HTML DTD enclosed

Dan Connolly (connolly@pixel.convex.com)
Wed, 15 Jul 92 22:35:19 CDT 

Message-Id: <9207160335.AA24812@pixel.convex.com>
To: www-talk@nxoc01.cern.ch
Subject: HTML DTD enclosed
Date: Wed, 15 Jul 92 22:35:19 CDT
From: Dan Connolly <connolly@pixel.convex.com>

<!-- html.dtd - document type declaration subset for
                HyperText Markup Language as defined
		by the World Wide Web project.

	15 Jul 92 by connolly@convex.com

	See also: http://info.cern.ch/hypertext/WWW/MarkUp/Tags.html
  -->

<!--      Terminal symbols        -->

<!ENTITY lt "<">
<!ENTITY gt ">">
<!ENTITY amp "&">

<!-- some existing html uses these. I think they meant
	&amp;
     in stead of 
	&amp.
     -->
<!ENTITY lt. "<">
<!ENTITY gt. ">">
<!ENTITY amp. "&">

<!--    Non-ELEMENT symbols       -->

<!ENTITY % heading "H1|H2|H3|H4|H5|H6" >
<!ENTITY % list "UL|OL|DIR|MENU|DL">
<!ENTITY % text "P|#PCDATA">
<!ENTITY % raw "XMP|LISTING">
<!-- PlainText is more than 8 characters, and changing the
     NAMELEN capacity involves including a lengthy SGML declaration
     in every HTML file. Besides: the semantics of PlainText can't
     be captured by real SGML anyway. -->
<!ENTITY % body "%heading|%list|%text|%raw">

<!--     Document structure       -->

<!ELEMENT HTML	O O  ((TITLE? & NEXTID? & ISINDEX?), BODY, ADDRESS?)>

<!ELEMENT TITLE	- -  (#PCDATA)>

<!ELEMENT NEXTID - O EMPTY >
<!ATTLIST NEXTID N NUMBER #REQUIRED>
<!-- as noted in Tags.html, the conventional <NEXTID 10> is
     illegal. Use <NEXTID N=10> to comply with this DTD. -->

<!ELEMENT ISINDEX - O EMPTY >

<!ELEMENT BODY O O ((%heading), (%body)+) +(A)>
<!-- The BODY element is necessary to avoid mixed content
     in the HTML element. Mixed content and optional elements
     don't mix very well. -->

<!ELEMENT (%heading)	- -  (%text)+
	--Tags.html says titles should fit on one line, but
	the browser handles paragraph breaks inside headings
	gracefully. -->

<!ELEMENT (MENU|UL|OL|DIR) - -  (LI+)>

<!ELEMENT DL	- -  ((DT, DD)+)>

<!ELEMENT LI	- O  (%text)+>
<!ELEMENT DT	- O  (#PCDATA)+>
<!ELEMENT DD	- O  (%text)+>
<!ELEMENT ADDRESS - O (%text)+ +(A)>
<!-- Tags.html says "This tag is for address information, signatures,
etc, normally at the top or bottom of a document." Here, it is only
allowed at the end of a document. -->

<!ELEMENT (%raw) - -  CDATA>
<!-- BUG:
tags.html says that you can put anything but </XMP> in the
text of an XMP element. SGML says that ETAGO, "</" ends a CDATA
section.
-->

<!ELEMENT P	- O  EMPTY -- paragraph SEPARATOR -->

<!-- We could use this to let blank lines separate paragraphs
  <!ENTITY   ptag   STARTTAG "p">
  <!SHORTREF bodymap "&#RS;&#RE;" ptag>
  <!USEMAP   bodymap  BODY;>
  -->

<!ELEMENT A	- -  (%body)+>
<!ATTLIST A
	HREF CDATA #IMPLIED -- attribute values with colons etc. must
				be quoted. --
	NAME CDATA #IMPLIED
	TYPE CDATA #IMPLIED >