Parent Directory
|
Revision Log
|
Patch
| revision 1.3 by wakaba, Wed May 2 13:44:34 2007 UTC | revision 1.155 by wakaba, Sat Aug 30 12:57:05 2008 UTC | |
|---|---|---|
| # | Line 1 | Line 1 |
| 1 | package Whatpm::HTML; | package Whatpm::HTML; |
| 2 | use strict; | use strict; |
| 3 | our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; | our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 4 | use Error qw(:try); | |
| 5 | ||
| 6 | ## This is an early version of an HTML parser. | ## ISSUE: |
| 7 | ## var doc = implementation.createDocument (null, null, null); | |
| 8 | my $permitted_slash_tag_name = { | ## doc.write (''); |
| 9 | base => 1, | ## alert (doc.compatMode); |
| 10 | link => 1, | |
| 11 | meta => 1, | require IO::Handle; |
| 12 | hr => 1, | |
| 13 | br => 1, | my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 14 | img=> 1, | my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 15 | embed => 1, | my $SVG_NS = q<http://www.w3.org/2000/svg>; |
| 16 | param => 1, | my $XLINK_NS = q<http://www.w3.org/1999/xlink>; |
| 17 | area => 1, | my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; |
| 18 | col => 1, | my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; |
| 19 | input => 1, | |
| 20 | sub A_EL () { 0b1 } | |
| 21 | sub ADDRESS_EL () { 0b10 } | |
| 22 | sub BODY_EL () { 0b100 } | |
| 23 | sub BUTTON_EL () { 0b1000 } | |
| 24 | sub CAPTION_EL () { 0b10000 } | |
| 25 | sub DD_EL () { 0b100000 } | |
| 26 | sub DIV_EL () { 0b1000000 } | |
| 27 | sub DT_EL () { 0b10000000 } | |
| 28 | sub FORM_EL () { 0b100000000 } | |
| 29 | sub FORMATTING_EL () { 0b1000000000 } | |
| 30 | sub FRAMESET_EL () { 0b10000000000 } | |
| 31 | sub HEADING_EL () { 0b100000000000 } | |
| 32 | sub HTML_EL () { 0b1000000000000 } | |
| 33 | sub LI_EL () { 0b10000000000000 } | |
| 34 | sub NOBR_EL () { 0b100000000000000 } | |
| 35 | sub OPTION_EL () { 0b1000000000000000 } | |
| 36 | sub OPTGROUP_EL () { 0b10000000000000000 } | |
| 37 | sub P_EL () { 0b100000000000000000 } | |
| 38 | sub SELECT_EL () { 0b1000000000000000000 } | |
| 39 | sub TABLE_EL () { 0b10000000000000000000 } | |
| 40 | sub TABLE_CELL_EL () { 0b100000000000000000000 } | |
| 41 | sub TABLE_ROW_EL () { 0b1000000000000000000000 } | |
| 42 | sub TABLE_ROW_GROUP_EL () { 0b10000000000000000000000 } | |
| 43 | sub MISC_SCOPING_EL () { 0b100000000000000000000000 } | |
| 44 | sub MISC_SPECIAL_EL () { 0b1000000000000000000000000 } | |
| 45 | sub FOREIGN_EL () { 0b10000000000000000000000000 } | |
| 46 | sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } | |
| 47 | sub MML_AXML_EL () { 0b1000000000000000000000000000 } | |
| 48 | sub RUBY_EL () { 0b10000000000000000000000000000 } | |
| 49 | sub RUBY_COMPONENT_EL () { 0b100000000000000000000000000000 } | |
| 50 | ||
| 51 | sub TABLE_ROWS_EL () { | |
| 52 | TABLE_EL | | |
| 53 | TABLE_ROW_EL | | |
| 54 | TABLE_ROW_GROUP_EL | |
| 55 | } | |
| 56 | ||
| 57 | ## NOTE: Used in "generate implied end tags" algorithm. | |
| 58 | ## NOTE: There is a code where a modified version of END_TAG_OPTIONAL_EL | |
| 59 | ## is used in "generate implied end tags" implementation (search for the | |
| 60 | ## function mae). | |
| 61 | sub END_TAG_OPTIONAL_EL () { | |
| 62 | DD_EL | | |
| 63 | DT_EL | | |
| 64 | LI_EL | | |
| 65 | P_EL | | |
| 66 | RUBY_COMPONENT_EL | |
| 67 | } | |
| 68 | ||
| 69 | ## NOTE: Used in </body> and EOF algorithms. | |
| 70 | sub ALL_END_TAG_OPTIONAL_EL () { | |
| 71 | DD_EL | | |
| 72 | DT_EL | | |
| 73 | LI_EL | | |
| 74 | P_EL | | |
| 75 | ||
| 76 | BODY_EL | | |
| 77 | HTML_EL | | |
| 78 | TABLE_CELL_EL | | |
| 79 | TABLE_ROW_EL | | |
| 80 | TABLE_ROW_GROUP_EL | |
| 81 | } | |
| 82 | ||
| 83 | sub SCOPING_EL () { | |
| 84 | BUTTON_EL | | |
| 85 | CAPTION_EL | | |
| 86 | HTML_EL | | |
| 87 | TABLE_EL | | |
| 88 | TABLE_CELL_EL | | |
| 89 | MISC_SCOPING_EL | |
| 90 | } | |
| 91 | ||
| 92 | sub TABLE_SCOPING_EL () { | |
| 93 | HTML_EL | | |
| 94 | TABLE_EL | |
| 95 | } | |
| 96 | ||
| 97 | sub TABLE_ROWS_SCOPING_EL () { | |
| 98 | HTML_EL | | |
| 99 | TABLE_ROW_GROUP_EL | |
| 100 | } | |
| 101 | ||
| 102 | sub TABLE_ROW_SCOPING_EL () { | |
| 103 | HTML_EL | | |
| 104 | TABLE_ROW_EL | |
| 105 | } | |
| 106 | ||
| 107 | sub SPECIAL_EL () { | |
| 108 | ADDRESS_EL | | |
| 109 | BODY_EL | | |
| 110 | DIV_EL | | |
| 111 | ||
| 112 | DD_EL | | |
| 113 | DT_EL | | |
| 114 | LI_EL | | |
| 115 | P_EL | | |
| 116 | ||
| 117 | FORM_EL | | |
| 118 | FRAMESET_EL | | |
| 119 | HEADING_EL | | |
| 120 | OPTION_EL | | |
| 121 | OPTGROUP_EL | | |
| 122 | SELECT_EL | | |
| 123 | TABLE_ROW_EL | | |
| 124 | TABLE_ROW_GROUP_EL | | |
| 125 | MISC_SPECIAL_EL | |
| 126 | } | |
| 127 | ||
| 128 | my $el_category = { | |
| 129 | a => A_EL | FORMATTING_EL, | |
| 130 | address => ADDRESS_EL, | |
| 131 | applet => MISC_SCOPING_EL, | |
| 132 | area => MISC_SPECIAL_EL, | |
| 133 | b => FORMATTING_EL, | |
| 134 | base => MISC_SPECIAL_EL, | |
| 135 | basefont => MISC_SPECIAL_EL, | |
| 136 | bgsound => MISC_SPECIAL_EL, | |
| 137 | big => FORMATTING_EL, | |
| 138 | blockquote => MISC_SPECIAL_EL, | |
| 139 | body => BODY_EL, | |
| 140 | br => MISC_SPECIAL_EL, | |
| 141 | button => BUTTON_EL, | |
| 142 | caption => CAPTION_EL, | |
| 143 | center => MISC_SPECIAL_EL, | |
| 144 | col => MISC_SPECIAL_EL, | |
| 145 | colgroup => MISC_SPECIAL_EL, | |
| 146 | dd => DD_EL, | |
| 147 | dir => MISC_SPECIAL_EL, | |
| 148 | div => DIV_EL, | |
| 149 | dl => MISC_SPECIAL_EL, | |
| 150 | dt => DT_EL, | |
| 151 | em => FORMATTING_EL, | |
| 152 | embed => MISC_SPECIAL_EL, | |
| 153 | fieldset => MISC_SPECIAL_EL, | |
| 154 | font => FORMATTING_EL, | |
| 155 | form => FORM_EL, | |
| 156 | frame => MISC_SPECIAL_EL, | |
| 157 | frameset => FRAMESET_EL, | |
| 158 | h1 => HEADING_EL, | |
| 159 | h2 => HEADING_EL, | |
| 160 | h3 => HEADING_EL, | |
| 161 | h4 => HEADING_EL, | |
| 162 | h5 => HEADING_EL, | |
| 163 | h6 => HEADING_EL, | |
| 164 | head => MISC_SPECIAL_EL, | |
| 165 | hr => MISC_SPECIAL_EL, | |
| 166 | html => HTML_EL, | |
| 167 | i => FORMATTING_EL, | |
| 168 | iframe => MISC_SPECIAL_EL, | |
| 169 | img => MISC_SPECIAL_EL, | |
| 170 | input => MISC_SPECIAL_EL, | |
| 171 | isindex => MISC_SPECIAL_EL, | |
| 172 | li => LI_EL, | |
| 173 | link => MISC_SPECIAL_EL, | |
| 174 | listing => MISC_SPECIAL_EL, | |
| 175 | marquee => MISC_SCOPING_EL, | |
| 176 | menu => MISC_SPECIAL_EL, | |
| 177 | meta => MISC_SPECIAL_EL, | |
| 178 | nobr => NOBR_EL | FORMATTING_EL, | |
| 179 | noembed => MISC_SPECIAL_EL, | |
| 180 | noframes => MISC_SPECIAL_EL, | |
| 181 | noscript => MISC_SPECIAL_EL, | |
| 182 | object => MISC_SCOPING_EL, | |
| 183 | ol => MISC_SPECIAL_EL, | |
| 184 | optgroup => OPTGROUP_EL, | |
| 185 | option => OPTION_EL, | |
| 186 | p => P_EL, | |
| 187 | param => MISC_SPECIAL_EL, | |
| 188 | plaintext => MISC_SPECIAL_EL, | |
| 189 | pre => MISC_SPECIAL_EL, | |
| 190 | rp => RUBY_COMPONENT_EL, | |
| 191 | rt => RUBY_COMPONENT_EL, | |
| 192 | ruby => RUBY_EL, | |
| 193 | s => FORMATTING_EL, | |
| 194 | script => MISC_SPECIAL_EL, | |
| 195 | select => SELECT_EL, | |
| 196 | small => FORMATTING_EL, | |
| 197 | spacer => MISC_SPECIAL_EL, | |
| 198 | strike => FORMATTING_EL, | |
| 199 | strong => FORMATTING_EL, | |
| 200 | style => MISC_SPECIAL_EL, | |
| 201 | table => TABLE_EL, | |
| 202 | tbody => TABLE_ROW_GROUP_EL, | |
| 203 | td => TABLE_CELL_EL, | |
| 204 | textarea => MISC_SPECIAL_EL, | |
| 205 | tfoot => TABLE_ROW_GROUP_EL, | |
| 206 | th => TABLE_CELL_EL, | |
| 207 | thead => TABLE_ROW_GROUP_EL, | |
| 208 | title => MISC_SPECIAL_EL, | |
| 209 | tr => TABLE_ROW_EL, | |
| 210 | tt => FORMATTING_EL, | |
| 211 | u => FORMATTING_EL, | |
| 212 | ul => MISC_SPECIAL_EL, | |
| 213 | wbr => MISC_SPECIAL_EL, | |
| 214 | }; | }; |
| 215 | ||
| 216 | my $entity_char = { | my $el_category_f = { |
| 217 | AElig => "\x{00C6}", | $MML_NS => { |
| 218 | Aacute => "\x{00C1}", | 'annotation-xml' => MML_AXML_EL, |
| 219 | Acirc => "\x{00C2}", | mi => FOREIGN_FLOW_CONTENT_EL, |
| 220 | Agrave => "\x{00C0}", | mo => FOREIGN_FLOW_CONTENT_EL, |
| 221 | Alpha => "\x{0391}", | mn => FOREIGN_FLOW_CONTENT_EL, |
| 222 | Aring => "\x{00C5}", | ms => FOREIGN_FLOW_CONTENT_EL, |
| 223 | Atilde => "\x{00C3}", | mtext => FOREIGN_FLOW_CONTENT_EL, |
| 224 | Auml => "\x{00C4}", | }, |
| 225 | Beta => "\x{0392}", | $SVG_NS => { |
| 226 | Ccedil => "\x{00C7}", | foreignObject => FOREIGN_FLOW_CONTENT_EL, |
| 227 | Chi => "\x{03A7}", | desc => FOREIGN_FLOW_CONTENT_EL, |
| 228 | Dagger => "\x{2021}", | title => FOREIGN_FLOW_CONTENT_EL, |
| 229 | Delta => "\x{0394}", | }, |
| 230 | ETH => "\x{00D0}", | ## NOTE: In addition, FOREIGN_EL is set to non-HTML elements. |
| Eacute => "\x{00C9}", | ||
| Ecirc => "\x{00CA}", | ||
| Egrave => "\x{00C8}", | ||
| Epsilon => "\x{0395}", | ||
| Eta => "\x{0397}", | ||
| Euml => "\x{00CB}", | ||
| Gamma => "\x{0393}", | ||
| Iacute => "\x{00CD}", | ||
| Icirc => "\x{00CE}", | ||
| Igrave => "\x{00CC}", | ||
| Iota => "\x{0399}", | ||
| Iuml => "\x{00CF}", | ||
| Kappa => "\x{039A}", | ||
| Lambda => "\x{039B}", | ||
| Mu => "\x{039C}", | ||
| Ntilde => "\x{00D1}", | ||
| Nu => "\x{039D}", | ||
| OElig => "\x{0152}", | ||
| Oacute => "\x{00D3}", | ||
| Ocirc => "\x{00D4}", | ||
| Ograve => "\x{00D2}", | ||
| Omega => "\x{03A9}", | ||
| Omicron => "\x{039F}", | ||
| Oslash => "\x{00D8}", | ||
| Otilde => "\x{00D5}", | ||
| Ouml => "\x{00D6}", | ||
| Phi => "\x{03A6}", | ||
| Pi => "\x{03A0}", | ||
| Prime => "\x{2033}", | ||
| Psi => "\x{03A8}", | ||
| Rho => "\x{03A1}", | ||
| Scaron => "\x{0160}", | ||
| Sigma => "\x{03A3}", | ||
| THORN => "\x{00DE}", | ||
| Tau => "\x{03A4}", | ||
| Theta => "\x{0398}", | ||
| Uacute => "\x{00DA}", | ||
| Ucirc => "\x{00DB}", | ||
| Ugrave => "\x{00D9}", | ||
| Upsilon => "\x{03A5}", | ||
| Uuml => "\x{00DC}", | ||
| Xi => "\x{039E}", | ||
| Yacute => "\x{00DD}", | ||
| Yuml => "\x{0178}", | ||
| Zeta => "\x{0396}", | ||
| aacute => "\x{00E1}", | ||
| acirc => "\x{00E2}", | ||
| acute => "\x{00B4}", | ||
| aelig => "\x{00E6}", | ||
| agrave => "\x{00E0}", | ||
| alefsym => "\x{2135}", | ||
| alpha => "\x{03B1}", | ||
| amp => "\x{0026}", | ||
| AMP => "\x{0026}", | ||
| and => "\x{2227}", | ||
| ang => "\x{2220}", | ||
| apos => "\x{0027}", | ||
| aring => "\x{00E5}", | ||
| asymp => "\x{2248}", | ||
| atilde => "\x{00E3}", | ||
| auml => "\x{00E4}", | ||
| bdquo => "\x{201E}", | ||
| beta => "\x{03B2}", | ||
| brvbar => "\x{00A6}", | ||
| bull => "\x{2022}", | ||
| cap => "\x{2229}", | ||
| ccedil => "\x{00E7}", | ||
| cedil => "\x{00B8}", | ||
| cent => "\x{00A2}", | ||
| chi => "\x{03C7}", | ||
| circ => "\x{02C6}", | ||
| clubs => "\x{2663}", | ||
| cong => "\x{2245}", | ||
| copy => "\x{00A9}", | ||
| COPY => "\x{00A9}", | ||
| crarr => "\x{21B5}", | ||
| cup => "\x{222A}", | ||
| curren => "\x{00A4}", | ||
| dArr => "\x{21D3}", | ||
| dagger => "\x{2020}", | ||
| darr => "\x{2193}", | ||
| deg => "\x{00B0}", | ||
| delta => "\x{03B4}", | ||
| diams => "\x{2666}", | ||
| divide => "\x{00F7}", | ||
| eacute => "\x{00E9}", | ||
| ecirc => "\x{00EA}", | ||
| egrave => "\x{00E8}", | ||
| empty => "\x{2205}", | ||
| emsp => "\x{2003}", | ||
| ensp => "\x{2002}", | ||
| epsilon => "\x{03B5}", | ||
| equiv => "\x{2261}", | ||
| eta => "\x{03B7}", | ||
| eth => "\x{00F0}", | ||
| euml => "\x{00EB}", | ||
| euro => "\x{20AC}", | ||
| exist => "\x{2203}", | ||
| fnof => "\x{0192}", | ||
| forall => "\x{2200}", | ||
| frac12 => "\x{00BD}", | ||
| frac14 => "\x{00BC}", | ||
| frac34 => "\x{00BE}", | ||
| frasl => "\x{2044}", | ||
| gamma => "\x{03B3}", | ||
| ge => "\x{2265}", | ||
| gt => "\x{003E}", | ||
| GT => "\x{003E}", | ||
| hArr => "\x{21D4}", | ||
| harr => "\x{2194}", | ||
| hearts => "\x{2665}", | ||
| hellip => "\x{2026}", | ||
| iacute => "\x{00ED}", | ||
| icirc => "\x{00EE}", | ||
| iexcl => "\x{00A1}", | ||
| igrave => "\x{00EC}", | ||
| image => "\x{2111}", | ||
| infin => "\x{221E}", | ||
| int => "\x{222B}", | ||
| iota => "\x{03B9}", | ||
| iquest => "\x{00BF}", | ||
| isin => "\x{2208}", | ||
| iuml => "\x{00EF}", | ||
| kappa => "\x{03BA}", | ||
| lArr => "\x{21D0}", | ||
| lambda => "\x{03BB}", | ||
| lang => "\x{2329}", | ||
| laquo => "\x{00AB}", | ||
| larr => "\x{2190}", | ||
| lceil => "\x{2308}", | ||
| ldquo => "\x{201C}", | ||
| le => "\x{2264}", | ||
| lfloor => "\x{230A}", | ||
| lowast => "\x{2217}", | ||
| loz => "\x{25CA}", | ||
| lrm => "\x{200E}", | ||
| lsaquo => "\x{2039}", | ||
| lsquo => "\x{2018}", | ||
| lt => "\x{003C}", | ||
| LT => "\x{003C}", | ||
| macr => "\x{00AF}", | ||
| mdash => "\x{2014}", | ||
| micro => "\x{00B5}", | ||
| middot => "\x{00B7}", | ||
| minus => "\x{2212}", | ||
| mu => "\x{03BC}", | ||
| nabla => "\x{2207}", | ||
| nbsp => "\x{00A0}", | ||
| ndash => "\x{2013}", | ||
| ne => "\x{2260}", | ||
| ni => "\x{220B}", | ||
| not => "\x{00AC}", | ||
| notin => "\x{2209}", | ||
| nsub => "\x{2284}", | ||
| ntilde => "\x{00F1}", | ||
| nu => "\x{03BD}", | ||
| oacute => "\x{00F3}", | ||
| ocirc => "\x{00F4}", | ||
| oelig => "\x{0153}", | ||
| ograve => "\x{00F2}", | ||
| oline => "\x{203E}", | ||
| omega => "\x{03C9}", | ||
| omicron => "\x{03BF}", | ||
| oplus => "\x{2295}", | ||
| or => "\x{2228}", | ||
| ordf => "\x{00AA}", | ||
| ordm => "\x{00BA}", | ||
| oslash => "\x{00F8}", | ||
| otilde => "\x{00F5}", | ||
| otimes => "\x{2297}", | ||
| ouml => "\x{00F6}", | ||
| para => "\x{00B6}", | ||
| part => "\x{2202}", | ||
| permil => "\x{2030}", | ||
| perp => "\x{22A5}", | ||
| phi => "\x{03C6}", | ||
| pi => "\x{03C0}", | ||
| piv => "\x{03D6}", | ||
| plusmn => "\x{00B1}", | ||
| pound => "\x{00A3}", | ||
| prime => "\x{2032}", | ||
| prod => "\x{220F}", | ||
| prop => "\x{221D}", | ||
| psi => "\x{03C8}", | ||
| quot => "\x{0022}", | ||
| QUOT => "\x{0022}", | ||
| rArr => "\x{21D2}", | ||
| radic => "\x{221A}", | ||
| rang => "\x{232A}", | ||
| raquo => "\x{00BB}", | ||
| rarr => "\x{2192}", | ||
| rceil => "\x{2309}", | ||
| rdquo => "\x{201D}", | ||
| real => "\x{211C}", | ||
| reg => "\x{00AE}", | ||
| REG => "\x{00AE}", | ||
| rfloor => "\x{230B}", | ||
| rho => "\x{03C1}", | ||
| rlm => "\x{200F}", | ||
| rsaquo => "\x{203A}", | ||
| rsquo => "\x{2019}", | ||
| sbquo => "\x{201A}", | ||
| scaron => "\x{0161}", | ||
| sdot => "\x{22C5}", | ||
| sect => "\x{00A7}", | ||
| shy => "\x{00AD}", | ||
| sigma => "\x{03C3}", | ||
| sigmaf => "\x{03C2}", | ||
| sim => "\x{223C}", | ||
| spades => "\x{2660}", | ||
| sub => "\x{2282}", | ||
| sube => "\x{2286}", | ||
| sum => "\x{2211}", | ||
| sup => "\x{2283}", | ||
| sup1 => "\x{00B9}", | ||
| sup2 => "\x{00B2}", | ||
| sup3 => "\x{00B3}", | ||
| supe => "\x{2287}", | ||
| szlig => "\x{00DF}", | ||
| tau => "\x{03C4}", | ||
| there4 => "\x{2234}", | ||
| theta => "\x{03B8}", | ||
| thetasym => "\x{03D1}", | ||
| thinsp => "\x{2009}", | ||
| thorn => "\x{00FE}", | ||
| tilde => "\x{02DC}", | ||
| times => "\x{00D7}", | ||
| trade => "\x{2122}", | ||
| uArr => "\x{21D1}", | ||
| uacute => "\x{00FA}", | ||
| uarr => "\x{2191}", | ||
| ucirc => "\x{00FB}", | ||
| ugrave => "\x{00F9}", | ||
| uml => "\x{00A8}", | ||
| upsih => "\x{03D2}", | ||
| upsilon => "\x{03C5}", | ||
| uuml => "\x{00FC}", | ||
| weierp => "\x{2118}", | ||
| xi => "\x{03BE}", | ||
| yacute => "\x{00FD}", | ||
| yen => "\x{00A5}", | ||
| yuml => "\x{00FF}", | ||
| zeta => "\x{03B6}", | ||
| zwj => "\x{200D}", | ||
| zwnj => "\x{200C}", | ||
| 231 | }; | }; |
| 232 | ||
| 233 | my $special_category = { | my $svg_attr_name = { |
| 234 | address => 1, area => 1, base => 1, basefont => 1, bgsound => 1, | attributename => 'attributeName', |
| 235 | blockquote => 1, body => 1, br => 1, center => 1, col => 1, colgroup => 1, | attributetype => 'attributeType', |
| 236 | dd => 1, dir => 1, div => 1, dl => 1, dt => 1, embed => 1, fieldset => 1, | basefrequency => 'baseFrequency', |
| 237 | form => 1, frame => 1, frameset => 1, h1 => 1, h2 => 1, h3 => 1, | baseprofile => 'baseProfile', |
| 238 | h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, iframe => 1, image => 1, | calcmode => 'calcMode', |
| 239 | img => 1, input => 1, isindex => 1, li => 1, link => 1, listing => 1, | clippathunits => 'clipPathUnits', |
| 240 | menu => 1, meta => 1, noembed => 1, noframes => 1, noscript => 1, | contentscripttype => 'contentScriptType', |
| 241 | ol => 1, optgroup => 1, option => 1, p => 1, param => 1, plaintext => 1, | contentstyletype => 'contentStyleType', |
| 242 | pre => 1, script => 1, select => 1, spacer => 1, style => 1, tbody => 1, | diffuseconstant => 'diffuseConstant', |
| 243 | textarea => 1, tfoot => 1, thead => 1, title => 1, tr => 1, ul => 1, wbr => 1, | edgemode => 'edgeMode', |
| 244 | }; | externalresourcesrequired => 'externalResourcesRequired', |
| 245 | my $scoping_category = { | filterres => 'filterRes', |
| 246 | button => 1, caption => 1, html => 1, marquee => 1, object => 1, | filterunits => 'filterUnits', |
| 247 | table => 1, td => 1, th => 1, | glyphref => 'glyphRef', |
| 248 | gradienttransform => 'gradientTransform', | |
| 249 | gradientunits => 'gradientUnits', | |
| 250 | kernelmatrix => 'kernelMatrix', | |
| 251 | kernelunitlength => 'kernelUnitLength', | |
| 252 | keypoints => 'keyPoints', | |
| 253 | keysplines => 'keySplines', | |
| 254 | keytimes => 'keyTimes', | |
| 255 | lengthadjust => 'lengthAdjust', | |
| 256 | limitingconeangle => 'limitingConeAngle', | |
| 257 | markerheight => 'markerHeight', | |
| 258 | markerunits => 'markerUnits', | |
| 259 | markerwidth => 'markerWidth', | |
| 260 | maskcontentunits => 'maskContentUnits', | |
| 261 | maskunits => 'maskUnits', | |
| 262 | numoctaves => 'numOctaves', | |
| 263 | pathlength => 'pathLength', | |
| 264 | patterncontentunits => 'patternContentUnits', | |
| 265 | patterntransform => 'patternTransform', | |
| 266 | patternunits => 'patternUnits', | |
| 267 | pointsatx => 'pointsAtX', | |
| 268 | pointsaty => 'pointsAtY', | |
| 269 | pointsatz => 'pointsAtZ', | |
| 270 | preservealpha => 'preserveAlpha', | |
| 271 | preserveaspectratio => 'preserveAspectRatio', | |
| 272 | primitiveunits => 'primitiveUnits', | |
| 273 | refx => 'refX', | |
| 274 | refy => 'refY', | |
| 275 | repeatcount => 'repeatCount', | |
| 276 | repeatdur => 'repeatDur', | |
| 277 | requiredextensions => 'requiredExtensions', | |
| 278 | requiredfeatures => 'requiredFeatures', | |
| 279 | specularconstant => 'specularConstant', | |
| 280 | specularexponent => 'specularExponent', | |
| 281 | spreadmethod => 'spreadMethod', | |
| 282 | startoffset => 'startOffset', | |
| 283 | stddeviation => 'stdDeviation', | |
| 284 | stitchtiles => 'stitchTiles', | |
| 285 | surfacescale => 'surfaceScale', | |
| 286 | systemlanguage => 'systemLanguage', | |
| 287 | tablevalues => 'tableValues', | |
| 288 | targetx => 'targetX', | |
| 289 | targety => 'targetY', | |
| 290 | textlength => 'textLength', | |
| 291 | viewbox => 'viewBox', | |
| 292 | viewtarget => 'viewTarget', | |
| 293 | xchannelselector => 'xChannelSelector', | |
| 294 | ychannelselector => 'yChannelSelector', | |
| 295 | zoomandpan => 'zoomAndPan', | |
| 296 | }; | }; |
| 297 | my $formatting_category = { | |
| 298 | a => 1, b => 1, big => 1, em => 1, font => 1, i => 1, nobr => 1, | my $foreign_attr_xname = { |
| 299 | s => 1, small => 1, strile => 1, strong => 1, tt => 1, u => 1, | 'xlink:actuate' => [$XLINK_NS, ['xlink', 'actuate']], |
| 300 | 'xlink:arcrole' => [$XLINK_NS, ['xlink', 'arcrole']], | |
| 301 | 'xlink:href' => [$XLINK_NS, ['xlink', 'href']], | |
| 302 | 'xlink:role' => [$XLINK_NS, ['xlink', 'role']], | |
| 303 | 'xlink:show' => [$XLINK_NS, ['xlink', 'show']], | |
| 304 | 'xlink:title' => [$XLINK_NS, ['xlink', 'title']], | |
| 305 | 'xlink:type' => [$XLINK_NS, ['xlink', 'type']], | |
| 306 | 'xml:base' => [$XML_NS, ['xml', 'base']], | |
| 307 | 'xml:lang' => [$XML_NS, ['xml', 'lang']], | |
| 308 | 'xml:space' => [$XML_NS, ['xml', 'space']], | |
| 309 | 'xmlns' => [$XMLNS_NS, [undef, 'xmlns']], | |
| 310 | 'xmlns:xlink' => [$XMLNS_NS, ['xmlns', 'xlink']], | |
| 311 | }; | }; |
| # $phrasing_category: all other elements | ||
| 312 | ||
| 313 | sub parse_string ($$$;$) { | ## ISSUE: xmlns:xlink="non-xlink-ns" is not an error. |
| 314 | my $self = shift->new; | |
| 315 | my $s = \$_[0]; | my $c1_entity_char = { |
| 316 | 0x80 => 0x20AC, | |
| 317 | 0x81 => 0xFFFD, | |
| 318 | 0x82 => 0x201A, | |
| 319 | 0x83 => 0x0192, | |
| 320 | 0x84 => 0x201E, | |
| 321 | 0x85 => 0x2026, | |
| 322 | 0x86 => 0x2020, | |
| 323 | 0x87 => 0x2021, | |
| 324 | 0x88 => 0x02C6, | |
| 325 | 0x89 => 0x2030, | |
| 326 | 0x8A => 0x0160, | |
| 327 | 0x8B => 0x2039, | |
| 328 | 0x8C => 0x0152, | |
| 329 | 0x8D => 0xFFFD, | |
| 330 | 0x8E => 0x017D, | |
| 331 | 0x8F => 0xFFFD, | |
| 332 | 0x90 => 0xFFFD, | |
| 333 | 0x91 => 0x2018, | |
| 334 | 0x92 => 0x2019, | |
| 335 | 0x93 => 0x201C, | |
| 336 | 0x94 => 0x201D, | |
| 337 | 0x95 => 0x2022, | |
| 338 | 0x96 => 0x2013, | |
| 339 | 0x97 => 0x2014, | |
| 340 | 0x98 => 0x02DC, | |
| 341 | 0x99 => 0x2122, | |
| 342 | 0x9A => 0x0161, | |
| 343 | 0x9B => 0x203A, | |
| 344 | 0x9C => 0x0153, | |
| 345 | 0x9D => 0xFFFD, | |
| 346 | 0x9E => 0x017E, | |
| 347 | 0x9F => 0x0178, | |
| 348 | }; # $c1_entity_char | |
| 349 | ||
| 350 | sub parse_byte_string ($$$$;$) { | |
| 351 | my $self = shift; | |
| 352 | my $charset_name = shift; | |
| 353 | open my $input, '<', ref $_[0] ? $_[0] : \($_[0]); | |
| 354 | return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]); | |
| 355 | } # parse_byte_string | |
| 356 | ||
| 357 | sub parse_byte_stream ($$$$;$) { | |
| 358 | my $self = ref $_[0] ? shift : shift->new; | |
| 359 |