Non-XML character "a\357\277\277b" [["Character", "ab"]] [["Character", "a\357\277\275b"]] Non-XML space "a\fb" [["Character", "ab"]] [["Character", "a b"]] Double hyphen in comment "" [["Comment", " foo -- bar "]] [["Comment", " foo - - bar "]] FF between attributes "" [["StartTag", "a", {"b"=>""}], ["EndTag", "a"], ["Character", "c=''>"]] [["StartTag", "a", {"b"=>"", "c"=>""}]] Correct Doctype uppercase "" [["DOCTYPE", "HTML", nil, nil, true]] [["DOCTYPE", "html", nil, nil, true]] Correct Doctype mixed case "" [["DOCTYPE", "HtMl", nil, nil, true]] [["DOCTYPE", "html", nil, nil, true]] Correct Doctype case with EOF "" [["DOCTYPE", "html", nil, nil, true]] [["Comment", "DOC"]] Empty end tag "" [["Character", ">"]] [] Empty start tag "<>" [] [["Character", "<>"]] Two unclosed start tags "

One

Two" [["StartTag", "p", {}], ["Character", "One"], ["EndTag", "p"], ["StartTag", "p", {}], ["Character", "Two"]] [["StartTag", "p", {}], ["Character", "One"], ["StartTag", "p", {}], ["Character", "Two"]] Unfinished comment "" [] [["Comment", ""]] Short comment two "" [] [["Comment", ""]] Ampersand space EOF "& " [["Character", "&"]] [["Character", "& "]] Ampersand, number sign "&#" [] [["Character", "&#"]] Unfinished numeric entity "&#x" [] [["Character", "&#x"]] Entity without trailing semicolon (1) "I'm ¬it" [["Character", "I'm ¬it"]] [["Character", "I'm "], ["Character", "\302\254it"]] Entity without trailing semicolon (2) "I'm ¬in" [["Character", "I'm ¬in"]] [["Character", "I'm "], ["Character", "\302\254in"]] Partial entity match at end of file "I'm &no" [["Character", "I'm &no"]] [["Character", "I'm "], ["Character", "&no"]] Entity in attribute without semicolon "" [["StartTag", "h", {"a"=>"©"}]] [["StartTag", "h", {"a"=>"\302\251"}]] Invalid Unicode character U+0001 "\001" [] [["Character", "\001"]] Invalid Unicode character U+0002 "\002" [] [["Character", "\002"]] Invalid Unicode character U+0003 "\003" [] [["Character", "\003"]] Invalid Unicode character U+0004 "\004" [] [["Character", "\004"]] Invalid Unicode character U+0005 "\005" [] [["Character", "\005"]] Invalid Unicode character U+0006 "\006" [] [["Character", "\006"]] Invalid Unicode character U+0007 "\a" [] [["Character", "\a"]] Invalid Unicode character U+0008 "\b" [] [["Character", "\b"]] Invalid Unicode character U+000B "\v" [] [["Character", "\v"]] Invalid Unicode character U+000E "\016" [] [["Character", "\016"]] Invalid Unicode character U+000F "\017" [] [["Character", "\017"]] Invalid Unicode character U+0010 "\020" [] [["Character", "\020"]] Invalid Unicode character U+0011 "\021" [] [["Character", "\021"]] Invalid Unicode character U+0012 "\022" [] [["Character", "\022"]] Invalid Unicode character U+0013 "\023" [] [["Character", "\023"]] Invalid Unicode character U+0014 "\024" [] [["Character", "\024"]] Invalid Unicode character U+0015 "\025" [] [["Character", "\025"]] Invalid Unicode character U+0016 "\026" [] [["Character", "\026"]] Invalid Unicode character U+0017 "\027" [] [["Character", "\027"]] Invalid Unicode character U+0018 "\030" [] [["Character", "\030"]] Invalid Unicode character U+0019 "\031" [] [["Character", "\031"]] Invalid Unicode character U+001A "\032" [] [["Character", "\032"]] Invalid Unicode character U+001B "\e" [] [["Character", "\e"]] Invalid Unicode character U+001C "\034" [] [["Character", "\034"]] Invalid Unicode character U+001D "\035" [] [["Character", "\035"]] Invalid Unicode character U+001E "\036" [] [["Character", "\036"]] Invalid Unicode character U+001F "\037" [] [["Character", "\037"]] Invalid Unicode character U+FFFE "\357\277\276" [] [["Character", "\357\277\276"]] Invalid Unicode character U+FFFF "\357\277\277" [] [["Character", "\357\277\277"]] Valid Unicode character U+0009 "\t" [] [["Character", "\t"]] Valid Unicode character U+000A "\n" [] [["Character", "\n"]] Valid Unicode character U+0020 " " [] [["Character", " "]] Invalid Unicode character U+DFFF "\\uDFFF" [["Character", "\\uDFFF"]] [["Character", "\\uFFFD"]] Invalid Unicode character U+D800 "\\uD800" [["Character", "\\uD800"]] [["Character", "\\uFFFD"]] Invalid Unicode character U+DFFF with valid preceding character "a\\uDFFF" [["Character", "a\\uDFFF"]] [["Character", "a\\uFFFD"]] Invalid Unicode character U+D800 with valid following character "\\uD800a" [["Character", "\\uD800a"]] [["Character", "\\uFFFDa"]] CR followed by U+0000 "\r\000" [] [["Character", "\n\357\277\275"]] Named entity: AElig without a semi-colon. "Æ" [["Character", "Æ"]] [["Character", "\303\206"]] Named entity: AMP with a semi-colon. "&" [["Character", "&"]] [["Character", "&"]] Named entity: AMP without a semi-colon. "&" [["Character", "&"]] [["Character", "&"]] Named entity: Aacute without a semi-colon. "Á" [["Character", "Á"]] [["Character", "\303\201"]] Named entity: Acirc without a semi-colon. "Â" [["Character", "Â"]] [["Character", "\303\202"]] Named entity: Agrave without a semi-colon. "À" [["Character", "À"]] [["Character", "\303\200"]] Named entity: Aring without a semi-colon. "Å" [["Character", "Å"]] [["Character", "\303\205"]] Named entity: Atilde without a semi-colon. "Ã" [["Character", "Ã"]] [["Character", "\303\203"]] Named entity: Auml without a semi-colon. "Ä" [["Character", "Ä"]] [["Character", "\303\204"]] Named entity: COPY with a semi-colon. "©" [["Character", "©"]] [["Character", "\302\251"]] Named entity: COPY without a semi-colon. "©" [["Character", "©"]] [["Character", "\302\251"]] Named entity: Ccedil without a semi-colon. "Ç" [["Character", "Ç"]] [["Character", "\303\207"]] Named entity: ETH without a semi-colon. "Ð" [["Character", "Ð"]] [["Character", "\303\220"]] Named entity: Eacute without a semi-colon. "É" [["Character", "É"]] [["Character", "\303\211"]] Named entity: Ecirc without a semi-colon. "Ê" [["Character", "Ê"]] [["Character", "\303\212"]] Named entity: Egrave without a semi-colon. "È" [["Character", "È"]] [["Character", "\303\210"]] Named entity: Euml without a semi-colon. "Ë" [["Character", "Ë"]] [["Character", "\303\213"]] Named entity: GT with a semi-colon. ">" [["Character", ">"]] [["Character", ">"]] Named entity: GT without a semi-colon. ">" [["Character", ">"]] [["Character", ">"]] Named entity: Iacute without a semi-colon. "Í" [["Character", "Í"]] [["Character", "\303\215"]] Named entity: Icirc without a semi-colon. "Î" [["Character", "Î"]] [["Character", "\303\216"]] Named entity: Igrave without a semi-colon. "Ì" [["Character", "Ì"]] [["Character", "\303\214"]] Named entity: Iuml without a semi-colon. "Ï" [["Character", "Ï"]] [["Character", "\303\217"]] Named entity: LT with a semi-colon. "<" [["Character", "<"]] [["Character", "<"]] Named entity: LT without a semi-colon. "<" [["Character", "<"]] [["Character", "<"]] Named entity: Ntilde without a semi-colon. "Ñ" [["Character", "Ñ"]] [["Character", "\303\221"]] Named entity: Oacute without a semi-colon. "Ó" [["Character", "Ó"]] [["Character", "\303\223"]] Named entity: Ocirc without a semi-colon. "Ô" [["Character", "Ô"]] [["Character", "\303\224"]] Named entity: Ograve without a semi-colon. "Ò" [["Character", "Ò"]] [["Character", "\303\222"]] Named entity: Oslash without a semi-colon. "Ø" [["Character", "Ø"]] [["Character", "\303\230"]] Named entity: Otilde without a semi-colon. "Õ" [["Character", "Õ"]] [["Character", "\303\225"]] Named entity: Ouml without a semi-colon. "Ö" [["Character", "Ö"]] [["Character", "\303\226"]] Named entity: QUOT with a semi-colon. """ [["Character", """]] [["Character", "\""]] Named entity: QUOT without a semi-colon. """ [["Character", """]] [["Character", "\""]] Named entity: REG with a semi-colon. "®" [["Character", "®"]] [["Character", "\302\256"]] Named entity: REG without a semi-colon. "®" [["Character", "®"]] [["Character", "\302\256"]] Named entity: THORN without a semi-colon. "Þ" [["Character", "Þ"]] [["Character", "\303\236"]] Named entity: TRADE with a semi-colon. "™" [["Character", "™"]] [["Character", "\342\204\242"]] Named entity: Uacute without a semi-colon. "Ú" [["Character", "Ú"]] [["Character", "\303\232"]] Named entity: Ucirc without a semi-colon. "Û" [["Character", "Û"]] [["Character", "\303\233"]] Named entity: Ugrave without a semi-colon. "Ù" [["Character", "Ù"]] [["Character", "\303\231"]] Named entity: Uuml without a semi-colon. "Ü" [["Character", "Ü"]] [["Character", "\303\234"]] Named entity: Yacute without a semi-colon. "Ý" [["Character", "Ý"]] [["Character", "\303\235"]] Named entity: aacute without a semi-colon. "á" [["Character", "á"]] [["Character", "\303\241"]] Named entity: acirc without a semi-colon. "â" [["Character", "â"]] [["Character", "\303\242"]] Named entity: acute without a semi-colon. "´" [["Character", "´"]] [["Character", "\302\264"]] Named entity: aelig without a semi-colon. "æ" [["Character", "æ"]] [["Character", "\303\246"]] Named entity: agrave without a semi-colon. "à" [["Character", "à"]] [["Character", "\303\240"]] Named entity: amp without a semi-colon. "&" [["Character", "&"]] [["Character", "&"]] Named entity: aring without a semi-colon. "å" [["Character", "å"]] [["Character", "\303\245"]] Named entity: atilde without a semi-colon. "ã" [["Character", "ã"]] [["Character", "\303\243"]] Named entity: auml without a semi-colon. "ä" [["Character", "ä"]] [["Character", "\303\244"]] Named entity: brvbar without a semi-colon. "¦" [["Character", "¦"]] [["Character", "\302\246"]] Named entity: ccedil without a semi-colon. "ç" [["Character", "ç"]] [["Character", "\303\247"]] Named entity: cedil without a semi-colon. "¸" [["Character", "¸"]] [["Character", "\302\270"]] Named entity: cent without a semi-colon. "¢" [["Character", "¢"]] [["Character", "\302\242"]] Named entity: copy without a semi-colon. "©" [["Character", "©"]] [["Character", "\302\251"]] Named entity: curren without a semi-colon. "¤" [["Character", "¤"]] [["Character", "\302\244"]] Named entity: deg without a semi-colon. "°" [["Character", "°"]] [["Character", "\302\260"]] Named entity: divide without a semi-colon. "÷" [["Character", "÷"]] [["Character", "\303\267"]] Named entity: eacute without a semi-colon. "é" [["Character", "é"]] [["Character", "\303\251"]] Named entity: ecirc without a semi-colon. "ê" [["Character", "ê"]] [["Character", "\303\252"]] Named entity: egrave without a semi-colon. "è" [["Character", "è"]] [["Character", "\303\250"]] Named entity: eth without a semi-colon. "ð" [["Character", "ð"]] [["Character", "\303\260"]] Named entity: euml without a semi-colon. "ë" [["Character", "ë"]] [["Character", "\303\253"]] Named entity: frac12 without a semi-colon. "½" [["Character", "½"]] [["Character", "\302\275"]] Named entity: frac14 without a semi-colon. "¼" [["Character", "¼"]] [["Character", "\302\274"]] Named entity: frac34 without a semi-colon. "¾" [["Character", "¾"]] [["Character", "\302\276"]] Named entity: gt without a semi-colon. ">" [["Character", ">"]] [["Character", ">"]] Named entity: iacute without a semi-colon. "í" [["Character", "í"]] [["Character", "\303\255"]] Named entity: icirc without a semi-colon. "î" [["Character", "î"]] [["Character", "\303\256"]] Named entity: iexcl without a semi-colon. "¡" [["Character", "¡"]] [["Character", "\302\241"]] Named entity: igrave without a semi-colon. "ì" [["Character", "ì"]] [["Character", "\303\254"]] Named entity: iquest without a semi-colon. "¿" [["Character", "¿"]] [["Character", "\302\277"]] Named entity: iuml without a semi-colon. "ï" [["Character", "ï"]] [["Character", "\303\257"]] Named entity: lang with a semi-colon. "⟨" [["Character", "\342\214\251"]] [["Character", "\342\237\250"]] Named entity: laquo without a semi-colon. "«" [["Character", "«"]] [["Character", "\302\253"]] Named entity: lt without a semi-colon. "<" [["Character", "<"]] [["Character", "<"]] Named entity: macr without a semi-colon. "¯" [["Character", "¯"]] [["Character", "\302\257"]] Named entity: micro without a semi-colon. "µ" [["Character", "µ"]] [["Character", "\302\265"]] Named entity: middot without a semi-colon. "·" [["Character", "·"]] [["Character", "\302\267"]] Named entity: nbsp without a semi-colon. " " [["Character", " "]] [["Character", "\302\240"]] Named entity: not without a semi-colon. "¬" [["Character", "¬"]] [["Character", "\302\254"]] Named entity: ntilde without a semi-colon. "ñ" [["Character", "ñ"]] [["Character", "\303\261"]] Named entity: oacute without a semi-colon. "ó" [["Character", "ó"]] [["Character", "\303\263"]] Named entity: ocirc without a semi-colon. "ô" [["Character", "ô"]] [["Character", "\303\264"]] Named entity: ograve without a semi-colon. "ò" [["Character", "ò"]] [["Character", "\303\262"]] Named entity: ordf without a semi-colon. "ª" [["Character", "ª"]] [["Character", "\302\252"]] Named entity: ordm without a semi-colon. "º" [["Character", "º"]] [["Character", "\302\272"]] Named entity: oslash without a semi-colon. "ø" [["Character", "ø"]] [["Character", "\303\270"]] Named entity: otilde without a semi-colon. "õ" [["Character", "õ"]] [["Character", "\303\265"]] Named entity: ouml without a semi-colon. "ö" [["Character", "ö"]] [["Character", "\303\266"]] Named entity: para without a semi-colon. "¶" [["Character", "¶"]] [["Character", "\302\266"]] Named entity: plusmn without a semi-colon. "±" [["Character", "±"]] [["Character", "\302\261"]] Named entity: pound without a semi-colon. "£" [["Character", "£"]] [["Character", "\302\243"]] Named entity: quot without a semi-colon. """ [["Character", """]] [["Character", "\""]] Named entity: rang with a semi-colon. "⟩" [["Character", "\342\214\252"]] [["Character", "\342\237\251"]] Named entity: raquo without a semi-colon. "»" [["Character", "»"]] [["Character", "\302\273"]] Named entity: reg without a semi-colon. "®" [["Character", "®"]] [["Character", "\302\256"]] Named entity: sect without a semi-colon. "§" [["Character", "§"]] [["Character", "\302\247"]] Named entity: shy without a semi-colon. "" [["Character", ""]] [["Character", "\302\255"]] Named entity: sup1 without a semi-colon. "¹" [["Character", "¹"]] [["Character", "\302\271"]] Named entity: sup2 without a semi-colon. "²" [["Character", "²"]] [["Character", "\302\262"]] Named entity: sup3 without a semi-colon. "³" [["Character", "³"]] [["Character", "\302\263"]] Named entity: szlig without a semi-colon. "ß" [["Character", "ß"]] [["Character", "\303\237"]] Named entity: thorn without a semi-colon. "þ" [["Character", "þ"]] [["Character", "\303\276"]] Named entity: times without a semi-colon. "×" [["Character", "×"]] [["Character", "\303\227"]] Named entity: uacute without a semi-colon. "ú" [["Character", "ú"]] [["Character", "\303\272"]] Named entity: ucirc without a semi-colon. "û" [["Character", "û"]] [["Character", "\303\273"]] Named entity: ugrave without a semi-colon. "ù" [["Character", "ù"]] [["Character", "\303\271"]] Named entity: uml without a semi-colon. "¨" [["Character", "¨"]] [["Character", "\302\250"]] Named entity: uuml without a semi-colon. "ü" [["Character", "ü"]] [["Character", "\303\274"]] Named entity: yacute without a semi-colon. "ý" [["Character", "ý"]] [["Character", "\303\275"]] Named entity: yen without a semi-colon. "¥" [["Character", "¥"]] [["Character", "\302\245"]] Named entity: yuml without a semi-colon. "ÿ" [["Character", "ÿ"]] [["Character", "\303\277"]] Bad named entity: notin without a semi-colon. "¬in" [["Character", "¬in"]] [["Character", "\302\254in"]] Windows-1252 EURO SIGN numeric entity. "€" [["Character", "\302\200"]] [["Character", "\342\202\254"]] Windows-1252 SINGLE LOW-9 QUOTATION MARK numeric entity. "‚" [["Character", "\302\202"]] [["Character", "\342\200\232"]] Windows-1252 LATIN SMALL LETTER F WITH HOOK numeric entity. "ƒ" [["Character", "\302\203"]] [["Character", "\306\222"]] Windows-1252 DOUBLE LOW-9 QUOTATION MARK numeric entity. "„" [["Character", "\302\204"]] [["Character", "\342\200\236"]] Windows-1252 HORIZONTAL ELLIPSIS numeric entity. "…" [["Character", "\302\205"]] [["Character", "\342\200\246"]] Windows-1252 DAGGER numeric entity. "†" [["Character", "\302\206"]] [["Character", "\342\200\240"]] Windows-1252 DOUBLE DAGGER numeric entity. "‡" [["Character", "\302\207"]] [["Character", "\342\200\241"]] Windows-1252 MODIFIER LETTER CIRCUMFLEX ACCENT numeric entity. "ˆ" [["Character", "\302\210"]] [["Character", "\313\206"]] Windows-1252 PER MILLE SIGN numeric entity. "‰" [["Character", "\302\211"]] [["Character", "\342\200\260"]] Windows-1252 LATIN CAPITAL LETTER S WITH CARON numeric entity. "Š" [["Character", "\302\212"]] [["Character", "\305\240"]] Windows-1252 SINGLE LEFT-POINTING ANGLE QUOTATION MARK numeric entity. "‹" [["Character", "\302\213"]] [["Character", "\342\200\271"]] Windows-1252 LATIN CAPITAL LIGATURE OE numeric entity. "Œ" [["Character", "\302\214"]] [["Character", "\305\222"]] Windows-1252 LATIN CAPITAL LETTER Z WITH CARON numeric entity. "Ž" [["Character", "\302\216"]] [["Character", "\305\275"]] Windows-1252 LEFT SINGLE QUOTATION MARK numeric entity. "‘" [["Character", "\302\221"]] [["Character", "\342\200\230"]] Windows-1252 RIGHT SINGLE QUOTATION MARK numeric entity. "’" [["Character", "\302\222"]] [["Character", "\342\200\231"]] Windows-1252 LEFT DOUBLE QUOTATION MARK numeric entity. "“" [["Character", "\302\223"]] [["Character", "\342\200\234"]] Windows-1252 RIGHT DOUBLE QUOTATION MARK numeric entity. "”" [["Character", "\302\224"]] [["Character", "\342\200\235"]] Windows-1252 BULLET numeric entity. "•" [["Character", "\302\225"]] [["Character", "\342\200\242"]] Windows-1252 EN DASH numeric entity. "–" [["Character", "\302\226"]] [["Character", "\342\200\223"]] Windows-1252 EM DASH numeric entity. "—" [["Character", "\302\227"]] [["Character", "\342\200\224"]] Windows-1252 SMALL TILDE numeric entity. "˜" [["Character", "\302\230"]] [["Character", "\313\234"]] Windows-1252 TRADE MARK SIGN numeric entity. "™" [["Character", "\302\231"]] [["Character", "\342\204\242"]] Windows-1252 LATIN SMALL LETTER S WITH CARON numeric entity. "š" [["Character", "\302\232"]] [["Character", "\305\241"]] Windows-1252 SINGLE RIGHT-POINTING ANGLE QUOTATION MARK numeric entity. "›" [["Character", "\302\233"]] [["Character", "\342\200\272"]] Windows-1252 LATIN SMALL LIGATURE OE numeric entity. "œ" [["Character", "\302\234"]] [["Character", "\305\223"]] Windows-1252 EURO SIGN hexadecimal numeric entity. "€" [["Character", "\302\200"]] [["Character", "\342\202\254"]] Windows-1252 SINGLE LOW-9 QUOTATION MARK hexadecimal numeric entity. "‚" [["Character", "\302\202"]] [["Character", "\342\200\232"]] Windows-1252 LATIN SMALL LETTER F WITH HOOK hexadecimal numeric entity. "ƒ" [["Character", "\302\203"]] [["Character", "\306\222"]] Windows-1252 DOUBLE LOW-9 QUOTATION MARK hexadecimal numeric entity. "„" [["Character", "\302\204"]] [["Character", "\342\200\236"]] Windows-1252 HORIZONTAL ELLIPSIS hexadecimal numeric entity. "…" [["Character", "\302\205"]] [["Character", "\342\200\246"]] Windows-1252 DAGGER hexadecimal numeric entity. "†" [["Character", "\302\206"]] [["Character", "\342\200\240"]] Windows-1252 DOUBLE DAGGER hexadecimal numeric entity. "‡" [["Character", "\302\207"]] [["Character", "\342\200\241"]] Windows-1252 MODIFIER LETTER CIRCUMFLEX ACCENT hexadecimal numeric entity. "ˆ" [["Character", "\302\210"]] [["Character", "\313\206"]] Windows-1252 PER MILLE SIGN hexadecimal numeric entity. "‰" [["Character", "\302\211"]] [["Character", "\342\200\260"]] Windows-1252 LATIN CAPITAL LETTER S WITH CARON hexadecimal numeric entity. "Š" [["Character", "\302\212"]] [["Character", "\305\240"]] Windows-1252 SINGLE LEFT-POINTING ANGLE QUOTATION MARK hexadecimal numeric entity. "‹" [["Character", "\302\213"]] [["Character", "\342\200\271"]] Windows-1252 LATIN CAPITAL LIGATURE OE hexadecimal numeric entity. "Œ" [["Character", "\302\214"]] [["Character", "\305\222"]] Windows-1252 LATIN CAPITAL LETTER Z WITH CARON hexadecimal numeric entity. "Ž" [["Character", "\302\216"]] [["Character", "\305\275"]] Windows-1252 LEFT SINGLE QUOTATION MARK hexadecimal numeric entity. "‘" [["Character", "\302\221"]] [["Character", "\342\200\230"]] Windows-1252 RIGHT SINGLE QUOTATION MARK hexadecimal numeric entity. "’" [["Character", "\302\222"]] [["Character", "\342\200\231"]] Windows-1252 LEFT DOUBLE QUOTATION MARK hexadecimal numeric entity. "“" [["Character", "\302\223"]] [["Character", "\342\200\234"]] Windows-1252 RIGHT DOUBLE QUOTATION MARK hexadecimal numeric entity. "”" [["Character", "\302\224"]] [["Character", "\342\200\235"]] Windows-1252 BULLET hexadecimal numeric entity. "•" [["Character", "\302\225"]] [["Character", "\342\200\242"]] Windows-1252 EN DASH hexadecimal numeric entity. "–" [["Character", "\302\226"]] [["Character", "\342\200\223"]] Windows-1252 EM DASH hexadecimal numeric entity. "—" [["Character", "\302\227"]] [["Character", "\342\200\224"]] Windows-1252 SMALL TILDE hexadecimal numeric entity. "˜" [["Character", "\302\230"]] [["Character", "\313\234"]] Windows-1252 TRADE MARK SIGN hexadecimal numeric entity. "™" [["Character", "\302\231"]] [["Character", "\342\204\242"]] Windows-1252 LATIN SMALL LETTER S WITH CARON hexadecimal numeric entity. "š" [["Character", "\302\232"]] [["Character", "\305\241"]] Windows-1252 SINGLE RIGHT-POINTING ANGLE QUOTATION MARK hexadecimal numeric entity. "›" [["Character", "\302\233"]] [["Character", "\342\200\272"]] Windows-1252 LATIN SMALL LIGATURE OE hexadecimal numeric entity. "œ" [["Character", "\302\234"]] [["Character", "\305\223"]] Windows-1252 LATIN SMALL LETTER Z WITH CARON hexadecimal numeric entity. "ž" [["Character", "\302\236"]] [["Character", "\305\276"]] Windows-1252 LATIN CAPITAL LETTER Y WITH DIAERESIS hexadecimal numeric entity. "Ÿ" [["Character", "\302\237"]] [["Character", "\305\270"]] Invalid numeric entity character U+0000 "�" [] [["Character", "\357\277\275"]] Invalid numeric entity character U+0001 "" [] [["Character", "\001"]] Invalid numeric entity character U+0002 "" [] [["Character", "\002"]] Invalid numeric entity character U+0003 "" [] [["Character", "\003"]] Invalid numeric entity character U+0004 "" [] [["Character", "\004"]] Invalid numeric entity character U+0005 "" [] [["Character", "\005"]] Invalid numeric entity character U+0006 "" [] [["Character", "\006"]] Invalid numeric entity character U+0007 "" [] [["Character", "\a"]] Invalid numeric entity character U+0008 "" [] [["Character", "\b"]] Invalid numeric entity character U+000B "" [] [["Character", "\v"]] Invalid numeric entity character U+000E "" [] [["Character", "\016"]] Invalid numeric entity character U+000F "" [] [["Character", "\017"]] Invalid numeric entity character U+0010 "" [] [["Character", "\020"]] Invalid numeric entity character U+0011 "" [] [["Character", "\021"]] Invalid numeric entity character U+0012 "" [] [["Character", "\022"]] Invalid numeric entity character U+0013 "" [] [["Character", "\023"]] Invalid numeric entity character U+0014 "" [] [["Character", "\024"]] Invalid numeric entity character U+0015 "" [] [["Character", "\025"]] Invalid numeric entity character U+0016 "" [] [["Character", "\026"]] Invalid numeric entity character U+0017 "" [] [["Character", "\027"]] Invalid numeric entity character U+0018 "" [] [["Character", "\030"]] Invalid numeric entity character U+0019 "" [] [["Character", "\031"]] Invalid numeric entity character U+001A "" [] [["Character", "\032"]] Invalid numeric entity character U+001B "" [] [["Character", "\e"]] Invalid numeric entity character U+001C "" [] [["Character", "\034"]] Invalid numeric entity character U+001D "" [] [["Character", "\035"]] Invalid numeric entity character U+001E "" [] [["Character", "\036"]] Invalid numeric entity character U+001F "" [] [["Character", "\037"]] Invalid numeric entity character U+D800 "�" [] [["Character", "\357\277\275"]] Invalid numeric entity character U+DFFF "�" [] [["Character", "\357\277\275"]] Invalid numeric entity character U+FFFE "" [] [["Character", "\357\277\276"]] Invalid numeric entity character U+FFFF "" [] [["Character", "\357\277\277"]] DOCTYPE without name "" [["DOCTYPE", nil, nil, nil, true]] [["DOCTYPE", "", nil, nil, false]] DOCTYPE with publicId "" [["DOCTYPE", "html", nil, nil, true]] [["DOCTYPE", "html", "-//W3C//DTD HTML Transitional 4.01//EN", nil, true]] DOCTYPE with EOF after PUBLIC "" [["DOCTYPE", "html", nil, nil, true]] [["DOCTYPE", "html", nil, "-//W3C//DTD HTML Transitional 4.01//EN", true]] DOCTYPE with publicId and systemId "" [["DOCTYPE", "html", nil, nil, true]] [["DOCTYPE", "html", "-//W3C//DTD HTML Transitional 4.01//EN", "-//W3C//DTD HTML Transitional 4.01//EN", true]] DOCTYPE with > in double-quoted publicId "x" [["DOCTYPE", "html", nil, nil, true], ["StartTag", "html", {}], ["StartTag", "body", {}], ["StartTag", "p", {}], ["Character", "x"]] [["DOCTYPE", "html", "", nil, false], ["Character", "x"]] DOCTYPE with > in single-quoted publicId "x" [["DOCTYPE", "html", nil, nil, true], ["StartTag", "html", {}], ["StartTag", "body", {}], ["StartTag", "p", {}], ["Character", "x"]] [["DOCTYPE", "html", "", nil, false], ["Character", "x"]] DOCTYPE with > in double-quoted systemId "x" [["DOCTYPE", "html", nil, nil, true]] [["DOCTYPE", "html", "foo", "", false], ["Character", "x"]] DOCTYPE with > in single-quoted systemId "x" [["DOCTYPE", "html", nil, nil, true]] [["DOCTYPE", "html", "foo", "", false], ["Character", "x"]] Incomplete doctype "" [["StartTag", "a", {}]] [["StartTag", "a" [["StartTag", "h", {}]] [["StartTag", "h", {}, true]] Void element with permitted slash "
" [["StartTag", "br", {}]] [["StartTag", "br", {}, true]] Void element with permitted slash (with attribute) "
" [["StartTag", "br", {"foo"=>"bar"}]] [["StartTag", "br", {"foo"=>"bar"}, true]] StartTag containing / "" [["StartTag", "h", {}]] [["StartTag", "h", {"a"=>"b"}]] Unescaped " [["Character", "1>"]] [["Comment", "1"]] Simili processing instruction "" [#] [["Comment", "?namespace"]] A bogus comment stops at >, even if preceeded by two dashes "" [#] [["Comment", "?foo--"]] Unescaped < "foo < bar" [["Character", "foo "]] [["Character", "foo "], ["Character", "< bar"]] Null Byte Replacement "\000" [] [["Character", "\357\277\275"]] Comment with dash " "" [] [["Comment", ""]] "" [] [["Comment", ""]] "" [] [["Comment", ""]] " [["Character", "foo"], ["Comment", ""]] [["Character", "foo"], ["EndTag", "xmp"]] Bogus comment in RCDATA or RAWTEXT "foobaz" [["Character", "foo"]] [["Character", "foobaz"], ["EndTag", "xmp"]] End tag surrounded by bogus comment in RCDATA or RAWTEXT "foobaz" [["Character", "foo"], ["Comment", ">"], ["EndTag", "xmp"], ["Comment", ""], ["Character", "baz"], ["EndTag", "xmp"]] Commented entities in RCDATA " & & " [["Character", "& "], ["Comment", " & "], ["Character", " & "]] [["Character", " & & "], ["EndTag", "xmp"]] Incorrect comment ending sequences in RCDATA or RAWTEXT "foox--<>" [["Character", "foo"]] [["Character", "foox--<>"], ["EndTag", "xmp"]]