/[suikacvs]/markup/html/whatpm/Whatpm/HTML.pm.src
Suika

Diff of /markup/html/whatpm/Whatpm/HTML.pm.src

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.141 by wakaba, Sat May 24 10:18:26 2008 UTC revision 1.146 by wakaba, Sat May 24 14:19:55 2008 UTC
# Line 8  use Error qw(:try); Line 8  use Error qw(:try);
8  ## doc.write ('');  ## doc.write ('');
9  ## alert (doc.compatMode);  ## alert (doc.compatMode);
10    
 ## TODO: 1252 parse error (revision 1264)  
 ## TODO: 8859-11 = 874 (revision 1271)  
   
11  require IO::Handle;  require IO::Handle;
12    
13  my $HTML_NS = q<http://www.w3.org/1999/xhtml>;  my $HTML_NS = q<http://www.w3.org/1999/xhtml>;
# Line 214  my $el_category_f = { Line 211  my $el_category_f = {
211  };  };
212    
213  my $svg_attr_name = {  my $svg_attr_name = {
214      attributename => 'attributeName',
215    attributetype => 'attributeType',    attributetype => 'attributeType',
216    basefrequency => 'baseFrequency',    basefrequency => 'baseFrequency',
217    baseprofile => 'baseProfile',    baseprofile => 'baseProfile',
# Line 224  my $svg_attr_name = { Line 222  my $svg_attr_name = {
222    diffuseconstant => 'diffuseConstant',    diffuseconstant => 'diffuseConstant',
223    edgemode => 'edgeMode',    edgemode => 'edgeMode',
224    externalresourcesrequired => 'externalResourcesRequired',    externalresourcesrequired => 'externalResourcesRequired',
   fecolormatrix => 'feColorMatrix',  
   fecomposite => 'feComposite',  
   fegaussianblur => 'feGaussianBlur',  
   femorphology => 'feMorphology',  
   fetile => 'feTile',  
225    filterres => 'filterRes',    filterres => 'filterRes',
226    filterunits => 'filterUnits',    filterunits => 'filterUnits',
227    glyphref => 'glyphRef',    glyphref => 'glyphRef',
# Line 262  my $svg_attr_name = { Line 255  my $svg_attr_name = {
255    repeatcount => 'repeatCount',    repeatcount => 'repeatCount',
256    repeatdur => 'repeatDur',    repeatdur => 'repeatDur',
257    requiredextensions => 'requiredExtensions',    requiredextensions => 'requiredExtensions',
258      requiredfeatures => 'requiredFeatures',
259    specularconstant => 'specularConstant',    specularconstant => 'specularConstant',
260    specularexponent => 'specularExponent',    specularexponent => 'specularExponent',
261    spreadmethod => 'spreadMethod',    spreadmethod => 'spreadMethod',
# Line 2739  sub _get_next_token ($) { Line 2733  sub _get_next_token ($) {
2733          redo A;          redo A;
2734        } elsif ($self->{next_char} == -1) {        } elsif ($self->{next_char} == -1) {
2735          !!!cp (217);          !!!cp (217);
         !!!parse-error (type => 'unclosed DOCTYPE');  
2736    
2737          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2738          ## reconsume          ## reconsume
# Line 3143  sub _tree_construction_initial ($) { Line 3136  sub _tree_construction_initial ($) {
3136        } elsif (defined $token->{public_identifier}) {        } elsif (defined $token->{public_identifier}) {
3137          my $pubid = $token->{public_identifier};          my $pubid = $token->{public_identifier};
3138          $pubid =~ tr/a-z/A-z/;          $pubid =~ tr/a-z/A-z/;
3139          if ({          my $prefix = [
3140            "+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1,            "+//SILMARIL//DTD HTML PRO V0R11 19970101//",
3141            "-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1,            "-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//",
3142            "-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1,            "-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//",
3143            "-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1,            "-//IETF//DTD HTML 2.0 LEVEL 1//",
3144            "-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1,            "-//IETF//DTD HTML 2.0 LEVEL 2//",
3145            "-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1,            "-//IETF//DTD HTML 2.0 STRICT LEVEL 1//",
3146            "-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1,            "-//IETF//DTD HTML 2.0 STRICT LEVEL 2//",
3147            "-//IETF//DTD HTML 2.0 STRICT//EN" => 1,            "-//IETF//DTD HTML 2.0 STRICT//",
3148            "-//IETF//DTD HTML 2.0//EN" => 1,            "-//IETF//DTD HTML 2.0//",
3149            "-//IETF//DTD HTML 2.1E//EN" => 1,            "-//IETF//DTD HTML 2.1E//",
3150            "-//IETF//DTD HTML 3.0//EN" => 1,            "-//IETF//DTD HTML 3.0//",
3151            "-//IETF//DTD HTML 3.0//EN//" => 1,            "-//IETF//DTD HTML 3.2 FINAL//",
3152            "-//IETF//DTD HTML 3.2 FINAL//EN" => 1,            "-//IETF//DTD HTML 3.2//",
3153            "-//IETF//DTD HTML 3.2//EN" => 1,            "-//IETF//DTD HTML 3//",
3154            "-//IETF//DTD HTML 3//EN" => 1,            "-//IETF//DTD HTML LEVEL 0//",
3155            "-//IETF//DTD HTML LEVEL 0//EN" => 1,            "-//IETF//DTD HTML LEVEL 1//",
3156            "-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1,            "-//IETF//DTD HTML LEVEL 2//",
3157            "-//IETF//DTD HTML LEVEL 1//EN" => 1,            "-//IETF//DTD HTML LEVEL 3//",
3158            "-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1,            "-//IETF//DTD HTML STRICT LEVEL 0//",
3159            "-//IETF//DTD HTML LEVEL 2//EN" => 1,            "-//IETF//DTD HTML STRICT LEVEL 1//",
3160            "-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1,            "-//IETF//DTD HTML STRICT LEVEL 2//",
3161            "-//IETF//DTD HTML LEVEL 3//EN" => 1,            "-//IETF//DTD HTML STRICT LEVEL 3//",
3162            "-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1,            "-//IETF//DTD HTML STRICT//",
3163            "-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1,            "-//IETF//DTD HTML//",
3164            "-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1,            "-//METRIUS//DTD METRIUS PRESENTATIONAL//",
3165            "-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1,            "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//",
3166            "-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1,            "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//",
3167            "-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1,            "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//",
3168            "-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1,            "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//",
3169            "-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1,            "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//",
3170            "-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1,            "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//",
3171            "-//IETF//DTD HTML STRICT//EN" => 1,            "-//NETSCAPE COMM. CORP.//DTD HTML//",
3172            "-//IETF//DTD HTML STRICT//EN//2.0" => 1,            "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//",
3173            "-//IETF//DTD HTML STRICT//EN//3.0" => 1,            "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//",
3174            "-//IETF//DTD HTML//EN" => 1,            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//",
3175            "-//IETF//DTD HTML//EN//2.0" => 1,            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//",
3176            "-//IETF//DTD HTML//EN//3.0" => 1,            "-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//",
3177            "-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1,            "-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//",
3178            "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1,            "-//SPYGLASS//DTD HTML 2.0 EXTENDED//",
3179            "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1,            "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//",
3180            "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1,            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//",
3181            "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1,            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//",
3182            "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1,            "-//W3C//DTD HTML 3 1995-03-24//",
3183            "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1,            "-//W3C//DTD HTML 3.2 DRAFT//",
3184            "-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1,            "-//W3C//DTD HTML 3.2 FINAL//",
3185            "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1,            "-//W3C//DTD HTML 3.2//",
3186            "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1,            "-//W3C//DTD HTML 3.2S DRAFT//",
3187            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1,            "-//W3C//DTD HTML 4.0 FRAMESET//",
3188            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1,            "-//W3C//DTD HTML 4.0 TRANSITIONAL//",
3189            "-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1,            "-//W3C//DTD HTML EXPERIMETNAL 19960712//",
3190            "-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1,            "-//W3C//DTD HTML EXPERIMENTAL 970421//",
3191            "-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1,            "-//W3C//DTD W3 HTML//",
3192            "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1,            "-//W3O//DTD W3 HTML 3.0//",
3193            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1,            "-//WEBTECHS//DTD MOZILLA HTML 2.0//",
3194            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1,            "-//WEBTECHS//DTD MOZILLA HTML//",
3195            "-//W3C//DTD HTML 3 1995-03-24//EN" => 1,          ]; # $prefix
3196            "-//W3C//DTD HTML 3.2 DRAFT//EN" => 1,          my $match;
3197            "-//W3C//DTD HTML 3.2 FINAL//EN" => 1,          for (@$prefix) {
3198            "-//W3C//DTD HTML 3.2//EN" => 1,            if (substr ($prefix, 0, length $_) eq $_) {
3199            "-//W3C//DTD HTML 3.2S DRAFT//EN" => 1,              $match = 1;
3200            "-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1,              last;
3201            "-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1,            }
3202            "-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1,          }
3203            "-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1,          if ($match or
3204            "-//W3C//DTD W3 HTML//EN" => 1,              $pubid eq "-//W3O//DTD W3 HTML STRICT 3.0//EN//" or
3205            "-//W3O//DTD W3 HTML 3.0//EN" => 1,              $pubid eq "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" or
3206            "-//W3O//DTD W3 HTML 3.0//EN//" => 1,              $pubid eq "HTML") {
           "-//W3O//DTD W3 HTML STRICT 3.0//EN//" => 1,  
           "-//WEBTECHS//DTD MOZILLA HTML 2.0//EN" => 1,  
           "-//WEBTECHS//DTD MOZILLA HTML//EN" => 1,  
           "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1,  
           "HTML" => 1,  
         }->{$pubid}) {  
3207            !!!cp ('t5');            !!!cp ('t5');
3208            $self->{document}->manakai_compat_mode ('quirks');            $self->{document}->manakai_compat_mode ('quirks');
3209          } elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or          } elsif ($pubid =~ m[^-//W3C//DTD HTML 4.01 FRAMESET//] or
3210                   $pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") {                   $pubid =~ m[^-//W3C//DTD HTML 4.01 TRANSITIONAL//]) {
3211            if (defined $token->{system_identifier}) {            if (defined $token->{system_identifier}) {
3212              !!!cp ('t6');              !!!cp ('t6');
3213              $self->{document}->manakai_compat_mode ('quirks');              $self->{document}->manakai_compat_mode ('quirks');
# Line 3228  sub _tree_construction_initial ($) { Line 3215  sub _tree_construction_initial ($) {
3215              !!!cp ('t7');              !!!cp ('t7');
3216              $self->{document}->manakai_compat_mode ('limited quirks');              $self->{document}->manakai_compat_mode ('limited quirks');
3217            }            }
3218          } elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or          } elsif ($pubid =~ m[^-//W3C//DTD XHTML 1.0 FRAMESET//] or
3219                   $pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") {                   $pubid =~ m[^-//W3C//DTD XHTML 1.0 TRANSITIONAL//]) {
3220            !!!cp ('t8');            !!!cp ('t8');
3221            $self->{document}->manakai_compat_mode ('limited quirks');            $self->{document}->manakai_compat_mode ('limited quirks');
3222          } else {          } else {
# Line 3242  sub _tree_construction_initial ($) { Line 3229  sub _tree_construction_initial ($) {
3229          my $sysid = $token->{system_identifier};          my $sysid = $token->{system_identifier};
3230          $sysid =~ tr/A-Z/a-z/;          $sysid =~ tr/A-Z/a-z/;
3231          if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") {          if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") {
3232            ## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)"            ## NOTE: Ensure that |PUBLIC "(limited quirks)" "(quirks)"| is
3233              ## marked as quirks.
3234            $self->{document}->manakai_compat_mode ('quirks');            $self->{document}->manakai_compat_mode ('quirks');
3235            !!!cp ('t11');            !!!cp ('t11');
3236          } else {          } else {
# Line 4033  sub _tree_construction_main ($) { Line 4021  sub _tree_construction_main ($) {
4021            #            #
4022          } elsif ({          } elsif ({
4023                    b => 1, big => 1, blockquote => 1, body => 1, br => 1,                    b => 1, big => 1, blockquote => 1, body => 1, br => 1,
4024                    center => 1, code => 1, dd => 1, div => 1, dl => 1, em => 1,                    center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1,
4025                    embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, ## No h4!                    em => 1, embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1,
4026                    h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, img => 1,                    h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1,
4027                    li => 1, menu => 1, meta => 1, nobr => 1, p => 1, pre => 1,                    img => 1, li => 1, listing => 1, menu => 1, meta => 1,
4028                    ruby => 1, s => 1, small => 1, span => 1, strong => 1,                    nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1,
4029                    sub => 1, sup => 1, table => 1, tt => 1, u => 1, ul => 1,                    small => 1, span => 1, strong => 1, strike => 1, sub => 1,
4030                    var => 1,                    sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1,
4031                   }->{$token->{tag_name}}) {                   }->{$token->{tag_name}}) {
4032            !!!cp ('t87.2');            !!!cp ('t87.2');
4033            !!!parse-error (type => 'not closed',            !!!parse-error (type => 'not closed',
# Line 4119  sub _tree_construction_main ($) { Line 4107  sub _tree_construction_main ($) {
4107          !!!cp ('t87.5');          !!!cp ('t87.5');
4108          #          #
4109        } elsif ($token->{type} == END_OF_FILE_TOKEN) {        } elsif ($token->{type} == END_OF_FILE_TOKEN) {
         ## NOTE: "using the rules for secondary insertion mode" then "continue"  
4110          !!!cp ('t87.6');          !!!cp ('t87.6');
4111          #          !!!parse-error (type => 'not closed',
4112          ## TODO: ...                          value => $self->{open_elements}->[-1]->[0]
4113                                ->manakai_local_name,
4114                            token => $token);
4115    
4116            pop @{$self->{open_elements}}
4117                while $self->{open_elements}->[-1]->[1] & FOREIGN_EL;
4118    
4119            $self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM;
4120            ## Reprocess.
4121            next B;
4122        } else {        } else {
4123          die "$0: $token->{type}: Unknown token type";                  die "$0: $token->{type}: Unknown token type";        
4124        }        }
# Line 4301  sub _tree_construction_main ($) { Line 4297  sub _tree_construction_main ($) {
4297                                                 ->{has_reference});                                                 ->{has_reference});
4298                  } elsif ($token->{attributes}->{content}) {                  } elsif ($token->{attributes}->{content}) {
4299                    if ($token->{attributes}->{content}->{value}                    if ($token->{attributes}->{content}->{value}
4300                        =~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt]                        =~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt]
4301                            [\x09-\x0D\x20]*=                            [\x09-\x0D\x20]*=
4302                            [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|                            [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|
4303                            ([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) {                            ([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) {
4304                      !!!cp ('t107');                      !!!cp ('t107');
4305                      ## NOTE: Whether the encoding is supported or not is handled                      ## NOTE: Whether the encoding is supported or not is handled
4306                      ## in the {change_encoding} callback.                      ## in the {change_encoding} callback.
# Line 5878  sub _tree_construction_main ($) { Line 5874  sub _tree_construction_main ($) {
5874            !!!nack ('t277.1');            !!!nack ('t277.1');
5875            !!!next-token;            !!!next-token;
5876            next B;            next B;
5877          } elsif ($token->{tag_name} eq 'select' or          } elsif ({
5878                   $token->{tag_name} eq 'input' or                     select => 1, input => 1, textarea => 1,
5879                     }->{$token->{tag_name}} or
5880                   ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and                   ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and
5881                    {                    {
5882                     caption => 1, table => 1,                     caption => 1, table => 1,
# Line 6364  sub _tree_construction_main ($) { Line 6361  sub _tree_construction_main ($) {
6361                                           ->{has_reference});                                           ->{has_reference});
6362            } elsif ($token->{attributes}->{content}) {            } elsif ($token->{attributes}->{content}) {
6363              if ($token->{attributes}->{content}->{value}              if ($token->{attributes}->{content}->{value}
6364                  =~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt]                  =~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt]
6365                      [\x09-\x0D\x20]*=                      [\x09-\x0D\x20]*=
6366                      [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|                      [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|
6367                      ([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) {                      ([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) {
6368                !!!cp ('t336');                !!!cp ('t336');
6369                ## NOTE: Whether the encoding is supported or not is handled                ## NOTE: Whether the encoding is supported or not is handled
6370                ## in the {change_encoding} callback.                ## in the {change_encoding} callback.

Legend:
Removed from v.1.141  
changed lines
  Added in v.1.146

[email protected]
ViewVC Help
Powered by ViewVC 1.1.24