Parent Directory
|
Revision Log
|
Patch
| revision 1.3 by wakaba, Wed May 2 13:44:34 2007 UTC | revision 1.228 by wakaba, Sun Aug 16 06:47:59 2009 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. | use Whatpm::HTML::Tokenizer; |
| 7 | ||
| 8 | my $permitted_slash_tag_name = { | ## NOTE: This module don't check all HTML5 parse errors; character |
| 9 | base => 1, | ## encoding related parse errors are expected to be handled by relevant |
| 10 | link => 1, | ## modules. |
| 11 | meta => 1, | ## Parse errors for control characters that are not allowed in HTML5 |
| 12 | hr => 1, | ## documents, for surrogate code points, and for noncharacter code |
| 13 | br => 1, | ## points, as well as U+FFFD substitions for characters whose code points |
| 14 | img=> 1, | ## is higher than U+10FFFF may be detected by combining the parser with |
| 15 | embed => 1, | ## the checker implemented by Whatpm::Charset::UnicodeChecker (for its |
| 16 | param => 1, | ## usage example, see |t/HTML-tree.t| in the Whatpm package or the |
| 17 | area => 1, | ## WebHACC::Language::HTML module in the WebHACC package). |
| 18 | col => 1, | |
| 19 | input => 1, | ## ISSUE: |
| 20 | ## var doc = implementation.createDocument (null, null, null); | |
| 21 | ## doc.write (''); | |
| 22 | ## alert (doc.compatMode); | |
| 23 | ||
| 24 | require IO::Handle; | |
| 25 | ||
| 26 | ## Namespace URLs | |
| 27 | ||
| 28 | my $HTML_NS = q<http://www.w3.org/1999/xhtml>; | |
| 29 | my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; | |
| 30 | my $SVG_NS = q<http://www.w3.org/2000/svg>; | |
| 31 | my $XLINK_NS = q<http://www.w3.org/1999/xlink>; | |
| 32 | my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; | |
| 33 | my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; | |
| 34 | ||
| 35 | ## Element categories | |
| 36 | ||
| 37 | ## Bits 12-15 | |
| 38 | sub SPECIAL_EL () { 0b1_000000000000000 } | |
| 39 | sub SCOPING_EL () { 0b1_00000000000000 } | |
| 40 | sub FORMATTING_EL () { 0b1_0000000000000 } | |
| 41 | sub PHRASING_EL () { 0b1_000000000000 } | |
| 42 | ||
| 43 | ## Bits 10-11 | |
| 44 | #sub FOREIGN_EL () { 0b1_00000000000 } # see Whatpm::HTML::Tokenizer | |
| 45 | sub FOREIGN_FLOW_CONTENT_EL () { 0b1_0000000000 } | |
| 46 | ||
| 47 | ## Bits 6-9 | |
| 48 | sub TABLE_SCOPING_EL () { 0b1_000000000 } | |
| 49 | sub TABLE_ROWS_SCOPING_EL () { 0b1_00000000 } | |
| 50 | sub TABLE_ROW_SCOPING_EL () { 0b1_0000000 } | |
| 51 | sub TABLE_ROWS_EL () { 0b1_000000 } | |
| 52 | ||
| 53 | ## Bit 5 | |
| 54 | sub ADDRESS_DIV_P_EL () { 0b1_00000 } | |
| 55 | ||
| 56 | ## NOTE: Used in </body> and EOF algorithms. | |
| 57 | ## Bit 4 | |
| 58 | sub ALL_END_TAG_OPTIONAL_EL () { 0b1_0000 } | |
| 59 | ||
| 60 | ## NOTE: Used in "generate implied end tags" algorithm. | |
| 61 | ## NOTE: There is a code where a modified version of | |
| 62 | ## END_TAG_OPTIONAL_EL is used in "generate implied end tags" | |
| 63 | ## implementation (search for the algorithm name). | |
| 64 | ## Bit 3 | |
| 65 | sub END_TAG_OPTIONAL_EL () { 0b1_000 } | |
| 66 | ||
| 67 | ## Bits 0-2 | |
| 68 | ||
| 69 | sub MISC_SPECIAL_EL () { SPECIAL_EL | 0b000 } | |
| 70 | sub FORM_EL () { SPECIAL_EL | 0b001 } | |
| 71 | sub FRAMESET_EL () { SPECIAL_EL | 0b010 } | |
| 72 | sub HEADING_EL () { SPECIAL_EL | 0b011 } | |
| 73 | sub SELECT_EL () { SPECIAL_EL | 0b100 } | |
| 74 | sub SCRIPT_EL () { SPECIAL_EL | 0b101 } | |
| 75 | ||
| 76 | sub ADDRESS_DIV_EL () { SPECIAL_EL | ADDRESS_DIV_P_EL | 0b001 } | |
| 77 | sub BODY_EL () { SPECIAL_EL | ALL_END_TAG_OPTIONAL_EL | 0b001 } | |
| 78 | ||
| 79 | sub DTDD_EL () { | |
| 80 | SPECIAL_EL | | |
| 81 | END_TAG_OPTIONAL_EL | | |
| 82 | ALL_END_TAG_OPTIONAL_EL | | |
| 83 | 0b010 | |
| 84 | } | |
| 85 | sub LI_EL () { | |
| 86 | SPECIAL_EL | | |
| 87 | END_TAG_OPTIONAL_EL | | |
| 88 | ALL_END_TAG_OPTIONAL_EL | | |
| 89 | 0b100 | |
| 90 | } | |
| 91 | sub P_EL () { | |
| 92 | SPECIAL_EL | | |
| 93 | ADDRESS_DIV_P_EL | | |
| 94 | END_TAG_OPTIONAL_EL | | |
| 95 | ALL_END_TAG_OPTIONAL_EL | | |
| 96 | 0b001 | |
| 97 | } | |
| 98 | ||
| 99 | sub TABLE_ROW_EL () { | |
| 100 | SPECIAL_EL | | |
| 101 | TABLE_ROWS_EL | | |
| 102 | TABLE_ROW_SCOPING_EL | | |
| 103 | ALL_END_TAG_OPTIONAL_EL | | |
| 104 | 0b001 | |
| 105 | } | |
| 106 | sub TABLE_ROW_GROUP_EL () { | |
| 107 | SPECIAL_EL | | |
| 108 | TABLE_ROWS_EL | | |
| 109 | TABLE_ROWS_SCOPING_EL | | |
| 110 | ALL_END_TAG_OPTIONAL_EL | | |
| 111 | 0b001 | |
| 112 | } | |
| 113 | ||
| 114 | sub MISC_SCOPING_EL () { SCOPING_EL | 0b000 } | |
| 115 | sub BUTTON_EL () { SCOPING_EL | 0b001 } | |
| 116 | sub CAPTION_EL () { SCOPING_EL | 0b010 } | |
| 117 | sub HTML_EL () { | |
| 118 | SCOPING_EL | | |
| 119 | TABLE_SCOPING_EL | | |
| 120 | TABLE_ROWS_SCOPING_EL | | |
| 121 | TABLE_ROW_SCOPING_EL | | |
| 122 | ALL_END_TAG_OPTIONAL_EL | | |
| 123 | 0b001 | |
| 124 | } | |
| 125 | sub TABLE_EL () { | |
| 126 | SCOPING_EL | | |
| 127 | TABLE_ROWS_EL | | |
| 128 | TABLE_SCOPING_EL | | |
| 129 | 0b001 | |
| 130 | } | |
| 131 | sub TABLE_CELL_EL () { | |
| 132 | SCOPING_EL | | |
| 133 | TABLE_ROW_SCOPING_EL | | |
| 134 | ALL_END_TAG_OPTIONAL_EL | | |
| 135 | 0b001 | |
| 136 | } | |
| 137 | ||
| 138 | sub MISC_FORMATTING_EL () { FORMATTING_EL | 0b000 } | |
| 139 | sub A_EL () { FORMATTING_EL | 0b001 } | |
| 140 | sub NOBR_EL () { FORMATTING_EL | 0b010 } | |
| 141 | ||
| 142 | sub RUBY_EL () { PHRASING_EL | 0b001 } | |
| 143 | ||
| 144 | ## ISSUE: ALL_END_TAG_OPTIONAL_EL? | |
| 145 | sub OPTGROUP_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b001 } | |
| 146 | sub OPTION_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b010 } | |
| 147 | sub RUBY_COMPONENT_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b100 } | |
| 148 | ||
| 149 | sub MML_AXML_EL () { PHRASING_EL | FOREIGN_EL | 0b001 } | |
| 150 | ||
| 151 | my $el_category = { | |
| 152 | a => A_EL, | |
| 153 | address => ADDRESS_DIV_EL, | |
| 154 | applet => MISC_SCOPING_EL, | |
| 155 | area => MISC_SPECIAL_EL, | |
| 156 | article => MISC_SPECIAL_EL, | |
| 157 | aside => MISC_SPECIAL_EL, | |
| 158 | b => FORMATTING_EL, | |
| 159 | base => MISC_SPECIAL_EL, | |
| 160 | basefont => MISC_SPECIAL_EL, | |
| 161 | bgsound => MISC_SPECIAL_EL, | |
| 162 | big => FORMATTING_EL, | |
| 163 | blockquote => MISC_SPECIAL_EL, | |
| 164 | body => BODY_EL, | |
| 165 | br => MISC_SPECIAL_EL, | |
| 166 | button => BUTTON_EL, | |
| 167 | caption => CAPTION_EL, | |
| 168 | center => MISC_SPECIAL_EL, | |
| 169 | col => MISC_SPECIAL_EL, | |
| 170 | colgroup => MISC_SPECIAL_EL, | |
| 171 | command => MISC_SPECIAL_EL, | |
| 172 | datagrid => MISC_SPECIAL_EL, | |
| 173 | dd => DTDD_EL, | |
| 174 | details => MISC_SPECIAL_EL, | |
| 175 | dialog => MISC_SPECIAL_EL, | |
| 176 | dir => MISC_SPECIAL_EL, | |
| 177 | div => ADDRESS_DIV_EL, | |
| 178 | dl => MISC_SPECIAL_EL, | |
| 179 | dt => DTDD_EL, | |
| 180 | em => FORMATTING_EL, | |
| 181 | embed => MISC_SPECIAL_EL, | |
| 182 | eventsource => MISC_SPECIAL_EL, | |
| 183 | fieldset => MISC_SPECIAL_EL, | |
| 184 | figure => MISC_SPECIAL_EL, | |
| 185 | font => FORMATTING_EL, | |
| 186 | footer => MISC_SPECIAL_EL, | |
| 187 | form => FORM_EL, | |
| 188 | frame => MISC_SPECIAL_EL, | |
| 189 | frameset => FRAMESET_EL, | |
| 190 | h1 => HEADING_EL, | |
| 191 | h2 => HEADING_EL, | |
| 192 | h3 => HEADING_EL, | |
| 193 | h4 => HEADING_EL, | |
| 194 | h5 => HEADING_EL, | |
| 195 | h6 => HEADING_EL, | |
| 196 | head => MISC_SPECIAL_EL, | |
| 197 | header => MISC_SPECIAL_EL, | |
| 198 | hr => MISC_SPECIAL_EL, | |
| 199 | html => HTML_EL, | |
| 200 | i => FORMATTING_EL, | |
| 201 | iframe => MISC_SPECIAL_EL, | |
| 202 | img => MISC_SPECIAL_EL, | |
| 203 | #image => MISC_SPECIAL_EL, ## NOTE: Commented out in the spec. | |
| 204 | input => MISC_SPECIAL_EL, | |
| 205 | isindex => MISC_SPECIAL_EL, | |
| 206 | li => LI_EL, | |
| 207 | link => MISC_SPECIAL_EL, | |
| 208 | listing => MISC_SPECIAL_EL, | |
| 209 | marquee => MISC_SCOPING_EL, | |
| 210 | menu => MISC_SPECIAL_EL, | |
| 211 | meta => MISC_SPECIAL_EL, | |
| 212 | nav => MISC_SPECIAL_EL, | |
| 213 | nobr => NOBR_EL, | |
| 214 | noembed => MISC_SPECIAL_EL, | |
| 215 | noframes => MISC_SPECIAL_EL, | |
| 216 | noscript => MISC_SPECIAL_EL, | |
| 217 | object => MISC_SCOPING_EL, | |
| 218 | ol => MISC_SPECIAL_EL, | |
| 219 | optgroup => OPTGROUP_EL, | |
| 220 | option => OPTION_EL, | |
| 221 | p => P_EL, | |
| 222 | param => MISC_SPECIAL_EL, | |
| 223 | plaintext => MISC_SPECIAL_EL, | |
| 224 | pre => MISC_SPECIAL_EL, | |
| 225 | rp => RUBY_COMPONENT_EL, | |
| 226 | rt => RUBY_COMPONENT_EL, | |
| 227 | ruby => RUBY_EL, | |
| 228 | s => FORMATTING_EL, | |
| 229 | script => MISC_SPECIAL_EL, | |
| 230 | select => SELECT_EL, | |
| 231 | section => MISC_SPECIAL_EL, | |
| 232 | small => FORMATTING_EL, | |
| 233 | spacer => MISC_SPECIAL_EL, | |
| 234 | strike => FORMATTING_EL, | |
| 235 | strong => FORMATTING_EL, | |
| 236 | style => MISC_SPECIAL_EL, | |
| 237 | table => TABLE_EL, | |
| 238 | tbody => TABLE_ROW_GROUP_EL, | |
| 239 | td => TABLE_CELL_EL, | |
| 240 | textarea => MISC_SPECIAL_EL, | |
| 241 | tfoot => TABLE_ROW_GROUP_EL, | |
| 242 | th => TABLE_CELL_EL, | |
| 243 | thead => TABLE_ROW_GROUP_EL, | |
| 244 | title => MISC_SPECIAL_EL, | |
| 245 | tr => TABLE_ROW_EL, | |
| 246 | tt => FORMATTING_EL, | |
| 247 | u => FORMATTING_EL, | |
| 248 | ul => MISC_SPECIAL_EL, | |
| 249 | wbr => MISC_SPECIAL_EL, | |
| 250 | }; | }; |
| 251 | ||
| 252 | my $entity_char = { | my $el_category_f = { |
| 253 | AElig => "\x{00C6}", | $MML_NS => { |
| 254 | Aacute => "\x{00C1}", | 'annotation-xml' => MML_AXML_EL, |
| 255 | Acirc => "\x{00C2}", | mi => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 256 | Agrave => "\x{00C0}", | mo => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 257 | Alpha => "\x{0391}", | mn => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 258 | Aring => "\x{00C5}", | ms => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 259 | Atilde => "\x{00C3}", | mtext => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 260 | Auml => "\x{00C4}", | }, |
| 261 | Beta => "\x{0392}", | $SVG_NS => { |
| 262 | Ccedil => "\x{00C7}", | foreignObject => SCOPING_EL | FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 263 | Chi => "\x{03A7}", | desc => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 264 | Dagger => "\x{2021}", | title => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 265 | Delta => "\x{0394}", | }, |
| 266 | 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}", |