vendor/rails/actionpack/lib/action_controller/vendor/html-scanner/html/document.rb

   1 require 'html/tokenizer'
   2 require 'html/node'
   3 require 'html/selector'
   4 require 'html/sanitizer'
   5
   6 module HTML #:nodoc:
   7   # A top-level HTMl document. You give it a body of text, and it will parse that
   8   # text into a tree of nodes.
   9   class Document #:nodoc:
  10
  11     # The root of the parsed document.
  12     attr_reader :root
  13
  14     # Create a new Document from the given text.
  15     def initialize(text, strict=false, xml=false)
  16       tokenizer = Tokenizer.new(text)
  17       @root = Node.new(nil)
  18       node_stack = [ @root ]
  19       while token = tokenizer.next
  20         node = Node.parse(node_stack.last, tokenizer.line, tokenizer.position, token, strict)
  21
  22         node_stack.last.children << node unless node.tag? && node.closing == :close
  23         if node.tag?
  24           if node_stack.length > 1 && node.closing == :close
  25             if node_stack.last.name == node.name
  26               if node_stack.last.children.empty?
  27                 node_stack.last.children << Text.new(node_stack.last, node.line, node.position, "")
  28               end
  29               node_stack.pop
  30             else
  31               open_start = node_stack.last.position - 20
  32               open_start = 0 if open_start < 0
  33               close_start = node.position - 20
  34               close_start = 0 if close_start < 0
  35               msg = <<EOF.strip
  36 ignoring attempt to close #{node_stack.last.name} with #{node.name}
  37   opened at byte #{node_stack.last.position}, line #{node_stack.last.line}
  38   closed at byte #{node.position}, line #{node.line}
  39   attributes at open: #{node_stack.last.attributes.inspect}
  40   text around open: #{text[open_start,40].inspect}
  41   text around close: #{text[close_start,40].inspect}
  42 EOF
  43               strict ? raise(msg) : warn(msg)
  44             end
  45           elsif !node.childless?(xml) && node.closing != :close
  46             node_stack.push node
  47           end
  48         end
  49       end
  50     end
  51
  52     # Search the tree for (and return) the first node that matches the given
  53     # conditions. The conditions are interpreted differently for different node
  54     # types, see HTML::Text#find and HTML::Tag#find.
  55     def find(conditions)
  56       @root.find(conditions)
  57     end
  58
  59     # Search the tree for (and return) all nodes that match the given
  60     # conditions. The conditions are interpreted differently for different node
  61     # types, see HTML::Text#find and HTML::Tag#find.
  62     def find_all(conditions)
  63       @root.find_all(conditions)
  64     end
  65
  66   end
  67
  68 end