123456789_123456789_123456789_123456789_123456789_

Class: Nokogiri::XML::SAX::PushParser

Relationships & Source Files
Extension / Inclusion / Inheritance Descendants
Subclasses:
HTML4::SAX::PushParser
Inherits: Object
Defined in: lib/nokogiri/xml/sax/push_parser.rb,
ext/nokogiri/xml_sax_push_parser.c

Overview

PushParser can parse a document that is fed to it manually. It must be given a Document object which will be called with ::Nokogiri::XML::SAX events as the document is being parsed.

Calling #<< writes ::Nokogiri::XML to the parser, calling any ::Nokogiri::XML::SAX callbacks it can.

#finish tells the parser that the document is finished and calls the end_document ::Nokogiri::XML::SAX method.

Example:

parser = PushParser.new(Class.new(XML::SAX::Document) {
  def start_document
    puts "start document called"
  end
}.new)
parser << "<div>hello<"
parser << "/div>"
parser.finish

Class Method Summary

Instance Attribute Summary

Instance Method Summary

Constructor Details

.new(doc = XML::SAX::Document.new, file_name = nil, encoding = "UTF-8") ⇒ PushParser

Create a new PushParser with doc as the ::Nokogiri::XML::SAX Document, providing an optional file_name and encoding

[ GitHub ] 

  


# File 'lib/nokogiri/xml/sax/push_parser.rb', line 35



def initialize(doc = XML::SAX::Document.new, file_name = nil, encoding = "UTF-8")
  @document = doc
  @encoding = encoding
  @sax_parser = XML::SAX::Parser.new(doc)

  ## Create our push parser context
  initialize_native(@sax_parser, file_name)
end


  







Instance Attribute Details



  

    #document   (rw)
  



  

    

The Document on which the PushParser will be operating


  



  [ GitHub ]


  

  


# File 'lib/nokogiri/xml/sax/push_parser.rb', line 30



attr_accessor :document


  








  

    #options   (rw)
  

  [ GitHub ]


  

  


# File 'ext/nokogiri/xml_sax_push_parser.c', line 105



static VALUE
get_options(VALUE self)
{
  xmlParserCtxtPtr ctx;

  ctx = noko_xml_sax_push_parser_unwrap(self);

  return INT2NUM(ctx->options);
}


  








  

    #options=(options)   (rw)
  

  [ GitHub ]


  

  


# File 'ext/nokogiri/xml_sax_push_parser.c', line 115



static VALUE
set_options(VALUE self, VALUE options)
{
  xmlParserCtxtPtr ctx;

  ctx = noko_xml_sax_push_parser_unwrap(self);

  if (xmlCtxtUseOptions(ctx, (int)NUM2INT(options)) != 0) {
    rb_raise(rb_eRuntimeError, "Cannot set XML parser context options");
  }

  return Qnil;
}


  








  

    #replace_entities   (rw)  



  

    

Should this parser replace entities?  &amp; will get converted to ‘&’ if set to true


  



  [ GitHub ]


  

  


# File 'ext/nokogiri/xml_sax_push_parser.c', line 136



static VALUE
get_replace_entities(VALUE self)
{
  xmlParserCtxtPtr ctx;

  ctx = noko_xml_sax_push_parser_unwrap(self);

  if (0 == ctx->replaceEntities) {
    return Qfalse;
  } else {
    return Qtrue;
  }
}


  








  

    #replace_entities=(boolean)   (rw)  



  

    

Should this parser replace entities?  &amp; will get converted to ‘&’ if set to true


  



  [ GitHub ]


  

  


# File 'ext/nokogiri/xml_sax_push_parser.c', line 157



static VALUE
set_replace_entities(VALUE self, VALUE value)
{
  xmlParserCtxtPtr ctx;

  ctx = noko_xml_sax_push_parser_unwrap(self);

  if (Qfalse == value) {
    ctx->replaceEntities = 0;
  } else {
    ctx->replaceEntities = 1;
  }

  return value;
}


  







Instance Method Details



  

    #<<(chunk, last_chunk = false)  
  



  

    

Alias for #write.


  



  [ GitHub ]


  

  


# File 'lib/nokogiri/xml/sax/push_parser.rb', line 50



alias_method :<<, :write


  








  

    #finish  
  



  

    

Finish the parsing.  This method is only necessary for Document#end_document to be called.


  



  [ GitHub ]


  

  


# File 'lib/nokogiri/xml/sax/push_parser.rb', line 55



def finish
  write("", true)
end


  








  

    #initialize_native(xml_sax, filename)   (private)  



  

    

Initialize the push parser with xml_sax using filename


  



  [ GitHub ]


  

  


# File 'ext/nokogiri/xml_sax_push_parser.c', line 76



static VALUE
initialize_native(VALUE self, VALUE _xml_sax, VALUE _filename)
{
  xmlSAXHandlerPtr sax;
  const char *filename = NULL;
  xmlParserCtxtPtr ctx;

  sax = noko_sax_handler_unwrap(_xml_sax);

  if (_filename != Qnil) { filename = StringValueCStr(_filename); }

  ctx = xmlCreatePushParserCtxt(
          sax,
          NULL,
          NULL,
          0,
          filename
        );
  if (ctx == NULL) {
    rb_raise(rb_eRuntimeError, "Could not create a parser context");
  }

  ctx->userData = NOKOGIRI_SAX_TUPLE_NEW(ctx, self);

  ctx->sax2 = 1;
  DATA_PTR(self) = ctx;
  return self;
}


  








  

    #native_write(chunk, last_chunk)   (private)  



  

    

Write chunk to PushParser. last_chunk triggers the end_document handle


  



  [ GitHub ]


  

  


# File 'ext/nokogiri/xml_sax_push_parser.c', line 43



static VALUE
native_write(VALUE self, VALUE _chunk, VALUE _last_chunk)
{
  xmlParserCtxtPtr ctx;
  const char *chunk  = NULL;
  int size            = 0;


  ctx = noko_xml_sax_push_parser_unwrap(self);

  if (Qnil != _chunk) {
    chunk = StringValuePtr(_chunk);
    size = (int)RSTRING_LEN(_chunk);
  }

  xmlSetStructuredErrorFunc(NULL, NULL);

  if (xmlParseChunk(ctx, chunk, size, Qtrue == _last_chunk ? 1 : 0)) {
    if (!(ctx->options & XML_PARSE_RECOVER)) {
      xmlErrorConstPtr e = xmlCtxtGetLastError(ctx);
      Nokogiri_error_raise(NULL, e);
    }
  }

  return self;
}


  








  

    #write(chunk, last_chunk = false)  
    Also known as: #<<
  



  

    

Write a chunk of ::Nokogiri::XML to the PushParser.  Any callback methods that can be called will be called immediately.


  



  [ GitHub ]


  

  


# File 'lib/nokogiri/xml/sax/push_parser.rb', line 47



def write(chunk, last_chunk = false)
  native_write(chunk, last_chunk)
end