123456789_123456789_123456789_123456789_123456789_

Class: LibXML::XML::Parser

Relationships & Source Files
Namespace Children
Modules:
Options
Classes:
Context
Inherits: Object
Defined in: ext/libxml/ruby_xml_parser.c,
ext/libxml/ruby_xml_parser.c,
lib/libxml/parser.rb

Overview

The Parser provides a tree based API for processing xml documents, in contract to XML::Reader’s stream based api and SaxParser callback based API.

As a result, parsing a document creates an in-memory document object that consist of any number of Node instances. This is simple and powerful model, but has the major limitation that the size of the document that can be processed is limited by the amount of memory available. In such cases, it is better to use the Reader.

Using the parser is simple:

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

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

Class Method Summary

Instance Attribute Summary

Instance Method Summary

Constructor Details

.new(context) ⇒ Parser

Creates a new Parser from the specified Parser::Context.

[ GitHub ] 

  


# File 'ext/libxml/ruby_xml_parser.c', line 39



static VALUE rxml_parser_initialize(int argc, VALUE *argv, VALUE self)
{
  VALUE context = Qnil;

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

  if (context == Qnil)
  {
    rb_raise(rb_eArgError, "An instance of a XML::Parser::Context must be passed to XML::Parser.new");
  }

  rb_ivar_set(self, CONTEXT_ATTR, context);
  return self;
}


  







Class Method Details



  

    XML::Parser.document(document)  ⇒ Parser   



  

    

Creates a new parser for the specified document.



Parameters:



document - A preparsed document.


  



  [ GitHub ]


  

  


# File 'lib/libxml/parser.rb', line 14



def self.document(doc)
  context = XML::Parser::Context.document(doc)
  self.new(context)
end


  








  

    

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

  



  

    

Creates a new parser for the specified file or uri.



Parameters:



path - Path to file
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 (|).


  





  


  [ GitHub ]


  

  


# File 'lib/libxml/parser.rb', line 35



def self.file(path, base_uri: nil, encoding: nil, options: nil)
  context = XML::Parser::Context.file(path)
  context.base_uri = base_uri if base_uri
  context.encoding = encoding if encoding
  context.options = options if options
  self.new(context)
end


  








  

    

      XML::Parser.io(io)  ⇒ Parser 
      XML::Parser.io(io, encoding: XML::Encoding::UTF_8)  
      .options  
      .base_uri  ⇒ Parser 
    

  



  

    

Creates a new parser for 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 (|).


  





  


  [ GitHub ]


  

  


# File 'lib/libxml/parser.rb', line 60



def self.io(io, base_uri: nil, encoding: nil, options: nil)
  context = XML::Parser::Context.io(io)
  context.base_uri = base_uri if base_uri
  context.encoding = encoding if encoding
  context.options = options if options
  self.new(context)
end


  








  

    .register_error_handler(proc)  
  

  [ GitHub ]


  

  


# File 'lib/libxml/parser.rb', line 93



def self.register_error_handler(proc)
  warn('Parser.register_error_handler is deprecated.  Use Error.set_handler instead')
  if proc.nil?
    Error.reset_handler
  else
    Error.set_handler(&proc)
  end
end


  








  

    

      XML::Parser.string(string)  
      XML::Parser.string(string, encoding: XML::Encoding::UTF_8)  
      .options  
      .base_uri  ⇒ Parser 
    

  



  

    

Creates a new parser by parsing the specified string.



Parameters:



string - The string to parse
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.  Multiple options can be combined
          by using Bitwise OR (|).


  





  


  [ GitHub ]


  

  


# File 'lib/libxml/parser.rb', line 85



def self.string(string, base_uri: nil, encoding: nil, options: nil)
  context = XML::Parser::Context.string(string)
  context.base_uri = base_uri if base_uri
  context.encoding = encoding if encoding
  context.options = options if options
  self.new(context)
end


  







Instance Attribute Details



  

    #context   (readonly)
  

  [ GitHub ]






  

    #input   (readonly)
  

  [ GitHub ]





Instance Method Details



  

    #parse  ⇒ XML::Document   



  

    

Parse the input ::LibXML::XML and create an Document with it’s content. If an error occurs, XML::Parser::ParseError is thrown.


  



  [ GitHub ]


  

  


# File 'ext/libxml/ruby_xml_parser.c', line 62



static VALUE rxml_parser_parse(VALUE self)
{
  xmlParserCtxtPtr ctxt;
  VALUE context = rb_ivar_get(self, CONTEXT_ATTR);
  
  Data_Get_Struct(context, xmlParserCtxt, ctxt);

  if ((xmlParseDocument(ctxt) == -1 || !ctxt->wellFormed) && ! ctxt->recovery)
  {
    rxml_raise(&ctxt->lastError);
  }

  rb_funcall(context, rb_intern("close"), 0);

  return rxml_document_wrap(ctxt->myDoc);
}