narf 0.6.3 → 0.7.1

data/lib/web/unit/htmlelem.rb

@@ -1,124 +0,0 @@
-=begin
-= Web::Unit::HtmlElem
-  Copyright(C) 2001 yuichi TAKAHASHI
-  $Id: htmlelem.rb,v 1.1.1.1 2003/01/21 11:50:40 yuichi Exp $
-=end
-
-module Web
-  module Unit #:nodoc: all
-
-  class HtmlElem
-
-    attr_reader :tag, :data, :attrs, :children, :array, :name
-
-    def initialize( tag, ah={} )
-      @children = []
-      @tag = tag
-      @attrs = ah
-      @data = ''
-      @array = []
-      @name = ah['name'] if ah
-    end
-
-    def append( data )
-      if data.is_a?( HtmlElem )
-        @children << data
-      else
-        @data  << data
-      end
-      @array << data
-    end
-
-    def extract
-      data = ''
-      @array.each do |e|
-        if e.is_a?( String )
-          data << " #{e} "
-        elsif e.is_a?( HtmlElem )
-          data << e.extract
-        end
-      end
-      data.squeeze( ' ' ).strip
-    end
-
-    def inspect
-      return "<#toplevel>" if @tag == nil
-      as = ''
-      attrs.each{ |k,v| as << " #{k}=#{v}" }
-      "<#{@tag+as}>:#{data}:"
-    end
-
-=begin
---- HtmlElem#find(tag)
-      return an Array of HtmlElems, which have ((|tag|)).
-=end
-
-    def find( tag )
-      a = []
-      a.push self if @tag == tag
-      @children.each do |c|
-        a = a + c.find( tag )
-      end
-      a
-    end
-
-=begin
---- HtmlElem#search(data)
-      return an Array of HtmlElems, which have ((|data|)).
-=end
-
-    def search( data )
-      a = []
-      a.push self if @data == data
-      @children.each do |c|
-        a = a + c.search( data )
-      end
-      a
-    end
-
-=begin
---- HtmlElem#readlink(str)
-      return a Response, gotten with reading a Link have ((|str|)).
-      raise ElemNotFound exception, when no Links found.
-=end
-
-    def readlink( str )
-      self.find( 'a' ).each do |link|
-        return link.read if link.data == str
-      end
-      raise ElemNotFound, "no Links have '#{str}' as data."
-    end
-
-=begin
---- HtmlElem#has?(elem)
-      return true, when self have ((|elem|)) as child.
-      otherwise, return false.
-      ((|elem|)) should be a HtmlElem or a String.
-=end
-
-    def has?( elem )
-      if elem.kind_of?( HtmlElem )
-        @children.include?( elem )
-      elsif elem.instance_of?( String )
-        @array.include?( elem )
-      else
-        false
-      end
-    end
-
-=begin
---- HtmlElem#print(indent='') -- FOR TEST USE ONLY
-     print tree structure, from self to lower.
-=end
-
-    def print( indent='' ) # not tested :-(
-      puts indent + inspect
-      @children.each do |c|
-        c.print( indent + '  ' )
-      end
-    end
-
-  end # class HtmlElem
-
-end # module Web::Unit
-end

data/lib/web/unit/htmlrepair.rb

@@ -1,116 +0,0 @@
-=begin
-
-= HTML Repair Library
-
-htmlrepair.rb
-
-Version 1.0.1
-
-Copyright (C) 2000 MoonWolf Development
-
-MoonWolf <moonwolf-ruby@moonwolf.com>
-
-  ��ά���줿��λ�������䤦��
-
-== �Ȥ���
-
-  obj = HTMLSplit.new(html)
-  obj.repair
-
-=end
-
-require "web/unit/htmlsplit"
-module Web
-module Unit
-class HTMLSplit #:nodoc: all
-	
-	PARENTTAG = {
-		'p'			=>	%w(body table),
-		'a'			=>	%w(body),
-		'thead'		=>	%w(table),
-		'tfoot'		=>	%w(table),
-		'tbody'		=>	%w(table),
-		'tr'		=>	%w(table thead tfoor tbody),
-		'td'		=>	%w(tr),
-		'th'		=>	%w(tr),
-		'li'		=>	%w(ol ul),
-		'dt'		=>	%w(dl),
-		'dd'		=>	%w(dl),
-		'col'		=>	%w(colgroup),
-		'param'		=>	%w(applet),
-		'area'		=>	%w(map),
-		'input'		=>	%w(form),
-		'textarea'	=>	%w(form),
-		'button'	=>	%w(form),
-		'select'	=>	%w(form),
-		'keygen'	=>	%w(form),
-		'label'		=>	%w(form),
-		'fieldset'	=>	%w(form),
-		'legend'	=>	%w(fieldset),
-		'option'	=>	%w(select),
-	}
-	
-	def repair
-		tag = []
-		doc = []
-		@document.each {|e|
-			case e
-			when EmptyElementTag
-				doc.push e
-			when StartTag
-				if PARENTTAG[e.name] && (a = tag.rindex(e.name))
-					#�ͥ��Ȥ���λ�����ξ�ά�������å�
-					flag = true
-					tag[a..-1].each {|t|
-						if PARENTTAG[e.name].include?(t)
-							#����ʥͥ���
-							flag = false
-							break
-						end
-					}
-					if flag
-						#��ά���줿��λ���������
-						while t=tag.pop
-							c = EndTag.new(t)
-							doc.push c
-							if t==e.name
-								break
-							end
-						end
-					end
-				else
-				end
-				#
-				tag.push e.name
-				doc.push e
-			when EndTag
-				if tag.include?(e.name)
-					while t = tag.pop
-						if t==e.name
-							break
-						else
-							c = EndTag.new(t)
-							doc.push c
-						end
-					end
-				else
-				end
-				doc.push e
-			when CharacterData
-				doc.push e
-			when Declaration
-				doc.push e
-			when Comment
-				doc.push e
-			else
-				doc.push e
-			end
-		}
-		while t = tag.pop
-			doc.push EndTag.new(t)
-		end
-		@document = doc
-	end
-end
-end
-end

data/lib/web/unit/htmlsplit.rb

@@ -1,840 +0,0 @@
-module Web
-  module Unit #:nodoc: all
-
-=begin Start of Document
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
-<html>
-<head>
-<title>htmlsplit.rb</title>
-<link href="rubydoc.css" rel="stylesheet">
-</head>
-<body>
-| <a href="./">���</a> |
-<h1>HTML Split Library</h1>
-<p> HTML���ɤ߽񤭤��롣 �ɤ߹����ʸ��ϥ�����ʸ���������ˤʤ롣 to_s�᥽�åɤ�HTML���᤹���Ȥ�����롣</p>
-<h2>���饹����</h2>
-<table bgcolor="#FFFFFF" border="1">
-  <tr><td><a href="#HTMLSplit">HTMLSplit</a><td>HTML�򥿥���ʸ���ǡ�����ʬ�䤹�롣 
-<tr>
-	<td><a href="#CharacterData">CharacterData</a>
-	<td>ʸ���ǡ���
-  <tr><td><a href="#EmptyElementTag">EmptyElementTag</a>
-	<td>�����ǤΥ���
-  <tr>
-	<td><a href="#StartTag">StartTag</a>
-	<td>���ϥ���
-  <tr>
-	<td><a href="#EndTag">EndTag</a>
-	<td>�����
-  <tr>
-	<td><a href="#Comment">Comment</a>
-	<td>������
-  <tr>
-	<td><a href="#Declaration">Declaration</a>
-	<td>���(DOCTYPE)
-  <tr>
-	<td><a href="#SSI">SSI</a>
-	<td>SSI��
-  <tr>
-	<td><a href="#ERuby">ERuby</a>
-	<td>eRuby/ASP/JSP������ץȢ�
-  <tr>
-	<td><a href="#PHP">PHP</a>
-	<td>PHP������ץȢ�
-  </table>
-��������°���ͤʤɤ������ޤ줿������ץȤ�ǧ���Ǥ��ޤ���
-<h2>�Ȥ��� </h2>
-<h3>�ɤ߹���</h3>
-<pre class="Exception"><samp>#!/usr/bin/ruby
-require "htmlsplit"
-
-obj = HTMlSplit.new(ARGF.read)</samp></pre>
-<h3>����</h3>
-<pre>
-obj.document.each {|e|
-    print e.to_s
-}
-</pre>
-<h3>°��������</h3>
-<pre>
-img = Tag('img/')
-img['src']='xxx.png'  #&lt;img src="xxx.png"&gt;
-
-o = Tag('option')
-o['selected']=true    #&lt;option selected&gt;
-</pre>
-=end
-
-require "cgi"
-require "kconv"
-
-=begin EmptyElementTag
- 
-<h2><a name="EmptyElementTag">EmptyElementTag</a></h2>
-�����ǤΥ��� 
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">name</var>[,<var class="Hash">attr</var>])
-  <dd>���������֥������Ȥ��������롣 <var class="String">name</var>�ϥ�����̾�� <var class="Hash">attr</var>�ϥ�����°��nil�ޤ���Hash
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">name
-  <dd>����̾���֤���
-  <dt class="Hash">attr 
-  <dd>°�����֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-  <dt class="String">self[<var class="String">key</var>]
-  <dd>key�˴�Ϣ�Ť���줿°���ͤ��֤��ޤ���
-      �������륭������Ͽ����Ƥ��ʤ����ˤϡ�nil���֤��ޤ���
-  <dt class="String">self[<var class="String">key</var>]= <var class="String">value</var>
-  <dd><var class="String">key</var>���Ф���<var class="String">value</var>���Ϣ�Ť��ޤ���
-      <var class="String">value</var>��nil�λ���<var class="String">key</var>���Ф����Ϣ��������ޤ���
-</dl>
-=end
-class EmptyElementTag #:nodoc: all
-	def initialize(name,attr=nil)
-		@name = name.downcase
-		@attr = attr
-	end
-	attr_accessor :name
-	attr_accessor :attr
-	def to_s
-		if @attr
-			"<"+@name+@attr.keys.sort.collect{|n|
-				v = @attr[n]
-				if v==true
-					' ' + n
-				else
-					' ' + n + '="' + CGI::escapeHTML(v) + '"'
-				end
-			}.to_s+">"
-		else
-			"<#{@name}>"
-		end
-	end
-	def [](key)
-		attr and attr[key]
-	end
-	def []=(key,value)
-		if attr
-			attr[key]=value
-		else
-			attr = value and {key=>value}
-		end
-	end
-end
-=begin StartTag
-<h2>StartTag</h2>
-���ϥ���
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">name</var>[,<var class="Hash">attr</var>])
-  <dd>���������֥������Ȥ��������롣 <var class="String">name</var>�ϥ�����̾�� <var class="Hash">attr</var>�ϥ�����°��nil�ޤ���Hash
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">name
-  <dd>����̾���֤���
-  <dt class="Hash">attr 
-  <dd>°�����֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-  <dt class="String">self[<var class="String">key</var>]
-  <dd>key�˴�Ϣ�Ť���줿°���ͤ��֤��ޤ���
-      �������륭������Ͽ����Ƥ��ʤ����ˤϡ�nil���֤��ޤ���
-  <dt class="String">self[<var class="String">key</var>]= <var class="String">value</var>
-  <dd><var class="String">key</var>���Ф���<var class="String">value</var>���Ϣ�Ť��ޤ���
-      <var class="String">value</var>��nil�λ���<var class="String">key</var>���Ф����Ϣ��������ޤ���
-</dl>
-=end
-class StartTag #:nodoc: all
-	attr_accessor :name
-	attr_accessor :attr
-	def initialize(name,attr=nil)
-		@name = name.downcase
-		@attr = attr
-	end
-	def to_s
-		if @attr
-			"<"+@name+@attr.keys.sort.collect{|n|
-				v = @attr[n]
-				if v==true
-					' ' + n
-				else
-					' ' + n + '="' + CGI::escapeHTML(v) + '"'
-				end
-			}.to_s+">"
-		else
-			"<#{@name}>"
-		end
-	end
-	def [](key)
-		attr and attr[key]
-	end
-	def []=(key,value)
-		if attr
-			attr[key]=value
-		else
-			attr = value and {key=>value}
-		end
-	end
-end
-=begin EndTag
-<h2>EndTag</h2>
-�����
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">name</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">name</var>�ϥ�����̾��
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">name 
-  <dd>����̾���֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-</dl>
-=end
-class EndTag #:nodoc: all
-	def initialize(name)
-		@name = name.downcase
-	end
-	attr_accessor :name
-	def to_s
-		"</#{@name}>"
-	end
-end
-=begin CharacterData
-<h2>CharacterData</h2>
-ʸ���ǡ���
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">text</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">text</var>�ϥƥ�����
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">text 
-  <dd>�ƥ����Ȥ��֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-</dl>
-=end
-class CharacterData #:nodoc: all
-	def initialize(text)
-		@text = text
-	end
-	attr_accessor :text
-	def to_s
-		@text
-	end
-end
-=begin Declaraion
-<h2>Declaraion</h2>
-SGML���
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">text</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">text</var>�ϥƥ�����
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">text 
-  <dd>�ƥ����Ȥ��֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-</dl>
-=end
-class Declaration #:nodoc: all
-	def initialize(text)
-		@text = text
-	end
-	attr_accessor :text
-	def to_s
-		"<!#{@text}>"
-	end
-end
-=begin Comment
-<h2>Comment</h2>
-������
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">text</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">text</var>�ϥƥ�����
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">text 
-  <dd>�ƥ����Ȥ��֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-</dl>
-=end
-class Comment #:nodoc: all
-	def initialize(text)
-		@text = text
-	end
-	attr_accessor :text
-	def to_s
-		"<!--#{@text}-->"
-	end
-end
-=begin SSI
-<h2>SSI</h2>
-SSI
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">text</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">text</var>�ϥƥ�����
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">text 
-  <dd>�ƥ����Ȥ��֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-</dl>
-=end
-class SSI #:nodoc: all
-	def initialize(text)
-		@text = text
-	end
-	attr_accessor :text
-	def to_s
-		"<!--#{@text}-->"
-	end
-end
-=begin ERuby
-<h2>ERuby</h2>
-eRuby/ASP/JSP������ץ�
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">text</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">text</var>�ϥƥ�����
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">text 
-  <dd>�ƥ����Ȥ��֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-</dl>
-=end
-class ERuby
-	def initialize(text)
-		@text = text
-	end
-	attr_accessor :text
-	def to_s
-		"<%#{@text}%>"
-	end
-end
-=begin PHP
-<h2>PHP</h2>
-PHP������ץ�
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">text</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">text</var>�ϥƥ�����
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="String">text 
-  <dd>�ƥ����Ȥ��֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-</dl>
-=end
-class PHP
-	attr_accessor :text
-	def initialize(text)
-		@text = text
-	end
-	def to_s
-		"<?#{@text}?>"
-	end
-end
-=begin HTMLSplit
- 
-<h2><a name="HTMLSplit">HTMLSplit</a></h2>
-HTML�ɤ߽� 
-<h3>���饹�᥽�å�</h3>
-<dl compact>
-  <dt>new(<var class="String">html</var>)
-  <dd>���������֥������Ȥ��������롣 <var class="String">html</var>��HTMLʸ��
-</dl>
-<h3>�᥽�å�</h3>
-<dl compact>
-  <dt class="Array">document 
-  <dd>�ɥ�����Ȥ�������֤���
-  <dt class="String">to_s 
-  <dd>HTML���֤���
-  <dt class="Iterator">each {|<var>obj</var>,<var class="Array">tag</var>| ...}
-  <dd>�ɥ�����Ȥγƥ��֥�������(<var>obj</var>)���Ф��ƥ֥��å���ɾ�����ޤ���
-      <var class="Array">tag</var>�ϳ��ϥ����Υꥹ�ȡ� [ StartTag , <var class="Integer">����ǥ���</var>] ��
-  <dt class="Integer">index(<var class="Class">class</var>, <var class="Integer">start</var>, <var class="Integer">end</var>, <var>value</var>, <var class="Integer">count</var>) {|obj| ...}
-  <dd><var class="Integer">start</var>����<var class="Integer">end</var>�ޤǤ����Ǥ�<var class="Class">class</var>��������<var class="Integer">count</var>���ܤ����Ǥΰ��֤��֤��ޤ���
-      ���������Ǥ��ҤȤĤ�ʤ��ä����ˤ�nil���֤��ޤ���<br>
-      <var>value</var>��nil�ʳ����ͤ���ꤷ�����ˤ����Ǥ�<var>value</var>���������������å���Ԥ��ޤ���<var class="Class">class</var>��EmptyElementTag,StartTag,EndTag�λ��ϥ���̾������ʳ��ϥƥ����Ȥˤ�ä���Ӥ��ޤ���<br>
-      �֥��å�����ꤷ�ƸƤӽФ��줿���ˤϥ֥��å������Ǥ���������ɾ�����롣
-  <dt class="Integer">end_index(<var class="Integer">start</var>)
-  <dd><var class="Integer">start</var>���б�����EndTag�Υ���ǥ������֤��ޤ���
-      �б��������Ǥ��ʤ��ä����ˤ�nil���֤��ޤ���<br>
-</dl>
-=end
-class HTMLSplit
-	EMPTY = %w(area base basefont bgsound br col frame hr img input isindex 
-	           keygen link meta nextid param spacer wbr)
-	def initialize(html)
-		@document = []	#�ѡ�������HTML�Υꥹ��
-		name = ''
-		text = ''
-		attr = {}
-		attrname = ''
-		state = :TEXT
-		#
-		html.each_byte {|c|
-			char = c.chr
-			case state
-			when :TEXT
-				if c==60
-					if text.length>0
-						@document << CharacterData.new(text)
-					end
-					name = ''
-					attr={}
-					state = :TAGNAME
-				else
-					text << char
-				end
-			when :TAGNAME
-				case char
-				when '>'
-					name.downcase!
-					if EMPTY.include?(name)
-						@document << EmptyElementTag.new(name,nil)
-					else
-						if name[0,1]=='/'
-							@document << EndTag.new(name[1..-1])
-						else
-							@document << StartTag.new(name,nil)
-						end
-					end
-					text = ''
-					state = :TEXT
-				when '!'
-					text = ''
-					state = :DECLARE
-				when '%'
-					text = ''
-					state = :ERUBY
-				when '?'
-					text = ''
-					state = :PHP
-				when /\s/
-					text=''
-					state = :SPACE
-				else
-					name << char
-				end
-			when :SPACE	#°���֤ζ���
-				case char
-				when '>'
-					name.downcase!
-					if EMPTY.include?(name)
-						@document << EmptyElementTag.new(name,attr)
-					else
-						if name[0,1]=='/'
-							@document << EndTag.new(name[1..-1])
-						else
-							@document << StartTag.new(name,attr)
-						end
-					end
-					text = ''
-					state = :TEXT
-				when /\s/
-				else
-					attrname=char
-					state = :ATTRNAME
-				end
-			when :ATTRNAME	#°��̾
-				case char
-				when /\s/
-					state = :BEFOREEQUAL
-				when '='
-					state = :AFTEREQUAL
-				when '>'
-					attr[attrname.downcase]=true
-					name.downcase!
-					if EMPTY.include?(name)
-						@document << EmptyElementTag.new(name,attr)
-					else
-						if name[0,1]=='/'
-							@document << EndTag.new(name[1..-1])
-						else
-							@document << StartTag.new(name,attr)
-						end
-					end
-					text = ''
-					state = :TEXT
-				else
-					attrname << char
-				end
-			when :BEFOREEQUAL	#=
-				case char
-				when '='
-					state = :AFTEREQUAL
-				when '>'
-					attr[attrname.downcase]=true
-					name.downcase!
-					if EMPTY.include?(name)
-						@document << EmptyElementTag.new(name,attr)
-					else
-						if name[0,1]=='/'
-							@document << EndTag.new(name[1..-1])
-						else
-							@document << StartTag.new(name,attr)
-						end
-					end
-					text = ''
-					state = :TEXT
-				when /\s/
-				else
-					attr[attrname.downcase]=true
-					attrname = char
-					state = :ATTRNAME
-				end
-			when :AFTEREQUAL	#=
-				case char
-				when "'"
-					text=''
-					state = :SQVALUE
-				when '"'
-					text=''
-					state = :DQVALUE
-				when '>'
-					attr[attrname.downcase]=true
-					name.downcase!
-					if EMPTY.include?(name)
-						@document << EmptyElementTag.new(name,attr)
-					else
-						if name[0,1]=='/'
-							@document << EndTag.new(name[1..-1])
-						else
-							@document << StartTag.new(name,attr)
-						end
-					end
-					text = ''
-					state = :TEXT
-				when /\s/
-				else
-					text=char
-					state = :VALUE
-				end
-			when :VALUE		#��
-				case char
-				when /\s/
-					attr[attrname.downcase]=CGI::unescapeHTML(text)
-					state = :SPACE
-				when '>'
-					attr[attrname.downcase]=CGI::unescapeHTML(text)
-					name.downcase!
-					if EMPTY.include?(name)
-						@document << EmptyElementTag.new(name,attr)
-					else
-						if name[0,1]=='/'
-							@document << EndTag.new(name[1..-1])
-						else
-							@document << StartTag.new(name,attr)
-						end
-					end
-					text = ''
-					state = :TEXT
-				else
-					text << char
-				end
-			when :SQVALUE	#'��'
-				if c==39
-					attr[attrname.downcase]=CGI::unescapeHTML(text)
-					state = :SPACE
-				else
-					text << char
-				end
-			when :DQVALUE	#"��"
-				if c==34
-					attr[attrname.downcase]=CGI::unescapeHTML(text)
-					state = :SPACE
-				else
-					text << char
-				end
-			when :COMMENT
-				case char
-				when '>'
-					if text[-2,2]=='--'	#�����Ƚ�λ	
-						text = text[0..-3]
-						if text=~/^#[a-z]+/	#SSI
-							@document << SSI.new(text)
-						else
-							@document << Comment.new(text)
-						end
-						text = ''
-						state = :TEXT
-					else
-						text << char
-					end
-				else
-					text << char
-				end
-			when :ERUBY
-				case char
-				when '>'
-					if text[-1,1]=='%'	#eRuby��λ	
-						text = text[0..-2]
-						@document << ERuby.new(text)
-						text = ''
-						state = :TEXT
-					else
-						text << char
-					end
-				else
-					text << char
-				end
-			when :PHP
-				case char
-				when '>'
-					if text[-1,1]=='?'	#eRuby��λ	
-						text = text[0..-2]
-						@document << PHP.new(text)
-						text = ''
-						state = :TEXT
-					else
-						text << char
-					end
-				else
-					text << char
-				end
-			when :DECLARE
-				case char
-				when '>'
-					@document << Declaration.new(text)
-					text = ''
-					state = :TEXT
-				else
-					text << char
-					if text=='--'
-						text = ''
-						state = :COMMENT
-					end
-				end
-			end
-		}
-		#EOF���
-		case state
-		when :TEXT
-			@document << CharacterData.new(text) if text.length>0
-		when :TAGNAME
-			@document << CharacterData.new('<'+text)
-		when :SPACE	#°���֤ζ���
-			name.downcase!
-			if EMPTY.include?(name)
-				@document << EmptyElementTag.new(name,attr)
-			else
-				if name[0,1]=='/'
-					@document << EndTag.new(name[1..-1])
-				else
-					@document << StartTag.new(name,attr)
-				end
-			end
-		when :ATTRNAME	#°��̾
-			attr[attrname.downcase]=true
-			name.downcase!
-			if EMPTY.include?(name)
-				@document << EmptyElementTag.new(name,attr)
-			else
-				if name[0,1]=='/'
-					@document << EndTag.new(name[1..-1])
-				else
-					@document << StartTag.new(name,attr)
-				end
-			end
-		when :BEFOREEQUAL	#=
-			attr[attrname.downcase]=true
-			name.downcase!
-			if EMPTY.include?(name)
-				@document << EmptyElementTag.new(name,attr)
-			else
-				if name[0,1]=='/'
-					@document << EndTag.new(name[1..-1])
-				else
-					@document << StartTag.new(name,attr)
-				end
-			end
-		when :AFTEREQUAL	#=
-			attr[attrname.downcase]=true
-			name.downcase!
-			if EMPTY.include?(name)
-				@document << EmptyElementTag.new(name,attr)
-			else
-				if name[0,1]=='/'
-					@document << EndTag.new(name[1..-1])
-				else
-					@document << StartTag.new(name,attr)
-				end
-			end
-		when :VALUE		#��
-			attr[attrname.downcase]=CGI::unescapeHTML(text)
-			name.downcase!
-			if EMPTY.include?(name)
-				@document << EmptyElementTag.new(name,attr)
-			else
-				if name[0,1]=='/'
-					@document << EndTag.new(name[1..-1])
-				else
-					@document << StartTag.new(name,attr)
-				end
-			end
-		when :SQVALUE	#'��'
-			attr[attrname.downcase]=CGI::unescapeHTML(text)
-		when :DQVALUE	#"��"
-			attr[attrname.downcase]=CGI::unescapeHTML(text)
-		when :COMMENT
-			if text=~/^#[a-zA-Z]+/	#SSI
-				@document << SSI.new(text)
-			else
-				@document << Comment.new(text)
-			end
-		when :ERUBY
-			@document << ERuby.new(text)
-		when :PHP
-			@document << PHP.new(text)
-		when :DECLARE
-			@document << Declaration.new(text)
-		end
-	end
-	#
-	attr_accessor :document
-	#
-	def to_s
-		s = ''
-		@document.each {|e|
-			s<<(e.to_s)
-		}
-		s
-	end
-	#
-	def each
-		tag = []
-		i = 0
-		@document.each {|e|
-			case e
-			when StartTag
-				tag.push [e,i]
-			when EndTag
-				idx = nil
-				(tag.size-1).downto(0) {|j|
-					if tag[j][0].name==e.name
-						idx = j
-						break
-					end
-				}
-				#
-				if idx
-					if idx==0
-						tag = []
-					else
-						tag = tag[0..idx-1]
-					end
-				end
-			else
-			end
-			yield e,tag
-			i += 1
-		}
-	end
-	#
-	def index(_class,_start=0,_end=-1,value=nil,count=1)
-		idx=_start
-		found=false
-		@document[_start.._end].each {|obj|
-			if obj.type==_class
-				if value
-					case obj
-					when StartTag,EmptyElementTag,EndTag
-						if value===obj.name
-							if (not iterator?) or yield(obj)
-								if (count-=1)<=0
-									found = true
-									break
-								end
-							end
-						end
-					else
-						if value===obj.text
-							if (not iterator?) or yield(obj)
-								if (count-=1)<=0
-									found = true
-									break
-								end
-							end
-						end
-					end
-				else
-					if (not iterator?) or yield(obj)
-						if (count-=1)<=0
-							found = true
-							break
-						end
-					end
-				end
-			end
-			idx+=1
-		}
-		if found
-			idx
-		else
-			nil
-		end
-	end
-	#
-	def end_index(start_index)
-		tag = []
-		end_index = nil
-		(start_index...@document.size).each {|idx|
-			e= @document[idx]
-			case e
-			when StartTag
-				tag.push [e,idx]
-			when EndTag
-				i = nil
-				(tag.size-1).downto(0) {|j|
-					if tag[j][0].name==e.name
-						i = j
-						break
-					end
-				}
-				#
-				if i
-					if i==0
-						tag = []
-					else
-						tag = tag[0..i-1]
-					end
-				end
-				if tag.size==0
-					end_index = idx
-					break
-				end
-			else
-			end
-		}
-		end_index
-	end
-end
-=begin End of Document
-</body>
-</html>
-=end
-end
-end