/[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 1.11 by wakaba, Sat Jun 23 03:53:35 2007 UTC revision 1.18 by wakaba, Sat Jun 23 12:21:01 2007 UTC
# Line 2  package Whatpm::HTML; Line 2  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    
5  ## This is an early version of an HTML parser.  ## ISSUE:
6    ## var doc = implementation.createDocument (null, null, null);
7    ## doc.write ('');
8    ## alert (doc.compatMode);
9    
10  my $permitted_slash_tag_name = {  my $permitted_slash_tag_name = {
11    base => 1,    base => 1,
# Line 18  my $permitted_slash_tag_name = { Line 21  my $permitted_slash_tag_name = {
21    input => 1,    input => 1,
22  };  };
23    
 my $entity_char = {  
   AElig => "\x{00C6}",  
   Aacute => "\x{00C1}",  
   Acirc => "\x{00C2}",  
   Agrave => "\x{00C0}",  
   Alpha => "\x{0391}",  
   Aring => "\x{00C5}",  
   Atilde => "\x{00C3}",  
   Auml => "\x{00C4}",  
   Beta => "\x{0392}",  
   Ccedil => "\x{00C7}",  
   Chi => "\x{03A7}",  
   Dagger => "\x{2021}",  
   Delta => "\x{0394}",  
   ETH => "\x{00D0}",  
   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}",  
 }; # $entity_char  
   
24  my $c1_entity_char = {  my $c1_entity_char = {
25    0x80 => 0x20AC,    0x80 => 0x20AC,
26    0x81 => 0xFFFD,    0x81 => 0xFFFD,
# Line 349  sub parse_string ($$$;$) { Line 90  sub parse_string ($$$;$) {
90    my $column = 0;    my $column = 0;
91    $self->{set_next_input_character} = sub {    $self->{set_next_input_character} = sub {
92      my $self = shift;      my $self = shift;
93    
94        pop @{$self->{prev_input_character}};
95        unshift @{$self->{prev_input_character}}, $self->{next_input_character};
96    
97      $self->{next_input_character} = -1 and return if $i >= length $$s;      $self->{next_input_character} = -1 and return if $i >= length $$s;
98      $self->{next_input_character} = ord substr $$s, $i++, 1;      $self->{next_input_character} = ord substr $$s, $i++, 1;
99      $column++;      $column++;
# Line 357  sub parse_string ($$$;$) { Line 102  sub parse_string ($$$;$) {
102        $line++;        $line++;
103        $column = 0;        $column = 0;
104      } elsif ($self->{next_input_character} == 0x000D) { # CR      } elsif ($self->{next_input_character} == 0x000D) { # CR
105        if ($i >= length $$s) {        $i++ if substr ($$s, $i, 1) eq "\x0A";
         #  
       } else {  
         my $next_char = ord substr $$s, $i++, 1;  
         if ($next_char == 0x000A) { # LF  
           #  
         } else {  
           push @{$self->{char}}, $next_char;  
         }  
       }  
106        $self->{next_input_character} = 0x000A; # LF # MUST        $self->{next_input_character} = 0x000A; # LF # MUST
107        $line++;        $line++;
108        $column = 0;        $column = 0;
# Line 377  sub parse_string ($$$;$) { Line 113  sub parse_string ($$$;$) {
113        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
114      }      }
115    };    };
116      $self->{prev_input_character} = [-1, -1, -1];
117      $self->{next_input_character} = -1;
118    
119    my $onerror = $_[2] || sub {    my $onerror = $_[2] || sub {
120      my (%opt) = @_;      my (%opt) = @_;
# Line 420  sub _initialize_tokenizer ($) { Line 158  sub _initialize_tokenizer ($) {
158    # $self->{next_input_character}    # $self->{next_input_character}
159    !!!next-input-character;    !!!next-input-character;
160    $self->{token} = [];    $self->{token} = [];
161      # $self->{escape}
162  } # _initialize_tokenizer  } # _initialize_tokenizer
163    
164  ## A token has:  ## A token has:
165  ##   ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment',  ##   ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment',
166  ##       'character', or 'end-of-file'  ##       'character', or 'end-of-file'
167  ##   ->{name} (DOCTYPE, start tag (tagname), end tag (tagname))  ##   ->{name} (DOCTYPE, start tag (tag name), end tag (tag name))
168      ## ISSUE: the spec need s/tagname/tag name/  ##   ->{public_identifier} (DOCTYPE)
169  ##   ->{error} == 1 or 0 (DOCTYPE)  ##   ->{system_identifier} (DOCTYPE)
170    ##   ->{correct} == 1 or 0 (DOCTYPE)
171  ##   ->{attributes} isa HASH (start tag, end tag)  ##   ->{attributes} isa HASH (start tag, end tag)
172  ##   ->{data} (comment, character)  ##   ->{data} (comment, character)
173    
 ## Macros  
 ##   Macros MUST be preceded by three EXCLAMATION MARKs.  
 ##   emit ($token)  
 ##     Emits the specified token.  
   
174  ## Emitted token MUST immediately be handled by the tree construction state.  ## Emitted token MUST immediately be handled by the tree construction state.
175    
176  ## Before each step, UA MAY check to see if either one of the scripts in  ## Before each step, UA MAY check to see if either one of the scripts in
# Line 461  sub _get_next_token ($) { Line 196  sub _get_next_token ($) {
196          } else {          } else {
197            #            #
198          }          }
199          } elsif ($self->{next_input_character} == 0x002D) { # -
200            if ($self->{content_model_flag} eq 'RCDATA' or
201                $self->{content_model_flag} eq 'CDATA') {
202              unless ($self->{escape}) {
203                if ($self->{prev_input_character}->[0] == 0x002D and # -
204                    $self->{prev_input_character}->[1] == 0x0021 and # !
205                    $self->{prev_input_character}->[2] == 0x003C) { # <
206                  $self->{escape} = 1;
207                }
208              }
209            }
210            
211            #
212        } elsif ($self->{next_input_character} == 0x003C) { # <        } elsif ($self->{next_input_character} == 0x003C) { # <
213          if ($self->{content_model_flag} ne 'PLAINTEXT') {          if ($self->{content_model_flag} eq 'PCDATA' or
214                (($self->{content_model_flag} eq 'CDATA' or
215                  $self->{content_model_flag} eq 'RCDATA') and
216                 not $self->{escape})) {
217            $self->{state} = 'tag open';            $self->{state} = 'tag open';
218            !!!next-input-character;            !!!next-input-character;
219            redo A;            redo A;
220          } else {          } else {
221            #            #
222          }          }
223          } elsif ($self->{next_input_character} == 0x003E) { # >
224            if ($self->{escape} and
225                ($self->{content_model_flag} eq 'RCDATA' or
226                 $self->{content_model_flag} eq 'CDATA')) {
227              if ($self->{prev_input_character}->[0] == 0x002D and # -
228                  $self->{prev_input_character}->[1] == 0x002D) { # -
229                delete $self->{escape};
230              }
231            }
232            
233            #
234        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_input_character} == -1) {
235          !!!emit ({type => 'end-of-file'});          !!!emit ({type => 'end-of-file'});
236          last A; ## TODO: ok?          last A; ## TODO: ok?
# Line 592  sub _get_next_token ($) { Line 354  sub _get_next_token ($) {
354                  $self->{next_input_character} == 0x0020 or # SP                  $self->{next_input_character} == 0x0020 or # SP
355                  $self->{next_input_character} == 0x003E or # >                  $self->{next_input_character} == 0x003E or # >
356                  $self->{next_input_character} == 0x002F or # /                  $self->{next_input_character} == 0x002F or # /
                 $self->{next_input_character} == 0x003C or # <  
357                  $self->{next_input_character} == -1) {                  $self->{next_input_character} == -1) {
358            !!!parse-error (type => 'unmatched end tag');            !!!parse-error (type => 'unmatched end tag');
359            $self->{next_input_character} = shift @next_char; # reconsume            $self->{next_input_character} = shift @next_char; # reconsume
# Line 676  sub _get_next_token ($) { Line 437  sub _get_next_token ($) {
437          ## Stay in this state          ## Stay in this state
438          !!!next-input-character;          !!!next-input-character;
439          redo A;          redo A;
440        } elsif ($self->{next_input_character} == 0x003C or # <        } elsif ($self->{next_input_character} == -1) {
                $self->{next_input_character} == -1) {  
441          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
442          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} eq 'start tag') {
443            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
# Line 763  sub _get_next_token ($) { Line 523  sub _get_next_token ($) {
523          ## Stay in the state          ## Stay in the state
524          # next-input-character is already done          # next-input-character is already done
525          redo A;          redo A;
526        } elsif ($self->{next_input_character} == 0x003C or # <        } elsif ($self->{next_input_character} == -1) {
                $self->{next_input_character} == -1) {  
527          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
528          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} eq 'start tag') {
529            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
# Line 855  sub _get_next_token ($) { Line 614  sub _get_next_token ($) {
614          $self->{state} = 'before attribute name';          $self->{state} = 'before attribute name';
615          # next-input-character is already done          # next-input-character is already done
616          redo A;          redo A;
617        } elsif ($self->{next_input_character} == 0x003C or # <        } elsif ($self->{next_input_character} == -1) {
                $self->{next_input_character} == -1) {  
618          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
619          $before_leave->();          $before_leave->();
620          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} eq 'start tag') {
# Line 933  sub _get_next_token ($) { Line 691  sub _get_next_token ($) {
691          $self->{state} = 'before attribute name';          $self->{state} = 'before attribute name';
692          # next-input-character is already done          # next-input-character is already done
693          redo A;          redo A;
694        } elsif ($self->{next_input_character} == 0x003C or # <        } elsif ($self->{next_input_character} == -1) {
                $self->{next_input_character} == -1) {  
695          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
696          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} eq 'start tag') {
697            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
# Line 999  sub _get_next_token ($) { Line 756  sub _get_next_token ($) {
756          undef $self->{current_token};          undef $self->{current_token};
757    
758          redo A;          redo A;
759        } elsif ($self->{next_input_character} == 0x003C or # <        } elsif ($self->{next_input_character} == -1) {
                $self->{next_input_character} == -1) {  
760          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
761          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} eq 'start tag') {
762            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
# Line 1127  sub _get_next_token ($) { Line 883  sub _get_next_token ($) {
883          undef $self->{current_token};          undef $self->{current_token};
884    
885          redo A;          redo A;
886        } elsif ($self->{next_input_character} == 0x003C or # <        } elsif ($self->{next_input_character} == -1) {
                $self->{next_input_character} == -1) {  
887          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
888          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} eq 'start tag') {
889            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
# Line 1348  sub _get_next_token ($) { Line 1103  sub _get_next_token ($) {
1103          ## Stay in the state          ## Stay in the state
1104          !!!next-input-character;          !!!next-input-character;
1105          redo A;          redo A;
       } elsif (0x0061 <= $self->{next_input_character} and  
                $self->{next_input_character} <= 0x007A) { # a..z  
 ## ISSUE: "Set the token's name name to the" in the spec  
         $self->{current_token} = {type => 'DOCTYPE',  
                           name => chr ($self->{next_input_character} - 0x0020),  
                           error => 1};  
         $self->{state} = 'DOCTYPE name';  
         !!!next-input-character;  
         redo A;  
1106        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_input_character} == 0x003E) { # >
1107          !!!parse-error (type => 'no DOCTYPE name');          !!!parse-error (type => 'no DOCTYPE name');
1108          $self->{state} = 'data';          $self->{state} = 'data';
1109          !!!next-input-character;          !!!next-input-character;
1110    
1111          !!!emit ({type => 'DOCTYPE', name => '', error => 1});          !!!emit ({type => 'DOCTYPE'}); # incorrect
1112    
1113          redo A;          redo A;
1114        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_input_character} == -1) {
# Line 1370  sub _get_next_token ($) { Line 1116  sub _get_next_token ($) {
1116          $self->{state} = 'data';          $self->{state} = 'data';
1117          ## reconsume          ## reconsume
1118    
1119          !!!emit ({type => 'DOCTYPE', name => '', error => 1});          !!!emit ({type => 'DOCTYPE'}); # incorrect
1120    
1121          redo A;          redo A;
1122        } else {        } else {
1123          $self->{current_token} = {type => 'DOCTYPE',          $self->{current_token}
1124                            name => chr ($self->{next_input_character}),              = {type => 'DOCTYPE',
1125                            error => 1};                 name => chr ($self->{next_input_character}),
1126                   correct => 1};
1127  ## ISSUE: "Set the token's name name to the" in the spec  ## ISSUE: "Set the token's name name to the" in the spec
1128          $self->{state} = 'DOCTYPE name';          $self->{state} = 'DOCTYPE name';
1129          !!!next-input-character;          !!!next-input-character;
1130          redo A;          redo A;
1131        }        }
1132      } elsif ($self->{state} eq 'DOCTYPE name') {      } elsif ($self->{state} eq 'DOCTYPE name') {
1133    ## ISSUE: Redundant "First," in the spec.
1134        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_input_character} == 0x0009 or # HT
1135            $self->{next_input_character} == 0x000A or # LF            $self->{next_input_character} == 0x000A or # LF
1136            $self->{next_input_character} == 0x000B or # VT            $self->{next_input_character} == 0x000B or # VT
1137            $self->{next_input_character} == 0x000C or # FF            $self->{next_input_character} == 0x000C or # FF
1138            $self->{next_input_character} == 0x0020) { # SP            $self->{next_input_character} == 0x0020) { # SP
         $self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); # DOCTYPE  
1139          $self->{state} = 'after DOCTYPE name';          $self->{state} = 'after DOCTYPE name';
1140          !!!next-input-character;          !!!next-input-character;
1141          redo A;          redo A;
1142        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_input_character} == 0x003E) { # >
         $self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); # DOCTYPE  
1143          $self->{state} = 'data';          $self->{state} = 'data';
1144          !!!next-input-character;          !!!next-input-character;
1145    
# Line 1401  sub _get_next_token ($) { Line 1147  sub _get_next_token ($) {
1147          undef $self->{current_token};          undef $self->{current_token};
1148    
1149          redo A;          redo A;
       } elsif (0x0061 <= $self->{next_input_character} and  
                $self->{next_input_character} <= 0x007A) { # a..z  
         $self->{current_token}->{name} .= chr ($self->{next_input_character} - 0x0020); # DOCTYPE  
         #$self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML');  
         ## Stay in the state  
         !!!next-input-character;  
         redo A;  
1150        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_input_character} == -1) {
1151          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
         $self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); # DOCTYPE  
1152          $self->{state} = 'data';          $self->{state} = 'data';
1153          ## reconsume          ## reconsume
1154    
1155          !!!emit ($self->{current_token});          delete $self->{current_token}->{correct};
1156            !!!emit ($self->{current_token}); # DOCTYPE
1157          undef $self->{current_token};          undef $self->{current_token};
1158    
1159          redo A;          redo A;
1160        } else {        } else {
1161          $self->{current_token}->{name}          $self->{current_token}->{name}
1162            .= chr ($self->{next_input_character}); # DOCTYPE            .= chr ($self->{next_input_character}); # DOCTYPE
         #$self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML');  
1163          ## Stay in the state          ## Stay in the state
1164          !!!next-input-character;          !!!next-input-character;
1165          redo A;          redo A;
# Line 1448  sub _get_next_token ($) { Line 1186  sub _get_next_token ($) {
1186          $self->{state} = 'data';          $self->{state} = 'data';
1187          ## reconsume          ## reconsume
1188    
1189            delete $self->{current_token}->{correct};
1190            !!!emit ($self->{current_token}); # DOCTYPE
1191            undef $self->{current_token};
1192    
1193            redo A;
1194          } elsif ($self->{next_input_character} == 0x0050 or # P
1195                   $self->{next_input_character} == 0x0070) { # p
1196            !!!next-input-character;
1197            if ($self->{next_input_character} == 0x0055 or # U
1198                $self->{next_input_character} == 0x0075) { # u
1199              !!!next-input-character;
1200              if ($self->{next_input_character} == 0x0042 or # B
1201                  $self->{next_input_character} == 0x0062) { # b
1202                !!!next-input-character;
1203                if ($self->{next_input_character} == 0x004C or # L
1204                    $self->{next_input_character} == 0x006C) { # l
1205                  !!!next-input-character;
1206                  if ($self->{next_input_character} == 0x0049 or # I
1207                      $self->{next_input_character} == 0x0069) { # i
1208                    !!!next-input-character;
1209                    if ($self->{next_input_character} == 0x0043 or # C
1210                        $self->{next_input_character} == 0x0063) { # c
1211                      $self->{state} = 'before DOCTYPE public identifier';
1212                      !!!next-input-character;
1213                      redo A;
1214                    }
1215                  }
1216                }
1217              }
1218            }
1219    
1220            #
1221          } elsif ($self->{next_input_character} == 0x0053 or # S
1222                   $self->{next_input_character} == 0x0073) { # s
1223            !!!next-input-character;
1224            if ($self->{next_input_character} == 0x0059 or # Y
1225                $self->{next_input_character} == 0x0079) { # y
1226              !!!next-input-character;
1227              if ($self->{next_input_character} == 0x0053 or # S
1228                  $self->{next_input_character} == 0x0073) { # s
1229                !!!next-input-character;
1230                if ($self->{next_input_character} == 0x0054 or # T
1231                    $self->{next_input_character} == 0x0074) { # t
1232                  !!!next-input-character;
1233                  if ($self->{next_input_character} == 0x0045 or # E
1234                      $self->{next_input_character} == 0x0065) { # e
1235                    !!!next-input-character;
1236                    if ($self->{next_input_character} == 0x004D or # M
1237                        $self->{next_input_character} == 0x006D) { # m
1238                      $self->{state} = 'before DOCTYPE system identifier';
1239                      !!!next-input-character;
1240                      redo A;
1241                    }
1242                  }
1243                }
1244              }
1245            }
1246    
1247            #
1248          } else {
1249            !!!next-input-character;
1250            #
1251          }
1252    
1253          !!!parse-error (type => 'string after DOCTYPE name');
1254          $self->{state} = 'bogus DOCTYPE';
1255          # next-input-character is already done
1256          redo A;
1257        } elsif ($self->{state} eq 'before DOCTYPE public identifier') {
1258          if ({
1259                0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
1260                #0x000D => 1, # HT, LF, VT, FF, SP, CR
1261              }->{$self->{next_input_character}}) {
1262            ## Stay in the state
1263            !!!next-input-character;
1264            redo A;
1265          } elsif ($self->{next_input_character} eq 0x0022) { # "
1266            $self->{current_token}->{public_identifier} = ''; # DOCTYPE
1267            $self->{state} = 'DOCTYPE public identifier (double-quoted)';
1268            !!!next-input-character;
1269            redo A;
1270          } elsif ($self->{next_input_character} eq 0x0027) { # '
1271            $self->{current_token}->{public_identifier} = ''; # DOCTYPE
1272            $self->{state} = 'DOCTYPE public identifier (single-quoted)';
1273            !!!next-input-character;
1274            redo A;
1275          } elsif ($self->{next_input_character} eq 0x003E) { # >
1276            !!!parse-error (type => 'no PUBLIC literal');
1277    
1278            $self->{state} = 'data';
1279            !!!next-input-character;
1280    
1281            delete $self->{current_token}->{correct};
1282            !!!emit ($self->{current_token}); # DOCTYPE
1283            undef $self->{current_token};
1284    
1285            redo A;
1286          } elsif ($self->{next_input_character} == -1) {
1287            !!!parse-error (type => 'unclosed DOCTYPE');
1288    
1289            $self->{state} = 'data';
1290            ## reconsume
1291    
1292            delete $self->{current_token}->{correct};
1293            !!!emit ($self->{current_token}); # DOCTYPE
1294            undef $self->{current_token};
1295    
1296            redo A;
1297          } else {
1298            !!!parse-error (type => 'string after PUBLIC');
1299            $self->{state} = 'bogus DOCTYPE';
1300            !!!next-input-character;
1301            redo A;
1302          }
1303        } elsif ($self->{state} eq 'DOCTYPE public identifier (double-quoted)') {
1304          if ($self->{next_input_character} == 0x0022) { # "
1305            $self->{state} = 'after DOCTYPE public identifier';
1306            !!!next-input-character;
1307            redo A;
1308          } elsif ($self->{next_input_character} == -1) {
1309            !!!parse-error (type => 'unclosed PUBLIC literal');
1310    
1311            $self->{state} = 'data';
1312            ## reconsume
1313    
1314            delete $self->{current_token}->{correct};
1315            !!!emit ($self->{current_token}); # DOCTYPE
1316            undef $self->{current_token};
1317    
1318            redo A;
1319          } else {
1320            $self->{current_token}->{public_identifier} # DOCTYPE
1321                .= chr $self->{next_input_character};
1322            ## Stay in the state
1323            !!!next-input-character;
1324            redo A;
1325          }
1326        } elsif ($self->{state} eq 'DOCTYPE public identifier (single-quoted)') {
1327          if ($self->{next_input_character} == 0x0027) { # '
1328            $self->{state} = 'after DOCTYPE public identifier';
1329            !!!next-input-character;
1330            redo A;
1331          } elsif ($self->{next_input_character} == -1) {
1332            !!!parse-error (type => 'unclosed PUBLIC literal');
1333    
1334            $self->{state} = 'data';
1335            ## reconsume
1336    
1337            delete $self->{current_token}->{correct};
1338            !!!emit ($self->{current_token}); # DOCTYPE
1339            undef $self->{current_token};
1340    
1341            redo A;
1342          } else {
1343            $self->{current_token}->{public_identifier} # DOCTYPE
1344                .= chr $self->{next_input_character};
1345            ## Stay in the state
1346            !!!next-input-character;
1347            redo A;
1348          }
1349        } elsif ($self->{state} eq 'after DOCTYPE public identifier') {
1350          if ({
1351                0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
1352                #0x000D => 1, # HT, LF, VT, FF, SP, CR
1353              }->{$self->{next_input_character}}) {
1354            ## Stay in the state
1355            !!!next-input-character;
1356            redo A;
1357          } elsif ($self->{next_input_character} == 0x0022) { # "
1358            $self->{current_token}->{system_identifier} = ''; # DOCTYPE
1359            $self->{state} = 'DOCTYPE system identifier (double-quoted)';
1360            !!!next-input-character;
1361            redo A;
1362          } elsif ($self->{next_input_character} == 0x0027) { # '
1363            $self->{current_token}->{system_identifier} = ''; # DOCTYPE
1364            $self->{state} = 'DOCTYPE system identifier (single-quoted)';
1365            !!!next-input-character;
1366            redo A;
1367          } elsif ($self->{next_input_character} == 0x003E) { # >
1368            $self->{state} = 'data';
1369            !!!next-input-character;
1370    
1371            !!!emit ($self->{current_token}); # DOCTYPE
1372            undef $self->{current_token};
1373    
1374            redo A;
1375          } elsif ($self->{next_input_character} == -1) {
1376            !!!parse-error (type => 'unclosed DOCTYPE');
1377    
1378            $self->{state} = 'data';
1379            ## recomsume
1380    
1381            delete $self->{current_token}->{correct};
1382            !!!emit ($self->{current_token}); # DOCTYPE
1383            undef $self->{current_token};
1384    
1385            redo A;
1386          } else {
1387            !!!parse-error (type => 'string after PUBLIC literal');
1388            $self->{state} = 'bogus DOCTYPE';
1389            !!!next-input-character;
1390            redo A;
1391          }
1392        } elsif ($self->{state} eq 'before DOCTYPE system identifier') {
1393          if ({
1394                0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
1395                #0x000D => 1, # HT, LF, VT, FF, SP, CR
1396              }->{$self->{next_input_character}}) {
1397            ## Stay in the state
1398            !!!next-input-character;
1399            redo A;
1400          } elsif ($self->{next_input_character} == 0x0022) { # "
1401            $self->{current_token}->{system_identifier} = ''; # DOCTYPE
1402            $self->{state} = 'DOCTYPE system identifier (double-quoted)';
1403            !!!next-input-character;
1404            redo A;
1405          } elsif ($self->{next_input_character} == 0x0027) { # '
1406            $self->{current_token}->{system_identifier} = ''; # DOCTYPE
1407            $self->{state} = 'DOCTYPE system identifier (single-quoted)';
1408            !!!next-input-character;
1409            redo A;
1410          } elsif ($self->{next_input_character} == 0x003E) { # >
1411            !!!parse-error (type => 'no SYSTEM literal');
1412            $self->{state} = 'data';
1413            !!!next-input-character;
1414    
1415            delete $self->{current_token}->{correct};
1416            !!!emit ($self->{current_token}); # DOCTYPE
1417            undef $self->{current_token};
1418    
1419            redo A;
1420          } elsif ($self->{next_input_character} == -1) {
1421            !!!parse-error (type => 'unclosed DOCTYPE');
1422    
1423            $self->{state} = 'data';
1424            ## recomsume
1425    
1426            delete $self->{current_token}->{correct};
1427            !!!emit ($self->{current_token}); # DOCTYPE
1428            undef $self->{current_token};
1429    
1430            redo A;
1431          } else {
1432            !!!parse-error (type => 'string after PUBLIC literal');
1433            $self->{state} = 'bogus DOCTYPE';
1434            !!!next-input-character;
1435            redo A;
1436          }
1437        } elsif ($self->{state} eq 'DOCTYPE system identifier (double-quoted)') {
1438          if ($self->{next_input_character} == 0x0022) { # "
1439            $self->{state} = 'after DOCTYPE system identifier';
1440            !!!next-input-character;
1441            redo A;
1442          } elsif ($self->{next_input_character} == -1) {
1443            !!!parse-error (type => 'unclosed SYSTEM literal');
1444    
1445            $self->{state} = 'data';
1446            ## reconsume
1447    
1448            delete $self->{current_token}->{correct};
1449          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1450          undef $self->{current_token};          undef $self->{current_token};
1451    
1452          redo A;          redo A;
1453        } else {        } else {
1454          !!!parse-error (type => 'string after DOCTYPE name');          $self->{current_token}->{system_identifier} # DOCTYPE
1455          $self->{current_token}->{error} = 1; # DOCTYPE              .= chr $self->{next_input_character};
1456            ## Stay in the state
1457            !!!next-input-character;
1458            redo A;
1459          }
1460        } elsif ($self->{state} eq 'DOCTYPE system identifier (single-quoted)') {
1461          if ($self->{next_input_character} == 0x0027) { # '
1462            $self->{state} = 'after DOCTYPE system identifier';
1463            !!!next-input-character;
1464            redo A;
1465          } elsif ($self->{next_input_character} == -1) {
1466            !!!parse-error (type => 'unclosed SYSTEM literal');
1467    
1468            $self->{state} = 'data';
1469            ## reconsume
1470    
1471            delete $self->{current_token}->{correct};
1472            !!!emit ($self->{current_token}); # DOCTYPE
1473            undef $self->{current_token};
1474    
1475            redo A;
1476          } else {
1477            $self->{current_token}->{system_identifier} # DOCTYPE
1478                .= chr $self->{next_input_character};
1479            ## Stay in the state
1480            !!!next-input-character;
1481            redo A;
1482          }
1483        } elsif ($self->{state} eq 'after DOCTYPE system identifier') {
1484          if ({
1485                0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
1486                #0x000D => 1, # HT, LF, VT, FF, SP, CR
1487              }->{$self->{next_input_character}}) {
1488            ## Stay in the state
1489            !!!next-input-character;
1490            redo A;
1491          } elsif ($self->{next_input_character} == 0x003E) { # >
1492            $self->{state} = 'data';
1493            !!!next-input-character;
1494    
1495            !!!emit ($self->{current_token}); # DOCTYPE
1496            undef $self->{current_token};
1497    
1498            redo A;
1499          } elsif ($self->{next_input_character} == -1) {
1500            !!!parse-error (type => 'unclosed DOCTYPE');
1501    
1502            $self->{state} = 'data';
1503            ## recomsume
1504    
1505            delete $self->{current_token}->{correct};
1506            !!!emit ($self->{current_token}); # DOCTYPE
1507            undef $self->{current_token};
1508    
1509            redo A;
1510          } else {
1511            !!!parse-error (type => 'string after SYSTEM literal');
1512          $self->{state} = 'bogus DOCTYPE';          $self->{state} = 'bogus DOCTYPE';
1513          !!!next-input-character;          !!!next-input-character;
1514          redo A;          redo A;
# Line 1464  sub _get_next_token ($) { Line 1518  sub _get_next_token ($) {
1518          $self->{state} = 'data';          $self->{state} = 'data';
1519          !!!next-input-character;          !!!next-input-character;
1520    
1521            delete $self->{current_token}->{correct};
1522          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1523          undef $self->{current_token};          undef $self->{current_token};
1524    
# Line 1473  sub _get_next_token ($) { Line 1528  sub _get_next_token ($) {
1528          $self->{state} = 'data';          $self->{state} = 'data';
1529          ## reconsume          ## reconsume
1530    
1531            delete $self->{current_token}->{correct};
1532          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1533          undef $self->{current_token};          undef $self->{current_token};
1534    
# Line 1588  sub _tokenize_attempt_to_consume_an_enti Line 1644  sub _tokenize_attempt_to_consume_an_enti
1644    
1645      my $value = $entity_name;      my $value = $entity_name;
1646      my $match;      my $match;
1647        require Whatpm::_NamedEntityList;
1648        our $EntityChar;
1649    
1650      while (length $entity_name < 10 and      while (length $entity_name < 10 and
1651             ## NOTE: Some number greater than the maximum length of entity name             ## NOTE: Some number greater than the maximum length of entity name
1652             ((0x0041 <= $self->{next_input_character} and             ((0x0041 <= $self->{next_input_character} and # a
1653               $self->{next_input_character} <= 0x005A) or               $self->{next_input_character} <= 0x005A) or # x
1654              (0x0061 <= $self->{next_input_character} and              (0x0061 <= $self->{next_input_character} and # a
1655               $self->{next_input_character} <= 0x007A) or               $self->{next_input_character} <= 0x007A) or # z
1656              (0x0030 <= $self->{next_input_character} and              (0x0030 <= $self->{next_input_character} and # 0
1657               $self->{next_input_character} <= 0x0039))) {               $self->{next_input_character} <= 0x0039) or # 9
1658                $self->{next_input_character} == 0x003B)) { # ;
1659        $entity_name .= chr $self->{next_input_character};        $entity_name .= chr $self->{next_input_character};
1660        if (defined $entity_char->{$entity_name}) {        if (defined $EntityChar->{$entity_name}) {
1661          $value = $entity_char->{$entity_name};          $value = $EntityChar->{$entity_name};
1662          $match = 1;          if ($self->{next_input_character} == 0x003B) { # ;
1663              $match = 1;
1664              !!!next-input-character;
1665              last;
1666            } else {
1667              $match = -1;
1668            }
1669        } else {        } else {
1670          $value .= chr $self->{next_input_character};          $value .= chr $self->{next_input_character};
1671        }        }
1672        !!!next-input-character;        !!!next-input-character;
1673      }      }
1674            
1675      if ($match) {      if ($match > 0) {
1676        if ($self->{next_input_character} == 0x003B) { # ;        return {type => 'character', data => $value};
1677          !!!next-input-character;      } elsif ($match < 0) {
1678        } else {        !!!parse-error (type => 'refc');
         !!!parse-error (type => 'refc');  
       }  
   
1679        return {type => 'character', data => $value};        return {type => 'character', data => $value};
1680      } else {      } else {
1681        !!!parse-error (type => 'bare ero');        !!!parse-error (type => 'bare ero');
# Line 1634  sub _initialize_tree_constructor ($) { Line 1696  sub _initialize_tree_constructor ($) {
1696    $self->{document}->strict_error_checking (0);    $self->{document}->strict_error_checking (0);
1697    ## TODO: Turn mutation events off # MUST    ## TODO: Turn mutation events off # MUST
1698    ## TODO: Turn loose Document option (manakai extension) on    ## TODO: Turn loose Document option (manakai extension) on
1699    ## TODO: Mark the Document as an HTML document # MUST    $self->{document}->manakai_is_html (1); # MUST
1700  } # _initialize_tree_constructor  } # _initialize_tree_constructor
1701    
1702  sub _terminate_tree_constructor ($) {  sub _terminate_tree_constructor ($) {
# Line 1674  sub _construct_tree ($) { Line 1736  sub _construct_tree ($) {
1736    
1737  sub _tree_construction_initial ($) {  sub _tree_construction_initial ($) {
1738    my $self = shift;    my $self = shift;
1739    B: {    INITIAL: {
1740        if ($token->{type} eq 'DOCTYPE') {      if ($token->{type} eq 'DOCTYPE') {
1741          if ($token->{error}) {        ## NOTE: Conformance checkers MAY, instead of reporting "not HTML5"
1742            ## ISSUE: Spec currently left this case undefined.        ## error, switch to a conformance checking mode for another
1743            !!!parse-error (type => 'bogus DOCTYPE');        ## language.
1744          }        my $doctype_name = $token->{name};
1745          my $doctype = $self->{document}->create_document_type_definition        $doctype_name = '' unless defined $doctype_name;
1746            ($token->{name});        $doctype_name =~ tr/a-z/A-Z/;
1747          $self->{document}->append_child ($doctype);        if (not defined $token->{name} or # <!DOCTYPE>
1748          #$phase = 'root element';            defined $token->{public_identifier} or
1749          !!!next-token;            defined $token->{system_identifier}) {
1750          #redo B;          !!!parse-error (type => 'not HTML5');
1751          return;        } elsif ($doctype_name ne 'HTML') {
1752        } elsif ({          ## ISSUE: ASCII case-insensitive? (in fact it does not matter)
1753                  comment => 1,          !!!parse-error (type => 'not HTML5');
1754                  'start tag' => 1,        }
1755                  'end tag' => 1,        
1756                  'end-of-file' => 1,        my $doctype = $self->{document}->create_document_type_definition
1757                 }->{$token->{type}}) {          ($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)?
1758          ## ISSUE: Spec currently left this case undefined.        $doctype->public_id ($token->{public_identifier})
1759          !!!parse-error (type => 'missing DOCTYPE');            if defined $token->{public_identifier};
1760          #$phase = 'root element';        $doctype->system_id ($token->{system_identifier})
1761          ## reprocess            if defined $token->{system_identifier};
1762          #redo B;        ## NOTE: Other DocumentType attributes are null or empty lists.
1763          return;        ## ISSUE: internalSubset = null??
1764        } elsif ($token->{type} eq 'character') {        $self->{document}->append_child ($doctype);
1765          if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) {        
1766            $self->{document}->manakai_append_text ($1);        if (not $token->{correct} or $doctype_name ne 'HTML') {
1767            ## ISSUE: DOM3 Core does not allow Document > Text          $self->{document}->manakai_compat_mode ('quirks');
1768            unless (length $token->{data}) {        } elsif (defined $token->{public_identifier}) {
1769              ## Stay in the phase          my $pubid = $token->{public_identifier};
1770              !!!next-token;          $pubid =~ tr/a-z/A-z/;
1771              redo B;          if ({
1772              "+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1,
1773              "-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1,
1774              "-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1,
1775              "-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1,
1776              "-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1,
1777              "-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1,
1778              "-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1,
1779              "-//IETF//DTD HTML 2.0 STRICT//EN" => 1,
1780              "-//IETF//DTD HTML 2.0//EN" => 1,
1781              "-//IETF//DTD HTML 2.1E//EN" => 1,
1782              "-//IETF//DTD HTML 3.0//EN" => 1,
1783              "-//IETF//DTD HTML 3.0//EN//" => 1,
1784              "-//IETF//DTD HTML 3.2 FINAL//EN" => 1,
1785              "-//IETF//DTD HTML 3.2//EN" => 1,
1786              "-//IETF//DTD HTML 3//EN" => 1,
1787              "-//IETF//DTD HTML LEVEL 0//EN" => 1,
1788              "-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1,
1789              "-//IETF//DTD HTML LEVEL 1//EN" => 1,
1790              "-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1,
1791              "-//IETF//DTD HTML LEVEL 2//EN" => 1,
1792              "-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1,
1793              "-//IETF//DTD HTML LEVEL 3//EN" => 1,
1794              "-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1,
1795              "-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1,
1796              "-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1,
1797              "-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1,
1798              "-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1,
1799              "-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1,
1800              "-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1,
1801              "-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1,
1802              "-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1,
1803              "-//IETF//DTD HTML STRICT//EN" => 1,
1804              "-//IETF//DTD HTML STRICT//EN//2.0" => 1,
1805              "-//IETF//DTD HTML STRICT//EN//3.0" => 1,
1806              "-//IETF//DTD HTML//EN" => 1,
1807              "-//IETF//DTD HTML//EN//2.0" => 1,
1808              "-//IETF//DTD HTML//EN//3.0" => 1,
1809              "-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1,
1810              "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1,
1811              "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1,
1812              "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1,
1813              "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1,
1814              "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1,
1815              "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1,
1816              "-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1,
1817              "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1,
1818              "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1,
1819              "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1,
1820              "-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1,
1821              "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1,
1822              "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1,
1823              "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1,
1824              "-//W3C//DTD HTML 3 1995-03-24//EN" => 1,
1825              "-//W3C//DTD HTML 3.2 DRAFT//EN" => 1,
1826              "-//W3C//DTD HTML 3.2 FINAL//EN" => 1,
1827              "-//W3C//DTD HTML 3.2//EN" => 1,
1828              "-//W3C//DTD HTML 3.2S DRAFT//EN" => 1,
1829              "-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1,
1830              "-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1,
1831              "-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1,
1832              "-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1,
1833              "-//W3C//DTD W3 HTML//EN" => 1,
1834              "-//W3O//DTD W3 HTML 3.0//EN" => 1,
1835              "-//W3O//DTD W3 HTML 3.0//EN//" => 1,
1836              "-//W3O//DTD W3 HTML STRICT 3.0//EN//" => 1,
1837              "-//WEBTECHS//DTD MOZILLA HTML 2.0//EN" => 1,
1838              "-//WEBTECHS//DTD MOZILLA HTML//EN" => 1,
1839              "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1,
1840              "HTML" => 1,
1841            }->{$pubid}) {
1842              $self->{document}->manakai_compat_mode ('quirks');
1843            } elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or
1844                     $pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") {
1845              if (defined $token->{system_identifier}) {
1846                $self->{document}->manakai_compat_mode ('quirks');
1847              } else {
1848                $self->{document}->manakai_compat_mode ('limited quirks');
1849            }            }
1850            } elsif ($pubid eq "-//W3C//DTD XHTML 1.0 Frameset//EN" or
1851                     $pubid eq "-//W3C//DTD XHTML 1.0 Transitional//EN") {
1852              $self->{document}->manakai_compat_mode ('limited quirks');
1853            }
1854          }
1855          if (defined $token->{system_identifier}) {
1856            my $sysid = $token->{system_identifier};
1857            $sysid =~ tr/A-Z/a-z/;
1858            if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") {
1859              $self->{document}->manakai_compat_mode ('quirks');
1860          }          }
         ## ISSUE: Spec currently left this case undefined.  
         !!!parse-error (type => 'missing DOCTYPE');  
         #$phase = 'root element';  
         ## reprocess  
         #redo B;  
         return;  
       } else {  
         die "$0: $token->{type}: Unknown token";  
1861        }        }
1862      } # B        
1863          ## Go to the root element phase.
1864          !!!next-token;
1865          return;
1866        } elsif ({
1867                  'start tag' => 1,
1868                  'end tag' => 1,
1869                  'end-of-file' => 1,
1870                 }->{$token->{type}}) {
1871          !!!parse-error (type => 'no DOCTYPE');
1872          $self->{document}->manakai_compat_mode ('quirks');
1873          ## Go to the root element phase
1874          ## reprocess
1875          return;
1876        } elsif ($token->{type} eq 'character') {
1877          if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D
1878            ## Ignore the token
1879            unless (length $token->{data}) {
1880              ## Stay in the phase
1881              !!!next-token;
1882              redo INITIAL;
1883            }
1884          }
1885    
1886          !!!parse-error (type => 'no DOCTYPE');
1887          $self->{document}->manakai_compat_mode ('quirks');
1888          ## Go to the root element phase
1889          ## reprocess
1890          return;
1891        } elsif ($token->{type} eq 'comment') {
1892          my $comment = $self->{document}->create_comment ($token->{data});
1893          $self->{document}->append_child ($comment);
1894          
1895          ## Stay in the phase.
1896          !!!next-token;
1897          redo INITIAL;
1898        } else {
1899          die "$0: $token->{type}: Unknown token";
1900        }
1901      } # INITIAL
1902  } # _tree_construction_initial  } # _tree_construction_initial
1903    
1904  sub _tree_construction_root_element ($) {  sub _tree_construction_root_element ($) {
# Line 1924  sub _tree_construction_main ($) { Line 2104  sub _tree_construction_main ($) {
2104       ? $self->{head_element} : $self->{open_elements}->[-1]->[0])       ? $self->{head_element} : $self->{open_elements}->[-1]->[0])
2105        ->append_child ($style_el);        ->append_child ($style_el);
2106      $self->{content_model_flag} = 'CDATA';      $self->{content_model_flag} = 'CDATA';
2107        delete $self->{escape}; # MUST
2108                                
2109      my $text = '';      my $text = '';
2110      !!!next-token;      !!!next-token;
# Line 1952  sub _tree_construction_main ($) { Line 2133  sub _tree_construction_main ($) {
2133      ## TODO: mark as "parser-inserted"      ## TODO: mark as "parser-inserted"
2134    
2135      $self->{content_model_flag} = 'CDATA';      $self->{content_model_flag} = 'CDATA';
2136        delete $self->{escape}; # MUST
2137            
2138      my $text = '';      my $text = '';
2139      !!!next-token;      !!!next-token;
# Line 2241  sub _tree_construction_main ($) { Line 2423  sub _tree_construction_main ($) {
2423          (defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0])          (defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0])
2424            ->append_child ($title_el);            ->append_child ($title_el);
2425          $self->{content_model_flag} = 'RCDATA';          $self->{content_model_flag} = 'RCDATA';
2426            delete $self->{escape}; # MUST
2427                    
2428          my $text = '';          my $text = '';
2429          !!!next-token;          !!!next-token;
# Line 2587  sub _tree_construction_main ($) { Line 2770  sub _tree_construction_main ($) {
2770          !!!insert-element-t ($token->{tag_name}, $token->{attributes});          !!!insert-element-t ($token->{tag_name}, $token->{attributes});
2771                    
2772          $self->{content_model_flag} = 'CDATA';          $self->{content_model_flag} = 'CDATA';
2773            delete $self->{escape}; # MUST
2774                    
2775          !!!next-token;          !!!next-token;
2776          return;          return;
# Line 2703  sub _tree_construction_main ($) { Line 2887  sub _tree_construction_main ($) {
2887          } else {          } else {
2888            $self->{content_model_flag} = 'CDATA';            $self->{content_model_flag} = 'CDATA';
2889          }          }
2890            delete $self->{escape}; # MUST
2891                    
2892          $insert->($el);          $insert->($el);
2893                    
# Line 2804  sub _tree_construction_main ($) { Line 2989  sub _tree_construction_main ($) {
2989                  address => 1, blockquote => 1, center => 1, dir => 1,                  address => 1, blockquote => 1, center => 1, dir => 1,
2990                  div => 1, dl => 1, fieldset => 1, listing => 1,                  div => 1, dl => 1, fieldset => 1, listing => 1,
2991                  menu => 1, ol => 1, pre => 1, ul => 1,                  menu => 1, ol => 1, pre => 1, ul => 1,
                 form => 1,  
2992                  p => 1,                  p => 1,
2993                  dd => 1, dt => 1, li => 1,                  dd => 1, dt => 1, li => 1,
2994                  button => 1, marquee => 1, object => 1,                  button => 1, marquee => 1, object => 1,
# Line 2842  sub _tree_construction_main ($) { Line 3026  sub _tree_construction_main ($) {
3026          }          }
3027                    
3028          splice @{$self->{open_elements}}, $i if defined $i;          splice @{$self->{open_elements}}, $i if defined $i;
         undef $self->{form_element} if $token->{tag_name} eq 'form';  
3029          $clear_up_to_marker->()          $clear_up_to_marker->()
3030            if {            if {
3031              button => 1, marquee => 1, object => 1,              button => 1, marquee => 1, object => 1,
3032            }->{$token->{tag_name}};            }->{$token->{tag_name}};
3033          !!!next-token;          !!!next-token;
3034          return;          return;
3035          } elsif ($token->{tag_name} eq 'form') {
3036            ## has an element in scope
3037            INSCOPE: for (reverse 0..$#{$self->{open_elements}}) {
3038              my $node = $self->{open_elements}->[$_];
3039              if ($node->[1] eq $token->{tag_name}) {
3040                ## generate implied end tags
3041                if ({
3042                     dd => 1, dt => 1, li => 1, p => 1,
3043                     td => 1, th => 1, tr => 1,
3044                    }->{$self->{open_elements}->[-1]->[1]}) {
3045                  !!!back-token;
3046                  $token = {type => 'end tag',
3047                            tag_name => $self->{open_elements}->[-1]->[1]}; # MUST
3048                  return;
3049                }
3050                last INSCOPE;
3051              } elsif ({
3052                        table => 1, caption => 1, td => 1, th => 1,
3053                        button => 1, marquee => 1, object => 1, html => 1,
3054                       }->{$node->[1]}) {
3055                last INSCOPE;
3056              }
3057            } # INSCOPE
3058            
3059            if ($self->{open_elements}->[-1]->[1] eq $token->{tag_name}) {
3060              pop @{$self->{open_elements}};
3061            } else {
3062              !!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]);
3063            }
3064    
3065            undef $self->{form_element};
3066            !!!next-token;
3067            return;
3068        } elsif ({        } elsif ({
3069                  h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1,                  h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1,
3070                 }->{$token->{tag_name}}) {                 }->{$token->{tag_name}}) {
# Line 3094  sub _tree_construction_main ($) { Line 3310  sub _tree_construction_main ($) {
3310                (defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0])                (defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0])
3311                  ->append_child ($title_el);                  ->append_child ($title_el);
3312                $self->{content_model_flag} = 'RCDATA';                $self->{content_model_flag} = 'RCDATA';
3313                  delete $self->{escape}; # MUST
3314    
3315                my $text = '';                my $text = '';
3316                !!!next-token;                !!!next-token;
# Line 4865  sub set_inner_html ($$$) { Line 5082  sub set_inner_html ($$$) {
5082      ## NOTE: Most of this code is copied from |parse_string|      ## NOTE: Most of this code is copied from |parse_string|
5083    
5084      ## Step 1 # MUST      ## Step 1 # MUST
5085      my $doc = $node->owner_document->implementation->create_document;      my $this_doc = $node->owner_document;
5086      ## TODO: Mark as HTML document      my $doc = $this_doc->implementation->create_document;
5087        $doc->manakai_is_html (1);
5088      my $p = $class->new;      my $p = $class->new;
5089      $p->{document} = $doc;      $p->{document} = $doc;
5090    
# Line 4876  sub set_inner_html ($$$) { Line 5094  sub set_inner_html ($$$) {
5094      my $column = 0;      my $column = 0;
5095      $p->{set_next_input_character} = sub {      $p->{set_next_input_character} = sub {
5096        my $self = shift;        my $self = shift;
5097    
5098          pop @{$self->{prev_input_character}};
5099          unshift @{$self->{prev_input_character}}, $self->{next_input_character};
5100    
5101        $self->{next_input_character} = -1 and return if $i >= length $$s;        $self->{next_input_character} = -1 and return if $i >= length $$s;
5102        $self->{next_input_character} = ord substr $$s, $i++, 1;        $self->{next_input_character} = ord substr $$s, $i++, 1;
5103        $column++;        $column++;
# Line 4884  sub set_inner_html ($$$) { Line 5106  sub set_inner_html ($$$) {
5106          $line++;          $line++;
5107          $column = 0;          $column = 0;
5108        } elsif ($self->{next_input_character} == 0x000D) { # CR        } elsif ($self->{next_input_character} == 0x000D) { # CR
5109          if ($i >= length $$s) {          $i++ if substr ($$s, $i, 1) eq "\x0A";
           #  
         } else {  
           my $next_char = ord substr $$s, $i++, 1;  
           if ($next_char == 0x000A) { # LF  
             #  
           } else {  
             push @{$self->{char}}, $next_char;  
           }  
         }  
5110          $self->{next_input_character} = 0x000A; # LF # MUST          $self->{next_input_character} = 0x000A; # LF # MUST
5111          $line++;          $line++;
5112          $column = 0;          $column = 0;
5113        } elsif ($self->{next_input_character} > 0x10FFFF) {        } elsif ($self->{next_input_character} > 0x10FFFF) {
5114          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
5115        } elsif ($self->{next_input_character} == 0x0000) { # NULL        } elsif ($self->{next_input_character} == 0x0000) { # NULL
5116            !!!parse-error (type => 'NULL');
5117          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
5118        }        }
5119      };      };
5120        $p->{prev_input_character} = [-1, -1, -1];
5121        $p->{next_input_character} = -1;
5122            
5123      my $ponerror = $onerror || sub {      my $ponerror = $onerror || sub {
5124        my (%opt) = @_;        my (%opt) = @_;
# Line 4981  sub set_inner_html ($$$) { Line 5197  sub set_inner_html ($$$) {
5197      ## Step 12 # MUST      ## Step 12 # MUST
5198      @cn = @{$root->child_nodes};      @cn = @{$root->child_nodes};
5199      for (@cn) {      for (@cn) {
5200          $this_doc->adopt_node ($_);
5201        $node->append_child ($_);        $node->append_child ($_);
5202      }      }
5203      ## ISSUE: adopt_node? mutation events?      ## ISSUE: mutation events?
5204    
5205      $p->_terminate_tree_constructor;      $p->_terminate_tree_constructor;
5206    } else {    } else {
Legend:
Removed from v.1.11  
changed lines
  Added in v.1.18
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24