Commits

mstrong  committed 3106854

add html4_0_1 dtd and sample catalog files to resolve issue #123

  • Participants
  • Parent commits 2b116d8
  • Tags Production Release v2.0.0 04192011

Comments (0)

Files changed (9)

File src/test/resources/examples/sgml/dtds/html4_0_1/HTML4.cat

+OVERRIDE YES
+
+PUBLIC "-//W3C//DTD HTML 4.01//EN" strict.dtd
+PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" loose.dtd
+PUBLIC "-//W3C//DTD HTML 4.01 Frameset//EN" frameset.dtd
+PUBLIC "-//W3C//ENTITIES Latin1//EN//HTML" HTMLlat1.ent
+PUBLIC "-//W3C//ENTITIES Special//EN//HTML" HTMLspecial.ent
+PUBLIC "-//W3C//ENTITIES Symbols//EN//HTML" HTMLsymbol.ent

File src/test/resources/examples/sgml/dtds/html4_0_1/HTMLlat1.ent

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

File src/test/resources/examples/sgml/dtds/html4_0_1/HTMLspecial.ent

+<!-- Special characters for HTML -->
+
+<!-- Character entity set. Typical invocation:
+     <!ENTITY % HTMLspecial PUBLIC
+       "-//W3C//ENTITIES Special//EN//HTML">
+     %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. CDATA values are decimal
+     conversions of the ISO 10646 values and refer to the document
+     character set. Names are ISO 10646 names. 
+
+-->
+
+<!-- C0 Controls and Basic Latin -->
+<!ENTITY quot    CDATA "&#34;"   -- quotation mark = APL quote,
+                                    U+0022 ISOnum -->
+<!ENTITY amp     CDATA "&#38;"   -- ampersand, U+0026 ISOnum -->
+<!ENTITY lt      CDATA "&#60;"   -- less-than sign, U+003C ISOnum -->
+<!ENTITY gt      CDATA "&#62;"   -- greater-than sign, U+003E ISOnum -->
+
+<!-- Latin Extended-A -->
+<!ENTITY OElig   CDATA "&#338;"  -- latin capital ligature OE,
+                                    U+0152 ISOlat2 -->
+<!ENTITY oelig   CDATA "&#339;"  -- latin small ligature oe, U+0153 ISOlat2 -->
+<!-- ligature is a misnomer, this is a separate character in some languages -->
+<!ENTITY Scaron  CDATA "&#352;"  -- latin capital letter S with caron,
+                                    U+0160 ISOlat2 -->
+<!ENTITY scaron  CDATA "&#353;"  -- latin small letter s with caron,
+                                    U+0161 ISOlat2 -->
+<!ENTITY Yuml    CDATA "&#376;"  -- latin capital letter Y with diaeresis,
+                                    U+0178 ISOlat2 -->
+
+<!-- Spacing Modifier Letters -->
+<!ENTITY circ    CDATA "&#710;"  -- modifier letter circumflex accent,
+                                    U+02C6 ISOpub -->
+<!ENTITY tilde   CDATA "&#732;"  -- small tilde, U+02DC ISOdia -->
+
+<!-- General Punctuation -->
+<!ENTITY ensp    CDATA "&#8194;" -- en space, U+2002 ISOpub -->
+<!ENTITY emsp    CDATA "&#8195;" -- em space, U+2003 ISOpub -->
+<!ENTITY thinsp  CDATA "&#8201;" -- thin space, U+2009 ISOpub -->
+<!ENTITY zwnj    CDATA "&#8204;" -- zero width non-joiner,
+                                    U+200C NEW RFC 2070 -->
+<!ENTITY zwj     CDATA "&#8205;" -- zero width joiner, U+200D NEW RFC 2070 -->
+<!ENTITY lrm     CDATA "&#8206;" -- left-to-right mark, U+200E NEW RFC 2070 -->
+<!ENTITY rlm     CDATA "&#8207;" -- right-to-left mark, U+200F NEW RFC 2070 -->
+<!ENTITY ndash   CDATA "&#8211;" -- en dash, U+2013 ISOpub -->
+<!ENTITY mdash   CDATA "&#8212;" -- em dash, U+2014 ISOpub -->
+<!ENTITY lsquo   CDATA "&#8216;" -- left single quotation mark,
+                                    U+2018 ISOnum -->
+<!ENTITY rsquo   CDATA "&#8217;" -- right single quotation mark,
+                                    U+2019 ISOnum -->
+<!ENTITY sbquo   CDATA "&#8218;" -- single low-9 quotation mark, U+201A NEW -->
+<!ENTITY ldquo   CDATA "&#8220;" -- left double quotation mark,
+                                    U+201C ISOnum -->
+<!ENTITY rdquo   CDATA "&#8221;" -- right double quotation mark,
+                                    U+201D ISOnum -->
+<!ENTITY bdquo   CDATA "&#8222;" -- double low-9 quotation mark, U+201E NEW -->
+<!ENTITY dagger  CDATA "&#8224;" -- dagger, U+2020 ISOpub -->
+<!ENTITY Dagger  CDATA "&#8225;" -- double dagger, U+2021 ISOpub -->
+<!ENTITY permil  CDATA "&#8240;" -- per mille sign, U+2030 ISOtech -->
+<!ENTITY lsaquo  CDATA "&#8249;" -- single left-pointing angle quotation mark,
+                                    U+2039 ISO proposed -->
+<!-- lsaquo is proposed but not yet ISO standardized -->
+<!ENTITY rsaquo  CDATA "&#8250;" -- single right-pointing angle quotation mark,
+                                    U+203A ISO proposed -->
+<!-- rsaquo is proposed but not yet ISO standardized -->
+<!ENTITY euro   CDATA "&#8364;"  -- euro sign, U+20AC NEW -->

File src/test/resources/examples/sgml/dtds/html4_0_1/HTMLsymbol.ent

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

File src/test/resources/examples/sgml/dtds/html4_0_1/frameset.dtd

+<!--
+    This is the HTML 4.01 Frameset DTD, which should be
+    used for documents with frames. This DTD is identical
+    to the HTML 4.01 Transitional DTD except for the
+    content model of the "HTML" element: in frameset 
+    documents, the "FRAMESET" element replaces the "BODY" 
+    element.
+
+          Draft: $Date: 1999/12/24 23:37:45 $
+
+          Authors:
+              Dave Raggett <dsr@w3.org>
+              Arnaud Le Hors <lehors@w3.org>
+              Ian Jacobs <ij@w3.org>
+
+    Further information about HTML 4.01 is available at:
+
+          http://www.w3.org/TR/1999/REC-html401-19991224.
+-->
+<!ENTITY % HTML.Version "-//W3C//DTD HTML 4.01 Frameset//EN"
+  -- Typical usage:
+
+    <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Frameset//EN"
+            "http://www.w3.org/TR/html4/frameset.dtd">
+    <html>
+    <head>
+    ...
+    </head>
+    <frameset>
+    ...
+    </frameset>
+    </html>
+-->
+
+<!ENTITY % HTML.Frameset "INCLUDE">
+<!ENTITY % HTML4.dtd PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+%HTML4.dtd;

File src/test/resources/examples/sgml/dtds/html4_0_1/loose.dtd

+<!--
+    This is the HTML 4.01 Transitional DTD, which includes
+    presentation attributes and elements that W3C expects to phase out
+    as support for style sheets matures. Authors should use the Strict
+    DTD when possible, but may use the Transitional DTD when support
+    for presentation attribute and elements is required.
+
+    HTML 4 includes mechanisms for style sheets, scripting,
+    embedding objects, improved support for right to left and mixed
+    direction text, and enhancements to forms for improved
+    accessibility for people with disabilities.
+
+          Draft: $Date: 1999/12/24 23:37:48 $
+
+          Authors:
+              Dave Raggett <dsr@w3.org>
+              Arnaud Le Hors <lehors@w3.org>
+              Ian Jacobs <ij@w3.org>
+
+    Further information about HTML 4.01 is available at:
+
+        http://www.w3.org/TR/1999/REC-html401-19991224
+
+
+    The HTML 4.01 specification includes additional
+    syntactic constraints that cannot be expressed within
+    the DTDs.
+
+-->
+<!ENTITY % HTML.Version "-//W3C//DTD HTML 4.01 Transitional//EN"
+  -- Typical usage:
+
+    <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+            "http://www.w3.org/TR/html4/loose.dtd">
+    <html>
+    <head>
+    ...
+    </head>
+    <body>
+    ...
+    </body>
+    </html>
+
+    The URI used as a system identifier with the public identifier allows
+    the user agent to download the DTD and entity sets as needed.
+
+    The FPI for the Strict HTML 4.01 DTD is:
+
+        "-//W3C//DTD HTML 4.01//EN"
+
+    This version of the strict DTD is:
+
+        http://www.w3.org/TR/1999/REC-html401-19991224/strict.dtd
+
+    Authors should use the Strict DTD unless they need the
+    presentation control for user agents that don't (adequately)
+    support style sheets.
+
+    If you are writing a document that includes frames, use 
+    the following FPI:
+
+        "-//W3C//DTD HTML 4.01 Frameset//EN"
+
+    This version of the frameset DTD is:
+
+        http://www.w3.org/TR/1999/REC-html401-19991224/frameset.dtd
+
+    Use the following (relative) URIs to refer to 
+    the DTDs and entity definitions of this specification:
+
+    "strict.dtd"
+    "loose.dtd"
+    "frameset.dtd"
+    "HTMLlat1.ent"
+    "HTMLsymbol.ent"
+    "HTMLspecial.ent"
+
+-->
+
+<!--================== Imported Names ====================================-->
+<!-- Feature Switch for frameset documents -->
+<!ENTITY % HTML.Frameset "IGNORE">
+
+<!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 "NAME"
+    -- a language code, as per [RFC1766]
+    -->
+
+<!ENTITY % Character "CDATA"
+    -- a single character from [ISO10646] 
+    -->
+
+<!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 [URI]
+    -->
+
+<!ENTITY % Datetime "CDATA" -- date and time information. ISO date format -->
+
+
+<!ENTITY % Script "CDATA" -- script expression -->
+
+<!ENTITY % StyleSheet "CDATA" -- style sheet data -->
+
+<!ENTITY % FrameTarget "CDATA" -- render in this frame -->
+
+
+<!ENTITY % Text "CDATA">
+
+
+<!-- Parameter Entities -->
+
+<!ENTITY % head.misc "SCRIPT|STYLE|META|LINK|OBJECT" -- repeatable head elements -->
+
+<!ENTITY % heading "H1|H2|H3|H4|H5|H6">
+
+<!ENTITY % list "UL | OL |  DIR | MENU">
+
+<!ENTITY % preformatted "PRE">
+
+<!ENTITY % Color "CDATA" -- a color using sRGB: #RRGGBB as Hex values -->
+
+<!-- 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
+ -->
+
+<!ENTITY % bodycolors "
+  bgcolor     %Color;        #IMPLIED  -- document background color --
+  text        %Color;        #IMPLIED  -- document text color --
+  link        %Color;        #IMPLIED  -- color of links --
+  vlink       %Color;        #IMPLIED  -- color of visited links --
+  alink       %Color;        #IMPLIED  -- color of selected links --
+  ">
+
+<!--================ Character mnemonic entities =========================-->
+
+<!ENTITY % HTMLlat1 PUBLIC
+   "-//W3C//ENTITIES Latin1//EN//HTML"
+   "HTMLlat1.ent">
+%HTMLlat1;
+
+<!ENTITY % HTMLsymbol PUBLIC
+   "-//W3C//ENTITIES Symbols//EN//HTML"
+   "HTMLsymbol.ent">
+%HTMLsymbol;
+
+<!ENTITY % HTMLspecial PUBLIC
+   "-//W3C//ENTITIES Special//EN//HTML"
+   "HTMLspecial.ent">
+%HTMLspecial;
+<!--=================== Generic Attributes ===============================-->
+
+<!ENTITY % coreattrs
+ "id          ID             #IMPLIED  -- document-wide unique id --
+  class       CDATA          #IMPLIED  -- space-separated list of classes --
+  style       %StyleSheet;   #IMPLIED  -- associated style info --
+  title       %Text;         #IMPLIED  -- advisory title --"
+  >
+
+<!ENTITY % i18n
+ "lang        %LanguageCode; #IMPLIED  -- language code --
+  dir         (ltr|rtl)      #IMPLIED  -- direction for weak/neutral text --"
+  >
+
+<!ENTITY % events
+ "onclick     %Script;       #IMPLIED  -- a pointer button was clicked --
+  ondblclick  %Script;       #IMPLIED  -- a pointer button was double clicked--
+  onmousedown %Script;       #IMPLIED  -- a pointer button was pressed down --
+  onmouseup   %Script;       #IMPLIED  -- a pointer button was released --
+  onmouseover %Script;       #IMPLIED  -- a pointer was moved onto --
+  onmousemove %Script;       #IMPLIED  -- a pointer was moved within --
+  onmouseout  %Script;       #IMPLIED  -- a pointer was moved away --
+  onkeypress  %Script;       #IMPLIED  -- a key was pressed and released --
+  onkeydown   %Script;       #IMPLIED  -- a key was pressed down --
+  onkeyup     %Script;       #IMPLIED  -- a key was released --"
+  >
+
+<!-- Reserved Feature Switch -->
+<!ENTITY % HTML.Reserved "IGNORE">
+
+<!-- The following attributes are reserved for possible future use -->
+<![ %HTML.Reserved; [
+<!ENTITY % reserved
+ "datasrc     %URI;          #IMPLIED  -- a single or tabular Data Source --
+  datafld     CDATA          #IMPLIED  -- the property or column name --
+  dataformatas (plaintext|html) plaintext -- text or html --"
+  >
+]]>
+
+<!ENTITY % reserved "">
+
+<!ENTITY % attrs "%coreattrs; %i18n; %events;">
+
+<!ENTITY % align "align (left|center|right|justify)  #IMPLIED"
+                   -- default is left for ltr paragraphs, right for rtl --
+  >
+
+<!--=================== Text Markup ======================================-->
+
+<!ENTITY % fontstyle
+ "TT | I | B | U | S | STRIKE | BIG | SMALL">
+
+<!ENTITY % phrase "EM | STRONG | DFN | CODE |
+                   SAMP | KBD | VAR | CITE | ABBR | ACRONYM" >
+
+<!ENTITY % special
+   "A | IMG | APPLET | OBJECT | FONT | BASEFONT | BR | SCRIPT |
+    MAP | Q | SUB | SUP | SPAN | BDO | IFRAME">
+
+<!ENTITY % formctrl "INPUT | SELECT | TEXTAREA | LABEL | BUTTON">
+
+<!-- %inline; covers inline or "text-level" elements -->
+<!ENTITY % inline "#PCDATA | %fontstyle; | %phrase; | %special; | %formctrl;">
+
+<!ELEMENT (%fontstyle;|%phrase;) - - (%inline;)*>
+<!ATTLIST (%fontstyle;|%phrase;)
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!ELEMENT (SUB|SUP) - - (%inline;)*    -- subscript, superscript -->
+<!ATTLIST (SUB|SUP)
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!ELEMENT SPAN - - (%inline;)*         -- generic language/style container -->
+<!ATTLIST SPAN
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  %reserved;			       -- reserved for possible future use --
+  >
+
+<!ELEMENT BDO - - (%inline;)*          -- I18N BiDi over-ride -->
+<!ATTLIST BDO
+  %coreattrs;                          -- id, class, style, title --
+  lang        %LanguageCode; #IMPLIED  -- language code --
+  dir         (ltr|rtl)      #REQUIRED -- directionality --
+  >
+
+<!ELEMENT BASEFONT - O EMPTY           -- base font size -->
+<!ATTLIST BASEFONT
+  id          ID             #IMPLIED  -- document-wide unique id --
+  size        CDATA          #REQUIRED -- base font size for FONT elements --
+  color       %Color;        #IMPLIED  -- text color --
+  face        CDATA          #IMPLIED  -- comma-separated list of font names --
+  >
+
+<!ELEMENT FONT - - (%inline;)*         -- local change to font -->
+<!ATTLIST FONT
+  %coreattrs;                          -- id, class, style, title --
+  %i18n;		               -- lang, dir --
+  size        CDATA          #IMPLIED  -- [+|-]nn e.g. size="+1", size="4" --
+  color       %Color;        #IMPLIED  -- text color --
+  face        CDATA          #IMPLIED  -- comma-separated list of font names --
+  >
+
+<!ELEMENT BR - O EMPTY                 -- forced line break -->
+<!ATTLIST BR
+  %coreattrs;                          -- id, class, style, title --
+  clear       (left|all|right|none) none -- control of text flow --
+  >
+
+<!--================== HTML content models ===============================-->
+
+<!--
+    HTML has two basic content models:
+
+        %inline;     character level elements and text strings
+        %block;      block-like elements e.g. paragraphs and lists
+-->
+
+<!ENTITY % block
+     "P | %heading; | %list; | %preformatted; | DL | DIV | CENTER |
+      NOSCRIPT | NOFRAMES | BLOCKQUOTE | FORM | ISINDEX | HR |
+      TABLE | FIELDSET | ADDRESS">
+
+<!ENTITY % flow "%block; | %inline;">
+
+<!--=================== Document Body ====================================-->
+
+<!ELEMENT BODY O O (%flow;)* +(INS|DEL) -- document body -->
+<!ATTLIST BODY
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  onload          %Script;   #IMPLIED  -- the document has been loaded --
+  onunload        %Script;   #IMPLIED  -- the document has been removed --
+  background      %URI;      #IMPLIED  -- texture tile for document
+                                          background --
+  %bodycolors;                         -- bgcolor, text, link, vlink, alink --
+  >
+
+<!ELEMENT ADDRESS - - ((%inline;)|P)*  -- information on author -->
+<!ATTLIST ADDRESS
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!ELEMENT DIV - - (%flow;)*            -- generic language/style container -->
+<!ATTLIST DIV
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  %align;                              -- align, text alignment --
+  %reserved;                           -- reserved for possible future use --
+  >
+
+<!ELEMENT CENTER - - (%flow;)*         -- shorthand for DIV align=center -->
+<!ATTLIST CENTER
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!--================== The Anchor Element ================================-->
+
+<!ENTITY % Shape "(rect|circle|poly|default)">
+<!ENTITY % Coords "CDATA" -- comma-separated list of lengths -->
+
+<!ELEMENT A - - (%inline;)* -(A)       -- anchor -->
+<!ATTLIST A
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  charset     %Charset;      #IMPLIED  -- char encoding of linked resource --
+  type        %ContentType;  #IMPLIED  -- advisory content type --
+  name        CDATA          #IMPLIED  -- named link end --
+  href        %URI;          #IMPLIED  -- URI for linked resource --
+  hreflang    %LanguageCode; #IMPLIED  -- language code --
+  target      %FrameTarget;  #IMPLIED  -- render in this frame --
+  rel         %LinkTypes;    #IMPLIED  -- forward link types --
+  rev         %LinkTypes;    #IMPLIED  -- reverse link types --
+  accesskey   %Character;    #IMPLIED  -- accessibility key character --
+  shape       %Shape;        rect      -- for use with client-side image maps --
+  coords      %Coords;       #IMPLIED  -- for use with client-side image maps --
+  tabindex    NUMBER         #IMPLIED  -- position in tabbing order --
+  onfocus     %Script;       #IMPLIED  -- the element got the focus --
+  onblur      %Script;       #IMPLIED  -- the element lost the focus --
+  >
+
+<!--================== 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;) | AREA)+ -- client-side image map -->
+<!ATTLIST MAP
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  name        CDATA          #REQUIRED -- for reference by usemap --
+  >
+
+<!ELEMENT AREA - O EMPTY               -- client-side image map area -->
+<!ATTLIST AREA
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  shape       %Shape;        rect      -- controls interpretation of coords --
+  coords      %Coords;       #IMPLIED  -- comma-separated list of lengths --
+  href        %URI;          #IMPLIED  -- URI for linked resource --
+  target      %FrameTarget;  #IMPLIED  -- render in this frame --
+  nohref      (nohref)       #IMPLIED  -- this region has no action --
+  alt         %Text;         #REQUIRED -- short description --
+  tabindex    NUMBER         #IMPLIED  -- position in tabbing order --
+  accesskey   %Character;    #IMPLIED  -- accessibility key character --
+  onfocus     %Script;       #IMPLIED  -- the element got the focus --
+  onblur      %Script;       #IMPLIED  -- the element lost the focus --
+  >
+
+<!--================== The LINK Element ==================================-->
+
+<!--
+  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 - O EMPTY               -- a media-independent link -->
+<!ATTLIST LINK
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  charset     %Charset;      #IMPLIED  -- char encoding of linked resource --
+  href        %URI;          #IMPLIED  -- URI for linked resource --
+  hreflang    %LanguageCode; #IMPLIED  -- language code --
+  type        %ContentType;  #IMPLIED  -- advisory content type --
+  rel         %LinkTypes;    #IMPLIED  -- forward link types --
+  rev         %LinkTypes;    #IMPLIED  -- reverse link types --
+  media       %MediaDesc;    #IMPLIED  -- for rendering on these media --
+  target      %FrameTarget;  #IMPLIED  -- render in this frame --
+  >
+
+<!--=================== Images ===========================================-->
+
+<!-- Length defined in strict DTD for cellpadding/cellspacing -->
+<!ENTITY % Length "CDATA" -- nn for pixels or nn% for percentage length -->
+<!ENTITY % MultiLength "CDATA" -- pixel, percentage, or relative -->
+
+<![ %HTML.Frameset; [
+<!ENTITY % MultiLengths "CDATA" -- comma-separated list of MultiLength -->
+]]>
+
+<!ENTITY % Pixels "CDATA" -- integer representing length in pixels -->
+
+<!ENTITY % IAlign "(top|middle|bottom|left|right)" -- center? -->
+
+<!-- To avoid problems with text-only UAs as well as 
+   to make image content understandable and navigable 
+   to users of non-visual UAs, you need to provide
+   a description with ALT, and avoid server-side image maps -->
+<!ELEMENT IMG - O EMPTY                -- Embedded image -->
+<!ATTLIST IMG
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  src         %URI;          #REQUIRED -- URI of image to embed --
+  alt         %Text;         #REQUIRED -- short description --
+  longdesc    %URI;          #IMPLIED  -- link to long description
+                                          (complements alt) --
+  name        CDATA          #IMPLIED  -- name of image for scripting --
+  height      %Length;       #IMPLIED  -- override height --
+  width       %Length;       #IMPLIED  -- override width --
+  usemap      %URI;          #IMPLIED  -- use client-side image map --
+  ismap       (ismap)        #IMPLIED  -- use server-side image map --
+  align       %IAlign;       #IMPLIED  -- vertical or horizontal alignment --
+  border      %Pixels;       #IMPLIED  -- link border width --
+  hspace      %Pixels;       #IMPLIED  -- horizontal gutter --
+  vspace      %Pixels;       #IMPLIED  -- vertical gutter --
+  >
+
+<!-- USEMAP points to a MAP element which may be in this document
+  or an external document, although the latter is not widely supported -->
+
+<!--==================== OBJECT ======================================-->
+<!--
+  OBJECT is used to embed objects as part of HTML pages 
+  PARAM elements should precede other content. SGML mixed content
+  model technicality precludes specifying this formally ...
+-->
+
+<!ELEMENT OBJECT - - (PARAM | %flow;)*
+ -- generic embedded object -->
+<!ATTLIST OBJECT
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  declare     (declare)      #IMPLIED  -- declare but don't instantiate flag --
+  classid     %URI;          #IMPLIED  -- identifies an implementation --
+  codebase    %URI;          #IMPLIED  -- base URI for classid, data, archive--
+  data        %URI;          #IMPLIED  -- reference to object's data --
+  type        %ContentType;  #IMPLIED  -- content type for data --
+  codetype    %ContentType;  #IMPLIED  -- content type for code --
+  archive     CDATA          #IMPLIED  -- space-separated list of URIs --
+  standby     %Text;         #IMPLIED  -- message to show while loading --
+  height      %Length;       #IMPLIED  -- override height --
+  width       %Length;       #IMPLIED  -- override width --
+  usemap      %URI;          #IMPLIED  -- use client-side image map --
+  name        CDATA          #IMPLIED  -- submit as part of form --
+  tabindex    NUMBER         #IMPLIED  -- position in tabbing order --
+  align       %IAlign;       #IMPLIED  -- vertical or horizontal alignment --
+  border      %Pixels;       #IMPLIED  -- link border width --
+  hspace      %Pixels;       #IMPLIED  -- horizontal gutter --
+  vspace      %Pixels;       #IMPLIED  -- vertical gutter --
+  %reserved;                           -- reserved for possible future use --
+  >
+
+<!ELEMENT PARAM - O EMPTY              -- named property value -->
+<!ATTLIST PARAM
+  id          ID             #IMPLIED  -- document-wide unique id --
+  name        CDATA          #REQUIRED -- property name --
+  value       CDATA          #IMPLIED  -- property value --
+  valuetype   (DATA|REF|OBJECT) DATA   -- How to interpret value --
+  type        %ContentType;  #IMPLIED  -- content type for value
+                                          when valuetype=ref --
+  >
+
+<!--=================== Java APPLET ==================================-->
+<!--
+  One of code or object attributes must be present.
+  Place PARAM elements before other content.
+-->
+<!ELEMENT APPLET - - (PARAM | %flow;)* -- Java applet -->
+<!ATTLIST APPLET
+  %coreattrs;                          -- id, class, style, title --
+  codebase    %URI;          #IMPLIED  -- optional base URI for applet --
+  archive     CDATA          #IMPLIED  -- comma-separated archive list --
+  code        CDATA          #IMPLIED  -- applet class file --
+  object      CDATA          #IMPLIED  -- serialized applet file --
+  alt         %Text;         #IMPLIED  -- short description --
+  name        CDATA          #IMPLIED  -- allows applets to find each other --
+  width       %Length;       #REQUIRED -- initial width --
+  height      %Length;       #REQUIRED -- initial height --
+  align       %IAlign;       #IMPLIED  -- vertical or horizontal alignment --
+  hspace      %Pixels;       #IMPLIED  -- horizontal gutter --
+  vspace      %Pixels;       #IMPLIED  -- vertical gutter --
+  >
+
+<!--=================== Horizontal Rule ==================================-->
+
+<!ELEMENT HR - O EMPTY -- horizontal rule -->
+<!ATTLIST HR
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  align       (left|center|right) #IMPLIED
+  noshade     (noshade)      #IMPLIED
+  size        %Pixels;       #IMPLIED
+  width       %Length;       #IMPLIED
+  >
+
+<!--=================== Paragraphs =======================================-->
+
+<!ELEMENT P - O (%inline;)*            -- paragraph -->
+<!ATTLIST P
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  %align;                              -- align, text alignment --
+  >
+
+<!--=================== Headings =========================================-->
+
+<!--
+  There are six levels of headings from H1 (the most important)
+  to H6 (the least important).
+-->
+
+<!ELEMENT (%heading;)  - - (%inline;)* -- heading -->
+<!ATTLIST (%heading;)
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  %align;                              -- align, text alignment --
+  >
+
+<!--=================== Preformatted Text ================================-->
+
+<!-- excludes markup for images and changes in font size -->
+<!ENTITY % pre.exclusion "IMG|OBJECT|APPLET|BIG|SMALL|SUB|SUP|FONT|BASEFONT">
+
+<!ELEMENT PRE - - (%inline;)* -(%pre.exclusion;) -- preformatted text -->
+<!ATTLIST PRE
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  width       NUMBER         #IMPLIED
+  >
+
+<!--===================== Inline Quotes ==================================-->
+
+<!ELEMENT Q - - (%inline;)*            -- short inline quotation -->
+<!ATTLIST Q
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  cite        %URI;          #IMPLIED  -- URI for source document or msg --
+  >
+
+<!--=================== Block-like Quotes ================================-->
+
+<!ELEMENT BLOCKQUOTE - - (%flow;)*     -- long quotation -->
+<!ATTLIST BLOCKQUOTE
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  cite        %URI;          #IMPLIED  -- URI for source document or msg --
+  >
+
+<!--=================== Inserted/Deleted Text ============================-->
+
+
+<!-- INS/DEL are handled by inclusion on BODY -->
+<!ELEMENT (INS|DEL) - - (%flow;)*      -- inserted text, deleted text -->
+<!ATTLIST (INS|DEL)
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  cite        %URI;          #IMPLIED  -- info on reason for change --
+  datetime    %Datetime;     #IMPLIED  -- date and time of change --
+  >
+
+<!--=================== Lists ============================================-->
+
+<!-- definition lists - DT for term, DD for its definition -->
+
+<!ELEMENT DL - - (DT|DD)+              -- definition list -->
+<!ATTLIST DL
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  compact     (compact)      #IMPLIED  -- reduced interitem spacing --
+  >
+
+<!ELEMENT DT - O (%inline;)*           -- definition term -->
+<!ELEMENT DD - O (%flow;)*             -- definition description -->
+<!ATTLIST (DT|DD)
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!-- Ordered lists (OL) Numbering style
+
+    1   arablic 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.
+
+    This can't be expressed directly in SGML due to case folding.
+-->
+
+<!ENTITY % OLStyle "CDATA"      -- constrained to: "(1|a|A|i|I)" -->
+
+<!ELEMENT OL - - (LI)+                 -- ordered list -->
+<!ATTLIST OL
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  type        %OLStyle;      #IMPLIED  -- numbering style --
+  compact     (compact)      #IMPLIED  -- reduced interitem spacing --
+  start       NUMBER         #IMPLIED  -- starting sequence number --
+  >
+
+<!-- Unordered Lists (UL) bullet styles -->
+<!ENTITY % ULStyle "(disc|square|circle)">
+
+<!ELEMENT UL - - (LI)+                 -- unordered list -->
+<!ATTLIST UL
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  type        %ULStyle;      #IMPLIED  -- bullet style --
+  compact     (compact)      #IMPLIED  -- reduced interitem spacing --
+  >
+
+<!ELEMENT (DIR|MENU) - - (LI)+ -(%block;) -- directory list, menu list -->
+<!ATTLIST DIR
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  compact     (compact)      #IMPLIED -- reduced interitem spacing --
+  >
+<!ATTLIST MENU
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  compact     (compact)      #IMPLIED -- reduced interitem spacing --
+  >
+
+<!ENTITY % LIStyle "CDATA" -- constrained to: "(%ULStyle;|%OLStyle;)" -->
+
+<!ELEMENT LI - O (%flow;)*             -- list item -->
+<!ATTLIST LI
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  type        %LIStyle;      #IMPLIED  -- list item style --
+  value       NUMBER         #IMPLIED  -- reset sequence number --
+  >
+
+<!--================ Forms ===============================================-->
+<!ELEMENT FORM - - (%flow;)* -(FORM)   -- interactive form -->
+<!ATTLIST FORM
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  action      %URI;          #REQUIRED -- server-side form handler --
+  method      (GET|POST)     GET       -- HTTP method used to submit the form--
+  enctype     %ContentType;  "application/x-www-form-urlencoded"
+  accept      %ContentTypes; #IMPLIED  -- list of MIME types for file upload --
+  name        CDATA          #IMPLIED  -- name of form for scripting --
+  onsubmit    %Script;       #IMPLIED  -- the form was submitted --
+  onreset     %Script;       #IMPLIED  -- the form was reset --
+  target      %FrameTarget;  #IMPLIED  -- render in this frame --
+  accept-charset %Charsets;  #IMPLIED  -- list of supported charsets --
+  >
+
+<!-- Each label must not contain more than ONE field -->
+<!ELEMENT LABEL - - (%inline;)* -(LABEL) -- form field label text -->
+<!ATTLIST LABEL
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  for         IDREF          #IMPLIED  -- matches field ID value --
+  accesskey   %Character;    #IMPLIED  -- accessibility key character --
+  onfocus     %Script;       #IMPLIED  -- the element got the focus --
+  onblur      %Script;       #IMPLIED  -- the element lost the focus --
+  >
+
+<!ENTITY % InputType
+  "(TEXT | PASSWORD | CHECKBOX |
+    RADIO | SUBMIT | RESET |
+    FILE | HIDDEN | IMAGE | BUTTON)"
+   >
+
+<!-- attribute name required for all but submit and reset -->
+<!ELEMENT INPUT - O EMPTY              -- form control -->
+<!ATTLIST INPUT
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  type        %InputType;    TEXT      -- what kind of widget is needed --
+  name        CDATA          #IMPLIED  -- submit as part of form --
+  value       CDATA          #IMPLIED  -- Specify for radio buttons and checkboxes --
+  checked     (checked)      #IMPLIED  -- for radio buttons and check boxes --
+  disabled    (disabled)     #IMPLIED  -- unavailable in this context --
+  readonly    (readonly)     #IMPLIED  -- for text and passwd --
+  size        CDATA          #IMPLIED  -- specific to each type of field --
+  maxlength   NUMBER         #IMPLIED  -- max chars for text fields --
+  src         %URI;          #IMPLIED  -- for fields with images --
+  alt         CDATA          #IMPLIED  -- short description --
+  usemap      %URI;          #IMPLIED  -- use client-side image map --
+  ismap       (ismap)        #IMPLIED  -- use server-side image map --
+  tabindex    NUMBER         #IMPLIED  -- position in tabbing order --
+  accesskey   %Character;    #IMPLIED  -- accessibility key character --
+  onfocus     %Script;       #IMPLIED  -- the element got the focus --
+  onblur      %Script;       #IMPLIED  -- the element lost the focus --
+  onselect    %Script;       #IMPLIED  -- some text was selected --
+  onchange    %Script;       #IMPLIED  -- the element value was changed --
+  accept      %ContentTypes; #IMPLIED  -- list of MIME types for file upload --
+  align       %IAlign;       #IMPLIED  -- vertical or horizontal alignment --
+  %reserved;                           -- reserved for possible future use --
+  >
+
+<!ELEMENT SELECT - - (OPTGROUP|OPTION)+ -- option selector -->
+<!ATTLIST SELECT
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  name        CDATA          #IMPLIED  -- field name --
+  size        NUMBER         #IMPLIED  -- rows visible --
+  multiple    (multiple)     #IMPLIED  -- default is single selection --
+  disabled    (disabled)     #IMPLIED  -- unavailable in this context --
+  tabindex    NUMBER         #IMPLIED  -- position in tabbing order --
+  onfocus     %Script;       #IMPLIED  -- the element got the focus --
+  onblur      %Script;       #IMPLIED  -- the element lost the focus --
+  onchange    %Script;       #IMPLIED  -- the element value was changed --
+  %reserved;                           -- reserved for possible future use --
+  >
+
+<!ELEMENT OPTGROUP - - (OPTION)+ -- option group -->
+<!ATTLIST OPTGROUP
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  disabled    (disabled)     #IMPLIED  -- unavailable in this context --
+  label       %Text;         #REQUIRED -- for use in hierarchical menus --
+  >
+
+<!ELEMENT OPTION - O (#PCDATA)         -- selectable choice -->
+<!ATTLIST OPTION
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  selected    (selected)     #IMPLIED
+  disabled    (disabled)     #IMPLIED  -- unavailable in this context --
+  label       %Text;         #IMPLIED  -- for use in hierarchical menus --
+  value       CDATA          #IMPLIED  -- defaults to element content --
+  >
+
+<!ELEMENT TEXTAREA - - (#PCDATA)       -- multi-line text field -->
+<!ATTLIST TEXTAREA
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  name        CDATA          #IMPLIED
+  rows        NUMBER         #REQUIRED
+  cols        NUMBER         #REQUIRED
+  disabled    (disabled)     #IMPLIED  -- unavailable in this context --
+  readonly    (readonly)     #IMPLIED
+  tabindex    NUMBER         #IMPLIED  -- position in tabbing order --
+  accesskey   %Character;    #IMPLIED  -- accessibility key character --
+  onfocus     %Script;       #IMPLIED  -- the element got the focus --
+  onblur      %Script;       #IMPLIED  -- the element lost the focus --
+  onselect    %Script;       #IMPLIED  -- some text was selected --
+  onchange    %Script;       #IMPLIED  -- the element value was changed --
+  %reserved;                           -- reserved for possible future use --
+  >
+
+<!--
+  #PCDATA is to solve the mixed content problem,
+  per specification only whitespace is allowed there!
+ -->
+<!ELEMENT FIELDSET - - (#PCDATA,LEGEND,(%flow;)*) -- form control group -->
+<!ATTLIST FIELDSET
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!ELEMENT LEGEND - - (%inline;)*       -- fieldset legend -->
+<!ENTITY % LAlign "(top|bottom|left|right)">
+
+<!ATTLIST LEGEND
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  accesskey   %Character;    #IMPLIED  -- accessibility key character --
+  align       %LAlign;       #IMPLIED  -- relative to fieldset --
+  >
+
+<!ELEMENT BUTTON - -
+     (%flow;)* -(A|%formctrl;|FORM|ISINDEX|FIELDSET|IFRAME)
+     -- push button -->
+<!ATTLIST BUTTON
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  name        CDATA          #IMPLIED
+  value       CDATA          #IMPLIED  -- sent to server when submitted --
+  type        (button|submit|reset) submit -- for use as form button --
+  disabled    (disabled)     #IMPLIED  -- unavailable in this context --
+  tabindex    NUMBER         #IMPLIED  -- position in tabbing order --
+  accesskey   %Character;    #IMPLIED  -- accessibility key character --
+  onfocus     %Script;       #IMPLIED  -- the element got the focus --
+  onblur      %Script;       #IMPLIED  -- the element lost the focus --
+  %reserved;                           -- reserved for possible future use --
+  >
+
+<!--======================= Tables =======================================-->
+
+<!-- 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.
+
+ The value "border" is included for backwards compatibility with
+ <TABLE BORDER> which yields frame=border and border=implied
+ For <TABLE BORDER=1> you get border=1 and frame=implied. In this
+ case, it is appropriate to treat this as frame=border for backwards
+ compatibility with deployed browsers.
+-->
+<!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 -->
+<!ENTITY % cellhalign
+  "align      (left|center|right|justify|char) #IMPLIED
+   char       %Character;    #IMPLIED  -- alignment char, e.g. char=':' --
+   charoff    %Length;       #IMPLIED  -- offset for alignment char --"
+  >
+
+<!-- vertical alignment attributes for cell contents -->
+<!ENTITY % cellvalign
+  "valign     (top|middle|bottom|baseline) #IMPLIED"
+  >
+
+<!ELEMENT TABLE - -
+     (CAPTION?, (COL*|COLGROUP*), THEAD?, TFOOT?, TBODY+)>
+<!ELEMENT CAPTION  - - (%inline;)*     -- table caption -->
+<!ELEMENT THEAD    - O (TR)+           -- table header -->
+<!ELEMENT TFOOT    - O (TR)+           -- table footer -->
+<!ELEMENT TBODY    O O (TR)+           -- table body -->
+<!ELEMENT COLGROUP - O (COL)*          -- table column group -->
+<!ELEMENT COL      - O EMPTY           -- table column -->
+<!ELEMENT TR       - O (TH|TD)+        -- table row -->
+<!ELEMENT (TH|TD)  - O (%flow;)*       -- table header cell, table data cell-->
+
+<!ATTLIST TABLE                        -- table element --
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  summary     %Text;         #IMPLIED  -- purpose/structure for speech output--
+  width       %Length;       #IMPLIED  -- table width --
+  border      %Pixels;       #IMPLIED  -- controls frame width around table --
+  frame       %TFrame;       #IMPLIED  -- which parts of frame to render --
+  rules       %TRules;       #IMPLIED  -- rulings between rows and cols --
+  cellspacing %Length;       #IMPLIED  -- spacing between cells --
+  cellpadding %Length;       #IMPLIED  -- spacing within cells --
+  align       %TAlign;       #IMPLIED  -- table position relative to window --
+  bgcolor     %Color;        #IMPLIED  -- background color for cells --
+  %reserved;                           -- reserved for possible future use --
+  datapagesize CDATA         #IMPLIED  -- reserved for possible future use --
+  >
+
+<!ENTITY % CAlign "(top|bottom|left|right)">
+
+<!ATTLIST CAPTION
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  align       %CAlign;       #IMPLIED  -- relative to table --
+  >
+
+<!--
+COLGROUP groups a set of COL elements. It allows you to group
+several semantically related columns together.
+-->
+<!ATTLIST COLGROUP
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  span        NUMBER         1         -- default number of columns in group --
+  width       %MultiLength;  #IMPLIED  -- default width for enclosed COLs --
+  %cellhalign;                         -- horizontal alignment in cells --
+  %cellvalign;                         -- vertical alignment in cells --
+  >
+
+<!--
+ 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                          -- column groups and properties --
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  span        NUMBER         1         -- COL attributes affect N columns --
+  width       %MultiLength;  #IMPLIED  -- column width specification --
+  %cellhalign;                         -- horizontal alignment in cells --
+  %cellvalign;                         -- vertical alignment in cells --
+  >
+
+<!--
+    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|TBODY|TFOOT)          -- table section --
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  %cellhalign;                         -- horizontal alignment in cells --
+  %cellvalign;                         -- vertical alignment in cells --
+  >
+
+<!ATTLIST TR                           -- table row --
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  %cellhalign;                         -- horizontal alignment in cells --
+  %cellvalign;                         -- vertical alignment in cells --
+  bgcolor     %Color;        #IMPLIED  -- background color for row --
+  >
+
+
+<!-- Scope is simpler than headers attribute for common tables -->
+<!ENTITY % Scope "(row|col|rowgroup|colgroup)">
+
+<!-- TH is for headers, TD for data, but for cells acting as both use TD -->
+<!ATTLIST (TH|TD)                      -- header or data cell --
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  abbr        %Text;         #IMPLIED  -- abbreviation for header cell --
+  axis        CDATA          #IMPLIED  -- comma-separated list of related headers--
+  headers     IDREFS         #IMPLIED  -- list of id's for header cells --
+  scope       %Scope;        #IMPLIED  -- scope covered by header cells --
+  rowspan     NUMBER         1         -- number of rows spanned by cell --
+  colspan     NUMBER         1         -- number of cols spanned by cell --
+  %cellhalign;                         -- horizontal alignment in cells --
+  %cellvalign;                         -- vertical alignment in cells --
+  nowrap      (nowrap)       #IMPLIED  -- suppress word wrap --
+  bgcolor     %Color;        #IMPLIED  -- cell background color --
+  width       %Length;       #IMPLIED  -- width for cell --
+  height      %Length;       #IMPLIED  -- height for cell --
+  >
+
+<!--================== Document Frames ===================================-->
+
+<!--
+  The content model for HTML documents depends on whether the HEAD is
+  followed by a FRAMESET or BODY element. The widespread omission of
+  the BODY start tag makes it impractical to define the content model
+  without the use of a marked section.
+-->
+
+<![ %HTML.Frameset; [
+<!ELEMENT FRAMESET - - ((FRAMESET|FRAME)+ & NOFRAMES?) -- window subdivision-->
+<!ATTLIST FRAMESET
+  %coreattrs;                          -- id, class, style, title --
+  rows        %MultiLengths; #IMPLIED  -- list of lengths,
+                                          default: 100% (1 row) --
+  cols        %MultiLengths; #IMPLIED  -- list of lengths,
+                                          default: 100% (1 col) --
+  onload      %Script;       #IMPLIED  -- all the frames have been loaded  -- 
+  onunload    %Script;       #IMPLIED  -- all the frames have been removed -- 
+  >
+]]>
+
+<![ %HTML.Frameset; [
+<!-- reserved frame names start with "_" otherwise starts with letter -->
+<!ELEMENT FRAME - O EMPTY              -- subwindow -->
+<!ATTLIST FRAME
+  %coreattrs;                          -- id, class, style, title --
+  longdesc    %URI;          #IMPLIED  -- link to long description
+                                          (complements title) --
+  name        CDATA          #IMPLIED  -- name of frame for targetting --
+  src         %URI;          #IMPLIED  -- source of frame content --
+  frameborder (1|0)          1         -- request frame borders? --
+  marginwidth %Pixels;       #IMPLIED  -- margin widths in pixels --
+  marginheight %Pixels;      #IMPLIED  -- margin height in pixels --
+  noresize    (noresize)     #IMPLIED  -- allow users to resize frames? --
+  scrolling   (yes|no|auto)  auto      -- scrollbar or none --
+  >
+]]>
+
+<!ELEMENT IFRAME - - (%flow;)*         -- inline subwindow -->
+<!ATTLIST IFRAME
+  %coreattrs;                          -- id, class, style, title --
+  longdesc    %URI;          #IMPLIED  -- link to long description
+                                          (complements title) --
+  name        CDATA          #IMPLIED  -- name of frame for targetting --
+  src         %URI;          #IMPLIED  -- source of frame content --
+  frameborder (1|0)          1         -- request frame borders? --
+  marginwidth %Pixels;       #IMPLIED  -- margin widths in pixels --
+  marginheight %Pixels;      #IMPLIED  -- margin height in pixels --
+  scrolling   (yes|no|auto)  auto      -- scrollbar or none --
+  align       %IAlign;       #IMPLIED  -- vertical or horizontal alignment --
+  height      %Length;       #IMPLIED  -- frame height --
+  width       %Length;       #IMPLIED  -- frame width --
+  >
+
+<![ %HTML.Frameset; [
+<!ENTITY % noframes.content "(BODY) -(NOFRAMES)">
+]]>
+
+<!ENTITY % noframes.content "(%flow;)*">
+
+<!ELEMENT NOFRAMES - - %noframes.content;
+ -- alternate content container for non frame-based rendering -->
+<!ATTLIST NOFRAMES
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!--================ Document Head =======================================-->
+<!-- %head.misc; defined earlier on as "SCRIPT|STYLE|META|LINK|OBJECT" -->
+<!ENTITY % head.content "TITLE & ISINDEX? & BASE?">
+
+<!ELEMENT HEAD O O (%head.content;) +(%head.misc;) -- document head -->
+<!ATTLIST HEAD
+  %i18n;                               -- lang, dir --
+  profile     %URI;          #IMPLIED  -- named dictionary of meta info --
+  >
+
+<!-- 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) -(%head.misc;) -- document title -->
+<!ATTLIST TITLE %i18n>
+
+<!ELEMENT ISINDEX - O EMPTY            -- single line prompt -->
+<!ATTLIST ISINDEX
+  %coreattrs;                          -- id, class, style, title --
+  %i18n;                               -- lang, dir --
+  prompt      %Text;         #IMPLIED  -- prompt message -->
+
+<!ELEMENT BASE - O EMPTY               -- document base URI -->
+<!ATTLIST BASE
+  href        %URI;          #IMPLIED  -- URI that acts as base URI --
+  target      %FrameTarget;  #IMPLIED  -- render in this frame --
+  >
+
+<!ELEMENT META - O EMPTY               -- generic metainformation -->
+<!ATTLIST META
+  %i18n;                               -- lang, dir, for use with content --
+  http-equiv  NAME           #IMPLIED  -- HTTP response header name  --
+  name        NAME           #IMPLIED  -- metainformation name --
+  content     CDATA          #REQUIRED -- associated information --
+  scheme      CDATA          #IMPLIED  -- select form of content --
+  >
+
+<!ELEMENT STYLE - - %StyleSheet        -- style info -->
+<!ATTLIST STYLE
+  %i18n;                               -- lang, dir, for use with title --
+  type        %ContentType;  #REQUIRED -- content type of style language --
+  media       %MediaDesc;    #IMPLIED  -- designed for use with these media --
+  title       %Text;         #IMPLIED  -- advisory title --
+  >
+
+<!ELEMENT SCRIPT - - %Script;          -- script statements -->
+<!ATTLIST SCRIPT
+  charset     %Charset;      #IMPLIED  -- char encoding of linked resource --
+  type        %ContentType;  #REQUIRED -- content type of script language --
+  language    CDATA          #IMPLIED  -- predefined script language name --
+  src         %URI;          #IMPLIED  -- URI for an external script --
+  defer       (defer)        #IMPLIED  -- UA may defer execution of script --
+  event       CDATA          #IMPLIED  -- reserved for possible future use --
+  for         %URI;          #IMPLIED  -- reserved for possible future use --
+  >
+
+<!ELEMENT NOSCRIPT - - (%flow;)*
+  -- alternate content container for non script-based rendering -->
+<!ATTLIST NOSCRIPT
+  %attrs;                              -- %coreattrs, %i18n, %events --
+  >
+
+<!--================ Document Structure ==================================-->
+<!ENTITY % version "version CDATA #FIXED '%HTML.Version;'">
+
+<![ %HTML.Frameset; [
+<!ENTITY % html.content "HEAD, FRAMESET">
+]]>
+
+<!ENTITY % html.content "HEAD, BODY">
+
+<!ELEMENT HTML O O (%html.content;)    -- document root element -->
+<!ATTLIST HTML
+  %i18n;                               -- lang, dir --
+  %version;
+  >

File src/test/resources/examples/sgml/dtds/html4_0_1/strict.dtd

+<!--
+    This is HTML 4.01 Strict DTD, which excludes the presentation 
+    attributes and elements that W3C expects to phase out as 
+    support for style sheets matures. Authors should use the Strict
+    DTD when possible, but may use the Transitional DTD when support
+    for presentation attribute and elements is required.
+    
+    HTML 4 includes mechanisms for style sheets, scripting,
+    embedding objects, improved support for right to left and mixed
+    direction text, and enhancements to forms for improved
+    accessibility for people with disabilities.
+
+          Draft: $Date: 1999/12/24 23:37:48 $
+
+          Authors:
+              Dave Raggett <dsr@w3.org>
+              Arnaud Le Hors <lehors@w3.org>
+              Ian Jacobs <ij@w3.org>
+
+    Further information about HTML 4.01 is available at:
+
+        http://www.w3.org/TR/1999/REC-html401-19991224
+
+
+    The HTML 4.01 specification includes additional
+    syntactic constraints that cannot be expressed within
+    the DTDs.
+
+-->
+<!--
+    Typical usage:
+
+    <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
+            "http://www.w3.org/TR/html4/strict.dtd">
+    <html>
+    <head>
+    ...
+    </head>
+    <body>
+    ...
+    </body>
+    </html>
+
+    The URI used as a system identifier with the public identifier allows
+    the user agent to download the DTD and entity sets as needed.
+
+    The FPI for the Transitional HTML 4.01 DTD is:
+
+        "-//W3C//DTD HTML 4.01 Transitional//EN"
+
+    This version of the transitional DTD is:
+
+        http://www.w3.org/TR/1999/REC-html401-19991224/loose.dtd
+
+    If you are writing a document that includes frames, use 
+    the following FPI:
+
+        "-//W3C//DTD HTML 4.01 Frameset//EN"
+
+    This version of the frameset DTD is:
+
+        http://www.w3.org/TR/1999/REC-html401-19991224/frameset.dtd
+
+    Use the following (relative) URIs to refer to 
+    the DTDs and entity definitions of this specification:
+
+    "strict.dtd"
+    "loose.dtd"
+    "frameset.dtd"
+    "HTMLlat1.ent"
+    "HTMLsymbol.ent"
+    "HTMLspecial.ent"
+
+-->
+
+<!--================== Imported Names ====================================-->
+<!-- Feature Switch for frameset documents -->
+<!ENTITY % HTML.Frameset "IGNORE">
+
+<!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 "NAME"
+    -- a language code, as per [RFC1766]
+    -->
+
+<!ENTITY % Character "CDATA"
+    -- a single character from [ISO10646] 
+    -->
+
+<!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 [URI]
+    -->
+
+<!ENTITY % Datetime "CDATA" -- date and time information. ISO date format -->
+
+
+<!ENTITY % Script "CDATA" -- script expression -->
+
+<!ENTITY % StyleSheet "CDATA" -- style sheet data -->
+