This API is experimental, and subject to change.
parser = PullParser.new( "<a>text<b att='val'/>txet</a>" ) while parser.has_next? res = parser.next puts res[1]['att'] if res.start_tag? and res[0] == 'b' end
See the PullEvent class for information on the content of the results. The data is identical to the arguments passed for the various events to the StreamListener API.
Notice that:
parser = PullParser.new( "<a>BAD DOCUMENT" ) while parser.has_next? res = parser.next raise res[1] if res.error? end
Nat Price gave me some good ideas for the API.
These are patterns to identify common markup errors, to make the error messages more informative.
Entity constants
 
               # File rexml/parsers/baseparser.rb, line 122
def add_listener( listener )
  @listeners << listener
end
             
            Returns true if there are no more events
 
               # File rexml/parsers/baseparser.rb, line 148
def empty?
  return (@source.empty? and @stack.empty?)
end
             
             
               # File rexml/parsers/baseparser.rb, line 449
def entity( reference, entities )
  value = nil
  value = entities[ reference ] if entities
  if not value
    value = DEFAULT_ENTITIES[ reference ]
    value = value[2] if value
  end
  unnormalize( value, entities ) if value
end
             
            Returns true if there are more events. Synonymous with !empty?
 
               # File rexml/parsers/baseparser.rb, line 153
def has_next?
  return !(@source.empty? and @stack.empty?)
end
             
            Escapes all possible entities
 
               # File rexml/parsers/baseparser.rb, line 460
def normalize( input, entities=nil, entity_filter=nil )
  copy = input.clone
  # Doing it like this rather than in a loop improves the speed
  copy.gsub!( EREFERENCE, '&' )
  entities.each do |key, value|
    copy.gsub!( value, "&#{key};" ) unless entity_filter and
                                entity_filter.include?(entity)
  end if entities
  copy.gsub!( EREFERENCE, '&' )
  DEFAULT_ENTITIES.each do |key, value|
    copy.gsub!( value[3], value[1] )
  end
  copy
end
             
            Peek at the depth event in the stack.  The first element on the stack is at depth 0.  If depth is -1, will parse to the end of the input stream and return the last event, which is always :end_document. Be aware that this causes the stream to be parsed up to the depth event, so you can effectively pre-parse the entire document (pull the entire thing into memory) using this method.
 
               # File rexml/parsers/baseparser.rb, line 169
def peek depth=0
  raise %Q[Illegal argument "#{depth}"] if depth < -1
  temp = []
  if depth == -1
    temp.push(pull()) until empty?
  else
    while @stack.size+temp.size < depth+1
      temp.push(pull())
    end
  end
  @stack += temp if temp.size > 0
  @stack[depth]
end
             
             
               # File rexml/parsers/baseparser.rb, line 138
def position
  if @source.respond_to? :position
    @source.position
  else
    # FIXME
    0
  end
end
             
            Returns the next event.  This is a PullEvent object.
 
               # File rexml/parsers/baseparser.rb, line 184
def pull
  pull_event.tap do |event|
    @listeners.each do |listener|
      listener.receive event
    end
  end
end
             
             
               # File rexml/parsers/baseparser.rb, line 128
def stream=( source )
  @source = SourceFactory.create_from( source )
  @closed = nil
  @document_status = nil
  @tags = []
  @stack = []
  @entities = []
  @nsstack = []
end
             
            Unescapes all possible entities
 
               # File rexml/parsers/baseparser.rb, line 476
def unnormalize( string, entities=nil, filter=nil )
  rv = string.clone
  rv.gsub!( /\r\n?/, "\n" )
  matches = rv.scan( REFERENCE_RE )
  return rv if matches.size == 0
  rv.gsub!( /�*((?:\d+)|(?:x[a-fA-F0-9]+));/ ) {
    m=$1
    m = "0#{m}" if m[0] == ?x
    [Integer(m)].pack('U*')
  }
  matches.collect!{|x|x[0]}.compact!
  if matches.size > 0
    matches.each do |entity_reference|
      unless filter and filter.include?(entity_reference)
        entity_value = entity( entity_reference, entities )
        if entity_value
          re = /&#{entity_reference};/
          rv.gsub!( re, entity_value )
        else
          er = DEFAULT_ENTITIES[entity_reference]
          rv.gsub!( er[0], er[2] ) if er
        end
      end
    end
    rv.gsub!( /&/, '&' )
  end
  rv
end