH);

    baseurl = rb_hash_aref(options, BASE_URI_SYMBOL);
    xbaseurl = NIL_P(baseurl) ? NULL : StringValueCStr(baseurl);

    encoding = rb_hash_aref(options, ENCODING_SYMBOL);
    xencoding = NIL_P(encoding) ? NULL : xmlGetCharEncodingName(NUM2INT(encoding));
      
    parserOptions = rb_hash_aref(options, OPTIONS_SYMBOL);
    xoptions = NIL_P(parserOptions) ? 0 : NUM2INT(parserOptions);
  }
  
  xreader = xmlReaderForMemory(StringValueCStr(string), (int)RSTRING_LEN(string),
                               xbaseurl, xencoding, xoptions);

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

  return rxml_reader_wrap(xreader);
}

Instance Method Details

#[](key) ⇒ Object

Provide the value of the attribute with the specified index (if key is an integer) or with the specified name (if key is a string) relative to the containing element, as a string.



869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
 
# File 'ext/libxml/ruby_xml_reader.c', line 869

static VALUE rxml_reader_attribute(VALUE self, VALUE key)
{
  VALUE result = Qnil;
  xmlChar *xattr;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  if (TYPE(key) == T_FIXNUM)
  {
    xattr = xmlTextReaderGetAttributeNo(xReader, FIX2INT(key));
  }
  else
  {
    xattr = xmlTextReaderGetAttribute(xReader, (const xmlChar *) StringValueCStr(key));
  }

  if (xattr)
  {
    result = rxml_new_cstr(xattr, xencoding);
    xmlFree(xattr);
  }
  return result;
}

#attribute_count ⇒ Object

Provide the number of attributes of the current node.



674
675
676
677
678
 
# File 'ext/libxml/ruby_xml_reader.c', line 674

static VALUE rxml_reader_attr_count(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderAttributeCount(xreader));
}

#base_uri ⇒ Object

Determine the base URI of the node.



712
713
714
715
716
717
718
719
 
# File 'ext/libxml/ruby_xml_reader.c', line 712

static VALUE rxml_reader_base_uri(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstBaseUri(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}

#byte_consumed ⇒ Object

This method provides the current index of the parser used by the reader, relative to the start of the current entity.



1044
1045
1046
1047
1048
1049
 
# File 'ext/libxml/ruby_xml_reader.c', line 1044

static VALUE
rxml_reader_byte_consumed(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2NUM(xmlTextReaderByteConsumed(xreader));
}

#close ⇒ Object

This method releases any resources allocated by the current instance changes the state to Closed and close any underlying input.



281
282
283
284
285
 
# File 'ext/libxml/ruby_xml_reader.c', line 281

static VALUE rxml_reader_close(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderClose(xreader));
}

#column_number ⇒ Numeric

Provide the column number of the current parsing point.

Returns:

  • (Numeric) 


1059
1060
1061
1062
1063
1064
 
# File 'ext/libxml/ruby_xml_reader.c', line 1059

static VALUE
rxml_reader_column_number(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2NUM(xmlTextReaderGetParserColumnNumber(xreader));
}

#default? ⇒ Boolean

Return whether an Attribute node was generated from the default value defined in the DTD or schema.

Returns:

  • (Boolean) 


1087
1088
1089
1090
1091
 
# File 'ext/libxml/ruby_xml_reader.c', line 1087

static VALUE rxml_reader_default(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return xmlTextReaderIsDefault(xreader) ? Qtrue : Qfalse;
}

#depth ⇒ Object

Get the depth of the node in the tree.



772
773
774
775
776
 
# File 'ext/libxml/ruby_xml_reader.c', line 772

static VALUE rxml_reader_depth(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderDepth(xreader));
}

#document ⇒ Object

Hacking interface that provides access to the current document being accessed by the reader. NOTE: as a result of this call, the reader will not destroy the associated XML document. Instead, it will be destroyed when the returned document goes out of scope.

Returns: document



1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
 
# File 'ext/libxml/ruby_xml_reader.c', line 1017

static VALUE rxml_reader_doc(VALUE self)
{
  VALUE result = Qnil;
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  xmlDocPtr xdoc = xmlTextReaderCurrentDoc(xreader);

  if (!xdoc)
    rb_raise(rb_eRuntimeError, "The reader does not have a document.  Did you forget to call read?");

  result = rxml_document_wrap(xdoc);

  // And now hook in a mark function to keep the document alive as long as the reader is valid
  RDATA(self)->dmark = (RUBY_DATA_FUNC)rxml_reader_mark;

  return result;
}

#empty_element? ⇒ Boolean

Check if the current node is empty.

Returns:

  • (Boolean) 


1112
1113
1114
1115
1116
 
# File 'ext/libxml/ruby_xml_reader.c', line 1112

static VALUE rxml_reader_empty_element(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return xmlTextReaderIsEmptyElement(xreader) ? Qtrue : Qfalse;
}

#encoding ⇒ XML::Encoding::UTF_8

Returns the encoding of the document being read. Note you first have to read data from the reader for encoding to return a value

reader = XML::Reader.file(XML_FILE)
assert_nil(reader.encoding)
reader.read
assert_equal(XML::Encoding::UTF_8, reader.encoding)

In addition, libxml always appears to return nil for the encoding when parsing strings.

Returns:



696
697
698
699
700
701
702
703
704
 
# File 'ext/libxml/ruby_xml_reader.c', line 696

static VALUE rxml_reader_encoding(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xreader);
  if (xencoding)
    return INT2NUM(xmlParseCharEncoding((const char*)xencoding));
  else
    return INT2NUM(XML_CHAR_ENCODING_NONE);
}

#expand ⇒ Object

Returns the current node and its full subtree. Note the returned node is valid ONLY until the next read call. If you would like to preserve the node, or search it via xpath, call reader.doc first.



987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
 
# File 'ext/libxml/ruby_xml_reader.c', line 987

static VALUE rxml_reader_expand(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  xmlNodePtr xnode = xmlTextReaderExpand(xreader);

  if (!xnode)
  {
    return Qnil;
  }
  else
  {
	  /* We cannot call rxml_node_wrap here because its sets up a mark function
	   for the node. But according to the libxml docs (http://xmlsoft.org/html/libxml-xmlreader.html#xmlTextReaderExpand)
	   this is only valid until the next xmlTextReaderRead call.  At that point the node is freed (from reading
	   the libxml2 source code.  So don't set a mark or free function, because they will get called in the next
	   garbage collection run and cause a segfault.*/
	return Data_Wrap_Struct(cXMLNode, NULL, NULL, xnode);
  }
}

#get_attribute(localName) ⇒ Object

Provide the value of the attribute with the specified name relative to the containing element.



900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
 
# File 'ext/libxml/ruby_xml_reader.c', line 900

static VALUE rxml_reader_get_attribute(VALUE self, VALUE name)
{
  VALUE result = Qnil;
  xmlChar *xattr;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  xattr = xmlTextReaderGetAttribute(xReader, (const xmlChar *) StringValueCStr(name));
  if (xattr)
  {
    result = rxml_new_cstr(xattr, xencoding);
    xmlFree(xattr);
  }
  return result;
}

#get_attribute_no(index) ⇒ Object

Provide the value of the attribute with the specified index relative to the containing element.



923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
 
# File 'ext/libxml/ruby_xml_reader.c', line 923

static VALUE rxml_reader_get_attribute_no(VALUE self, VALUE index)
{
  VALUE result = Qnil;
  xmlChar *xattr;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  xattr = xmlTextReaderGetAttributeNo(xReader, FIX2INT(index));
  if (xattr)
  {
    result = rxml_new_cstr(xattr, xencoding);
    xmlFree(xattr);
  }
  return result;
}

#get_attribute_ns(name, ns) ⇒ Object 



939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
 
# File 'ext/libxml/ruby_xml_reader.c', line 939

static VALUE rxml_reader_get_attribute_ns(VALUE self, VALUE name, VALUE ns)
{
  VALUE result = Qnil;
  xmlChar *xattr;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  xattr = xmlTextReaderGetAttributeNs(xReader,
    (const xmlChar *) StringValueCStr(name),
    (const xmlChar *) StringValueCStr(ns));
  if (xattr)
  {
    result = rxml_new_cstr(xattr, xencoding);
    xmlFree(xattr);
  }
  return result;
}

#has_attributes? ⇒ Boolean

Get whether the node has attributes.

Returns:

  • (Boolean) 


843
844
845
846
847
 
# File 'ext/libxml/ruby_xml_reader.c', line 843

static VALUE rxml_reader_has_attributes(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return xmlTextReaderHasAttributes(xreader) ? Qtrue : Qfalse;
}

#has_value? ⇒ Boolean

Get whether the node can have a text value.

Returns:

  • (Boolean) 


855
856
857
858
859
 
# File 'ext/libxml/ruby_xml_reader.c', line 855

static VALUE rxml_reader_has_value(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return xmlTextReaderHasValue(xreader) ? Qtrue : Qfalse;
}

#line_number ⇒ Numeric

Provide the line number of the current parsing point.

Returns:

  • (Numeric) 


1072
1073
1074
1075
1076
1077
 
# File 'ext/libxml/ruby_xml_reader.c', line 1072

static VALUE
rxml_reader_line_number(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2NUM(xmlTextReaderGetParserLineNumber(xreader));
}

#local_name ⇒ Object

Return the local name of the node.



659
660
661
662
663
664
665
666
 
# File 'ext/libxml/ruby_xml_reader.c', line 659

static VALUE rxml_reader_local_name(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstLocalName(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}

#lookup_namespace(prefix) ⇒ Object

Resolve a namespace prefix in the scope of the current element. To return the default namespace, specify nil as prefix.



964
965
966
967
968
969
970
971
972
973
974
975
976
977
 
# File 'ext/libxml/ruby_xml_reader.c', line 964

static VALUE rxml_reader_lookup_namespace(VALUE self, VALUE prefix)
{
  VALUE result = Qnil;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *xnamespace = xmlTextReaderLookupNamespace(xReader, (const xmlChar *) StringValueCStr(prefix));
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  if (xnamespace)
  {
    result = rxml_new_cstr(xnamespace, xencoding);
    xmlFree((void *)xnamespace);
  }
  return result;
}

#move_to_attribute(localName) ⇒ Object

Move the position of the current instance to the attribute with the specified name relative to the containing element.



312
313
314
315
316
317
318
319
320
321
322
 
# File 'ext/libxml/ruby_xml_reader.c', line 312

static VALUE rxml_reader_move_to_attr(VALUE self, VALUE val)
{
  int ret;
  xmlTextReaderPtr xreader;

  xreader = rxml_text_reader_get(self);
  ret = xmlTextReaderMoveToAttribute(xreader,
      (const xmlChar *) StringValueCStr(val));

  return INT2FIX(ret);
}

#move_to_attribute_no(index) ⇒ Object

Move the position of the current instance to the attribute with the specified index relative to the containing element.



294
295
296
297
298
299
300
301
302
303
 
# File 'ext/libxml/ruby_xml_reader.c', line 294

static VALUE rxml_reader_move_to_attr_no(VALUE self, VALUE index)
{
  int ret;
  xmlTextReaderPtr xreader;

  xreader = rxml_text_reader_get(self);
  ret = xmlTextReaderMoveToAttributeNo(xreader, FIX2INT(index));

  return INT2FIX(ret);
}

#move_to_attribute_ns(localName, namespaceURI) ⇒ Object

Move the position of the current instance to the attribute with the specified name and namespace relative to the containing element.



331
332
333
334
335
336
337
338
339
340
341
342
 
# File 'ext/libxml/ruby_xml_reader.c', line 331

static VALUE rxml_reader_move_to_attr_ns(VALUE self, VALUE name, VALUE ns)
{
  int ret;
  xmlTextReaderPtr xreader;

  xreader = rxml_text_reader_get(self);
  ret = xmlTextReaderMoveToAttributeNs(xreader,
      (const xmlChar *) StringValueCStr(name),
      (const xmlChar *) StringValueCStr(ns));

  return INT2FIX(ret);
}

#move_to_element ⇒ Object

Move the position of the current instance to the node that contains the current attribute node.



377
378
379
380
381
 
# File 'ext/libxml/ruby_xml_reader.c', line 377

static VALUE rxml_reader_move_to_element(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderMoveToElement(xreader));
}

#move_to_first_attribute ⇒ Object

Move the position of the current instance to the first attribute associated with the current node.



351
352
353
354
355
 
# File 'ext/libxml/ruby_xml_reader.c', line 351

static VALUE rxml_reader_move_to_first_attr(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderMoveToFirstAttribute(xreader));
}

#move_to_next_attribute ⇒ Object

Move the position of the current instance to the next attribute associated with the current node.



364
365
366
367
368
 
# File 'ext/libxml/ruby_xml_reader.c', line 364

static VALUE rxml_reader_move_to_next_attr(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderMoveToNextAttribute(xreader));
}

#name ⇒ Object

Return the qualified name of the node.



644
645
646
647
648
649
650
651
 
# File 'ext/libxml/ruby_xml_reader.c', line 644

static VALUE rxml_reader_name(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstName(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}

#namespace_declaration? ⇒ Boolean

Determine whether the current node is a namespace declaration rather than a regular attribute.

Returns:

  • (Boolean) 


1100
1101
1102
1103
1104
 
# File 'ext/libxml/ruby_xml_reader.c', line 1100

static VALUE rxml_reader_namespace_declaration(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return xmlTextReaderIsNamespaceDecl(xreader) ? Qtrue : Qfalse;
}

#namespace_uri ⇒ Object

Determine the namespace URI of the node.



727
728
729
730
731
732
733
734
 
# File 'ext/libxml/ruby_xml_reader.c', line 727

static VALUE rxml_reader_namespace_uri(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstNamespaceUri(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}

#next ⇒ Object

Skip to the node following the current one in document order while avoiding the subtree if any.



390
391
392
393
394
 
# File 'ext/libxml/ruby_xml_reader.c', line 390

static VALUE rxml_reader_next(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderNext(xreader));
}

#next_sibling ⇒ Object

Skip to the node following the current one in document order while avoiding the subtree if any. Currently implemented only for Readers built on a document.



404
405
406
407
408
 
# File 'ext/libxml/ruby_xml_reader.c', line 404

static VALUE rxml_reader_next_sibling(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderNextSibling(xreader));
}

#node ⇒ XML::Node

Returns the reader’s current node. It will return nil if Reader#read has not yet been called. WARNING - Using this method is dangerous because the the node may be destroyed on the next #read.

Returns:



419
420
421
422
423
424
 
# File 'ext/libxml/ruby_xml_reader.c', line 419

static VALUE rxml_reader_node(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  xmlNodePtr xnode = xmlTextReaderCurrentNode(xreader);
  return xnode ? rxml_node_wrap(xnode) : Qnil;
}

#node_type ⇒ Object

Get the node type of the current node. Reference: dotgnu.org/pnetlib-doc/System/Xml/XmlNodeType.html



433
434
435
436
437
 
# File 'ext/libxml/ruby_xml_reader.c', line 433

static VALUE rxml_reader_node_type(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderNodeType(xreader));
}

#normalization ⇒ Object

The value indicating whether to normalize white space and attribute values. Since attribute value and end of line normalizations are a MUST in the XML specification only the value true is accepted. The broken bahaviour of accepting out of range character entities like &#0; is of course not supported either.

Return 1 or -1 in case of error.



451
452
453
454
455
 
# File 'ext/libxml/ruby_xml_reader.c', line 451

static VALUE rxml_reader_normalization(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderNormalization(xreader));
}

#prefix ⇒ Object

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



757
758
759
760
761
762
763
764
 
# File 'ext/libxml/ruby_xml_reader.c', line 757

static VALUE rxml_reader_prefix(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstPrefix(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}

#quote_char ⇒ String

Get the quotation mark character used to enclose the value of an attribute, as an integer value (and -1 in case of error).

Returns:

  • (String) 


785
786
787
788
789
 
# File 'ext/libxml/ruby_xml_reader.c', line 785

static VALUE rxml_reader_quote_char(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderQuoteChar(xreader));
}

#read ⇒ Object

Causes the reader to move to the next node in the stream, exposing its properties.

Returns true if a node was successfully read or false if there are no more nodes to read. On errors, an exception is raised.



465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
 
# File 'ext/libxml/ruby_xml_reader.c', line 465

static VALUE rxml_reader_read(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  int result = xmlTextReaderRead(xreader);
  switch(result)
  {
    case -1:
      rxml_raise(&xmlLastError);
      return Qnil;
      break;
    case 0:
      return Qfalse;
    case 1:
      return Qtrue;
    default:
      rb_raise(rb_eRuntimeError,
               "xmlTextReaderRead did not return -1, 0 or 1.  Return value was: %d", result);
  }
}

#read_attribute_value ⇒ Object

Parse an attribute value into one or more Text and EntityReference nodes.

Return 1 in case of success, 0 if the reader was not positionned on an attribute node or all the attribute values have been read, or -1 in case of error.



495
496
497
498
499
 
# File 'ext/libxml/ruby_xml_reader.c', line 495

static VALUE rxml_reader_read_attr_value(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderReadAttributeValue(xreader));
}

#read_inner_xml ⇒ Object

Read the contents of the current node, including child nodes and markup.

Return a string containing the XML content, or nil if the current node is neither an element nor attribute, or has no child nodes.



510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
 
# File 'ext/libxml/ruby_xml_reader.c', line 510

static VALUE rxml_reader_read_inner_xml(VALUE self)
{
  VALUE result = Qnil;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);

  xmlChar *xml = xmlTextReaderReadInnerXml(xReader);

  if (xml)
  {
    const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);
    result = rxml_new_cstr( xml, xencoding);
    xmlFree(xml);
  }

  return result;
}

#read_outer_xml ⇒ Object

Read the contents of the current node, including child nodes and markup.

Return a string containing the XML content, or nil if the current node is neither an element nor attribute, or has no child nodes.



536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
 
# File 'ext/libxml/ruby_xml_reader.c', line 536

static VALUE rxml_reader_read_outer_xml(VALUE self)
{
  VALUE result = Qnil;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);

  xmlChar *xml = xmlTextReaderReadOuterXml(xReader);

  if (xml)
  {
    const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);
    result = rxml_new_cstr( xml, xencoding);
    xmlFree(xml);
  }

  return result;
}

#read_state ⇒ Object

Get the read state of the reader.



559
560
561
562
563
 
# File 'ext/libxml/ruby_xml_reader.c', line 559

static VALUE rxml_reader_read_state(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderReadState(xreader));
}

#read_string ⇒ String

Read the contents of an element or a text node as a string.

Return a string containing the contents of the Element or Text node, or nil if the reader is positioned on any other type of node.

Returns:

  • (String) 


574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
 
# File 'ext/libxml/ruby_xml_reader.c', line 574

static VALUE rxml_reader_read_string(VALUE self)
{
  VALUE result = Qnil;
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);

  xmlChar *xml = xmlTextReaderReadString(xReader);

  if (xml)
  {
    const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);
    result = rxml_new_cstr( xml, xencoding);
    xmlFree(xml);
  }

  return result;
}

#relax_ng_validate(rng) ⇒ Boolean

Use RelaxNG to validate the document as it is processed. Activation is only possible before the first read. If rng is nil, the RelaxNG validation is desactivated.

Return true in case the RelaxNG validation could be (des)activated and false in case of error.

Returns:

  • (Boolean) 


602
603
604
605
606
607
608
609
610
611
 
# File 'ext/libxml/ruby_xml_reader.c', line 602

static VALUE rxml_reader_relax_ng_validate(VALUE self, VALUE rng)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  xmlRelaxNGPtr xrelax;
  int status;
  Data_Get_Struct(rng, xmlRelaxNG, xrelax);
  
  status = xmlTextReaderRelaxNGSetSchema(xreader, xrelax);
  return (status == 0 ? Qtrue : Qfalse);
}

#schema_validate(schema) ⇒ Boolean

Use W3C XSD schema to validate the document as it is processed. Activation is only possible before the first read. If schema is nil, then XML Schema validation is deactivated.

Return false if if the schema’s validation could be (de)activated and true otherwise.

Returns:

  • (Boolean) 


625
626
627
628
629
630
631
632
633
634
635
 
# File 'ext/libxml/ruby_xml_reader.c', line 625

static VALUE
rxml_reader_schema_validate(VALUE self, VALUE xsd)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  xmlSchemaPtr xschema;
  int status;

  Data_Get_Struct(xsd, xmlSchema, xschema);
  status = xmlTextReaderSetSchema(xreader, xschema);
  return (status == 0 ? Qtrue : Qfalse);
}

#standalone ⇒ Object

Determine the standalone status of the document being read.

Return 1 if the document was declared to be standalone, 0 if it was declared to be not standalone, or -1 if the document did not specify its standalone status or in case of error.



801
802
803
804
805
 
# File 'ext/libxml/ruby_xml_reader.c', line 801

static VALUE rxml_reader_standalone(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return INT2FIX(xmlTextReaderStandalone(xreader));
}

#valid? ⇒ Boolean

Retrieve the validity status from the parser context.

Returns:

  • (Boolean) 


1124
1125
1126
1127
1128
 
# File 'ext/libxml/ruby_xml_reader.c', line 1124

static VALUE rxml_reader_valid(VALUE self)
{
  xmlTextReaderPtr xreader = rxml_text_reader_get(self);
  return xmlTextReaderIsValid(xreader) ? Qtrue : Qfalse;
}

#value ⇒ Object

Provide the text value of the node if present.



742
743
744
745
746
747
748
749
 
# File 'ext/libxml/ruby_xml_reader.c', line 742

static VALUE rxml_reader_value(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstValue(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}

#xml_lang ⇒ Object

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



813
814
815
816
817
818
819
820
 
# File 'ext/libxml/ruby_xml_reader.c', line 813

static VALUE rxml_reader_xml_lang(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstXmlLang(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}

#xml_version ⇒ Object

Determine the XML version of the document being read.



828
829
830
831
832
833
834
835
 
# File 'ext/libxml/ruby_xml_reader.c', line 828

static VALUE rxml_reader_xml_version(VALUE self)
{
  xmlTextReaderPtr xReader = rxml_text_reader_get(self);
  const xmlChar *result = xmlTextReaderConstXmlVersion(xReader);
  const xmlChar *xencoding = xmlTextReaderConstEncoding(xReader);

  return (result == NULL ? Qnil : rxml_new_cstr(result, xencoding));
}