--- test/html.dtd	1994/04/04 23:58:38	1.7.2.3
+++ test/html.dtd	1994/06/03 20:02:52	1.14
@@ -1,11 +1,161 @@
 <!--	html.dtd
 
         Document Type Definition for the HyperText Markup Language
-        as used by the World Wide Web application (HTML DTD).
+        as used by the World Wide Web (HTML DTD).
 
-        $Id: html.dtd,v 1.7.2.3 1994/04/04 23:58:38 connolly Exp $
+	$Id: html.dtd,v 1.14 1994/06/03 20:02:52 connolly Exp $
+
+	Author: Daniel W. Connolly <connolly@hal.com>
+	See Also: http://www.hal.com/%7Econnolly/html-spec/HTML.html
+		  http://info.cern.ch/hypertext/WWW/MarkUp2/MarkUp.html
 -->
 
+<!ENTITY HTML.Version
+	"-//W3O//DTD WWW HTML 2.0//EN"
+	-- public identifier for "current pracitice" version             -- 
+
+        -- Typical usage:
+
+            <!DOCTYPE HTML PUBLIC "-//W3O//DTD WWW HTML 2.0//EN">
+	    <html>
+	    ...
+	    </html>
+	--
+	>
+
+
+<!-- Feature Test Entities -->
+
+<!-- To use these, write your document like:
+	<!DOCTYPE HTML [
+	<!ENTITY % HTML.Optional "INCLUDE">
+	<!ENTITY % html PUBLIC "-//connolly hal.com//DTD WWW HTML 1.8//EN">
+	%html;
+	]>
+	<TITLE>Here's my doc</TITLE>
+	<p>It uses lots of optional features
+
+ In practice, if you're using sgmls to validate your docs,
+ you can stick the <!DOCTYPE [...]> in a separate file and
+ validate with:
+	sgmls -s doctype.sgml foo.html
+ -->
+
+<!ENTITY % HTML.Level0  "IGNORE">
+<!ENTITY % HTML.Obsolete "IGNORE">
+<!ENTITY % HTML.Prescriptive "IGNORE">
+
+<![ %HTML.Level0 [
+	<!ENTITY % HTML.linkRelationships "IGNORE">
+	<!ENTITY % HTML.linkMethods "IGNORE">
+	<!ENTITY % HTML.linkRedundantInfo "IGNORE">
+	<!ENTITY % HTML.forms "IGNORE">
+	<!ENTITY % HTML.phrase "IGNORE">
+	<!ENTITY % HTML.NEXTID "IGNORE">
+	<!-- @# Are the following required for conformance? -->
+	<!-- @# nested lists -->
+	<!-- @# IMG -->
+	<!-- @# headers inside A -->
+	<!-- @# nested phrases, fonts -->
+	]]>
+	
+<![ %HTML.Obsolete [
+	<!ENTITY % HTML.titleCDATA "INCLUDE">
+	<!ENTITY % HTML.litCDATA "INCLUDE">
+	<!ENTITY % HTML.pSeparator "INCLUDE">
+	]]>
+
+<![ %HTML.Prescriptive [
+	<!--
+	This feature test entity prescribes that certain
+	idioms detract from the structural integrity of an
+	HTML document, and are therefore disallowed.
+	-->
+	<!ENTITY % HTML.font-phrase "IGNORE">
+	<!ENTITY % HTML.anchorNameCDATA "IGNORE">
+	<!ENTITY % HTML.PLAINTEXT "IGNORE">
+	<!ENTITY % HTML.bodyBlockOnly "INCLUDE">
+	]]>
+
+<!ENTITY % HTML.phrase "INCLUDE"
+	-- phrase markup, ala TeXinfo: TT, EM, etc.
+	-->
+
+<!ENTITY % HTML.bodyBlockOnly "IGNORE"
+	-- only allow block elements in the BODY element
+	This means all paragraphs need to start with a <P> tag.
+	-->
+
+<!ENTITY % HTML.pSeparator "IGNORE"
+	-- use P element as paragraph separator, rather	that container.
+	-->
+
+<!ENTITY % HTML.linkRelationships "INCLUDE"
+	-- Adding markup to links to show the relationship between
+	ends of a link
+	see http://info.cern.ch/hypertext/WWW/MarkUp/Relationships.html
+	-->
+
+<!ENTITY % HTML.linkMethods "INCLUDE"
+	-- Adding markup to links to show the methods supported
+	by the referent object
+	see http://info.cern.ch/hypertext/WWW/MarkUp/Elements/A.html
+	-->
+
+<!ENTITY % HTML.linkRedundantInfo "INCLUDE"
+	-- Adding markup to links to give redundant information
+	like URN, content type, title...
+	-->
+
+<!ENTITY % HTML.anchorNameCDATA "INCLUDE"
+	-- Anchor names should be distinct. SGML parser can validate
+	this if the NAME attribute of the A element is declared as ID.
+	But that restricts the syntax of an anchor name to an SGML name,
+	i.e. a letter followed by letters, numbers, periods and dashes,
+	up to NAMELEN (34) characters long.
+	-->
+
+<!ENTITY % HTML.PLAINTEXT "INCLUDE"
+	-- Support for the <PLAINTEXT> tag as a sign of the
+	end of th HTML data stream and the beginning of a stream
+	of text/plain data
+	-->
+
+<!ENTITY % HTML.titleCDATA "IGNORE"
+	-- Is the TITLE element #PCDATA, RCDATA, or CDATA content?
+	On Mosaic, it's #PCDATA, but in the linemode browser,
+	it's more like CDATA, but not quite.
+	-->
+
+<!ENTITY % HTML.NEXTID "INCLUDE"
+	-- Used by the NeXT implementation to keep track of the
+	next anchor id to use
+	-->
+
+<!ENTITY % HTML.font-phrase "INCLUDE"
+	-- allow B, I, TT, U outside PRE,
+	CITE, VAR, etc. inside PRE
+	-->
+
+<!ENTITY % HTML.KEY "IGNORE"
+	-- There was once a KEY element, for keyboard keys, menu items,
+	buttons, etc. but it's not supported or widely documented
+	-->
+
+<!ENTITY % HTML.U "IGNORE"
+	-- There was also a U element, but since it clashes with
+	the common pracitce of underlining hypertext links, it is
+	not widely supported
+	-->
+
+<!ENTITY % HTML.litCDATA "IGNORE"
+	-- treat XMP, LISTING as CDATA, as per linemodeWWW
+	-->
+
+<!ENTITY % HTML.forms "INCLUDE"
+	-- Support for forms as per
+http://www.ncsa.uiuc.edu/SDG/Software/Mosaic/Docs/fill-out-forms/overview.html
+	-->
 
 <!-- DTD definitions -->
 
@@ -13,45 +163,75 @@
 <!ENTITY % list " UL | OL | DIR | MENU ">
 <!ENTITY % literal " XMP | LISTING ">
 
-<!ENTITY % bodyelement
-         "P | HR | %heading |
-         %list | DL | ADDRESS | PRE | BLOCKQUOTE
-        | %literal">
-
-<!ENTITY % URL "CDATA"
-        -- The term URL means a CDATA attribute
-           whose value is a Uniform Resource Locator,
-           as defined. (A URN may also be usable here when defined.)
+<!ENTITY % URI "CDATA"
+        -- The term URI means a CDATA attribute
+           whose value is a Uniform Resource Identifier,
+           as defined by 
+	"Universal Resource Identifiers" by Tim Berners-Lee
+	aka http://info.cern.ch/hypertext/WWW/Addressing/URL/URI_Overview.html
+
+	Note that CDATA attributes are limited by the LITLEN
+	capacity (1024 in the current version of html.decl),
+	so that URIs in HTML have a bounded length.
+
         -->
 
-<!ENTITY % linkattributes
-        "NAME NMTOKEN #IMPLIED
-        HREF %URL;  #IMPLIED
+<!ENTITY % Content-Type "CDATA"
+	-- meaning a MIME content type, as per RFC1521
+	-->
+
+<![ %HTML.anchorNameCDATA [ <!ENTITY % anchor-name "CDATA"> ]]>
+<!ENTITY % anchor-name "ID">
+
+<![ %HTML.linkRelationships [ <!ENTITY % linkRelAttrs "
         REL CDATA #IMPLIED -- forward relationship type --
         REV CDATA #IMPLIED -- reversed relationship type
                               to referent data:
 
                                 PARENT CHILD, SIBLING, NEXT, TOP,
                                 DEFINITION, UPDATE, ORIGINAL etc. --
+	"> ]]>
+<!ENTITY % linkRelAttrs "">
 
+<![ %HTML.linkRedundantInfo [ <!ENTITY % linkRedundantAttrs "
         URN CDATA #IMPLIED -- universal resource number --
 
         TITLE CDATA #IMPLIED -- advisory only --
+	"> ]]>
+<!ENTITY % linkRedundantAttrs "">
 
+<![ %HTML.linkMethods [ <!ENTITY % linkMethodAttrs "
         METHODS NAMES #IMPLIED -- supported public methods of the object:
                                         TEXTSEARCH, GET, HEAD, ... --
+	"> ]]>
+<!ENTITY % linkMethodAttrs "">
 
+<!ENTITY % linkattributes
+        "NAME %anchor-name #IMPLIED
+        HREF %URI;  #IMPLIED
+	%linkRelAttrs;
+	%linkRedundantAttrs;
+	%linkMethodAttrs;
         ">
 
 
 <!-- Document Element -->
 
-<!ELEMENT HTML O O  (HEAD, BODY)>
 
-<!ELEMENT HEAD O O  ( TITLE?  & ISINDEX?  & NEXTID?  & LINK*
-                              & BASE?)>
+<![ %HTML.PLAINTEXT [ <!ENTITY % obsolete-plaintext ", PLAINTEXT?"> ]]>
+<!ENTITY % obsolete-plaintext "">
 
-<!ELEMENT TITLE - -  (#PCDATA)
+<!ENTITY % html-content "HEAD, BODY %obsolete-plaintext;">
+<!ELEMENT HTML O O  (%html-content)>
+
+<![ %HTML.NEXTID [  <!ENTITY % head-content "TITLE? & ISINDEX? & LINK* & BASE?
+			& NEXTID?"> ]]>
+<!ENTITY % head-content "TITLE & ISINDEX? & LINK* & BASE?">
+<!ELEMENT HEAD O O  (%head-content)>
+
+<![ %HTML.titleCDATA [ <!ENTITY % title-content "CDATA"> ]]>
+<!ENTITY % title-content "(#PCDATA)">
+<!ELEMENT TITLE - -  %title-content
           -- The TITLE element is not considered part of the flow of text.
              It should be displayed, for example as the page header or
              window title.
@@ -62,78 +242,139 @@
              documents containing ISINDEX.
           -->
 
+<!ELEMENT NEXTID - O EMPTY>
+<!ATTLIST NEXTID N %anchor-name #REQUIRED
+          -- The number should be a name suitable for use
+             for the ID of a new element. When used, the value
+             has its numeric part incremented. EG Z67 becomes Z68
+          -->
 <!ELEMENT LINK - O EMPTY>
 <!ATTLIST LINK
         %linkattributes>
         
-<!ELEMENT BASE - O EMPTY    -- Reference context for URLS -->
+<!ELEMENT BASE - O EMPTY    -- Reference context for URIs -->
 <!ATTLIST BASE
 
-        HREF %URL; #IMPLIED
+        HREF %URI; #REQUIRED
 
         >
-<!ENTITY % inline "EM | STRONG |
-                        CODE | SAMP | KBD | KEY | VAR | DFN | CITE "
-        >
 
-<!ELEMENT (%inline;) - - (#PCDATA | A)+>
-<!ELEMENT (B | I | U | TT) - - (#PCDATA | A)+>
+<![ %HTML.KEY [
+	<!ENTITY % key-emph "| KEY">
+	]]>
+<!ENTITY % key-emph "">
+
+<![ %HTML.U [
+	<!ENTITY % u-font "| U">
+	]]>
+<!ENTITY % u-font "">
+
+<![ %HTML.phrase [
+<!ENTITY % font "TT | B | I %u-font">
+<!ENTITY % phrase "EM | STRONG | CODE | SAMP | KBD | VAR | DFN | CITE
+	 | STRIKE %key-emph">
+
+
+<![ %HTML.font-phrase [
+	<!ENTITY % obsolete-font "| %font">
+	<!ENTITY % obsolete-phrase "| %phrase">
+	]]>
+<!ENTITY % obsolete-font "">
+<!ENTITY % obsolete-phrase "">
+<![ %HTML.pSeparator [
+	<!ENTITY % obsolete-p "| P">
+	]]>
+<!ENTITY % obsolete-p "">
+
+<!ENTITY % inline "%phrase %obsolete-font">
+<!ENTITY % pre-inline "%font %obsolete-phrase %obsolete-p">
+]]>
 
-<!ENTITY % text "#PCDATA | IMG | %inline; | BR">
-
-<!ENTITY % htext "A | %text"    -- Plus links, no structure -->
+<!ENTITY % inline "">
+<!ENTITY % pre-inline "">
 
-<!ENTITY % stext                -- as htext but also nested structure --
-                        "P | HR | %list | DL | ADDRESS
-                        | PRE | BLOCKQUOTE
-                        | %literal | %htext">
-
-<!ENTITY % block                -- as htext but also nested structure --
-                        "P | HR | %list | DL
-                        | PRE | BLOCKQUOTE | ADDRESS
-                        | %literal">
-
-
-<!ELEMENT BODY O O  (%heading | %block)+>
+<!ENTITY % text "#PCDATA | IMG | %inline | BR %obsolete-p">
 
+<!ENTITY % htext "A | %text"    -- Plus links, no structure -->
 
-<!ELEMENT A     - -  ANY>
+<![ %HTML.font-phrase [ <!ENTITY % font-content "(%htext)+"> ]]>
+<!ENTITY % font-content "#PCDATA">
+<!ELEMENT (%font;) - - (%font-content;)>
+
+<![ %HTML.phrase [
+<!ELEMENT (%phrase;) - - (%htext)+>
+]]>
+
+<!ENTITY % pre "PRE | XMP | LISTING">
+
+<![ %HTML.forms [ <!ENTITY % block-form "| FORM | ISINDEX"> ]]>
+<!ENTITY % block-form "">
+
+<![ %HTML.pSeparator [
+	<!ENTITY % obsolete-htext "| %htext">
+	<!ENTITY % block-p "">
+	]]>
+<!ENTITY % obsolete-htext "| A">
+<!ENTITY % block-p "| P ">
+
+<!ENTITY % block "HR | %list | DL
+		| %pre | BLOCKQUOTE | ADDRESS 
+		%block-form %block-p">
+
+
+<![ %HTML.bodyBlockOnly [
+	<!ENTITY % current-htext "">
+	]]>
+<!ENTITY % current-htext "| %htext">
+
+<!ENTITY % body-content "%heading | %block %current-htext">
+<!ELEMENT BODY O O  (%body-content)*>
+
+
+<!ELEMENT A     - - (%heading|%block|%text)+ -(A)
+	-- @# Technically, this allows silliness like:
+		<H2><A>xyz<H1>h1</H1></A></H2>
+	The right way to do anchors outside of %htext is more like:
+		<as id=z1><H2>lkjlkj</h2><ae start=z1>
+	-->
 <!ATTLIST A
         %linkattributes;
         >
 
 <!ELEMENT IMG    - O EMPTY --  Embedded image -->
 <!ATTLIST IMG
-        SRC %URL;  #IMPLIED     -- URL of document to embed --
+        SRC %URI;  #IMPLIED     -- URI of document to embed --
+	ALT CDATA #IMPLIED
+	ALIGN (top|middle|bottom) #IMPLIED
+	ISMAP (ISMAP) #IMPLIED
         >
 
 
-<!ELEMENT P     - O (%htext)+ -- paragraph -->
-<!ELEMENT (HR|BR)    - O EMPTY -- horizontal rule -->
+<![ %HTML.pSeparator [ <!ENTITY % p-content "EMPTY"> ]]>
+<!ENTITY % p-content "(%htext)+">
+<!ELEMENT P     - O %p-content>
+<!ELEMENT HR    - O EMPTY -- horizontal rule -->
+<!ELEMENT BR    - O EMPTY -- @# BR -> &br; -->
 
 <!ELEMENT ( %heading )  - -  (%htext;)+>
 
-<!ELEMENT DL    - -  (DT+, DD+)+>
-<!--    structured DL's
-  -->
+<!ELEMENT DL    - -  (DT*, DD?)+>
+<!ATTLIST DL
+	COMPACT (COMPACT) #IMPLIED>
 
 <!ELEMENT DT    - O (%htext)+>
 <!ELEMENT DD    - O (%htext|%block)+>
 
 <!ELEMENT (%list) - -  (LI)+>
 
-<!ATTLIST (%list)
-        COMPACT NAME #IMPLIED -- COMPACT, etc.--
-        >
-
 <!ELEMENT LI    - O (%htext|%block)+>
 
-<!ELEMENT BLOCKQUOTE - - ((%htext|P)+, ADDRESS?)+
+<!ELEMENT BLOCKQUOTE - - (%htext|%block)+ -- @# Hmm... --
         -- for quoting some other source -->
 
-<!ELEMENT ADDRESS - - (%htext;)+>
+<!ELEMENT ADDRESS - - (%htext;|%block)+>
 
-<!ELEMENT PRE - - (#PCDATA | TT | B | I | U | A | P | BR)+>
+<!ELEMENT PRE - - (#PCDATA|%pre-inline|A)+>
 <!ATTLIST PRE
         WIDTH NUMBER #implied
         >
@@ -144,16 +385,72 @@
   "ISO 8879:1986//ENTITIES Added Latin 1//EN">
 %ISOlat1;
 
-<!ENTITY amp "&#38;"     -- ampersand -->
-<!ENTITY gt "&#62;"      -- greater than -->
-<!ENTITY lt "&#60;"      -- less than -->
-<!ENTITY nbsp "&#32;"    --  @@should be NON_BREAKING space -->
-<!-- @@ should add entites for processing instructions
+<!ENTITY #DEFAULT SDATA "&#38;unkown;" --display the markup-->
+<!ENTITY amp CDATA "&#38;"     -- ampersand -->
+<!ENTITY gt CDATA "&#62;"      -- greater than -->
+<!ENTITY lt CDATA "&#60;"      -- less than -->
+<!ENTITY quot CDATA "&#34;"    -- double quote -->
+
+<!-- Processing Entities -->
+
+<!ENTITY nbsp "<? nonbreaking-space>">
+<!-- @# should add entites for processing instructions
 	for line break, centering, etc. -->
 
-<!-- deprecated elements -->
 
-<!ELEMENT (%literal) - -  CDATA>
+<!-- Forms  -->
+<![ %HTML.forms [
 
-<!ELEMENT PLAINTEXT - O EMPTY>
+<!ENTITY % HTTP-Method "(GET | POST)">
+<!ELEMENT FORM - - (%body-content)* -(FORM) +(INPUT|SELECT|TEXTAREA)>
+<!ATTLIST FORM
+	ACTION %URI #REQUIRED
+	METHOD %HTTP-Method #IMPLIED -- @# MAILTO? --
+	ENCTYPE %Content-Type; #IMPLIED
+	>
+
+<!ENTITY % InputType "(TEXT | PASSWORD | CHECKBOX |
+			RADIO | SUBMIT | RESET |
+			IMAGE | HIDDEN )">
+<!ELEMENT INPUT - O EMPTY>
+<!ATTLIST INPUT
+	TYPE %InputType #IMPLIED -- @# defaults to TEXT?? --
+	NAME CDATA #IMPLIED -- required for all but submit and reset --
+	VALUE CDATA #IMPLIED
+	SRC %URI #IMPLIED -- for image inputs -- 
+	CHECKED (CHECKED) #IMPLIED
+	SIZE CDATA #IMPLIED -- @# should be NUMBERS: delimit with space, not comma --
+	MAXLENGTH NUMBER #IMPLIED
+	ALIGN (top|middle|bottom|left|center|right) #IMPLIED --@#supported?--
+	>
+
+<!ELEMENT SELECT - - (OPTION+)>
+<!ATTLIST SELECT
+	NAME CDATA #REQUIRED
+	SIZE NUMBER #IMPLIED
+	MULTIPLE (MULTIPLE) #IMPLIED
+	>
+
+<!ELEMENT OPTION - O (#PCDATA)>
+<!ATTLIST OPTION
+	SELECTED (SELECTED) #IMPLIED
+	VALUE CDATA #IMPLIED
+	>
+
+<!ELEMENT TEXTAREA - - (#PCDATA)>
+<!ATTLIST TEXTAREA
+	NAME CDATA #REQUIRED
+	ROWS NUMBER #REQUIRED -- @#implied? --
+	COLS NUMBER #REQUIRED
+	>
+]]>
+
+<!-- Obsolete Elements  -->
+
+<![ %HTML.litCDATA [ <!ENTITY % lit-content "CDATA"> ]]>
+<!ENTITY % lit-content "RCDATA">
+<!ELEMENT (%literal) - -  %lit-content>
 
+<![ %HTML.PLAINTEXT [
+<!ELEMENT PLAINTEXT - O EMPTY>
+]]>
