require File.dirname(__FILE__) + '/tokenizer' require File.dirname(__FILE__) + '/node' module HTML #:nodoc: # A top-level HTMl document. You give it a body of text, and it will parse that # text into a tree of nodes. class Document #:nodoc: # The root of the parsed document. attr_reader :root # Create a new Document from the given text. def initialize(text, strict=false, xml=false) tokenizer = Tokenizer.new(text) @root = Node.new(nil) node_stack = [ @root ] while token = tokenizer.next node = Node.parse(node_stack.last, tokenizer.line, tokenizer.position, token) node_stack.last.children << node unless node.tag? && node.closing == :close if node.tag? if node_stack.length > 1 && node.closing == :close if node_stack.last.name == node.name node_stack.pop else open_start = node_stack.last.position - 20 open_start = 0 if open_start < 0 close_start = node.position - 20 close_start = 0 if close_start < 0 msg = <