/[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 1.33 by wakaba, Sat Jul 7 13:41:05 2007 UTC revision 1.129 by wakaba, Sat Apr 12 15:37:33 2008 UTC
# Line 1  Line 1 
1  package Whatpm::HTML;  package Whatpm::HTML;
2  use strict;  use strict;
3  our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r};  our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r};
4    use Error qw(:try);
5    
6  ## ISSUE:  ## ISSUE:
7  ## var doc = implementation.createDocument (null, null, null);  ## var doc = implementation.createDocument (null, null, null);
8  ## doc.write ('');  ## doc.write ('');
9  ## alert (doc.compatMode);  ## alert (doc.compatMode);
10    
11  ## ISSUE: HTML5 revision 967 says that the encoding layer MUST NOT  ## TODO: Control charcters and noncharacters are not allowed (HTML5 revision 1263)
12  ## strip BOM and the HTML layer MUST ignore it.  Whether we can do it  ## TODO: 1252 parse error (revision 1264)
13  ## is not yet clear.  ## TODO: 8859-11 = 874 (revision 1271)
14  ## "{U+FEFF}..." in UTF-16BE/UTF-16LE is three or four characters?  
15  ## "{U+FEFF}..." in GB18030?  my $HTML_NS = q<http://www.w3.org/1999/xhtml>;
16    my $MML_NS = q<http://www.w3.org/1998/Math/MathML>;
17  my $permitted_slash_tag_name = {  my $SVG_NS = q<http://www.w3.org/2000/svg>;
18    base => 1,  my $XLINK_NS = q<http://www.w3.org/1999/xlink>;
19    link => 1,  my $XML_NS = q<http://www.w3.org/XML/1998/namespace>;
20    meta => 1,  my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>;
21    hr => 1,  
22    br => 1,  sub A_EL () { 0b1 }
23    img=> 1,  sub ADDRESS_EL () { 0b10 }
24    embed => 1,  sub BODY_EL () { 0b100 }
25    param => 1,  sub BUTTON_EL () { 0b1000 }
26    area => 1,  sub CAPTION_EL () { 0b10000 }
27    col => 1,  sub DD_EL () { 0b100000 }
28    input => 1,  sub DIV_EL () { 0b1000000 }
29    sub DT_EL () { 0b10000000 }
30    sub FORM_EL () { 0b100000000 }
31    sub FORMATTING_EL () { 0b1000000000 }
32    sub FRAMESET_EL () { 0b10000000000 }
33    sub HEADING_EL () { 0b100000000000 }
34    sub HTML_EL () { 0b1000000000000 }
35    sub LI_EL () { 0b10000000000000 }
36    sub NOBR_EL () { 0b100000000000000 }
37    sub OPTION_EL () { 0b1000000000000000 }
38    sub OPTGROUP_EL () { 0b10000000000000000 }
39    sub P_EL () { 0b100000000000000000 }
40    sub SELECT_EL () { 0b1000000000000000000 }
41    sub TABLE_EL () { 0b10000000000000000000 }
42    sub TABLE_CELL_EL () { 0b100000000000000000000 }
43    sub TABLE_ROW_EL () { 0b1000000000000000000000 }
44    sub TABLE_ROW_GROUP_EL () { 0b10000000000000000000000 }
45    sub MISC_SCOPING_EL () { 0b100000000000000000000000 }
46    sub MISC_SPECIAL_EL () { 0b1000000000000000000000000 }
47    sub FOREIGN_EL () { 0b10000000000000000000000000 }
48    sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 }
49    sub MML_AXML_EL () { 0b1000000000000000000000000000 }
50    
51    sub TABLE_ROWS_EL () {
52      TABLE_EL |
53      TABLE_ROW_EL |
54      TABLE_ROW_GROUP_EL
55    }
56    
57    sub END_TAG_OPTIONAL_EL () {
58      DD_EL |
59      DT_EL |
60      LI_EL |
61      P_EL
62    }
63    
64    sub ALL_END_TAG_OPTIONAL_EL () {
65      END_TAG_OPTIONAL_EL |
66      BODY_EL |
67      HTML_EL |
68      TABLE_CELL_EL |
69      TABLE_ROW_EL |
70      TABLE_ROW_GROUP_EL
71    }
72    
73    sub SCOPING_EL () {
74      BUTTON_EL |
75      CAPTION_EL |
76      HTML_EL |
77      TABLE_EL |
78      TABLE_CELL_EL |
79      MISC_SCOPING_EL
80    }
81    
82    sub TABLE_SCOPING_EL () {
83      HTML_EL |
84      TABLE_EL
85    }
86    
87    sub TABLE_ROWS_SCOPING_EL () {
88      HTML_EL |
89      TABLE_ROW_GROUP_EL
90    }
91    
92    sub TABLE_ROW_SCOPING_EL () {
93      HTML_EL |
94      TABLE_ROW_EL
95    }
96    
97    sub SPECIAL_EL () {
98      ADDRESS_EL |
99      BODY_EL |
100      DIV_EL |
101      END_TAG_OPTIONAL_EL |
102      FORM_EL |
103      FRAMESET_EL |
104      HEADING_EL |
105      OPTION_EL |
106      OPTGROUP_EL |
107      SELECT_EL |
108      TABLE_ROW_EL |
109      TABLE_ROW_GROUP_EL |
110      MISC_SPECIAL_EL
111    }
112    
113    my $el_category = {
114      a => A_EL | FORMATTING_EL,
115      address => ADDRESS_EL,
116      applet => MISC_SCOPING_EL,
117      area => MISC_SPECIAL_EL,
118      b => FORMATTING_EL,
119      base => MISC_SPECIAL_EL,
120      basefont => MISC_SPECIAL_EL,
121      bgsound => MISC_SPECIAL_EL,
122      big => FORMATTING_EL,
123      blockquote => MISC_SPECIAL_EL,
124      body => BODY_EL,
125      br => MISC_SPECIAL_EL,
126      button => BUTTON_EL,
127      caption => CAPTION_EL,
128      center => MISC_SPECIAL_EL,
129      col => MISC_SPECIAL_EL,
130      colgroup => MISC_SPECIAL_EL,
131      dd => DD_EL,
132      dir => MISC_SPECIAL_EL,
133      div => DIV_EL,
134      dl => MISC_SPECIAL_EL,
135      dt => DT_EL,
136      em => FORMATTING_EL,
137      embed => MISC_SPECIAL_EL,
138      fieldset => MISC_SPECIAL_EL,
139      font => FORMATTING_EL,
140      form => FORM_EL,
141      frame => MISC_SPECIAL_EL,
142      frameset => FRAMESET_EL,
143      h1 => HEADING_EL,
144      h2 => HEADING_EL,
145      h3 => HEADING_EL,
146      h4 => HEADING_EL,
147      h5 => HEADING_EL,
148      h6 => HEADING_EL,
149      head => MISC_SPECIAL_EL,
150      hr => MISC_SPECIAL_EL,
151      html => HTML_EL,
152      i => FORMATTING_EL,
153      iframe => MISC_SPECIAL_EL,
154      img => MISC_SPECIAL_EL,
155      input => MISC_SPECIAL_EL,
156      isindex => MISC_SPECIAL_EL,
157      li => LI_EL,
158      link => MISC_SPECIAL_EL,
159      listing => MISC_SPECIAL_EL,
160      marquee => MISC_SCOPING_EL,
161      menu => MISC_SPECIAL_EL,
162      meta => MISC_SPECIAL_EL,
163      nobr => NOBR_EL | FORMATTING_EL,
164      noembed => MISC_SPECIAL_EL,
165      noframes => MISC_SPECIAL_EL,
166      noscript => MISC_SPECIAL_EL,
167      object => MISC_SCOPING_EL,
168      ol => MISC_SPECIAL_EL,
169      optgroup => OPTGROUP_EL,
170      option => OPTION_EL,
171      p => P_EL,
172      param => MISC_SPECIAL_EL,
173      plaintext => MISC_SPECIAL_EL,
174      pre => MISC_SPECIAL_EL,
175      s => FORMATTING_EL,
176      script => MISC_SPECIAL_EL,
177      select => SELECT_EL,
178      small => FORMATTING_EL,
179      spacer => MISC_SPECIAL_EL,
180      strike => FORMATTING_EL,
181      strong => FORMATTING_EL,
182      style => MISC_SPECIAL_EL,
183      table => TABLE_EL,
184      tbody => TABLE_ROW_GROUP_EL,
185      td => TABLE_CELL_EL,
186      textarea => MISC_SPECIAL_EL,
187      tfoot => TABLE_ROW_GROUP_EL,
188      th => TABLE_CELL_EL,
189      thead => TABLE_ROW_GROUP_EL,
190      title => MISC_SPECIAL_EL,
191      tr => TABLE_ROW_EL,
192      tt => FORMATTING_EL,
193      u => FORMATTING_EL,
194      ul => MISC_SPECIAL_EL,
195      wbr => MISC_SPECIAL_EL,
196    };
197    
198    my $el_category_f = {
199      $MML_NS => {
200        'annotation-xml' => MML_AXML_EL,
201        mi => FOREIGN_FLOW_CONTENT_EL,
202        mo => FOREIGN_FLOW_CONTENT_EL,
203        mn => FOREIGN_FLOW_CONTENT_EL,
204        ms => FOREIGN_FLOW_CONTENT_EL,
205        mtext => FOREIGN_FLOW_CONTENT_EL,
206      },
207      $SVG_NS => {
208        foreignobject => FOREIGN_FLOW_CONTENT_EL, ## TODO: case
209        desc => FOREIGN_FLOW_CONTENT_EL,
210        title => FOREIGN_FLOW_CONTENT_EL,
211      },
212      ## NOTE: In addition, FOREIGN_EL is set to non-HTML elements.
213  };  };
214    
215  my $c1_entity_char = {  my $c1_entity_char = {
# Line 62  my $c1_entity_char = { Line 247  my $c1_entity_char = {
247    0x9F => 0x0178,    0x9F => 0x0178,
248  }; # $c1_entity_char  }; # $c1_entity_char
249    
250  my $special_category = {  sub parse_byte_string ($$$$;$) {
251    address => 1, area => 1, base => 1, basefont => 1, bgsound => 1,    my $self = ref $_[0] ? shift : shift->new;
252    blockquote => 1, body => 1, br => 1, center => 1, col => 1, colgroup => 1,    my $charset = shift;
253    dd => 1, dir => 1, div => 1, dl => 1, dt => 1, embed => 1, fieldset => 1,    my $bytes_s = ref $_[0] ? $_[0] : \($_[0]);
254    form => 1, frame => 1, frameset => 1, h1 => 1, h2 => 1, h3 => 1,    my $s;
255    h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, iframe => 1, image => 1,    
256    img => 1, input => 1, isindex => 1, li => 1, link => 1, listing => 1,    if (defined $charset) {
257    menu => 1, meta => 1, noembed => 1, noframes => 1, noscript => 1,      require Encode; ## TODO: decode(utf8) don't delete BOM
258    ol => 1, optgroup => 1, option => 1, p => 1, param => 1, plaintext => 1,      $s = \ (Encode::decode ($charset, $$bytes_s));
259    pre => 1, script => 1, select => 1, spacer => 1, style => 1, tbody => 1,      $self->{input_encoding} = lc $charset; ## TODO: normalize name
260    textarea => 1, tfoot => 1, thead => 1, title => 1, tr => 1, ul => 1, wbr => 1,      $self->{confident} = 1;
261  };    } else {
262  my $scoping_category = {      ## TODO: Implement HTML5 detection algorithm
263    button => 1, caption => 1, html => 1, marquee => 1, object => 1,      require Whatpm::Charset::UniversalCharDet;
264    table => 1, td => 1, th => 1,      $charset = Whatpm::Charset::UniversalCharDet->detect_byte_string
265  };          (substr ($$bytes_s, 0, 1024));
266  my $formatting_category = {      $charset ||= 'windows-1252';
267    a => 1, b => 1, big => 1, em => 1, font => 1, i => 1, nobr => 1,      $s = \ (Encode::decode ($charset, $$bytes_s));
268    s => 1, small => 1, strile => 1, strong => 1, tt => 1, u => 1,      $self->{input_encoding} = $charset;
269  };      $self->{confident} = 0;
270  # $phrasing_category: all other elements    }
271    
272      $self->{change_encoding} = sub {
273        my $self = shift;
274        my $charset = lc shift;
275        my $token = shift;
276        ## TODO: if $charset is supported
277        ## TODO: normalize charset name
278    
279        ## "Change the encoding" algorithm:
280    
281        ## Step 1    
282        if ($charset eq 'utf-16') { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8?
283          $charset = 'utf-8';
284        }
285    
286        ## Step 2
287        if (defined $self->{input_encoding} and
288            $self->{input_encoding} eq $charset) {
289          $self->{confident} = 1;
290          return;
291        }
292    
293        !!!parse-error (type => 'charset label detected:'.$self->{input_encoding}.
294            ':'.$charset, level => 'w', token => $token);
295    
296        ## Step 3
297        # if (can) {
298          ## change the encoding on the fly.
299          #$self->{confident} = 1;
300          #return;
301        # }
302    
303        ## Step 4
304        throw Whatpm::HTML::RestartParser (charset => $charset);
305      }; # $self->{change_encoding}
306    
307      my @args = @_; shift @args; # $s
308      my $return;
309      try {
310        $return = $self->parse_char_string ($s, @args);  
311      } catch Whatpm::HTML::RestartParser with {
312        my $charset = shift->{charset};
313        $s = \ (Encode::decode ($charset, $$bytes_s));    
314        $self->{input_encoding} = $charset; ## TODO: normalize
315        $self->{confident} = 1;
316        $return = $self->parse_char_string ($s, @args);
317      };
318      return $return;
319    } # parse_byte_string
320    
321    ## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM
322    ## and the HTML layer MUST ignore it.  However, we does strip BOM in
323    ## the encoding layer and the HTML layer does not ignore any U+FEFF,
324    ## because the core part of our HTML parser expects a string of character,
325    ## not a string of bytes or code units or anything which might contain a BOM.
326    ## Therefore, any parser interface that accepts a string of bytes,
327    ## such as |parse_byte_string| in this module, must ensure that it does
328    ## strip the BOM and never strip any ZWNBSP.
329    
330    *parse_char_string = \&parse_string;
331    
332  sub parse_string ($$$;$) {  sub parse_string ($$$;$) {
333    my $self = shift->new;    my $self = ref $_[0] ? shift : shift->new;
334    my $s = \$_[0];    my $s = ref $_[0] ? $_[0] : \($_[0]);
335    $self->{document} = $_[1];    $self->{document} = $_[1];
336      @{$self->{document}->child_nodes} = ();
337    
338    ## NOTE: |set_inner_html| copies most of this method's code    ## NOTE: |set_inner_html| copies most of this method's code
339    
340      $self->{confident} = 1 unless exists $self->{confident};
341      $self->{document}->input_encoding ($self->{input_encoding})
342          if defined $self->{input_encoding};
343    
344    my $i = 0;    my $i = 0;
345    my $line = 1;    $self->{line_prev} = $self->{line} = 1;
346    my $column = 0;    $self->{column_prev} = $self->{column} = 0;
347    $self->{set_next_input_character} = sub {    $self->{set_next_char} = sub {
348      my $self = shift;      my $self = shift;
349    
350      pop @{$self->{prev_input_character}};      pop @{$self->{prev_char}};
351      unshift @{$self->{prev_input_character}}, $self->{next_input_character};      unshift @{$self->{prev_char}}, $self->{next_char};
352    
353        $self->{next_char} = -1 and return if $i >= length $$s;
354        $self->{next_char} = ord substr $$s, $i++, 1;
355    
356      $self->{next_input_character} = -1 and return if $i >= length $$s;      ($self->{line_prev}, $self->{column_prev})
357      $self->{next_input_character} = ord substr $$s, $i++, 1;          = ($self->{line}, $self->{column});
358      $column++;      $self->{column}++;
359            
360      if ($self->{next_input_character} == 0x000A) { # LF      if ($self->{next_char} == 0x000A) { # LF
361        $line++;        $self->{line}++;
362        $column = 0;        $self->{column} = 0;
363      } elsif ($self->{next_input_character} == 0x000D) { # CR      } elsif ($self->{next_char} == 0x000D) { # CR
364        $i++ if substr ($$s, $i, 1) eq "\x0A";        $i++ if substr ($$s, $i, 1) eq "\x0A";
365        $self->{next_input_character} = 0x000A; # LF # MUST        $self->{next_char} = 0x000A; # LF # MUST
366        $line++;        $self->{line}++;
367        $column = 0;        $self->{column} = 0;
368      } elsif ($self->{next_input_character} > 0x10FFFF) {      } elsif ($self->{next_char} > 0x10FFFF) {
369        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST        $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
370      } elsif ($self->{next_input_character} == 0x0000) { # NULL      } elsif ($self->{next_char} == 0x0000) { # NULL
371        !!!parse-error (type => 'NULL');        !!!parse-error (type => 'NULL');
372        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST        $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
373      }      }
374    };    };
375    $self->{prev_input_character} = [-1, -1, -1];    $self->{prev_char} = [-1, -1, -1];
376    $self->{next_input_character} = -1;    $self->{next_char} = -1;
377    
378    my $onerror = $_[2] || sub {    my $onerror = $_[2] || sub {
379      my (%opt) = @_;      my (%opt) = @_;
380      warn "Parse error ($opt{type}) at line $opt{line} column $opt{column}\n";      my $line = $opt{token} ? $opt{token}->{line} : $opt{line};
381        my $column = $opt{token} ? $opt{token}->{column} : $opt{column};
382        warn "Parse error ($opt{type}) at line $line column $column\n";
383    };    };
384    $self->{parse_error} = sub {    $self->{parse_error} = sub {
385      $onerror->(@_, line => $line, column => $column);      $onerror->(line => $self->{line}, column => $self->{column}, @_);
386    };    };
387    
388    $self->_initialize_tokenizer;    $self->_initialize_tokenizer;
# Line 135  sub parse_string ($$$;$) { Line 390  sub parse_string ($$$;$) {
390    $self->_construct_tree;    $self->_construct_tree;
391    $self->_terminate_tree_constructor;    $self->_terminate_tree_constructor;
392    
393      delete $self->{parse_error}; # remove loop
394    
395    return $self->{document};    return $self->{document};
396  } # parse_string  } # parse_string
397    
398  sub new ($) {  sub new ($) {
399    my $class = shift;    my $class = shift;
400    my $self = bless {}, $class;    my $self = bless {}, $class;
401    $self->{set_next_input_character} = sub {    $self->{set_next_char} = sub {
402      $self->{next_input_character} = -1;      $self->{next_char} = -1;
403    };    };
404    $self->{parse_error} = sub {    $self->{parse_error} = sub {
405      #      #
406    };    };
407      $self->{change_encoding} = sub {
408        # if ($_[0] is a supported encoding) {
409        #   run "change the encoding" algorithm;
410        #   throw Whatpm::HTML::RestartParser (charset => $new_encoding);
411        # }
412      };
413      $self->{application_cache_selection} = sub {
414        #
415      };
416    return $self;    return $self;
417  } # new  } # new
418    
419    sub CM_ENTITY () { 0b001 } # & markup in data
420    sub CM_LIMITED_MARKUP () { 0b010 } # < markup in data (limited)
421    sub CM_FULL_MARKUP () { 0b100 } # < markup in data (any)
422    
423    sub PLAINTEXT_CONTENT_MODEL () { 0 }
424    sub CDATA_CONTENT_MODEL () { CM_LIMITED_MARKUP }
425    sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP }
426    sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP }
427    
428    sub DATA_STATE () { 0 }
429    sub ENTITY_DATA_STATE () { 1 }
430    sub TAG_OPEN_STATE () { 2 }
431    sub CLOSE_TAG_OPEN_STATE () { 3 }
432    sub TAG_NAME_STATE () { 4 }
433    sub BEFORE_ATTRIBUTE_NAME_STATE () { 5 }
434    sub ATTRIBUTE_NAME_STATE () { 6 }
435    sub AFTER_ATTRIBUTE_NAME_STATE () { 7 }
436    sub BEFORE_ATTRIBUTE_VALUE_STATE () { 8 }
437    sub ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE () { 9 }
438    sub ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE () { 10 }
439    sub ATTRIBUTE_VALUE_UNQUOTED_STATE () { 11 }
440    sub ENTITY_IN_ATTRIBUTE_VALUE_STATE () { 12 }
441    sub MARKUP_DECLARATION_OPEN_STATE () { 13 }
442    sub COMMENT_START_STATE () { 14 }
443    sub COMMENT_START_DASH_STATE () { 15 }
444    sub COMMENT_STATE () { 16 }
445    sub COMMENT_END_STATE () { 17 }
446    sub COMMENT_END_DASH_STATE () { 18 }
447    sub BOGUS_COMMENT_STATE () { 19 }
448    sub DOCTYPE_STATE () { 20 }
449    sub BEFORE_DOCTYPE_NAME_STATE () { 21 }
450    sub DOCTYPE_NAME_STATE () { 22 }
451    sub AFTER_DOCTYPE_NAME_STATE () { 23 }
452    sub BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 24 }
453    sub DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE () { 25 }
454    sub DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE () { 26 }
455    sub AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 27 }
456    sub BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 28 }
457    sub DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE () { 29 }
458    sub DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE () { 30 }
459    sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 }
460    sub BOGUS_DOCTYPE_STATE () { 32 }
461    sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 }
462    sub SELF_CLOSING_START_TAG_STATE () { 34 }
463    sub CDATA_BLOCK_STATE () { 35 }
464    
465    sub DOCTYPE_TOKEN () { 1 }
466    sub COMMENT_TOKEN () { 2 }
467    sub START_TAG_TOKEN () { 3 }
468    sub END_TAG_TOKEN () { 4 }
469    sub END_OF_FILE_TOKEN () { 5 }
470    sub CHARACTER_TOKEN () { 6 }
471    
472    sub AFTER_HTML_IMS () { 0b100 }
473    sub HEAD_IMS ()       { 0b1000 }
474    sub BODY_IMS ()       { 0b10000 }
475    sub BODY_TABLE_IMS () { 0b100000 }
476    sub TABLE_IMS ()      { 0b1000000 }
477    sub ROW_IMS ()        { 0b10000000 }
478    sub BODY_AFTER_IMS () { 0b100000000 }
479    sub FRAME_IMS ()      { 0b1000000000 }
480    sub SELECT_IMS ()     { 0b10000000000 }
481    sub IN_FOREIGN_CONTENT_IM () { 0b100000000000 }
482        ## NOTE: "in foreign content" insertion mode is special; it is combined
483        ## with the secondary insertion mode.  In this parser, they are stored
484        ## together in the bit-or'ed form.
485    
486    ## NOTE: "initial" and "before html" insertion modes have no constants.
487    
488    ## NOTE: "after after body" insertion mode.
489    sub AFTER_HTML_BODY_IM () { AFTER_HTML_IMS | BODY_AFTER_IMS }
490    
491    ## NOTE: "after after frameset" insertion mode.
492    sub AFTER_HTML_FRAMESET_IM () { AFTER_HTML_IMS | FRAME_IMS }
493    
494    sub IN_HEAD_IM () { HEAD_IMS | 0b00 }
495    sub IN_HEAD_NOSCRIPT_IM () { HEAD_IMS | 0b01 }
496    sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 }
497    sub BEFORE_HEAD_IM () { HEAD_IMS | 0b11 }
498    sub IN_BODY_IM () { BODY_IMS }
499    sub IN_CELL_IM () { BODY_IMS | BODY_TABLE_IMS | 0b01 }
500    sub IN_CAPTION_IM () { BODY_IMS | BODY_TABLE_IMS | 0b10 }
501    sub IN_ROW_IM () { TABLE_IMS | ROW_IMS | 0b01 }
502    sub IN_TABLE_BODY_IM () { TABLE_IMS | ROW_IMS | 0b10 }
503    sub IN_TABLE_IM () { TABLE_IMS }
504    sub AFTER_BODY_IM () { BODY_AFTER_IMS }
505    sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 }
506    sub AFTER_FRAMESET_IM () { FRAME_IMS | 0b10 }
507    sub IN_SELECT_IM () { SELECT_IMS | 0b01 }
508    sub IN_SELECT_IN_TABLE_IM () { SELECT_IMS | 0b10 }
509    sub IN_COLUMN_GROUP_IM () { 0b10 }
510    
511  ## Implementations MUST act as if state machine in the spec  ## Implementations MUST act as if state machine in the spec
512    
513  sub _initialize_tokenizer ($) {  sub _initialize_tokenizer ($) {
514    my $self = shift;    my $self = shift;
515    $self->{state} = 'data'; # MUST    $self->{state} = DATA_STATE; # MUST
516    $self->{content_model_flag} = 'PCDATA'; # be    $self->{content_model} = PCDATA_CONTENT_MODEL; # be
517    undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE    undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE
518    undef $self->{current_attribute};    undef $self->{current_attribute};
519    undef $self->{last_emitted_start_tag_name};    undef $self->{last_emitted_start_tag_name};
520    undef $self->{last_attribute_value_state};    undef $self->{last_attribute_value_state};
521      delete $self->{self_closing};
522    $self->{char} = [];    $self->{char} = [];
523    # $self->{next_input_character}    # $self->{next_char}
524    !!!next-input-character;    !!!next-input-character;
525    $self->{token} = [];    $self->{token} = [];
526    # $self->{escape}    # $self->{escape}
527  } # _initialize_tokenizer  } # _initialize_tokenizer
528    
529  ## A token has:  ## A token has:
530  ##   ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment',  ##   ->{type} == DOCTYPE_TOKEN, START_TAG_TOKEN, END_TAG_TOKEN, COMMENT_TOKEN,
531  ##       'character', or 'end-of-file'  ##       CHARACTER_TOKEN, or END_OF_FILE_TOKEN
532  ##   ->{name} (DOCTYPE, start tag (tag name), end tag (tag name))  ##   ->{name} (DOCTYPE_TOKEN)
533  ##   ->{public_identifier} (DOCTYPE)  ##   ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN)
534  ##   ->{system_identifier} (DOCTYPE)  ##   ->{public_identifier} (DOCTYPE_TOKEN)
535  ##   ->{correct} == 1 or 0 (DOCTYPE)  ##   ->{system_identifier} (DOCTYPE_TOKEN)
536  ##   ->{attributes} isa HASH (start tag, end tag)  ##   ->{quirks} == 1 or 0 (DOCTYPE_TOKEN): "force-quirks" flag
537  ##   ->{data} (comment, character)  ##   ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN)
538    ##        ->{name}
539    ##        ->{value}
540    ##        ->{has_reference} == 1 or 0
541    ##   ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN)
542    ## NOTE: The "self-closing flag" is hold as |$self->{self_closing}|.
543    ##     |->{self_closing}| is used to save the value of |$self->{self_closing}|
544    ##     while the token is pushed back to the stack.
545    
546    ## ISSUE: "When a DOCTYPE token is created, its
547    ## <i>self-closing flag</i> must be unset (its other state is that it
548    ## be set), and its attributes list must be empty.": Wrong subject?
549    
550  ## Emitted token MUST immediately be handled by the tree construction state.  ## Emitted token MUST immediately be handled by the tree construction state.
551    
# Line 185  sub _initialize_tokenizer ($) { Line 555  sub _initialize_tokenizer ($) {
555  ## has completed loading.  If one has, then it MUST be executed  ## has completed loading.  If one has, then it MUST be executed
556  ## and removed from the list.  ## and removed from the list.
557    
558    ## NOTE: HTML5 "Writing HTML documents" section, applied to
559    ## documents and not to user agents and conformance checkers,
560    ## contains some requirements that are not detected by the
561    ## parsing algorithm:
562    ## - Some requirements on character encoding declarations. ## TODO
563    ## - "Elements MUST NOT contain content that their content model disallows."
564    ##   ... Some are parse error, some are not (will be reported by c.c.).
565    ## - Polytheistic slash SHOULD NOT be used. (Applied only to atheists.) ## TODO
566    ## - Text (in elements, attributes, and comments) SHOULD NOT contain
567    ##   control characters other than space characters. ## TODO: (what is control character? C0, C1 and DEL?  Unicode control character?)
568    
569    ## TODO: HTML5 poses authors two SHOULD-level requirements that cannot
570    ## be detected by the HTML5 parsing algorithm:
571    ## - Text,
572    
573  sub _get_next_token ($) {  sub _get_next_token ($) {
574    my $self = shift;    my $self = shift;
575    
576      if ($self->{self_closing}) {
577        !!!parse-error (type => 'nestc', token => $self->{current_token});
578        ## NOTE: The |self_closing| flag is only set by start tag token.
579        ## In addition, when a start tag token is emitted, it is always set to
580        ## |current_token|.
581        delete $self->{self_closing};
582      }
583    
584    if (@{$self->{token}}) {    if (@{$self->{token}}) {
585        $self->{self_closing} = $self->{token}->[0]->{self_closing};
586      return shift @{$self->{token}};      return shift @{$self->{token}};
587    }    }
588    
589    A: {    A: {
590      if ($self->{state} eq 'data') {      if ($self->{state} == DATA_STATE) {
591        if ($self->{next_input_character} == 0x0026) { # &        if ($self->{next_char} == 0x0026) { # &
592          if ($self->{content_model_flag} eq 'PCDATA' or          if ($self->{content_model} & CM_ENTITY and # PCDATA | RCDATA
593              $self->{content_model_flag} eq 'RCDATA') {              not $self->{escape}) {
594            $self->{state} = 'entity data';            !!!cp (1);
595              $self->{state} = ENTITY_DATA_STATE;
596            !!!next-input-character;            !!!next-input-character;
597            redo A;            redo A;
598          } else {          } else {
599              !!!cp (2);
600            #            #
601          }          }
602        } elsif ($self->{next_input_character} == 0x002D) { # -        } elsif ($self->{next_char} == 0x002D) { # -
603          if ($self->{content_model_flag} eq 'RCDATA' or          if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA
             $self->{content_model_flag} eq 'CDATA') {  
604            unless ($self->{escape}) {            unless ($self->{escape}) {
605              if ($self->{prev_input_character}->[0] == 0x002D and # -              if ($self->{prev_char}->[0] == 0x002D and # -
606                  $self->{prev_input_character}->[1] == 0x0021 and # !                  $self->{prev_char}->[1] == 0x0021 and # !
607                  $self->{prev_input_character}->[2] == 0x003C) { # <                  $self->{prev_char}->[2] == 0x003C) { # <
608                  !!!cp (3);
609                $self->{escape} = 1;                $self->{escape} = 1;
610                } else {
611                  !!!cp (4);
612              }              }
613              } else {
614                !!!cp (5);
615            }            }
616          }          }
617                    
618          #          #
619        } elsif ($self->{next_input_character} == 0x003C) { # <        } elsif ($self->{next_char} == 0x003C) { # <
620          if ($self->{content_model_flag} eq 'PCDATA' or          if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA
621              (($self->{content_model_flag} eq 'CDATA' or              (($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA
               $self->{content_model_flag} eq 'RCDATA') and  
622               not $self->{escape})) {               not $self->{escape})) {
623            $self->{state} = 'tag open';            !!!cp (6);
624              $self->{state} = TAG_OPEN_STATE;
625            !!!next-input-character;            !!!next-input-character;
626            redo A;            redo A;
627          } else {          } else {
628              !!!cp (7);
629            #            #
630          }          }
631        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
632          if ($self->{escape} and          if ($self->{escape} and
633              ($self->{content_model_flag} eq 'RCDATA' or              ($self->{content_model} & CM_LIMITED_MARKUP)) { # RCDATA | CDATA
634               $self->{content_model_flag} eq 'CDATA')) {            if ($self->{prev_char}->[0] == 0x002D and # -
635            if ($self->{prev_input_character}->[0] == 0x002D and # -                $self->{prev_char}->[1] == 0x002D) { # -
636                $self->{prev_input_character}->[1] == 0x002D) { # -              !!!cp (8);
637              delete $self->{escape};              delete $self->{escape};
638              } else {
639                !!!cp (9);
640            }            }
641            } else {
642              !!!cp (10);
643          }          }
644                    
645          #          #
646        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
647          !!!emit ({type => 'end-of-file'});          !!!cp (11);
648            !!!emit ({type => END_OF_FILE_TOKEN,
649                      line => $self->{line}, column => $self->{column}});
650          last A; ## TODO: ok?          last A; ## TODO: ok?
651          } else {
652            !!!cp (12);
653        }        }
654        # Anything else        # Anything else
655        my $token = {type => 'character',        my $token = {type => CHARACTER_TOKEN,
656                     data => chr $self->{next_input_character}};                     data => chr $self->{next_char},
657                       line => $self->{line}, column => $self->{column},
658                      };
659        ## Stay in the data state        ## Stay in the data state
660        !!!next-input-character;        !!!next-input-character;
661    
662        !!!emit ($token);        !!!emit ($token);
663    
664        redo A;        redo A;
665      } elsif ($self->{state} eq 'entity data') {      } elsif ($self->{state} == ENTITY_DATA_STATE) {
666        ## (cannot happen in CDATA state)        ## (cannot happen in CDATA state)
667    
668          my ($l, $c) = ($self->{line_prev}, $self->{column_prev});
669                
670        my $token = $self->_tokenize_attempt_to_consume_an_entity (0);        my $token = $self->_tokenize_attempt_to_consume_an_entity (0, -1);
671    
672        $self->{state} = 'data';        $self->{state} = DATA_STATE;
673        # next-input-character is already done        # next-input-character is already done
674    
675        unless (defined $token) {        unless (defined $token) {
676          !!!emit ({type => 'character', data => '&'});          !!!cp (13);
677            !!!emit ({type => CHARACTER_TOKEN, data => '&',
678                      line => $l, column => $c,
679                     });
680        } else {        } else {
681            !!!cp (14);
682          !!!emit ($token);          !!!emit ($token);
683        }        }
684    
685        redo A;        redo A;
686      } elsif ($self->{state} eq 'tag open') {      } elsif ($self->{state} == TAG_OPEN_STATE) {
687        if ($self->{content_model_flag} eq 'RCDATA' or        if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA
688            $self->{content_model_flag} eq 'CDATA') {          if ($self->{next_char} == 0x002F) { # /
689          if ($self->{next_input_character} == 0x002F) { # /            !!!cp (15);
690            !!!next-input-character;            !!!next-input-character;
691            $self->{state} = 'close tag open';            $self->{state} = CLOSE_TAG_OPEN_STATE;
692            redo A;            redo A;
693          } else {          } else {
694              !!!cp (16);
695            ## reconsume            ## reconsume
696            $self->{state} = 'data';            $self->{state} = DATA_STATE;
697    
698            !!!emit ({type => 'character', data => '<'});            !!!emit ({type => CHARACTER_TOKEN, data => '<',
699                        line => $self->{line_prev},
700                        column => $self->{column_prev},
701                       });
702    
703            redo A;            redo A;
704          }          }
705        } elsif ($self->{content_model_flag} eq 'PCDATA') {        } elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA
706          if ($self->{next_input_character} == 0x0021) { # !          if ($self->{next_char} == 0x0021) { # !
707            $self->{state} = 'markup declaration open';            !!!cp (17);
708              $self->{state} = MARKUP_DECLARATION_OPEN_STATE;
709            !!!next-input-character;            !!!next-input-character;
710            redo A;            redo A;
711          } elsif ($self->{next_input_character} == 0x002F) { # /          } elsif ($self->{next_char} == 0x002F) { # /
712            $self->{state} = 'close tag open';            !!!cp (18);
713              $self->{state} = CLOSE_TAG_OPEN_STATE;
714            !!!next-input-character;            !!!next-input-character;
715            redo A;            redo A;
716          } elsif (0x0041 <= $self->{next_input_character} and          } elsif (0x0041 <= $self->{next_char} and
717                   $self->{next_input_character} <= 0x005A) { # A..Z                   $self->{next_char} <= 0x005A) { # A..Z
718              !!!cp (19);
719            $self->{current_token}            $self->{current_token}
720              = {type => 'start tag',              = {type => START_TAG_TOKEN,
721                 tag_name => chr ($self->{next_input_character} + 0x0020)};                 tag_name => chr ($self->{next_char} + 0x0020),
722            $self->{state} = 'tag name';                 line => $self->{line_prev},
723                   column => $self->{column_prev}};
724              $self->{state} = TAG_NAME_STATE;
725            !!!next-input-character;            !!!next-input-character;
726            redo A;            redo A;
727          } elsif (0x0061 <= $self->{next_input_character} and          } elsif (0x0061 <= $self->{next_char} and
728                   $self->{next_input_character} <= 0x007A) { # a..z                   $self->{next_char} <= 0x007A) { # a..z
729            $self->{current_token} = {type => 'start tag',            !!!cp (20);
730                              tag_name => chr ($self->{next_input_character})};            $self->{current_token} = {type => START_TAG_TOKEN,
731            $self->{state} = 'tag name';                                      tag_name => chr ($self->{next_char}),
732                                        line => $self->{line_prev},
733                                        column => $self->{column_prev}};
734              $self->{state} = TAG_NAME_STATE;
735            !!!next-input-character;            !!!next-input-character;
736            redo A;            redo A;
737          } elsif ($self->{next_input_character} == 0x003E) { # >          } elsif ($self->{next_char} == 0x003E) { # >
738            !!!parse-error (type => 'empty start tag');            !!!cp (21);
739            $self->{state} = 'data';            !!!parse-error (type => 'empty start tag',
740                              line => $self->{line_prev},
741                              column => $self->{column_prev});
742              $self->{state} = DATA_STATE;
743            !!!next-input-character;            !!!next-input-character;
744    
745            !!!emit ({type => 'character', data => '<>'});            !!!emit ({type => CHARACTER_TOKEN, data => '<>',
746                        line => $self->{line_prev},
747                        column => $self->{column_prev},
748                       });
749    
750            redo A;            redo A;
751          } elsif ($self->{next_input_character} == 0x003F) { # ?          } elsif ($self->{next_char} == 0x003F) { # ?
752            !!!parse-error (type => 'pio');            !!!cp (22);
753            $self->{state} = 'bogus comment';            !!!parse-error (type => 'pio',
754            ## $self->{next_input_character} is intentionally left as is                            line => $self->{line_prev},
755                              column => $self->{column_prev});
756              $self->{state} = BOGUS_COMMENT_STATE;
757              $self->{current_token} = {type => COMMENT_TOKEN, data => '',
758                                        line => $self->{line_prev},
759                                        column => $self->{column_prev},
760                                       };
761              ## $self->{next_char} is intentionally left as is
762            redo A;            redo A;
763          } else {          } else {
764              !!!cp (23);
765            !!!parse-error (type => 'bare stago');            !!!parse-error (type => 'bare stago');
766            $self->{state} = 'data';            $self->{state} = DATA_STATE;
767            ## reconsume            ## reconsume
768    
769            !!!emit ({type => 'character', data => '<'});            !!!emit ({type => CHARACTER_TOKEN, data => '<',
770                        line => $self->{line_prev},
771                        column => $self->{column_prev},
772                       });
773    
774            redo A;            redo A;
775          }          }
776        } else {        } else {
777          die "$0: $self->{content_model_flag}: Unknown content model flag";          die "$0: $self->{content_model} in tag open";
778        }        }
779      } elsif ($self->{state} eq 'close tag open') {      } elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) {
780        if ($self->{content_model_flag} eq 'RCDATA' or        my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); # "<"of"</"
781            $self->{content_model_flag} eq 'CDATA') {        if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA
782          if (defined $self->{last_emitted_start_tag_name}) {          if (defined $self->{last_emitted_start_tag_name}) {
783    
784            ## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>            ## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>
785            my @next_char;            my @next_char;
786            TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) {            TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) {
787              push @next_char, $self->{next_input_character};              push @next_char, $self->{next_char};
788              my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1);              my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1);
789              my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c;              my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c;
790              if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) {              if ($self->{next_char} == $c or $self->{next_char} == $C) {
791                  !!!cp (24);
792                !!!next-input-character;                !!!next-input-character;
793                next TAGNAME;                next TAGNAME;
794              } else {              } else {
795                $self->{next_input_character} = shift @next_char; # reconsume                !!!cp (25);
796                  $self->{next_char} = shift @next_char; # reconsume
797                !!!back-next-input-character (@next_char);                !!!back-next-input-character (@next_char);
798                $self->{state} = 'data';                $self->{state} = DATA_STATE;
799    
800                !!!emit ({type => 'character', data => '</'});                !!!emit ({type => CHARACTER_TOKEN, data => '</',
801                            line => $l, column => $c,
802                           });
803        
804                redo A;                redo A;
805              }              }
806            }            }
807            push @next_char, $self->{next_input_character};            push @next_char, $self->{next_char};
808                
809            unless ($self->{next_input_character} == 0x0009 or # HT            unless ($self->{next_char} == 0x0009 or # HT
810                    $self->{next_input_character} == 0x000A or # LF                    $self->{next_char} == 0x000A or # LF
811                    $self->{next_input_character} == 0x000B or # VT                    $self->{next_char} == 0x000B or # VT
812                    $self->{next_input_character} == 0x000C or # FF                    $self->{next_char} == 0x000C or # FF
813                    $self->{next_input_character} == 0x0020 or # SP                    $self->{next_char} == 0x0020 or # SP
814                    $self->{next_input_character} == 0x003E or # >                    $self->{next_char} == 0x003E or # >
815                    $self->{next_input_character} == 0x002F or # /                    $self->{next_char} == 0x002F or # /
816                    $self->{next_input_character} == -1) {                    $self->{next_char} == -1) {
817              $self->{next_input_character} = shift @next_char; # reconsume              !!!cp (26);
818                $self->{next_char} = shift @next_char; # reconsume
819              !!!back-next-input-character (@next_char);              !!!back-next-input-character (@next_char);
820              $self->{state} = 'data';              $self->{state} = DATA_STATE;
821              !!!emit ({type => 'character', data => '</'});              !!!emit ({type => CHARACTER_TOKEN, data => '</',
822                          line => $l, column => $c,
823                         });
824              redo A;              redo A;
825            } else {            } else {
826              $self->{next_input_character} = shift @next_char;              !!!cp (27);
827                $self->{next_char} = shift @next_char;
828              !!!back-next-input-character (@next_char);              !!!back-next-input-character (@next_char);
829              # and consume...              # and consume...
830            }            }
831          } else {          } else {
832            ## No start tag token has ever been emitted            ## No start tag token has ever been emitted
833              !!!cp (28);
834            # next-input-character is already done            # next-input-character is already done
835            $self->{state} = 'data';            $self->{state} = DATA_STATE;
836            !!!emit ({type => 'character', data => '</'});            !!!emit ({type => CHARACTER_TOKEN, data => '</',
837                        line => $l, column => $c,
838                       });
839            redo A;            redo A;
840          }          }
841        }        }
842                
843        if (0x0041 <= $self->{next_input_character} and        if (0x0041 <= $self->{next_char} and
844            $self->{next_input_character} <= 0x005A) { # A..Z            $self->{next_char} <= 0x005A) { # A..Z
845          $self->{current_token} = {type => 'end tag',          !!!cp (29);
846                            tag_name => chr ($self->{next_input_character} + 0x0020)};          $self->{current_token}
847          $self->{state} = 'tag name';              = {type => END_TAG_TOKEN,
848          !!!next-input-character;                 tag_name => chr ($self->{next_char} + 0x0020),
849          redo A;                 line => $l, column => $c};
850        } elsif (0x0061 <= $self->{next_input_character} and          $self->{state} = TAG_NAME_STATE;
851                 $self->{next_input_character} <= 0x007A) { # a..z          !!!next-input-character;
852          $self->{current_token} = {type => 'end tag',          redo A;
853                            tag_name => chr ($self->{next_input_character})};        } elsif (0x0061 <= $self->{next_char} and
854          $self->{state} = 'tag name';                 $self->{next_char} <= 0x007A) { # a..z
855          !!!next-input-character;          !!!cp (30);
856          redo A;          $self->{current_token} = {type => END_TAG_TOKEN,
857        } elsif ($self->{next_input_character} == 0x003E) { # >                                    tag_name => chr ($self->{next_char}),
858          !!!parse-error (type => 'empty end tag');                                    line => $l, column => $c};
859          $self->{state} = 'data';          $self->{state} = TAG_NAME_STATE;
860            !!!next-input-character;
861            redo A;
862          } elsif ($self->{next_char} == 0x003E) { # >
863            !!!cp (31);
864            !!!parse-error (type => 'empty end tag',
865                            line => $self->{line_prev}, ## "<" in "</>"
866                            column => $self->{column_prev} - 1);
867            $self->{state} = DATA_STATE;
868          !!!next-input-character;          !!!next-input-character;
869          redo A;          redo A;
870        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
871            !!!cp (32);
872          !!!parse-error (type => 'bare etago');          !!!parse-error (type => 'bare etago');
873          $self->{state} = 'data';          $self->{state} = DATA_STATE;
874          # reconsume          # reconsume
875    
876          !!!emit ({type => 'character', data => '</'});          !!!emit ({type => CHARACTER_TOKEN, data => '</',
877                      line => $l, column => $c,
878                     });
879    
880          redo A;          redo A;
881        } else {        } else {
882            !!!cp (33);
883          !!!parse-error (type => 'bogus end tag');          !!!parse-error (type => 'bogus end tag');
884          $self->{state} = 'bogus comment';          $self->{state} = BOGUS_COMMENT_STATE;
885          ## $self->{next_input_character} is intentionally left as is          $self->{current_token} = {type => COMMENT_TOKEN, data => '',
886          redo A;                                    line => $self->{line_prev}, # "<" of "</"
887        }                                    column => $self->{column_prev} - 1,
888      } elsif ($self->{state} eq 'tag name') {                                   };
889        if ($self->{next_input_character} == 0x0009 or # HT          ## $self->{next_char} is intentionally left as is
890            $self->{next_input_character} == 0x000A or # LF          redo A;
891            $self->{next_input_character} == 0x000B or # VT        }
892            $self->{next_input_character} == 0x000C or # FF      } elsif ($self->{state} == TAG_NAME_STATE) {
893            $self->{next_input_character} == 0x0020) { # SP        if ($self->{next_char} == 0x0009 or # HT
894          $self->{state} = 'before attribute name';            $self->{next_char} == 0x000A or # LF
895          !!!next-input-character;            $self->{next_char} == 0x000B or # VT
896          redo A;            $self->{next_char} == 0x000C or # FF
897        } elsif ($self->{next_input_character} == 0x003E) { # >            $self->{next_char} == 0x0020) { # SP
898          if ($self->{current_token}->{type} eq 'start tag') {          !!!cp (34);
899            $self->{current_token}->{first_start_tag}          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
900                = not defined $self->{last_emitted_start_tag_name};          !!!next-input-character;
901            redo A;
902          } elsif ($self->{next_char} == 0x003E) { # >
903            if ($self->{current_token}->{type} == START_TAG_TOKEN) {
904              !!!cp (35);
905            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
906          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
907            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
908            if ($self->{current_token}->{attributes}) {            #if ($self->{current_token}->{attributes}) {
909              !!!parse-error (type => 'end tag attribute');            #  ## NOTE: This should never be reached.
910            }            #  !!! cp (36);
911              #  !!! parse-error (type => 'end tag attribute');
912              #} else {
913                !!!cp (37);
914              #}
915          } else {          } else {
916            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
917          }          }
918          $self->{state} = 'data';          $self->{state} = DATA_STATE;
919          !!!next-input-character;          !!!next-input-character;
920    
921          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
922    
923          redo A;          redo A;
924        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
925                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
926          $self->{current_token}->{tag_name} .= chr ($self->{next_input_character} + 0x0020);          !!!cp (38);
927            $self->{current_token}->{tag_name} .= chr ($self->{next_char} + 0x0020);
928            # start tag or end tag            # start tag or end tag
929          ## Stay in this state          ## Stay in this state
930          !!!next-input-character;          !!!next-input-character;
931          redo A;          redo A;
932        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
933          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
934          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
935            $self->{current_token}->{first_start_tag}            !!!cp (39);
               = not defined $self->{last_emitted_start_tag_name};  
936            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
937          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
938            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
939            if ($self->{current_token}->{attributes}) {            #if ($self->{current_token}->{attributes}) {
940              !!!parse-error (type => 'end tag attribute');            #  ## NOTE: This state should never be reached.
941            }            #  !!! cp (40);
942              #  !!! parse-error (type => 'end tag attribute');
943              #} else {
944                !!!cp (41);
945              #}
946          } else {          } else {
947            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
948          }          }
949          $self->{state} = 'data';          $self->{state} = DATA_STATE;
950          # reconsume          # reconsume
951    
952          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
953    
954          redo A;          redo A;
955        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == 0x002F) { # /
956            !!!cp (42);
957            $self->{state} = SELF_CLOSING_START_TAG_STATE;
958          !!!next-input-character;          !!!next-input-character;
         if ($self->{next_input_character} == 0x003E and # >  
             $self->{current_token}->{type} eq 'start tag' and  
             $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {  
           # permitted slash  
           #  
         } else {  
           !!!parse-error (type => 'nestc');  
         }  
         $self->{state} = 'before attribute name';  
         # next-input-character is already done  
959          redo A;          redo A;
960        } else {        } else {
961          $self->{current_token}->{tag_name} .= chr $self->{next_input_character};          !!!cp (44);
962            $self->{current_token}->{tag_name} .= chr $self->{next_char};
963            # start tag or end tag            # start tag or end tag
964          ## Stay in the state          ## Stay in the state
965          !!!next-input-character;          !!!next-input-character;
966          redo A;          redo A;
967        }        }
968      } elsif ($self->{state} eq 'before attribute name') {      } elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) {
969        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
970            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
971            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
972            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
973            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
974            !!!cp (45);
975          ## Stay in the state          ## Stay in the state
976          !!!next-input-character;          !!!next-input-character;
977          redo A;          redo A;
978        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
979          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
980            $self->{current_token}->{first_start_tag}            !!!cp (46);
               = not defined $self->{last_emitted_start_tag_name};  
981            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
982          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
983            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
984            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
985                !!!cp (47);
986              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
987              } else {
988                !!!cp (48);
989            }            }
990          } else {          } else {
991            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
992          }          }
993          $self->{state} = 'data';          $self->{state} = DATA_STATE;
994          !!!next-input-character;          !!!next-input-character;
995    
996          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
997    
998          redo A;          redo A;
999        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
1000                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
1001          $self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020),          !!!cp (49);
1002                                value => ''};          $self->{current_attribute}
1003          $self->{state} = 'attribute name';              = {name => chr ($self->{next_char} + 0x0020),
1004                   value => '',
1005                   line => $self->{line}, column => $self->{column}};
1006            $self->{state} = ATTRIBUTE_NAME_STATE;
1007            !!!next-input-character;
1008            redo A;
1009          } elsif ($self->{next_char} == 0x002F) { # /
1010            !!!cp (50);
1011            $self->{state} = SELF_CLOSING_START_TAG_STATE;
1012          !!!next-input-character;          !!!next-input-character;
1013          redo A;          redo A;
1014        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == -1) {
         !!!next-input-character;  
         if ($self->{next_input_character} == 0x003E and # >  
             $self->{current_token}->{type} eq 'start tag' and  
             $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {  
           # permitted slash  
           #  
         } else {  
           !!!parse-error (type => 'nestc');  
         }  
         ## Stay in the state  
         # next-input-character is already done  
         redo A;  
       } elsif ($self->{next_input_character} == -1) {  
1015          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1016          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1017            $self->{current_token}->{first_start_tag}            !!!cp (52);
               = not defined $self->{last_emitted_start_tag_name};  
1018            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1019          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1020            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1021            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1022                !!!cp (53);
1023              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1024              } else {
1025                !!!cp (54);
1026            }            }
1027          } else {          } else {
1028            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1029          }          }
1030          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1031          # reconsume          # reconsume
1032    
1033          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1034    
1035          redo A;          redo A;
1036        } else {        } else {
1037          $self->{current_attribute} = {name => chr ($self->{next_input_character}),          if ({
1038                                value => ''};               0x0022 => 1, # "
1039          $self->{state} = 'attribute name';               0x0027 => 1, # '
1040                 0x003D => 1, # =
1041                }->{$self->{next_char}}) {
1042              !!!cp (55);
1043              !!!parse-error (type => 'bad attribute name');
1044            } else {
1045              !!!cp (56);
1046            }
1047            $self->{current_attribute}
1048                = {name => chr ($self->{next_char}),
1049                   value => '',
1050                   line => $self->{line}, column => $self->{column}};
1051            $self->{state} = ATTRIBUTE_NAME_STATE;
1052          !!!next-input-character;          !!!next-input-character;
1053          redo A;          redo A;
1054        }        }
1055      } elsif ($self->{state} eq 'attribute name') {      } elsif ($self->{state} == ATTRIBUTE_NAME_STATE) {
1056        my $before_leave = sub {        my $before_leave = sub {
1057          if (exists $self->{current_token}->{attributes} # start tag or end tag          if (exists $self->{current_token}->{attributes} # start tag or end tag
1058              ->{$self->{current_attribute}->{name}}) { # MUST              ->{$self->{current_attribute}->{name}}) { # MUST
1059            !!!parse-error (type => 'dupulicate attribute');            !!!cp (57);
1060              !!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}, line => $self->{current_attribute}->{line}, column => $self->{current_attribute}->{column});
1061            ## Discard $self->{current_attribute} # MUST            ## Discard $self->{current_attribute} # MUST
1062          } else {          } else {
1063              !!!cp (58);
1064            $self->{current_token}->{attributes}->{$self->{current_attribute}->{name}}            $self->{current_token}->{attributes}->{$self->{current_attribute}->{name}}
1065              = $self->{current_attribute};              = $self->{current_attribute};
1066          }          }
1067        }; # $before_leave        }; # $before_leave
1068    
1069        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1070            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1071            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1072            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1073            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1074            !!!cp (59);
1075          $before_leave->();          $before_leave->();
1076          $self->{state} = 'after attribute name';          $self->{state} = AFTER_ATTRIBUTE_NAME_STATE;
1077          !!!next-input-character;          !!!next-input-character;
1078          redo A;          redo A;
1079        } elsif ($self->{next_input_character} == 0x003D) { # =        } elsif ($self->{next_char} == 0x003D) { # =
1080            !!!cp (60);
1081          $before_leave->();          $before_leave->();
1082          $self->{state} = 'before attribute value';          $self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE;
1083          !!!next-input-character;          !!!next-input-character;
1084          redo A;          redo A;
1085        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1086          $before_leave->();          $before_leave->();
1087          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1088            $self->{current_token}->{first_start_tag}            !!!cp (61);
               = not defined $self->{last_emitted_start_tag_name};  
1089            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1090          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1091            $self->{content_model_flag} = 'PCDATA'; # MUST            !!!cp (62);
1092              $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1093            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1094              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1095            }            }
1096          } else {          } else {
1097            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1098          }          }
1099          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1100          !!!next-input-character;          !!!next-input-character;
1101    
1102          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1103    
1104          redo A;          redo A;
1105        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
1106                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
1107          $self->{current_attribute}->{name} .= chr ($self->{next_input_character} + 0x0020);          !!!cp (63);
1108            $self->{current_attribute}->{name} .= chr ($self->{next_char} + 0x0020);
1109          ## Stay in the state          ## Stay in the state
1110          !!!next-input-character;          !!!next-input-character;
1111          redo A;          redo A;
1112        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == 0x002F) { # /
1113            !!!cp (64);
1114          $before_leave->();          $before_leave->();
1115            $self->{state} = SELF_CLOSING_START_TAG_STATE;
1116          !!!next-input-character;          !!!next-input-character;
         if ($self->{next_input_character} == 0x003E and # >  
             $self->{current_token}->{type} eq 'start tag' and  
             $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {  
           # permitted slash  
           #  
         } else {  
           !!!parse-error (type => 'nestc');  
         }  
         $self->{state} = 'before attribute name';  
         # next-input-character is already done  
1117          redo A;          redo A;
1118        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1119          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1120          $before_leave->();          $before_leave->();
1121          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1122            $self->{current_token}->{first_start_tag}            !!!cp (66);
               = not defined $self->{last_emitted_start_tag_name};  
1123            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1124          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1125            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1126            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1127                !!!cp (67);
1128              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1129              } else {
1130                ## NOTE: This state should never be reached.
1131                !!!cp (68);
1132            }            }
1133          } else {          } else {
1134            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1135          }          }
1136          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1137          # reconsume          # reconsume
1138    
1139          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1140    
1141          redo A;          redo A;
1142        } else {        } else {
1143          $self->{current_attribute}->{name} .= chr ($self->{next_input_character});          if ($self->{next_char} == 0x0022 or # "
1144                $self->{next_char} == 0x0027) { # '
1145              !!!cp (69);
1146              !!!parse-error (type => 'bad attribute name');
1147            } else {
1148              !!!cp (70);
1149            }
1150            $self->{current_attribute}->{name} .= chr ($self->{next_char});
1151          ## Stay in the state          ## Stay in the state
1152          !!!next-input-character;          !!!next-input-character;
1153          redo A;          redo A;
1154        }        }
1155      } elsif ($self->{state} eq 'after attribute name') {      } elsif ($self->{state} == AFTER_ATTRIBUTE_NAME_STATE) {
1156        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1157            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1158            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1159            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1160            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1161            !!!cp (71);
1162          ## Stay in the state          ## Stay in the state
1163          !!!next-input-character;          !!!next-input-character;
1164          redo A;          redo A;
1165        } elsif ($self->{next_input_character} == 0x003D) { # =        } elsif ($self->{next_char} == 0x003D) { # =
1166          $self->{state} = 'before attribute value';          !!!cp (72);
1167            $self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE;
1168          !!!next-input-character;          !!!next-input-character;
1169          redo A;          redo A;
1170        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1171          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1172            $self->{current_token}->{first_start_tag}            !!!cp (73);
               = not defined $self->{last_emitted_start_tag_name};  
1173            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1174          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1175            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1176            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1177                !!!cp (74);
1178              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1179              } else {
1180                ## NOTE: This state should never be reached.
1181                !!!cp (75);
1182            }            }
1183          } else {          } else {
1184            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1185          }          }
1186          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1187          !!!next-input-character;          !!!next-input-character;
1188    
1189          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1190    
1191          redo A;          redo A;
1192        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
1193                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
1194          $self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020),          !!!cp (76);
1195                                value => ''};          $self->{current_attribute}
1196          $self->{state} = 'attribute name';              = {name => chr ($self->{next_char} + 0x0020),
1197                   value => '',
1198                   line => $self->{line}, column => $self->{column}};
1199            $self->{state} = ATTRIBUTE_NAME_STATE;
1200            !!!next-input-character;
1201            redo A;
1202          } elsif ($self->{next_char} == 0x002F) { # /
1203            !!!cp (77);
1204            $self->{state} = SELF_CLOSING_START_TAG_STATE;
1205          !!!next-input-character;          !!!next-input-character;
1206          redo A;          redo A;
1207        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == -1) {
         !!!next-input-character;  
         if ($self->{next_input_character} == 0x003E and # >  
             $self->{current_token}->{type} eq 'start tag' and  
             $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {  
           # permitted slash  
           #  
         } else {  
           !!!parse-error (type => 'nestc');  
           ## TODO: Different error type for <aa / bb> than <aa/>  
         }  
         $self->{state} = 'before attribute name';  
         # next-input-character is already done  
         redo A;  
       } elsif ($self->{next_input_character} == -1) {  
1208          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1209          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1210            $self->{current_token}->{first_start_tag}            !!!cp (79);
               = not defined $self->{last_emitted_start_tag_name};  
1211            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1212          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1213            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1214            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1215                !!!cp (80);
1216              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1217              } else {
1218                ## NOTE: This state should never be reached.
1219                !!!cp (81);
1220            }            }
1221          } else {          } else {
1222            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1223          }          }
1224          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1225          # reconsume          # reconsume
1226    
1227          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1228    
1229          redo A;          redo A;
1230        } else {        } else {
1231          $self->{current_attribute} = {name => chr ($self->{next_input_character}),          !!!cp (82);
1232                                value => ''};          $self->{current_attribute}
1233          $self->{state} = 'attribute name';              = {name => chr ($self->{next_char}),
1234                   value => '',
1235                   line => $self->{line}, column => $self->{column}};
1236            $self->{state} = ATTRIBUTE_NAME_STATE;
1237          !!!next-input-character;          !!!next-input-character;
1238          redo A;                  redo A;        
1239        }        }
1240      } elsif ($self->{state} eq 'before attribute value') {      } elsif ($self->{state} == BEFORE_ATTRIBUTE_VALUE_STATE) {
1241        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1242            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1243            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1244            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1245            $self->{next_input_character} == 0x0020) { # SP                  $self->{next_char} == 0x0020) { # SP      
1246            !!!cp (83);
1247          ## Stay in the state          ## Stay in the state
1248          !!!next-input-character;          !!!next-input-character;
1249          redo A;          redo A;
1250        } elsif ($self->{next_input_character} == 0x0022) { # "        } elsif ($self->{next_char} == 0x0022) { # "
1251          $self->{state} = 'attribute value (double-quoted)';          !!!cp (84);
1252            $self->{state} = ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE;
1253          !!!next-input-character;          !!!next-input-character;
1254          redo A;          redo A;
1255        } elsif ($self->{next_input_character} == 0x0026) { # &        } elsif ($self->{next_char} == 0x0026) { # &
1256          $self->{state} = 'attribute value (unquoted)';          !!!cp (85);
1257            $self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE;
1258          ## reconsume          ## reconsume
1259          redo A;          redo A;
1260        } elsif ($self->{next_input_character} == 0x0027) { # '        } elsif ($self->{next_char} == 0x0027) { # '
1261          $self->{state} = 'attribute value (single-quoted)';          !!!cp (86);
1262            $self->{state} = ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE;
1263          !!!next-input-character;          !!!next-input-character;
1264          redo A;          redo A;
1265        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1266          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1267            $self->{current_token}->{first_start_tag}            !!!cp (87);
               = not defined $self->{last_emitted_start_tag_name};  
1268            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1269          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1270            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1271            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1272                !!!cp (88);
1273              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1274              } else {
1275                ## NOTE: This state should never be reached.
1276                !!!cp (89);
1277            }            }
1278          } else {          } else {
1279            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1280          }          }
1281          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1282          !!!next-input-character;          !!!next-input-character;
1283    
1284          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1285    
1286          redo A;          redo A;
1287        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1288          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1289          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1290            $self->{current_token}->{first_start_tag}            !!!cp (90);
               = not defined $self->{last_emitted_start_tag_name};  
1291            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1292          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1293            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1294            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1295                !!!cp (91);
1296              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1297              } else {
1298                ## NOTE: This state should never be reached.
1299                !!!cp (92);
1300            }            }
1301          } else {          } else {
1302            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1303          }          }
1304          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1305          ## reconsume          ## reconsume
1306    
1307          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1308    
1309          redo A;          redo A;
1310        } else {        } else {
1311          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          if ($self->{next_char} == 0x003D) { # =
1312          $self->{state} = 'attribute value (unquoted)';            !!!cp (93);
1313              !!!parse-error (type => 'bad attribute value');
1314            } else {
1315              !!!cp (94);
1316            }
1317            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1318            $self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE;
1319          !!!next-input-character;          !!!next-input-character;
1320          redo A;          redo A;
1321        }        }
1322      } elsif ($self->{state} eq 'attribute value (double-quoted)') {      } elsif ($self->{state} == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE) {
1323        if ($self->{next_input_character} == 0x0022) { # "        if ($self->{next_char} == 0x0022) { # "
1324          $self->{state} = 'before attribute name';          !!!cp (95);
1325            $self->{state} = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE;
1326          !!!next-input-character;          !!!next-input-character;
1327          redo A;          redo A;
1328        } elsif ($self->{next_input_character} == 0x0026) { # &        } elsif ($self->{next_char} == 0x0026) { # &
1329          $self->{last_attribute_value_state} = 'attribute value (double-quoted)';          !!!cp (96);
1330          $self->{state} = 'entity in attribute value';          $self->{last_attribute_value_state} = $self->{state};
1331            $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;
1332          !!!next-input-character;          !!!next-input-character;
1333          redo A;          redo A;
1334        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1335          !!!parse-error (type => 'unclosed attribute value');          !!!parse-error (type => 'unclosed attribute value');
1336          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1337            $self->{current_token}->{first_start_tag}            !!!cp (97);
               = not defined $self->{last_emitted_start_tag_name};  
1338            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1339          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1340            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1341            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1342                !!!cp (98);
1343              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1344              } else {
1345                ## NOTE: This state should never be reached.
1346                !!!cp (99);
1347            }            }
1348          } else {          } else {
1349            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1350          }          }
1351          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1352          ## reconsume          ## reconsume
1353    
1354          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1355    
1356          redo A;          redo A;
1357        } else {        } else {
1358          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          !!!cp (100);
1359            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1360          ## Stay in the state          ## Stay in the state
1361          !!!next-input-character;          !!!next-input-character;
1362          redo A;          redo A;
1363        }        }
1364      } elsif ($self->{state} eq 'attribute value (single-quoted)') {      } elsif ($self->{state} == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE) {
1365        if ($self->{next_input_character} == 0x0027) { # '        if ($self->{next_char} == 0x0027) { # '
1366          $self->{state} = 'before attribute name';          !!!cp (101);
1367            $self->{state} = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE;
1368          !!!next-input-character;          !!!next-input-character;
1369          redo A;          redo A;
1370        } elsif ($self->{next_input_character} == 0x0026) { # &        } elsif ($self->{next_char} == 0x0026) { # &
1371          $self->{last_attribute_value_state} = 'attribute value (single-quoted)';          !!!cp (102);
1372          $self->{state} = 'entity in attribute value';          $self->{last_attribute_value_state} = $self->{state};
1373            $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;
1374          !!!next-input-character;          !!!next-input-character;
1375          redo A;          redo A;
1376        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1377          !!!parse-error (type => 'unclosed attribute value');          !!!parse-error (type => 'unclosed attribute value');
1378          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1379            $self->{current_token}->{first_start_tag}            !!!cp (103);
               = not defined $self->{last_emitted_start_tag_name};  
1380            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1381          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1382            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1383            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1384                !!!cp (104);
1385              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1386              } else {
1387                ## NOTE: This state should never be reached.
1388                !!!cp (105);
1389            }            }
1390          } else {          } else {
1391            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1392          }          }
1393          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1394          ## reconsume          ## reconsume
1395    
1396          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1397    
1398          redo A;          redo A;
1399        } else {        } else {
1400          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          !!!cp (106);
1401            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1402          ## Stay in the state          ## Stay in the state
1403          !!!next-input-character;          !!!next-input-character;
1404          redo A;          redo A;
1405        }        }
1406      } elsif ($self->{state} eq 'attribute value (unquoted)') {      } elsif ($self->{state} == ATTRIBUTE_VALUE_UNQUOTED_STATE) {
1407        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1408            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1409            $self->{next_input_character} == 0x000B or # HT            $self->{next_char} == 0x000B or # HT
1410            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1411            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1412          $self->{state} = 'before attribute name';          !!!cp (107);
1413          !!!next-input-character;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1414          redo A;          !!!next-input-character;
1415        } elsif ($self->{next_input_character} == 0x0026) { # &          redo A;
1416          $self->{last_attribute_value_state} = 'attribute value (unquoted)';        } elsif ($self->{next_char} == 0x0026) { # &
1417          $self->{state} = 'entity in attribute value';          !!!cp (108);
1418          !!!next-input-character;          $self->{last_attribute_value_state} = $self->{state};
1419          redo A;          $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;
1420        } elsif ($self->{next_input_character} == 0x003E) { # >          !!!next-input-character;
1421          if ($self->{current_token}->{type} eq 'start tag') {          redo A;
1422            $self->{current_token}->{first_start_tag}        } elsif ($self->{next_char} == 0x003E) { # >
1423                = not defined $self->{last_emitted_start_tag_name};          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1424              !!!cp (109);
1425            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1426          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1427            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1428            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1429                !!!cp (110);
1430              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1431              } else {
1432                ## NOTE: This state should never be reached.
1433                !!!cp (111);
1434            }            }
1435          } else {          } else {
1436            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1437          }          }
1438          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1439          !!!next-input-character;          !!!next-input-character;
1440    
1441          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1442    
1443          redo A;          redo A;
1444        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1445          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1446          if ($self->{current_token}->{type} eq 'start tag') {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1447            $self->{current_token}->{first_start_tag}            !!!cp (112);
               = not defined $self->{last_emitted_start_tag_name};  
1448            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1449          } elsif ($self->{current_token}->{type} eq 'end tag') {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1450            $self->{content_model_flag} = 'PCDATA'; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1451            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1452                !!!cp (113);
1453              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1454              } else {
1455                ## NOTE: This state should never be reached.
1456                !!!cp (114);
1457            }            }
1458          } else {          } else {
1459            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
1460          }          }
1461          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1462          ## reconsume          ## reconsume
1463    
1464          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1465    
1466          redo A;          redo A;
1467        } else {        } else {
1468          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          if ({
1469                 0x0022 => 1, # "
1470                 0x0027 => 1, # '
1471                 0x003D => 1, # =
1472                }->{$self->{next_char}}) {
1473              !!!cp (115);
1474              !!!parse-error (type => 'bad attribute value');
1475            } else {
1476              !!!cp (116);
1477            }
1478            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1479          ## Stay in the state          ## Stay in the state
1480          !!!next-input-character;          !!!next-input-character;
1481          redo A;          redo A;
1482        }        }
1483      } elsif ($self->{state} eq 'entity in attribute value') {      } elsif ($self->{state} == ENTITY_IN_ATTRIBUTE_VALUE_STATE) {
1484        my $token = $self->_tokenize_attempt_to_consume_an_entity (1);        my $token = $self->_tokenize_attempt_to_consume_an_entity
1485              (1,
1486               $self->{last_attribute_value_state}
1487                 == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE ? 0x0022 : # "
1488               $self->{last_attribute_value_state}
1489                 == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE ? 0x0027 : # '
1490               -1);
1491    
1492        unless (defined $token) {        unless (defined $token) {
1493            !!!cp (117);
1494          $self->{current_attribute}->{value} .= '&';          $self->{current_attribute}->{value} .= '&';
1495        } else {        } else {
1496            !!!cp (118);
1497          $self->{current_attribute}->{value} .= $token->{data};          $self->{current_attribute}->{value} .= $token->{data};
1498            $self->{current_attribute}->{has_reference} = $token->{has_reference};
1499          ## ISSUE: spec says "append the returned character token to the current attribute's value"          ## ISSUE: spec says "append the returned character token to the current attribute's value"
1500        }        }
1501    
1502        $self->{state} = $self->{last_attribute_value_state};        $self->{state} = $self->{last_attribute_value_state};
1503        # next-input-character is already done        # next-input-character is already done
1504        redo A;        redo A;
1505      } elsif ($self->{state} eq 'bogus comment') {      } elsif ($self->{state} == AFTER_ATTRIBUTE_VALUE_QUOTED_STATE) {
1506          if ($self->{next_char} == 0x0009 or # HT
1507              $self->{next_char} == 0x000A or # LF
1508              $self->{next_char} == 0x000B or # VT
1509              $self->{next_char} == 0x000C or # FF
1510              $self->{next_char} == 0x0020) { # SP
1511            !!!cp (118);
1512            $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1513            !!!next-input-character;
1514            redo A;
1515          } elsif ($self->{next_char} == 0x003E) { # >
1516            if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1517              !!!cp (119);
1518              $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1519            } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1520              $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1521              if ($self->{current_token}->{attributes}) {
1522                !!!cp (120);
1523                !!!parse-error (type => 'end tag attribute');
1524              } else {
1525                ## NOTE: This state should never be reached.
1526                !!!cp (121);
1527              }
1528            } else {
1529              die "$0: $self->{current_token}->{type}: Unknown token type";
1530            }
1531            $self->{state} = DATA_STATE;
1532            !!!next-input-character;
1533    
1534            !!!emit ($self->{current_token}); # start tag or end tag
1535    
1536            redo A;
1537          } elsif ($self->{next_char} == 0x002F) { # /
1538            !!!cp (122);
1539            $self->{state} = SELF_CLOSING_START_TAG_STATE;
1540            !!!next-input-character;
1541            redo A;
1542          } else {
1543            !!!cp ('124.1');
1544            !!!parse-error (type => 'no space between attributes');
1545            $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1546            ## reconsume
1547            redo A;
1548          }
1549        } elsif ($self->{state} == SELF_CLOSING_START_TAG_STATE) {
1550          if ($self->{next_char} == 0x003E) { # >
1551            if ($self->{current_token}->{type} == END_TAG_TOKEN) {
1552              !!!cp ('124.2');
1553              !!!parse-error (type => 'nestc', token => $self->{current_token});
1554              ## TODO: Different type than slash in start tag
1555              $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1556              if ($self->{current_token}->{attributes}) {
1557                !!!cp ('124.4');
1558                !!!parse-error (type => 'end tag attribute');
1559              } else {
1560                !!!cp ('124.5');
1561              }
1562              ## TODO: Test |<title></title/>|
1563            } else {
1564              !!!cp ('124.3');
1565              $self->{self_closing} = 1;
1566            }
1567    
1568            $self->{state} = DATA_STATE;
1569            !!!next-input-character;
1570    
1571            !!!emit ($self->{current_token}); # start tag or end tag
1572    
1573            redo A;
1574          } else {
1575            !!!cp ('124.4');
1576            !!!parse-error (type => 'nestc');
1577            ## TODO: This error type is wrong.
1578            $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1579            ## Reconsume.
1580            redo A;
1581          }
1582        } elsif ($self->{state} == BOGUS_COMMENT_STATE) {
1583        ## (only happen if PCDATA state)        ## (only happen if PCDATA state)
1584                
1585        my $token = {type => 'comment', data => ''};        ## NOTE: Set by the previous state
1586          #my $token = {type => COMMENT_TOKEN, data => ''};
1587    
1588        BC: {        BC: {
1589          if ($self->{next_input_character} == 0x003E) { # >          if ($self->{next_char} == 0x003E) { # >
1590            $self->{state} = 'data';            !!!cp (124);
1591              $self->{state} = DATA_STATE;
1592            !!!next-input-character;            !!!next-input-character;
1593    
1594            !!!emit ($token);            !!!emit ($self->{current_token}); # comment
1595    
1596            redo A;            redo A;
1597          } elsif ($self->{next_input_character} == -1) {          } elsif ($self->{next_char} == -1) {
1598            $self->{state} = 'data';            !!!cp (125);
1599              $self->{state} = DATA_STATE;
1600            ## reconsume            ## reconsume
1601    
1602            !!!emit ($token);            !!!emit ($self->{current_token}); # comment
1603    
1604            redo A;            redo A;
1605          } else {          } else {
1606            $token->{data} .= chr ($self->{next_input_character});            !!!cp (126);
1607              $self->{current_token}->{data} .= chr ($self->{next_char}); # comment
1608            !!!next-input-character;            !!!next-input-character;
1609            redo BC;            redo BC;
1610          }          }
1611        } # BC        } # BC
1612      } elsif ($self->{state} eq 'markup declaration open') {  
1613          die "$0: _get_next_token: unexpected case [BC]";
1614        } elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) {
1615        ## (only happen if PCDATA state)        ## (only happen if PCDATA state)
1616    
1617          my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1);
1618    
1619        my @next_char;        my @next_char;
1620        push @next_char, $self->{next_input_character};        push @next_char, $self->{next_char};
1621                
1622        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1623          !!!next-input-character;          !!!next-input-character;
1624          push @next_char, $self->{next_input_character};          push @next_char, $self->{next_char};
1625          if ($self->{next_input_character} == 0x002D) { # -          if ($self->{next_char} == 0x002D) { # -
1626            $self->{current_token} = {type => 'comment', data => ''};            !!!cp (127);
1627            $self->{state} = 'comment start';            $self->{current_token} = {type => COMMENT_TOKEN, data => '',
1628                                        line => $l, column => $c,
1629                                       };
1630              $self->{state} = COMMENT_START_STATE;
1631            !!!next-input-character;            !!!next-input-character;
1632            redo A;            redo A;
1633            } else {
1634              !!!cp (128);
1635            }
1636          } elsif ($self->{next_char} == 0x0044 or # D
1637                   $self->{next_char} == 0x0064) { # d
1638            !!!next-input-character;
1639            push @next_char, $self->{next_char};
1640            if ($self->{next_char} == 0x004F or # O
1641                $self->{next_char} == 0x006F) { # o
1642              !!!next-input-character;
1643              push @next_char, $self->{next_char};
1644              if ($self->{next_char} == 0x0043 or # C
1645                  $self->{next_char} == 0x0063) { # c
1646                !!!next-input-character;
1647                push @next_char, $self->{next_char};
1648                if ($self->{next_char} == 0x0054 or # T
1649                    $self->{next_char} == 0x0074) { # t
1650                  !!!next-input-character;
1651                  push @next_char, $self->{next_char};
1652                  if ($self->{next_char} == 0x0059 or # Y
1653                      $self->{next_char} == 0x0079) { # y
1654                    !!!next-input-character;
1655                    push @next_char, $self->{next_char};
1656                    if ($self->{next_char} == 0x0050 or # P
1657                        $self->{next_char} == 0x0070) { # p
1658                      !!!next-input-character;
1659                      push @next_char, $self->{next_char};
1660                      if ($self->{next_char} == 0x0045 or # E
1661                          $self->{next_char} == 0x0065) { # e
1662                        !!!cp (129);
1663                        ## TODO: What a stupid code this is!
1664                        $self->{state} = DOCTYPE_STATE;
1665                        $self->{current_token} = {type => DOCTYPE_TOKEN,
1666                                                  quirks => 1,
1667                                                  line => $l, column => $c,
1668                                                 };
1669                        !!!next-input-character;
1670                        redo A;
1671                      } else {
1672                        !!!cp (130);
1673                      }
1674                    } else {
1675                      !!!cp (131);
1676                    }
1677                  } else {
1678                    !!!cp (132);
1679                  }
1680                } else {
1681                  !!!cp (133);
1682                }
1683              } else {
1684                !!!cp (134);
1685              }
1686            } else {
1687              !!!cp (135);
1688          }          }
1689        } elsif ($self->{next_input_character} == 0x0044 or # D        } elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and
1690                 $self->{next_input_character} == 0x0064) { # d                 $self->{open_elements}->[-1]->[1] & FOREIGN_EL and
1691                   $self->{next_char} == 0x005B) { # [
1692          !!!next-input-character;          !!!next-input-character;
1693          push @next_char, $self->{next_input_character};          push @next_char, $self->{next_char};
1694          if ($self->{next_input_character} == 0x004F or # O          if ($self->{next_char} == 0x0043) { # C
             $self->{next_input_character} == 0x006F) { # o  
1695            !!!next-input-character;            !!!next-input-character;
1696            push @next_char, $self->{next_input_character};            push @next_char, $self->{next_char};
1697            if ($self->{next_input_character} == 0x0043 or # C            if ($self->{next_char} == 0x0044) { # D
               $self->{next_input_character} == 0x0063) { # c  
1698              !!!next-input-character;              !!!next-input-character;
1699              push @next_char, $self->{next_input_character};              push @next_char, $self->{next_char};
1700              if ($self->{next_input_character} == 0x0054 or # T              if ($self->{next_char} == 0x0041) { # A
                 $self->{next_input_character} == 0x0074) { # t  
1701                !!!next-input-character;                !!!next-input-character;
1702                push @next_char, $self->{next_input_character};                push @next_char, $self->{next_char};
1703                if ($self->{next_input_character} == 0x0059 or # Y                if ($self->{next_char} == 0x0054) { # T
                   $self->{next_input_character} == 0x0079) { # y  
1704                  !!!next-input-character;                  !!!next-input-character;
1705                  push @next_char, $self->{next_input_character};                  push @next_char, $self->{next_char};
1706                  if ($self->{next_input_character} == 0x0050 or # P                  if ($self->{next_char} == 0x0041) { # A
                     $self->{next_input_character} == 0x0070) { # p  
1707                    !!!next-input-character;                    !!!next-input-character;
1708                    push @next_char, $self->{next_input_character};                    push @next_char, $self->{next_char};
1709                    if ($self->{next_input_character} == 0x0045 or # E                    if ($self->{next_char} == 0x005B) { # [
1710                        $self->{next_input_character} == 0x0065) { # e                      !!!cp (135.1);
1711                      ## ISSUE: What a stupid code this is!                      $self->{state} = CDATA_BLOCK_STATE;
                     $self->{state} = 'DOCTYPE';  
1712                      !!!next-input-character;                      !!!next-input-character;
1713                      redo A;                      redo A;
1714                      } else {
1715                        !!!cp (135.2);
1716                    }                    }
1717                    } else {
1718                      !!!cp (135.3);
1719                  }                  }
1720                  } else {
1721                    !!!cp (135.4);                
1722                }                }
1723                } else {
1724                  !!!cp (135.5);
1725              }              }
1726              } else {
1727                !!!cp (135.6);
1728            }            }
1729            } else {
1730              !!!cp (135.7);
1731          }          }
1732          } else {
1733            !!!cp (136);
1734        }        }
1735    
1736        !!!parse-error (type => 'bogus comment');        !!!parse-error (type => 'bogus comment');
1737        $self->{next_input_character} = shift @next_char;        $self->{next_char} = shift @next_char;
1738        !!!back-next-input-character (@next_char);        !!!back-next-input-character (@next_char);
1739        $self->{state} = 'bogus comment';        $self->{state} = BOGUS_COMMENT_STATE;
1740          $self->{current_token} = {type => COMMENT_TOKEN, data => '',
1741                                    line => $l, column => $c,
1742                                   };
1743        redo A;        redo A;
1744                
1745        ## ISSUE: typos in spec: chacacters, is is a parse error        ## ISSUE: typos in spec: chacacters, is is a parse error
1746        ## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it?        ## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it?
1747      } elsif ($self->{state} eq 'comment start') {      } elsif ($self->{state} == COMMENT_START_STATE) {
1748        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1749          $self->{state} = 'comment start dash';          !!!cp (137);
1750            $self->{state} = COMMENT_START_DASH_STATE;
1751          !!!next-input-character;          !!!next-input-character;
1752          redo A;          redo A;
1753        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1754            !!!cp (138);
1755          !!!parse-error (type => 'bogus comment');          !!!parse-error (type => 'bogus comment');
1756          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1757          !!!next-input-character;          !!!next-input-character;
1758    
1759          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1760    
1761          redo A;          redo A;
1762        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1763            !!!cp (139);
1764          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1765          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1766          ## reconsume          ## reconsume
1767    
1768          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1769    
1770          redo A;          redo A;
1771        } else {        } else {
1772            !!!cp (140);
1773          $self->{current_token}->{data} # comment          $self->{current_token}->{data} # comment
1774              .= chr ($self->{next_input_character});              .= chr ($self->{next_char});
1775          $self->{state} = 'comment';          $self->{state} = COMMENT_STATE;
1776          !!!next-input-character;          !!!next-input-character;
1777          redo A;          redo A;
1778        }        }
1779      } elsif ($self->{state} eq 'comment start dash') {      } elsif ($self->{state} == COMMENT_START_DASH_STATE) {
1780        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1781          $self->{state} = 'comment end';          !!!cp (141);
1782            $self->{state} = COMMENT_END_STATE;
1783          !!!next-input-character;          !!!next-input-character;
1784          redo A;          redo A;
1785        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1786            !!!cp (142);
1787          !!!parse-error (type => 'bogus comment');          !!!parse-error (type => 'bogus comment');
1788          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1789          !!!next-input-character;          !!!next-input-character;
1790    
1791          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1792    
1793          redo A;          redo A;
1794        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1795            !!!cp (143);
1796          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1797          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1798          ## reconsume          ## reconsume
1799    
1800          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1801    
1802          redo A;          redo A;
1803        } else {        } else {
1804            !!!cp (144);
1805          $self->{current_token}->{data} # comment          $self->{current_token}->{data} # comment
1806              .= '-' . chr ($self->{next_input_character});              .= '-' . chr ($self->{next_char});
1807          $self->{state} = 'comment';          $self->{state} = COMMENT_STATE;
1808          !!!next-input-character;          !!!next-input-character;
1809          redo A;          redo A;
1810        }        }
1811      } elsif ($self->{state} eq 'comment') {      } elsif ($self->{state} == COMMENT_STATE) {
1812        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1813          $self->{state} = 'comment end dash';          !!!cp (145);
1814            $self->{state} = COMMENT_END_DASH_STATE;
1815          !!!next-input-character;          !!!next-input-character;
1816          redo A;          redo A;
1817        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1818            !!!cp (146);
1819          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1820          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1821          ## reconsume          ## reconsume
1822    
1823          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1824    
1825          redo A;          redo A;
1826        } else {        } else {
1827          $self->{current_token}->{data} .= chr ($self->{next_input_character}); # comment          !!!cp (147);
1828            $self->{current_token}->{data} .= chr ($self->{next_char}); # comment
1829          ## Stay in the state          ## Stay in the state
1830          !!!next-input-character;          !!!next-input-character;
1831          redo A;          redo A;
1832        }        }
1833      } elsif ($self->{state} eq 'comment end dash') {      } elsif ($self->{state} == COMMENT_END_DASH_STATE) {
1834        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1835          $self->{state} = 'comment end';          !!!cp (148);
1836            $self->{state} = COMMENT_END_STATE;
1837          !!!next-input-character;          !!!next-input-character;
1838          redo A;          redo A;
1839        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1840            !!!cp (149);
1841          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1842          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1843          ## reconsume          ## reconsume
1844    
1845          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1846    
1847          redo A;          redo A;
1848        } else {        } else {
1849          $self->{current_token}->{data} .= '-' . chr ($self->{next_input_character}); # comment          !!!cp (150);
1850          $self->{state} = 'comment';          $self->{current_token}->{data} .= '-' . chr ($self->{next_char}); # comment
1851            $self->{state} = COMMENT_STATE;
1852          !!!next-input-character;          !!!next-input-character;
1853          redo A;          redo A;
1854        }        }
1855      } elsif ($self->{state} eq 'comment end') {      } elsif ($self->{state} == COMMENT_END_STATE) {
1856        if ($self->{next_input_character} == 0x003E) { # >        if ($self->{next_char} == 0x003E) { # >
1857          $self->{state} = 'data';          !!!cp (151);
1858            $self->{state} = DATA_STATE;
1859          !!!next-input-character;          !!!next-input-character;
1860    
1861          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1862    
1863          redo A;          redo A;
1864        } elsif ($self->{next_input_character} == 0x002D) { # -        } elsif ($self->{next_char} == 0x002D) { # -
1865          !!!parse-error (type => 'dash in comment');          !!!cp (152);
1866            !!!parse-error (type => 'dash in comment',
1867                            line => $self->{line_prev},
1868                            column => $self->{column_prev});
1869          $self->{current_token}->{data} .= '-'; # comment          $self->{current_token}->{data} .= '-'; # comment
1870          ## Stay in the state          ## Stay in the state
1871          !!!next-input-character;          !!!next-input-character;
1872          redo A;          redo A;
1873        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1874            !!!cp (153);
1875          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1876          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1877          ## reconsume          ## reconsume
1878    
1879          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1880    
1881          redo A;          redo A;
1882        } else {        } else {
1883          !!!parse-error (type => 'dash in comment');          !!!cp (154);
1884          $self->{current_token}->{data} .= '--' . chr ($self->{next_input_character}); # comment          !!!parse-error (type => 'dash in comment',
1885          $self->{state} = 'comment';                          line => $self->{line_prev},
1886                            column => $self->{column_prev});
1887            $self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment
1888            $self->{state} = COMMENT_STATE;
1889          !!!next-input-character;          !!!next-input-character;
1890          redo A;          redo A;
1891        }        }
1892      } elsif ($self->{state} eq 'DOCTYPE') {      } elsif ($self->{state} == DOCTYPE_STATE) {
1893        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1894            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1895            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1896            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1897            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1898          $self->{state} = 'before DOCTYPE name';          !!!cp (155);
1899            $self->{state} = BEFORE_DOCTYPE_NAME_STATE;
1900          !!!next-input-character;          !!!next-input-character;
1901          redo A;          redo A;
1902        } else {        } else {
1903            !!!cp (156);
1904          !!!parse-error (type => 'no space before DOCTYPE name');          !!!parse-error (type => 'no space before DOCTYPE name');
1905          $self->{state} = 'before DOCTYPE name';          $self->{state} = BEFORE_DOCTYPE_NAME_STATE;
1906          ## reconsume          ## reconsume
1907          redo A;          redo A;
1908        }        }
1909      } elsif ($self->{state} eq 'before DOCTYPE name') {      } elsif ($self->{state} == BEFORE_DOCTYPE_NAME_STATE) {
1910        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1911            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1912            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1913            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1914            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1915            !!!cp (157);
1916          ## Stay in the state          ## Stay in the state
1917          !!!next-input-character;          !!!next-input-character;
1918          redo A;          redo A;
1919        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1920            !!!cp (158);
1921          !!!parse-error (type => 'no DOCTYPE name');          !!!parse-error (type => 'no DOCTYPE name');
1922          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1923          !!!next-input-character;          !!!next-input-character;
1924    
1925          !!!emit ({type => 'DOCTYPE'}); # incorrect          !!!emit ($self->{current_token}); # DOCTYPE (quirks)
1926    
1927          redo A;          redo A;
1928        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1929            !!!cp (159);
1930          !!!parse-error (type => 'no DOCTYPE name');          !!!parse-error (type => 'no DOCTYPE name');
1931          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1932          ## reconsume          ## reconsume
1933    
1934          !!!emit ({type => 'DOCTYPE'}); # incorrect          !!!emit ($self->{current_token}); # DOCTYPE (quirks)
1935    
1936          redo A;          redo A;
1937        } else {        } else {
1938          $self->{current_token}          !!!cp (160);
1939              = {type => 'DOCTYPE',          $self->{current_token}->{name} = chr $self->{next_char};
1940                 name => chr ($self->{next_input_character}),          delete $self->{current_token}->{quirks};
                correct => 1};  
1941  ## ISSUE: "Set the token's name name to the" in the spec  ## ISSUE: "Set the token's name name to the" in the spec
1942          $self->{state} = 'DOCTYPE name';          $self->{state} = DOCTYPE_NAME_STATE;
1943          !!!next-input-character;          !!!next-input-character;
1944          redo A;          redo A;
1945        }        }
1946      } elsif ($self->{state} eq 'DOCTYPE name') {      } elsif ($self->{state} == DOCTYPE_NAME_STATE) {
1947  ## ISSUE: Redundant "First," in the spec.  ## ISSUE: Redundant "First," in the spec.
1948        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1949            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1950            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1951            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1952            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1953          $self->{state} = 'after DOCTYPE name';          !!!cp (161);
1954            $self->{state} = AFTER_DOCTYPE_NAME_STATE;
1955          !!!next-input-character;          !!!next-input-character;
1956          redo A;          redo A;
1957        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1958          $self->{state} = 'data';          !!!cp (162);
1959            $self->{state} = DATA_STATE;
1960          !!!next-input-character;          !!!next-input-character;
1961    
1962          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1963    
1964          redo A;          redo A;
1965        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1966            !!!cp (163);
1967          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
1968          $self->{state} = 'data';          $self->{state} = DATA_STATE;
1969          ## reconsume          ## reconsume
1970    
1971          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1972          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1973    
1974          redo A;          redo A;
1975        } else {        } else {
1976            !!!cp (164);
1977          $self->{current_token}->{name}          $self->{current_token}->{name}
1978            .= chr ($self->{next_input_character}); # DOCTYPE            .= chr ($self->{next_char}); # DOCTYPE
1979          ## Stay in the state          ## Stay in the state
1980          !!!next-input-character;          !!!next-input-character;
1981          redo A;          redo A;
1982        }        }
1983      } elsif ($self->{state} eq 'after DOCTYPE name') {      } elsif ($self->{state} == AFTER_DOCTYPE_NAME_STATE) {
1984        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1985            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1986            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1987            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1988            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1989            !!!cp (165);
1990          ## Stay in the state          ## Stay in the state
1991          !!!next-input-character;          !!!next-input-character;
1992          redo A;          redo A;
1993        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1994          $self->{state} = 'data';          !!!cp (166);
1995            $self->{state} = DATA_STATE;
1996          !!!next-input-character;          !!!next-input-character;
1997    
1998          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1999    
2000          redo A;          redo A;
2001        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2002            !!!cp (167);
2003          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2004          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2005          ## reconsume          ## reconsume
2006    
2007          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2008          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2009    
2010          redo A;          redo A;
2011        } elsif ($self->{next_input_character} == 0x0050 or # P        } elsif ($self->{next_char} == 0x0050 or # P
2012                 $self->{next_input_character} == 0x0070) { # p                 $self->{next_char} == 0x0070) { # p
2013          !!!next-input-character;          !!!next-input-character;
2014          if ($self->{next_input_character} == 0x0055 or # U          if ($self->{next_char} == 0x0055 or # U
2015              $self->{next_input_character} == 0x0075) { # u              $self->{next_char} == 0x0075) { # u
2016            !!!next-input-character;            !!!next-input-character;
2017            if ($self->{next_input_character} == 0x0042 or # B            if ($self->{next_char} == 0x0042 or # B
2018                $self->{next_input_character} == 0x0062) { # b                $self->{next_char} == 0x0062) { # b
2019              !!!next-input-character;              !!!next-input-character;
2020              if ($self->{next_input_character} == 0x004C or # L              if ($self->{next_char} == 0x004C or # L
2021                  $self->{next_input_character} == 0x006C) { # l                  $self->{next_char} == 0x006C) { # l
2022                !!!next-input-character;                !!!next-input-character;
2023                if ($self->{next_input_character} == 0x0049 or # I                if ($self->{next_char} == 0x0049 or # I
2024                    $self->{next_input_character} == 0x0069) { # i                    $self->{next_char} == 0x0069) { # i
2025                  !!!next-input-character;                  !!!next-input-character;
2026                  if ($self->{next_input_character} == 0x0043 or # C                  if ($self->{next_char} == 0x0043 or # C
2027                      $self->{next_input_character} == 0x0063) { # c                      $self->{next_char} == 0x0063) { # c
2028                    $self->{state} = 'before DOCTYPE public identifier';                    !!!cp (168);
2029                      $self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE;
2030                    !!!next-input-character;                    !!!next-input-character;
2031                    redo A;                    redo A;
2032                    } else {
2033                      !!!cp (169);
2034                  }                  }
2035                  } else {
2036                    !!!cp (170);
2037                }                }
2038                } else {
2039                  !!!cp (171);
2040              }              }
2041              } else {
2042                !!!cp (172);
2043            }            }
2044            } else {
2045              !!!cp (173);
2046          }          }
2047    
2048          #          #
2049        } elsif ($self->{next_input_character} == 0x0053 or # S        } elsif ($self->{next_char} == 0x0053 or # S
2050                 $self->{next_input_character} == 0x0073) { # s                 $self->{next_char} == 0x0073) { # s
2051          !!!next-input-character;          !!!next-input-character;
2052          if ($self->{next_input_character} == 0x0059 or # Y          if ($self->{next_char} == 0x0059 or # Y
2053              $self->{next_input_character} == 0x0079) { # y              $self->{next_char} == 0x0079) { # y
2054            !!!next-input-character;            !!!next-input-character;
2055            if ($self->{next_input_character} == 0x0053 or # S            if ($self->{next_char} == 0x0053 or # S
2056                $self->{next_input_character} == 0x0073) { # s                $self->{next_char} == 0x0073) { # s
2057              !!!next-input-character;              !!!next-input-character;
2058              if ($self->{next_input_character} == 0x0054 or # T              if ($self->{next_char} == 0x0054 or # T
2059                  $self->{next_input_character} == 0x0074) { # t                  $self->{next_char} == 0x0074) { # t
2060                !!!next-input-character;                !!!next-input-character;
2061                if ($self->{next_input_character} == 0x0045 or # E                if ($self->{next_char} == 0x0045 or # E
2062                    $self->{next_input_character} == 0x0065) { # e                    $self->{next_char} == 0x0065) { # e
2063                  !!!next-input-character;                  !!!next-input-character;
2064                  if ($self->{next_input_character} == 0x004D or # M                  if ($self->{next_char} == 0x004D or # M
2065                      $self->{next_input_character} == 0x006D) { # m                      $self->{next_char} == 0x006D) { # m
2066                    $self->{state} = 'before DOCTYPE system identifier';                    !!!cp (174);
2067                      $self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
2068                    !!!next-input-character;                    !!!next-input-character;
2069                    redo A;                    redo A;
2070                    } else {
2071                      !!!cp (175);
2072                  }                  }
2073                  } else {
2074                    !!!cp (176);
2075                }                }
2076                } else {
2077                  !!!cp (177);
2078              }              }
2079              } else {
2080                !!!cp (178);
2081            }            }
2082            } else {
2083              !!!cp (179);
2084          }          }
2085    
2086          #          #
2087        } else {        } else {
2088            !!!cp (180);
2089          !!!next-input-character;          !!!next-input-character;
2090          #          #
2091        }        }
2092    
2093        !!!parse-error (type => 'string after DOCTYPE name');        !!!parse-error (type => 'string after DOCTYPE name');
2094        $self->{state} = 'bogus DOCTYPE';        $self->{current_token}->{quirks} = 1;
2095    
2096          $self->{state} = BOGUS_DOCTYPE_STATE;
2097        # next-input-character is already done        # next-input-character is already done
2098        redo A;        redo A;
2099      } elsif ($self->{state} eq 'before DOCTYPE public identifier') {      } elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) {
2100        if ({        if ({
2101              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
2102              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
2103            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
2104            !!!cp (181);
2105          ## Stay in the state          ## Stay in the state
2106          !!!next-input-character;          !!!next-input-character;
2107          redo A;          redo A;
2108        } elsif ($self->{next_input_character} eq 0x0022) { # "        } elsif ($self->{next_char} eq 0x0022) { # "
2109            !!!cp (182);
2110          $self->{current_token}->{public_identifier} = ''; # DOCTYPE          $self->{current_token}->{public_identifier} = ''; # DOCTYPE
2111          $self->{state} = 'DOCTYPE public identifier (double-quoted)';          $self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE;
2112          !!!next-input-character;          !!!next-input-character;
2113          redo A;          redo A;
2114        } elsif ($self->{next_input_character} eq 0x0027) { # '        } elsif ($self->{next_char} eq 0x0027) { # '
2115            !!!cp (183);
2116          $self->{current_token}->{public_identifier} = ''; # DOCTYPE          $self->{current_token}->{public_identifier} = ''; # DOCTYPE
2117          $self->{state} = 'DOCTYPE public identifier (single-quoted)';          $self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE;
2118          !!!next-input-character;          !!!next-input-character;
2119          redo A;          redo A;
2120        } elsif ($self->{next_input_character} eq 0x003E) { # >        } elsif ($self->{next_char} eq 0x003E) { # >
2121            !!!cp (184);
2122          !!!parse-error (type => 'no PUBLIC literal');          !!!parse-error (type => 'no PUBLIC literal');
2123    
2124          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2125          !!!next-input-character;          !!!next-input-character;
2126    
2127          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2128          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2129    
2130          redo A;          redo A;
2131        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2132            !!!cp (185);
2133          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2134    
2135          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2136          ## reconsume          ## reconsume
2137    
2138          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2139          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2140    
2141          redo A;          redo A;
2142        } else {        } else {
2143            !!!cp (186);
2144          !!!parse-error (type => 'string after PUBLIC');          !!!parse-error (type => 'string after PUBLIC');
2145          $self->{state} = 'bogus DOCTYPE';          $self->{current_token}->{quirks} = 1;
2146    
2147            $self->{state} = BOGUS_DOCTYPE_STATE;
2148          !!!next-input-character;          !!!next-input-character;
2149          redo A;          redo A;
2150        }        }
2151      } elsif ($self->{state} eq 'DOCTYPE public identifier (double-quoted)') {      } elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE) {
2152        if ($self->{next_input_character} == 0x0022) { # "        if ($self->{next_char} == 0x0022) { # "
2153          $self->{state} = 'after DOCTYPE public identifier';          !!!cp (187);
2154            $self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE;
2155            !!!next-input-character;
2156            redo A;
2157          } elsif ($self->{next_char} == 0x003E) { # >
2158            !!!cp (188);
2159            !!!parse-error (type => 'unclosed PUBLIC literal');
2160    
2161            $self->{state} = DATA_STATE;
2162          !!!next-input-character;          !!!next-input-character;
2163    
2164            $self->{current_token}->{quirks} = 1;
2165            !!!emit ($self->{current_token}); # DOCTYPE
2166    
2167          redo A;          redo A;
2168        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2169            !!!cp (189);
2170          !!!parse-error (type => 'unclosed PUBLIC literal');          !!!parse-error (type => 'unclosed PUBLIC literal');
2171    
2172          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2173          ## reconsume          ## reconsume
2174    
2175          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2176          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2177    
2178          redo A;          redo A;
2179        } else {        } else {
2180            !!!cp (190);
2181          $self->{current_token}->{public_identifier} # DOCTYPE          $self->{current_token}->{public_identifier} # DOCTYPE
2182              .= chr $self->{next_input_character};              .= chr $self->{next_char};
2183          ## Stay in the state          ## Stay in the state
2184          !!!next-input-character;          !!!next-input-character;
2185          redo A;          redo A;
2186        }        }
2187      } elsif ($self->{state} eq 'DOCTYPE public identifier (single-quoted)') {      } elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE) {
2188        if ($self->{next_input_character} == 0x0027) { # '        if ($self->{next_char} == 0x0027) { # '
2189          $self->{state} = 'after DOCTYPE public identifier';          !!!cp (191);
2190            $self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE;
2191          !!!next-input-character;          !!!next-input-character;
2192          redo A;          redo A;
2193        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == 0x003E) { # >
2194            !!!cp (192);
2195          !!!parse-error (type => 'unclosed PUBLIC literal');          !!!parse-error (type => 'unclosed PUBLIC literal');
2196    
2197          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2198            !!!next-input-character;
2199    
2200            $self->{current_token}->{quirks} = 1;
2201            !!!emit ($self->{current_token}); # DOCTYPE
2202    
2203            redo A;
2204          } elsif ($self->{next_char} == -1) {
2205            !!!cp (193);
2206            !!!parse-error (type => 'unclosed PUBLIC literal');
2207    
2208            $self->{state} = DATA_STATE;
2209          ## reconsume          ## reconsume
2210    
2211          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2212          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2213    
2214          redo A;          redo A;
2215        } else {        } else {
2216            !!!cp (194);
2217          $self->{current_token}->{public_identifier} # DOCTYPE          $self->{current_token}->{public_identifier} # DOCTYPE
2218              .= chr $self->{next_input_character};              .= chr $self->{next_char};
2219          ## Stay in the state          ## Stay in the state
2220          !!!next-input-character;          !!!next-input-character;
2221          redo A;          redo A;
2222        }        }
2223      } elsif ($self->{state} eq 'after DOCTYPE public identifier') {      } elsif ($self->{state} == AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE) {
2224        if ({        if ({
2225              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
2226              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
2227            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
2228            !!!cp (195);
2229          ## Stay in the state          ## Stay in the state
2230          !!!next-input-character;          !!!next-input-character;
2231          redo A;          redo A;
2232        } elsif ($self->{next_input_character} == 0x0022) { # "        } elsif ($self->{next_char} == 0x0022) { # "
2233            !!!cp (196);
2234          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
2235          $self->{state} = 'DOCTYPE system identifier (double-quoted)';          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;
2236          !!!next-input-character;          !!!next-input-character;
2237          redo A;          redo A;
2238        } elsif ($self->{next_input_character} == 0x0027) { # '        } elsif ($self->{next_char} == 0x0027) { # '
2239            !!!cp (197);
2240          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
2241          $self->{state} = 'DOCTYPE system identifier (single-quoted)';          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;
2242          !!!next-input-character;          !!!next-input-character;
2243          redo A;          redo A;
2244        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
2245          $self->{state} = 'data';          !!!cp (198);
2246            $self->{state} = DATA_STATE;
2247          !!!next-input-character;          !!!next-input-character;
2248    
2249          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2250    
2251          redo A;          redo A;
2252        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2253            !!!cp (199);
2254          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2255    
2256          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2257          ## reconsume          ## reconsume
2258    
2259          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2260          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2261    
2262          redo A;          redo A;
2263        } else {        } else {
2264            !!!cp (200);
2265          !!!parse-error (type => 'string after PUBLIC literal');          !!!parse-error (type => 'string after PUBLIC literal');
2266          $self->{state} = 'bogus DOCTYPE';          $self->{current_token}->{quirks} = 1;
2267    
2268            $self->{state} = BOGUS_DOCTYPE_STATE;
2269          !!!next-input-character;          !!!next-input-character;
2270          redo A;          redo A;
2271        }        }
2272      } elsif ($self->{state} eq 'before DOCTYPE system identifier') {      } elsif ($self->{state} == BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE) {
2273        if ({        if ({
2274              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
2275              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
2276            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
2277            !!!cp (201);
2278          ## Stay in the state          ## Stay in the state
2279          !!!next-input-character;          !!!next-input-character;
2280          redo A;          redo A;
2281        } elsif ($self->{next_input_character} == 0x0022) { # "        } elsif ($self->{next_char} == 0x0022) { # "
2282            !!!cp (202);
2283          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
2284          $self->{state} = 'DOCTYPE system identifier (double-quoted)';          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;
2285          !!!next-input-character;          !!!next-input-character;
2286          redo A;          redo A;
2287        } elsif ($self->{next_input_character} == 0x0027) { # '        } elsif ($self->{next_char} == 0x0027) { # '
2288            !!!cp (203);
2289          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
2290          $self->{state} = 'DOCTYPE system identifier (single-quoted)';          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;
2291          !!!next-input-character;          !!!next-input-character;
2292          redo A;          redo A;
2293        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
2294            !!!cp (204);
2295          !!!parse-error (type => 'no SYSTEM literal');          !!!parse-error (type => 'no SYSTEM literal');
2296          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2297          !!!next-input-character;          !!!next-input-character;
2298    
2299          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2300          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2301    
2302          redo A;          redo A;
2303        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2304            !!!cp (205);
2305          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2306    
2307          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2308          ## reconsume          ## reconsume
2309    
2310          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2311          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2312    
2313          redo A;          redo A;
2314        } else {        } else {
2315            !!!cp (206);
2316          !!!parse-error (type => 'string after SYSTEM');          !!!parse-error (type => 'string after SYSTEM');
2317          $self->{state} = 'bogus DOCTYPE';          $self->{current_token}->{quirks} = 1;
2318    
2319            $self->{state} = BOGUS_DOCTYPE_STATE;
2320          !!!next-input-character;          !!!next-input-character;
2321          redo A;          redo A;
2322        }        }
2323      } elsif ($self->{state} eq 'DOCTYPE system identifier (double-quoted)') {      } elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE) {
2324        if ($self->{next_input_character} == 0x0022) { # "        if ($self->{next_char} == 0x0022) { # "
2325          $self->{state} = 'after DOCTYPE system identifier';          !!!cp (207);
2326            $self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
2327          !!!next-input-character;          !!!next-input-character;
2328          redo A;          redo A;
2329        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == 0x003E) { # >
2330            !!!cp (208);
2331            !!!parse-error (type => 'unclosed PUBLIC literal');
2332    
2333            $self->{state} = DATA_STATE;
2334            !!!next-input-character;
2335    
2336            $self->{current_token}->{quirks} = 1;
2337            !!!emit ($self->{current_token}); # DOCTYPE
2338    
2339            redo A;
2340          } elsif ($self->{next_char} == -1) {
2341            !!!cp (209);
2342          !!!parse-error (type => 'unclosed SYSTEM literal');          !!!parse-error (type => 'unclosed SYSTEM literal');
2343    
2344          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2345          ## reconsume          ## reconsume
2346    
2347          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2348          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2349    
2350          redo A;          redo A;
2351        } else {        } else {
2352            !!!cp (210);
2353          $self->{current_token}->{system_identifier} # DOCTYPE          $self->{current_token}->{system_identifier} # DOCTYPE
2354              .= chr $self->{next_input_character};              .= chr $self->{next_char};
2355          ## Stay in the state          ## Stay in the state
2356          !!!next-input-character;          !!!next-input-character;
2357          redo A;          redo A;
2358        }        }
2359      } elsif ($self->{state} eq 'DOCTYPE system identifier (single-quoted)') {      } elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE) {
2360        if ($self->{next_input_character} == 0x0027) { # '        if ($self->{next_char} == 0x0027) { # '
2361          $self->{state} = 'after DOCTYPE system identifier';          !!!cp (211);
2362            $self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
2363          !!!next-input-character;          !!!next-input-character;
2364          redo A;          redo A;
2365        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == 0x003E) { # >
2366            !!!cp (212);
2367            !!!parse-error (type => 'unclosed PUBLIC literal');
2368    
2369            $self->{state} = DATA_STATE;
2370            !!!next-input-character;
2371    
2372            $self->{current_token}->{quirks} = 1;
2373            !!!emit ($self->{current_token}); # DOCTYPE
2374    
2375            redo A;
2376          } elsif ($self->{next_char} == -1) {
2377            !!!cp (213);
2378          !!!parse-error (type => 'unclosed SYSTEM literal');          !!!parse-error (type => 'unclosed SYSTEM literal');
2379    
2380          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2381          ## reconsume          ## reconsume
2382    
2383          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2384          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2385    
2386          redo A;          redo A;
2387        } else {        } else {
2388            !!!cp (214);
2389          $self->{current_token}->{system_identifier} # DOCTYPE          $self->{current_token}->{system_identifier} # DOCTYPE
2390              .= chr $self->{next_input_character};              .= chr $self->{next_char};
2391          ## Stay in the state          ## Stay in the state
2392          !!!next-input-character;          !!!next-input-character;
2393          redo A;          redo A;
2394        }        }
2395      } elsif ($self->{state} eq 'after DOCTYPE system identifier') {      } elsif ($self->{state} == AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE) {
2396        if ({        if ({
2397              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
2398              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
2399            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
2400            !!!cp (215);
2401          ## Stay in the state          ## Stay in the state
2402          !!!next-input-character;          !!!next-input-character;
2403          redo A;          redo A;
2404        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
2405          $self->{state} = 'data';          !!!cp (216);
2406            $self->{state} = DATA_STATE;
2407          !!!next-input-character;          !!!next-input-character;
2408    
2409          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2410    
2411          redo A;          redo A;
2412        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2413            !!!cp (217);
2414          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2415    
2416          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2417          ## reconsume          ## reconsume
2418    
2419          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2420          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2421    
2422          redo A;          redo A;
2423        } else {        } else {
2424            !!!cp (218);
2425          !!!parse-error (type => 'string after SYSTEM literal');          !!!parse-error (type => 'string after SYSTEM literal');
2426          $self->{state} = 'bogus DOCTYPE';          #$self->{current_token}->{quirks} = 1;
2427    
2428            $self->{state} = BOGUS_DOCTYPE_STATE;
2429          !!!next-input-character;          !!!next-input-character;
2430          redo A;          redo A;
2431        }        }
2432      } elsif ($self->{state} eq 'bogus DOCTYPE') {      } elsif ($self->{state} == BOGUS_DOCTYPE_STATE) {
2433        if ($self->{next_input_character} == 0x003E) { # >        if ($self->{next_char} == 0x003E) { # >
2434          $self->{state} = 'data';          !!!cp (219);
2435            $self->{state} = DATA_STATE;
2436          !!!next-input-character;          !!!next-input-character;
2437    
         delete $self->{current_token}->{correct};  
2438          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2439    
2440          redo A;          redo A;
2441        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2442            !!!cp (220);
2443          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2444          $self->{state} = 'data';          $self->{state} = DATA_STATE;
2445          ## reconsume          ## reconsume
2446    
         delete $self->{current_token}->{correct};  
2447          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2448    
2449          redo A;          redo A;
2450        } else {        } else {
2451            !!!cp (221);
2452          ## Stay in the state          ## Stay in the state
2453          !!!next-input-character;          !!!next-input-character;
2454          redo A;          redo A;
2455        }        }
2456        } elsif ($self->{state} == CDATA_BLOCK_STATE) {
2457          my $s = '';
2458          
2459          my ($l, $c) = ($self->{line}, $self->{column});
2460    
2461          CS: while ($self->{next_char} != -1) {
2462            if ($self->{next_char} == 0x005D) { # ]
2463              !!!next-input-character;
2464              if ($self->{next_char} == 0x005D) { # ]
2465                !!!next-input-character;
2466                MDC: {
2467                  if ($self->{next_char} == 0x003E) { # >
2468                    !!!cp (221.1);
2469                    !!!next-input-character;
2470                    last CS;
2471                  } elsif ($self->{next_char} == 0x005D) { # ]
2472                    !!!cp (221.2);
2473                    $s .= ']';
2474                    !!!next-input-character;
2475                    redo MDC;
2476                  } else {
2477                    !!!cp (221.3);
2478                    $s .= ']]';
2479                    #
2480                  }
2481                } # MDC
2482              } else {
2483                !!!cp (221.4);
2484                $s .= ']';
2485                #
2486              }
2487            } else {
2488              !!!cp (221.5);
2489              #
2490            }
2491            $s .= chr $self->{next_char};
2492            !!!next-input-character;
2493          } # CS
2494    
2495          $self->{state} = DATA_STATE;
2496          ## next-input-character done or EOF, which is reconsumed.
2497    
2498          if (length $s) {
2499            !!!cp (221.6);
2500            !!!emit ({type => CHARACTER_TOKEN, data => $s,
2501                      line => $l, column => $c});
2502          } else {
2503            !!!cp (221.7);
2504          }
2505    
2506          redo A;
2507    
2508          ## ISSUE: "text tokens" in spec.
2509          ## TODO: Streaming support
2510      } else {      } else {
2511        die "$0: $self->{state}: Unknown state";        die "$0: $self->{state}: Unknown state";
2512      }      }
# Line 1606  sub _get_next_token ($) { Line 2515  sub _get_next_token ($) {
2515    die "$0: _get_next_token: unexpected case";    die "$0: _get_next_token: unexpected case";
2516  } # _get_next_token  } # _get_next_token
2517    
2518  sub _tokenize_attempt_to_consume_an_entity ($$) {  sub _tokenize_attempt_to_consume_an_entity ($$$) {
2519    my ($self, $in_attr) = @_;    my ($self, $in_attr, $additional) = @_;
2520    
2521      my ($l, $c) = ($self->{line_prev}, $self->{column_prev});
2522    
2523    if ({    if ({
2524         0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF,         0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF,
2525         0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR         0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR
2526        }->{$self->{next_input_character}}) {         $additional => 1,
2527          }->{$self->{next_char}}) {
2528        !!!cp (1001);
2529      ## Don't consume      ## Don't consume
2530      ## No error      ## No error
2531      return undef;      return undef;
2532    } elsif ($self->{next_input_character} == 0x0023) { # #    } elsif ($self->{next_char} == 0x0023) { # #
2533      !!!next-input-character;      !!!next-input-character;
2534      if ($self->{next_input_character} == 0x0078 or # x      if ($self->{next_char} == 0x0078 or # x
2535          $self->{next_input_character} == 0x0058) { # X          $self->{next_char} == 0x0058) { # X
2536        my $code;        my $code;
2537        X: {        X: {
2538          my $x_char = $self->{next_input_character};          my $x_char = $self->{next_char};
2539          !!!next-input-character;          !!!next-input-character;
2540          if (0x0030 <= $self->{next_input_character} and          if (0x0030 <= $self->{next_char} and
2541              $self->{next_input_character} <= 0x0039) { # 0..9              $self->{next_char} <= 0x0039) { # 0..9
2542              !!!cp (1002);
2543            $code ||= 0;            $code ||= 0;
2544            $code *= 0x10;            $code *= 0x10;
2545            $code += $self->{next_input_character} - 0x0030;            $code += $self->{next_char} - 0x0030;
2546            redo X;            redo X;
2547          } elsif (0x0061 <= $self->{next_input_character} and          } elsif (0x0061 <= $self->{next_char} and
2548                   $self->{next_input_character} <= 0x0066) { # a..f                   $self->{next_char} <= 0x0066) { # a..f
2549              !!!cp (1003);
2550            $code ||= 0;            $code ||= 0;
2551            $code *= 0x10;            $code *= 0x10;
2552            $code += $self->{next_input_character} - 0x0060 + 9;            $code += $self->{next_char} - 0x0060 + 9;
2553            redo X;            redo X;
2554          } elsif (0x0041 <= $self->{next_input_character} and          } elsif (0x0041 <= $self->{next_char} and
2555                   $self->{next_input_character} <= 0x0046) { # A..F                   $self->{next_char} <= 0x0046) { # A..F
2556              !!!cp (1004);
2557            $code ||= 0;            $code ||= 0;
2558            $code *= 0x10;            $code *= 0x10;
2559            $code += $self->{next_input_character} - 0x0040 + 9;            $code += $self->{next_char} - 0x0040 + 9;
2560            redo X;            redo X;
2561          } elsif (not defined $code) { # no hexadecimal digit          } elsif (not defined $code) { # no hexadecimal digit
2562            !!!parse-error (type => 'bare hcro');            !!!cp (1005);
2563            $self->{next_input_character} = 0x0023; # #            !!!parse-error (type => 'bare hcro', line => $l, column => $c);
2564            !!!back-next-input-character ($x_char);            !!!back-next-input-character ($x_char, $self->{next_char});
2565              $self->{next_char} = 0x0023; # #
2566            return undef;            return undef;
2567          } elsif ($self->{next_input_character} == 0x003B) { # ;          } elsif ($self->{next_char} == 0x003B) { # ;
2568              !!!cp (1006);
2569            !!!next-input-character;            !!!next-input-character;
2570          } else {          } else {
2571            !!!parse-error (type => 'no refc');            !!!cp (1007);
2572              !!!parse-error (type => 'no refc', line => $l, column => $c);
2573          }          }
2574    
2575          if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {          if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {
2576            !!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code);            !!!cp (1008);
2577              !!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c);
2578            $code = 0xFFFD;            $code = 0xFFFD;
2579          } elsif ($code > 0x10FFFF) {          } elsif ($code > 0x10FFFF) {
2580            !!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code);            !!!cp (1009);
2581              !!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c);
2582            $code = 0xFFFD;            $code = 0xFFFD;
2583          } elsif ($code == 0x000D) {          } elsif ($code == 0x000D) {
2584            !!!parse-error (type => 'CR character reference');            !!!cp (1010);
2585              !!!parse-error (type => 'CR character reference', line => $l, column => $c);
2586            $code = 0x000A;            $code = 0x000A;
2587          } elsif (0x80 <= $code and $code <= 0x9F) {          } elsif (0x80 <= $code and $code <= 0x9F) {
2588            !!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code);            !!!cp (1011);
2589              !!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c);
2590            $code = $c1_entity_char->{$code};            $code = $c1_entity_char->{$code};
2591          }          }
2592    
2593          return {type => 'character', data => chr $code};          return {type => CHARACTER_TOKEN, data => chr $code,
2594                    has_reference => 1,
2595                    line => $l, column => $c,
2596                   };
2597        } # X        } # X
2598      } elsif (0x0030 <= $self->{next_input_character} and      } elsif (0x0030 <= $self->{next_char} and
2599               $self->{next_input_character} <= 0x0039) { # 0..9               $self->{next_char} <= 0x0039) { # 0..9
2600        my $code = $self->{next_input_character} - 0x0030;        my $code = $self->{next_char} - 0x0030;
2601        !!!next-input-character;        !!!next-input-character;
2602                
2603        while (0x0030 <= $self->{next_input_character} and        while (0x0030 <= $self->{next_char} and
2604                  $self->{next_input_character} <= 0x0039) { # 0..9                  $self->{next_char} <= 0x0039) { # 0..9
2605            !!!cp (1012);
2606          $code *= 10;          $code *= 10;
2607          $code += $self->{next_input_character} - 0x0030;          $code += $self->{next_char} - 0x0030;
2608                    
2609          !!!next-input-character;          !!!next-input-character;
2610        }        }
2611    
2612        if ($self->{next_input_character} == 0x003B) { # ;        if ($self->{next_char} == 0x003B) { # ;
2613            !!!cp (1013);
2614          !!!next-input-character;          !!!next-input-character;
2615        } else {        } else {
2616          !!!parse-error (type => 'no refc');          !!!cp (1014);
2617            !!!parse-error (type => 'no refc', line => $l, column => $c);
2618        }        }
2619    
2620        if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {        if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {
2621          !!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code);          !!!cp (1015);
2622            !!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c);
2623          $code = 0xFFFD;          $code = 0xFFFD;
2624        } elsif ($code > 0x10FFFF) {        } elsif ($code > 0x10FFFF) {
2625          !!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code);          !!!cp (1016);
2626            !!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c);
2627          $code = 0xFFFD;          $code = 0xFFFD;
2628        } elsif ($code == 0x000D) {        } elsif ($code == 0x000D) {
2629          !!!parse-error (type => 'CR character reference');          !!!cp (1017);
2630            !!!parse-error (type => 'CR character reference', line => $l, column => $c);
2631          $code = 0x000A;          $code = 0x000A;
2632        } elsif (0x80 <= $code and $code <= 0x9F) {        } elsif (0x80 <= $code and $code <= 0x9F) {
2633          !!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code);          !!!cp (1018);
2634            !!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c);
2635          $code = $c1_entity_char->{$code};          $code = $c1_entity_char->{$code};
2636        }        }
2637                
2638        return {type => 'character', data => chr $code};        return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1,
2639                  line => $l, column => $c,
2640                 };
2641      } else {      } else {
2642        !!!parse-error (type => 'bare nero');        !!!cp (1019);
2643        !!!back-next-input-character ($self->{next_input_character});        !!!parse-error (type => 'bare nero', line => $l, column => $c);
2644        $self->{next_input_character} = 0x0023; # #        !!!back-next-input-character ($self->{next_char});
2645          $self->{next_char} = 0x0023; # #
2646        return undef;        return undef;
2647      }      }
2648    } elsif ((0x0041 <= $self->{next_input_character} and    } elsif ((0x0041 <= $self->{next_char} and
2649              $self->{next_input_character} <= 0x005A) or              $self->{next_char} <= 0x005A) or
2650             (0x0061 <= $self->{next_input_character} and             (0x0061 <= $self->{next_char} and
2651              $self->{next_input_character} <= 0x007A)) {              $self->{next_char} <= 0x007A)) {
2652      my $entity_name = chr $self->{next_input_character};      my $entity_name = chr $self->{next_char};
2653      !!!next-input-character;      !!!next-input-character;
2654    
2655      my $value = $entity_name;      my $value = $entity_name;
2656      my $match;      my $match = 0;
2657      require Whatpm::_NamedEntityList;      require Whatpm::_NamedEntityList;
2658      our $EntityChar;      our $EntityChar;
2659    
2660      while (length $entity_name < 10 and      while (length $entity_name < 30 and
2661             ## NOTE: Some number greater than the maximum length of entity name             ## NOTE: Some number greater than the maximum length of entity name
2662             ((0x0041 <= $self->{next_input_character} and # a             ((0x0041 <= $self->{next_char} and # a
2663               $self->{next_input_character} <= 0x005A) or # x               $self->{next_char} <= 0x005A) or # x
2664              (0x0061 <= $self->{next_input_character} and # a              (0x0061 <= $self->{next_char} and # a
2665               $self->{next_input_character} <= 0x007A) or # z               $self->{next_char} <= 0x007A) or # z
2666              (0x0030 <= $self->{next_input_character} and # 0              (0x0030 <= $self->{next_char} and # 0
2667               $self->{next_input_character} <= 0x0039) or # 9               $self->{next_char} <= 0x0039) or # 9
2668              $self->{next_input_character} == 0x003B)) { # ;              $self->{next_char} == 0x003B)) { # ;
2669        $entity_name .= chr $self->{next_input_character};        $entity_name .= chr $self->{next_char};
2670        if (defined $EntityChar->{$entity_name}) {        if (defined $EntityChar->{$entity_name}) {
2671          if ($self->{next_input_character} == 0x003B) { # ;          if ($self->{next_char} == 0x003B) { # ;
2672              !!!cp (1020);
2673            $value = $EntityChar->{$entity_name};            $value = $EntityChar->{$entity_name};
2674            $match = 1;            $match = 1;
2675            !!!next-input-character;            !!!next-input-character;
2676            last;            last;
2677          } elsif (not $in_attr) {          } else {
2678              !!!cp (1021);
2679            $value = $EntityChar->{$entity_name};            $value = $EntityChar->{$entity_name};
2680            $match = -1;            $match = -1;
2681          } else {            !!!next-input-character;
           $value .= chr $self->{next_input_character};  
2682          }          }
2683        } else {        } else {
2684          $value .= chr $self->{next_input_character};          !!!cp (1022);
2685            $value .= chr $self->{next_char};
2686            $match *= 2;
2687            !!!next-input-character;
2688        }        }
       !!!next-input-character;  
2689      }      }
2690            
2691      if ($match > 0) {      if ($match > 0) {
2692        return {type => 'character', data => $value};        !!!cp (1023);
2693          return {type => CHARACTER_TOKEN, data => $value, has_reference => 1,
2694                  line => $l, column => $c,
2695                 };
2696      } elsif ($match < 0) {      } elsif ($match < 0) {
2697        !!!parse-error (type => 'no refc');        !!!parse-error (type => 'no refc', line => $l, column => $c);
2698        return {type => 'character', data => $value};        if ($in_attr and $match < -1) {
2699            !!!cp (1024);
2700            return {type => CHARACTER_TOKEN, data => '&'.$entity_name,
2701                    line => $l, column => $c,
2702                   };
2703          } else {
2704            !!!cp (1025);
2705            return {type => CHARACTER_TOKEN, data => $value, has_reference => 1,
2706                    line => $l, column => $c,
2707                   };
2708          }
2709      } else {      } else {
2710        !!!parse-error (type => 'bare ero');        !!!cp (1026);
2711        ## NOTE: No characters are consumed in the spec.        !!!parse-error (type => 'bare ero', line => $l, column => $c);
2712        return {type => 'character', data => '&'.$value};        ## NOTE: "No characters are consumed" in the spec.
2713          return {type => CHARACTER_TOKEN, data => '&'.$value,
2714                  line => $l, column => $c,
2715                 };
2716      }      }
2717    } else {    } else {
2718        !!!cp (1027);
2719      ## no characters are consumed      ## no characters are consumed
2720      !!!parse-error (type => 'bare ero');      !!!parse-error (type => 'bare ero', line => $l, column => $c);
2721      return undef;      return undef;
2722    }    }
2723  } # _tokenize_attempt_to_consume_an_entity  } # _tokenize_attempt_to_consume_an_entity
# Line 1799  sub _construct_tree ($) { Line 2755  sub _construct_tree ($) {
2755        
2756    !!!next-token;    !!!next-token;
2757    
   $self->{insertion_mode} = 'before head';  
2758    undef $self->{form_element};    undef $self->{form_element};
2759    undef $self->{head_element};    undef $self->{head_element};
2760    $self->{open_elements} = [];    $self->{open_elements} = [];
2761    undef $self->{inner_html_node};    undef $self->{inner_html_node};
2762    
2763      ## NOTE: The "initial" insertion mode.
2764    $self->_tree_construction_initial; # MUST    $self->_tree_construction_initial; # MUST
2765    
2766      ## NOTE: The "before html" insertion mode.
2767    $self->_tree_construction_root_element;    $self->_tree_construction_root_element;
2768      $self->{insertion_mode} = BEFORE_HEAD_IM;
2769    
2770      ## NOTE: The "before head" insertion mode and so on.
2771    $self->_tree_construction_main;    $self->_tree_construction_main;
2772  } # _construct_tree  } # _construct_tree
2773    
2774  sub _tree_construction_initial ($) {  sub _tree_construction_initial ($) {
2775    my $self = shift;    my $self = shift;
2776    
2777      ## NOTE: "initial" insertion mode
2778    
2779    INITIAL: {    INITIAL: {
2780      if ($token->{type} eq 'DOCTYPE') {      if ($token->{type} == DOCTYPE_TOKEN) {
2781        ## NOTE: Conformance checkers MAY, instead of reporting "not HTML5"        ## NOTE: Conformance checkers MAY, instead of reporting "not HTML5"
2782        ## error, switch to a conformance checking mode for another        ## error, switch to a conformance checking mode for another
2783        ## language.        ## language.
# Line 1823  sub _tree_construction_initial ($) { Line 2787  sub _tree_construction_initial ($) {
2787        if (not defined $token->{name} or # <!DOCTYPE>        if (not defined $token->{name} or # <!DOCTYPE>
2788            defined $token->{public_identifier} or            defined $token->{public_identifier} or
2789            defined $token->{system_identifier}) {            defined $token->{system_identifier}) {
2790          !!!parse-error (type => 'not HTML5');          !!!cp ('t1');
2791            !!!parse-error (type => 'not HTML5', token => $token);
2792        } elsif ($doctype_name ne 'HTML') {        } elsif ($doctype_name ne 'HTML') {
2793            !!!cp ('t2');
2794          ## ISSUE: ASCII case-insensitive? (in fact it does not matter)          ## ISSUE: ASCII case-insensitive? (in fact it does not matter)
2795          !!!parse-error (type => 'not HTML5');          !!!parse-error (type => 'not HTML5', token => $token);
2796          } else {
2797            !!!cp ('t3');
2798        }        }
2799                
2800        my $doctype = $self->{document}->create_document_type_definition        my $doctype = $self->{document}->create_document_type_definition
2801          ($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)?          ($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)?
2802          ## NOTE: Default value for both |public_id| and |system_id| attributes
2803          ## are empty strings, so that we don't set any value in missing cases.
2804        $doctype->public_id ($token->{public_identifier})        $doctype->public_id ($token->{public_identifier})
2805            if defined $token->{public_identifier};            if defined $token->{public_identifier};
2806        $doctype->system_id ($token->{system_identifier})        $doctype->system_id ($token->{system_identifier})
# Line 1839  sub _tree_construction_initial ($) { Line 2809  sub _tree_construction_initial ($) {
2809        ## ISSUE: internalSubset = null??        ## ISSUE: internalSubset = null??
2810        $self->{document}->append_child ($doctype);        $self->{document}->append_child ($doctype);
2811                
2812        if (not $token->{correct} or $doctype_name ne 'HTML') {        if ($token->{quirks} or $doctype_name ne 'HTML') {
2813            !!!cp ('t4');
2814          $self->{document}->manakai_compat_mode ('quirks');          $self->{document}->manakai_compat_mode ('quirks');
2815        } elsif (defined $token->{public_identifier}) {        } elsif (defined $token->{public_identifier}) {
2816          my $pubid = $token->{public_identifier};          my $pubid = $token->{public_identifier};
# Line 1893  sub _tree_construction_initial ($) { Line 2864  sub _tree_construction_initial ($) {
2864            "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1,            "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1,
2865            "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1,            "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1,
2866            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1,            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1,
2867              "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1,
2868              "-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1,
2869              "-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1,
2870            "-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1,            "-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1,
2871            "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1,            "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1,
2872            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1,            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1,
# Line 1915  sub _tree_construction_initial ($) { Line 2889  sub _tree_construction_initial ($) {
2889            "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1,            "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1,
2890            "HTML" => 1,            "HTML" => 1,
2891          }->{$pubid}) {          }->{$pubid}) {
2892              !!!cp ('t5');
2893            $self->{document}->manakai_compat_mode ('quirks');            $self->{document}->manakai_compat_mode ('quirks');
2894          } elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or          } elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or
2895                   $pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") {                   $pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") {
2896            if (defined $token->{system_identifier}) {            if (defined $token->{system_identifier}) {
2897                !!!cp ('t6');
2898              $self->{document}->manakai_compat_mode ('quirks');              $self->{document}->manakai_compat_mode ('quirks');
2899            } else {            } else {
2900                !!!cp ('t7');
2901              $self->{document}->manakai_compat_mode ('limited quirks');              $self->{document}->manakai_compat_mode ('limited quirks');
2902            }            }
2903          } elsif ($pubid eq "-//W3C//DTD XHTML 1.0 Frameset//EN" or          } elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or
2904                   $pubid eq "-//W3C//DTD XHTML 1.0 Transitional//EN") {                   $pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") {
2905              !!!cp ('t8');
2906            $self->{document}->manakai_compat_mode ('limited quirks');            $self->{document}->manakai_compat_mode ('limited quirks');
2907            } else {
2908              !!!cp ('t9');
2909          }          }
2910          } else {
2911            !!!cp ('t10');
2912        }        }
2913        if (defined $token->{system_identifier}) {        if (defined $token->{system_identifier}) {
2914          my $sysid = $token->{system_identifier};          my $sysid = $token->{system_identifier};
2915          $sysid =~ tr/A-Z/a-z/;          $sysid =~ tr/A-Z/a-z/;
2916          if ($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") {
2917              ## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)"
2918            $self->{document}->manakai_compat_mode ('quirks');            $self->{document}->manakai_compat_mode ('quirks');
2919              !!!cp ('t11');
2920            } else {
2921              !!!cp ('t12');
2922          }          }
2923          } else {
2924            !!!cp ('t13');
2925        }        }
2926                
2927        ## Go to the root element phase.        ## Go to the "before html" insertion mode.
2928        !!!next-token;        !!!next-token;
2929        return;        return;
2930      } elsif ({      } elsif ({
2931                'start tag' => 1,                START_TAG_TOKEN, 1,
2932                'end tag' => 1,                END_TAG_TOKEN, 1,
2933                'end-of-file' => 1,                END_OF_FILE_TOKEN, 1,
2934               }->{$token->{type}}) {               }->{$token->{type}}) {
2935        !!!parse-error (type => 'no DOCTYPE');        !!!cp ('t14');
2936          !!!parse-error (type => 'no DOCTYPE', token => $token);
2937        $self->{document}->manakai_compat_mode ('quirks');        $self->{document}->manakai_compat_mode ('quirks');
2938        ## Go to the root element phase        ## Go to the "before html" insertion mode.
2939        ## reprocess        ## reprocess
2940          !!!ack-later;
2941        return;        return;
2942      } elsif ($token->{type} eq 'character') {      } elsif ($token->{type} == CHARACTER_TOKEN) {
2943        if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D        if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D
2944          ## Ignore the token          ## Ignore the token
2945    
2946          unless (length $token->{data}) {          unless (length $token->{data}) {
2947            ## Stay in the phase            !!!cp ('t15');
2948              ## Stay in the insertion mode.
2949            !!!next-token;            !!!next-token;
2950            redo INITIAL;            redo INITIAL;
2951            } else {
2952              !!!cp ('t16');
2953          }          }
2954          } else {
2955            !!!cp ('t17');
2956        }        }
2957    
2958        !!!parse-error (type => 'no DOCTYPE');        !!!parse-error (type => 'no DOCTYPE', token => $token);
2959        $self->{document}->manakai_compat_mode ('quirks');        $self->{document}->manakai_compat_mode ('quirks');
2960        ## Go to the root element phase        ## Go to the "before html" insertion mode.
2961        ## reprocess        ## reprocess
2962        return;        return;
2963      } elsif ($token->{type} eq 'comment') {      } elsif ($token->{type} == COMMENT_TOKEN) {
2964          !!!cp ('t18');
2965        my $comment = $self->{document}->create_comment ($token->{data});        my $comment = $self->{document}->create_comment ($token->{data});
2966        $self->{document}->append_child ($comment);        $self->{document}->append_child ($comment);
2967                
2968        ## Stay in the phase.        ## Stay in the insertion mode.
2969        !!!next-token;        !!!next-token;
2970        redo INITIAL;        redo INITIAL;
2971      } else {      } else {
2972        die "$0: $token->{type}: Unknown token";        die "$0: $token->{type}: Unknown token type";
2973      }      }
2974    } # INITIAL    } # INITIAL
2975    
2976      die "$0: _tree_construction_initial: This should be never reached";
2977  } # _tree_construction_initial  } # _tree_construction_initial
2978    
2979  sub _tree_construction_root_element ($) {  sub _tree_construction_root_element ($) {
2980    my $self = shift;    my $self = shift;
2981    
2982      ## NOTE: "before html" insertion mode.
2983        
2984    B: {    B: {
2985        if ($token->{type} eq 'DOCTYPE') {        if ($token->{type} == DOCTYPE_TOKEN) {
2986          !!!parse-error (type => 'in html:#DOCTYPE');          !!!cp ('t19');
2987            !!!parse-error (type => 'in html:#DOCTYPE', token => $token);
2988          ## Ignore the token          ## Ignore the token
2989          ## Stay in the phase          ## Stay in the insertion mode.
2990          !!!next-token;          !!!next-token;
2991          redo B;          redo B;
2992        } elsif ($token->{type} eq 'comment') {        } elsif ($token->{type} == COMMENT_TOKEN) {
2993            !!!cp ('t20');
2994          my $comment = $self->{document}->create_comment ($token->{data});          my $comment = $self->{document}->create_comment ($token->{data});
2995          $self->{document}->append_child ($comment);          $self->{document}->append_child ($comment);
2996          ## Stay in the phase          ## Stay in the insertion mode.
2997          !!!next-token;          !!!next-token;
2998          redo B;          redo B;
2999        } elsif ($token->{type} eq 'character') {        } elsif ($token->{type} == CHARACTER_TOKEN) {
3000          if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D          if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D
3001            ## Ignore the token.            ## Ignore the token.
3002    
3003            unless (length $token->{data}) {            unless (length $token->{data}) {
3004              ## Stay in the phase              !!!cp ('t21');
3005                ## Stay in the insertion mode.
3006              !!!next-token;              !!!next-token;
3007              redo B;              redo B;
3008              } else {
3009                !!!cp ('t22');
3010            }            }
3011            } else {
3012              !!!cp ('t23');
3013          }          }
3014    
3015            $self->{application_cache_selection}->(undef);
3016    
3017          #          #
3018          } elsif ($token->{type} == START_TAG_TOKEN) {
3019            if ($token->{tag_name} eq 'html') {
3020              my $root_element;
3021              !!!create-element ($root_element, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token);
3022              $self->{document}->append_child ($root_element);
3023              push @{$self->{open_elements}},
3024                  [$root_element, $el_category->{html}];
3025    
3026              if ($token->{attributes}->{manifest}) {
3027                !!!cp ('t24');
3028                $self->{application_cache_selection}
3029                    ->($token->{attributes}->{manifest}->{value});
3030                ## ISSUE: Spec is unclear on relative references.
3031                ## According to Hixie (#whatwg 2008-03-19), it should be
3032                ## resolved against the base URI of the document in HTML
3033                ## or xml:base of the element in XHTML.
3034              } else {
3035                !!!cp ('t25');
3036                $self->{application_cache_selection}->(undef);
3037              }
3038    
3039              !!!nack ('t25c');
3040    
3041              !!!next-token;
3042              return; ## Go to the "before head" insertion mode.
3043            } else {
3044              !!!cp ('t25.1');
3045              #
3046            }
3047        } elsif ({        } elsif ({
3048                  'start tag' => 1,                  END_TAG_TOKEN, 1,
3049                  'end tag' => 1,                  END_OF_FILE_TOKEN, 1,
                 'end-of-file' => 1,  
3050                 }->{$token->{type}}) {                 }->{$token->{type}}) {
3051          ## ISSUE: There is an issue in the spec          !!!cp ('t26');
3052          #          #
3053        } else {        } else {
3054          die "$0: $token->{type}: Unknown token";          die "$0: $token->{type}: Unknown token type";
3055        }        }
3056        my $root_element; !!!create-element ($root_element, 'html');  
3057        $self->{document}->append_child ($root_element);      my $root_element;
3058        push @{$self->{open_elements}}, [$root_element, 'html'];      !!!create-element ($root_element, $HTML_NS, 'html',, $token);
3059        #$phase = 'main';      $self->{document}->append_child ($root_element);
3060        ## reprocess      push @{$self->{open_elements}}, [$root_element, $el_category->{html}];
3061        #redo B;  
3062        return;      $self->{application_cache_selection}->(undef);
3063    
3064        ## NOTE: Reprocess the token.
3065        !!!ack-later;
3066        return; ## Go to the "before head" insertion mode.
3067    
3068        ## ISSUE: There is an issue in the spec
3069    } # B    } # B
3070    
3071      die "$0: _tree_construction_root_element: This should never be reached";
3072  } # _tree_construction_root_element  } # _tree_construction_root_element
3073    
3074  sub _reset_insertion_mode ($) {  sub _reset_insertion_mode ($) {
# Line 2037  sub _reset_insertion_mode ($) { Line 3083  sub _reset_insertion_mode ($) {
3083            
3084      ## Step 3      ## Step 3
3085      S3: {      S3: {
       ## ISSUE: Oops! "If node is the first node in the stack of open  
       ## elements, then set last to true. If the context element of the  
       ## HTML fragment parsing algorithm is neither a td element nor a  
       ## th element, then set node to the context element. (fragment case)":  
       ## The second "if" is in the scope of the first "if"!?  
3086        if ($self->{open_elements}->[0]->[0] eq $node->[0]) {        if ($self->{open_elements}->[0]->[0] eq $node->[0]) {
3087          $last = 1;          $last = 1;
3088          if (defined $self->{inner_html_node}) {          if (defined $self->{inner_html_node}) {
3089            if ($self->{inner_html_node}->[1] eq 'td' or            if ($self->{inner_html_node}->[1] & TABLE_CELL_EL) {
3090                $self->{inner_html_node}->[1] eq 'th') {              !!!cp ('t27');
3091              #              #
3092            } else {            } else {
3093                !!!cp ('t28');
3094              $node = $self->{inner_html_node};              $node = $self->{inner_html_node};
3095            }            }
3096          }          }
3097        }        }
3098            
3099        ## Step 4..13      ## Step 4..14
3100        my $new_mode = {      my $new_mode;
3101                        select => 'in select',      if ($node->[1] & FOREIGN_EL) {
3102                        td => 'in cell',        ## NOTE: Strictly spaking, the line below only applies to MathML and
3103                        th => 'in cell',        ## SVG elements.  Currently the HTML syntax supports only MathML and
3104                        tr => 'in row',        ## SVG elements as foreigners.
3105                        tbody => 'in table body',        $new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM;
3106                        thead => 'in table head',        ## ISSUE: What is set as the secondary insertion mode?
3107                        tfoot => 'in table foot',      } else {
3108                        caption => 'in caption',        $new_mode = {
3109                        colgroup => 'in column group',                        select => IN_SELECT_IM,
3110                        table => 'in table',                        ## NOTE: |option| and |optgroup| do not set
3111                        head => 'in body', # not in head!                        ## insertion mode to "in select" by themselves.
3112                        body => 'in body',                        td => IN_CELL_IM,
3113                        frameset => 'in frameset',                        th => IN_CELL_IM,
3114                       }->{$node->[1]};                        tr => IN_ROW_IM,
3115        $self->{insertion_mode} = $new_mode and return if defined $new_mode;                        tbody => IN_TABLE_BODY_IM,
3116                          thead => IN_TABLE_BODY_IM,
3117                          tfoot => IN_TABLE_BODY_IM,
3118                          caption => IN_CAPTION_IM,
3119                          colgroup => IN_COLUMN_GROUP_IM,
3120                          table => IN_TABLE_IM,
3121                          head => IN_BODY_IM, # not in head!
3122                          body => IN_BODY_IM,
3123                          frameset => IN_FRAMESET_IM,
3124                         }->{$node->[0]->manakai_local_name};
3125        }
3126        $self->{insertion_mode} = $new_mode and return if defined $new_mode;
3127                
3128        ## Step 14        ## Step 15
3129        if ($node->[1] eq 'html') {        if ($node->[1] & HTML_EL) {
3130          unless (defined $self->{head_element}) {          unless (defined $self->{head_element}) {
3131            $self->{insertion_mode} = 'before head';            !!!cp ('t29');
3132              $self->{insertion_mode} = BEFORE_HEAD_IM;
3133          } else {          } else {
3134            $self->{insertion_mode} = 'after head';            ## ISSUE: Can this state be reached?
3135              !!!cp ('t30');
3136              $self->{insertion_mode} = AFTER_HEAD_IM;
3137          }          }
3138          return;          return;
3139          } else {
3140            !!!cp ('t31');
3141        }        }
3142                
       ## Step 15  
       $self->{insertion_mode} = 'in body' and return if $last;  
         
3143        ## Step 16        ## Step 16
3144          $self->{insertion_mode} = IN_BODY_IM and return if $last;
3145          
3146          ## Step 17
3147        $i--;        $i--;
3148        $node = $self->{open_elements}->[$i];        $node = $self->{open_elements}->[$i];
3149                
3150        ## Step 17        ## Step 18
3151        redo S3;        redo S3;
3152      } # S3      } # S3
3153    
3154      die "$0: _reset_insertion_mode: This line should never be reached";
3155  } # _reset_insertion_mode  } # _reset_insertion_mode
3156    
3157  sub _tree_construction_main ($) {  sub _tree_construction_main ($) {
3158    my $self = shift;    my $self = shift;
3159    
   my $phase = 'main';  
   
3160    my $active_formatting_elements = [];    my $active_formatting_elements = [];
3161    
3162    my $reconstruct_active_formatting_elements = sub { # MUST    my $reconstruct_active_formatting_elements = sub { # MUST
# Line 2115  sub _tree_construction_main ($) { Line 3173  sub _tree_construction_main ($) {
3173      return if $entry->[0] eq '#marker';      return if $entry->[0] eq '#marker';
3174      for (@{$self->{open_elements}}) {      for (@{$self->{open_elements}}) {
3175        if ($entry->[0] eq $_->[0]) {        if ($entry->[0] eq $_->[0]) {
3176            !!!cp ('t32');
3177          return;          return;
3178        }        }
3179      }      }
# Line 2129  sub _tree_construction_main ($) { Line 3188  sub _tree_construction_main ($) {
3188    
3189        ## Step 6        ## Step 6
3190        if ($entry->[0] eq '#marker') {        if ($entry->[0] eq '#marker') {
3191            !!!cp ('t33_1');
3192          #          #
3193        } else {        } else {
3194          my $in_open_elements;          my $in_open_elements;
3195          OE: for (@{$self->{open_elements}}) {          OE: for (@{$self->{open_elements}}) {
3196            if ($entry->[0] eq $_->[0]) {            if ($entry->[0] eq $_->[0]) {
3197                !!!cp ('t33');
3198              $in_open_elements = 1;              $in_open_elements = 1;
3199              last OE;              last OE;
3200            }            }
3201          }          }
3202          if ($in_open_elements) {          if ($in_open_elements) {
3203              !!!cp ('t34');
3204            #            #
3205          } else {          } else {
3206              ## NOTE: <!DOCTYPE HTML><p><b><i><u></p> <p>X
3207              !!!cp ('t35');
3208            redo S4;            redo S4;
3209          }          }
3210        }        }
# Line 2163  sub _tree_construction_main ($) { Line 3227  sub _tree_construction_main ($) {
3227    
3228        ## Step 11        ## Step 11
3229        unless ($clone->[0] eq $active_formatting_elements->[-1]->[0]) {        unless ($clone->[0] eq $active_formatting_elements->[-1]->[0]) {
3230            !!!cp ('t36');
3231          ## Step 7'          ## Step 7'
3232          $i++;          $i++;
3233          $entry = $active_formatting_elements->[$i];          $entry = $active_formatting_elements->[$i];
3234                    
3235          redo S7;          redo S7;
3236        }        }
3237    
3238          !!!cp ('t37');
3239      } # S7      } # S7
3240    }; # $reconstruct_active_formatting_elements    }; # $reconstruct_active_formatting_elements
3241    
3242    my $clear_up_to_marker = sub {    my $clear_up_to_marker = sub {
3243      for (reverse 0..$#$active_formatting_elements) {      for (reverse 0..$#$active_formatting_elements) {
3244        if ($active_formatting_elements->[$_]->[0] eq '#marker') {        if ($active_formatting_elements->[$_]->[0] eq '#marker') {
3245            !!!cp ('t38');
3246          splice @$active_formatting_elements, $_;          splice @$active_formatting_elements, $_;
3247          return;          return;
3248        }        }
3249      }      }
3250    
3251        !!!cp ('t39');
3252    }; # $clear_up_to_marker    }; # $clear_up_to_marker
3253    
3254    my $parse_rcdata = sub ($$) {    my $insert;
3255      my ($content_model_flag, $insert) = @_;  
3256      my $parse_rcdata = sub ($) {
3257        my ($content_model_flag) = @_;
3258    
3259      ## Step 1      ## Step 1
3260      my $start_tag_name = $token->{tag_name};      my $start_tag_name = $token->{tag_name};
3261      my $el;      my $el;
3262      !!!create-element ($el, $start_tag_name, $token->{attributes});      !!!create-element ($el, $HTML_NS, $start_tag_name, $token->{attributes}, $token);
3263    
3264      ## Step 2      ## Step 2
3265      $insert->($el); # /context node/->append_child ($el)      $insert->($el);
3266    
3267      ## Step 3      ## Step 3
3268      $self->{content_model_flag} = $content_model_flag; # CDATA or RCDATA      $self->{content_model} = $content_model_flag; # CDATA or RCDATA
3269      delete $self->{escape}; # MUST      delete $self->{escape}; # MUST
3270    
3271      ## Step 4      ## Step 4
3272      my $text = '';      my $text = '';
3273        !!!nack ('t40.1');
3274      !!!next-token;      !!!next-token;
3275      while ($token->{type} eq 'character') { # or until stop tokenizing      while ($token->{type} == CHARACTER_TOKEN) { # or until stop tokenizing
3276          !!!cp ('t40');
3277        $text .= $token->{data};        $text .= $token->{data};
3278        !!!next-token;        !!!next-token;
3279      }      }
3280    
3281      ## Step 5      ## Step 5
3282      if (length $text) {      if (length $text) {
3283          !!!cp ('t41');
3284        my $text = $self->{document}->create_text_node ($text);        my $text = $self->{document}->create_text_node ($text);
3285        $el->append_child ($text);        $el->append_child ($text);
3286      }      }
3287    
3288      ## Step 6      ## Step 6
3289      $self->{content_model_flag} = 'PCDATA';      $self->{content_model} = PCDATA_CONTENT_MODEL;
3290    
3291      ## Step 7      ## Step 7
3292      if ($token->{type} eq 'end tag' and $token->{tag_name} eq $start_tag_name) {      if ($token->{type} == END_TAG_TOKEN and
3293            $token->{tag_name} eq $start_tag_name) {
3294          !!!cp ('t42');
3295        ## Ignore the token        ## Ignore the token
3296      } else {      } else {
3297        !!!parse-error (type => 'in '.$content_model_flag.':#'.$token->{type});        ## NOTE: An end-of-file token.
3298          if ($content_model_flag == CDATA_CONTENT_MODEL) {
3299            !!!cp ('t43');
3300            !!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token);
3301          } elsif ($content_model_flag == RCDATA_CONTENT_MODEL) {
3302            !!!cp ('t44');
3303            !!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token);
3304          } else {
3305            die "$0: $content_model_flag in parse_rcdata";
3306          }
3307      }      }
3308      !!!next-token;      !!!next-token;
3309    }; # $parse_rcdata    }; # $parse_rcdata
3310    
3311    my $script_start_tag = sub ($) {    my $script_start_tag = sub () {
     my $insert = $_[0];  
3312      my $script_el;      my $script_el;
3313      !!!create-element ($script_el, 'script', $token->{attributes});      !!!create-element ($script_el, $HTML_NS, 'script', $token->{attributes}, $token);
3314      ## TODO: mark as "parser-inserted"      ## TODO: mark as "parser-inserted"
3315