hxt 9.0.1 → 9.1.0

raw patch · 73 files changed

+9905/−2235 lines, 73 filesdep ~hxt-charpropertiesPVP ok

version bump matches the API change (PVP)

Dependency ranges changed: hxt-charproperties

API changes (from Hackage documentation)

Files

• examples/arrows/AGentleIntroductionToHXT/PicklerExample/Baseball.hs +209/−201
• examples/arrows/hparser/HXmlParser.hs +1/−2
• examples/arrows/hparser/Makefile +5/−1
• examples/arrows/hparser/example1CRLF.xml +22/−0
• examples/arrows/hparser/lousy.html +4/−3
• examples/arrows/performance/GenDoc.hs +299/−128
• examples/arrows/performance/Makefile +24/−6
• examples/arrows/pickle/PickleTest.hs +55/−26
• examples/xhtml/tmp.xml +4/−0
• examples/xhtml/xhtml-lat1.ent +196/−0
• examples/xhtml/xhtml-special.ent +79/−0
• examples/xhtml/xhtml-symbol.ent +242/−0
• examples/xhtml/xhtml.xml +1484/−0
• examples/xhtml/xhtml1-frameset.dtd +1225/−0
• examples/xhtml/xhtml1-strict.dtd +988/−0
• examples/xhtml/xhtml1-transitional.dtd +1196/−0
• hxt.cabal +21/−4
• src/Control/Arrow/ArrowExc.hs +2/−2
• src/Control/Arrow/ArrowIO.hs +4/−0
• src/Control/Arrow/ArrowIf.hs +11/−0
• src/Control/Arrow/ArrowList.hs +18/−1
• src/Control/Arrow/ArrowNF.hs +26/−3
• src/Control/Arrow/ArrowNavigatableTree.hs +313/−0
• src/Control/Arrow/ArrowState.hs +2/−0
• src/Control/Arrow/ArrowTree.hs +18/−1
• src/Control/Arrow/IOListArrow.hs +18/−11
• src/Control/Arrow/IOStateListArrow.hs +20/−0
• src/Control/Arrow/ListArrow.hs +19/−3
• src/Control/Arrow/ListArrows.hs +6/−0
• src/Control/Arrow/NTreeEdit.hs +46/−0
• src/Control/Arrow/StateListArrow.hs +19/−1
• src/Control/FlatSeq.hs +90/−0
• src/Data/Function/Selector.hs +46/−46
• src/Data/Tree/Class.hs +47/−0
• src/Data/Tree/NTree/Edit.hs +98/−0
• src/Data/Tree/NTree/TypeDefs.hs +26/−45
• src/Data/Tree/NTree/Zipper/TypeDefs.hs +240/−0
• src/Data/Tree/NavigatableTree/Class.hs +77/−0
• src/Data/Tree/NavigatableTree/XPathAxis.hs +128/−0
• src/Text/XML/HXT/Arrow/DTDProcessing.hs +71/−61
• src/Text/XML/HXT/Arrow/DocumentInput.hs +38/−16
• src/Text/XML/HXT/Arrow/DocumentOutput.hs +101/−30
• src/Text/XML/HXT/Arrow/Edit.hs +152/−197
• src/Text/XML/HXT/Arrow/GeneralEntitySubstitution.hs +65/−66
• src/Text/XML/HXT/Arrow/Namespace.hs +23/−22
• src/Text/XML/HXT/Arrow/ParserInterface.hs +4/−56
• src/Text/XML/HXT/Arrow/Pickle.hs +10/−5
• src/Text/XML/HXT/Arrow/Pickle/DTD.hs +2/−0
• src/Text/XML/HXT/Arrow/Pickle/Xml.hs +16/−1
• src/Text/XML/HXT/Arrow/ProcessDocument.hs +65/−30
• src/Text/XML/HXT/Arrow/ReadDocument.hs +41/−42
• src/Text/XML/HXT/Arrow/WriteDocument.hs +10/−16
• src/Text/XML/HXT/Arrow/XmlArrow.hs +103/−2
• src/Text/XML/HXT/Arrow/XmlRegex.hs +2/−2
• src/Text/XML/HXT/Arrow/XmlState/RunIOStateArrow.hs +15/−3
• src/Text/XML/HXT/Arrow/XmlState/TypeDefs.hs +49/−25
• src/Text/XML/HXT/DOM/FormatXmlTree.hs +4/−13
• src/Text/XML/HXT/DOM/Interface.hs +1/−0
• src/Text/XML/HXT/DOM/MimeTypes.hs +3/−0
• src/Text/XML/HXT/DOM/QualifiedName.hs +262/−189
• src/Text/XML/HXT/DOM/ShowXml.hs +327/−286
• src/Text/XML/HXT/DOM/TypeDefs.hs +100/−57
• src/Text/XML/HXT/DOM/XmlNode.hs +207/−40
• src/Text/XML/HXT/DTDValidation/DocTransformation.hs +3/−3
• src/Text/XML/HXT/DTDValidation/Validation.hs +5/−0
• src/Text/XML/HXT/IO/GetFILE.hs +12/−23
• src/Text/XML/HXT/Parser/HtmlParsec.hs +299/−168
• src/Text/XML/HXT/Parser/XmlCharParser.hs +71/−21
• src/Text/XML/HXT/Parser/XmlDTDParser.hs +61/−49
• src/Text/XML/HXT/Parser/XmlDTDTokenParser.hs +20/−19
• src/Text/XML/HXT/Parser/XmlParsec.hs +260/−175
• src/Text/XML/HXT/Parser/XmlTokenParser.hs +174/−133
• src/Text/XML/HXT/Version.hs +1/−1

@@ -23,7 +23,7 @@     { sYear    :: Int     , sLeagues :: Leagues     }-	      deriving (Show, Eq)+              deriving (Show, Eq)  type Leagues   = Map String Divisions @@ -34,8 +34,8 @@     , city     :: String     , players  :: [Player]     }-	    deriving (Show, Eq)-	     +            deriving (Show, Eq)+              data Player = Player     { firstName :: String     , lastName  :: String@@ -44,7 +44,7 @@     , hits      :: Maybe Int     , era       :: Maybe Float     }-	      deriving (Show, Eq)+              deriving (Show, Eq)  -- ------------------------------------------------------------ -- the pickler instance declarations@@ -64,73 +64,81 @@  -- the XML root element -xpSeason	:: PU Season+xpSeason        :: PU Season xpSeason     = xpElem "SEASON" $       xpWrap ( uncurry Season-	     , \ s -> (sYear s, sLeagues s)) $+             , \ s -> (sYear s, sLeagues s)) $       xpPair (xpAttr "YEAR" xpickle) xpLeagues -xpLeagues	:: PU Leagues+xpLeagues       :: PU Leagues xpLeagues     = xpWrap ( fromList-	     , toList ) $+             , toList ) $       xpList $       xpElem "LEAGUE" $       xpPair (xpAttr "NAME" xpText) xpDivisions -xpDivisions	:: PU Divisions+xpDivisions     :: PU Divisions xpDivisions     = xpWrap ( fromList-	     , toList-	     ) $+             , toList+             ) $       xpList $       xpElem "DIVISION" $-      xpPair (xpAttr "NAME" xpText) xpickle+      xpPair (xpAttr "NAME" xpText)+             xpickle -xpTeam	:: PU Team+xpTeam  :: PU Team xpTeam     = xpElem "TEAM" $       xpWrap ( uncurry3 Team-	     , \ t -> (teamName t, city t, players t)) $-      xpTriple (xpAttr "NAME" xpText) (xpAttr "CITY" xpText) (xpList xpickle)+             , \ t -> (teamName t, city t, players t)+             ) $+      xpTriple (xpAttr "NAME" xpText)+               (xpAttr "CITY" xpText)+               (xpList xpickle) -xpPlayer	:: PU Player+xpPlayer        :: PU Player xpPlayer     = xpElem "PLAYER" $-      xpWrap ( \ ((f,l,p),(a,h,e)) -> Player f l p a h e-	     , \ t -> ((firstName t, lastName t, position t),(atBats t, hits t, era t))) $-      xpPair (xpTriple (xpAttr "GIVEN_NAME" xpText)-	               (xpAttr "SURNAME"    xpText)-	               (xpAttr "POSITION"   xpText))-             (xpTriple (xpOption (xpAttr "AT_BATS" xpickle))-	               (xpOption (xpAttr "HITS"    xpickle))-	               (xpOption (xpAttr "ERA"     xpPrim )))+      xpWrap ( \ ((f,l,p,a,h,e)) -> Player f l p a h e+             , \ t -> (firstName t, lastName t+                      , position t, atBats t+                      , hits t, era t+                      )+             ) $+      xp6Tuple (xpAttr "GIVEN_NAME" xpText)+               (xpAttr "SURNAME"    xpText)+               (xpAttr "POSITION"   xpText)+               (xpOption (xpAttr "AT_BATS" xpickle))+               (xpOption (xpAttr "HITS"    xpickle))+               (xpOption (xpAttr "ERA"     xpPrim ))   -- ------------------------------------------------------------  -- a simple pickle/unpickle application -main	:: IO ()+main    :: IO () main     = do       runX ( xunpickleDocument xpSeason [ withValidate no-					, withTrace 1-					, withRemoveWS yes-					, withPreserveComment no-					] "simple2.xml"-	     >>>-	     processSeason-	     >>>-	     xpickleDocument xpSeason [ withIndent yes-				      ] "new-simple2.xml"-	   )+                                        , withTrace 1+                                        , withRemoveWS yes+                                        , withPreserveComment no+                                        ] "simple2.xml"+             >>>+             processSeason+             >>>+             xpickleDocument xpSeason [ withIndent yes+                                      ] "new-simple2.xml"+           )       return ()  -- the dummy for processing the unpickled data -processSeason	:: IOSArrow Season Season+processSeason   :: IOSArrow Season Season processSeason     = arrIO ( \ x -> do {print x ; return x}) @@ -138,175 +146,175 @@  -- the internal data of "simple2.xml" -season1998	:: Season+season1998      :: Season season1998     = Season       { sYear = 1998       , sLeagues = fromList-	[ ( "American League"-	  , fromList-	    [ ( "Central"-	      , [ Team { teamName = "White Sox"-		       , city = "Chicago"-		       , players = []}-		, Team { teamName = "Royals"-		       , city = "Kansas City"-		       , players = []}-		, Team { teamName = "Tigers"-		       , city = "Detroit"-		       , players = []}-		, Team { teamName = "Indians"-		       , city = "Cleveland"-		       , players = []}-		, Team { teamName = "Twins"-		       , city = "Minnesota"-		       , players = []}-		])-	    , ( "East"-	      , [ Team { teamName = "Orioles"-		       , city = "Baltimore"-		       , players = []}-		, Team { teamName = "Red Sox"-		       , city = "Boston"-		       , players = []}-		, Team { teamName = "Yankees"-		       , city = "New York"-		       , players = []}-		, Team { teamName = "Devil Rays"-		       , city = "Tampa Bay"-		       , players = []}-		, Team { teamName = "Blue Jays"-		       , city = "Toronto"-		       , players = []}-		])-	    , ( "West"-	      , [ Team { teamName = "Angels"-		       , city = "Anaheim"-		       , players = []}-		, Team { teamName = "Athletics"-		       , city = "Oakland"-		       , players = []}-		, Team { teamName = "Mariners"-		       , city = "Seattle"-		       , players = []}-		, Team { teamName = "Rangers"-		       , city = "Texas"-		       , players = []}-		])-	    ])-	, ( "National League"-	  , fromList-	    [ ( "Central"-	      , [ Team { teamName = "Cubs"-		       , city = "Chicago"-		       , players = []}-		, Team { teamName = "Reds"-		       , city = "Cincinnati"-		       , players = []}-		, Team { teamName = "Astros"-		       , city = "Houston"-		       , players = []}-		, Team { teamName = "Brewers"-		       , city = "Milwaukee"-		       , players = []}-		, Team { teamName = "Pirates"-		       , city = "Pittsburgh"-		       , players = []}-		, Team { teamName = "Cardinals"-		       , city = "St. Louis"-		       , players = []}-		])-	    , ( "East"-	      , [ Team { teamName = "Braves"-		       , city = "Atlanta"-		       , players =-			 [ Player { firstName = "Marty"-				  , lastName = "Malloy"-				  , position = "Second Base"-				  , atBats = Just 28-				  , hits = Just 5-				  , era = Nothing}-			 , Player { firstName = "Ozzie"-				  , lastName = "Guillen"-				  , position = "Shortstop"-				  , atBats = Just 264-				  , hits = Just 73-				  , era = Nothing}-			 , Player { firstName = "Danny"-				  , lastName = "Bautista"-				  , position = "Outfield"-				  , atBats = Just 144-				  , hits = Just 36-				  , era = Nothing}-			 , Player { firstName = "Gerald"-				  , lastName = "Williams"-				  , position = "Outfield"-				  , atBats = Just 266-				  , hits = Just 81-				  , era = Nothing}-			 , Player { firstName = "Tom"-				  , lastName = "Glavine"-				  , position = "Starting Pitcher"-				  , atBats = Nothing-				  , hits = Nothing-				  , era = Just 2.47}-			 , Player { firstName = "Javier"-				  , lastName = "Lopez"-				  , position = "Catcher"-				  , atBats = Just 489-				  , hits = Just 139-				  , era = Nothing}-			 , Player { firstName = "Ryan"-				  , lastName = "Klesko"-				  , position = "Outfield"-				  , atBats = Just 427-				  , hits = Just 117-				  , era = Nothing}-			 , Player { firstName = "Andres"-				  , lastName = "Galarraga"-				  , position = "First Base"-				  , atBats = Just 555-				  , hits = Just 169-				  , era = Nothing}-			 , Player { firstName = "Wes"-				  , lastName = "Helms"-				  , position = "Third Base"-				  , atBats = Just 13-				  , hits = Just 4-				  , era = Nothing}-			 ]}-		, Team { teamName = "Marlins"-		       , city = "Florida"-		       , players = []}-		, Team { teamName = "Expos"-		       , city = "Montreal"-		       , players = []}-		, Team { teamName = "Mets"-		       , city = "New York"-		       , players = []}-		, Team { teamName = "Phillies"-		       , city = "Philadelphia"-		       , players = []}-		])-	    , ( "West"-	      , [ Team { teamName = "Diamondbacks"-		       , city = "Arizona"-		       , players = []}-		, Team { teamName = "Rockies"-		       , city = "Colorado"-		       , players = []}-		, Team { teamName = "Dodgers"-		       , city = "Los Angeles"-		       , players = []}-		, Team { teamName = "Padres"-		       , city = "San Diego"-		       , players = []}-		, Team { teamName = "Giants"-		       , city = "San Francisco"-		       , players = []}-		])-	    ])-	]+        [ ( "American League"+          , fromList+            [ ( "Central"+              , [ Team { teamName = "White Sox"+                       , city = "Chicago"+                       , players = []}+                , Team { teamName = "Royals"+                       , city = "Kansas City"+                       , players = []}+                , Team { teamName = "Tigers"+                       , city = "Detroit"+                       , players = []}+                , Team { teamName = "Indians"+                       , city = "Cleveland"+                       , players = []}+                , Team { teamName = "Twins"+                       , city = "Minnesota"+                       , players = []}+                ])+            , ( "East"+              , [ Team { teamName = "Orioles"+                       , city = "Baltimore"+                       , players = []}+                , Team { teamName = "Red Sox"+                       , city = "Boston"+                       , players = []}+                , Team { teamName = "Yankees"+                       , city = "New York"+                       , players = []}+                , Team { teamName = "Devil Rays"+                       , city = "Tampa Bay"+                       , players = []}+                , Team { teamName = "Blue Jays"+                       , city = "Toronto"+                       , players = []}+                ])+            , ( "West"+              , [ Team { teamName = "Angels"+                       , city = "Anaheim"+                       , players = []}+                , Team { teamName = "Athletics"+                       , city = "Oakland"+                       , players = []}+                , Team { teamName = "Mariners"+                       , city = "Seattle"+                       , players = []}+                , Team { teamName = "Rangers"+                       , city = "Texas"+                       , players = []}+                ])+            ])+        , ( "National League"+          , fromList+            [ ( "Central"+              , [ Team { teamName = "Cubs"+                       , city = "Chicago"+                       , players = []}+                , Team { teamName = "Reds"+                       , city = "Cincinnati"+                       , players = []}+                , Team { teamName = "Astros"+                       , city = "Houston"+                       , players = []}+                , Team { teamName = "Brewers"+                       , city = "Milwaukee"+                       , players = []}+                , Team { teamName = "Pirates"+                       , city = "Pittsburgh"+                       , players = []}+                , Team { teamName = "Cardinals"+                       , city = "St. Louis"+                       , players = []}+                ])+            , ( "East"+              , [ Team { teamName = "Braves"+                       , city = "Atlanta"+                       , players =+                         [ Player { firstName = "Marty"+                                  , lastName = "Malloy"+                                  , position = "Second Base"+                                  , atBats = Just 28+                                  , hits = Just 5+                                  , era = Nothing}+                         , Player { firstName = "Ozzie"+                                  , lastName = "Guillen"+                                  , position = "Shortstop"+                                  , atBats = Just 264+                                  , hits = Just 73+                                  , era = Nothing}+                         , Player { firstName = "Danny"+                                  , lastName = "Bautista"+                                  , position = "Outfield"+                                  , atBats = Just 144+                                  , hits = Just 36+                                  , era = Nothing}+                         , Player { firstName = "Gerald"+                                  , lastName = "Williams"+                                  , position = "Outfield"+                                  , atBats = Just 266+                                  , hits = Just 81+                                  , era = Nothing}+                         , Player { firstName = "Tom"+                                  , lastName = "Glavine"+                                  , position = "Starting Pitcher"+                                  , atBats = Nothing+                                  , hits = Nothing+                                  , era = Just 2.47}+                         , Player { firstName = "Javier"+                                  , lastName = "Lopez"+                                  , position = "Catcher"+                                  , atBats = Just 489+                                  , hits = Just 139+                                  , era = Nothing}+                         , Player { firstName = "Ryan"+                                  , lastName = "Klesko"+                                  , position = "Outfield"+                                  , atBats = Just 427+                                  , hits = Just 117+                                  , era = Nothing}+                         , Player { firstName = "Andres"+                                  , lastName = "Galarraga"+                                  , position = "First Base"+                                  , atBats = Just 555+                                  , hits = Just 169+                                  , era = Nothing}+                         , Player { firstName = "Wes"+                                  , lastName = "Helms"+                                  , position = "Third Base"+                                  , atBats = Just 13+                                  , hits = Just 4+                                  , era = Nothing}+                         ]}+                , Team { teamName = "Marlins"+                       , city = "Florida"+                       , players = []}+                , Team { teamName = "Expos"+                       , city = "Montreal"+                       , players = []}+                , Team { teamName = "Mets"+                       , city = "New York"+                       , players = []}+                , Team { teamName = "Phillies"+                       , city = "Philadelphia"+                       , players = []}+                ])+            , ( "West"+              , [ Team { teamName = "Diamondbacks"+                       , city = "Arizona"+                       , players = []}+                , Team { teamName = "Rockies"+                       , city = "Colorado"+                       , players = []}+                , Team { teamName = "Dodgers"+                       , city = "Los Angeles"+                       , players = []}+                , Team { teamName = "Padres"+                       , city = "San Diego"+                       , players = []}+                , Team { teamName = "Giants"+                       , city = "San Francisco"+                       , players = []}+                ])+            ])+        ]       }  -- ------------------------------------------------------------

@@ -125,8 +125,7 @@       ++       showOptions       ++-      [ Option "f"      ["output-file"] (ReqArg  (withSysAttr "output-file") "FILE") "output file for resulting document (default: stdout)"-      , Option "q"      ["no-output"]   (NoArg $  withSysAttr "no-output"      "1")   "no output of resulting document"+      [ Option "q"      ["no-output"]   (NoArg $  withSysAttr "no-output"      "1")   "no output of resulting document"       , Option "x"      ["action"]      (ReqArg  (withSysAttr "action")   "ACTION")   "actions are: only-text, indent, no-op"       ]       -- the last 2 option values will be stored by withAttr in the system key-value list

@@ -32,6 +32,7 @@ 		$(MAKE) test0 test1 test2 test3 test4  EX1		= ./example1.xml+EX1a		= ./example1CRLF.xml EXi		= ./invalid.xml EX2		= ../../xhtml/xhtml.xml EX3		= ./namespace0.xml@@ -76,6 +77,9 @@ 		@sleep 2 ; echo ; echo "===> once again, but without any markup" ; echo ; sleep 2 		$(prog) --action=only-text --output-encoding=ISO-8859-1 $(EX1) 		@echo+		@sleep 2 ; echo ; echo "===> same source, but with CRLF, parser will emit UTF-8" ; echo ; sleep 2+		$(prog) --output-encoding=UTF-8 $(EX1a)+		@echo  test2		: 		@echo "===> the source of a xhtml document" ; echo ; sleep 2@@ -110,7 +114,7 @@ 		@echo "===> the source of another lousy html document containing empty elements" ; echo ; sleep 2 		cat $(EX4a) 		@sleep 2 ; echo ; echo "===> parser accepts this document and tries to format this as a HTML document without any dangarous empty elements" ; echo ; sleep 2-		$(prog) --indent --preserve-comment --parse-html --output-html --no-empty-elements $(EX4a)+		$(prog) --indent --preserve-comment --parse-html --output-xhtml $(EX4a) 		@echo  dist		:

@@ -0,0 +1,22 @@+<?xml version="1.0" encoding="ISO-8859-1" ?>
+
+<!DOCTYPE a [
+<!ATTLIST a  att1  NMTOKENS  #IMPLIED
+             att2  ID        #REQUIRED>
+<!ATTLIST b  btt2  ID        #REQUIRED
+             btt3  IDREF     #REQUIRED>
+<!ELEMENT a  (b, cü?)>
+<!ELEMENT b  EMPTY>
+<!ELEMENT cü (#PCDATA)>
+]>
+
+<?pi a processing instruction?>
+
+<a att1=" test
+          äöüß
+          test "
+   att2="root"
+>
+    <b btt2="b1" btt3="root"/>
+    <cü>hello world äöüß test</cü>
+</a>

@@ -21,6 +21,7 @@     </table>      <xxx>xxx</xxx>+    <? abc + xyz ?>     <yyy a=b/>       <![CDATA[a CDATA       section with some unescaped chars@@ -30,8 +31,8 @@       &Auml; &Ouml; &Uuml; &#65;     <address><a href="mailto:uwe@muehle.welt.all">Uwe 		Schmidt</a></address>-<!-- Created: Tue Apr 29 16:07:57 CEST 2003 -->+<!-- Created: -- Tue Apr 29 16:07:57 CEST 2003 --> <!-- hhmts start -->-Last modified: Tue Aug 17 15:56:59 CEST 2010-<!-- hhmts end -->+Last modified: Thu Feb  3 13:27:19 CET 2011+<!-- hhmts end -> </html>

@@ -1,27 +1,41 @@ {-# LANGUAGE BangPatterns#-}+{-# OPTIONS_GHC -fno-warn-incomplete-patterns #-}  -- ----------------------------------------  module Main where -import Text.XML.HXT.Core-import Text.XML.HXT.TagSoup+import Text.XML.HXT.Core hiding (trace)+-- import Text.XML.HXT.TagSoup+-- import Text.XML.HXT.Expat +import Data.Char (isDigit)+import Data.List (foldl')+ import Data.String.Unicode     ( unicodeToXmlEntity     )  import Control.Monad.State.Strict hiding (when) +import Control.DeepSeq+import Control.FlatSeq+ import Data.Maybe -import System.IO			-- import the IO and commandline option stuff+import System.IO  hiding (utf8)                      -- import the IO and commandline option stuff import System.Environment --- ----------------------------------------+import qualified Text.XML.HXT.DOM.XmlNode as XN+import qualified Data.Tree.Class as T+import Data.Tree.NTree.TypeDefs -- as T -main	:: IO ()+import           Debug.Trace++-- ------------------------------------------------------------++main    :: IO () main     = do       p <- getProgName@@ -30,18 +44,19 @@       main' p i     where     main' p' = fromMaybe main0 . lookup (pn p') $ mpt-    mpt = [ ("GenDoc",	   main1)-	  , ("ReadDoc",    main2)-	  , ("PruneRight", main3 False)-	  , ("PruneLeft",  main3 True)-	  , ("MemTest",    main4)-	 ]+    mpt = [ ("GenDoc",     main1)+          , ("ReadDoc",    main2)+          , ("PruneRight", main3 False)+          , ("PruneLeft",  main3 True)+          , ("MemTest",    main4 True)+          , ("MemTest1",   main4 False)+         ]  -- ----------------------------------------  -- generate a document containing a binary tree of 2^i leafs (= 2^(i-1) XML elements) -main1	:: Int -> IO ()+main1   :: Int -> IO () main1 i     = runX (genDoc i (fn i))       >> return ()@@ -50,62 +65,101 @@  -- read a document containing a binary tree of 2^i leafs -main2	:: Int -> IO ()+main2   :: Int -> IO () main2 i     = do-      [x] <- runX (readDoc (fn i)-		   >>>-		   traceMsg 1 "start unpickle"-		   >>>-		   unpickleTree-		   >>>-		   traceMsg 1 "start fold"-		   >>>-		   arr (foldT1 max)-		  )+      [x] <- runX (setTraceLevel 2+                   >>>+                   readDoc (fn i)+                   >>>+{-+                   traceMsg 1 "start rnfA"+                   >>>+                   rnfA this+                   >>>+-}+                   traceMsg 1 "start unpickle"+                   >>>+                   unpickleTree+                   >>>+                   traceMsg 1 "start fold"+                   >>>+                   arr (foldT1 max)+                  )       putStrLn ( "maximum value in tree is " ++ show x ++-		 ", expected value was " ++ show ((2::Int)^i)-	       )+                 ", expected value was " ++ show ((2::Int)^i)+               )  -- ----------------------------------------  -- test on lazyness, is the whole tree read or only the first child of every child node? -main3	:: Bool -> Int -> IO ()+main3   :: Bool -> Int -> IO () main3 l i     = do       [t] <- runX ( readDoc (fn i)-		    >>>-		    fromLA (xshow ( getChildren-				    >>>-				    if l then pruneForkLeft else pruneForkRight-				  )-			   )-		  )+                    >>>+                    fromLA (xshow ( getChildren+                                    >>>+                                    if l then pruneForkLeft else pruneForkRight+                                  )+                           )+                  )       putStrLn ("pruned binary tree is : " ++ show t)  -- ---------------------------------------- -main4	:: Int -> IO ()-main4 i+main4   :: Bool -> Int -> IO ()+main4 wnf i     = do       [x] <- runX ( setTraceLevel 1-		    >>>-		    traceMsg 1 ("generate tree of depth " ++ show i)-		    >>>-		    fromLA (genTree 0 i)-		    >>>-		    traceMsg 1 ("compute maximum and minimum")-		    >>>-		    fromLA ( foldBTree maximum &&& foldBTree minimum )	-- 2 traversals: complete tree in mem-		    >>>-		    arr2 (\ ma mi -> "maximum value = " ++ show ma ++ ", minimum = " ++ show mi )-		    >>>-		    traceValue 1 id-		  )+                    >>>+                    traceMsg 1 ("generate tree of depth " ++ show i)+                    >>>+                    ( if wnf+                      then fromLA (genTree'' 0 i)+                      else fromLA (rnfA $ genTree   0 i)+                    )+                    >>>+                    perform ( traceMsg 1 ("deep hasAttrValue")+                              >>>+                              deep (hasName "leaf" >>> hasAttrValue "value" (== "1"))+                              >>>+                              getAttrValue "value"+                              >>>+                              arrIO putStrLn+                            )+                    >>>+                    perform ( traceMsg 1 ("deep hasAttrValue")+                              >>>+                              deep (hasName "leaf" >>> hasAttrValue "value" (== "1"))+                              >>>+                              getAttrValue "value"+                              >>>+                              arrIO putStrLn+                            )+                    {-+                    perform (traceMsg 1 ("write doc")+                             >>>+                             putDoc "./tmp.xml"+                            )+                    >>>+                    traceMsg 1 ("compute maximum and minimum")+                    >>>+                    fromLA ( foldBTree maximum &&& foldBTree minimum )  -- 2 traversals: complete tree in mem+                    >>>+                    arr2 (\ ma mi -> "maximum value = " ++ show ma ++ ", minimum = " ++ show mi )+                    >>>+                    traceValue 1 id+                     -}+                    >>>+                    traceMsg 1 "done"+                    >>>+                    constA "0"+                  )       putStrLn x -foldBTree	:: ([Int] -> Int) -> LA XmlTree Int+foldBTree       :: ([Int] -> Int) -> LA XmlTree Int foldBTree f     = choiceA       [ hasName "leaf" :-> ( getAttrValue "value" >>^ read )@@ -117,7 +171,7 @@  -- just to check how much memory is used for the tree -main0	:: Int -> IO ()+main0   :: Int -> IO () main0 i     = do       let t = mkBTree i@@ -127,117 +181,225 @@  -- ---------------------------------------- -pn	:: String -> String-pn	= reverse . takeWhile (/= '/') . reverse+pn      :: String -> String+pn      = reverse . takeWhile (/= '/') . reverse -fn	:: Int -> String-fn	= ("tree-" ++) . (++ ".xml") . reverse . take 4 . reverse . ((replicate 4 '0') ++ ) . show+fn      :: Int -> String+fn      = ("tree-" ++) . (++ ".xml") . reverse . take 4 . reverse . ((replicate 4 '0') ++ ) . show  -- ---------------------------------------- -genTree	:: Int -> Int -> LA XmlTree XmlTree+genTree :: Int -> Int -> LA XmlTree XmlTree genTree !n !d-    | d == 0	= aelem "leaf" [sattr "value" (show (n + 1))]-    | otherwise	= selem "fork" [ genTree (2*n)   (d-1)-			       , genTree (2*n+1) (d-1)-			       ]+    | d == 0    = aelem "leaf" [sattr "value" (show (n + 1))]+    | otherwise = selem "fork" [ genTree (2*n)   (d-1)+                               , genTree (2*n+1) (d-1)+                               ]  -- ---------------------------------------- -genDoc		:: Int -> String -> IOSArrow b XmlTree-genDoc d out    = constA (mkBTree d)-		  >>>-		  xpickleVal xpickle-		  >>>-		  putDoc out+genTree'        :: Int -> Int -> LA XmlTree XmlTree+genTree' !n !d+    | d == 0    = aelem' "leaf" [sattr' "value" (show (n + 1))]+    | otherwise = selem' "fork" [ genTree' (2*n)   (d-1)+                                , genTree' (2*n+1) (d-1)+                                ]  -- ---------------------------------------- -readDoc	:: String -> IOSArrow b XmlTree+genTree''       :: Int -> Int -> LA XmlTree XmlTree+genTree'' !n !d+    | d == 0    = rwnfA $+                  -- trace ("+leaf " ++ show (n+1)) $+                  aelem "leaf" $+                  -- trace ("++leaf " ++ show (n+1)) $+                  [rwnf2A $+                   -- trace ("+valu " ++ show (n+1)) $+                   sattr "value" $+                   show $+                   -- trace ("++valu " ++ show (n+1)) $+                   (n + 1)+                  ]+    | otherwise = rwnfA $+                  -- trace ("+fork " ++ show (n+1)) $+                  selem "fork" $+                  -- trace ("++fork " ++ show (n+1)) $+                  [ genTree'' (2*n)   (d-1)+                  , genTree'' (2*n+1) (d-1)+                  ]++-- ----------------------------------------++-- (hopefully) strict constructors++mkText' s               = rwnf s `seq`+                          T.mkLeaf tn+    where+    tn = XN.mkText s++mkAttr' n al            = n        `seq`+                          rwnf al `seq`+                          T.mkTree an al+    where+    an = XN.mkAttrNode n++mkElem' n al cl         = n        `seq`+                          en       `seq`+                          rwnf al `seq`+                          rwnf cl `seq`+                          T.mkTree en cl+    where+    en = XN.mkElementNode n al++-- ----------------------------------------+-- strict arrows++mkElement'              :: String -> LA n XmlTree -> LA n XmlTree -> LA n XmlTree+mkElement' n af cf      = (listA af &&& listA cf)+                          >>>+                          arr2 (mkElem' (mkName n))++selem'                  :: String -> [LA n XmlTree] -> LA n XmlTree+selem' n cfs            = mkElement' n none (catA cfs)++aelem'                  :: String -> [LA n XmlTree] -> LA n XmlTree+aelem' n afs            = mkElement' n (catA afs) none++sattr'                  :: String -> String -> LA n XmlTree+sattr' an av            = constA (mkAttr' (mkName an) [mkText' av])++-- ----------------------------------------++genDoc          :: Int -> String -> IOSArrow b XmlTree+genDoc d out    = constA (let t = mkBTree d in rnf t `seq` t)+                  >>>+                  xpickleVal xpickle+                  >>>+{-+                  strictA+                  >>>+                  perform (writeBinaryValue (out ++ ".bin"))+                  >>>+                  readBinaryValue (out ++ ".bin")+                  >>>+                  strictA+                  >>>+-}+                  putDoc out++-- ----------------------------------------++readDoc :: String -> IOSArrow b XmlTree readDoc src-    = readDocument [ withTagSoup-		   , withParseHTML no-		   , withRemoveWS yes-		   , withInputEncoding isoLatin1-		   , withWarnings no-		   , withTrace 1-		   , withStrictInput no-		   ] src+    = readDocument [ withParseHTML no+                   , withTrace 2+                   , withValidate no+                   , withInputEncoding isoLatin1+                   , withWarnings yes+                   , withStrictInput no+                   , withCanonicalize yes+                   , withRemoveWS no+                   -- , withExpat yes+                   -- , withTagSoup+                   ] src+{-       >>>-      processChildren (isElem `guards` this)-+      perform ( writeDocument [ withShowTree yes+                              , withOutputHTML+                              ] ""+              )+      >>>+      perform ( writeDocument [ withShowTree no+                              , withOutputHTML+                              ] ""+              )+-} -- ---------------------------------------- -unpickleTree	:: ArrowXml a => a XmlTree BTree-unpickleTree	= xunpickleVal xpickle+unpickleTree    :: ArrowXml a => a XmlTree BTree+unpickleTree    = xunpickleVal xpickle  -- ---------------------------------------- -pruneForkRight	:: LA XmlTree XmlTree+pruneForkRight  :: LA XmlTree XmlTree pruneForkRight     = ( replaceChildren-	( ( getChildren >>. take 1 )-	  >>>-	  pruneForkRight-	)+        ( ( getChildren >>. take 1 )+          >>>+          pruneForkRight+        )       ) `when` (hasName "fork")  -pruneForkLeft	:: LA XmlTree XmlTree+pruneForkLeft   :: LA XmlTree XmlTree pruneForkLeft     = ( replaceChildren-	( ( getChildren >>. drop 1 )-	  >>>-	  pruneForkLeft-	)+        ( ( getChildren >>. drop 1 )+          >>>+          pruneForkLeft+        )       ) `when` (hasName "fork")  -- ---------------------------------------- -type Counter a	= State Int a+type Counter a  = State Int a -incr	:: Counter Int-incr	= do-	  modify (+1)-	  get+incr    :: Counter Int+incr    = do+          modify (+1)+          get  -- ---------------------------------------- -data BTree	= Leaf Int-		| Fork BTree BTree-		  deriving (Show)+data BTree      = Leaf Int+                | Fork BTree BTree+                  deriving (Show) +instance NFData BTree where+    rnf (Leaf i)	= rnf i+    rnf (Fork t1 t2)	= rnf t1 `seq` rnf t2+ instance XmlPickler BTree where     xpickle = xpAlt tag ps-	where-	tag (Leaf _	) = 0-	tag (Fork _ _	) = 1-	ps = [ xpWrap ( Leaf, \ (Leaf i) -> i)-	       ( xpElem "leaf" $ xpAttr "value" $ xpickle )+        where+        tag (Leaf _     ) = 0+        tag (Fork _ _   ) = 1 -	     , xpWrap ( uncurry Fork, \ (Fork l r) -> (l, r))-	       ( xpElem "fork" $ xpPair xpickle xpickle )-	       ]+        ps = [ xpWrap ( Leaf, \ (Leaf i) -> i)+               ( xpElem "leaf" $ xpAttr "value" $ xpInt ) -- xpWrap (const 0, const ">&\"äöü") $ xpText )+             , xpWrap ( uncurry Fork, \ (Fork l r) -> (l, r))+               ( xpElem "fork" $ xpPair xpickle xpickle )+             ]  -- ---------------------------------------- -mkBTree		:: Int -> BTree-mkBTree	depth	= evalState (mkT depth) 0+mkBTree         :: Int -> BTree+mkBTree depth   = evalState (mkT depth) 0+    where+    mkT :: Int -> Counter BTree+    mkT 0 = do+            i <- incr+            return (Leaf i)+    mkT n = do+            l <- mkT (n-1)+            r <- mkT (n-1)+            return (Fork l r) -mkT	:: Int -> Counter BTree-mkT 0	= do-	  i <- incr-	  return (Leaf i)-mkT n	= do-	  l <- mkT (n-1)-	  r <- mkT (n-1)-	  return (Fork l r)+bTreeToNTree	:: BTree -> NTree Int+bTreeToNTree (Leaf i)	= NTree i []+bTreeToNTree (Fork l r) = NTree j [l',r']+    where+    l' = bTreeToNTree l+    r' = bTreeToNTree r+    j  = T.getNode l' + T.getNode r' +mkNTree = bTreeToNTree . mkBTree+ -- ---------------------------------------- -foldT1	:: (Int -> Int -> Int) -> BTree -> Int-foldT1 _  (Leaf v)	= v-foldT1 op (Fork l r)	= foldT1 op l `op` foldT1 op r+foldT1  :: (Int -> Int -> Int) -> BTree -> Int+foldT1 _  (Leaf v)      = v+foldT1 op (Fork l r)    = foldT1 op l `op` foldT1 op r  -- ---------------------------------------- @@ -248,8 +410,17 @@ -- docs with latin1 encoding. Here ist done even with ASCCI -- every none ASCII char is represented by a char ref (&nnn;) -putDoc	:: String -> IOStateArrow s XmlTree XmlTree+putDoc  :: String -> IOStateArrow s XmlTree XmlTree putDoc dst+    = writeDocument [ withOutputEncoding isoLatin1+                    , withOutputXML+                    ] dst++-- ----------------------------------------+{-++putDoc  :: String -> IOStateArrow s XmlTree XmlTree+putDoc dst     = addXmlPi       >>>       addXmlPiEncoding isoLatin1@@ -262,16 +433,16 @@       >>>       none       where-      isStdout	= null dst || dst == "-"+      isStdout  = null dst || dst == "-" -      hPutDocument	:: (Handle -> IO()) -> IO()+      hPutDocument      :: (Handle -> IO()) -> IO()       hPutDocument action-	  | isStdout-	      = action stdout-	  | otherwise-	      = do-		handle <- openBinaryFile dst WriteMode-		action handle-		hClose handle-+          | isStdout+              = action stdout+          | otherwise+              = do+                handle <- openBinaryFile dst WriteMode+                action handle+                hClose handle+-} -- ----------------------------------------

@@ -11,16 +11,21 @@ CNT		= 3  ropts		= +RTS -s -RTS +popts		= +RTS -P -hy -RTS  prog		= ./GenDoc prog2		= ./ReadDoc prog3		= ./PruneRight prog4		= ./PruneLeft prog5		= ./MemTest-progs		= $(prog) $(prog2) $(prog3) $(prog4) $(prog5)+prog6		= ./MemTest1+progs		= $(prog) $(prog2) $(prog3) $(prog4) $(prog5) $(prog6)  all		: $(progs) +prof		:+		$(MAKE) all PKGFLAGS="-prof -auto-all -caf-all"+ $(prog)		: $(prog).hs 		$(GHC) --make -o $@ $< @@ -39,6 +44,9 @@ $(prog5)	: $(prog) 		ln -f $(prog) $(prog5) +$(prog6)	: $(prog)+		ln -f $(prog) $(prog6)+ # generate and read documents containing a binary tree # with 2^i leaf nodes containing the numbers 1 to 2^i # for i up to at least 22 (8M XML elements) output works fine@@ -48,6 +56,7 @@ # these tests have run on a box with 1Gb memory  tests		= 2 3 10 11 12+ptests          = 16  test		: $(prog) 		$(MAKE) genfiles   tests="$(tests)"@@ -58,11 +67,20 @@ perftest	: $(prog) 		$(MAKE) test tests="2 3 10 11 12 13 14 15 16 17 18 19 20" +pgenfiles	:+		rm -f $(prog).aux $(prog).hp $(prog).ps $(prog).prof+		$(MAKE) genfiles ropts="$(popts)" tests=$(ptests)+		hp2ps -c $(prog).hp++preadfiles	:+		$(MAKE) readfiles ropts="$(popts)" tests=$(ptests)+		hp2ps -c $(prog2).hp+ genfiles	: 		@for i in $(tests) ; \ 		do \ 		echo time $(prog) $(ropts) $$i ; \-		time $(prog) $$i ; \+		time $(prog) $(ropts) $$i ; \ 		ls -l tree-*$$i.xml ; \ 		echo ; \ 		done@@ -71,7 +89,7 @@ 		@for i in $(tests) ; \ 		do \ 		echo time $(prog2) $(ropts) $$i ; \-		time $(prog2) $$i ; \+		time $(prog2) $(ropts) $$i ; \ 		echo ; \ 		done @@ -79,7 +97,7 @@ 		@for i in $(tests) ; \ 		do \ 		echo time $(prog3) $(ropts) $$i ; \-		time $(prog3) $$i ; \+		time $(prog3)  $(ropts) $$i ; \ 		echo ; \ 		done @@ -87,14 +105,14 @@ 		@for i in $(tests) ; \ 		do \ 		echo time $(prog4) $(ropts) $$i ; \-		time $(prog4) $$i ; \+		time $(prog4) $(ropts) $$i ; \ 		echo ; \ 		done  memtest	: 		@for i in $(tests) ; \ 		do \-		echo time $(prog5) $$i ; \+		echo time $(prog5) $(ropts) $$i ; \ 		time $(prog5) $(ropts) $$i ; \ 		echo ; \ 		done

@@ -71,29 +71,45 @@ 	tag (UnExpr _ _    ) = 3 	tag (BinExpr _ _ _ ) = 4 	ps = [ xpWrap ( IntConst-		      , \ (IntConst i ) -> i ) ( xpElem "int"  $-					         xpAttr "value" $-					         xpickle )+		      , \ (IntConst i ) -> i+                      ) $+               ( xpElem "int"   $+		 xpAttr "value" $+		 xpickle+               )  	     , xpWrap ( BoolConst-		      , \ (BoolConst b) -> b)  ( xpElem "bool" $-						 xpAttr "value" $-						 xpWrap (toEnum, fromEnum) xpickle )+		      , \ (BoolConst b) -> b+                      ) $+               ( xpElem "bool"  $+		 xpAttr "value" $+		 xpWrap (toEnum, fromEnum) xpickle+               )  	     , xpWrap ( Var-		      , \ (Var n)       -> n)  ( xpElem "var"  $-						 xpAttr "name"  $-						 xpText )+		      , \ (Var n)       -> n+                      ) $+               ( xpElem "var"   $+		 xpAttr "name"  $+		 xpText+               )  	     , xpWrap ( uncurry UnExpr-		      , \ (UnExpr op e) -> (op, e))-                                               ( xpElem "unex" $-						 xpPair (xpAttr "op" xpickle) xpickle )+		      , \ (UnExpr op e) -> (op, e)+                      ) $+               ( xpElem "unex" $+		 xpPair (xpAttr "op" xpickle)+                         xpickle+               )  	     , xpWrap ( uncurry3 $ BinExpr-		      , \ (BinExpr op e1 e2) -> (op, e1, e2))-                                               ( xpElem "binex" $-						 xpTriple (xpAttr "op" xpickle) xpickle xpickle )+		      , \ (BinExpr op e1 e2) -> (op, e1, e2)+                      ) $+               ( xpElem "binex" $+		 xpTriple (xpAttr "op" xpickle)+                           xpickle+                           xpickle+               ) 	     ]  instance XmlPickler Stmt where@@ -104,20 +120,33 @@ 	tag ( If _ _ _ )   = 2 	tag ( While _ _ )  = 3 	ps = [ xpWrap ( uncurry Assign-		      , \ (Assign n v) -> (n, v))-                                               ( xpElem "assign" $-						 xpPair (xpAttr "name" xpText) xpickle )+		      , \ (Assign n v) -> (n, v)+                      ) $+               ( xpElem "assign" $+		 xpPair (xpAttr "name" xpText)+                         xpickle+               ) 	     , xpWrap ( Stmts-		      , \ (Stmts sl) -> sl)    ( xpElem "block" $-						 xpList xpickle )+		      , \ (Stmts sl) -> sl+                      ) $+               ( xpElem "block" $+		 xpList xpickle+               ) 	     , xpWrap ( uncurry3 If-		      , \ (If c t e) -> (c, t, e))-                                               ( xpElem "if" $-						 xpTriple xpickle xpickle xpickle )+		      , \ (If c t e) -> (c, t, e)+                      ) $+               ( xpElem "if" $+		 xpTriple xpickle+                          xpickle+                          xpickle+               ) 	     , xpWrap ( uncurry While-		      , \ (While c b) -> (c, b))-                                               ( xpElem "while" $-						 xpPair xpickle xpickle )+		      , \ (While c b) -> (c, b)+                      ) $+               ( xpElem "while" $+		 xpPair xpickle+                        xpickle+               ) 	     ]  -- ------------------------------------------------------------

@@ -0,0 +1,4 @@+<!DOCTYPE html SYSTEM "xhtml1-strict.dtd">+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">+<head><title/></head><body/>+</html>

@@ -0,0 +1,196 @@+<!-- Portions (C) International Organization for Standardization 1986+     Permission to copy in any form is granted for use with+     conforming SGML systems and applications as defined in+     ISO 8879, provided this notice is included in all copies.+-->+<!-- Character entity set. Typical invocation:+    <!ENTITY % HTMLlat1 PUBLIC+       "-//W3C//ENTITIES Latin 1 for XHTML//EN"+       "http://www.w3.org/TR/xhtml1/DTD/xhtml-lat1.ent">+    %HTMLlat1;+-->++<!ENTITY nbsp   "&#160;"> <!-- no-break space = non-breaking space,+                                  U+00A0 ISOnum -->+<!ENTITY iexcl  "&#161;"> <!-- inverted exclamation mark, U+00A1 ISOnum -->+<!ENTITY cent   "&#162;"> <!-- cent sign, U+00A2 ISOnum -->+<!ENTITY pound  "&#163;"> <!-- pound sign, U+00A3 ISOnum -->+<!ENTITY curren "&#164;"> <!-- currency sign, U+00A4 ISOnum -->+<!ENTITY yen    "&#165;"> <!-- yen sign = yuan sign, U+00A5 ISOnum -->+<!ENTITY brvbar "&#166;"> <!-- broken bar = broken vertical bar,+                                  U+00A6 ISOnum -->+<!ENTITY sect   "&#167;"> <!-- section sign, U+00A7 ISOnum -->+<!ENTITY uml    "&#168;"> <!-- diaeresis = spacing diaeresis,+                                  U+00A8 ISOdia -->+<!ENTITY copy   "&#169;"> <!-- copyright sign, U+00A9 ISOnum -->+<!ENTITY ordf   "&#170;"> <!-- feminine ordinal indicator, U+00AA ISOnum -->+<!ENTITY laquo  "&#171;"> <!-- left-pointing double angle quotation mark+                                  = left pointing guillemet, U+00AB ISOnum -->+<!ENTITY not    "&#172;"> <!-- not sign = discretionary hyphen,+                                  U+00AC ISOnum -->+<!ENTITY shy    "&#173;"> <!-- soft hyphen = discretionary hyphen,+                                  U+00AD ISOnum -->+<!ENTITY reg    "&#174;"> <!-- registered sign = registered trade mark sign,+                                  U+00AE ISOnum -->+<!ENTITY macr   "&#175;"> <!-- macron = spacing macron = overline+                                  = APL overbar, U+00AF ISOdia -->+<!ENTITY deg    "&#176;"> <!-- degree sign, U+00B0 ISOnum -->+<!ENTITY plusmn "&#177;"> <!-- plus-minus sign = plus-or-minus sign,+                                  U+00B1 ISOnum -->+<!ENTITY sup2   "&#178;"> <!-- superscript two = superscript digit two+                                  = squared, U+00B2 ISOnum -->+<!ENTITY sup3   "&#179;"> <!-- superscript three = superscript digit three+                                  = cubed, U+00B3 ISOnum -->+<!ENTITY acute  "&#180;"> <!-- acute accent = spacing acute,+                                  U+00B4 ISOdia -->+<!ENTITY micro  "&#181;"> <!-- micro sign, U+00B5 ISOnum -->+<!ENTITY para   "&#182;"> <!-- pilcrow sign = paragraph sign,+                                  U+00B6 ISOnum -->+<!ENTITY middot "&#183;"> <!-- middle dot = Georgian comma+                                  = Greek middle dot, U+00B7 ISOnum -->+<!ENTITY cedil  "&#184;"> <!-- cedilla = spacing cedilla, U+00B8 ISOdia -->+<!ENTITY sup1   "&#185;"> <!-- superscript one = superscript digit one,+                                  U+00B9 ISOnum -->+<!ENTITY ordm   "&#186;"> <!-- masculine ordinal indicator,+                                  U+00BA ISOnum -->+<!ENTITY raquo  "&#187;"> <!-- right-pointing double angle quotation mark+                                  = right pointing guillemet, U+00BB ISOnum -->+<!ENTITY frac14 "&#188;"> <!-- vulgar fraction one quarter+                                  = fraction one quarter, U+00BC ISOnum -->+<!ENTITY frac12 "&#189;"> <!-- vulgar fraction one half+                                  = fraction one half, U+00BD ISOnum -->+<!ENTITY frac34 "&#190;"> <!-- vulgar fraction three quarters+                                  = fraction three quarters, U+00BE ISOnum -->+<!ENTITY iquest "&#191;"> <!-- inverted question mark+                                  = turned question mark, U+00BF ISOnum -->+<!ENTITY Agrave "&#192;"> <!-- latin capital letter A with grave+                                  = latin capital letter A grave,+                                  U+00C0 ISOlat1 -->+<!ENTITY Aacute "&#193;"> <!-- latin capital letter A with acute,+                                  U+00C1 ISOlat1 -->+<!ENTITY Acirc  "&#194;"> <!-- latin capital letter A with circumflex,+                                  U+00C2 ISOlat1 -->+<!ENTITY Atilde "&#195;"> <!-- latin capital letter A with tilde,+                                  U+00C3 ISOlat1 -->+<!ENTITY Auml   "&#196;"> <!-- latin capital letter A with diaeresis,+                                  U+00C4 ISOlat1 -->+<!ENTITY Aring  "&#197;"> <!-- latin capital letter A with ring above+                                  = latin capital letter A ring,+                                  U+00C5 ISOlat1 -->+<!ENTITY AElig  "&#198;"> <!-- latin capital letter AE+                                  = latin capital ligature AE,+                                  U+00C6 ISOlat1 -->+<!ENTITY Ccedil "&#199;"> <!-- latin capital letter C with cedilla,+                                  U+00C7 ISOlat1 -->+<!ENTITY Egrave "&#200;"> <!-- latin capital letter E with grave,+                                  U+00C8 ISOlat1 -->+<!ENTITY Eacute "&#201;"> <!-- latin capital letter E with acute,+                                  U+00C9 ISOlat1 -->+<!ENTITY Ecirc  "&#202;"> <!-- latin capital letter E with circumflex,+                                  U+00CA ISOlat1 -->+<!ENTITY Euml   "&#203;"> <!-- latin capital letter E with diaeresis,+                                  U+00CB ISOlat1 -->+<!ENTITY Igrave "&#204;"> <!-- latin capital letter I with grave,+                                  U+00CC ISOlat1 -->+<!ENTITY Iacute "&#205;"> <!-- latin capital letter I with acute,+                                  U+00CD ISOlat1 -->+<!ENTITY Icirc  "&#206;"> <!-- latin capital letter I with circumflex,+                                  U+00CE ISOlat1 -->+<!ENTITY Iuml   "&#207;"> <!-- latin capital letter I with diaeresis,+                                  U+00CF ISOlat1 -->+<!ENTITY ETH    "&#208;"> <!-- latin capital letter ETH, U+00D0 ISOlat1 -->+<!ENTITY Ntilde "&#209;"> <!-- latin capital letter N with tilde,+                                  U+00D1 ISOlat1 -->+<!ENTITY Ograve "&#210;"> <!-- latin capital letter O with grave,+                                  U+00D2 ISOlat1 -->+<!ENTITY Oacute "&#211;"> <!-- latin capital letter O with acute,+                                  U+00D3 ISOlat1 -->+<!ENTITY Ocirc  "&#212;"> <!-- latin capital letter O with circumflex,+                                  U+00D4 ISOlat1 -->+<!ENTITY Otilde "&#213;"> <!-- latin capital letter O with tilde,+                                  U+00D5 ISOlat1 -->+<!ENTITY Ouml   "&#214;"> <!-- latin capital letter O with diaeresis,+                                  U+00D6 ISOlat1 -->+<!ENTITY times  "&#215;"> <!-- multiplication sign, U+00D7 ISOnum -->+<!ENTITY Oslash "&#216;"> <!-- latin capital letter O with stroke+                                  = latin capital letter O slash,+                                  U+00D8 ISOlat1 -->+<!ENTITY Ugrave "&#217;"> <!-- latin capital letter U with grave,+                                  U+00D9 ISOlat1 -->+<!ENTITY Uacute "&#218;"> <!-- latin capital letter U with acute,+                                  U+00DA ISOlat1 -->+<!ENTITY Ucirc  "&#219;"> <!-- latin capital letter U with circumflex,+                                  U+00DB ISOlat1 -->+<!ENTITY Uuml   "&#220;"> <!-- latin capital letter U with diaeresis,+                                  U+00DC ISOlat1 -->+<!ENTITY Yacute "&#221;"> <!-- latin capital letter Y with acute,+                                  U+00DD ISOlat1 -->+<!ENTITY THORN  "&#222;"> <!-- latin capital letter THORN,+                                  U+00DE ISOlat1 -->+<!ENTITY szlig  "&#223;"> <!-- latin small letter sharp s = ess-zed,+                                  U+00DF ISOlat1 -->+<!ENTITY agrave "&#224;"> <!-- latin small letter a with grave+                                  = latin small letter a grave,+                                  U+00E0 ISOlat1 -->+<!ENTITY aacute "&#225;"> <!-- latin small letter a with acute,+                                  U+00E1 ISOlat1 -->+<!ENTITY acirc  "&#226;"> <!-- latin small letter a with circumflex,+                                  U+00E2 ISOlat1 -->+<!ENTITY atilde "&#227;"> <!-- latin small letter a with tilde,+                                  U+00E3 ISOlat1 -->+<!ENTITY auml   "&#228;"> <!-- latin small letter a with diaeresis,+                                  U+00E4 ISOlat1 -->+<!ENTITY aring  "&#229;"> <!-- latin small letter a with ring above+                                  = latin small letter a ring,+                                  U+00E5 ISOlat1 -->+<!ENTITY aelig  "&#230;"> <!-- latin small letter ae+                                  = latin small ligature ae, U+00E6 ISOlat1 -->+<!ENTITY ccedil "&#231;"> <!-- latin small letter c with cedilla,+                                  U+00E7 ISOlat1 -->+<!ENTITY egrave "&#232;"> <!-- latin small letter e with grave,+                                  U+00E8 ISOlat1 -->+<!ENTITY eacute "&#233;"> <!-- latin small letter e with acute,+                                  U+00E9 ISOlat1 -->+<!ENTITY ecirc  "&#234;"> <!-- latin small letter e with circumflex,+                                  U+00EA ISOlat1 -->+<!ENTITY euml   "&#235;"> <!-- latin small letter e with diaeresis,+                                  U+00EB ISOlat1 -->+<!ENTITY igrave "&#236;"> <!-- latin small letter i with grave,+                                  U+00EC ISOlat1 -->+<!ENTITY iacute "&#237;"> <!-- latin small letter i with acute,+                                  U+00ED ISOlat1 -->+<!ENTITY icirc  "&#238;"> <!-- latin small letter i with circumflex,+                                  U+00EE ISOlat1 -->+<!ENTITY iuml   "&#239;"> <!-- latin small letter i with diaeresis,+                                  U+00EF ISOlat1 -->+<!ENTITY eth    "&#240;"> <!-- latin small letter eth, U+00F0 ISOlat1 -->+<!ENTITY ntilde "&#241;"> <!-- latin small letter n with tilde,+                                  U+00F1 ISOlat1 -->+<!ENTITY ograve "&#242;"> <!-- latin small letter o with grave,+                                  U+00F2 ISOlat1 -->+<!ENTITY oacute "&#243;"> <!-- latin small letter o with acute,+                                  U+00F3 ISOlat1 -->+<!ENTITY ocirc  "&#244;"> <!-- latin small letter o with circumflex,+                                  U+00F4 ISOlat1 -->+<!ENTITY otilde "&#245;"> <!-- latin small letter o with tilde,+                                  U+00F5 ISOlat1 -->+<!ENTITY ouml   "&#246;"> <!-- latin small letter o with diaeresis,+                                  U+00F6 ISOlat1 -->+<!ENTITY divide "&#247;"> <!-- division sign, U+00F7 ISOnum -->+<!ENTITY oslash "&#248;"> <!-- latin small letter o with stroke,+                                  = latin small letter o slash,+                                  U+00F8 ISOlat1 -->+<!ENTITY ugrave "&#249;"> <!-- latin small letter u with grave,+                                  U+00F9 ISOlat1 -->+<!ENTITY uacute "&#250;"> <!-- latin small letter u with acute,+                                  U+00FA ISOlat1 -->+<!ENTITY ucirc  "&#251;"> <!-- latin small letter u with circumflex,+                                  U+00FB ISOlat1 -->+<!ENTITY uuml   "&#252;"> <!-- latin small letter u with diaeresis,+                                  U+00FC ISOlat1 -->+<!ENTITY yacute "&#253;"> <!-- latin small letter y with acute,+                                  U+00FD ISOlat1 -->+<!ENTITY thorn  "&#254;"> <!-- latin small letter thorn with,+                                  U+00FE ISOlat1 -->+<!ENTITY yuml   "&#255;"> <!-- latin small letter y with diaeresis,+                                  U+00FF ISOlat1 -->

@@ -0,0 +1,79 @@+<!-- Special characters for HTML -->++<!-- Character entity set. Typical invocation:+     <!ENTITY % HTMLspecial PUBLIC+        "-//W3C//ENTITIES Special for XHTML//EN"+        "http://www.w3.org/TR/xhtml1/DTD/xhtml-special.ent">+     %HTMLspecial;+-->++<!-- Portions (C) International Organization for Standardization 1986:+     Permission to copy in any form is granted for use with+     conforming SGML systems and applications as defined in+     ISO 8879, provided this notice is included in all copies.+-->++<!-- Relevant ISO entity set is given unless names are newly introduced.+     New names (i.e., not in ISO 8879 list) do not clash with any+     existing ISO 8879 entity names. ISO 10646 character numbers+     are given for each character, in hex. values are decimal+     conversions of the ISO 10646 values and refer to the document+     character set. Names are Unicode names. +-->++<!-- C0 Controls and Basic Latin -->+<!ENTITY quot    "&#34;"> <!--  quotation mark = APL quote,+                                    U+0022 ISOnum -->+<!ENTITY amp     "&#38;#38;"> <!--  ampersand, U+0026 ISOnum -->+<!ENTITY lt      "&#38;#60;"> <!--  less-than sign, U+003C ISOnum -->+<!ENTITY gt      "&#62;"> <!--  greater-than sign, U+003E ISOnum -->+<!ENTITY apos	 "&#39;"> <!--  apostrophe mark, U+0027 ISOnum -->++<!-- Latin Extended-A -->+<!ENTITY OElig   "&#338;"> <!--  latin capital ligature OE,+                                    U+0152 ISOlat2 -->+<!ENTITY oelig   "&#339;"> <!--  latin small ligature oe, U+0153 ISOlat2 -->+<!-- ligature is a misnomer, this is a separate character in some languages -->+<!ENTITY Scaron  "&#352;"> <!--  latin capital letter S with caron,+                                    U+0160 ISOlat2 -->+<!ENTITY scaron  "&#353;"> <!--  latin small letter s with caron,+                                    U+0161 ISOlat2 -->+<!ENTITY Yuml    "&#376;"> <!--  latin capital letter Y with diaeresis,+                                    U+0178 ISOlat2 -->++<!-- Spacing Modifier Letters -->+<!ENTITY circ    "&#710;"> <!--  modifier letter circumflex accent,+                                    U+02C6 ISOpub -->+<!ENTITY tilde   "&#732;"> <!--  small tilde, U+02DC ISOdia -->++<!-- General Punctuation -->+<!ENTITY ensp    "&#8194;"> <!-- en space, U+2002 ISOpub -->+<!ENTITY emsp    "&#8195;"> <!-- em space, U+2003 ISOpub -->+<!ENTITY thinsp  "&#8201;"> <!-- thin space, U+2009 ISOpub -->+<!ENTITY zwnj    "&#8204;"> <!-- zero width non-joiner,+                                    U+200C NEW RFC 2070 -->+<!ENTITY zwj     "&#8205;"> <!-- zero width joiner, U+200D NEW RFC 2070 -->+<!ENTITY lrm     "&#8206;"> <!-- left-to-right mark, U+200E NEW RFC 2070 -->+<!ENTITY rlm     "&#8207;"> <!-- right-to-left mark, U+200F NEW RFC 2070 -->+<!ENTITY ndash   "&#8211;"> <!-- en dash, U+2013 ISOpub -->+<!ENTITY mdash   "&#8212;"> <!-- em dash, U+2014 ISOpub -->+<!ENTITY lsquo   "&#8216;"> <!-- left single quotation mark,+                                    U+2018 ISOnum -->+<!ENTITY rsquo   "&#8217;"> <!-- right single quotation mark,+                                    U+2019 ISOnum -->+<!ENTITY sbquo   "&#8218;"> <!-- single low-9 quotation mark, U+201A NEW -->+<!ENTITY ldquo   "&#8220;"> <!-- left double quotation mark,+                                    U+201C ISOnum -->+<!ENTITY rdquo   "&#8221;"> <!-- right double quotation mark,+                                    U+201D ISOnum -->+<!ENTITY bdquo   "&#8222;"> <!-- double low-9 quotation mark, U+201E NEW -->+<!ENTITY dagger  "&#8224;"> <!-- dagger, U+2020 ISOpub -->+<!ENTITY Dagger  "&#8225;"> <!-- double dagger, U+2021 ISOpub -->+<!ENTITY permil  "&#8240;"> <!-- per mille sign, U+2030 ISOtech -->+<!ENTITY lsaquo  "&#8249;"> <!-- single left-pointing angle quotation mark,+                                    U+2039 ISO proposed -->+<!-- lsaquo is proposed but not yet ISO standardized -->+<!ENTITY rsaquo  "&#8250;"> <!-- single right-pointing angle quotation mark,+                                    U+203A ISO proposed -->+<!-- rsaquo is proposed but not yet ISO standardized -->+<!ENTITY euro   "&#8364;"> <!--  euro sign, U+20AC NEW -->

@@ -0,0 +1,242 @@+<!-- Mathematical, Greek and Symbolic characters for HTML -->++<!-- Character entity set. Typical invocation:+     <!ENTITY % HTMLsymbol PUBLIC+        "-//W3C//ENTITIES Symbols for XHTML//EN"+        "http://www.w3.org/TR/xhtml1/DTD/xhtml-symbol.ent">+     %HTMLsymbol;+-->++<!-- Portions (C) International Organization for Standardization 1986:+     Permission to copy in any form is granted for use with+     conforming SGML systems and applications as defined in+     ISO 8879, provided this notice is included in all copies.+-->++<!-- Relevant ISO entity set is given unless names are newly introduced.+     New names (i.e., not in ISO 8879 list) do not clash with any+     existing ISO 8879 entity names. ISO 10646 character numbers+     are given for each character, in hex. values are decimal+     conversions of the ISO 10646 values and refer to the document+     character set. Names are Unicode names. +-->++<!-- Latin Extended-B -->+<!ENTITY fnof     "&#402;"> <!-- latin small f with hook = function+                                    = florin, U+0192 ISOtech -->++<!-- Greek -->+<!ENTITY Alpha    "&#913;"> <!-- greek capital letter alpha, U+0391 -->+<!ENTITY Beta     "&#914;"> <!-- greek capital letter beta, U+0392 -->+<!ENTITY Gamma    "&#915;"> <!-- greek capital letter gamma,+                                    U+0393 ISOgrk3 -->+<!ENTITY Delta    "&#916;"> <!-- greek capital letter delta,+                                    U+0394 ISOgrk3 -->+<!ENTITY Epsilon  "&#917;"> <!-- greek capital letter epsilon, U+0395 -->+<!ENTITY Zeta     "&#918;"> <!-- greek capital letter zeta, U+0396 -->+<!ENTITY Eta      "&#919;"> <!-- greek capital letter eta, U+0397 -->+<!ENTITY Theta    "&#920;"> <!-- greek capital letter theta,+                                    U+0398 ISOgrk3 -->+<!ENTITY Iota     "&#921;"> <!-- greek capital letter iota, U+0399 -->+<!ENTITY Kappa    "&#922;"> <!-- greek capital letter kappa, U+039A -->+<!ENTITY Lambda   "&#923;"> <!-- greek capital letter lambda,+                                    U+039B ISOgrk3 -->+<!ENTITY Mu       "&#924;"> <!-- greek capital letter mu, U+039C -->+<!ENTITY Nu       "&#925;"> <!-- greek capital letter nu, U+039D -->+<!ENTITY Xi       "&#926;"> <!-- greek capital letter xi, U+039E ISOgrk3 -->+<!ENTITY Omicron  "&#927;"> <!-- greek capital letter omicron, U+039F -->+<!ENTITY Pi       "&#928;"> <!-- greek capital letter pi, U+03A0 ISOgrk3 -->+<!ENTITY Rho      "&#929;"> <!-- greek capital letter rho, U+03A1 -->+<!-- there is no Sigmaf, and no U+03A2 character either -->+<!ENTITY Sigma    "&#931;"> <!-- greek capital letter sigma,+                                    U+03A3 ISOgrk3 -->+<!ENTITY Tau      "&#932;"> <!-- greek capital letter tau, U+03A4 -->+<!ENTITY Upsilon  "&#933;"> <!-- greek capital letter upsilon,+                                    U+03A5 ISOgrk3 -->+<!ENTITY Phi      "&#934;"> <!-- greek capital letter phi,+                                    U+03A6 ISOgrk3 -->+<!ENTITY Chi      "&#935;"> <!-- greek capital letter chi, U+03A7 -->+<!ENTITY Psi      "&#936;"> <!-- greek capital letter psi,+                                    U+03A8 ISOgrk3 -->+<!ENTITY Omega    "&#937;"> <!-- greek capital letter omega,+                                    U+03A9 ISOgrk3 -->++<!ENTITY alpha    "&#945;"> <!-- greek small letter alpha,+                                    U+03B1 ISOgrk3 -->+<!ENTITY beta     "&#946;"> <!-- greek small letter beta, U+03B2 ISOgrk3 -->+<!ENTITY gamma    "&#947;"> <!-- greek small letter gamma,+                                    U+03B3 ISOgrk3 -->+<!ENTITY delta    "&#948;"> <!-- greek small letter delta,+                                    U+03B4 ISOgrk3 -->+<!ENTITY epsilon  "&#949;"> <!-- greek small letter epsilon,+                                    U+03B5 ISOgrk3 -->+<!ENTITY zeta     "&#950;"> <!-- greek small letter zeta, U+03B6 ISOgrk3 -->+<!ENTITY eta      "&#951;"> <!-- greek small letter eta, U+03B7 ISOgrk3 -->+<!ENTITY theta    "&#952;"> <!-- greek small letter theta,+                                    U+03B8 ISOgrk3 -->+<!ENTITY iota     "&#953;"> <!-- greek small letter iota, U+03B9 ISOgrk3 -->+<!ENTITY kappa    "&#954;"> <!-- greek small letter kappa,+                                    U+03BA ISOgrk3 -->+<!ENTITY lambda   "&#955;"> <!-- greek small letter lambda,+                                    U+03BB ISOgrk3 -->+<!ENTITY mu       "&#956;"> <!-- greek small letter mu, U+03BC ISOgrk3 -->+<!ENTITY nu       "&#957;"> <!-- greek small letter nu, U+03BD ISOgrk3 -->+<!ENTITY xi       "&#958;"> <!-- greek small letter xi, U+03BE ISOgrk3 -->+<!ENTITY omicron  "&#959;"> <!-- greek small letter omicron, U+03BF NEW -->+<!ENTITY pi       "&#960;"> <!-- greek small letter pi, U+03C0 ISOgrk3 -->+<!ENTITY rho      "&#961;"> <!-- greek small letter rho, U+03C1 ISOgrk3 -->+<!ENTITY sigmaf   "&#962;"> <!-- greek small letter final sigma,+                                    U+03C2 ISOgrk3 -->+<!ENTITY sigma    "&#963;"> <!-- greek small letter sigma,+                                    U+03C3 ISOgrk3 -->+<!ENTITY tau      "&#964;"> <!-- greek small letter tau, U+03C4 ISOgrk3 -->+<!ENTITY upsilon  "&#965;"> <!-- greek small letter upsilon,+                                    U+03C5 ISOgrk3 -->+<!ENTITY phi      "&#966;"> <!-- greek small letter phi, U+03C6 ISOgrk3 -->+<!ENTITY chi      "&#967;"> <!-- greek small letter chi, U+03C7 ISOgrk3 -->+<!ENTITY psi      "&#968;"> <!-- greek small letter psi, U+03C8 ISOgrk3 -->+<!ENTITY omega    "&#969;"> <!-- greek small letter omega,+                                    U+03C9 ISOgrk3 -->+<!ENTITY thetasym "&#977;"> <!-- greek small letter theta symbol,+                                    U+03D1 NEW -->+<!ENTITY upsih    "&#978;"> <!-- greek upsilon with hook symbol,+                                    U+03D2 NEW -->+<!ENTITY piv      "&#982;"> <!-- greek pi symbol, U+03D6 ISOgrk3 -->++<!-- General Punctuation -->+<!ENTITY bull     "&#8226;"> <!-- bullet = black small circle,+                                     U+2022 ISOpub  -->+<!-- bullet is NOT the same as bullet operator, U+2219 -->+<!ENTITY hellip   "&#8230;"> <!-- horizontal ellipsis = three dot leader,+                                     U+2026 ISOpub  -->+<!ENTITY prime    "&#8242;"> <!-- prime = minutes = feet, U+2032 ISOtech -->+<!ENTITY Prime    "&#8243;"> <!-- double prime = seconds = inches,+                                     U+2033 ISOtech -->+<!ENTITY oline    "&#8254;"> <!-- overline = spacing overscore,+                                     U+203E NEW -->+<!ENTITY frasl    "&#8260;"> <!-- fraction slash, U+2044 NEW -->++<!-- Letterlike Symbols -->+<!ENTITY weierp   "&#8472;"> <!-- script capital P = power set+                                     = Weierstrass p, U+2118 ISOamso -->+<!ENTITY image    "&#8465;"> <!-- blackletter capital I = imaginary part,+                                     U+2111 ISOamso -->+<!ENTITY real     "&#8476;"> <!-- blackletter capital R = real part symbol,+                                     U+211C ISOamso -->+<!ENTITY trade    "&#8482;"> <!-- trade mark sign, U+2122 ISOnum -->+<!ENTITY alefsym  "&#8501;"> <!-- alef symbol = first transfinite cardinal,+                                     U+2135 NEW -->+<!-- alef symbol is NOT the same as hebrew letter alef,+     U+05D0 although the same glyph could be used to depict both characters -->++<!-- Arrows -->+<!ENTITY larr     "&#8592;"> <!-- leftwards arrow, U+2190 ISOnum -->+<!ENTITY uarr     "&#8593;"> <!-- upwards arrow, U+2191 ISOnum-->+<!ENTITY rarr     "&#8594;"> <!-- rightwards arrow, U+2192 ISOnum -->+<!ENTITY darr     "&#8595;"> <!-- downwards arrow, U+2193 ISOnum -->+<!ENTITY harr     "&#8596;"> <!-- left right arrow, U+2194 ISOamsa -->+<!ENTITY crarr    "&#8629;"> <!-- downwards arrow with corner leftwards+                                     = carriage return, U+21B5 NEW -->+<!ENTITY lArr     "&#8656;"> <!-- leftwards double arrow, U+21D0 ISOtech -->+<!-- Unicode does not say that lArr is the same as the 'is implied by' arrow+    but also does not have any other character for that function. So ? lArr can+    be used for 'is implied by' as ISOtech suggests -->+<!ENTITY uArr     "&#8657;"> <!-- upwards double arrow, U+21D1 ISOamsa -->+<!ENTITY rArr     "&#8658;"> <!-- rightwards double arrow,+                                     U+21D2 ISOtech -->+<!-- Unicode does not say this is the 'implies' character but does not have +     another character with this function so ?+     rArr can be used for 'implies' as ISOtech suggests -->+<!ENTITY dArr     "&#8659;"> <!-- downwards double arrow, U+21D3 ISOamsa -->+<!ENTITY hArr     "&#8660;"> <!-- left right double arrow,+                                     U+21D4 ISOamsa -->++<!-- Mathematical Operators -->+<!ENTITY forall   "&#8704;"> <!-- for all, U+2200 ISOtech -->+<!ENTITY part     "&#8706;"> <!-- partial differential, U+2202 ISOtech  -->+<!ENTITY exist    "&#8707;"> <!-- there exists, U+2203 ISOtech -->+<!ENTITY empty    "&#8709;"> <!-- empty set = null set = diameter,+                                     U+2205 ISOamso -->+<!ENTITY nabla    "&#8711;"> <!-- nabla = backward difference,+                                     U+2207 ISOtech -->+<!ENTITY isin     "&#8712;"> <!-- element of, U+2208 ISOtech -->+<!ENTITY notin    "&#8713;"> <!-- not an element of, U+2209 ISOtech -->+<!ENTITY ni       "&#8715;"> <!-- contains as member, U+220B ISOtech -->+<!-- should there be a more memorable name than 'ni'? -->+<!ENTITY prod     "&#8719;"> <!-- n-ary product = product sign,+                                     U+220F ISOamsb -->+<!-- prod is NOT the same character as U+03A0 'greek capital letter pi' though+     the same glyph might be used for both -->+<!ENTITY sum      "&#8721;"> <!-- n-ary sumation, U+2211 ISOamsb -->+<!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'+     though the same glyph might be used for both -->+<!ENTITY minus    "&#8722;"> <!-- minus sign, U+2212 ISOtech -->+<!ENTITY lowast   "&#8727;"> <!-- asterisk operator, U+2217 ISOtech -->+<!ENTITY radic    "&#8730;"> <!-- square root = radical sign,+                                     U+221A ISOtech -->+<!ENTITY prop     "&#8733;"> <!-- proportional to, U+221D ISOtech -->+<!ENTITY infin    "&#8734;"> <!-- infinity, U+221E ISOtech -->+<!ENTITY ang      "&#8736;"> <!-- angle, U+2220 ISOamso -->+<!ENTITY and      "&#8743;"> <!-- logical and = wedge, U+2227 ISOtech -->+<!ENTITY or       "&#8744;"> <!-- logical or = vee, U+2228 ISOtech -->+<!ENTITY cap      "&#8745;"> <!-- intersection = cap, U+2229 ISOtech -->+<!ENTITY cup      "&#8746;"> <!-- union = cup, U+222A ISOtech -->+<!ENTITY int      "&#8747;"> <!-- integral, U+222B ISOtech -->+<!ENTITY there4   "&#8756;"> <!-- therefore, U+2234 ISOtech -->+<!ENTITY sim      "&#8764;"> <!-- tilde operator = varies with = similar to,+                                     U+223C ISOtech -->+<!-- tilde operator is NOT the same character as the tilde, U+007E,+     although the same glyph might be used to represent both  -->+<!ENTITY cong     "&#8773;"> <!-- approximately equal to, U+2245 ISOtech -->+<!ENTITY asymp    "&#8776;"> <!-- almost equal to = asymptotic to,+                                     U+2248 ISOamsr -->+<!ENTITY ne       "&#8800;"> <!-- not equal to, U+2260 ISOtech -->+<!ENTITY equiv    "&#8801;"> <!-- identical to, U+2261 ISOtech -->+<!ENTITY le       "&#8804;"> <!-- less-than or equal to, U+2264 ISOtech -->+<!ENTITY ge       "&#8805;"> <!-- greater-than or equal to,+                                     U+2265 ISOtech -->+<!ENTITY sub      "&#8834;"> <!-- subset of, U+2282 ISOtech -->+<!ENTITY sup      "&#8835;"> <!-- superset of, U+2283 ISOtech -->+<!-- note that nsup, 'not a superset of, U+2283' is not covered by the Symbol +     font encoding and is not included. Should it be, for symmetry?+     It is in ISOamsn  --> +<!ENTITY nsub     "&#8836;"> <!-- not a subset of, U+2284 ISOamsn -->+<!ENTITY sube     "&#8838;"> <!-- subset of or equal to, U+2286 ISOtech -->+<!ENTITY supe     "&#8839;"> <!-- superset of or equal to,+                                     U+2287 ISOtech -->+<!ENTITY oplus    "&#8853;"> <!-- circled plus = direct sum,+                                     U+2295 ISOamsb -->+<!ENTITY otimes   "&#8855;"> <!-- circled times = vector product,+                                     U+2297 ISOamsb -->+<!ENTITY perp     "&#8869;"> <!-- up tack = orthogonal to = perpendicular,+                                     U+22A5 ISOtech -->+<!ENTITY sdot     "&#8901;"> <!-- dot operator, U+22C5 ISOamsb -->+<!-- dot operator is NOT the same character as U+00B7 middle dot -->++<!-- Miscellaneous Technical -->+<!ENTITY lceil    "&#8968;"> <!-- left ceiling = apl upstile,+                                     U+2308 ISOamsc  -->+<!ENTITY rceil    "&#8969;"> <!-- right ceiling, U+2309 ISOamsc  -->+<!ENTITY lfloor   "&#8970;"> <!-- left floor = apl downstile,+                                     U+230A ISOamsc  -->+<!ENTITY rfloor   "&#8971;"> <!-- right floor, U+230B ISOamsc  -->+<!ENTITY lang     "&#9001;"> <!-- left-pointing angle bracket = bra,+                                     U+2329 ISOtech -->+<!-- lang is NOT the same character as U+003C 'less than' +     or U+2039 'single left-pointing angle quotation mark' -->+<!ENTITY rang     "&#9002;"> <!-- right-pointing angle bracket = ket,+                                     U+232A ISOtech -->+<!-- rang is NOT the same character as U+003E 'greater than' +     or U+203A 'single right-pointing angle quotation mark' -->++<!-- Geometric Shapes -->+<!ENTITY loz      "&#9674;"> <!-- lozenge, U+25CA ISOpub -->++<!-- Miscellaneous Symbols -->+<!ENTITY spades   "&#9824;"> <!-- black spade suit, U+2660 ISOpub -->+<!-- black here seems to mean filled as opposed to hollow -->+<!ENTITY clubs    "&#9827;"> <!-- black club suit = shamrock,+                                     U+2663 ISOpub -->+<!ENTITY hearts   "&#9829;"> <!-- black heart suit = valentine,+                                     U+2665 ISOpub -->+<!ENTITY diams    "&#9830;"> <!-- black diamond suit, U+2666 ISOpub -->

@@ -0,0 +1,1484 @@+<!DOCTYPE html SYSTEM "xhtml1-strict.dtd">+<?xml-stylesheet href="http://www.w3.org/StyleSheets/TR/W3C-REC.css" type="text/css"?>+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">+<head>+<title>XHTML 1.0: The Extensible HyperText Markup+Language</title>+<link rel="stylesheet"+href="http://www.w3.org/StyleSheets/TR/W3C-REC.css" type="text/css" />+<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />+<style type="text/css">+span.term { font-style: italic; color: rgb(0, 0, 192) }+code {+	color: green;+	font-family: monospace;+	font-weight: bold;+}++code.greenmono {+	color: green;+	font-family: monospace;+	font-weight: bold;+}+.good {+	border: solid green;+	border-width: 2px;+	color: green;+	font-weight: bold;+	margin-right: 5%;+	margin-left: 0;+}+.bad  {+	border: solid red;+	border-width: 2px;+	margin-left: 0;+	margin-right: 5%;+	color: rgb(192, 101, 101);+}++img {+	color: white;+	border: none;+}++div.navbar { text-align: center; }+div.contents {+	background-color: rgb(204,204,255);+	padding: 0.5em;+	border: none;+	margin-right: 5%;+}+.tocline { list-style: none; }+table.exceptions { background-color: rgb(255,255,153); }+</style>+</head>+<body>+<div class="navbar">+  <a href="#toc">table of contents</a>+  <hr />+</div>+<div class="head"><p><a href="http://www.w3.org/"><img class="head"+src="http://www.w3.org/Icons/WWW/w3c_home.gif" alt="W3C" /></a></p>++<h1 class="head"><a name="title" id="title">XHTML</a><sup>&#8482;</sup> 1.0:+The Extensible HyperText Markup Language</h1>++<h2>A Reformulation of HTML 4 in XML 1.0</h2>++<h3>W3C Recommendation 26 January 2000</h3>++<dl>+<dt>This version:</dt>++<dd><a href=+"http://www.w3.org/TR/2000/REC-xhtml1-20000126">+http://www.w3.org/TR/2000/REC-xhtml1-20000126</a> <br />+(<a href="xhtml1.ps">Postscript version</a>,+<a href="xhtml1.pdf">PDF version</a>,+<a href="xhtml1.zip">ZIP archive</a>, or+<a href="xhtml1.tgz">Gzip'd TAR archive</a>)+</dd>++<dt>Latest version:</dt>++<dd><a href="http://www.w3.org/TR/xhtml1">+http://www.w3.org/TR/xhtml1</a></dd>++<dt>Previous version:</dt>++<dd><a href=+"http://www.w3.org/TR/1999/PR-xhtml1-19991210">+http://www.w3.org/TR/1999/PR-xhtml1-19991210</a></dd>++<dt>Authors:</dt>++<dd>See <a href="#acks">acknowledgements</a>.</dd>+</dl>++<p class="copyright"><a+href="http://www.w3.org/Consortium/Legal/ipr-notice#Copyright"> Copyright</a>+&copy;2000 <a href="http://www.w3.org/"><abbr title="World Wide Web+Consortium">W3C</abbr></a><sup>&reg;</sup> (<a+href="http://www.lcs.mit.edu/"><abbr+title="Massachusetts Institute of Technology">MIT</abbr></a>, <a+href="http://www.inria.fr/"><abbr+lang="fr" title="Institut National de Recherche en Informatique et+Automatique">INRIA</abbr></a>, <a+href="http://www.keio.ac.jp/">Keio</a>), All Rights Reserved. W3C <a+href="http://www.w3.org/Consortium/Legal/ipr-notice#Legal_Disclaimer">liability</a>,+<a+href="http://www.w3.org/Consortium/Legal/ipr-notice#W3C_Trademarks">trademark</a>,+<a+href="http://www.w3.org/Consortium/Legal/copyright-documents-19990405">document+use</a> and <a+href="http://www.w3.org/Consortium/Legal/copyright-software-19980720">software+licensing</a> rules+apply.</p>+<hr />+</div>++<h2 class="notoc">Abstract</h2>++<p>This specification defines <abbr title="Extensible Hypertext Markup+Language">XHTML</abbr> 1.0, a reformulation of HTML&nbsp;4+as an XML 1.0 application, and three <abbr title="Document Type+Definition">DTDs</abbr> corresponding to+the ones defined by HTML&nbsp;4. The semantics of the elements and+their attributes are defined in the W3C Recommendation for HTML&nbsp;4.+These semantics provide the foundation for future+extensibility of XHTML. Compatibility with existing HTML user+agents is possible by following a small set of guidelines.</p>++<h2>Status of this document</h2>++<p><em>This section describes the status of this document at the time+of its publication. Other documents may supersede this document. The+latest status of this document series is maintained at the W3C.</em></p>++<p>+This document has been reviewed by W3C Members and other+interested parties and has been endorsed by the Director+as a W3C Recommendation. It is a stable document and may be+used as reference material or cited as a normative+reference from another document. W3C's role in making the+Recommendation is to draw attention to the specification and+to promote its widespread deployment. This enhances the+functionality and interoperability of the Web.+</p>+<p>This document has been produced as part of the <a href=+"http://www.w3.org/MarkUp/">W3C HTML Activity</a>. The goals of+the <a href="http://www.w3.org/MarkUp/Group/">HTML Working+Group</a> <i>(<a href="http://cgi.w3.org/MemberAccess/">members+only</a>)</i> are discussed in the <a href=+"http://www.w3.org/MarkUp/Group/HTMLcharter">HTML Working Group+charter</a> <i>(<a href="http://cgi.w3.org/MemberAccess/">members+only</a>)</i>.</p>++<p>A list of current W3C Recommendations and other technical documents+can be found at <a+href="http://www.w3.org/TR">http://www.w3.org/TR</a>.</p>++<p>Public discussion on <abbr title="HyperText Markup+Language">HTML</abbr> features takes place on the mailing list <a+href="mailto:www-html@w3.org"> www-html@w3.org</a> (<a href=+"http://lists.w3.org/Archives/Public/www-html/">archive</a>).</p>++<p>Please report errors in this document to <a+href="mailto:www-html-editor@w3.org">www-html-editor@w3.org</a>.</p>++<p>The list of known errors in this specification is available at <a+href="http://www.w3.org/2000/01/REC-xhtml1-20000126-errata">http://www.w3.org/2000/01/REC-xhtml1-20000126-errata</a>.</p>++<h2 class="notoc"><a id="toc" name="toc">Contents</a></h2>++<div class="contents">+<ul class="toc">+<li class="tocline">1. <a href="#xhtml">What is XHTML?</a>++<ul class="toc">+<li class="tocline">1.1 <a href="#html4">What is HTML 4?</a></li>++<li class="tocline">1.2 <a href="#xml">What is XML?</a></li>++<li class="tocline">1.3 <a href="#why">Why the need for XHTML?</a></li>+</ul>+</li>++<li class="tocline">2. <a href="#defs">Definitions</a>++<ul class="toc">+<li class="tocline">2.1 <a href="#terms">Terminology</a></li>++<li class="tocline">2.2 <a href="#general">General Terms</a></li>+</ul>+</li>++<li class="tocline">3. <a href="#normative">Normative Definition of XHTML 1.0</a>+++<ul class="toc">+<li class="tocline">3.1 <a href="#docconf">Document Conformance</a></li>++<li class="tocline">3.2 <a href="#uaconf">User Agent Conformance</a></li>+</ul>+</li>++<li class="tocline">4. <a href="#diffs">Differences with HTML 4</a>++</li>++<li class="tocline">5. <a href="#issues">Compatibility Issues</a>++<ul class="toc">+<li class="tocline">5.1 <a href="#media">Internet Media Types</a></li>+</ul>+</li>++<li class="tocline">6. <a href="#future">Future Directions</a>++<ul class="toc">+<li class="tocline">6.1 <a href="#mods">Modularizing HTML</a></li>++<li class="tocline">6.2 <a href="#extensions">Subsets and Extensibility</a></li>++<li class="tocline">6.3 <a href="#profiles">Document Profiles</a></li>+</ul>+</li>++<li class="tocline"><a href="#dtds">Appendix A. DTDs</a></li>++<li class="tocline"><a href="#prohibitions">Appendix B. Element+Prohibitions</a></li>++<li class="tocline"><a href="#guidelines">Appendix C. HTML Compatibility Guidelines</a></li>++<li class="tocline"><a href="#acks">Appendix D. Acknowledgements</a></li>++<li class="tocline"><a href="#refs">Appendix E. References</a></li>+</ul>+</div>++<!--OddPage-->+<h1><a name="xhtml" id="xhtml">1. What is XHTML?</a></h1>++<p>XHTML is a family of current and future document types and modules that+reproduce, subset, and extend HTML&nbsp;4 <a href="#ref-html4">[HTML]</a>. XHTML family document types are <abbr title="Extensible Markup Language">XML</abbr> based,+and ultimately are designed to work in conjunction with XML-based user agents.+The details of this family and its evolution are+discussed in more detail in the section on <a href="#future">Future+Directions</a>. </p>++<p>XHTML 1.0 (this specification) is the first document type in the XHTML+family. It is a reformulation of the three HTML&nbsp;4 document types as+applications of XML 1.0 <a href="#ref-xml"> [XML]</a>. It is intended+to be used as a language for content that is both XML-conforming and, if some+simple <a href="#guidelines">guidelines</a> are followed,+operates in HTML&nbsp;4 conforming user agents. Developers who migrate+their content to XHTML 1.0 will realize the following benefits:</p>++<ul>+<li>XHTML documents are XML conforming. As such, they are readily viewed,+edited, and validated with standard XML tools.</li>+<li>XHTML documents can be written to+to operate as well or better than they did before in existing+HTML&nbsp;4-conforming user agents as well as in new, XHTML 1.0 conforming user+agents.</li>+<li>XHTML documents can utilize applications (e.g. scripts and applets) that rely+upon either the HTML Document Object Model or the XML Document Object Model <a+href="#ref-dom">[DOM]</a>.</li>+<li>As the XHTML family evolves, documents conforming to XHTML 1.0 will be more+likely to interoperate within and among various XHTML environments.</li>+</ul>++<p>The XHTML family is the next step in the evolution of the Internet. By+migrating to XHTML today, content developers can enter the XML world with all+of its attendant benefits, while still remaining confident in their+content's backward and future compatibility.</p>++<h2><a name="html4" id="html4">1.1 What is HTML&nbsp;4?</a></h2>++<p>HTML 4 <a href="#ref-html4">[HTML]</a> is an <abbr title="Standard+Generalized Markup Language">SGML</abbr> (Standard+Generalized Markup Language) application conforming to+International Standard <abbr title="Organization for International+Standardization">ISO</abbr> 8879, and is widely regarded as the+standard publishing language of the World Wide Web.</p>++<p>SGML is a language for describing markup languages,+particularly those used in electronic document exchange, document+management, and document publishing. HTML is an example of a+language defined in SGML.</p>++<p>SGML has been around since the middle 1980's and has remained+quite stable. Much of this stability stems from the fact that the+language is both feature-rich and flexible. This flexibility,+however, comes at a price, and that price is a level of+complexity that has inhibited its adoption in a diversity of+environments, including the World Wide Web.</p>++<p>HTML, as originally conceived, was to be a language for the+exchange of scientific and other technical documents, suitable+for use by non-document specialists. HTML addressed the problem+of SGML complexity by specifying a small set of structural and+semantic tags suitable for authoring relatively simple documents.+In addition to simplifying the document structure, HTML added+support for hypertext. Multimedia capabilities were added+later.</p>++<p>In a remarkably short space of time, HTML became wildly+popular and rapidly outgrew its original purpose. Since HTML's+inception, there has been rapid invention of new elements for use+within HTML (as a standard) and for adapting HTML to vertical,+highly specialized, markets. This plethora of new elements has+led to compatibility problems for documents across different+platforms.</p>++<p>As the heterogeneity of both software and platforms rapidly+proliferate, it is clear that the suitability of 'classic' HTML&nbsp;4+for use on these platforms is somewhat limited.</p>++<h2><a name="xml" id="xml">1.2 What is XML?</a></h2>++<p>XML<sup>&#8482;</sup> is the shorthand for Extensible Markup+Language, and is an acronym of Extensible Markup Language <a+href="#ref-xml">[XML]</a>.</p>++<p>XML was conceived as a means of regaining the power and+flexibility of SGML without most of its complexity. Although a+restricted form of SGML, XML nonetheless preserves most of SGML's+power and richness, and yet still retains all of SGML's commonly+used features.</p>++<p>While retaining these beneficial features, XML removes many of+the more complex features of SGML that make the authoring and+design of suitable software both difficult and costly.</p>++<h2><a name="why" id="why">1.3 Why the need for XHTML?</a></h2>++<p>The benefits of migrating to XHTML 1.0 are described above. Some of the+benefits of migrating to XHTML in general are:</p>++<ul>+<li>Document developers and user agent designers are constantly+discovering new ways to express their ideas through new markup. In XML, it is+relatively easy to introduce new elements or additional element+attributes.  The XHTML family is designed to accommodate these extensions+through XHTML modules and techniques for developing new XHTML-conforming+modules (described in the forthcoming XHTML Modularization specification).+These modules will permit the combination of existing and+new feature sets when developing content and when designing new user+agents.</li>++<li>Alternate ways of accessing the Internet are constantly being+introduced.  Some estimates indicate that by the year 2002, 75% of+Internet document viewing will be carried out on these alternate+platforms.  The XHTML family is designed with general user agent+interoperability in mind. Through a new user agent and document profiling+mechanism, servers, proxies, and user agents will be able to perform+best effort content transformation. Ultimately, it will be possible to+develop XHTML-conforming content that is usable by any XHTML-conforming+user agent.</li>++</ul>+<!--OddPage-->+<h1><a name="defs" id="defs">2. Definitions</a></h1>++<h2><a name="terms" id="terms">2.1 Terminology</a></h2>++<p>The following terms are used in this specification. These+terms extend the definitions in <a href="#ref-rfc2119">+[RFC2119]</a> in ways based upon similar definitions in ISO/<abbr+title="International Electro-technical Commission">IEC</abbr>+9945-1:1990 <a href="#ref-posix">[POSIX.1]</a>:</p>++<dl>+<dt>Implementation-defined</dt>++<dd>A value or behavior is implementation-defined when it is left+to the implementation to define [and document] the corresponding+requirements for correct document construction.</dd>++<dt>May</dt>++<dd>With respect to implementations, the word "may" is to be+interpreted as an optional feature that is not required in this+specification but can be provided. With respect to <a href=+"#docconf">Document Conformance</a>, the word "may" means that+the optional feature must not be used. The term "optional" has+the same definition as "may".</dd>++<dt>Must</dt>++<dd>In this specification, the word "must" is to be interpreted+as a mandatory requirement on the implementation or on Strictly+Conforming XHTML Documents, depending upon the context. The term+"shall" has the same definition as "must".</dd>++<dt>Reserved</dt>++<dd>A value or behavior is unspecified, but it is not allowed to+be used by Conforming Documents nor to be supported by a+Conforming User Agents.</dd>++<dt>Should</dt>++<dd>With respect to implementations, the word "should" is to be+interpreted as an implementation recommendation, but not a+requirement. With respect to documents, the word "should" is to+be interpreted as recommended programming practice for documents+and a requirement for Strictly Conforming XHTML Documents.</dd>++<dt>Supported</dt>++<dd>Certain facilities in this specification are optional. If a+facility is supported, it behaves as specified by this+specification.</dd>++<dt>Unspecified</dt>++<dd>When a value or behavior is unspecified, the specification+defines no portability requirements for a facility on an+implementation even when faced with a document that uses the+facility. A document that requires specific behavior in such an+instance, rather than tolerating any behavior when using that+facility, is not a Strictly Conforming XHTML Document.</dd>+</dl>++<h2><a name="general" id="general">2.2 General Terms</a></h2>++<dl>+<dt>Attribute</dt>++<dd>An attribute is a parameter to an element declared in the+DTD. An attribute's type and value range, including a possible+default value, are defined in the DTD.</dd>++<dt>DTD</dt>++<dd>A DTD, or document type definition, is a collection of XML+declarations that, as a collection, defines the legal structure,+<span class="term">elements</span>, and <span class="term">+attributes</span> that are available for use in a document that+complies to the DTD.</dd>++<dt>Document</dt>++<dd>A document is a stream of data that, after being combined+with any other streams it references, is structured such that it+holds information contained within <span class="term">+elements</span> that are organized as defined in the associated+<span class="term">DTD</span>. See <a href="#docconf">Document+Conformance</a> for more information.</dd>++<dt>Element</dt>++<dd>An element is a document structuring unit declared in the+<span class="term">DTD</span>. The element's content model is+defined in the <span class="term">DTD</span>, and additional+semantics may be defined in the prose description of the+element.</dd>++<dt><a name="facilities" id="facilities">Facilities</a></dt>++<dd>Functionality includes <span class="term">elements</span>,+<span class="term">attributes</span>, and the semantics+associated with those <span class="term">elements</span> and+<span class="term">attributes</span>. An implementation+supporting that functionality is said to provide the necessary+facilities.</dd>++<dt>Implementation</dt>++<dd>An implementation is a system that provides collection of+<span class="term">facilities</span> and services that supports+this specification. See <a href="#uaconf">User Agent+Conformance</a> for more information.</dd>++<dt>Parsing</dt>++<dd>Parsing is the act whereby a <span class="term">+document</span> is scanned, and the information contained within+the <span class="term">document</span> is filtered into the+context of the <span class="term">elements</span> in which the+information is structured.</dd>++<dt>Rendering</dt>++<dd>Rendering is the act whereby the information in a <span+class="term">document</span> is presented. This presentation is+done in the form most appropriate to the environment (e.g.+aurally, visually, in print).</dd>++<dt>User Agent</dt>++<dd>A user agent is an <span class="term">implementation</span>+that retrieves and processes XHTML documents. See <a href=+"#uaconf">User Agent Conformance</a> for more information.</dd>++<dt>Validation</dt>++<dd>Validation is a process whereby <span class="term">+documents</span> are verified against the associated <span class=+"term">DTD</span>, ensuring that the structure, use of <span+class="term">elements</span>, and use of <span class="term">+attributes</span> are consistent with the definitions in the+<span class="term">DTD</span>.</dd>++<dt><a name="wellformed" id="wellformed">Well-formed</a></dt>++<dd>A <span class="term">document</span> is well-formed when it+is structured according to the rules defined in <a href=+"http://www.w3.org/TR/REC-xml#sec-well-formed">Section 2.1</a> of+the XML 1.0 Recommendation <a href="#ref-xml">[XML]</a>.+Basically, this definition states that elements, delimited by+their start and end tags, are nested properly within one+another.</dd>+</dl>++<!--OddPage-->+<h1><a name="normative" id="normative">3. Normative Definition of+XHTML 1.0</a></h1>++<h2><a name="docconf" id="docconf">3.1 Document+Conformance</a></h2>++<p>This version of XHTML provides a definition of strictly+conforming XHTML documents, which are restricted to tags and+attributes from the XHTML namespace. See <a href=+"#well-formed">Section 3.1.2</a> for information on using XHTML+with other namespaces, for instance, to include metadata+expressed in <abbr title="Resource Description Format">RDF</abbr> within XHTML documents.</p>++<h3><a name="strict" id="strict">3.1.1 Strictly Conforming+Documents</a></h3>++<p>A Strictly Conforming XHTML Document is a document that+requires only the facilities described as mandatory in this+specification. Such a document must meet all of the following+criteria:</p>++<ol>+<li>+<p>It must validate against one of the three DTDs found in <a+href="#dtds">Appendix&#160;A</a>.</p>+</li>++<li>+<p>The root element of the document must be <code>+&lt;html&gt;</code>.</p>+</li>++<li>+<p>The root element of the document must designate the XHTML+namespace using the <code>xmlns</code> attribute <a href=+"#ref-xmlns">[XMLNAMES]</a>. The namespace for XHTML is+defined to be+<code>http://www.w3.org/1999/xhtml</code>.</p>+</li>++<li>+<p>There must be a DOCTYPE declaration in the document prior to+the root element. The public identifier included in+the DOCTYPE declaration must reference one of the three DTDs+found in <a href="#dtds">Appendix&#160;A</a> using the respective+Formal Public Identifier. The system identifier may be changed to reflect+local system conventions.</p>++<pre>+&lt;!DOCTYPE html+     PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"+     "DTD/xhtml1-strict.dtd"&gt;++&lt;!DOCTYPE html+     PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"+     "DTD/xhtml1-transitional.dtd"&gt;++&lt;!DOCTYPE html+     PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN"+     "DTD/xhtml1-frameset.dtd"&gt;+</pre>+</li>+</ol>++<p>Here is an example of a minimal XHTML document.</p>++<div class="good">+<pre>+&lt;?xml version="1.0" encoding="UTF-8"?&gt;+&lt;!DOCTYPE html+     PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"+    "DTD/xhtml1-strict.dtd"&gt;+&lt;html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"&gt;+  &lt;head&gt;+    &lt;title&gt;Virtual Library&lt;/title&gt;+  &lt;/head&gt;+  &lt;body&gt;+    &lt;p&gt;Moved to &lt;a href="http://vlib.org/"&gt;vlib.org&lt;/a&gt;.&lt;/p&gt;+  &lt;/body&gt;+&lt;/html&gt;</pre>+</div>++<p>Note that in this example, the XML declaration is included. An XML+declaration like the one above is+not required in all XML documents. XHTML document authors are strongly encouraged to use XML declarations in all their documents. Such a declaration is required+when the character encoding of the document is other than the default UTF-8 or+UTF-16.</p>++<h3><a name="well-formed" id="well-formed">3.1.2 Using XHTML with+other namespaces</a></h3>++<p>The XHTML namespace may be used with other XML namespaces+as per <a href="#ref-xmlns">[XMLNAMES]</a>, although such+documents are not strictly conforming XHTML 1.0 documents as+defined above. Future work by W3C will address ways to specify+conformance for documents involving multiple namespaces.</p>++<p>The following example shows the way in which XHTML 1.0 could+be used in conjunction with the MathML Recommendation:</p>++<div class="good">+<pre>+&lt;html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"&gt;+  &lt;head&gt;+    &lt;title&gt;A Math Example&lt;/title&gt;+  &lt;/head&gt;+  &lt;body&gt;+    &lt;p&gt;The following is MathML markup:&lt;/p&gt;+    &lt;math xmlns="http://www.w3.org/1998/Math/MathML"&gt;+      &lt;apply&gt; &lt;log/&gt;+        &lt;logbase&gt;+          &lt;cn&gt; 3 &lt;/cn&gt;+        &lt;/logbase&gt;+        &lt;ci&gt; x &lt;/ci&gt;+      &lt;/apply&gt;+    &lt;/math&gt;+  &lt;/body&gt;+&lt;/html&gt;+</pre>+</div>++<p>The following example shows the way in which XHTML 1.0 markup+could be incorporated into another XML namespace:</p>++<div class="good">+<pre>+&lt;?xml version="1.0" encoding="UTF-8"?&gt;+&lt;!-- initially, the default namespace is "books" --&gt;+&lt;book xmlns='urn:loc.gov:books'+    xmlns:isbn='urn:ISBN:0-395-36341-6' xml:lang="en" lang="en"&gt;+  &lt;title&gt;Cheaper by the Dozen&lt;/title&gt;+  &lt;isbn:number&gt;1568491379&lt;/isbn:number&gt;+  &lt;notes&gt;+    &lt;!-- make HTML the default namespace for a hypertext commentary --&gt;+    &lt;p xmlns='http://www.w3.org/1999/xhtml'&gt;+        This is also available &lt;a href="http://www.w3.org/"&gt;online&lt;/a&gt;.+    &lt;/p&gt;+  &lt;/notes&gt;+&lt;/book&gt;+</pre>+</div>++<h2><a name="uaconf" id="uaconf">3.2 User Agent+Conformance</a></h2>++<p>A conforming user agent must meet all of the following+criteria:</p>++<ol>+<li>In order to be consistent with the XML 1.0 Recommendation <a+href="#ref-xml">[XML]</a>, the user agent must parse and evaluate+an XHTML document for well-formedness. If the user agent claims+to be a validating user agent, it must also validate documents+against their referenced DTDs according to <a href="#ref-xml">+[XML]</a>.</li>++<li>When the user agent claims to support <a href="#facilities">+facilities</a> defined within this specification or required by+this specification through normative reference, it must do so in+ways consistent with the facilities' definition.</li>++<li>When a user agent processes an XHTML document as generic XML,+it shall only recognize attributes of type+<code>ID</code> (e.g. the <code>id</code> attribute on most XHTML elements)+as fragment identifiers.</li>++<li>If a user agent encounters an element it does not recognize,+it must render the element's content.</li>++<li>If a user agent encounters an attribute it does not+recognize, it must ignore the entire attribute specification+(i.e., the attribute and its value).</li>++<li>If a user agent encounters an attribute value it doesn't+recognize, it must use the default attribute value.</li>++<li>If it encounters an entity reference (other than one+of the predefined entities) for which the User Agent has+processed no declaration (which could happen if the declaration+is in the external subset which the User Agent hasn't read), the entity+reference should be rendered as the characters (starting+with the ampersand and ending with the semi-colon) that+make up the entity reference.</li>++<li>When rendering content, User Agents that encounter+characters or character entity references that are recognized but not renderable should display the document in such a way that it is obvious to the user that normal rendering has not taken place.</li>++<li>+The following characters are defined in [XML] as whitespace characters:++<ul>+<li>Space (&amp;#x0020;)</li>+<li>Tab (&amp;#x0009;)</li>+<li>Carriage return (&amp;#x000D;)</li>+<li>Line feed (&amp;#x000A;)</li>+</ul>++<p>+The XML processor normalizes different system's line end codes into one+single line-feed character, that is passed up to the application. The XHTML+user agent in addition, must treat the following characters as whitespace:+</p>++<ul>+<li>Form feed (&amp;#x000C;)</li>+<li>Zero-width space (&amp;#x200B;)</li>+</ul>++<p>+In elements where the 'xml:space' attribute is set to 'preserve', the user+agent must leave all whitespace characters intact (with the exception of+leading and trailing whitespace characters, which should be removed).+Otherwise, whitespace+is handled according to the following rules:+</p>++<ul>+<li>+All whitespace surrounding block elements should be removed.+</li>+<li>+Comments are removed entirely and do not affect whitespace handling. One+whitespace character on either side of a comment is treated as two white+space characters.+</li>+<li>+Leading and trailing whitespace inside a block element must be removed.+</li>+<li>Line feed characters within a block element must be converted into a+space (except when the 'xml:space' attribute is set to 'preserve').+</li>+<li>+A sequence of white space characters must be reduced to a single space+character (except when the 'xml:space' attribute is set to 'preserve').+</li>+<li>+With regard to rendition,+the User Agent should render the content in a+manner appropriate to the language in which the content is written.+In languages whose primary script is Latinate, the ASCII space+character is typically used to encode both grammatical word boundaries and+typographic whitespace; in languages whose script is related to Nagari+(e.g., Sanskrit, Thai, etc.), grammatical boundaries may be encoded using+the ZW 'space' character, but will not typically be represented by+typographic whitespace in rendered output; languages using Arabiform scripts+may encode typographic whitespace using a space character, but may also use+the ZW space character to delimit 'internal' grammatical boundaries (what+look like words in Arabic to an English eye frequently encode several words,+e.g. 'kitAbuhum' = 'kitAbu-hum' = 'book them' == their book); and languages+in the Chinese script tradition typically neither encode such delimiters nor+use typographic whitespace in this way.+</li>+</ul>++<p>Whitespace in attribute values is processed according to <a+href="#ref-xml">[XML]</a>.</p>+</li>+</ol>++<!--OddPage-->+<h1><a name="diffs" id="diffs">4. Differences with HTML&nbsp;4</a></h1>++<p>Due to the fact that XHTML is an XML application, certain+practices that were perfectly legal in SGML-based HTML&nbsp;4 <a+href="#ref-html4">[HTML]</a> must be changed.</p>++<h2><a name="h-4.1" id="h-4.1">4.1 Documents must be+well-formed</a></h2>++<p><a href="#wellformed">Well-formedness</a> is a new concept+introduced by <a href="#ref-xml">[XML]</a>. Essentially this+means that all elements must either have closing tags or be+written in a special form (as described below), and that all the+elements must nest.</p>++<p>Although overlapping is illegal in SGML, it was widely+tolerated in existing browsers.</p>++<div class="good">+<p><strong><em>CORRECT: nested elements.</em></strong></p>++<p>&lt;p&gt;here is an emphasized+&lt;em&gt;paragraph&lt;/em&gt;.&lt;/p&gt;</p>+</div>++<div class="bad">+<p><strong><em>INCORRECT: overlapping elements</em></strong></p>++<p>&lt;p&gt;here is an emphasized+&lt;em&gt;paragraph.&lt;/p&gt;&lt;/em&gt;</p>+</div>++<h2><a name="h-4.2" id="h-4.2">4.2 Element and attribute+names must be in lower case</a></h2>++<p>XHTML documents must use lower case for all HTML element and+attribute names. This difference is necessary because XML is+case-sensitive e.g. &lt;li&gt; and &lt;LI&gt; are different+tags.</p>++<h2><a name="h-4.3" id="h-4.3">4.3 For non-empty elements,+end tags are required</a></h2>++<p>In SGML-based HTML 4 certain elements were permitted to omit+the end tag; with the elements that followed implying closure.+This omission is not permitted in XML-based XHTML. All elements+other than those declared in the DTD as <code>EMPTY</code> must+have an end tag.</p>++<div class="good">+<p><strong><em>CORRECT: terminated elements</em></strong></p>++<p>&lt;p&gt;here is a paragraph.&lt;/p&gt;&lt;p&gt;here is+another paragraph.&lt;/p&gt;</p>+</div>++<div class="bad">+<p><strong><em>INCORRECT: unterminated elements</em></strong></p>++<p>&lt;p&gt;here is a paragraph.&lt;p&gt;here is another+paragraph.</p>+</div>++<h2><a name="h-4.4" id="h-4.4">4.4 Attribute values must+always be quoted</a></h2>++<p>All attribute values must be quoted, even those which appear+to be numeric.</p>++<div class="good">+<p><strong><em>CORRECT: quoted attribute values</em></strong></p>++<p>&lt;table rows="3"&gt;</p>+</div>++<div class="bad">+<p><strong><em>INCORRECT: unquoted attribute values</em></strong></p>++<p>&lt;table rows=3&gt;</p>+</div>++<h2><a name="h-4.5" id="h-4.5">4.5 Attribute+Minimization</a></h2>++<p>XML does not support attribute minimization. Attribute-value+pairs must be written in full. Attribute names such as <code>+compact</code> and <code>checked</code> cannot occur in elements+without their value being specified.</p>++<div class="good">+<p><strong><em>CORRECT: unminimized attributes</em></strong></p>++<p>&lt;dl compact="compact"&gt;</p>+</div>++<div class="bad">+<p><strong><em>INCORRECT: minimized attributes</em></strong></p>++<p>&lt;dl compact&gt;</p>+</div>++<h2><a name="h-4.6" id="h-4.6">4.6 Empty Elements</a></h2>++<p>Empty elements must either have an end tag or the start tag must end with <code>/&gt;</code>. For instance,+<code>&lt;br/&gt;</code> or <code>&lt;hr&gt;&lt;/hr&gt;</code>. See <a+href="#guidelines">HTML Compatibility Guidelines</a> for information on ways to+ensure this is backward compatible with HTML 4 user agents.</p>++<div class="good">+<p><strong><em>CORRECT: terminated empty tags</em></strong></p>++<p>&lt;br/&gt;&lt;hr/&gt;</p>+</div>++<div class="bad">+<p><strong><em>INCORRECT: unterminated empty tags</em></strong></p>++<p>&lt;br&gt;&lt;hr&gt;</p>+</div>++<h2><a name="h-4.7" id="h-4.7">4.7 Whitespace handling in+attribute values</a></h2>++<p>In attribute values, user agents will strip leading and+trailing whitespace from attribute values and map sequences+of one or more whitespace characters (including line breaks) to+a single inter-word space (an ASCII space character for western+scripts). See <a href="http://www.w3.org/TR/REC-xml#AVNormalize">+Section 3.3.3</a> of <a href="#ref-xml">[XML]</a>.</p>++<h2><a name="h-4.8" id="h-4.8">4.8 Script and Style+elements</a></h2>++<p>In XHTML, the script and style elements are declared as having+<code>#PCDATA</code> content. As a result, <code>&lt;</code> and+<code>&amp;</code> will be treated as the start of markup, and+entities such as <code>&amp;lt;</code> and <code>&amp;amp;</code>+will be recognized as entity references by the XML processor to+<code>&lt;</code> and <code>&amp;</code> respectively. Wrapping+the content of the script or style element within a <code>+CDATA</code> marked section avoids the expansion of these+entities.</p>++<div class="good">+<pre>+&lt;script&gt;+ &lt;![CDATA[+ ... unescaped script content ...+ ]]&gt;+ &lt;/script&gt;+</pre>+</div>++<p><code>CDATA</code> sections are recognized by the XML+processor and appear as nodes in the Document Object Model, see+<a href=+"http://www.w3.org/TR/REC-DOM-Level-1/level-one-core.html#ID-E067D597">+Section 1.3</a> of the DOM Level 1 Recommendation <a href=+"#ref-dom">[DOM]</a>.</p>++<p>An alternative is to use external script and style+documents.</p>++<h2><a name="h-4.9" id="h-4.9">4.9 SGML exclusions</a></h2>++<p>SGML gives the writer of a DTD the ability to exclude specific+elements from being contained within an element. Such+prohibitions (called "exclusions") are not possible in XML.</p>++<p>For example, the HTML 4 Strict DTD forbids the nesting of an+'<code>a</code>' element within another '<code>a</code>' element+to any descendant depth. It is not possible to spell out such+prohibitions in XML. Even though these prohibitions cannot be+defined in the DTD, certain elements should not be nested. A+summary of such elements and the elements that should not be+nested in them is found in the normative <a href="#prohibitions">+Appendix&#160;B</a>.</p>++<h2><a name="h-4.10" id="h-4.10">4.10 The elements with 'id' and 'name'+attributes</a></h2>++<p>HTML 4 defined the <code>name</code> attribute for the elements+<code>a</code>,+<code>applet</code>, <code>form</code>, <code>frame</code>,+<code>iframe</code>, <code>img</code>, and <code>map</code>.+HTML 4 also introduced+the <code>id</code> attribute. Both of these attributes are designed to be+used as fragment identifiers.</p>+<p>In XML, fragment identifiers are of type <code>ID</code>, and+there can only be a single attribute of type <code>ID</code> per element.+Therefore, in XHTML 1.0 the <code>id</code>+attribute is defined to be of type <code>ID</code>. In order to+ensure that XHTML 1.0 documents are well-structured XML documents, XHTML 1.0+documents MUST use the <code>id</code> attribute when defining fragment+identifiers, even on elements that historically have also had a+<code>name</code> attribute.+See the <a href="#guidelines">HTML Compatibility+Guidelines</a> for information on ensuring such anchors are backwards+compatible when serving XHTML documents as media type <code>text/html</code>.+</p>+<p>Note that in XHTML 1.0, the <code>name</code> attribute of these+elements is formally deprecated, and will be removed in a+subsequent version of XHTML.</p>++<!--OddPage-->+<h1><a name="issues" id="issues">5. Compatibility Issues</a></h1>++<p>Although there is no requirement for XHTML 1.0 documents to be+compatible with existing user agents, in practice this is easy to+accomplish. Guidelines for creating compatible documents can be+found in <a href="#guidelines">Appendix&#160;C</a>.</p>++<h2><a name="media" id="media">5.1 Internet Media Type</a></h2>+<p>As of the publication of this recommendation, the general+recommended MIME labeling for XML-based applications+has yet to be resolved.</p>++<p>However, XHTML Documents which follow the guidelines set forth+in <a href="#guidelines">Appendix C</a>, "HTML Compatibility Guidelines" may be+labeled with the Internet Media Type "text/html", as they+are compatible with most HTML browsers. This document+makes no recommendation about MIME labeling of other+XHTML documents.</p>++<!--OddPage-->+<h1><a name="future" id="future">6. Future Directions</a></h1>++<p>XHTML 1.0 provides the basis for a family of document types+that will extend and subset XHTML, in order to support a wide+range of new devices and applications, by defining modules and+specifying a mechanism for combining these modules. This+mechanism will enable the extension and sub-setting of XHTML 1.0+in a uniform way through the definition of new modules.</p>++<h2><a name="mods" id="mods">6.1 Modularizing HTML</a></h2>++<p>As the use of XHTML moves from the traditional desktop user+agents to other platforms, it is clear that not all of the XHTML+elements will be required on all platforms. For example a hand+held device or a cell-phone may only support a subset of XHTML+elements.</p>++<p>The process of modularization breaks XHTML up into a series of+smaller element sets. These elements can then be recombined to+meet the needs of different communities.</p>++<p>These modules will be defined in a later W3C document.</p>++<h2><a name="extensions" id="extensions">6.2 Subsets and+Extensibility</a></h2>++<p>Modularization brings with it several advantages:</p>++<ul>+<li>+<p>It provides a formal mechanism for sub-setting XHTML.</p>+</li>++<li>+<p>It provides a formal mechanism for extending XHTML.</p>+</li>++<li>+<p>It simplifies the transformation between document types.</p>+</li>++<li>+<p>It promotes the reuse of modules in new document types.</p>+</li>+</ul>++<h2><a name="profiles" id="profiles">6.3 Document+Profiles</a></h2>++<p>A document profile specifies the syntax and semantics of a set+of documents. Conformance to a document profile provides a basis+for interoperability guarantees. The document profile specifies+the facilities required to process documents of that type, e.g.+which image formats can be used, levels of scripting, style sheet+support, and so on.</p>++<p>For product designers this enables various groups to define+their own standard profile.</p>++<p>For authors this will obviate the need to write several+different versions of documents for different clients.</p>++<p>For special groups such as chemists, medical doctors, or+mathematicians this allows a special profile to be built using+standard HTML elements plus a group of elements geared to the+specialist's needs.</p>++<!--OddPage-->+<h1><a name="appendices" id="appendices"></a>+<a name="dtds" id="dtds">Appendix A. DTDs</a></h1>++<p><b>This appendix is normative.</b></p>++<p>These DTDs and entity sets form a normative part of this+specification. The complete set of DTD files together with an XML+declaration and SGML Open Catalog is included in the <a href=+"xhtml1.zip">zip file</a> for this specification.</p>++<h2><a name="h-A1" id="h-A1">A.1 Document Type+Definitions</a></h2>++<p>These DTDs approximate the HTML 4 DTDs. It is likely that+when the DTDs are modularized, a method of DTD construction will+be employed that corresponds more closely to HTML 4.</p>++<ul>+<li>+<p><a href="DTD/xhtml1-strict.dtd" type="text/plain">+XHTML-1.0-Strict</a></p>+</li>++<li>+<p><a href="DTD/xhtml1-transitional.dtd" type="text/plain">+XHTML-1.0-Transitional</a></p>+</li>++<li>+<p><a href="DTD/xhtml1-frameset.dtd" type="text/plain">+XHTML-1.0-Frameset</a></p>+</li>+</ul>++<h2><a name="h-A2" id="h-A2">A.2 Entity Sets</a></h2>++<p>The XHTML entity sets are the same as for HTML 4, but have+been modified to be valid XML 1.0 entity declarations. Note the+entity for the Euro currency sign (<code>&amp;euro;</code> or+<code>&amp;#8364;</code> or <code>&amp;#x20AC;</code>) is defined+as part of the special characters.</p>++<ul>+<li>+<p><a href="DTD/xhtml-lat1.ent">Latin-1 characters</a></p>+</li>++<li>+<p><a href="DTD/xhtml-special.ent">Special characters</a></p>+</li>++<li>+<p><a href="DTD/xhtml-symbol.ent">Symbols</a></p>+</li>+</ul>++<!--OddPage-->+<h1><a name="prohibitions" id="prohibitions">Appendix B. Element+Prohibitions</a></h1>++<p><b>This appendix is normative.</b></p>++<p>The following elements have prohibitions on which elements+they can contain (see <a href="#h-4.9">Section 4.9</a>). This+prohibition applies to all depths of nesting, i.e. it contains+all the descendant elements.</p>++<dl><dt><code class="tag">a</code></dt>+<dd>+cannot contain other <code>a</code> elements.</dd>+<dt><code class="tag">pre</code></dt>+<dd>cannot contain the <code>img</code>, <code>object</code>,+<code>big</code>, <code>small</code>, <code>sub</code>, or <code>+sup</code> elements.</dd>++<dt><code class="tag">button</code></dt>+<dd>cannot contain the <code>input</code>, <code>select</code>,+<code>textarea</code>, <code>label</code>, <code>button</code>,+<code>form</code>, <code>fieldset</code>, <code>iframe</code> or+<code>isindex</code> elements.</dd>+<dt><code class="tag">label</code></dt>+<dd>cannot contain other <code class="tag">label</code> elements.</dd>+<dt><code class="tag">form</code></dt>+<dd>cannot contain other <code>form</code> elements.</dd>+</dl>++<!--OddPage-->+<h1><a name="guidelines" id="guidelines">Appendix C.+HTML Compatibility Guidelines</a></h1>++<p><b>This appendix is informative.</b></p>++<p>This appendix summarizes design guidelines for authors who+wish their XHTML documents to render on existing HTML user+agents.</p>++<h2>C.1 Processing Instructions</h2>+<p>Be aware that processing instructions are rendered on some+user agents. However, also note that when the XML declaration is not included+in a document, the document can only use the default character encodings UTF-8+or UTF-16.</p>++<h2>C.2 Empty Elements</h2>+<p>Include a space before the trailing <code>/</code> and <code>+&gt;</code> of empty elements, e.g. <code class="greenmono">+&lt;br&#160;/&gt;</code>, <code class="greenmono">+&lt;hr&#160;/&gt;</code> and <code class="greenmono">&lt;img+src="karen.jpg" alt="Karen"&#160;/&gt;</code>. Also, use the+minimized tag syntax for empty elements, e.g. <code class=+"greenmono">&lt;br /&gt;</code>, as the alternative syntax <code+class="greenmono">&lt;br&gt;&lt;/br&gt;</code> allowed by XML+gives uncertain results in many existing user agents.</p>++<h2>C.3 Element Minimization and Empty Element Content</h2>+<p>Given an empty instance of an element whose content model is+not <code>EMPTY</code> (for example, an empty title or paragraph)+do not use the minimized form (e.g. use <code class="greenmono">+&lt;p&gt; &lt;/p&gt;</code> and not <code class="greenmono">+&lt;p&#160;/&gt;</code>).</p>++<h2>C.4 Embedded Style Sheets and Scripts</h2>+<p>Use external style sheets if your style sheet uses <code>+&lt;</code> or <code>&amp;</code> or <code>]]&gt;</code> or <code>--</code>. Use+external scripts if your script uses <code>&lt;</code> or <code>+&amp;</code> or <code>]]&gt;</code> or <code>--</code>. Note that XML parsers+are permitted to silently remove the contents of comments. Therefore, the historical+practice of "hiding" scripts and style sheets within comments to make the+documents backward compatible is likely to not work as expected in XML-based+implementations.</p>++<h2>C.5 Line Breaks within Attribute Values</h2>+<p>Avoid line breaks and multiple whitespace characters within+attribute values. These are handled inconsistently by user+agents.</p>++<h2>C.6 Isindex</h2>+<p>Don't include more than one <code>isindex</code> element in+the document <code>head</code>. The <code>isindex</code> element+is deprecated in favor of the <code>input</code> element.</p>++<h2>C.7 The <code>lang</code> and <code>xml:lang</code> Attributes</h2>+<p>Use both the <code>lang</code> and <code>xml:lang</code>+attributes when specifying the language of an element. The value+of the <code>xml:lang</code> attribute takes precedence.</p>++<h2>C.8 Fragment Identifiers</h2>+<p>In XML, <abbr title="Uniform Resource Identifiers">URIs</abbr> [<a href="#ref-rfc2396">RFC2396</a>] that end with fragment identifiers of the form+<code>"#foo"</code> do not refer to elements with an attribute+<code>name="foo"</code>; rather, they refer to elements with an+attribute defined to be of type <code>ID</code>, e.g., the <code>+id</code> attribute in HTML 4. Many existing HTML clients don't+support the use of <code>ID</code>-type attributes in this way,+so identical values may be supplied for both of these attributes to ensure+maximum forward and backward compatibility (e.g., <code class=+"greenmono">&lt;a id="foo" name="foo"&gt;...&lt;/a&gt;</code>).</p>++<p>Further, since the set of+legal values for attributes of type <code>ID</code> is much smaller than+for those of type <code>CDATA</code>, the type of the <code>name</code>+attribute has been changed to <code>NMTOKEN</code>. This attribute is+constrained such that it can only have the same values as type+<code>ID</code>, or as the <code>Name</code> production in XML 1.0 Section+2.5, production 5. Unfortunately, this constraint cannot be expressed in the+XHTML 1.0 DTDs.  Because of this change, care must be taken when+converting existing HTML documents. The values of these attributes+must be unique within the document, valid, and any references to these+fragment identifiers (both+internal and external) must be updated should the values be changed during+conversion.</p>+<p>Finally, note that XHTML 1.0 has deprecated the+<code>name</code> attribute of the <code>a</code>, <code>applet</code>, <code>form</code>, <code>frame</code>, <code>iframe</code>, <code>img</code>, and <code>map</code>+elements, and it will be+removed from XHTML in subsequent versions.</p>++<h2>C.9 Character Encoding</h2>+<p>To specify a character encoding in the document, use both the+encoding attribute specification on the xml declaration (e.g.+<code class="greenmono">&lt;?xml version="1.0"+encoding="EUC-JP"?&gt;</code>) and a meta http-equiv statement+(e.g. <code class="greenmono">&lt;meta http-equiv="Content-type"+content='text/html; charset="EUC-JP"'&#160;/&gt;</code>). The+value of the encoding attribute of the xml processing instruction+takes precedence.</p>++<h2>C.10 Boolean Attributes</h2>+<p>Some HTML user agents are unable to interpret boolean+attributes when these appear in their full (non-minimized) form,+as required by XML 1.0. Note this problem doesn't affect user+agents compliant with HTML 4. The following attributes are+involved: <code>compact</code>, <code>nowrap</code>, <code>+ismap</code>, <code>declare</code>, <code>noshade</code>, <code>+checked</code>, <code>disabled</code>, <code>readonly</code>,+<code>multiple</code>, <code>selected</code>, <code>+noresize</code>, <code>defer</code>.</p>++<h2>C.11 Document Object Model and XHTML</h2>+<p>+The Document Object Model level 1 Recommendation [<a href="#ref-dom">DOM</a>]+defines document object model interfaces for XML and HTML 4. The HTML 4+document object model specifies that HTML element and attribute names are+returned in upper-case. The XML document object model specifies that+element and attribute names are returned in the case they are specified. In+XHTML 1.0, elements and attributes are specified in lower-case. This apparent difference can be+addressed in two ways:+</p>+<ol>+<li>Applications that access XHTML documents served as Internet media type+<code>text/html</code>+via the <abbr title="Document Object Model">DOM</abbr> can use the HTML DOM,+and can rely upon element and attribute names being returned in+upper-case from those interfaces.</li>+<li>Applications that access XHTML documents served as Internet media types+<code>text/xml</code> or <code>application/xml</code>+can also use the XML DOM. Elements and attributes will be returned in lower-case.+Also, some XHTML elements may or may+not appear+in the object tree because they are optional in the content model+(e.g. the <code>tbody</code> element within+<code>table</code>).  This occurs because in HTML 4 some elements were+permitted to be minimized such that their start and end tags are both omitted+(an SGML feature).+This is not possible in XML. Rather than require document authors to insert+extraneous elements, XHTML has made the elements optional.+Applications need to adapt to this+accordingly.</li>+</ol>++<h2>C.12 Using Ampersands in Attribute Values</h2>+<p>+When an attribute value contains an ampersand, it must be expressed as a character+entity reference+(e.g. "<code>&amp;amp;</code>"). For example, when the+<code>href</code> attribute+of the <code>a</code> element refers to a+CGI script that takes parameters, it must be expressed as+<code>http://my.site.dom/cgi-bin/myscript.pl?class=guest&amp;amp;name=user</code>+rather than as+<code>http://my.site.dom/cgi-bin/myscript.pl?class=guest&amp;name=user</code>.+</p>++<h2>C.13 Cascading Style Sheets (CSS) and XHTML</h2>++<p>The Cascading Style Sheets level 2 Recommendation [<a href="#ref-css2">CSS2</a>] defines style+properties which are applied to the parse tree of the HTML or XML+document.  Differences in parsing will produce different visual or+aural results, depending on the selectors used. The following hints+will reduce this effect for documents which are served without+modification as both media types:</p>++<ol>+<li>+CSS style sheets for XHTML should use lower case element and+attribute names.</li>+++<li>In tables, the tbody element will be inferred by the parser of an+HTML user agent, but not by the parser of an XML user agent. Therefore+you should always explicitly add a tbody element if it is referred to+in a CSS selector.</li>++<li>Within the XHTML name space, user agents are expected to+recognize the "id" attribute as an attribute of type ID.+Therefore, style sheets should be able to continue using the+shorthand "#" selector syntax even if the user agent does not read+the DTD.</li>++<li>Within the XHTML name space, user agents are expected to+recognize the "class" attribute. Therefore, style sheets should be+able to continue using the shorthand "." selector syntax.</li>++<li>+CSS defines different conformance rules for HTML and XML documents;+be aware that the HTML rules apply to XHTML documents delivered as+HTML and the XML rules apply to XHTML documents delivered as XML.</li>+</ol>+<!--OddPage-->+<h1><a name="acks" id="acks">Appendix D.+Acknowledgements</a></h1>++<p><b>This appendix is informative.</b></p>++<p>This specification was written with the participation of the+members of the W3C HTML working group:</p>++<dl>+<dd>Steven Pemberton, CWI (HTML Working Group Chair)<br />+Murray Altheim, Sun Microsystems<br />+Daniel Austin, AskJeeves (CNET: The Computer Network through July 1999)<br />+Frank Boumphrey, HTML Writers Guild<br />+John Burger, Mitre<br />+Andrew W. Donoho, IBM<br />+Sam Dooley, IBM<br />+Klaus Hofrichter, GMD<br />+Philipp Hoschka, W3C<br />+Masayasu Ishikawa, W3C<br />+Warner ten Kate, Philips Electronics<br />+Peter King, Phone.com<br />+Paula Klante, JetForm<br />+Shin'ichi Matsui, Panasonic (W3C visiting engineer through September 1999)<br />+Shane McCarron, Applied Testing and Technology (The Open Group through August+1999)<br />+Ann Navarro, HTML Writers Guild<br />+Zach Nies, Quark<br />+Dave Raggett, W3C/HP (W3C lead for HTML)<br />+Patrick Schmitz, Microsoft<br />+Sebastian Schnitzenbaumer, Stack Overflow<br />+Peter Stark, Phone.com<br />+Chris Wilson, Microsoft<br />+Ted Wugofski, Gateway 2000<br />+Dan Zigmond, WebTV Networks</dd>+</dl>++<!--OddPage-->+<h1><a name="refs" id="refs">Appendix E. References</a></h1>++<p><b>This appendix is informative.</b></p>++<dl>++<dt><a name="ref-css2" id="ref-css2"><b>[CSS2]</b></a></dt>++<dd><a href="http://www.w3.org/TR/1998/REC-CSS2-19980512">"Cascading Style Sheets, level 2 (CSS2) Specification"</a>, B.+Bos, H. W. Lie, C. Lilley, I. Jacobs, 12 May 1998.<br />+Latest version available at: <a href="http://www.w3.org/TR/REC-CSS2">+http://www.w3.org/TR/REC-CSS2</a></dd>++<dt><a name="ref-dom" id="ref-dom"><b>[DOM]</b></a></dt>++<dd><a href="http://www.w3.org/TR/1998/REC-DOM-Level-1-19981001">"Document Object Model (DOM) Level 1 Specification"</a>, Lauren+Wood <i>et al.</i>, 1 October 1998.<br />+Latest version available at: <a href="http://www.w3.org/TR/REC-DOM-Level-1">+http://www.w3.org/TR/REC-DOM-Level-1</a></dd>++<dt><a name="ref-html4" id="ref-html4"><b>[HTML]</b></a></dt>++<dd><a href="http://www.w3.org/TR/1999/REC-html401-19991224">"HTML 4.01 Specification"</a>, D. Raggett, A. Le&#160;Hors, I.+Jacobs, 24 December 1999.<br />+Latest version available at: <a href="http://www.w3.org/TR/html401">+http://www.w3.org/TR/html401</a></dd>++<dt><a name="ref-posix" id="ref-posix"><b>[POSIX.1]</b></a></dt>++<dd>"ISO/IEC 9945-1:1990 Information Technology - Portable+Operating System Interface (POSIX) - Part 1: System Application+Program Interface (API) [C Language]", Institute of Electrical+and Electronics Engineers, Inc, 1990.</dd>++<dt><a name="ref-rfc2046" id="ref-rfc2046"><b>+[RFC2046]</b></a></dt>++<dd><a href="http://www.ietf.org/rfc/rfc2046.txt">"RFC2046: Multipurpose Internet Mail Extensions (MIME) Part+Two: Media Types"</a>, N. Freed and N. Borenstein, November+1996.<br />+Available at <a href="http://www.ietf.org/rfc/rfc2046.txt">+http://www.ietf.org/rfc/rfc2046.txt</a>. Note that this RFC+obsoletes RFC1521, RFC1522, and RFC1590.</dd>++<dt><a name="ref-rfc2119" id="ref-rfc2119"><b>+[RFC2119]</b></a></dt>++<dd><a href="http://www.ietf.org/rfc/rfc2119.txt">"RFC2119: Key words for use in RFCs to Indicate Requirement+Levels"</a>, S. Bradner, March 1997.<br />+Available at: <a href="http://www.ietf.org/rfc/rfc2119.txt">+http://www.ietf.org/rfc/rfc2119.txt</a></dd>++<dt><a name="ref-rfc2376" id="ref-rfc2376"><b>+[RFC2376]</b></a></dt>++<dd><a href="http://www.ietf.org/rfc/rfc2376.txt">"RFC2376: XML Media Types"</a>, E. Whitehead, M. Murata, July+1998.<br />+Available at: <a href="http://www.ietf.org/rfc/rfc2376.txt">+http://www.ietf.org/rfc/rfc2376.txt</a></dd>++<dt><a name="ref-rfc2396" id="ref-rfc2396"><b>+[RFC2396]</b></a></dt>++<dd><a href="http://www.ietf.org/rfc/rfc2396.txt">"RFC2396: Uniform Resource Identifiers (URI): Generic+Syntax"</a>, T. Berners-Lee, R. Fielding, L. Masinter, August+1998.<br />+This document updates RFC1738 and RFC1808.<br />+Available at: <a href="http://www.ietf.org/rfc/rfc2396.txt">+http://www.ietf.org/rfc/rfc2396.txt</a></dd>++<dt><a name="ref-xml" id="ref-xml"><b>[XML]</b></a></dt>++<dd><a href="http://www.w3.org/TR/1998/REC-xml-19980210">"Extensible Markup Language (XML) 1.0 Specification"</a>, T.+Bray, J. Paoli, C. M. Sperberg-McQueen, 10 February 1998.<br />+Latest version available at: <a href="http://www.w3.org/TR/REC-xml">+http://www.w3.org/TR/REC-xml</a></dd>++<dt><a name="ref-xmlns" id="ref-xmlns"><b>[XMLNAMES]</b></a></dt>++<dd><a href="http://www.w3.org/TR/1999/REC-xml-names-19990114">"Namespaces in XML"</a>, T. Bray, D. Hollander, A. Layman, 14+January 1999.<br />+XML namespaces provide a simple method for qualifying names used+in XML documents by associating them with namespaces identified+by URI.<br />+Latest version available at: <a href="http://www.w3.org/TR/REC-xml-names">+http://www.w3.org/TR/REC-xml-names</a></dd>++</dl>+<p><a href="http://www.w3.org/WAI/WCAG1AAA-Conformance"+title="Explanation of Level Triple-A Conformance">+<img height="32" width="88"+src="http://www.w3.org/WAI/wcag1AAA.gif"+alt="Level Triple-A conformance icon, W3C-WAI Web Content Accessibility Guidelines 1.0" /></a></p>+<div class="navbar">+  <hr />+  <a href="#toc">table of contents</a>+</div>+</body>+</html>+

@@ -0,0 +1,1225 @@+<!--+   Extensible HTML version 1.0 Frameset DTD++   This is the same as HTML 4.0 Frameset except for+   changes due to the differences between XML and SGML.++   Namespace = http://www.w3.org/1999/xhtml++   For further information, see: http://www.w3.org/TR/xhtml1++   Copyright (c) 1998-2000 W3C (MIT, INRIA, Keio),+   All Rights Reserved. ++   This DTD module is identified by the PUBLIC and SYSTEM identifiers:++   PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN"+   SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd"++   $Revision: 1.1 $+   $Date: 2002/10/01 13:47:08 $++-->++<!--================ Character mnemonic entities =========================-->++<!ENTITY % HTMLlat1 PUBLIC+   "-//W3C//ENTITIES Latin 1 for XHTML//EN"+   "xhtml-lat1.ent">+%HTMLlat1;++<!ENTITY % HTMLsymbol PUBLIC+   "-//W3C//ENTITIES Symbols for XHTML//EN"+   "xhtml-symbol.ent">+%HTMLsymbol;++<!ENTITY % HTMLspecial PUBLIC+   "-//W3C//ENTITIES Special for XHTML//EN"+   "xhtml-special.ent">+%HTMLspecial;++<!--================== Imported Names ====================================-->++<!ENTITY % ContentType "CDATA">+    <!-- media type, as per [RFC2045] -->++<!ENTITY % ContentTypes "CDATA">+    <!-- comma-separated list of media types, as per [RFC2045] -->++<!ENTITY % Charset "CDATA">+    <!-- a character encoding, as per [RFC2045] -->++<!ENTITY % Charsets "CDATA">+    <!-- a space separated list of character encodings, as per [RFC2045] -->++<!ENTITY % LanguageCode "NMTOKEN">+    <!-- a language code, as per [RFC1766] -->++<!ENTITY % Character "CDATA">+    <!-- a single character from [ISO10646] -->++<!ENTITY % Number "CDATA">+    <!-- one or more digits -->++<!ENTITY % LinkTypes "CDATA">+    <!-- space-separated list of link types -->++<!ENTITY % MediaDesc "CDATA">+    <!-- single or comma-separated list of media descriptors -->++<!ENTITY % URI "CDATA">+    <!-- a Uniform Resource Identifier, see [RFC2396] -->++<!ENTITY % UriList "CDATA">+    <!-- a space separated list of Uniform Resource Identifiers -->++<!ENTITY % Datetime "CDATA">+    <!-- date and time information. ISO date format -->++<!ENTITY % Script "CDATA">+    <!-- script expression -->++<!ENTITY % StyleSheet "CDATA">+    <!-- style sheet data -->++<!ENTITY % Text "CDATA">+    <!-- used for titles etc. -->++<!ENTITY % FrameTarget "NMTOKEN">+    <!-- render in this frame -->++<!ENTITY % Length "CDATA">+    <!-- nn for pixels or nn% for percentage length -->++<!ENTITY % MultiLength "CDATA">+    <!-- pixel, percentage, or relative -->++<!ENTITY % MultiLengths "CDATA">+    <!-- comma-separated list of MultiLength -->++<!ENTITY % Pixels "CDATA">+    <!-- integer representing length in pixels -->++<!-- these are used for image maps -->++<!ENTITY % Shape "(rect|circle|poly|default)">++<!ENTITY % Coords "CDATA">+    <!-- comma separated list of lengths -->++<!-- used for object, applet, img, input and iframe -->+<!ENTITY % ImgAlign "(top|middle|bottom|left|right)">++<!-- a color using sRGB: #RRGGBB as Hex values -->+<!ENTITY % Color "CDATA">++<!-- There are also 16 widely known color names with their sRGB values:++    Black  = #000000    Green  = #008000+    Silver = #C0C0C0    Lime   = #00FF00+    Gray   = #808080    Olive  = #808000+    White  = #FFFFFF    Yellow = #FFFF00+    Maroon = #800000    Navy   = #000080+    Red    = #FF0000    Blue   = #0000FF+    Purple = #800080    Teal   = #008080+    Fuchsia= #FF00FF    Aqua   = #00FFFF+-->++<!--=================== Generic Attributes ===============================-->++<!-- core attributes common to most elements+  id       document-wide unique id+  class    space separated list of classes+  style    associated style info+  title    advisory title/amplification+-->+<!ENTITY % coreattrs+ "id          ID             #IMPLIED+  class       CDATA          #IMPLIED+  style       %StyleSheet;   #IMPLIED+  title       %Text;         #IMPLIED"+  >++<!-- internationalization attributes+  lang        language code (backwards compatible)+  xml:lang    language code (as per XML 1.0 spec)+  dir         direction for weak/neutral text+-->+<!ENTITY % i18n+ "lang        %LanguageCode; #IMPLIED+  xml:lang    %LanguageCode; #IMPLIED+  dir         (ltr|rtl)      #IMPLIED"+  >++<!-- attributes for common UI events+  onclick     a pointer button was clicked+  ondblclick  a pointer button was double clicked+  onmousedown a pointer button was pressed down+  onmouseup   a pointer button was released+  onmousemove a pointer was moved onto the element+  onmouseout  a pointer was moved away from the element+  onkeypress  a key was pressed and released+  onkeydown   a key was pressed down+  onkeyup     a key was released+-->+<!ENTITY % events+ "onclick     %Script;       #IMPLIED+  ondblclick  %Script;       #IMPLIED+  onmousedown %Script;       #IMPLIED+  onmouseup   %Script;       #IMPLIED+  onmouseover %Script;       #IMPLIED+  onmousemove %Script;       #IMPLIED+  onmouseout  %Script;       #IMPLIED+  onkeypress  %Script;       #IMPLIED+  onkeydown   %Script;       #IMPLIED+  onkeyup     %Script;       #IMPLIED"+  >++<!-- attributes for elements that can get the focus+  accesskey   accessibility key character+  tabindex    position in tabbing order+  onfocus     the element got the focus+  onblur      the element lost the focus+-->+<!ENTITY % focus+ "accesskey   %Character;    #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED"+  >++<!ENTITY % attrs "%coreattrs; %i18n; %events;">++<!-- text alignment for p, div, h1-h6. The default is+     align="left" for ltr headings, "right" for rtl -->++<!ENTITY % TextAlign "align (left|center|right) #IMPLIED">++<!--=================== Text Elements ====================================-->++<!ENTITY % special+   "br | span | bdo |object | applet | img | map | iframe">++<!ENTITY % fontstyle "tt | i | b | big | small | u+                      | s | strike |font | basefont">++<!ENTITY % phrase "em | strong | dfn | code | q | sub | sup |+                   samp | kbd | var | cite | abbr | acronym">++<!ENTITY % inline.forms "input | select | textarea | label | button">++<!-- these can occur at block or inline level -->+<!ENTITY % misc "ins | del | script | noscript">++<!ENTITY % inline "a | %special; | %fontstyle; | %phrase; | %inline.forms;">++<!-- %Inline; covers inline or "text-level" elements -->+<!ENTITY % Inline "(#PCDATA | %inline; | %misc;)*">++<!--================== Block level elements ==============================-->++<!ENTITY % heading "h1|h2|h3|h4|h5|h6">+<!ENTITY % lists "ul | ol | dl | menu | dir">+<!ENTITY % blocktext "pre | hr | blockquote | address | center">++<!ENTITY % block+    "p | %heading; | div | %lists; | %blocktext; | isindex | fieldset | table">++<!ENTITY % Block "(%block; | form | %misc;)*">++<!-- %Flow; mixes Block and Inline and is used for list items etc. -->+<!ENTITY % Flow "(#PCDATA | %block; | form | %inline; | %misc;)*">++<!--================== Content models for exclusions =====================-->++<!-- a elements use %Inline; excluding a -->++<!ENTITY % a.content+   "(#PCDATA | %special; | %fontstyle; | %phrase; | %inline.forms; | %misc;)*">++<!-- pre uses %Inline excluding img, object, applet, big, small,+     sub, sup, font, or basefont -->++<!ENTITY % pre.content+   "(#PCDATA | a | br | span | bdo | map | tt | i | b | u | s |+      %phrase; | %inline.forms;)*">++<!-- form uses %Flow; excluding form -->++<!ENTITY % form.content "(#PCDATA | %block; | %inline; | %misc;)*">++<!-- button uses %Flow; but excludes a, form, form controls, iframe -->++<!ENTITY % button.content+   "(#PCDATA | p | %heading; | div | %lists; | %blocktext; |+      table | br | span | bdo | object | applet | img | map |+      %fontstyle; | %phrase; | %misc;)*">++<!--================ Document Structure ==================================-->++<!-- the namespace URI designates the document profile -->++<!ELEMENT html (head, frameset)>+<!ATTLIST html+  %i18n;+  xmlns       %URI;          #FIXED 'http://www.w3.org/1999/xhtml'+  >++<!--================ Document Head =======================================-->++<!ENTITY % head.misc "(script|style|meta|link|object|isindex)*">++<!-- content model is %head.misc; combined with a single+     title and an optional base element in any order -->++<!ELEMENT head (%head.misc;,+     ((title, %head.misc;, (base, %head.misc;)?) |+      (base, %head.misc;, (title, %head.misc;))))>++<!ATTLIST head+  %i18n;+  profile     %URI;          #IMPLIED+  >++<!-- 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. Exactly one title is required per document.+    -->+<!ELEMENT title (#PCDATA)>+<!ATTLIST title %i18n;>++<!-- document base URI -->++<!ELEMENT base EMPTY>+<!ATTLIST base+  href        %URI;          #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!-- generic metainformation -->+<!ELEMENT meta EMPTY>+<!ATTLIST meta+  %i18n;+  http-equiv  CDATA          #IMPLIED+  name        CDATA          #IMPLIED+  content     CDATA          #REQUIRED+  scheme      CDATA          #IMPLIED+  >++<!--+  Relationship values can be used in principle:++   a) for document specific toolbars/menus when used+      with the link element in document head e.g.+        start, contents, previous, next, index, end, help+   b) to link to a separate style sheet (rel="stylesheet")+   c) to make a link to a script (rel="script")+   d) by stylesheets to control how collections of+      html nodes are rendered into printed documents+   e) to make a link to a printable version of this document+      e.g. a PostScript or PDF version (rel="alternate" media="print")+-->++<!ELEMENT link EMPTY>+<!ATTLIST link+  %attrs;+  charset     %Charset;      #IMPLIED+  href        %URI;          #IMPLIED+  hreflang    %LanguageCode; #IMPLIED+  type        %ContentType;  #IMPLIED+  rel         %LinkTypes;    #IMPLIED+  rev         %LinkTypes;    #IMPLIED+  media       %MediaDesc;    #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!-- style info, which may include CDATA sections -->+<!ELEMENT style (#PCDATA)>+<!ATTLIST style+  %i18n;+  type        %ContentType;  #REQUIRED+  media       %MediaDesc;    #IMPLIED+  title       %Text;         #IMPLIED+  xml:space   (preserve)     #FIXED 'preserve'+  >++<!-- script statements, which may include CDATA sections -->+<!ELEMENT script (#PCDATA)>+<!ATTLIST script+  charset     %Charset;      #IMPLIED+  type        %ContentType;  #REQUIRED+  language    CDATA          #IMPLIED+  src         %URI;          #IMPLIED+  defer       (defer)        #IMPLIED+  xml:space   (preserve)     #FIXED 'preserve'+  >++<!-- alternate content container for non script-based rendering -->++<!ELEMENT noscript %Flow;>+<!ATTLIST noscript+  %attrs;+  >++<!--======================= Frames =======================================-->++<!-- only one noframes element permitted per document -->++<!ELEMENT frameset (frameset|frame|noframes)*>+<!ATTLIST frameset+  %coreattrs;+  rows        %MultiLengths; #IMPLIED+  cols        %MultiLengths; #IMPLIED+  onload      %Script;       #IMPLIED+  onunload    %Script;       #IMPLIED+  >++<!-- reserved frame names start with "_" otherwise starts with letter -->++<!-- tiled window within frameset -->++<!ELEMENT frame EMPTY>+<!ATTLIST frame+  %coreattrs;+  longdesc    %URI;          #IMPLIED+  name        NMTOKEN        #IMPLIED+  src         %URI;          #IMPLIED+  frameborder (1|0)          "1"+  marginwidth %Pixels;       #IMPLIED+  marginheight %Pixels;      #IMPLIED+  noresize    (noresize)     #IMPLIED+  scrolling   (yes|no|auto)  "auto"+  >++<!-- inline subwindow -->++<!ELEMENT iframe %Flow;>+<!ATTLIST iframe+  %coreattrs;+  longdesc    %URI;          #IMPLIED+  name        NMTOKEN        #IMPLIED+  src         %URI;          #IMPLIED+  frameborder (1|0)          "1"+  marginwidth %Pixels;       #IMPLIED+  marginheight %Pixels;      #IMPLIED+  scrolling   (yes|no|auto)  "auto"+  align       %ImgAlign;     #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  >++<!-- alternate content container for non frame-based rendering -->++<!ELEMENT noframes (body)>+<!ATTLIST noframes+  %attrs;+  >++<!--=================== Document Body ====================================-->++<!ELEMENT body %Flow;>+<!ATTLIST body+  %attrs;+  onload      %Script;       #IMPLIED+  onunload    %Script;       #IMPLIED+  background  %URI;          #IMPLIED+  bgcolor     %Color;        #IMPLIED+  text        %Color;        #IMPLIED+  link        %Color;        #IMPLIED+  vlink       %Color;        #IMPLIED+  alink       %Color;        #IMPLIED+  >++<!ELEMENT div %Flow;>  <!-- generic language/style container -->+<!ATTLIST div+  %attrs;+  %TextAlign;+  >++<!--=================== Paragraphs =======================================-->++<!ELEMENT p %Inline;>+<!ATTLIST p+  %attrs;+  %TextAlign;+  >++<!--=================== Headings =========================================-->++<!--+  There are six levels of headings from h1 (the most important)+  to h6 (the least important).+-->++<!ELEMENT h1  %Inline;>+<!ATTLIST h1+  %attrs;+  %TextAlign;+  >++<!ELEMENT h2 %Inline;>+<!ATTLIST h2+  %attrs;+  %TextAlign;+  >++<!ELEMENT h3 %Inline;>+<!ATTLIST h3+  %attrs;+  %TextAlign;+  >++<!ELEMENT h4 %Inline;>+<!ATTLIST h4+  %attrs;+  %TextAlign;+  >++<!ELEMENT h5 %Inline;>+<!ATTLIST h5+  %attrs;+  %TextAlign;+  >++<!ELEMENT h6 %Inline;>+<!ATTLIST h6+  %attrs;+  %TextAlign;+  >++<!--=================== Lists ============================================-->++<!-- Unordered list bullet styles -->++<!ENTITY % ULStyle "(disc|square|circle)">++<!-- Unordered list -->++<!ELEMENT ul (li)+>+<!ATTLIST ul+  %attrs;+  type        %ULStyle;     #IMPLIED+  compact     (compact)     #IMPLIED+  >++<!-- Ordered list numbering style++    1   arabic numbers      1, 2, 3, ...+    a   lower alpha         a, b, c, ...+    A   upper alpha         A, B, C, ...+    i   lower roman         i, ii, iii, ...+    I   upper roman         I, II, III, ...++    The style is applied to the sequence number which by default+    is reset to 1 for the first list item in an ordered list.+-->+<!ENTITY % OLStyle "CDATA">++<!-- Ordered (numbered) list -->++<!ELEMENT ol (li)+>+<!ATTLIST ol+  %attrs;+  type        %OLStyle;      #IMPLIED+  compact     (compact)      #IMPLIED+  start       %Number;       #IMPLIED+  >++<!-- single column list (DEPRECATED) --> +<!ELEMENT menu (li)+>+<!ATTLIST menu+  %attrs;+  compact     (compact)     #IMPLIED+  >++<!-- multiple column list (DEPRECATED) --> +<!ELEMENT dir (li)+>+<!ATTLIST dir+  %attrs;+  compact     (compact)     #IMPLIED+  >++<!-- LIStyle is constrained to: "(%ULStyle;|%OLStyle;)" -->+<!ENTITY % LIStyle "CDATA">++<!-- list item -->++<!ELEMENT li %Flow;>+<!ATTLIST li+  %attrs;+  type        %LIStyle;      #IMPLIED+  value       %Number;       #IMPLIED+  >++<!-- definition lists - dt for term, dd for its definition -->++<!ELEMENT dl (dt|dd)+>+<!ATTLIST dl+  %attrs;+  compact     (compact)      #IMPLIED+  >++<!ELEMENT dt %Inline;>+<!ATTLIST dt+  %attrs;+  >++<!ELEMENT dd %Flow;>+<!ATTLIST dd+  %attrs;+  >++<!--=================== Address ==========================================-->++<!-- information on author -->++<!ELEMENT address %Inline;>+<!ATTLIST address+  %attrs;+  >++<!--=================== Horizontal Rule ==================================-->++<!ELEMENT hr EMPTY>+<!ATTLIST hr+  %attrs;+  align       (left|center|right) #IMPLIED+  noshade     (noshade)      #IMPLIED+  size        %Pixels;       #IMPLIED+  width       %Length;       #IMPLIED+  >++<!--=================== Preformatted Text ================================-->++<!-- content is %Inline; excluding +        "img|object|applet|big|small|sub|sup|font|basefont" -->++<!ELEMENT pre %pre.content;>+<!ATTLIST pre+  %attrs;+  width       %Number;      #IMPLIED+  xml:space   (preserve)    #FIXED 'preserve'+  >++<!--=================== Block-like Quotes ================================-->++<!ELEMENT blockquote %Flow;>+<!ATTLIST blockquote+  %attrs;+  cite        %URI;          #IMPLIED+  >++<!--=================== Text alignment ===================================-->++<!-- center content -->+<!ELEMENT center %Flow;>+<!ATTLIST center+  %attrs;+  >++<!--=================== Inserted/Deleted Text ============================-->+++<!--+  ins/del are allowed in block and inline content, but its+  inappropriate to include block content within an ins element+  occurring in inline content.+-->+<!ELEMENT ins %Flow;>+<!ATTLIST ins+  %attrs;+  cite        %URI;          #IMPLIED+  datetime    %Datetime;     #IMPLIED+  >++<!ELEMENT del %Flow;>+<!ATTLIST del+  %attrs;+  cite        %URI;          #IMPLIED+  datetime    %Datetime;     #IMPLIED+  >++<!--================== The Anchor Element ================================-->++<!-- content is %Inline; except that anchors shouldn't be nested -->++<!ELEMENT a %a.content;>+<!ATTLIST a+  %attrs;+  charset     %Charset;      #IMPLIED+  type        %ContentType;  #IMPLIED+  name        NMTOKEN        #IMPLIED+  href        %URI;          #IMPLIED+  hreflang    %LanguageCode; #IMPLIED+  rel         %LinkTypes;    #IMPLIED+  rev         %LinkTypes;    #IMPLIED+  accesskey   %Character;    #IMPLIED+  shape       %Shape;        "rect"+  coords      %Coords;       #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!--===================== Inline Elements ================================-->++<!ELEMENT span %Inline;> <!-- generic language/style container -->+<!ATTLIST span+  %attrs;+  >++<!ELEMENT bdo %Inline;>  <!-- I18N BiDi over-ride -->+<!ATTLIST bdo+  %coreattrs;+  %events;+  lang        %LanguageCode; #IMPLIED+  xml:lang    %LanguageCode; #IMPLIED+  dir         (ltr|rtl)      #REQUIRED+  >++<!ELEMENT br EMPTY>   <!-- forced line break -->+<!ATTLIST br+  %coreattrs;+  clear       (left|all|right|none) "none"+  >++<!ELEMENT em %Inline;>   <!-- emphasis -->+<!ATTLIST em %attrs;>++<!ELEMENT strong %Inline;>   <!-- strong emphasis -->+<!ATTLIST strong %attrs;>++<!ELEMENT dfn %Inline;>   <!-- definitional -->+<!ATTLIST dfn %attrs;>++<!ELEMENT code %Inline;>   <!-- program code -->+<!ATTLIST code %attrs;>++<!ELEMENT samp %Inline;>   <!-- sample -->+<!ATTLIST samp %attrs;>++<!ELEMENT kbd %Inline;>  <!-- something user would type -->+<!ATTLIST kbd %attrs;>++<!ELEMENT var %Inline;>   <!-- variable -->+<!ATTLIST var %attrs;>++<!ELEMENT cite %Inline;>   <!-- citation -->+<!ATTLIST cite %attrs;>++<!ELEMENT abbr %Inline;>   <!-- abbreviation -->+<!ATTLIST abbr %attrs;>++<!ELEMENT acronym %Inline;>   <!-- acronym -->+<!ATTLIST acronym %attrs;>++<!ELEMENT q %Inline;>   <!-- inlined quote -->+<!ATTLIST q+   %attrs;+  cite        %URI;          #IMPLIED+   >++<!ELEMENT sub %Inline;> <!-- subscript -->+<!ATTLIST sub %attrs;>++<!ELEMENT sup %Inline;> <!-- superscript -->+<!ATTLIST sup %attrs;>++<!ELEMENT tt %Inline;>   <!-- fixed pitch font -->+<!ATTLIST tt %attrs;>++<!ELEMENT i %Inline;>   <!-- italic font -->+<!ATTLIST i %attrs;>++<!ELEMENT b %Inline;>   <!-- bold font -->+<!ATTLIST b %attrs;>++<!ELEMENT big %Inline;>   <!-- bigger font -->+<!ATTLIST big %attrs;>++<!ELEMENT small %Inline;>   <!-- smaller font -->+<!ATTLIST small %attrs;>++<!ELEMENT u %Inline;>   <!-- underline -->+<!ATTLIST u %attrs;>++<!ELEMENT s %Inline;>   <!-- strike-through -->+<!ATTLIST s %attrs;>++<!ELEMENT strike %Inline;>   <!-- strike-through -->+<!ATTLIST strike %attrs;>++<!ELEMENT basefont EMPTY>  <!-- base font size -->+<!ATTLIST basefont+  id          ID             #IMPLIED+  size        CDATA          #REQUIRED+  color       %Color;        #IMPLIED+  face        CDATA          #IMPLIED+  >++<!ELEMENT font %Inline;> <!-- local change to font -->+<!ATTLIST font+  %coreattrs;+  %i18n;+  size        CDATA          #IMPLIED+  color       %Color;        #IMPLIED+  face        CDATA          #IMPLIED+  >++<!--==================== Object ======================================-->+<!--+  object is used to embed objects as part of HTML pages.+  param elements should precede other content. Parameters+  can also be expressed as attribute/value pairs on the+  object element itself when brevity is desired.+-->++<!ELEMENT object (#PCDATA | param | %block; | form |%inline; | %misc;)*>+<!ATTLIST object+  %attrs;+  declare     (declare)      #IMPLIED+  classid     %URI;          #IMPLIED+  codebase    %URI;          #IMPLIED+  data        %URI;          #IMPLIED+  type        %ContentType;  #IMPLIED+  codetype    %ContentType;  #IMPLIED+  archive     %UriList;      #IMPLIED+  standby     %Text;         #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  usemap      %URI;          #IMPLIED+  name        NMTOKEN        #IMPLIED+  tabindex    %Number;       #IMPLIED+  align       %ImgAlign;     #IMPLIED+  border      %Pixels;       #IMPLIED+  hspace      %Pixels;       #IMPLIED+  vspace      %Pixels;       #IMPLIED+  >++<!--+  param is used to supply a named property value.+  In XML it would seem natural to follow RDF and support an+  abbreviated syntax where the param elements are replaced+  by attribute value pairs on the object start tag.+-->+<!ELEMENT param EMPTY>+<!ATTLIST param+  id          ID             #IMPLIED+  name        CDATA          #REQUIRED+  value       CDATA          #IMPLIED+  valuetype   (data|ref|object) "data"+  type        %ContentType;  #IMPLIED+  >++<!--=================== Java applet ==================================-->+<!--+  One of code or object attributes must be present.+  Place param elements before other content.+-->+<!ELEMENT applet (#PCDATA | param | %block; | form | %inline; | %misc;)*>+<!ATTLIST applet+  %coreattrs;+  codebase    %URI;          #IMPLIED+  archive     CDATA          #IMPLIED+  code        CDATA          #IMPLIED+  object      CDATA          #IMPLIED+  alt         %Text;         #IMPLIED+  name        NMTOKEN        #IMPLIED+  width       %Length;       #REQUIRED+  height      %Length;       #REQUIRED+  align       %ImgAlign;     #IMPLIED+  hspace      %Pixels;       #IMPLIED+  vspace      %Pixels;       #IMPLIED+  >++<!--=================== Images ===========================================-->++<!--+   To avoid accessibility problems for people who aren't+   able to see the image, you should provide a text+   description using the alt and longdesc attributes.+   In addition, avoid the use of server-side image maps.+-->++<!ELEMENT img EMPTY>+<!ATTLIST img+  %attrs;+  src         %URI;          #REQUIRED+  alt         %Text;         #REQUIRED+  name        NMTOKEN        #IMPLIED+  longdesc    %URI;          #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  usemap      %URI;          #IMPLIED+  ismap       (ismap)        #IMPLIED+  align       %ImgAlign;     #IMPLIED+  border      %Pixels;       #IMPLIED+  hspace      %Pixels;       #IMPLIED+  vspace      %Pixels;       #IMPLIED+  >++<!-- usemap points to a map element which may be in this document+  or an external document, although the latter is not widely supported -->++<!--================== Client-side image maps ============================-->++<!-- These can be placed in the same document or grouped in a+     separate document although this isn't yet widely supported -->++<!ELEMENT map ((%block; | form | %misc;)+ | area+)>+<!ATTLIST map+  %i18n;+  %events;+  id          ID             #REQUIRED+  class       CDATA          #IMPLIED+  style       %StyleSheet;   #IMPLIED+  title       %Text;         #IMPLIED+  name        NMTOKEN        #IMPLIED+  >++<!ELEMENT area EMPTY>+<!ATTLIST area+  %attrs;+  shape       %Shape;        "rect"+  coords      %Coords;       #IMPLIED+  href        %URI;          #IMPLIED+  nohref      (nohref)       #IMPLIED+  alt         %Text;         #REQUIRED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!--================ Forms ===============================================-->++<!ELEMENT form %form.content;>   <!-- forms shouldn't be nested -->++<!ATTLIST form+  %attrs;+  action      %URI;          #REQUIRED+  method      (get|post)     "get"+  name        NMTOKEN        #IMPLIED+  enctype     %ContentType;  "application/x-www-form-urlencoded"+  onsubmit    %Script;       #IMPLIED+  onreset     %Script;       #IMPLIED+  accept      %ContentTypes; #IMPLIED+  accept-charset %Charsets;  #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!--+  Each label must not contain more than ONE field+  Label elements shouldn't be nested.+-->+<!ELEMENT label %Inline;>+<!ATTLIST label+  %attrs;+  for         IDREF          #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!ENTITY % InputType+  "(text | password | checkbox |+    radio | submit | reset |+    file | hidden | image | button)"+   >++<!-- the name attribute is required for all but submit & reset -->++<!ELEMENT input EMPTY>     <!-- form control -->+<!ATTLIST input+  %attrs;+  type        %InputType;    "text"+  name        CDATA          #IMPLIED+  value       CDATA          #IMPLIED+  checked     (checked)      #IMPLIED+  disabled    (disabled)     #IMPLIED+  readonly    (readonly)     #IMPLIED+  size        CDATA          #IMPLIED+  maxlength   %Number;       #IMPLIED+  src         %URI;          #IMPLIED+  alt         CDATA          #IMPLIED+  usemap      %URI;          #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onselect    %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  accept      %ContentTypes; #IMPLIED+  align       %ImgAlign;     #IMPLIED+  >++<!ELEMENT select (optgroup|option)+>  <!-- option selector -->+<!ATTLIST select+  %attrs;+  name        CDATA          #IMPLIED+  size        %Number;       #IMPLIED+  multiple    (multiple)     #IMPLIED+  disabled    (disabled)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  >++<!ELEMENT optgroup (option)+>   <!-- option group -->+<!ATTLIST optgroup+  %attrs;+  disabled    (disabled)     #IMPLIED+  label       %Text;         #REQUIRED+  >++<!ELEMENT option (#PCDATA)>     <!-- selectable choice -->+<!ATTLIST option+  %attrs;+  selected    (selected)     #IMPLIED+  disabled    (disabled)     #IMPLIED+  label       %Text;         #IMPLIED+  value       CDATA          #IMPLIED+  >++<!ELEMENT textarea (#PCDATA)>     <!-- multi-line text field -->+<!ATTLIST textarea+  %attrs;+  name        CDATA          #IMPLIED+  rows        %Number;       #REQUIRED+  cols        %Number;       #REQUIRED+  disabled    (disabled)     #IMPLIED+  readonly    (readonly)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onselect    %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  >++<!--+  The fieldset element is used to group form fields.+  Only one legend element should occur in the content+  and if present should only be preceded by whitespace.+-->+<!ELEMENT fieldset (#PCDATA | legend | %block; | form | %inline; | %misc;)*>+<!ATTLIST fieldset+  %attrs;+  >++<!ENTITY % LAlign "(top|bottom|left|right)">++<!ELEMENT legend %Inline;>     <!-- fieldset label -->+<!ATTLIST legend+  %attrs;+  accesskey   %Character;    #IMPLIED+  align       %LAlign;       #IMPLIED+  >++<!--+ Content is %Flow; excluding a, form, form controls, iframe+--> +<!ELEMENT button %button.content;>  <!-- push button -->+<!ATTLIST button+  %attrs;+  name        CDATA          #IMPLIED+  value       CDATA          #IMPLIED+  type        (button|submit|reset) "submit"+  disabled    (disabled)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!-- single-line text input control (DEPRECATED) -->+<!ELEMENT isindex EMPTY>+<!ATTLIST isindex+  %coreattrs;+  %i18n;+  prompt      %Text;         #IMPLIED+  >++<!--======================= Tables =======================================-->++<!-- Derived from IETF HTML table standard, see [RFC1942] -->++<!--+ The border attribute sets the thickness of the frame around the+ table. The default units are screen pixels.++ The frame attribute specifies which parts of the frame around+ the table should be rendered. The values are not the same as+ CALS to avoid a name clash with the valign attribute.+-->+<!ENTITY % TFrame "(void|above|below|hsides|lhs|rhs|vsides|box|border)">++<!--+ The rules attribute defines which rules to draw between cells:++ If rules is absent then assume:+     "none" if border is absent or border="0" otherwise "all"+-->++<!ENTITY % TRules "(none | groups | rows | cols | all)">+  +<!-- horizontal placement of table relative to document -->+<!ENTITY % TAlign "(left|center|right)">++<!-- horizontal alignment attributes for cell contents++  char        alignment char, e.g. char=":"+  charoff     offset for alignment char+-->+<!ENTITY % cellhalign+  "align      (left|center|right|justify|char) #IMPLIED+   char       %Character;    #IMPLIED+   charoff    %Length;       #IMPLIED"+  >++<!-- vertical alignment attributes for cell contents -->+<!ENTITY % cellvalign+  "valign     (top|middle|bottom|baseline) #IMPLIED"+  >++<!ELEMENT table+     (caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))>+<!ELEMENT caption  %Inline;>+<!ELEMENT thead    (tr)+>+<!ELEMENT tfoot    (tr)+>+<!ELEMENT tbody    (tr)+>+<!ELEMENT colgroup (col)*>+<!ELEMENT col      EMPTY>+<!ELEMENT tr       (th|td)+>+<!ELEMENT th       %Flow;>+<!ELEMENT td       %Flow;>++<!ATTLIST table+  %attrs;+  summary     %Text;         #IMPLIED+  width       %Length;       #IMPLIED+  border      %Pixels;       #IMPLIED+  frame       %TFrame;       #IMPLIED+  rules       %TRules;       #IMPLIED+  cellspacing %Length;       #IMPLIED+  cellpadding %Length;       #IMPLIED+  align       %TAlign;       #IMPLIED+  bgcolor     %Color;        #IMPLIED+  >++<!ENTITY % CAlign "(top|bottom|left|right)">++<!ATTLIST caption+  %attrs;+  align       %CAlign;       #IMPLIED+  >++<!--+colgroup groups a set of col elements. It allows you to group+several semantically related columns together.+-->+<!ATTLIST colgroup+  %attrs;+  span        %Number;       "1"+  width       %MultiLength;  #IMPLIED+  %cellhalign;+  %cellvalign;+  >++<!--+ col elements define the alignment properties for cells in+ one or more columns.++ The width attribute specifies the width of the columns, e.g.++     width=64        width in screen pixels+     width=0.5*      relative width of 0.5++ The span attribute causes the attributes of one+ col element to apply to more than one column.+-->+<!ATTLIST col+  %attrs;+  span        %Number;       "1"+  width       %MultiLength;  #IMPLIED+  %cellhalign;+  %cellvalign;+  >++<!--+    Use thead to duplicate headers when breaking table+    across page boundaries, or for static headers when+    tbody sections are rendered in scrolling panel.++    Use tfoot to duplicate footers when breaking table+    across page boundaries, or for static footers when+    tbody sections are rendered in scrolling panel.++    Use multiple tbody sections when rules are needed+    between groups of table rows.+-->+<!ATTLIST thead+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tfoot+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tbody+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tr+  %attrs;+  %cellhalign;+  %cellvalign;+  bgcolor     %Color;        #IMPLIED+  >++<!-- Scope is simpler than headers attribute for common tables -->+<!ENTITY % Scope "(row|col|rowgroup|colgroup)">++<!-- th is for headers, td for data and for cells acting as both -->++<!ATTLIST th+  %attrs;+  abbr        %Text;         #IMPLIED+  axis        CDATA          #IMPLIED+  headers     IDREFS         #IMPLIED+  scope       %Scope;        #IMPLIED+  rowspan     %Number;       "1"+  colspan     %Number;       "1"+  %cellhalign;+  %cellvalign;+  nowrap      (nowrap)       #IMPLIED+  bgcolor     %Color;        #IMPLIED+  width       %Pixels;       #IMPLIED+  height      %Pixels;       #IMPLIED+  >++<!ATTLIST td+  %attrs;+  abbr        %Text;         #IMPLIED+  axis        CDATA          #IMPLIED+  headers     IDREFS         #IMPLIED+  scope       %Scope;        #IMPLIED+  rowspan     %Number;       "1"+  colspan     %Number;       "1"+  %cellhalign;+  %cellvalign;+  nowrap      (nowrap)       #IMPLIED+  bgcolor     %Color;        #IMPLIED+  width       %Pixels;       #IMPLIED+  height      %Pixels;       #IMPLIED+  >+

@@ -0,0 +1,988 @@+<!--+   Extensible HTML version 1.0 Strict DTD++   This is the same as HTML 4.0 Strict except for+   changes due to the differences between XML and SGML.++   Namespace = http://www.w3.org/1999/xhtml++   For further information, see: http://www.w3.org/TR/xhtml1++   Copyright (c) 1998-2000 W3C (MIT, INRIA, Keio),+   All Rights Reserved. ++   This DTD module is identified by the PUBLIC and SYSTEM identifiers:++   PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"+   SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"++   $Revision: 1.1 $+   $Date: 2002/10/01 13:47:08 $++-->++<!--================ Character mnemonic entities =========================-->++<!ENTITY % HTMLlat1 PUBLIC+   "-//W3C//ENTITIES Latin 1 for XHTML//EN"+   "xhtml-lat1.ent">+%HTMLlat1;++<!ENTITY % HTMLsymbol PUBLIC+   "-//W3C//ENTITIES Symbols for XHTML//EN"+   "xhtml-symbol.ent">+%HTMLsymbol;++<!ENTITY % HTMLspecial PUBLIC+   "-//W3C//ENTITIES Special for XHTML//EN"+   "xhtml-special.ent">+%HTMLspecial;++<!--================== Imported Names ====================================-->++<!ENTITY % ContentType "CDATA">+    <!-- media type, as per [RFC2045] -->++<!ENTITY % ContentTypes "CDATA">+    <!-- comma-separated list of media types, as per [RFC2045] -->++<!ENTITY % Charset "CDATA">+    <!-- a character encoding, as per [RFC2045] -->++<!ENTITY % Charsets "CDATA">+    <!-- a space separated list of character encodings, as per [RFC2045] -->++<!ENTITY % LanguageCode "NMTOKEN">+    <!-- a language code, as per [RFC1766] -->++<!ENTITY % Character "CDATA">+    <!-- a single character from [ISO10646] -->++<!ENTITY % Number "CDATA">+    <!-- one or more digits -->++<!ENTITY % LinkTypes "CDATA">+    <!-- space-separated list of link types -->++<!ENTITY % MediaDesc "CDATA">+    <!-- single or comma-separated list of media descriptors -->++<!ENTITY % URI "CDATA">+    <!-- a Uniform Resource Identifier, see [RFC2396] -->++<!ENTITY % UriList "CDATA">+    <!-- a space separated list of Uniform Resource Identifiers -->++<!ENTITY % Datetime "CDATA">+    <!-- date and time information. ISO date format -->++<!ENTITY % Script "CDATA">+    <!-- script expression -->++<!ENTITY % StyleSheet "CDATA">+    <!-- style sheet data -->++<!ENTITY % Text "CDATA">+    <!-- used for titles etc. -->++<!ENTITY % FrameTarget "NMTOKEN">+    <!-- render in this frame -->++<!ENTITY % Length "CDATA">+    <!-- nn for pixels or nn% for percentage length -->++<!ENTITY % MultiLength "CDATA">+    <!-- pixel, percentage, or relative -->++<!ENTITY % MultiLengths "CDATA">+    <!-- comma-separated list of MultiLength -->++<!ENTITY % Pixels "CDATA">+    <!-- integer representing length in pixels -->++<!-- these are used for image maps -->++<!ENTITY % Shape "(rect|circle|poly|default)">++<!ENTITY % Coords "CDATA">+    <!-- comma separated list of lengths -->++<!--=================== Generic Attributes ===============================-->++<!-- core attributes common to most elements+  id       document-wide unique id+  class    space separated list of classes+  style    associated style info+  title    advisory title/amplification+-->+<!ENTITY % coreattrs+ "id          ID             #IMPLIED+  class       CDATA          #IMPLIED+  style       %StyleSheet;   #IMPLIED+  title       %Text;         #IMPLIED"+  >++<!-- internationalization attributes+  lang        language code (backwards compatible)+  xml:lang    language code (as per XML 1.0 spec)+  dir         direction for weak/neutral text+-->+<!ENTITY % i18n+ "lang        %LanguageCode; #IMPLIED+  xml:lang    %LanguageCode; #IMPLIED+  dir         (ltr|rtl)      #IMPLIED"+  >++<!-- attributes for common UI events+  onclick     a pointer button was clicked+  ondblclick  a pointer button was double clicked+  onmousedown a pointer button was pressed down+  onmouseup   a pointer button was released+  onmousemove a pointer was moved onto the element+  onmouseout  a pointer was moved away from the element+  onkeypress  a key was pressed and released+  onkeydown   a key was pressed down+  onkeyup     a key was released+-->+<!ENTITY % events+ "onclick     %Script;       #IMPLIED+  ondblclick  %Script;       #IMPLIED+  onmousedown %Script;       #IMPLIED+  onmouseup   %Script;       #IMPLIED+  onmouseover %Script;       #IMPLIED+  onmousemove %Script;       #IMPLIED+  onmouseout  %Script;       #IMPLIED+  onkeypress  %Script;       #IMPLIED+  onkeydown   %Script;       #IMPLIED+  onkeyup     %Script;       #IMPLIED"+  >++<!-- attributes for elements that can get the focus+  accesskey   accessibility key character+  tabindex    position in tabbing order+  onfocus     the element got the focus+  onblur      the element lost the focus+-->+<!ENTITY % focus+ "accesskey   %Character;    #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED"+  >++<!ENTITY % attrs "%coreattrs; %i18n; %events;">++<!--=================== Text Elements ====================================-->++<!ENTITY % special+   "br | span | bdo | object | img | map">++<!ENTITY % fontstyle "tt | i | b | big | small">++<!ENTITY % phrase "em | strong | dfn | code | q | sub | sup |+                   samp | kbd | var | cite | abbr | acronym">++<!ENTITY % inline.forms "input | select | textarea | label | button">++<!-- these can occur at block or inline level -->+<!ENTITY % misc "ins | del | script | noscript">++<!ENTITY % inline "a | %special; | %fontstyle; | %phrase; | %inline.forms;">++<!-- %Inline; covers inline or "text-level" elements -->+<!ENTITY % Inline "(#PCDATA | %inline; | %misc;)*">++<!--================== Block level elements ==============================-->++<!ENTITY % heading "h1|h2|h3|h4|h5|h6">+<!ENTITY % lists "ul | ol | dl">+<!ENTITY % blocktext "pre | hr | blockquote | address">++<!ENTITY % block+     "p | %heading; | div | %lists; | %blocktext; | fieldset | table">++<!ENTITY % Block "(%block; | form | %misc;)*">++<!-- %Flow; mixes Block and Inline and is used for list items etc. -->+<!ENTITY % Flow "(#PCDATA | %block; | form | %inline; | %misc;)*">++<!--================== Content models for exclusions =====================-->++<!-- a elements use %Inline; excluding a -->++<!ENTITY % a.content+   "(#PCDATA | %special; | %fontstyle; | %phrase; | %inline.forms; | %misc;)*">++<!-- pre uses %Inline excluding img, object, big, small, sup or sup -->++<!ENTITY % pre.content+   "(#PCDATA | a | br | span | bdo | map | tt | i | b |+      %phrase; | %inline.forms;)*">++<!-- form uses %Block; excluding form -->++<!ENTITY % form.content "(%block; | %misc;)*">++<!-- button uses %Flow; but excludes a, form and form controls -->++<!ENTITY % button.content+   "(#PCDATA | p | %heading; | div | %lists; | %blocktext; |+    table | %special; | %fontstyle; | %phrase; | %misc;)*">++<!--================ Document Structure ==================================-->++<!-- the namespace URI designates the document profile -->++<!ELEMENT html (head, body)>+<!ATTLIST html+  %i18n;+  xmlns       %URI;          #FIXED 'http://www.w3.org/1999/xhtml'+  >++<!--================ Document Head =======================================-->++<!ENTITY % head.misc "(script|style|meta|link|object)*">++<!-- content model is %head.misc; combined with a single+     title and an optional base element in any order -->++<!ELEMENT head (%head.misc;,+     ((title, %head.misc;, (base, %head.misc;)?) |+      (base, %head.misc;, (title, %head.misc;))))>++<!ATTLIST head+  %i18n;+  profile     %URI;          #IMPLIED+  >++<!-- 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. Exactly one title is required per document.+    -->+<!ELEMENT title (#PCDATA)>+<!ATTLIST title %i18n;>++<!-- document base URI -->++<!ELEMENT base EMPTY>+<!ATTLIST base+  href        %URI;          #IMPLIED+  >++<!-- generic metainformation -->+<!ELEMENT meta EMPTY>+<!ATTLIST meta+  %i18n;+  http-equiv  CDATA          #IMPLIED+  name        CDATA          #IMPLIED+  content     CDATA          #REQUIRED+  scheme      CDATA          #IMPLIED+  >++<!--+  Relationship values can be used in principle:++   a) for document specific toolbars/menus when used+      with the link element in document head e.g.+        start, contents, previous, next, index, end, help+   b) to link to a separate style sheet (rel="stylesheet")+   c) to make a link to a script (rel="script")+   d) by stylesheets to control how collections of+      html nodes are rendered into printed documents+   e) to make a link to a printable version of this document+      e.g. a PostScript or PDF version (rel="alternate" media="print")+-->++<!ELEMENT link EMPTY>+<!ATTLIST link+  %attrs;+  charset     %Charset;      #IMPLIED+  href        %URI;          #IMPLIED+  hreflang    %LanguageCode; #IMPLIED+  type        %ContentType;  #IMPLIED+  rel         %LinkTypes;    #IMPLIED+  rev         %LinkTypes;    #IMPLIED+  media       %MediaDesc;    #IMPLIED+  >++<!-- style info, which may include CDATA sections -->+<!ELEMENT style (#PCDATA)>+<!ATTLIST style+  %i18n;+  type        %ContentType;  #REQUIRED+  media       %MediaDesc;    #IMPLIED+  title       %Text;         #IMPLIED+  xml:space   (preserve)     #FIXED 'preserve'+  >++<!-- script statements, which may include CDATA sections -->+<!ELEMENT script (#PCDATA)>+<!ATTLIST script+  charset     %Charset;      #IMPLIED+  type        %ContentType;  #REQUIRED+  src         %URI;          #IMPLIED+  defer       (defer)        #IMPLIED+  xml:space   (preserve)     #FIXED 'preserve'+  >++<!-- alternate content container for non script-based rendering -->++<!ELEMENT noscript %Block;>+<!ATTLIST noscript+  %attrs;+  >++<!--=================== Document Body ====================================-->++<!ELEMENT body %Block;>+<!ATTLIST body+  %attrs;+  onload          %Script;   #IMPLIED+  onunload        %Script;   #IMPLIED+  >++<!ELEMENT div %Flow;>  <!-- generic language/style container -->+<!ATTLIST div+  %attrs;+  >++<!--=================== Paragraphs =======================================-->++<!ELEMENT p %Inline;>+<!ATTLIST p+  %attrs;+  >++<!--=================== Headings =========================================-->++<!--+  There are six levels of headings from h1 (the most important)+  to h6 (the least important).+-->++<!ELEMENT h1  %Inline;>+<!ATTLIST h1+   %attrs;+   >++<!ELEMENT h2 %Inline;>+<!ATTLIST h2+   %attrs;+   >++<!ELEMENT h3 %Inline;>+<!ATTLIST h3+   %attrs;+   >++<!ELEMENT h4 %Inline;>+<!ATTLIST h4+   %attrs;+   >++<!ELEMENT h5 %Inline;>+<!ATTLIST h5+   %attrs;+   >++<!ELEMENT h6 %Inline;>+<!ATTLIST h6+   %attrs;+   >++<!--=================== Lists ============================================-->++<!-- Unordered list -->++<!ELEMENT ul (li)+>+<!ATTLIST ul+  %attrs;+  >++<!-- Ordered (numbered) list -->++<!ELEMENT ol (li)+>+<!ATTLIST ol+  %attrs;+  >++<!-- list item -->++<!ELEMENT li %Flow;>+<!ATTLIST li+  %attrs;+  >++<!-- definition lists - dt for term, dd for its definition -->++<!ELEMENT dl (dt|dd)+>+<!ATTLIST dl+  %attrs;+  >++<!ELEMENT dt %Inline;>+<!ATTLIST dt+  %attrs;+  >++<!ELEMENT dd %Flow;>+<!ATTLIST dd+  %attrs;+  >++<!--=================== Address ==========================================-->++<!-- information on author -->++<!ELEMENT address %Inline;>+<!ATTLIST address+  %attrs;+  >++<!--=================== Horizontal Rule ==================================-->++<!ELEMENT hr EMPTY>+<!ATTLIST hr+  %attrs;+  >++<!--=================== Preformatted Text ================================-->++<!-- content is %Inline; excluding "img|object|big|small|sub|sup" -->++<!ELEMENT pre %pre.content;>+<!ATTLIST pre+  %attrs;+  xml:space (preserve) #FIXED 'preserve'+  >++<!--=================== Block-like Quotes ================================-->++<!ELEMENT blockquote %Block;>+<!ATTLIST blockquote+  %attrs;+  cite        %URI;          #IMPLIED+  >++<!--=================== Inserted/Deleted Text ============================-->++<!--+  ins/del are allowed in block and inline content, but its+  inappropriate to include block content within an ins element+  occurring in inline content.+-->+<!ELEMENT ins %Flow;>+<!ATTLIST ins+  %attrs;+  cite        %URI;          #IMPLIED+  datetime    %Datetime;     #IMPLIED+  >++<!ELEMENT del %Flow;>+<!ATTLIST del+  %attrs;+  cite        %URI;          #IMPLIED+  datetime    %Datetime;     #IMPLIED+  >++<!--================== The Anchor Element ================================-->++<!-- content is %Inline; except that anchors shouldn't be nested -->++<!ELEMENT a %a.content;>+<!ATTLIST a+  %attrs;+  charset     %Charset;      #IMPLIED+  type        %ContentType;  #IMPLIED+  name        NMTOKEN        #IMPLIED+  href        %URI;          #IMPLIED+  hreflang    %LanguageCode; #IMPLIED+  rel         %LinkTypes;    #IMPLIED+  rev         %LinkTypes;    #IMPLIED+  accesskey   %Character;    #IMPLIED+  shape       %Shape;        "rect"+  coords      %Coords;       #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!--===================== Inline Elements ================================-->++<!ELEMENT span %Inline;> <!-- generic language/style container -->+<!ATTLIST span+  %attrs;+  >++<!ELEMENT bdo %Inline;>  <!-- I18N BiDi over-ride -->+<!ATTLIST bdo+  %coreattrs;+  %events;+  lang        %LanguageCode; #IMPLIED+  xml:lang    %LanguageCode; #IMPLIED+  dir         (ltr|rtl)      #REQUIRED+  >++<!ELEMENT br EMPTY>   <!-- forced line break -->+<!ATTLIST br+  %coreattrs;+  >++<!ELEMENT em %Inline;>   <!-- emphasis -->+<!ATTLIST em %attrs;>++<!ELEMENT strong %Inline;>   <!-- strong emphasis -->+<!ATTLIST strong %attrs;>++<!ELEMENT dfn %Inline;>   <!-- definitional -->+<!ATTLIST dfn %attrs;>++<!ELEMENT code %Inline;>   <!-- program code -->+<!ATTLIST code %attrs;>++<!ELEMENT samp %Inline;>   <!-- sample -->+<!ATTLIST samp %attrs;>++<!ELEMENT kbd %Inline;>  <!-- something user would type -->+<!ATTLIST kbd %attrs;>++<!ELEMENT var %Inline;>   <!-- variable -->+<!ATTLIST var %attrs;>++<!ELEMENT cite %Inline;>   <!-- citation -->+<!ATTLIST cite %attrs;>++<!ELEMENT abbr %Inline;>   <!-- abbreviation -->+<!ATTLIST abbr %attrs;>++<!ELEMENT acronym %Inline;>   <!-- acronym -->+<!ATTLIST acronym %attrs;>++<!ELEMENT q %Inline;>   <!-- inlined quote -->+<!ATTLIST q+  %attrs;+  cite        %URI;          #IMPLIED+  >++<!ELEMENT sub %Inline;> <!-- subscript -->+<!ATTLIST sub %attrs;>++<!ELEMENT sup %Inline;> <!-- superscript -->+<!ATTLIST sup %attrs;>++<!ELEMENT tt %Inline;>   <!-- fixed pitch font -->+<!ATTLIST tt %attrs;>++<!ELEMENT i %Inline;>   <!-- italic font -->+<!ATTLIST i %attrs;>++<!ELEMENT b %Inline;>   <!-- bold font -->+<!ATTLIST b %attrs;>++<!ELEMENT big %Inline;>   <!-- bigger font -->+<!ATTLIST big %attrs;>++<!ELEMENT small %Inline;>   <!-- smaller font -->+<!ATTLIST small %attrs;>++<!--==================== Object ======================================-->+<!--+  object is used to embed objects as part of HTML pages.+  param elements should precede other content. Parameters+  can also be expressed as attribute/value pairs on the+  object element itself when brevity is desired.+-->++<!ELEMENT object (#PCDATA | param | %block; | form | %inline; | %misc;)*>+<!ATTLIST object+  %attrs;+  declare     (declare)      #IMPLIED+  classid     %URI;          #IMPLIED+  codebase    %URI;          #IMPLIED+  data        %URI;          #IMPLIED+  type        %ContentType;  #IMPLIED+  codetype    %ContentType;  #IMPLIED+  archive     %UriList;      #IMPLIED+  standby     %Text;         #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  usemap      %URI;          #IMPLIED+  name        NMTOKEN        #IMPLIED+  tabindex    %Number;       #IMPLIED+  >++<!--+  param is used to supply a named property value.+  In XML it would seem natural to follow RDF and support an+  abbreviated syntax where the param elements are replaced+  by attribute value pairs on the object start tag.+-->+<!ELEMENT param EMPTY>+<!ATTLIST param+  id          ID             #IMPLIED+  name        CDATA          #IMPLIED+  value       CDATA          #IMPLIED+  valuetype   (data|ref|object) "data"+  type        %ContentType;  #IMPLIED+  >++<!--=================== Images ===========================================-->++<!--+   To avoid accessibility problems for people who aren't+   able to see the image, you should provide a text+   description using the alt and longdesc attributes.+   In addition, avoid the use of server-side image maps.+   Note that in this DTD there is no name attribute. That+   is only available in the transitional and frameset DTD.+-->++<!ELEMENT img EMPTY>+<!ATTLIST img+  %attrs;+  src         %URI;          #REQUIRED+  alt         %Text;         #REQUIRED+  longdesc    %URI;          #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  usemap      %URI;          #IMPLIED+  ismap       (ismap)        #IMPLIED+  >++<!-- usemap points to a map element which may be in this document+  or an external document, although the latter is not widely supported -->++<!--================== Client-side image maps ============================-->++<!-- These can be placed in the same document or grouped in a+     separate document although this isn't yet widely supported -->++<!ELEMENT map ((%block; | form | %misc;)+ | area+)>+<!ATTLIST map+  %i18n;+  %events;+  id          ID             #REQUIRED+  class       CDATA          #IMPLIED+  style       %StyleSheet;   #IMPLIED+  title       %Text;         #IMPLIED+  name        NMTOKEN        #IMPLIED+  >++<!ELEMENT area EMPTY>+<!ATTLIST area+  %attrs;+  shape       %Shape;        "rect"+  coords      %Coords;       #IMPLIED+  href        %URI;          #IMPLIED+  nohref      (nohref)       #IMPLIED+  alt         %Text;         #REQUIRED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!--================ Forms ===============================================-->+<!ELEMENT form %form.content;>   <!-- forms shouldn't be nested -->++<!ATTLIST form+  %attrs;+  action      %URI;          #REQUIRED+  method      (get|post)     "get"+  enctype     %ContentType;  "application/x-www-form-urlencoded"+  onsubmit    %Script;       #IMPLIED+  onreset     %Script;       #IMPLIED+  accept      %ContentTypes; #IMPLIED+  accept-charset %Charsets;  #IMPLIED+  >++<!--+  Each label must not contain more than ONE field+  Label elements shouldn't be nested.+-->+<!ELEMENT label %Inline;>+<!ATTLIST label+  %attrs;+  for         IDREF          #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!ENTITY % InputType+  "(text | password | checkbox |+    radio | submit | reset |+    file | hidden | image | button)"+   >++<!-- the name attribute is required for all but submit & reset -->++<!ELEMENT input EMPTY>     <!-- form control -->+<!ATTLIST input+  %attrs;+  type        %InputType;    "text"+  name        CDATA          #IMPLIED+  value       CDATA          #IMPLIED+  checked     (checked)      #IMPLIED+  disabled    (disabled)     #IMPLIED+  readonly    (readonly)     #IMPLIED+  size        CDATA          #IMPLIED+  maxlength   %Number;       #IMPLIED+  src         %URI;          #IMPLIED+  alt         CDATA          #IMPLIED+  usemap      %URI;          #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onselect    %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  accept      %ContentTypes; #IMPLIED+  >++<!ELEMENT select (optgroup|option)+>  <!-- option selector -->+<!ATTLIST select+  %attrs;+  name        CDATA          #IMPLIED+  size        %Number;       #IMPLIED+  multiple    (multiple)     #IMPLIED+  disabled    (disabled)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  >++<!ELEMENT optgroup (option)+>   <!-- option group -->+<!ATTLIST optgroup+  %attrs;+  disabled    (disabled)     #IMPLIED+  label       %Text;         #REQUIRED+  >++<!ELEMENT option (#PCDATA)>     <!-- selectable choice -->+<!ATTLIST option+  %attrs;+  selected    (selected)     #IMPLIED+  disabled    (disabled)     #IMPLIED+  label       %Text;         #IMPLIED+  value       CDATA          #IMPLIED+  >++<!ELEMENT textarea (#PCDATA)>     <!-- multi-line text field -->+<!ATTLIST textarea+  %attrs;+  name        CDATA          #IMPLIED+  rows        %Number;       #REQUIRED+  cols        %Number;       #REQUIRED+  disabled    (disabled)     #IMPLIED+  readonly    (readonly)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onselect    %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  >++<!--+  The fieldset element is used to group form fields.+  Only one legend element should occur in the content+  and if present should only be preceded by whitespace.+-->+<!ELEMENT fieldset (#PCDATA | legend | %block; | form | %inline; | %misc;)*>+<!ATTLIST fieldset+  %attrs;+  >++<!ELEMENT legend %Inline;>     <!-- fieldset label -->+<!ATTLIST legend+  %attrs;+  accesskey   %Character;    #IMPLIED+  >++<!--+ Content is %Flow; excluding a, form and form controls+--> +<!ELEMENT button %button.content;>  <!-- push button -->+<!ATTLIST button+  %attrs;+  name        CDATA          #IMPLIED+  value       CDATA          #IMPLIED+  type        (button|submit|reset) "submit"+  disabled    (disabled)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!--======================= Tables =======================================-->++<!-- Derived from IETF HTML table standard, see [RFC1942] -->++<!--+ The border attribute sets the thickness of the frame around the+ table. The default units are screen pixels.++ The frame attribute specifies which parts of the frame around+ the table should be rendered. The values are not the same as+ CALS to avoid a name clash with the valign attribute.+-->+<!ENTITY % TFrame "(void|above|below|hsides|lhs|rhs|vsides|box|border)">++<!--+ The rules attribute defines which rules to draw between cells:++ If rules is absent then assume:+     "none" if border is absent or border="0" otherwise "all"+-->++<!ENTITY % TRules "(none | groups | rows | cols | all)">+  +<!-- horizontal placement of table relative to document -->+<!ENTITY % TAlign "(left|center|right)">++<!-- horizontal alignment attributes for cell contents++  char        alignment char, e.g. char=':'+  charoff     offset for alignment char+-->+<!ENTITY % cellhalign+  "align      (left|center|right|justify|char) #IMPLIED+   char       %Character;    #IMPLIED+   charoff    %Length;       #IMPLIED"+  >++<!-- vertical alignment attributes for cell contents -->+<!ENTITY % cellvalign+  "valign     (top|middle|bottom|baseline) #IMPLIED"+  >++<!ELEMENT table+     (caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))>+<!ELEMENT caption  %Inline;>+<!ELEMENT thead    (tr)+>+<!ELEMENT tfoot    (tr)+>+<!ELEMENT tbody    (tr)+>+<!ELEMENT colgroup (col)*>+<!ELEMENT col      EMPTY>+<!ELEMENT tr       (th|td)+>+<!ELEMENT th       %Flow;>+<!ELEMENT td       %Flow;>++<!ATTLIST table+  %attrs;+  summary     %Text;         #IMPLIED+  width       %Length;       #IMPLIED+  border      %Pixels;       #IMPLIED+  frame       %TFrame;       #IMPLIED+  rules       %TRules;       #IMPLIED+  cellspacing %Length;       #IMPLIED+  cellpadding %Length;       #IMPLIED+  >++<!ENTITY % CAlign "(top|bottom|left|right)">++<!ATTLIST caption+  %attrs;+  >++<!--+colgroup groups a set of col elements. It allows you to group+several semantically related columns together.+-->+<!ATTLIST colgroup+  %attrs;+  span        %Number;       "1"+  width       %MultiLength;  #IMPLIED+  %cellhalign;+  %cellvalign;+  >++<!--+ col elements define the alignment properties for cells in+ one or more columns.++ The width attribute specifies the width of the columns, e.g.++     width=64        width in screen pixels+     width=0.5*      relative width of 0.5++ The span attribute causes the attributes of one+ col element to apply to more than one column.+-->+<!ATTLIST col+  %attrs;+  span        %Number;       "1"+  width       %MultiLength;  #IMPLIED+  %cellhalign;+  %cellvalign;+  >++<!--+    Use thead to duplicate headers when breaking table+    across page boundaries, or for static headers when+    tbody sections are rendered in scrolling panel.++    Use tfoot to duplicate footers when breaking table+    across page boundaries, or for static footers when+    tbody sections are rendered in scrolling panel.++    Use multiple tbody sections when rules are needed+    between groups of table rows.+-->+<!ATTLIST thead+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tfoot+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tbody+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tr+  %attrs;+  %cellhalign;+  %cellvalign;+  >+++<!-- Scope is simpler than headers attribute for common tables -->+<!ENTITY % Scope "(row|col|rowgroup|colgroup)">++<!-- th is for headers, td for data and for cells acting as both -->++<!ATTLIST th+  %attrs;+  abbr        %Text;         #IMPLIED+  axis        CDATA          #IMPLIED+  headers     IDREFS         #IMPLIED+  scope       %Scope;        #IMPLIED+  rowspan     %Number;       "1"+  colspan     %Number;       "1"+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST td+  %attrs;+  abbr        %Text;         #IMPLIED+  axis        CDATA          #IMPLIED+  headers     IDREFS         #IMPLIED+  scope       %Scope;        #IMPLIED+  rowspan     %Number;       "1"+  colspan     %Number;       "1"+  %cellhalign;+  %cellvalign;+  >+

@@ -0,0 +1,1196 @@+<!--+   Extensible HTML version 1.0 Transitional DTD++   This is the same as HTML 4.0 Transitional except for+   changes due to the differences between XML and SGML.++   Namespace = http://www.w3.org/1999/xhtml++   For further information, see: http://www.w3.org/TR/xhtml1++   Copyright (c) 1998-2000 W3C (MIT, INRIA, Keio),+   All Rights Reserved. ++   This DTD module is identified by the PUBLIC and SYSTEM identifiers:++   PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"+   SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"++   $Revision: 1.1 $+   $Date: 2002/10/01 13:47:08 $++-->++<!--================ Character mnemonic entities =========================-->++<!ENTITY % HTMLlat1 PUBLIC+   "-//W3C//ENTITIES Latin 1 for XHTML//EN"+   "xhtml-lat1.ent">+%HTMLlat1;++<!ENTITY % HTMLsymbol PUBLIC+   "-//W3C//ENTITIES Symbols for XHTML//EN"+   "xhtml-symbol.ent">+%HTMLsymbol;++<!ENTITY % HTMLspecial PUBLIC+   "-//W3C//ENTITIES Special for XHTML//EN"+   "xhtml-special.ent">+%HTMLspecial;++<!--================== Imported Names ====================================-->++<!ENTITY % ContentType "CDATA">+    <!-- media type, as per [RFC2045] -->++<!ENTITY % ContentTypes "CDATA">+    <!-- comma-separated list of media types, as per [RFC2045] -->++<!ENTITY % Charset "CDATA">+    <!-- a character encoding, as per [RFC2045] -->++<!ENTITY % Charsets "CDATA">+    <!-- a space separated list of character encodings, as per [RFC2045] -->++<!ENTITY % LanguageCode "NMTOKEN">+    <!-- a language code, as per [RFC1766] -->++<!ENTITY % Character "CDATA">+    <!-- a single character from [ISO10646] -->++<!ENTITY % Number "CDATA">+    <!-- one or more digits -->++<!ENTITY % LinkTypes "CDATA">+    <!-- space-separated list of link types -->++<!ENTITY % MediaDesc "CDATA">+    <!-- single or comma-separated list of media descriptors -->++<!ENTITY % URI "CDATA">+    <!-- a Uniform Resource Identifier, see [RFC2396] -->++<!ENTITY % UriList "CDATA">+    <!-- a space separated list of Uniform Resource Identifiers -->++<!ENTITY % Datetime "CDATA">+    <!-- date and time information. ISO date format -->++<!ENTITY % Script "CDATA">+    <!-- script expression -->++<!ENTITY % StyleSheet "CDATA">+    <!-- style sheet data -->++<!ENTITY % Text "CDATA">+    <!-- used for titles etc. -->++<!ENTITY % FrameTarget "NMTOKEN">+    <!-- render in this frame -->++<!ENTITY % Length "CDATA">+    <!-- nn for pixels or nn% for percentage length -->++<!ENTITY % MultiLength "CDATA">+    <!-- pixel, percentage, or relative -->++<!ENTITY % MultiLengths "CDATA">+    <!-- comma-separated list of MultiLength -->++<!ENTITY % Pixels "CDATA">+    <!-- integer representing length in pixels -->++<!-- these are used for image maps -->++<!ENTITY % Shape "(rect|circle|poly|default)">++<!ENTITY % Coords "CDATA">+    <!-- comma separated list of lengths -->++<!-- used for object, applet, img, input and iframe -->+<!ENTITY % ImgAlign "(top|middle|bottom|left|right)">++<!-- a color using sRGB: #RRGGBB as Hex values -->+<!ENTITY % Color "CDATA">++<!-- There are also 16 widely known color names with their sRGB values:++    Black  = #000000    Green  = #008000+    Silver = #C0C0C0    Lime   = #00FF00+    Gray   = #808080    Olive  = #808000+    White  = #FFFFFF    Yellow = #FFFF00+    Maroon = #800000    Navy   = #000080+    Red    = #FF0000    Blue   = #0000FF+    Purple = #800080    Teal   = #008080+    Fuchsia= #FF00FF    Aqua   = #00FFFF+-->++<!--=================== Generic Attributes ===============================-->++<!-- core attributes common to most elements+  id       document-wide unique id+  class    space separated list of classes+  style    associated style info+  title    advisory title/amplification+-->+<!ENTITY % coreattrs+ "id          ID             #IMPLIED+  class       CDATA          #IMPLIED+  style       %StyleSheet;   #IMPLIED+  title       %Text;         #IMPLIED"+  >++<!-- internationalization attributes+  lang        language code (backwards compatible)+  xml:lang    language code (as per XML 1.0 spec)+  dir         direction for weak/neutral text+-->+<!ENTITY % i18n+ "lang        %LanguageCode; #IMPLIED+  xml:lang    %LanguageCode; #IMPLIED+  dir         (ltr|rtl)      #IMPLIED"+  >++<!-- attributes for common UI events+  onclick     a pointer button was clicked+  ondblclick  a pointer button was double clicked+  onmousedown a pointer button was pressed down+  onmouseup   a pointer button was released+  onmousemove a pointer was moved onto the element+  onmouseout  a pointer was moved away from the element+  onkeypress  a key was pressed and released+  onkeydown   a key was pressed down+  onkeyup     a key was released+-->+<!ENTITY % events+ "onclick     %Script;       #IMPLIED+  ondblclick  %Script;       #IMPLIED+  onmousedown %Script;       #IMPLIED+  onmouseup   %Script;       #IMPLIED+  onmouseover %Script;       #IMPLIED+  onmousemove %Script;       #IMPLIED+  onmouseout  %Script;       #IMPLIED+  onkeypress  %Script;       #IMPLIED+  onkeydown   %Script;       #IMPLIED+  onkeyup     %Script;       #IMPLIED"+  >++<!-- attributes for elements that can get the focus+  accesskey   accessibility key character+  tabindex    position in tabbing order+  onfocus     the element got the focus+  onblur      the element lost the focus+-->+<!ENTITY % focus+ "accesskey   %Character;    #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED"+  >++<!ENTITY % attrs "%coreattrs; %i18n; %events;">++<!-- text alignment for p, div, h1-h6. The default is+     align="left" for ltr headings, "right" for rtl -->++<!ENTITY % TextAlign "align (left|center|right) #IMPLIED">++<!--=================== Text Elements ====================================-->++<!ENTITY % special+   "br | span | bdo | object | applet | img | map | iframe">++<!ENTITY % fontstyle "tt | i | b | big | small | u+                      | s | strike |font | basefont">++<!ENTITY % phrase "em | strong | dfn | code | q | sub | sup |+                   samp | kbd | var | cite | abbr | acronym">++<!ENTITY % inline.forms "input | select | textarea | label | button">++<!-- these can occur at block or inline level -->+<!ENTITY % misc "ins | del | script | noscript">++<!ENTITY % inline "a | %special; | %fontstyle; | %phrase; | %inline.forms;">++<!-- %Inline; covers inline or "text-level" elements -->+<!ENTITY % Inline "(#PCDATA | %inline; | %misc;)*">++<!--================== Block level elements ==============================-->++<!ENTITY % heading "h1|h2|h3|h4|h5|h6">+<!ENTITY % lists "ul | ol | dl | menu | dir">+<!ENTITY % blocktext "pre | hr | blockquote | address | center | noframes">++<!ENTITY % block+    "p | %heading; | div | %lists; | %blocktext; | isindex |fieldset | table">++<!ENTITY % Block "(%block; | form | %misc;)*">++<!-- %Flow; mixes Block and Inline and is used for list items etc. -->+<!ENTITY % Flow "(#PCDATA | %block; | form | %inline; | %misc;)*">++<!--================== Content models for exclusions =====================-->++<!-- a elements use %Inline; excluding a -->++<!ENTITY % a.content+   "(#PCDATA | %special; | %fontstyle; | %phrase; | %inline.forms; | %misc;)*">++<!-- pre uses %Inline excluding img, object, applet, big, small,+     sub, sup, font, or basefont -->++<!ENTITY % pre.content+   "(#PCDATA | a | br | span | bdo | map | tt | i | b | u | s |+      %phrase; | %inline.forms;)*">++<!-- form uses %Flow; excluding form -->++<!ENTITY % form.content "(#PCDATA | %block; | %inline; | %misc;)*">++<!-- button uses %Flow; but excludes a, form, form controls, iframe -->++<!ENTITY % button.content+   "(#PCDATA | p | %heading; | div | %lists; | %blocktext; |+      table | br | span | bdo | object | applet | img | map |+      %fontstyle; | %phrase; | %misc;)*">++<!--================ Document Structure ==================================-->++<!-- the namespace URI designates the document profile -->++<!ELEMENT html (head, body)>+<!ATTLIST html+  %i18n;+  xmlns       %URI;          #FIXED 'http://www.w3.org/1999/xhtml'+  >++<!--================ Document Head =======================================-->++<!ENTITY % head.misc "(script|style|meta|link|object|isindex)*">++<!-- content model is %head.misc; combined with a single+     title and an optional base element in any order -->++<!ELEMENT head (%head.misc;,+     ((title, %head.misc;, (base, %head.misc;)?) |+      (base, %head.misc;, (title, %head.misc;))))>++<!ATTLIST head+  %i18n;+  profile     %URI;          #IMPLIED+  >++<!-- 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. Exactly one title is required per document.+    -->+<!ELEMENT title (#PCDATA)>+<!ATTLIST title %i18n;>++<!-- document base URI -->++<!ELEMENT base EMPTY>+<!ATTLIST base+  href        %URI;          #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!-- generic metainformation -->+<!ELEMENT meta EMPTY>+<!ATTLIST meta+  %i18n;+  http-equiv  CDATA          #IMPLIED+  name        CDATA          #IMPLIED+  content     CDATA          #REQUIRED+  scheme      CDATA          #IMPLIED+  >++<!--+  Relationship values can be used in principle:++   a) for document specific toolbars/menus when used+      with the link element in document head e.g.+        start, contents, previous, next, index, end, help+   b) to link to a separate style sheet (rel="stylesheet")+   c) to make a link to a script (rel="script")+   d) by stylesheets to control how collections of+      html nodes are rendered into printed documents+   e) to make a link to a printable version of this document+      e.g. a PostScript or PDF version (rel="alternate" media="print")+-->++<!ELEMENT link EMPTY>+<!ATTLIST link+  %attrs;+  charset     %Charset;      #IMPLIED+  href        %URI;          #IMPLIED+  hreflang    %LanguageCode; #IMPLIED+  type        %ContentType;  #IMPLIED+  rel         %LinkTypes;    #IMPLIED+  rev         %LinkTypes;    #IMPLIED+  media       %MediaDesc;    #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!-- style info, which may include CDATA sections -->+<!ELEMENT style (#PCDATA)>+<!ATTLIST style+  %i18n;+  type        %ContentType;  #REQUIRED+  media       %MediaDesc;    #IMPLIED+  title       %Text;         #IMPLIED+  xml:space   (preserve)     #FIXED 'preserve'+  >++<!-- script statements, which may include CDATA sections -->+<!ELEMENT script (#PCDATA)>+<!ATTLIST script+  charset     %Charset;      #IMPLIED+  type        %ContentType;  #REQUIRED+  language    CDATA          #IMPLIED+  src         %URI;          #IMPLIED+  defer       (defer)        #IMPLIED+  xml:space   (preserve)     #FIXED 'preserve'+  >++<!-- alternate content container for non script-based rendering -->++<!ELEMENT noscript %Flow;>+<!ATTLIST noscript+  %attrs;+  >++<!--======================= Frames =======================================-->++<!-- inline subwindow -->++<!ELEMENT iframe %Flow;>+<!ATTLIST iframe+  %coreattrs;+  longdesc    %URI;          #IMPLIED+  name        NMTOKEN        #IMPLIED+  src         %URI;          #IMPLIED+  frameborder (1|0)          "1"+  marginwidth %Pixels;       #IMPLIED+  marginheight %Pixels;      #IMPLIED+  scrolling   (yes|no|auto)  "auto"+  align       %ImgAlign;     #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  >++<!-- alternate content container for non frame-based rendering -->++<!ELEMENT noframes %Flow;>+<!ATTLIST noframes+  %attrs;+  >++<!--=================== Document Body ====================================-->++<!ELEMENT body %Flow;>+<!ATTLIST body+  %attrs;+  onload      %Script;       #IMPLIED+  onunload    %Script;       #IMPLIED+  background  %URI;          #IMPLIED+  bgcolor     %Color;        #IMPLIED+  text        %Color;        #IMPLIED+  link        %Color;        #IMPLIED+  vlink       %Color;        #IMPLIED+  alink       %Color;        #IMPLIED+  >++<!ELEMENT div %Flow;>  <!-- generic language/style container -->+<!ATTLIST div+  %attrs;+  %TextAlign;+  >++<!--=================== Paragraphs =======================================-->++<!ELEMENT p %Inline;>+<!ATTLIST p+  %attrs;+  %TextAlign;+  >++<!--=================== Headings =========================================-->++<!--+  There are six levels of headings from h1 (the most important)+  to h6 (the least important).+-->++<!ELEMENT h1  %Inline;>+<!ATTLIST h1+  %attrs;+  %TextAlign;+  >++<!ELEMENT h2 %Inline;>+<!ATTLIST h2+  %attrs;+  %TextAlign;+  >++<!ELEMENT h3 %Inline;>+<!ATTLIST h3+  %attrs;+  %TextAlign;+  >++<!ELEMENT h4 %Inline;>+<!ATTLIST h4+  %attrs;+  %TextAlign;+  >++<!ELEMENT h5 %Inline;>+<!ATTLIST h5+  %attrs;+  %TextAlign;+  >++<!ELEMENT h6 %Inline;>+<!ATTLIST h6+  %attrs;+  %TextAlign;+  >++<!--=================== Lists ============================================-->++<!-- Unordered list bullet styles -->++<!ENTITY % ULStyle "(disc|square|circle)">++<!-- Unordered list -->++<!ELEMENT ul (li)+>+<!ATTLIST ul+  %attrs;+  type        %ULStyle;     #IMPLIED+  compact     (compact)     #IMPLIED+  >++<!-- Ordered list numbering style++    1   arabic numbers      1, 2, 3, ...+    a   lower alpha         a, b, c, ...+    A   upper alpha         A, B, C, ...+    i   lower roman         i, ii, iii, ...+    I   upper roman         I, II, III, ...++    The style is applied to the sequence number which by default+    is reset to 1 for the first list item in an ordered list.+-->+<!ENTITY % OLStyle "CDATA">++<!-- Ordered (numbered) list -->++<!ELEMENT ol (li)+>+<!ATTLIST ol+  %attrs;+  type        %OLStyle;      #IMPLIED+  compact     (compact)      #IMPLIED+  start       %Number;       #IMPLIED+  >++<!-- single column list (DEPRECATED) --> +<!ELEMENT menu (li)+>+<!ATTLIST menu+  %attrs;+  compact     (compact)     #IMPLIED+  >++<!-- multiple column list (DEPRECATED) --> +<!ELEMENT dir (li)+>+<!ATTLIST dir+  %attrs;+  compact     (compact)     #IMPLIED+  >++<!-- LIStyle is constrained to: "(%ULStyle;|%OLStyle;)" -->+<!ENTITY % LIStyle "CDATA">++<!-- list item -->++<!ELEMENT li %Flow;>+<!ATTLIST li+  %attrs;+  type        %LIStyle;      #IMPLIED+  value       %Number;       #IMPLIED+  >++<!-- definition lists - dt for term, dd for its definition -->++<!ELEMENT dl (dt|dd)+>+<!ATTLIST dl+  %attrs;+  compact     (compact)      #IMPLIED+  >++<!ELEMENT dt %Inline;>+<!ATTLIST dt+  %attrs;+  >++<!ELEMENT dd %Flow;>+<!ATTLIST dd+  %attrs;+  >++<!--=================== Address ==========================================-->++<!-- information on author -->++<!ELEMENT address %Inline;>+<!ATTLIST address+  %attrs;+  >++<!--=================== Horizontal Rule ==================================-->++<!ELEMENT hr EMPTY>+<!ATTLIST hr+  %attrs;+  align       (left|center|right) #IMPLIED+  noshade     (noshade)      #IMPLIED+  size        %Pixels;       #IMPLIED+  width       %Length;       #IMPLIED+  >++<!--=================== Preformatted Text ================================-->++<!-- content is %Inline; excluding +        "img|object|applet|big|small|sub|sup|font|basefont" -->++<!ELEMENT pre %pre.content;>+<!ATTLIST pre+  %attrs;+  width       %Number;      #IMPLIED+  xml:space   (preserve)    #FIXED 'preserve'+  >++<!--=================== Block-like Quotes ================================-->++<!ELEMENT blockquote %Flow;>+<!ATTLIST blockquote+  %attrs;+  cite        %URI;          #IMPLIED+  >++<!--=================== Text alignment ===================================-->++<!-- center content -->+<!ELEMENT center %Flow;>+<!ATTLIST center+  %attrs;+  >++<!--=================== Inserted/Deleted Text ============================-->++<!--+  ins/del are allowed in block and inline content, but its+  inappropriate to include block content within an ins element+  occurring in inline content.+-->+<!ELEMENT ins %Flow;>+<!ATTLIST ins+  %attrs;+  cite        %URI;          #IMPLIED+  datetime    %Datetime;     #IMPLIED+  >++<!ELEMENT del %Flow;>+<!ATTLIST del+  %attrs;+  cite        %URI;          #IMPLIED+  datetime    %Datetime;     #IMPLIED+  >++<!--================== The Anchor Element ================================-->++<!-- content is %Inline; except that anchors shouldn't be nested -->++<!ELEMENT a %a.content;>+<!ATTLIST a+  %attrs;+  charset     %Charset;      #IMPLIED+  type        %ContentType;  #IMPLIED+  name        NMTOKEN        #IMPLIED+  href        %URI;          #IMPLIED+  hreflang    %LanguageCode; #IMPLIED+  rel         %LinkTypes;    #IMPLIED+  rev         %LinkTypes;    #IMPLIED+  accesskey   %Character;    #IMPLIED+  shape       %Shape;        "rect"+  coords      %Coords;       #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!--===================== Inline Elements ================================-->++<!ELEMENT span %Inline;> <!-- generic language/style container -->+<!ATTLIST span+  %attrs;+  >++<!ELEMENT bdo %Inline;>  <!-- I18N BiDi over-ride -->+<!ATTLIST bdo+  %coreattrs;+  %events;+  lang        %LanguageCode; #IMPLIED+  xml:lang    %LanguageCode; #IMPLIED+  dir         (ltr|rtl)      #REQUIRED+  >++<!ELEMENT br EMPTY>   <!-- forced line break -->+<!ATTLIST br+  %coreattrs;+  clear       (left|all|right|none) "none"+  >++<!ELEMENT em %Inline;>   <!-- emphasis -->+<!ATTLIST em %attrs;>++<!ELEMENT strong %Inline;>   <!-- strong emphasis -->+<!ATTLIST strong %attrs;>++<!ELEMENT dfn %Inline;>   <!-- definitional -->+<!ATTLIST dfn %attrs;>++<!ELEMENT code %Inline;>   <!-- program code -->+<!ATTLIST code %attrs;>++<!ELEMENT samp %Inline;>   <!-- sample -->+<!ATTLIST samp %attrs;>++<!ELEMENT kbd %Inline;>  <!-- something user would type -->+<!ATTLIST kbd %attrs;>++<!ELEMENT var %Inline;>   <!-- variable -->+<!ATTLIST var %attrs;>++<!ELEMENT cite %Inline;>   <!-- citation -->+<!ATTLIST cite %attrs;>++<!ELEMENT abbr %Inline;>   <!-- abbreviation -->+<!ATTLIST abbr %attrs;>++<!ELEMENT acronym %Inline;>   <!-- acronym -->+<!ATTLIST acronym %attrs;>++<!ELEMENT q %Inline;>   <!-- inlined quote -->+<!ATTLIST q+  %attrs;+  cite        %URI;          #IMPLIED+  >++<!ELEMENT sub %Inline;> <!-- subscript -->+<!ATTLIST sub %attrs;>++<!ELEMENT sup %Inline;> <!-- superscript -->+<!ATTLIST sup %attrs;>++<!ELEMENT tt %Inline;>   <!-- fixed pitch font -->+<!ATTLIST tt %attrs;>++<!ELEMENT i %Inline;>   <!-- italic font -->+<!ATTLIST i %attrs;>++<!ELEMENT b %Inline;>   <!-- bold font -->+<!ATTLIST b %attrs;>++<!ELEMENT big %Inline;>   <!-- bigger font -->+<!ATTLIST big %attrs;>++<!ELEMENT small %Inline;>   <!-- smaller font -->+<!ATTLIST small %attrs;>++<!ELEMENT u %Inline;>   <!-- underline -->+<!ATTLIST u %attrs;>++<!ELEMENT s %Inline;>   <!-- strike-through -->+<!ATTLIST s %attrs;>++<!ELEMENT strike %Inline;>   <!-- strike-through -->+<!ATTLIST strike %attrs;>++<!ELEMENT basefont EMPTY>  <!-- base font size -->+<!ATTLIST basefont+  id          ID             #IMPLIED+  size        CDATA          #REQUIRED+  color       %Color;        #IMPLIED+  face        CDATA          #IMPLIED+  >++<!ELEMENT font %Inline;> <!-- local change to font -->+<!ATTLIST font+  %coreattrs;+  %i18n;+  size        CDATA          #IMPLIED+  color       %Color;        #IMPLIED+  face        CDATA          #IMPLIED+  >++<!--==================== Object ======================================-->+<!--+  object is used to embed objects as part of HTML pages.+  param elements should precede other content. Parameters+  can also be expressed as attribute/value pairs on the+  object element itself when brevity is desired.+-->++<!ELEMENT object (#PCDATA | param | %block; | form | %inline; | %misc;)*>+<!ATTLIST object+  %attrs;+  declare     (declare)      #IMPLIED+  classid     %URI;          #IMPLIED+  codebase    %URI;          #IMPLIED+  data        %URI;          #IMPLIED+  type        %ContentType;  #IMPLIED+  codetype    %ContentType;  #IMPLIED+  archive     %UriList;      #IMPLIED+  standby     %Text;         #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  usemap      %URI;          #IMPLIED+  name        NMTOKEN        #IMPLIED+  tabindex    %Number;       #IMPLIED+  align       %ImgAlign;     #IMPLIED+  border      %Pixels;       #IMPLIED+  hspace      %Pixels;       #IMPLIED+  vspace      %Pixels;       #IMPLIED+  >++<!--+  param is used to supply a named property value.+  In XML it would seem natural to follow RDF and support an+  abbreviated syntax where the param elements are replaced+  by attribute value pairs on the object start tag.+-->+<!ELEMENT param EMPTY>+<!ATTLIST param+  id          ID             #IMPLIED+  name        CDATA          #REQUIRED+  value       CDATA          #IMPLIED+  valuetype   (data|ref|object) "data"+  type        %ContentType;  #IMPLIED+  >++<!--=================== Java applet ==================================-->+<!--+  One of code or object attributes must be present.+  Place param elements before other content.+-->+<!ELEMENT applet (#PCDATA | param | %block; | form | %inline; | %misc;)*>+<!ATTLIST applet+  %coreattrs;+  codebase    %URI;          #IMPLIED+  archive     CDATA          #IMPLIED+  code        CDATA          #IMPLIED+  object      CDATA          #IMPLIED+  alt         %Text;         #IMPLIED+  name        NMTOKEN        #IMPLIED+  width       %Length;       #REQUIRED+  height      %Length;       #REQUIRED+  align       %ImgAlign;     #IMPLIED+  hspace      %Pixels;       #IMPLIED+  vspace      %Pixels;       #IMPLIED+  >++<!--=================== Images ===========================================-->++<!--+   To avoid accessibility problems for people who aren't+   able to see the image, you should provide a text+   description using the alt and longdesc attributes.+   In addition, avoid the use of server-side image maps.+-->++<!ELEMENT img EMPTY>+<!ATTLIST img+  %attrs;+  src         %URI;          #REQUIRED+  alt         %Text;         #REQUIRED+  name        NMTOKEN        #IMPLIED+  longdesc    %URI;          #IMPLIED+  height      %Length;       #IMPLIED+  width       %Length;       #IMPLIED+  usemap      %URI;          #IMPLIED+  ismap       (ismap)        #IMPLIED+  align       %ImgAlign;     #IMPLIED+  border      %Length;       #IMPLIED+  hspace      %Pixels;       #IMPLIED+  vspace      %Pixels;       #IMPLIED+  >++<!-- usemap points to a map element which may be in this document+  or an external document, although the latter is not widely supported -->++<!--================== Client-side image maps ============================-->++<!-- These can be placed in the same document or grouped in a+     separate document although this isn't yet widely supported -->++<!ELEMENT map ((%block; | form | %misc;)+ | area+)>+<!ATTLIST map+  %i18n;+  %events;+  id          ID             #REQUIRED+  class       CDATA          #IMPLIED+  style       %StyleSheet;   #IMPLIED+  title       %Text;         #IMPLIED+  name        CDATA          #IMPLIED+  >++<!ELEMENT area EMPTY>+<!ATTLIST area+  %attrs;+  shape       %Shape;        "rect"+  coords      %Coords;       #IMPLIED+  href        %URI;          #IMPLIED+  nohref      (nohref)       #IMPLIED+  alt         %Text;         #REQUIRED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!--================ Forms ===============================================-->++<!ELEMENT form %form.content;>   <!-- forms shouldn't be nested -->++<!ATTLIST form+  %attrs;+  action      %URI;          #REQUIRED+  method      (get|post)     "get"+  name        NMTOKEN        #IMPLIED+  enctype     %ContentType;  "application/x-www-form-urlencoded"+  onsubmit    %Script;       #IMPLIED+  onreset     %Script;       #IMPLIED+  accept      %ContentTypes; #IMPLIED+  accept-charset %Charsets;  #IMPLIED+  target      %FrameTarget;  #IMPLIED+  >++<!--+  Each label must not contain more than ONE field+  Label elements shouldn't be nested.+-->+<!ELEMENT label %Inline;>+<!ATTLIST label+  %attrs;+  for         IDREF          #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!ENTITY % InputType+  "(text | password | checkbox |+    radio | submit | reset |+    file | hidden | image | button)"+   >++<!-- the name attribute is required for all but submit & reset -->++<!ELEMENT input EMPTY>     <!-- form control -->+<!ATTLIST input+  %attrs;+  type        %InputType;    "text"+  name        CDATA          #IMPLIED+  value       CDATA          #IMPLIED+  checked     (checked)      #IMPLIED+  disabled    (disabled)     #IMPLIED+  readonly    (readonly)     #IMPLIED+  size        CDATA          #IMPLIED+  maxlength   %Number;       #IMPLIED+  src         %URI;          #IMPLIED+  alt         CDATA          #IMPLIED+  usemap      %URI;          #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onselect    %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  accept      %ContentTypes; #IMPLIED+  align       %ImgAlign;     #IMPLIED+  >++<!ELEMENT select (optgroup|option)+>  <!-- option selector -->+<!ATTLIST select+  %attrs;+  name        CDATA          #IMPLIED+  size        %Number;       #IMPLIED+  multiple    (multiple)     #IMPLIED+  disabled    (disabled)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  >++<!ELEMENT optgroup (option)+>   <!-- option group -->+<!ATTLIST optgroup+  %attrs;+  disabled    (disabled)     #IMPLIED+  label       %Text;         #REQUIRED+  >++<!ELEMENT option (#PCDATA)>     <!-- selectable choice -->+<!ATTLIST option+  %attrs;+  selected    (selected)     #IMPLIED+  disabled    (disabled)     #IMPLIED+  label       %Text;         #IMPLIED+  value       CDATA          #IMPLIED+  >++<!ELEMENT textarea (#PCDATA)>     <!-- multi-line text field -->+<!ATTLIST textarea+  %attrs;+  name        CDATA          #IMPLIED+  rows        %Number;       #REQUIRED+  cols        %Number;       #REQUIRED+  disabled    (disabled)     #IMPLIED+  readonly    (readonly)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  onselect    %Script;       #IMPLIED+  onchange    %Script;       #IMPLIED+  >++<!--+  The fieldset element is used to group form fields.+  Only one legend element should occur in the content+  and if present should only be preceded by whitespace.+-->+<!ELEMENT fieldset (#PCDATA | legend | %block; | form | %inline; | %misc;)*>+<!ATTLIST fieldset+  %attrs;+  >++<!ENTITY % LAlign "(top|bottom|left|right)">++<!ELEMENT legend %Inline;>     <!-- fieldset label -->+<!ATTLIST legend+  %attrs;+  accesskey   %Character;    #IMPLIED+  align       %LAlign;       #IMPLIED+  >++<!--+ Content is %Flow; excluding a, form, form controls, iframe+--> +<!ELEMENT button %button.content;>  <!-- push button -->+<!ATTLIST button+  %attrs;+  name        CDATA          #IMPLIED+  value       CDATA          #IMPLIED+  type        (button|submit|reset) "submit"+  disabled    (disabled)     #IMPLIED+  tabindex    %Number;       #IMPLIED+  accesskey   %Character;    #IMPLIED+  onfocus     %Script;       #IMPLIED+  onblur      %Script;       #IMPLIED+  >++<!-- single-line text input control (DEPRECATED) -->+<!ELEMENT isindex EMPTY>+<!ATTLIST isindex+  %coreattrs;+  %i18n;+  prompt      %Text;         #IMPLIED+  >++<!--======================= Tables =======================================-->++<!-- Derived from IETF HTML table standard, see [RFC1942] -->++<!--+ The border attribute sets the thickness of the frame around the+ table. The default units are screen pixels.++ The frame attribute specifies which parts of the frame around+ the table should be rendered. The values are not the same as+ CALS to avoid a name clash with the valign attribute.+-->+<!ENTITY % TFrame "(void|above|below|hsides|lhs|rhs|vsides|box|border)">++<!--+ The rules attribute defines which rules to draw between cells:++ If rules is absent then assume:+     "none" if border is absent or border="0" otherwise "all"+-->++<!ENTITY % TRules "(none | groups | rows | cols | all)">+  +<!-- horizontal placement of table relative to document -->+<!ENTITY % TAlign "(left|center|right)">++<!-- horizontal alignment attributes for cell contents++  char        alignment char, e.g. char=':'+  charoff     offset for alignment char+-->+<!ENTITY % cellhalign+  "align      (left|center|right|justify|char) #IMPLIED+   char       %Character;    #IMPLIED+   charoff    %Length;       #IMPLIED"+  >++<!-- vertical alignment attributes for cell contents -->+<!ENTITY % cellvalign+  "valign     (top|middle|bottom|baseline) #IMPLIED"+  >++<!ELEMENT table+     (caption?, (col*|colgroup*), thead?, tfoot?, (tbody+|tr+))>+<!ELEMENT caption  %Inline;>+<!ELEMENT thead    (tr)+>+<!ELEMENT tfoot    (tr)+>+<!ELEMENT tbody    (tr)+>+<!ELEMENT colgroup (col)*>+<!ELEMENT col      EMPTY>+<!ELEMENT tr       (th|td)+>+<!ELEMENT th       %Flow;>+<!ELEMENT td       %Flow;>++<!ATTLIST table+  %attrs;+  summary     %Text;         #IMPLIED+  width       %Length;       #IMPLIED+  border      %Pixels;       #IMPLIED+  frame       %TFrame;       #IMPLIED+  rules       %TRules;       #IMPLIED+  cellspacing %Length;       #IMPLIED+  cellpadding %Length;       #IMPLIED+  align       %TAlign;       #IMPLIED+  bgcolor     %Color;        #IMPLIED+  >++<!ENTITY % CAlign "(top|bottom|left|right)">++<!ATTLIST caption+  %attrs;+  align       %CAlign;       #IMPLIED+  >++<!--+colgroup groups a set of col elements. It allows you to group+several semantically related columns together.+-->+<!ATTLIST colgroup+  %attrs;+  span        %Number;       "1"+  width       %MultiLength;  #IMPLIED+  %cellhalign;+  %cellvalign;+  >++<!--+ col elements define the alignment properties for cells in+ one or more columns.++ The width attribute specifies the width of the columns, e.g.++     width=64        width in screen pixels+     width=0.5*      relative width of 0.5++ The span attribute causes the attributes of one+ col element to apply to more than one column.+-->+<!ATTLIST col+  %attrs;+  span        %Number;       "1"+  width       %MultiLength;  #IMPLIED+  %cellhalign;+  %cellvalign;+  >++<!--+    Use thead to duplicate headers when breaking table+    across page boundaries, or for static headers when+    tbody sections are rendered in scrolling panel.++    Use tfoot to duplicate footers when breaking table+    across page boundaries, or for static footers when+    tbody sections are rendered in scrolling panel.++    Use multiple tbody sections when rules are needed+    between groups of table rows.+-->+<!ATTLIST thead+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tfoot+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tbody+  %attrs;+  %cellhalign;+  %cellvalign;+  >++<!ATTLIST tr+  %attrs;+  %cellhalign;+  %cellvalign;+  bgcolor     %Color;        #IMPLIED+  >++<!-- Scope is simpler than headers attribute for common tables -->+<!ENTITY % Scope "(row|col|rowgroup|colgroup)">++<!-- th is for headers, td for data and for cells acting as both -->++<!ATTLIST th+  %attrs;+  abbr        %Text;         #IMPLIED+  axis        CDATA          #IMPLIED+  headers     IDREFS         #IMPLIED+  scope       %Scope;        #IMPLIED+  rowspan     %Number;       "1"+  colspan     %Number;       "1"+  %cellhalign;+  %cellvalign;+  nowrap      (nowrap)       #IMPLIED+  bgcolor     %Color;        #IMPLIED+  width       %Pixels;       #IMPLIED+  height      %Pixels;       #IMPLIED+  >++<!ATTLIST td+  %attrs;+  abbr        %Text;         #IMPLIED+  axis        CDATA          #IMPLIED+  headers     IDREFS         #IMPLIED+  scope       %Scope;        #IMPLIED+  rowspan     %Number;       "1"+  colspan     %Number;       "1"+  %cellhalign;+  %cellvalign;+  nowrap      (nowrap)       #IMPLIED+  bgcolor     %Color;        #IMPLIED+  width       %Pixels;       #IMPLIED+  height      %Pixels;       #IMPLIED+  >+

@@ -1,6 +1,6 @@ -- arch-tag: Haskell XML Toolbox main description file Name:           hxt-Version:        9.0.1+Version:        9.1.0 Synopsis:       A collection of tools for processing XML with Haskell. Description:    The Haskell XML Toolbox bases on the ideas of HaXml and HXML,                 but introduces a more general approach for processing XML with Haskell.@@ -48,6 +48,7 @@  examples/arrows/HelloWorld/Mini.hs  examples/arrows/hparser/emptyElements.html  examples/arrows/hparser/example1.xml+ examples/arrows/hparser/example1CRLF.xml  examples/arrows/hparser/HXmlParser.hs  examples/arrows/hparser/invalid1.xml  examples/arrows/hparser/invalid2.rng@@ -63,6 +64,14 @@  examples/arrows/performance/Makefile  examples/arrows/pickle/Makefile  examples/arrows/pickle/PickleTest.hs+ examples/xhtml/tmp.xml+ examples/xhtml/xhtml1-frameset.dtd+ examples/xhtml/xhtml1-strict.dtd+ examples/xhtml/xhtml1-transitional.dtd+ examples/xhtml/xhtml-lat1.ent+ examples/xhtml/xhtml-special.ent+ examples/xhtml/xhtml-symbol.ent+ examples/xhtml/xhtml.xml  library  exposed-modules:@@ -71,18 +80,25 @@   Control.Arrow.ArrowIf,   Control.Arrow.ArrowList,   Control.Arrow.ArrowNF,+  Control.Arrow.ArrowNavigatableTree,   Control.Arrow.ArrowState,   Control.Arrow.ArrowTree,   Control.Arrow.IOListArrow,   Control.Arrow.IOStateListArrow,   Control.Arrow.ListArrow,   Control.Arrow.ListArrows,+  Control.Arrow.NTreeEdit,   Control.Arrow.StateListArrow,+  Control.FlatSeq,   Data.AssocList,   Data.Atom,   Data.Function.Selector,   Data.Tree.Class,   Data.Tree.NTree.TypeDefs,+  Data.Tree.NTree.Edit,+  Data.Tree.NTree.Zipper.TypeDefs,+  Data.Tree.NavigatableTree.Class,+  Data.Tree.NavigatableTree.XPathAxis,   Text.XML.HXT.Arrow.Binary,   Text.XML.HXT.Arrow.DTDProcessing,   Text.XML.HXT.Arrow.DocumentInput,@@ -145,6 +161,7 @@  hs-source-dirs: src   ghc-options: -Wall+ ghc-prof-options: -auto-all -caf-all   extensions: MultiParamTypeClasses DeriveDataTypeable FunctionalDependencies FlexibleInstances @@ -159,6 +176,6 @@                 deepseq    >= 1.1 && < 2,                 bytestring >= 0.9 && < 1,                 binary     >= 0.5 && < 1,-                hxt-charproperties  >= 9 && < 10,-                hxt-unicode         >= 9 && < 10,-                hxt-regex-xmlschema >= 9 && < 10+                hxt-charproperties  >= 9.1 && < 10,+                hxt-unicode         >= 9   && < 10,+                hxt-regex-xmlschema >= 9   && < 10

@@ -31,8 +31,8 @@      catchA      :: a b c -> a SomeException c -> a b c     catchA f h  = tryA f-		  >>>-		  ( h ||| returnA )+                  >>>+                  ( h ||| returnA )   -- ------------------------------------------------------------

@@ -33,6 +33,7 @@     -- | construct an arrow from an IO action without any parameter     arrIO0              :: IO c -> a b c     arrIO0 f            = arrIO (const f)+    {-# INLINE arrIO0 #-}      -- | construction of a 2 argument arrow from a binary IO action     -- |@@ -40,6 +41,7 @@      arrIO2              :: (b1 -> b2 -> IO c) -> a (b1, b2) c     arrIO2 f            = arrIO (\ ~(x1, x2) -> f x1 x2)+    {-# INLINE arrIO2 #-}      -- | construction of a 3 argument arrow from a 3-ary IO action     -- |@@ -47,6 +49,7 @@      arrIO3              :: (b1 -> b2 -> b3 -> IO c) -> a (b1, (b2, b3)) c     arrIO3 f            = arrIO (\ ~(x1, ~(x2, x3)) -> f x1 x2 x3)+    {-# INLINE arrIO3 #-}      -- | construction of a 4 argument arrow from a 4-ary IO action     -- |@@ -54,6 +57,7 @@      arrIO4              :: (b1 -> b2 -> b3 -> b4 -> IO c) -> a (b1, (b2, (b3, b4))) c     arrIO4 f            = arrIO (\ ~(x1, ~(x2, ~(x3, x4))) -> f x1 x2 x3 x4)+    {-# INLINE arrIO4 #-}   -- | the interface for converting an IO predicate into a list arrow

@@ -47,46 +47,55 @@      ifP                 :: (b -> Bool) -> a b d -> a b d -> a b d     ifP p               = ifA (isA p)+    {-# INLINE ifP #-}      -- | negation: @ neg f = ifA f none this @      neg                 :: a b c -> a b b     neg f               = ifA f none this+    {-# INLINE neg #-}      -- | @ f \`when\` g @ : when the predicate g holds, f is applied, else the identity filter this      when                :: a b b -> a b c -> a b b     f `when` g          = ifA g f this+    {-# INLINE when #-}      -- | shortcut: @ f \`whenP\` p = f \`when\` (isA p) @      whenP               :: a b b -> (b -> Bool) -> a b b     f `whenP` g         = ifP g f this+    {-# INLINE whenP #-}      -- | @ f \`whenNot\` g @ : when the predicate g does not hold, f is applied, else the identity filter this      whenNot             :: a b b -> a b c -> a b b     f `whenNot` g       = ifA g this f+    {-# INLINE whenNot #-}      -- | like 'whenP'      whenNotP            :: a b b -> (b -> Bool) -> a b b     f `whenNotP` g      = ifP g this f+    {-# INLINE whenNotP #-}      -- | @ g \`guards\` f @ : when the predicate g holds, f is applied, else none      guards              :: a b c -> a b d -> a b d     f `guards` g        = ifA f g none+    {-# INLINE guards #-}      -- | like 'whenP'      guardsP             :: (b -> Bool) -> a b d -> a b d     f `guardsP` g       = ifP f g none+    {-# INLINE guardsP #-}      -- | shortcut for @ f `guards` this @      filterA             :: a b c -> a b b     filterA f           = ifA f this none+    {-# INLINE filterA #-}      -- | @ f \`containing\` g @ : keep only those results from f for which g holds     --@@ -94,6 +103,7 @@      containing          :: a b c -> a c d -> a b c     f `containing` g    = f >>> g `guards` this+    {-# INLINE containing #-}      -- | @ f \`notContaining\` g @ : keep only those results from f for which g does not hold     --@@ -101,6 +111,7 @@      notContaining       :: a b c -> a c d -> a b c     f `notContaining` g = f >>> ifA g none this+    {-# INLINE notContaining #-}      -- | @ f \`orElse\` g @ : directional choice: if f succeeds, the result of f is the result, else g is applied     orElse              :: a b c -> a b c -> a b c

@@ -39,7 +39,7 @@  -- | The interface for list arrows ----- Only 'mkA', 'arr2A', 'isA' '(>>.)' don't have default implementations+-- Only 'mkA', 'isA' '(>>.)' don't have default implementations  class (Arrow a, ArrowPlus a, ArrowZero a, ArrowApply a) => ArrowList a where @@ -49,6 +49,7 @@      arr2                :: (b1 -> b2 -> c) -> a (b1, b2) c     arr2                = arr . uncurry+    {-# INLINE arr2 #-}      -- | construction of a 3 argument arrow from a 3-ary function     -- |@@ -56,6 +57,7 @@      arr3                :: (b1 -> b2 -> b3 -> c) -> a (b1, (b2, b3)) c     arr3 f              = arr (\ ~(x1, ~(x2, x3)) -> f x1 x2 x3)+    {-# INLINE arr3 #-}      -- | construction of a 4 argument arrow from a 4-ary function     -- |@@ -63,10 +65,13 @@      arr4                :: (b1 -> b2 -> b3 -> b4 -> c) -> a (b1, (b2, (b3, b4))) c     arr4 f              = arr (\ ~(x1, ~(x2, ~(x3, x4))) -> f x1 x2 x3 x4)+    {-# INLINE arr4 #-}      -- | construction of a 2 argument arrow from a singe argument arrow      arr2A               :: (b -> a c d) -> a (b, c) d+    arr2A f             = first (arr f) >>> app+    {-# INLINE arr2A #-}      -- | constructor for a list arrow from a function with a list as result @@ -76,16 +81,19 @@      arr2L               :: (b -> c -> [d]) -> a (b, c) d     arr2L               = arrL . uncurry+    {-# INLINE arr2L #-}      -- | constructor for a const arrow: @ constA = arr . const @      constA              :: c -> a b c     constA              = arr . const+    {-# INLINE constA #-}      -- | constructor for a const arrow: @ constL = arrL . const @      constL              :: [c] -> a b c     constL              = arrL . const+    {-# INLINE constL #-}      -- | builds an arrow from a predicate.     -- If the predicate holds, the single list containing the input is returned, else the empty list@@ -104,6 +112,7 @@      (>.)                :: a b c -> ([c] ->  d ) -> a b d     af >. f             = af >>. ((:[]) . f)+    {-# INLINE (>.) #-}      -- | combinator for converting an arrow into a determinstic version with all results collected in a single element list     --@@ -119,6 +128,7 @@      listA               :: a b c -> a b [c]     listA af            = af >>.  (:[])+    {-# INLINE listA #-}      -- | the inverse of 'listA'     --@@ -128,16 +138,19 @@      unlistA             :: a [b] b     unlistA             = arrL id+    {-# INLINE unlistA #-}      -- | the identity arrow, alias for returnA      this                :: a b b     this                = returnA+    {-# INLINE this #-}      -- | the zero arrow, alias for zeroArrow      none                :: a b c     none                = zeroArrow+    {-# INLINE none #-}      -- | converts an arrow, that may fail, into an arrow that always succeeds     --@@ -145,6 +158,7 @@      withDefault         :: a b c -> c -> a b c     withDefault a d     = a >>. \ x -> if null x then [d] else x+    {-# INLINE withDefault #-}      -- | makes a list arrow deterministic, the number of results is at most 1     --@@ -327,6 +341,7 @@      perform             :: a b c -> a b b     perform f           = listA f &&& this >>> arr snd+    {-# INLINE perform #-}      -- | generalization of arrow combinator '<+>'     --@@ -334,6 +349,7 @@      catA                :: [a b c] -> a b c     catA                = foldl (<+>) none+    {-# INLINE catA #-}      -- | generalization of arrow combinator '>>>'     --@@ -341,5 +357,6 @@      seqA                :: [a b b] -> a b b     seqA                = foldl (>>>) this+    {-# INLINE seqA #-}  -- ------------------------------------------------------------

@@ -2,7 +2,7 @@  {- |    Module     : Control.Arrow.ArrowNF-   Copyright  : Copyright (C) 2005-8 Uwe Schmidt+   Copyright  : Copyright (C) 2011 Uwe Schmidt    License    : MIT     Maintainer : Uwe Schmidt (uwe\@fh-wedel.de)@@ -19,7 +19,10 @@ where  import Control.Arrow+import Control.Arrow.ArrowList+ import Control.DeepSeq+import Control.FlatSeq  -- | -- complete evaluation of an arrow result using 'Control.DeepSeq'@@ -32,7 +35,27 @@ strictA = arr $ \ x -> deepseq x x  class (Arrow a) => ArrowNF a where-    rnfA        :: (NFData c) => a b c -> a b c-    rnfA f      = f >>> strictA+    rnfA        		:: (NFData c) => a b c -> a b c+    rnfA f      		= f >>^ (\ x -> deepseq x x)+    {-# INLINE rnfA #-}++-- |+-- partial evaluation of an arrow result using 'Control.FlatSeq'+--+-- There are tow arrows with force the partial evaluation. By convention+-- the 2. should be less lazy than the 1.+--+-- These arrows are sometimes useful for preventing space leaks, especially when parsing+-- complex data structures. In many cases the evaluated AST is more space efficient+-- than the unevaluaded with a lot of closures.++class (Arrow a, ArrowList a) => ArrowWNF a where+    rwnfA                       :: (WNFData c) => a b c -> a b c+    rwnfA f                     = f >>. \ x -> rlnf rwnf x `seq` x+    {-# INLINE rwnfA #-}++    rwnf2A                  	:: (WNFData c) => a b c -> a b c+    rwnf2A f                	= f >>. \ x -> rlnf rwnf2 x `seq` x+    {-# INLINE rwnf2A #-}  -- ------------------------------------------------------------

@@ -0,0 +1,313 @@+-- ------------------------------------------------------------++{- |+   Module     : Control.Arrow.ArrowNavigatableTree+   Copyright  : Copyright (C) 2010 Uwe Schmidt+   License    : MIT++   Maintainer : Uwe Schmidt (uwe\@fh-wedel.de)+   Stability  : experimental+   Portability: portable++   List arrows for navigatable trees++   Trees that implement the "Data.Tree.NavigatableTree.Class" interface, can be processed+   with these arrows.+-}++-- ------------------------------------------------------------++module Control.Arrow.ArrowNavigatableTree+where++import           Control.Arrow+import           Control.Arrow.ArrowList+import           Control.Arrow.ArrowIf++import           Data.Maybe++import           Data.Tree.NavigatableTree.Class        ( NavigatableTree+                                                        , NavigatableTreeToTree+                                                        , NavigatableTreeModify+                                                        )+import qualified Data.Tree.NavigatableTree.Class        as T+import qualified Data.Tree.NavigatableTree.XPathAxis    as T++-- ------------------------------------------------------------++-- | The interface for navigatable tree arrows+--+-- all functions have default implementations++class (ArrowList a) => ArrowNavigatableTree a where++    -- move one step towards the root+    moveUp              :: NavigatableTree t => a (t b) (t b)+    moveUp              = arrL $ maybeToList . T.mvUp++    -- descend one step to the leftmost child+    moveDown            :: NavigatableTree t => a (t b) (t b)+    moveDown            = arrL $ maybeToList . T.mvDown++    -- move to the left neighbour+    moveLeft            :: NavigatableTree t => a (t b) (t b)+    moveLeft            = arrL $ maybeToList . T.mvLeft++    -- move to the right neighbour+    moveRight           :: NavigatableTree t => a (t b) (t b)+    moveRight           = arrL $ maybeToList . T.mvRight++-- derived functions++parentAxis              :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+parentAxis              = arrL T.parentAxis++-- | XPath axis: ancestor++ancestorAxis            :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+ancestorAxis            = arrL T.ancestorAxis++-- | XPath axis: ancestor or self++ancestorOrSelfAxis      :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+ancestorOrSelfAxis      = arrL T.ancestorOrSelfAxis++-- | XPath axis: child++childAxis               :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+childAxis               = arrL T.childAxis++-- | XPath axis: descendant++descendantAxis          :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+descendantAxis          = arrL T.descendantAxis++-- | XPath axis: descendant or self++descendantOrSelfAxis    :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+descendantOrSelfAxis    = arrL T.descendantOrSelfAxis++-- | not an XPath axis but useful: descendant or following++descendantOrFollowingAxis    :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+descendantOrFollowingAxis    = descendantAxis <+> followingAxis++-- | not an official XPath axis but useful: reverse descendant or self, used in preceding axis++revDescendantOrSelfAxis :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+revDescendantOrSelfAxis = arrL T.revDescendantOrSelfAxis++-- | XPath axis: following sibling++followingSiblingAxis    :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+followingSiblingAxis    = arrL T.followingSiblingAxis++-- | XPath axis: preceeding sibling++precedingSiblingAxis    :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+precedingSiblingAxis    = arrL T.precedingSiblingAxis++-- | XPath axis: self++selfAxis                :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+selfAxis                = arrL T.selfAxis++-- | XPath axis: following++followingAxis           :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+followingAxis           = arrL T.followingAxis++-- | XPath axis: preceding++precedingAxis           :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+precedingAxis           = arrL T.precedingAxis++-- ------------------------------------------------------------++-- | move to the root++moveToRoot              :: (Arrow a, NavigatableTree t) => a (t b) (t b)+moveToRoot              = arr T.mvToRoot++isAtRoot                :: (ArrowList a, NavigatableTree t) => a (t b) (t b)+isAtRoot                = isA (null . T.ancestorAxis)++-- ------------------------------------------------------------++-- | Conversion from a tree into a navigatable tree++addNav                  :: ( ArrowList a+                           , NavigatableTreeToTree nt t+                           ) =>+                           a (t b) (nt b)+addNav                  = arr T.fromTree+++-- | Conversion from a navigatable tree into an ordinary tree++remNav                  :: ( ArrowList a+                           , NavigatableTreeToTree nt t+                           ) =>+                           a (nt b) (t b)+remNav                  = arr T.toTree++-- | apply an operation using navigation to an ordinary tree+--+-- This root and all children may be visited in arbitrary order++withNav                 :: ( ArrowList a+                           , NavigatableTreeToTree nt t+                           ) =>+                           a (nt b) (nt c) -> a (t b) (t c)+withNav f               = addNav >>> f >>> remNav+++-- | apply a simple operation without use of navigation to a navigatable tree+--+-- This enables to apply arbitrary tree operations to navigatable trees++withoutNav              :: ( ArrowList a+                           , NavigatableTreeToTree nt t+                           , NavigatableTreeModify nt t+                           ) =>+                           a (t b) (t b) -> a (nt b) (nt b)+withoutNav f            = ( (remNav >>> f)                      -- apply the simple arrow to the tree+                            &&&+                            this                                -- remember the navigation context+                          )+                          >>> arr (uncurry T.substThisTree)             -- resore the context+                             +-- ------------------------------------------------------------++-- | Filter an axis with an ordinary tree predicate+--+-- Example: In a tree of Ints find all nodes in the subtrees (in preorder) that have label 42+--+-- > descendantAxis >>> filterAxis (hasNode (== 42))+--+-- Example: In an XML Tree find the following nodes of a node with attribute id and value 42+--+-- > descendantAxis >>> filterAxis (hasAttrValue "id" (=="42")) >>> followingAxis++filterAxis              :: ( ArrowIf a+                           , NavigatableTreeToTree nt t+                           ) =>+                           a (t b) c -> a (nt b) (nt b)++filterAxis p            = (remNav >>> p) `guards` this+{-# INLINE filterAxis #-}+++-- | Move to the next tree on a given axis. Deterministic arrow+--+-- Example: Move to the next node in a preorder visit: next child or else next following+--+-- > moveOn descendantOrFollowingAxis++moveOn                  :: ( ArrowList a+                           , NavigatableTree t+                           ) =>+                           a (t b) (t b) -> a (t b) (t b)+moveOn axis             = single $ axis+{-# INLINE moveOn #-}++-- ------------------------------------------------------------++-- | Change the current subtree of a navigatable tree.+--+-- The arrow for computing the changes should be deterministic. If it fails+-- nothing is changed.++changeThisTree          :: ( ArrowList a+                           , ArrowIf a+                           , NavigatableTreeToTree nt t+                           , NavigatableTreeModify nt t+                           ) =>+                           a (t b) (t b) -> a (nt b) (nt b)+changeThisTree cf       = withoutNav $ single cf `orElse` this++-- | Substitute the current subtree of a navigatable tree by a given tree++substThisTree           :: ( ArrowList a+                           , ArrowIf a+                           , NavigatableTreeToTree nt t+                           , NavigatableTreeModify nt t+                           ) =>+                           t b -> a (nt b) (nt b)+substThisTree t         = changeThisTree (constA t)++-- ------------------------------------------------------------++-- | apply an ordinary arrow to the current subtree of a navigatabe tree and add the result trees in front of the current tree.+--+-- If this arrow is applied to the root, it will fail, because we want a tree as result, not a forest.++addToTheLeft            :: ( ArrowList a+                           , NavigatableTreeToTree nt t+                           , NavigatableTreeModify nt t+                           ) =>+                           a (t b) (t b) -> a (nt b) (nt b)+addToTheLeft            = addToOneSide $+                          foldl (\ acc t -> acc >>= T.addTreeLeft t)+{-# INLINE addToTheLeft #-}++-- | apply an ordinary arrow to the current subtree of a navigatabe tree and add the result trees behind the current tree.+--+-- If this arrow is applied to the root, it will fail, because we want a tree as result, not a forest.++addToTheRight           :: ( ArrowList a+                           , NavigatableTreeToTree nt t+                           , NavigatableTreeModify nt t+                           ) =>+                           a (t b) (t b) -> a (nt b) (nt b)+addToTheRight           = addToOneSide $+                          foldr (\ t acc -> acc >>= T.addTreeRight t)+{-# INLINE addToTheRight #-}+++-- | addToOneSide does the real work for 'addToTheLeft' and 'addToTheRight'++addToOneSide            :: ( ArrowList a+                           , NavigatableTreeToTree nt t+                           , NavigatableTreeModify nt t+                           ) =>+                           ( Maybe (nt b) -> [t b] -> Maybe (nt b) ) ->+                           a (t  b) (t  b) ->+                           a (nt b) (nt b)+addToOneSide side f     = ( ( remNav >>> listA f )+                            &&&+                            this+                          )+                          >>>+                          arrL ( uncurry (\ ts nt -> side (Just nt) ts)+                                 >>>+                                 maybeToList+                               )++-- ------------------------------------------------------------++-- | drop the direct left sibling tree of the given navigatable tree+--+-- If this arrow is applied to the root or a leftmost tree, it will fail, because there is nothing to remove++dropFromTheLeft         :: ( ArrowList a+                           -- , NavigatableTreeToTree nt t+                           , NavigatableTreeModify nt t+                           ) =>+                           a (nt b) (nt b)+dropFromTheLeft            = arrL $ T.dropTreeLeft >>> maybeToList+{-# INLINE dropFromTheLeft #-}++-- | drop the direct left sibling tree of the given navigatable tree+--+-- If this arrow is applied to the root or a rightmost tree, it will fail, because there is nothing to remove++dropFromTheRight        :: ( ArrowList a+                           , NavigatableTreeModify nt t+                           ) =>+                           a (nt b) (nt b)+dropFromTheRight            = arrL $ T.dropTreeRight >>> maybeToList+{-# INLINE dropFromTheRight #-}++-- ------------------------------------------------------------+