/[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 1.58 by wakaba, Tue Sep 4 11:19:07 2007 UTC revision 1.78 by wakaba, Mon Mar 3 11:56:18 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)
 ## "{U+FEFF}..." in UTF-16BE/UTF-16LE is three or four characters?  
 ## "{U+FEFF}..." in GB18030?  
14    
15  my $permitted_slash_tag_name = {  my $permitted_slash_tag_name = {
16    base => 1,    base => 1,
# Line 19  my $permitted_slash_tag_name = { Line 18  my $permitted_slash_tag_name = {
18    meta => 1,    meta => 1,
19    hr => 1,    hr => 1,
20    br => 1,    br => 1,
21    img=> 1,    img => 1,
22    embed => 1,    embed => 1,
23    param => 1,    param => 1,
24    area => 1,    area => 1,
# Line 84  my $formatting_category = { Line 83  my $formatting_category = {
83  };  };
84  # $phrasing_category: all other elements  # $phrasing_category: all other elements
85    
86    sub parse_byte_string ($$$$;$) {
87      my $self = ref $_[0] ? shift : shift->new;
88      my $charset = shift;
89      my $bytes_s = ref $_[0] ? $_[0] : \($_[0]);
90      my $s;
91      
92      if (defined $charset) {
93        require Encode; ## TODO: decode(utf8) don't delete BOM
94        $s = \ (Encode::decode ($charset, $$bytes_s));
95        $self->{input_encoding} = lc $charset; ## TODO: normalize name
96        $self->{confident} = 1;
97      } else {
98        ## TODO: Implement HTML5 detection algorithm
99        require Whatpm::Charset::UniversalCharDet;
100        $charset = Whatpm::Charset::UniversalCharDet->detect_byte_string
101            (substr ($$bytes_s, 0, 1024));
102        $charset ||= 'windows-1252';
103        $s = \ (Encode::decode ($charset, $$bytes_s));
104        $self->{input_encoding} = $charset;
105        $self->{confident} = 0;
106      }
107    
108      $self->{change_encoding} = sub {
109        my $self = shift;
110        my $charset = lc shift;
111        ## TODO: if $charset is supported
112        ## TODO: normalize charset name
113    
114        ## "Change the encoding" algorithm:
115    
116        ## Step 1    
117        if ($charset eq 'utf-16') { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8?
118          $charset = 'utf-8';
119        }
120    
121        ## Step 2
122        if (defined $self->{input_encoding} and
123            $self->{input_encoding} eq $charset) {
124          $self->{confident} = 1;
125          return;
126        }
127    
128        !!!parse-error (type => 'charset label detected:'.$self->{input_encoding}.
129            ':'.$charset, level => 'w');
130    
131        ## Step 3
132        # if (can) {
133          ## change the encoding on the fly.
134          #$self->{confident} = 1;
135          #return;
136        # }
137    
138        ## Step 4
139        throw Whatpm::HTML::RestartParser (charset => $charset);
140      }; # $self->{change_encoding}
141    
142      my @args = @_; shift @args; # $s
143      my $return;
144      try {
145        $return = $self->parse_char_string ($s, @args);  
146      } catch Whatpm::HTML::RestartParser with {
147        my $charset = shift->{charset};
148        $s = \ (Encode::decode ($charset, $$bytes_s));    
149        $self->{input_encoding} = $charset; ## TODO: normalize
150        $self->{confident} = 1;
151        $return = $self->parse_char_string ($s, @args);
152      };
153      return $return;
154    } # parse_byte_string
155    
156    ## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM
157    ## and the HTML layer MUST ignore it.  However, we does strip BOM in
158    ## the encoding layer and the HTML layer does not ignore any U+FEFF,
159    ## because the core part of our HTML parser expects a string of character,
160    ## not a string of bytes or code units or anything which might contain a BOM.
161    ## Therefore, any parser interface that accepts a string of bytes,
162    ## such as |parse_byte_string| in this module, must ensure that it does
163    ## strip the BOM and never strip any ZWNBSP.
164    
165    *parse_char_string = \&parse_string;
166    
167  sub parse_string ($$$;$) {  sub parse_string ($$$;$) {
168    my $self = shift->new;    my $self = ref $_[0] ? shift : shift->new;
169    my $s = \$_[0];    my $s = ref $_[0] ? $_[0] : \($_[0]);
170    $self->{document} = $_[1];    $self->{document} = $_[1];
171      @{$self->{document}->child_nodes} = ();
172    
173    ## NOTE: |set_inner_html| copies most of this method's code    ## NOTE: |set_inner_html| copies most of this method's code
174    
175      $self->{confident} = 1 unless exists $self->{confident};
176      $self->{document}->input_encoding ($self->{input_encoding})
177          if defined $self->{input_encoding};
178    
179    my $i = 0;    my $i = 0;
180    my $line = 1;    my $line = 1;
181    my $column = 0;    my $column = 0;
182    $self->{set_next_input_character} = sub {    $self->{set_next_char} = sub {
183      my $self = shift;      my $self = shift;
184    
185      pop @{$self->{prev_input_character}};      pop @{$self->{prev_char}};
186      unshift @{$self->{prev_input_character}}, $self->{next_input_character};      unshift @{$self->{prev_char}}, $self->{next_char};
187    
188      $self->{next_input_character} = -1 and return if $i >= length $$s;      $self->{next_char} = -1 and return if $i >= length $$s;
189      $self->{next_input_character} = ord substr $$s, $i++, 1;      $self->{next_char} = ord substr $$s, $i++, 1;
190      $column++;      $column++;
191            
192      if ($self->{next_input_character} == 0x000A) { # LF      if ($self->{next_char} == 0x000A) { # LF
193        $line++;        $line++;
194        $column = 0;        $column = 0;
195      } elsif ($self->{next_input_character} == 0x000D) { # CR      } elsif ($self->{next_char} == 0x000D) { # CR
196        $i++ if substr ($$s, $i, 1) eq "\x0A";        $i++ if substr ($$s, $i, 1) eq "\x0A";
197        $self->{next_input_character} = 0x000A; # LF # MUST        $self->{next_char} = 0x000A; # LF # MUST
198        $line++;        $line++;
199        $column = 0;        $column = 0;
200      } elsif ($self->{next_input_character} > 0x10FFFF) {      } elsif ($self->{next_char} > 0x10FFFF) {
201        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST        $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
202      } elsif ($self->{next_input_character} == 0x0000) { # NULL      } elsif ($self->{next_char} == 0x0000) { # NULL
203        !!!parse-error (type => 'NULL');        !!!parse-error (type => 'NULL');
204        $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST        $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
205      }      }
206    };    };
207    $self->{prev_input_character} = [-1, -1, -1];    $self->{prev_char} = [-1, -1, -1];
208    $self->{next_input_character} = -1;    $self->{next_char} = -1;
209    
210    my $onerror = $_[2] || sub {    my $onerror = $_[2] || sub {
211      my (%opt) = @_;      my (%opt) = @_;
# Line 141  sub parse_string ($$$;$) { Line 226  sub parse_string ($$$;$) {
226  sub new ($) {  sub new ($) {
227    my $class = shift;    my $class = shift;
228    my $self = bless {}, $class;    my $self = bless {}, $class;
229    $self->{set_next_input_character} = sub {    $self->{set_next_char} = sub {
230      $self->{next_input_character} = -1;      $self->{next_char} = -1;
231    };    };
232    $self->{parse_error} = sub {    $self->{parse_error} = sub {
233      #      #
234    };    };
235      $self->{change_encoding} = sub {
236        # if ($_[0] is a supported encoding) {
237        #   run "change the encoding" algorithm;
238        #   throw Whatpm::HTML::RestartParser (charset => $new_encoding);
239        # }
240      };
241      $self->{application_cache_selection} = sub {
242        #
243      };
244    return $self;    return $self;
245  } # new  } # new
246    
# Line 192  sub DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUO Line 286  sub DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUO
286  sub DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE () { 30 }  sub DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE () { 30 }
287  sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 }  sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 }
288  sub BOGUS_DOCTYPE_STATE () { 32 }  sub BOGUS_DOCTYPE_STATE () { 32 }
289    sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 }
290    
291  sub DOCTYPE_TOKEN () { 1 }  sub DOCTYPE_TOKEN () { 1 }
292  sub COMMENT_TOKEN () { 2 }  sub COMMENT_TOKEN () { 2 }
# Line 238  sub _initialize_tokenizer ($) { Line 333  sub _initialize_tokenizer ($) {
333    undef $self->{last_emitted_start_tag_name};    undef $self->{last_emitted_start_tag_name};
334    undef $self->{last_attribute_value_state};    undef $self->{last_attribute_value_state};
335    $self->{char} = [];    $self->{char} = [];
336    # $self->{next_input_character}    # $self->{next_char}
337    !!!next-input-character;    !!!next-input-character;
338    $self->{token} = [];    $self->{token} = [];
339    # $self->{escape}    # $self->{escape}
# Line 251  sub _initialize_tokenizer ($) { Line 346  sub _initialize_tokenizer ($) {
346  ##   ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN)  ##   ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN)
347  ##   ->{public_identifier} (DOCTYPE_TOKEN)  ##   ->{public_identifier} (DOCTYPE_TOKEN)
348  ##   ->{system_identifier} (DOCTYPE_TOKEN)  ##   ->{system_identifier} (DOCTYPE_TOKEN)
349  ##   ->{correct} == 1 or 0 (DOCTYPE_TOKEN)  ##   ->{quirks} == 1 or 0 (DOCTYPE_TOKEN): "force-quirks" flag
350  ##   ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN)  ##   ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN)
351    ##        ->{name}
352    ##        ->{value}
353    ##        ->{has_reference} == 1 or 0
354  ##   ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN)  ##   ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN)
355    
356  ## Emitted token MUST immediately be handled by the tree construction state.  ## Emitted token MUST immediately be handled by the tree construction state.
# Line 263  sub _initialize_tokenizer ($) { Line 361  sub _initialize_tokenizer ($) {
361  ## has completed loading.  If one has, then it MUST be executed  ## has completed loading.  If one has, then it MUST be executed
362  ## and removed from the list.  ## and removed from the list.
363    
364    ## NOTE: HTML5 "Writing HTML documents" section, applied to
365    ## documents and not to user agents and conformance checkers,
366    ## contains some requirements that are not detected by the
367    ## parsing algorithm:
368    ## - Some requirements on character encoding declarations. ## TODO
369    ## - "Elements MUST NOT contain content that their content model disallows."
370    ##   ... Some are parse error, some are not (will be reported by c.c.).
371    ## - Polytheistic slash SHOULD NOT be used. (Applied only to atheists.) ## TODO
372    ## - Text (in elements, attributes, and comments) SHOULD NOT contain
373    ##   control characters other than space characters. ## TODO: (what is control character? C0, C1 and DEL?  Unicode control character?)
374    
375    ## TODO: HTML5 poses authors two SHOULD-level requirements that cannot
376    ## be detected by the HTML5 parsing algorithm:
377    ## - Text,
378    
379  sub _get_next_token ($) {  sub _get_next_token ($) {
380    my $self = shift;    my $self = shift;
381    if (@{$self->{token}}) {    if (@{$self->{token}}) {
# Line 271  sub _get_next_token ($) { Line 384  sub _get_next_token ($) {
384    
385    A: {    A: {
386      if ($self->{state} == DATA_STATE) {      if ($self->{state} == DATA_STATE) {
387        if ($self->{next_input_character} == 0x0026) { # &        if ($self->{next_char} == 0x0026) { # &
388          if ($self->{content_model} & CM_ENTITY) { # PCDATA | RCDATA          if ($self->{content_model} & CM_ENTITY and # PCDATA | RCDATA
389                not $self->{escape}) {
390              !!!cp (1);
391            $self->{state} = ENTITY_DATA_STATE;            $self->{state} = ENTITY_DATA_STATE;
392            !!!next-input-character;            !!!next-input-character;
393            redo A;            redo A;
394          } else {          } else {
395              !!!cp (2);
396            #            #
397          }          }
398        } elsif ($self->{next_input_character} == 0x002D) { # -        } elsif ($self->{next_char} == 0x002D) { # -
399          if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA          if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA
400            unless ($self->{escape}) {            unless ($self->{escape}) {
401              if ($self->{prev_input_character}->[0] == 0x002D and # -              if ($self->{prev_char}->[0] == 0x002D and # -
402                  $self->{prev_input_character}->[1] == 0x0021 and # !                  $self->{prev_char}->[1] == 0x0021 and # !
403                  $self->{prev_input_character}->[2] == 0x003C) { # <                  $self->{prev_char}->[2] == 0x003C) { # <
404                  !!!cp (3);
405                $self->{escape} = 1;                $self->{escape} = 1;
406                } else {
407                  !!!cp (4);
408              }              }
409              } else {
410                !!!cp (5);
411            }            }
412          }          }
413                    
414          #          #
415        } elsif ($self->{next_input_character} == 0x003C) { # <        } elsif ($self->{next_char} == 0x003C) { # <
416          if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA          if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA
417              (($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA              (($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA
418               not $self->{escape})) {               not $self->{escape})) {
419              !!!cp (6);
420            $self->{state} = TAG_OPEN_STATE;            $self->{state} = TAG_OPEN_STATE;
421            !!!next-input-character;            !!!next-input-character;
422            redo A;            redo A;
423          } else {          } else {
424              !!!cp (7);
425            #            #
426          }          }
427        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
428          if ($self->{escape} and          if ($self->{escape} and
429              ($self->{content_model} & CM_LIMITED_MARKUP)) { # RCDATA | CDATA              ($self->{content_model} & CM_LIMITED_MARKUP)) { # RCDATA | CDATA
430            if ($self->{prev_input_character}->[0] == 0x002D and # -            if ($self->{prev_char}->[0] == 0x002D and # -
431                $self->{prev_input_character}->[1] == 0x002D) { # -                $self->{prev_char}->[1] == 0x002D) { # -
432                !!!cp (8);
433              delete $self->{escape};              delete $self->{escape};
434              } else {
435                !!!cp (9);
436            }            }
437            } else {
438              !!!cp (10);
439          }          }
440                    
441          #          #
442        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
443            !!!cp (11);
444          !!!emit ({type => END_OF_FILE_TOKEN});          !!!emit ({type => END_OF_FILE_TOKEN});
445          last A; ## TODO: ok?          last A; ## TODO: ok?
446          } else {
447            !!!cp (12);
448        }        }
449        # Anything else        # Anything else
450        my $token = {type => CHARACTER_TOKEN,        my $token = {type => CHARACTER_TOKEN,
451                     data => chr $self->{next_input_character}};                     data => chr $self->{next_char}};
452        ## Stay in the data state        ## Stay in the data state
453        !!!next-input-character;        !!!next-input-character;
454    
# Line 327  sub _get_next_token ($) { Line 458  sub _get_next_token ($) {
458      } elsif ($self->{state} == ENTITY_DATA_STATE) {      } elsif ($self->{state} == ENTITY_DATA_STATE) {
459        ## (cannot happen in CDATA state)        ## (cannot happen in CDATA state)
460                
461        my $token = $self->_tokenize_attempt_to_consume_an_entity (0);        my $token = $self->_tokenize_attempt_to_consume_an_entity (0, -1);
462    
463        $self->{state} = DATA_STATE;        $self->{state} = DATA_STATE;
464        # next-input-character is already done        # next-input-character is already done
465    
466        unless (defined $token) {        unless (defined $token) {
467            !!!cp (13);
468          !!!emit ({type => CHARACTER_TOKEN, data => '&'});          !!!emit ({type => CHARACTER_TOKEN, data => '&'});
469        } else {        } else {
470            !!!cp (14);
471          !!!emit ($token);          !!!emit ($token);
472        }        }
473    
474        redo A;        redo A;
475      } elsif ($self->{state} == TAG_OPEN_STATE) {      } elsif ($self->{state} == TAG_OPEN_STATE) {
476        if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA        if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA
477          if ($self->{next_input_character} == 0x002F) { # /          if ($self->{next_char} == 0x002F) { # /
478              !!!cp (15);
479            !!!next-input-character;            !!!next-input-character;
480            $self->{state} = CLOSE_TAG_OPEN_STATE;            $self->{state} = CLOSE_TAG_OPEN_STATE;
481            redo A;            redo A;
482          } else {          } else {
483              !!!cp (16);
484            ## reconsume            ## reconsume
485            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
486    
# Line 354  sub _get_next_token ($) { Line 489  sub _get_next_token ($) {
489            redo A;            redo A;
490          }          }
491        } elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA        } elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA
492          if ($self->{next_input_character} == 0x0021) { # !          if ($self->{next_char} == 0x0021) { # !
493              !!!cp (17);
494            $self->{state} = MARKUP_DECLARATION_OPEN_STATE;            $self->{state} = MARKUP_DECLARATION_OPEN_STATE;
495            !!!next-input-character;            !!!next-input-character;
496            redo A;            redo A;
497          } elsif ($self->{next_input_character} == 0x002F) { # /          } elsif ($self->{next_char} == 0x002F) { # /
498              !!!cp (18);
499            $self->{state} = CLOSE_TAG_OPEN_STATE;            $self->{state} = CLOSE_TAG_OPEN_STATE;
500            !!!next-input-character;            !!!next-input-character;
501            redo A;            redo A;
502          } elsif (0x0041 <= $self->{next_input_character} and          } elsif (0x0041 <= $self->{next_char} and
503                   $self->{next_input_character} <= 0x005A) { # A..Z                   $self->{next_char} <= 0x005A) { # A..Z
504              !!!cp (19);
505            $self->{current_token}            $self->{current_token}
506              = {type => START_TAG_TOKEN,              = {type => START_TAG_TOKEN,
507                 tag_name => chr ($self->{next_input_character} + 0x0020)};                 tag_name => chr ($self->{next_char} + 0x0020)};
508            $self->{state} = TAG_NAME_STATE;            $self->{state} = TAG_NAME_STATE;
509            !!!next-input-character;            !!!next-input-character;
510            redo A;            redo A;
511          } elsif (0x0061 <= $self->{next_input_character} and          } elsif (0x0061 <= $self->{next_char} and
512                   $self->{next_input_character} <= 0x007A) { # a..z                   $self->{next_char} <= 0x007A) { # a..z
513              !!!cp (20);
514            $self->{current_token} = {type => START_TAG_TOKEN,            $self->{current_token} = {type => START_TAG_TOKEN,
515                              tag_name => chr ($self->{next_input_character})};                              tag_name => chr ($self->{next_char})};
516            $self->{state} = TAG_NAME_STATE;            $self->{state} = TAG_NAME_STATE;
517            !!!next-input-character;            !!!next-input-character;
518            redo A;            redo A;
519          } elsif ($self->{next_input_character} == 0x003E) { # >          } elsif ($self->{next_char} == 0x003E) { # >
520              !!!cp (21);
521            !!!parse-error (type => 'empty start tag');            !!!parse-error (type => 'empty start tag');
522            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
523            !!!next-input-character;            !!!next-input-character;
# Line 385  sub _get_next_token ($) { Line 525  sub _get_next_token ($) {
525            !!!emit ({type => CHARACTER_TOKEN, data => '<>'});            !!!emit ({type => CHARACTER_TOKEN, data => '<>'});
526    
527            redo A;            redo A;
528          } elsif ($self->{next_input_character} == 0x003F) { # ?          } elsif ($self->{next_char} == 0x003F) { # ?
529              !!!cp (22);
530            !!!parse-error (type => 'pio');            !!!parse-error (type => 'pio');
531            $self->{state} = BOGUS_COMMENT_STATE;            $self->{state} = BOGUS_COMMENT_STATE;
532            ## $self->{next_input_character} is intentionally left as is            ## $self->{next_char} is intentionally left as is
533            redo A;            redo A;
534          } else {          } else {
535              !!!cp (23);
536            !!!parse-error (type => 'bare stago');            !!!parse-error (type => 'bare stago');
537            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
538            ## reconsume            ## reconsume
# Line 408  sub _get_next_token ($) { Line 550  sub _get_next_token ($) {
550            ## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>            ## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>
551            my @next_char;            my @next_char;
552            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++) {
553              push @next_char, $self->{next_input_character};              push @next_char, $self->{next_char};
554              my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1);              my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1);
555              my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c;              my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c;
556              if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) {              if ($self->{next_char} == $c or $self->{next_char} == $C) {
557                  !!!cp (24);
558                !!!next-input-character;                !!!next-input-character;
559                next TAGNAME;                next TAGNAME;
560              } else {              } else {
561                $self->{next_input_character} = shift @next_char; # reconsume                !!!cp (25);
562                  $self->{next_char} = shift @next_char; # reconsume
563                !!!back-next-input-character (@next_char);                !!!back-next-input-character (@next_char);
564                $self->{state} = DATA_STATE;                $self->{state} = DATA_STATE;
565    
# Line 424  sub _get_next_token ($) { Line 568  sub _get_next_token ($) {
568                redo A;                redo A;
569              }              }
570            }            }
571            push @next_char, $self->{next_input_character};            push @next_char, $self->{next_char};
572                
573            unless ($self->{next_input_character} == 0x0009 or # HT            unless ($self->{next_char} == 0x0009 or # HT
574                    $self->{next_input_character} == 0x000A or # LF                    $self->{next_char} == 0x000A or # LF
575                    $self->{next_input_character} == 0x000B or # VT                    $self->{next_char} == 0x000B or # VT
576                    $self->{next_input_character} == 0x000C or # FF                    $self->{next_char} == 0x000C or # FF
577                    $self->{next_input_character} == 0x0020 or # SP                    $self->{next_char} == 0x0020 or # SP
578                    $self->{next_input_character} == 0x003E or # >                    $self->{next_char} == 0x003E or # >
579                    $self->{next_input_character} == 0x002F or # /                    $self->{next_char} == 0x002F or # /
580                    $self->{next_input_character} == -1) {                    $self->{next_char} == -1) {
581              $self->{next_input_character} = shift @next_char; # reconsume              !!!cp (26);
582                $self->{next_char} = shift @next_char; # reconsume
583              !!!back-next-input-character (@next_char);              !!!back-next-input-character (@next_char);
584              $self->{state} = DATA_STATE;              $self->{state} = DATA_STATE;
585              !!!emit ({type => CHARACTER_TOKEN, data => '</'});              !!!emit ({type => CHARACTER_TOKEN, data => '</'});
586              redo A;              redo A;
587            } else {            } else {
588              $self->{next_input_character} = shift @next_char;              !!!cp (27);
589                $self->{next_char} = shift @next_char;
590              !!!back-next-input-character (@next_char);              !!!back-next-input-character (@next_char);
591              # and consume...              # and consume...
592            }            }
593          } else {          } else {
594            ## No start tag token has ever been emitted            ## No start tag token has ever been emitted
595              !!!cp (28);
596            # next-input-character is already done            # next-input-character is already done
597            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
598            !!!emit ({type => CHARACTER_TOKEN, data => '</'});            !!!emit ({type => CHARACTER_TOKEN, data => '</'});
# Line 453  sub _get_next_token ($) { Line 600  sub _get_next_token ($) {
600          }          }
601        }        }
602                
603        if (0x0041 <= $self->{next_input_character} and        if (0x0041 <= $self->{next_char} and
604            $self->{next_input_character} <= 0x005A) { # A..Z            $self->{next_char} <= 0x005A) { # A..Z
605            !!!cp (29);
606          $self->{current_token} = {type => END_TAG_TOKEN,          $self->{current_token} = {type => END_TAG_TOKEN,
607                            tag_name => chr ($self->{next_input_character} + 0x0020)};                            tag_name => chr ($self->{next_char} + 0x0020)};
608          $self->{state} = TAG_NAME_STATE;          $self->{state} = TAG_NAME_STATE;
609          !!!next-input-character;          !!!next-input-character;
610          redo A;          redo A;
611        } elsif (0x0061 <= $self->{next_input_character} and        } elsif (0x0061 <= $self->{next_char} and
612                 $self->{next_input_character} <= 0x007A) { # a..z                 $self->{next_char} <= 0x007A) { # a..z
613            !!!cp (30);
614          $self->{current_token} = {type => END_TAG_TOKEN,          $self->{current_token} = {type => END_TAG_TOKEN,
615                            tag_name => chr ($self->{next_input_character})};                            tag_name => chr ($self->{next_char})};
616          $self->{state} = TAG_NAME_STATE;          $self->{state} = TAG_NAME_STATE;
617          !!!next-input-character;          !!!next-input-character;
618          redo A;          redo A;
619        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
620            !!!cp (31);
621          !!!parse-error (type => 'empty end tag');          !!!parse-error (type => 'empty end tag');
622          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
623          !!!next-input-character;          !!!next-input-character;
624          redo A;          redo A;
625        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
626            !!!cp (32);
627          !!!parse-error (type => 'bare etago');          !!!parse-error (type => 'bare etago');
628          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
629          # reconsume          # reconsume
# Line 481  sub _get_next_token ($) { Line 632  sub _get_next_token ($) {
632    
633          redo A;          redo A;
634        } else {        } else {
635            !!!cp (33);
636          !!!parse-error (type => 'bogus end tag');          !!!parse-error (type => 'bogus end tag');
637          $self->{state} = BOGUS_COMMENT_STATE;          $self->{state} = BOGUS_COMMENT_STATE;
638          ## $self->{next_input_character} is intentionally left as is          ## $self->{next_char} is intentionally left as is
639          redo A;          redo A;
640        }        }
641      } elsif ($self->{state} == TAG_NAME_STATE) {      } elsif ($self->{state} == TAG_NAME_STATE) {
642        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
643            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
644            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
645            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
646            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
647            !!!cp (34);
648          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
649          !!!next-input-character;          !!!next-input-character;
650          redo A;          redo A;
651        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
652          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
653              !!!cp (35);
654            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
655                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
656            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
657          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
658            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
659            if ($self->{current_token}->{attributes}) {            #if ($self->{current_token}->{attributes}) {
660              !!!parse-error (type => 'end tag attribute');            #  ## NOTE: This should never be reached.
661            }            #  !!! cp (36);
662              #  !!! parse-error (type => 'end tag attribute');
663              #} else {
664                !!!cp (37);
665              #}
666          } else {          } else {
667            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
668          }          }
# Line 514  sub _get_next_token ($) { Line 672  sub _get_next_token ($) {
672          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
673    
674          redo A;          redo A;
675        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
676                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
677          $self->{current_token}->{tag_name} .= chr ($self->{next_input_character} + 0x0020);          !!!cp (38);
678            $self->{current_token}->{tag_name} .= chr ($self->{next_char} + 0x0020);
679            # start tag or end tag            # start tag or end tag
680          ## Stay in this state          ## Stay in this state
681          !!!next-input-character;          !!!next-input-character;
682          redo A;          redo A;
683        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
684          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
685          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
686              !!!cp (39);
687            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
688                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
689            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
690          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
691            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
692            if ($self->{current_token}->{attributes}) {            #if ($self->{current_token}->{attributes}) {
693              !!!parse-error (type => 'end tag attribute');            #  ## NOTE: This state should never be reached.
694            }            #  !!! cp (40);
695              #  !!! parse-error (type => 'end tag attribute');
696              #} else {
697                !!!cp (41);
698              #}
699          } else {          } else {
700            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
701          }          }
# Line 541  sub _get_next_token ($) { Line 705  sub _get_next_token ($) {
705          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
706    
707          redo A;          redo A;
708        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == 0x002F) { # /
709          !!!next-input-character;          !!!next-input-character;
710          if ($self->{next_input_character} == 0x003E and # >          if ($self->{next_char} == 0x003E and # >
711              $self->{current_token}->{type} == START_TAG_TOKEN and              $self->{current_token}->{type} == START_TAG_TOKEN and
712              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {
713            # permitted slash            # permitted slash
714              !!!cp (42);
715            #            #
716          } else {          } else {
717              !!!cp (43);
718            !!!parse-error (type => 'nestc');            !!!parse-error (type => 'nestc');
719          }          }
720          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
721          # next-input-character is already done          # next-input-character is already done
722          redo A;          redo A;
723        } else {        } else {
724          $self->{current_token}->{tag_name} .= chr $self->{next_input_character};          !!!cp (44);
725            $self->{current_token}->{tag_name} .= chr $self->{next_char};
726            # start tag or end tag            # start tag or end tag
727          ## Stay in the state          ## Stay in the state
728          !!!next-input-character;          !!!next-input-character;
729          redo A;          redo A;
730        }        }
731      } elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) {      } elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) {
732        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
733            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
734            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
735            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
736            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
737            !!!cp (45);
738          ## Stay in the state          ## Stay in the state
739          !!!next-input-character;          !!!next-input-character;
740          redo A;          redo A;
741        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
742          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
743              !!!cp (46);
744            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
745                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
746            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
747          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
748            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
749            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
750                !!!cp (47);
751              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
752              } else {
753                !!!cp (48);
754            }            }
755          } else {          } else {
756            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 589  sub _get_next_token ($) { Line 761  sub _get_next_token ($) {
761          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
762    
763          redo A;          redo A;
764        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
765                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
766          $self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020),          !!!cp (49);
767            $self->{current_attribute} = {name => chr ($self->{next_char} + 0x0020),
768                                value => ''};                                value => ''};
769          $self->{state} = ATTRIBUTE_NAME_STATE;          $self->{state} = ATTRIBUTE_NAME_STATE;
770          !!!next-input-character;          !!!next-input-character;
771          redo A;          redo A;
772        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == 0x002F) { # /
773          !!!next-input-character;          !!!next-input-character;
774          if ($self->{next_input_character} == 0x003E and # >          if ($self->{next_char} == 0x003E and # >
775              $self->{current_token}->{type} == START_TAG_TOKEN and              $self->{current_token}->{type} == START_TAG_TOKEN and
776              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {
777            # permitted slash            # permitted slash
778              !!!cp (50);
779            #            #
780          } else {          } else {
781              !!!cp (51);
782            !!!parse-error (type => 'nestc');            !!!parse-error (type => 'nestc');
783          }          }
784          ## Stay in the state          ## Stay in the state
785          # next-input-character is already done          # next-input-character is already done
786          redo A;          redo A;
787        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
788          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
789          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
790              !!!cp (52);
791            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
792                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
793            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
794          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
795            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
796            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
797                !!!cp (53);
798              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
799              } else {
800                !!!cp (54);
801            }            }
802          } else {          } else {
803            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 630  sub _get_next_token ($) { Line 809  sub _get_next_token ($) {
809    
810          redo A;          redo A;
811        } else {        } else {
812          $self->{current_attribute} = {name => chr ($self->{next_input_character}),          if ({
813                 0x0022 => 1, # "
814                 0x0027 => 1, # '
815                 0x003D => 1, # =
816                }->{$self->{next_char}}) {
817              !!!cp (55);
818              !!!parse-error (type => 'bad attribute name');
819            } else {
820              !!!cp (56);
821            }
822            $self->{current_attribute} = {name => chr ($self->{next_char}),
823                                value => ''};                                value => ''};
824          $self->{state} = ATTRIBUTE_NAME_STATE;          $self->{state} = ATTRIBUTE_NAME_STATE;
825          !!!next-input-character;          !!!next-input-character;
# Line 640  sub _get_next_token ($) { Line 829  sub _get_next_token ($) {
829        my $before_leave = sub {        my $before_leave = sub {
830          if (exists $self->{current_token}->{attributes} # start tag or end tag          if (exists $self->{current_token}->{attributes} # start tag or end tag
831              ->{$self->{current_attribute}->{name}}) { # MUST              ->{$self->{current_attribute}->{name}}) { # MUST
832              !!!cp (57);
833            !!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name});            !!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name});
834            ## Discard $self->{current_attribute} # MUST            ## Discard $self->{current_attribute} # MUST
835          } else {          } else {
836              !!!cp (58);
837            $self->{current_token}->{attributes}->{$self->{current_attribute}->{name}}            $self->{current_token}->{attributes}->{$self->{current_attribute}->{name}}
838              = $self->{current_attribute};              = $self->{current_attribute};
839          }          }
840        }; # $before_leave        }; # $before_leave
841    
842        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
843            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
844            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
845            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
846            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
847            !!!cp (59);
848          $before_leave->();          $before_leave->();
849          $self->{state} = AFTER_ATTRIBUTE_NAME_STATE;          $self->{state} = AFTER_ATTRIBUTE_NAME_STATE;
850          !!!next-input-character;          !!!next-input-character;
851          redo A;          redo A;
852        } elsif ($self->{next_input_character} == 0x003D) { # =        } elsif ($self->{next_char} == 0x003D) { # =
853            !!!cp (60);
854          $before_leave->();          $before_leave->();
855          $self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE;          $self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE;
856          !!!next-input-character;          !!!next-input-character;
857          redo A;          redo A;
858        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
859          $before_leave->();          $before_leave->();
860          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
861              !!!cp (61);
862            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
863                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
864            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
865          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
866              !!!cp (62);
867            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
868            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
869              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
# Line 682  sub _get_next_token ($) { Line 877  sub _get_next_token ($) {
877          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
878    
879          redo A;          redo A;
880        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
881                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
882          $self->{current_attribute}->{name} .= chr ($self->{next_input_character} + 0x0020);          !!!cp (63);
883            $self->{current_attribute}->{name} .= chr ($self->{next_char} + 0x0020);
884          ## Stay in the state          ## Stay in the state
885          !!!next-input-character;          !!!next-input-character;
886          redo A;          redo A;
887        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == 0x002F) { # /
888          $before_leave->();          $before_leave->();
889          !!!next-input-character;          !!!next-input-character;
890          if ($self->{next_input_character} == 0x003E and # >          if ($self->{next_char} == 0x003E and # >
891              $self->{current_token}->{type} == START_TAG_TOKEN and              $self->{current_token}->{type} == START_TAG_TOKEN and
892              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {
893            # permitted slash            # permitted slash
894              !!!cp (64);
895            #            #
896          } else {          } else {
897              !!!cp (65);
898            !!!parse-error (type => 'nestc');            !!!parse-error (type => 'nestc');
899          }          }
900          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
901          # next-input-character is already done          # next-input-character is already done
902          redo A;          redo A;
903        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
904          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
905          $before_leave->();          $before_leave->();
906          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
907              !!!cp (66);
908            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
909                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
910            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
911          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
912            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
913            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
914                !!!cp (67);
915              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
916              } else {
917                ## NOTE: This state should never be reached.
918                !!!cp (68);
919            }            }
920          } else {          } else {
921            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 724  sub _get_next_token ($) { Line 927  sub _get_next_token ($) {
927    
928          redo A;          redo A;
929        } else {        } else {
930          $self->{current_attribute}->{name} .= chr ($self->{next_input_character});          if ($self->{next_char} == 0x0022 or # "
931                $self->{next_char} == 0x0027) { # '
932              !!!cp (69);
933              !!!parse-error (type => 'bad attribute name');
934            } else {
935              !!!cp (70);
936            }
937            $self->{current_attribute}->{name} .= chr ($self->{next_char});
938          ## Stay in the state          ## Stay in the state
939          !!!next-input-character;          !!!next-input-character;
940          redo A;          redo A;
941        }        }
942      } elsif ($self->{state} == AFTER_ATTRIBUTE_NAME_STATE) {      } elsif ($self->{state} == AFTER_ATTRIBUTE_NAME_STATE) {
943        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
944            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
945            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
946            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
947            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
948            !!!cp (71);
949          ## Stay in the state          ## Stay in the state
950          !!!next-input-character;          !!!next-input-character;
951          redo A;          redo A;
952        } elsif ($self->{next_input_character} == 0x003D) { # =        } elsif ($self->{next_char} == 0x003D) { # =
953            !!!cp (72);
954          $self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE;          $self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE;
955          !!!next-input-character;          !!!next-input-character;
956          redo A;          redo A;
957        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
958          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
959              !!!cp (73);
960            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
961                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
962            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
963          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
964            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
965            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
966                !!!cp (74);
967              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
968              } else {
969                ## NOTE: This state should never be reached.
970                !!!cp (75);
971            }            }
972          } else {          } else {
973            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 761  sub _get_next_token ($) { Line 978  sub _get_next_token ($) {
978          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
979    
980          redo A;          redo A;
981        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
982                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
983          $self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020),          !!!cp (76);
984            $self->{current_attribute} = {name => chr ($self->{next_char} + 0x0020),
985                                value => ''};                                value => ''};
986          $self->{state} = ATTRIBUTE_NAME_STATE;          $self->{state} = ATTRIBUTE_NAME_STATE;
987          !!!next-input-character;          !!!next-input-character;
988          redo A;          redo A;
989        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == 0x002F) { # /
990          !!!next-input-character;          !!!next-input-character;
991          if ($self->{next_input_character} == 0x003E and # >          if ($self->{next_char} == 0x003E and # >
992              $self->{current_token}->{type} == START_TAG_TOKEN and              $self->{current_token}->{type} == START_TAG_TOKEN and
993              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {
994            # permitted slash            # permitted slash
995              !!!cp (77);
996            #            #
997          } else {          } else {
998              !!!cp (78);
999            !!!parse-error (type => 'nestc');            !!!parse-error (type => 'nestc');
1000            ## TODO: Different error type for <aa / bb> than <aa/>            ## TODO: Different error type for <aa / bb> than <aa/>
1001          }          }
1002          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1003          # next-input-character is already done          # next-input-character is already done
1004          redo A;          redo A;
1005        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1006          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1007          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1008              !!!cp (79);
1009            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
1010                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
1011            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1012          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1013            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1014            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1015                !!!cp (80);
1016              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1017              } else {
1018                ## NOTE: This state should never be reached.
1019                !!!cp (81);
1020            }            }
1021          } else {          } else {
1022            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 803  sub _get_next_token ($) { Line 1028  sub _get_next_token ($) {
1028    
1029          redo A;          redo A;
1030        } else {        } else {
1031          $self->{current_attribute} = {name => chr ($self->{next_input_character}),          !!!cp (82);
1032            $self->{current_attribute} = {name => chr ($self->{next_char}),
1033                                value => ''};                                value => ''};
1034          $self->{state} = ATTRIBUTE_NAME_STATE;          $self->{state} = ATTRIBUTE_NAME_STATE;
1035          !!!next-input-character;          !!!next-input-character;
1036          redo A;                  redo A;        
1037        }        }
1038      } elsif ($self->{state} == BEFORE_ATTRIBUTE_VALUE_STATE) {      } elsif ($self->{state} == BEFORE_ATTRIBUTE_VALUE_STATE) {
1039        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1040            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1041            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1042            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1043            $self->{next_input_character} == 0x0020) { # SP                  $self->{next_char} == 0x0020) { # SP      
1044            !!!cp (83);
1045          ## Stay in the state          ## Stay in the state
1046          !!!next-input-character;          !!!next-input-character;
1047          redo A;          redo A;
1048        } elsif ($self->{next_input_character} == 0x0022) { # "        } elsif ($self->{next_char} == 0x0022) { # "
1049            !!!cp (84);
1050          $self->{state} = ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE;          $self->{state} = ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE;
1051          !!!next-input-character;          !!!next-input-character;
1052          redo A;          redo A;
1053        } elsif ($self->{next_input_character} == 0x0026) { # &        } elsif ($self->{next_char} == 0x0026) { # &
1054            !!!cp (85);
1055          $self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE;          $self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE;
1056          ## reconsume          ## reconsume
1057          redo A;          redo A;
1058        } elsif ($self->{next_input_character} == 0x0027) { # '        } elsif ($self->{next_char} == 0x0027) { # '
1059            !!!cp (86);
1060          $self->{state} = ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE;          $self->{state} = ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE;
1061          !!!next-input-character;          !!!next-input-character;
1062          redo A;          redo A;
1063        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1064          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1065              !!!cp (87);
1066            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
1067                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
1068            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1069          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1070            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1071            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1072                !!!cp (88);
1073              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1074              } else {
1075                ## NOTE: This state should never be reached.
1076                !!!cp (89);
1077            }            }
1078          } else {          } else {
1079            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 849  sub _get_next_token ($) { Line 1084  sub _get_next_token ($) {
1084          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1085    
1086          redo A;          redo A;
1087        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1088          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1089          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1090              !!!cp (90);
1091            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
1092                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
1093            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1094          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1095            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1096            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1097                !!!cp (91);
1098              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1099              } else {
1100                ## NOTE: This state should never be reached.
1101                !!!cp (92);
1102            }            }
1103          } else {          } else {
1104            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 870  sub _get_next_token ($) { Line 1110  sub _get_next_token ($) {
1110    
1111          redo A;          redo A;
1112        } else {        } else {
1113          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          if ($self->{next_char} == 0x003D) { # =
1114              !!!cp (93);
1115              !!!parse-error (type => 'bad attribute value');
1116            } else {
1117              !!!cp (94);
1118            }
1119            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1120          $self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE;          $self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE;
1121          !!!next-input-character;          !!!next-input-character;
1122          redo A;          redo A;
1123        }        }
1124      } elsif ($self->{state} == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE) {      } elsif ($self->{state} == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE) {
1125        if ($self->{next_input_character} == 0x0022) { # "        if ($self->{next_char} == 0x0022) { # "
1126          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          !!!cp (95);
1127            $self->{state} = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE;
1128          !!!next-input-character;          !!!next-input-character;
1129          redo A;          redo A;
1130        } elsif ($self->{next_input_character} == 0x0026) { # &        } elsif ($self->{next_char} == 0x0026) { # &
1131            !!!cp (96);
1132          $self->{last_attribute_value_state} = $self->{state};          $self->{last_attribute_value_state} = $self->{state};
1133          $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;          $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;
1134          !!!next-input-character;          !!!next-input-character;
1135          redo A;          redo A;
1136        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1137          !!!parse-error (type => 'unclosed attribute value');          !!!parse-error (type => 'unclosed attribute value');
1138          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1139              !!!cp (97);
1140            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
1141                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
1142            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1143          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1144            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1145            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1146                !!!cp (98);
1147              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1148              } else {
1149                ## NOTE: This state should never be reached.
1150                !!!cp (99);
1151            }            }
1152          } else {          } else {
1153            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 906  sub _get_next_token ($) { Line 1159  sub _get_next_token ($) {
1159    
1160          redo A;          redo A;
1161        } else {        } else {
1162          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          !!!cp (100);
1163            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1164          ## Stay in the state          ## Stay in the state
1165          !!!next-input-character;          !!!next-input-character;
1166          redo A;          redo A;
1167        }        }
1168      } elsif ($self->{state} == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE) {      } elsif ($self->{state} == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE) {
1169        if ($self->{next_input_character} == 0x0027) { # '        if ($self->{next_char} == 0x0027) { # '
1170          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          !!!cp (101);
1171            $self->{state} = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE;
1172          !!!next-input-character;          !!!next-input-character;
1173          redo A;          redo A;
1174        } elsif ($self->{next_input_character} == 0x0026) { # &        } elsif ($self->{next_char} == 0x0026) { # &
1175            !!!cp (102);
1176          $self->{last_attribute_value_state} = $self->{state};          $self->{last_attribute_value_state} = $self->{state};
1177          $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;          $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;
1178          !!!next-input-character;          !!!next-input-character;
1179          redo A;          redo A;
1180        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1181          !!!parse-error (type => 'unclosed attribute value');          !!!parse-error (type => 'unclosed attribute value');
1182          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1183              !!!cp (103);
1184            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
1185                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
1186            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1187          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1188            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1189            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1190                !!!cp (104);
1191              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1192              } else {
1193                ## NOTE: This state should never be reached.
1194                !!!cp (105);
1195            }            }
1196          } else {          } else {
1197            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 942  sub _get_next_token ($) { Line 1203  sub _get_next_token ($) {
1203    
1204          redo A;          redo A;
1205        } else {        } else {
1206          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          !!!cp (106);
1207            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1208          ## Stay in the state          ## Stay in the state
1209          !!!next-input-character;          !!!next-input-character;
1210          redo A;          redo A;
1211        }        }
1212      } elsif ($self->{state} == ATTRIBUTE_VALUE_UNQUOTED_STATE) {      } elsif ($self->{state} == ATTRIBUTE_VALUE_UNQUOTED_STATE) {
1213        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1214            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1215            $self->{next_input_character} == 0x000B or # HT            $self->{next_char} == 0x000B or # HT
1216            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1217            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1218            !!!cp (107);
1219          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1220          !!!next-input-character;          !!!next-input-character;
1221          redo A;          redo A;
1222        } elsif ($self->{next_input_character} == 0x0026) { # &        } elsif ($self->{next_char} == 0x0026) { # &
1223            !!!cp (108);
1224          $self->{last_attribute_value_state} = $self->{state};          $self->{last_attribute_value_state} = $self->{state};
1225          $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;          $self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE;
1226          !!!next-input-character;          !!!next-input-character;
1227          redo A;          redo A;
1228        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1229          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1230              !!!cp (109);
1231            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
1232                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
1233            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1234          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1235            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1236            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1237                !!!cp (110);
1238              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1239              } else {
1240                ## NOTE: This state should never be reached.
1241                !!!cp (111);
1242            }            }
1243          } else {          } else {
1244            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 980  sub _get_next_token ($) { Line 1249  sub _get_next_token ($) {
1249          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
1250    
1251          redo A;          redo A;
1252        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1253          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
1254          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1255              !!!cp (112);
1256            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
1257                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
1258            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1259          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1260            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1261            if ($self->{current_token}->{attributes}) {            if ($self->{current_token}->{attributes}) {
1262                !!!cp (113);
1263              !!!parse-error (type => 'end tag attribute');              !!!parse-error (type => 'end tag attribute');
1264              } else {
1265                ## NOTE: This state should never be reached.
1266                !!!cp (114);
1267            }            }
1268          } else {          } else {
1269            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
# Line 1001  sub _get_next_token ($) { Line 1275  sub _get_next_token ($) {
1275    
1276          redo A;          redo A;
1277        } else {        } else {
1278          $self->{current_attribute}->{value} .= chr ($self->{next_input_character});          if ({
1279                 0x0022 => 1, # "
1280                 0x0027 => 1, # '
1281                 0x003D => 1, # =
1282                }->{$self->{next_char}}) {
1283              !!!cp (115);
1284              !!!parse-error (type => 'bad attribute value');
1285            } else {
1286              !!!cp (116);
1287            }
1288            $self->{current_attribute}->{value} .= chr ($self->{next_char});
1289          ## Stay in the state          ## Stay in the state
1290          !!!next-input-character;          !!!next-input-character;
1291          redo A;          redo A;
1292        }        }
1293      } elsif ($self->{state} == ENTITY_IN_ATTRIBUTE_VALUE_STATE) {      } elsif ($self->{state} == ENTITY_IN_ATTRIBUTE_VALUE_STATE) {
1294        my $token = $self->_tokenize_attempt_to_consume_an_entity (1);        my $token = $self->_tokenize_attempt_to_consume_an_entity
1295              (1,
1296               $self->{last_attribute_value_state}
1297                 == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE ? 0x0022 : # "
1298               $self->{last_attribute_value_state}
1299                 == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE ? 0x0027 : # '
1300               -1);
1301    
1302        unless (defined $token) {        unless (defined $token) {
1303            !!!cp (117);
1304          $self->{current_attribute}->{value} .= '&';          $self->{current_attribute}->{value} .= '&';
1305        } else {        } else {
1306            !!!cp (118);
1307          $self->{current_attribute}->{value} .= $token->{data};          $self->{current_attribute}->{value} .= $token->{data};
1308            $self->{current_attribute}->{has_reference} = $token->{has_reference};
1309          ## 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"
1310        }        }
1311    
1312        $self->{state} = $self->{last_attribute_value_state};        $self->{state} = $self->{last_attribute_value_state};
1313        # next-input-character is already done        # next-input-character is already done
1314        redo A;        redo A;
1315        } elsif ($self->{state} == AFTER_ATTRIBUTE_VALUE_QUOTED_STATE) {
1316          if ($self->{next_char} == 0x0009 or # HT
1317              $self->{next_char} == 0x000A or # LF
1318              $self->{next_char} == 0x000B or # VT
1319              $self->{next_char} == 0x000C or # FF
1320              $self->{next_char} == 0x0020) { # SP
1321            !!!cp (118);
1322            $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1323            !!!next-input-character;
1324            redo A;
1325          } elsif ($self->{next_char} == 0x003E) { # >
1326            if ($self->{current_token}->{type} == START_TAG_TOKEN) {
1327              !!!cp (119);
1328              $self->{current_token}->{first_start_tag}
1329                  = not defined $self->{last_emitted_start_tag_name};
1330              $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
1331            } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
1332              $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
1333              if ($self->{current_token}->{attributes}) {
1334                !!!cp (120);
1335                !!!parse-error (type => 'end tag attribute');
1336              } else {
1337                ## NOTE: This state should never be reached.
1338                !!!cp (121);
1339              }
1340            } else {
1341              die "$0: $self->{current_token}->{type}: Unknown token type";
1342            }
1343            $self->{state} = DATA_STATE;
1344            !!!next-input-character;
1345    
1346            !!!emit ($self->{current_token}); # start tag or end tag
1347    
1348            redo A;
1349          } elsif ($self->{next_char} == 0x002F) { # /
1350            !!!next-input-character;
1351            if ($self->{next_char} == 0x003E and # >
1352                $self->{current_token}->{type} == START_TAG_TOKEN and
1353                $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {
1354              # permitted slash
1355              !!!cp (122);
1356              #
1357            } else {
1358              !!!cp (123);
1359              !!!parse-error (type => 'nestc');
1360            }
1361            $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1362            # next-input-character is already done
1363            redo A;
1364          } else {
1365            !!!cp (124);
1366            !!!parse-error (type => 'no space between attributes');
1367            $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
1368            ## reconsume
1369            redo A;
1370          }
1371      } elsif ($self->{state} == BOGUS_COMMENT_STATE) {      } elsif ($self->{state} == BOGUS_COMMENT_STATE) {
1372        ## (only happen if PCDATA state)        ## (only happen if PCDATA state)
1373                
1374        my $token = {type => COMMENT_TOKEN, data => ''};        my $token = {type => COMMENT_TOKEN, data => ''};
1375    
1376        BC: {        BC: {
1377          if ($self->{next_input_character} == 0x003E) { # >          if ($self->{next_char} == 0x003E) { # >
1378              !!!cp (124);
1379            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
1380            !!!next-input-character;            !!!next-input-character;
1381    
1382            !!!emit ($token);            !!!emit ($token);
1383    
1384            redo A;            redo A;
1385          } elsif ($self->{next_input_character} == -1) {          } elsif ($self->{next_char} == -1) {
1386              !!!cp (125);
1387            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
1388            ## reconsume            ## reconsume
1389    
# Line 1040  sub _get_next_token ($) { Line 1391  sub _get_next_token ($) {
1391    
1392            redo A;            redo A;
1393          } else {          } else {
1394            $token->{data} .= chr ($self->{next_input_character});            !!!cp (126);
1395              $token->{data} .= chr ($self->{next_char});
1396            !!!next-input-character;            !!!next-input-character;
1397            redo BC;            redo BC;
1398          }          }
1399        } # BC        } # BC
1400    
1401          die "$0: _get_next_token: unexpected case [BC]";
1402      } elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) {      } elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) {
1403        ## (only happen if PCDATA state)        ## (only happen if PCDATA state)
1404    
1405        my @next_char;        my @next_char;
1406        push @next_char, $self->{next_input_character};        push @next_char, $self->{next_char};
1407                
1408        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1409          !!!next-input-character;          !!!next-input-character;
1410          push @next_char, $self->{next_input_character};          push @next_char, $self->{next_char};
1411          if ($self->{next_input_character} == 0x002D) { # -          if ($self->{next_char} == 0x002D) { # -
1412              !!!cp (127);
1413            $self->{current_token} = {type => COMMENT_TOKEN, data => ''};            $self->{current_token} = {type => COMMENT_TOKEN, data => ''};
1414            $self->{state} = COMMENT_START_STATE;            $self->{state} = COMMENT_START_STATE;
1415            !!!next-input-character;            !!!next-input-character;
1416            redo A;            redo A;
1417            } else {
1418              !!!cp (128);
1419          }          }
1420        } elsif ($self->{next_input_character} == 0x0044 or # D        } elsif ($self->{next_char} == 0x0044 or # D
1421                 $self->{next_input_character} == 0x0064) { # d                 $self->{next_char} == 0x0064) { # d
1422          !!!next-input-character;          !!!next-input-character;
1423          push @next_char, $self->{next_input_character};          push @next_char, $self->{next_char};
1424          if ($self->{next_input_character} == 0x004F or # O          if ($self->{next_char} == 0x004F or # O
1425              $self->{next_input_character} == 0x006F) { # o              $self->{next_char} == 0x006F) { # o
1426            !!!next-input-character;            !!!next-input-character;
1427            push @next_char, $self->{next_input_character};            push @next_char, $self->{next_char};
1428            if ($self->{next_input_character} == 0x0043 or # C            if ($self->{next_char} == 0x0043 or # C
1429                $self->{next_input_character} == 0x0063) { # c                $self->{next_char} == 0x0063) { # c
1430              !!!next-input-character;              !!!next-input-character;
1431              push @next_char, $self->{next_input_character};              push @next_char, $self->{next_char};
1432              if ($self->{next_input_character} == 0x0054 or # T              if ($self->{next_char} == 0x0054 or # T
1433                  $self->{next_input_character} == 0x0074) { # t                  $self->{next_char} == 0x0074) { # t
1434                !!!next-input-character;                !!!next-input-character;
1435                push @next_char, $self->{next_input_character};                push @next_char, $self->{next_char};
1436                if ($self->{next_input_character} == 0x0059 or # Y                if ($self->{next_char} == 0x0059 or # Y
1437                    $self->{next_input_character} == 0x0079) { # y                    $self->{next_char} == 0x0079) { # y
1438                  !!!next-input-character;                  !!!next-input-character;
1439                  push @next_char, $self->{next_input_character};                  push @next_char, $self->{next_char};
1440                  if ($self->{next_input_character} == 0x0050 or # P                  if ($self->{next_char} == 0x0050 or # P
1441                      $self->{next_input_character} == 0x0070) { # p                      $self->{next_char} == 0x0070) { # p
1442                    !!!next-input-character;                    !!!next-input-character;
1443                    push @next_char, $self->{next_input_character};                    push @next_char, $self->{next_char};
1444                    if ($self->{next_input_character} == 0x0045 or # E                    if ($self->{next_char} == 0x0045 or # E
1445                        $self->{next_input_character} == 0x0065) { # e                        $self->{next_char} == 0x0065) { # e
1446                      ## ISSUE: What a stupid code this is!                      !!!cp (129);
1447                        ## TODO: What a stupid code this is!
1448                      $self->{state} = DOCTYPE_STATE;                      $self->{state} = DOCTYPE_STATE;
1449                      !!!next-input-character;                      !!!next-input-character;
1450                      redo A;                      redo A;
1451                      } else {
1452                        !!!cp (130);
1453                    }                    }
1454                    } else {
1455                      !!!cp (131);
1456                  }                  }
1457                  } else {
1458                    !!!cp (132);
1459                }                }
1460                } else {
1461                  !!!cp (133);
1462              }              }
1463              } else {
1464                !!!cp (134);
1465            }            }
1466            } else {
1467              !!!cp (135);
1468          }          }
1469          } else {
1470            !!!cp (136);
1471        }        }
1472    
1473        !!!parse-error (type => 'bogus comment');        !!!parse-error (type => 'bogus comment');
1474        $self->{next_input_character} = shift @next_char;        $self->{next_char} = shift @next_char;
1475        !!!back-next-input-character (@next_char);        !!!back-next-input-character (@next_char);
1476        $self->{state} = BOGUS_COMMENT_STATE;        $self->{state} = BOGUS_COMMENT_STATE;
1477        redo A;        redo A;
# Line 1107  sub _get_next_token ($) { Line 1479  sub _get_next_token ($) {
1479        ## ISSUE: typos in spec: chacacters, is is a parse error        ## ISSUE: typos in spec: chacacters, is is a parse error
1480        ## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it?        ## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it?
1481      } elsif ($self->{state} == COMMENT_START_STATE) {      } elsif ($self->{state} == COMMENT_START_STATE) {
1482        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1483            !!!cp (137);
1484          $self->{state} = COMMENT_START_DASH_STATE;          $self->{state} = COMMENT_START_DASH_STATE;
1485          !!!next-input-character;          !!!next-input-character;
1486          redo A;          redo A;
1487        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1488            !!!cp (138);
1489          !!!parse-error (type => 'bogus comment');          !!!parse-error (type => 'bogus comment');
1490          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1491          !!!next-input-character;          !!!next-input-character;
# Line 1119  sub _get_next_token ($) { Line 1493  sub _get_next_token ($) {
1493          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1494    
1495          redo A;          redo A;
1496        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1497            !!!cp (139);
1498          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1499          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1500          ## reconsume          ## reconsume
# Line 1128  sub _get_next_token ($) { Line 1503  sub _get_next_token ($) {
1503    
1504          redo A;          redo A;
1505        } else {        } else {
1506            !!!cp (140);
1507          $self->{current_token}->{data} # comment          $self->{current_token}->{data} # comment
1508              .= chr ($self->{next_input_character});              .= chr ($self->{next_char});
1509          $self->{state} = COMMENT_STATE;          $self->{state} = COMMENT_STATE;
1510          !!!next-input-character;          !!!next-input-character;
1511          redo A;          redo A;
1512        }        }
1513      } elsif ($self->{state} == COMMENT_START_DASH_STATE) {      } elsif ($self->{state} == COMMENT_START_DASH_STATE) {
1514        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1515            !!!cp (141);
1516          $self->{state} = COMMENT_END_STATE;          $self->{state} = COMMENT_END_STATE;
1517          !!!next-input-character;          !!!next-input-character;
1518          redo A;          redo A;
1519        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1520            !!!cp (142);
1521          !!!parse-error (type => 'bogus comment');          !!!parse-error (type => 'bogus comment');
1522          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1523          !!!next-input-character;          !!!next-input-character;
# Line 1147  sub _get_next_token ($) { Line 1525  sub _get_next_token ($) {
1525          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1526    
1527          redo A;          redo A;
1528        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1529            !!!cp (143);
1530          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1531          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1532          ## reconsume          ## reconsume
# Line 1156  sub _get_next_token ($) { Line 1535  sub _get_next_token ($) {
1535    
1536          redo A;          redo A;
1537        } else {        } else {
1538            !!!cp (144);
1539          $self->{current_token}->{data} # comment          $self->{current_token}->{data} # comment
1540              .= '-' . chr ($self->{next_input_character});              .= '-' . chr ($self->{next_char});
1541          $self->{state} = COMMENT_STATE;          $self->{state} = COMMENT_STATE;
1542          !!!next-input-character;          !!!next-input-character;
1543          redo A;          redo A;
1544        }        }
1545      } elsif ($self->{state} == COMMENT_STATE) {      } elsif ($self->{state} == COMMENT_STATE) {
1546        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1547            !!!cp (145);
1548          $self->{state} = COMMENT_END_DASH_STATE;          $self->{state} = COMMENT_END_DASH_STATE;
1549          !!!next-input-character;          !!!next-input-character;
1550          redo A;          redo A;
1551        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1552            !!!cp (146);
1553          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1554          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1555          ## reconsume          ## reconsume
# Line 1176  sub _get_next_token ($) { Line 1558  sub _get_next_token ($) {
1558    
1559          redo A;          redo A;
1560        } else {        } else {
1561          $self->{current_token}->{data} .= chr ($self->{next_input_character}); # comment          !!!cp (147);
1562            $self->{current_token}->{data} .= chr ($self->{next_char}); # comment
1563          ## Stay in the state          ## Stay in the state
1564          !!!next-input-character;          !!!next-input-character;
1565          redo A;          redo A;
1566        }        }
1567      } elsif ($self->{state} == COMMENT_END_DASH_STATE) {      } elsif ($self->{state} == COMMENT_END_DASH_STATE) {
1568        if ($self->{next_input_character} == 0x002D) { # -        if ($self->{next_char} == 0x002D) { # -
1569            !!!cp (148);
1570          $self->{state} = COMMENT_END_STATE;          $self->{state} = COMMENT_END_STATE;
1571          !!!next-input-character;          !!!next-input-character;
1572          redo A;          redo A;
1573        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1574            !!!cp (149);
1575          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1576          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1577          ## reconsume          ## reconsume
# Line 1195  sub _get_next_token ($) { Line 1580  sub _get_next_token ($) {
1580    
1581          redo A;          redo A;
1582        } else {        } else {
1583          $self->{current_token}->{data} .= '-' . chr ($self->{next_input_character}); # comment          !!!cp (150);
1584            $self->{current_token}->{data} .= '-' . chr ($self->{next_char}); # comment
1585          $self->{state} = COMMENT_STATE;          $self->{state} = COMMENT_STATE;
1586          !!!next-input-character;          !!!next-input-character;
1587          redo A;          redo A;
1588        }        }
1589      } elsif ($self->{state} == COMMENT_END_STATE) {      } elsif ($self->{state} == COMMENT_END_STATE) {
1590        if ($self->{next_input_character} == 0x003E) { # >        if ($self->{next_char} == 0x003E) { # >
1591            !!!cp (151);
1592          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1593          !!!next-input-character;          !!!next-input-character;
1594    
1595          !!!emit ($self->{current_token}); # comment          !!!emit ($self->{current_token}); # comment
1596    
1597          redo A;          redo A;
1598        } elsif ($self->{next_input_character} == 0x002D) { # -        } elsif ($self->{next_char} == 0x002D) { # -
1599            !!!cp (152);
1600          !!!parse-error (type => 'dash in comment');          !!!parse-error (type => 'dash in comment');
1601          $self->{current_token}->{data} .= '-'; # comment          $self->{current_token}->{data} .= '-'; # comment
1602          ## Stay in the state          ## Stay in the state
1603          !!!next-input-character;          !!!next-input-character;
1604          redo A;          redo A;
1605        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1606            !!!cp (153);
1607          !!!parse-error (type => 'unclosed comment');          !!!parse-error (type => 'unclosed comment');
1608          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1609          ## reconsume          ## reconsume
# Line 1223  sub _get_next_token ($) { Line 1612  sub _get_next_token ($) {
1612    
1613          redo A;          redo A;
1614        } else {        } else {
1615            !!!cp (154);
1616          !!!parse-error (type => 'dash in comment');          !!!parse-error (type => 'dash in comment');
1617          $self->{current_token}->{data} .= '--' . chr ($self->{next_input_character}); # comment          $self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment
1618          $self->{state} = COMMENT_STATE;          $self->{state} = COMMENT_STATE;
1619          !!!next-input-character;          !!!next-input-character;
1620          redo A;          redo A;
1621        }        }
1622      } elsif ($self->{state} == DOCTYPE_STATE) {      } elsif ($self->{state} == DOCTYPE_STATE) {
1623        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1624            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1625            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1626            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1627            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1628            !!!cp (155);
1629          $self->{state} = BEFORE_DOCTYPE_NAME_STATE;          $self->{state} = BEFORE_DOCTYPE_NAME_STATE;
1630          !!!next-input-character;          !!!next-input-character;
1631          redo A;          redo A;
1632        } else {        } else {
1633            !!!cp (156);
1634          !!!parse-error (type => 'no space before DOCTYPE name');          !!!parse-error (type => 'no space before DOCTYPE name');
1635          $self->{state} = BEFORE_DOCTYPE_NAME_STATE;          $self->{state} = BEFORE_DOCTYPE_NAME_STATE;
1636          ## reconsume          ## reconsume
1637          redo A;          redo A;
1638        }        }
1639      } elsif ($self->{state} == BEFORE_DOCTYPE_NAME_STATE) {      } elsif ($self->{state} == BEFORE_DOCTYPE_NAME_STATE) {
1640        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1641            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1642            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1643            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1644            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1645            !!!cp (157);
1646          ## Stay in the state          ## Stay in the state
1647          !!!next-input-character;          !!!next-input-character;
1648          redo A;          redo A;
1649        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1650            !!!cp (158);
1651          !!!parse-error (type => 'no DOCTYPE name');          !!!parse-error (type => 'no DOCTYPE name');
1652          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1653          !!!next-input-character;          !!!next-input-character;
1654    
1655          !!!emit ({type => DOCTYPE_TOKEN}); # incorrect          !!!emit ({type => DOCTYPE_TOKEN, quirks => 1});
1656    
1657          redo A;          redo A;
1658        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1659            !!!cp (159);
1660          !!!parse-error (type => 'no DOCTYPE name');          !!!parse-error (type => 'no DOCTYPE name');
1661          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1662          ## reconsume          ## reconsume
1663    
1664          !!!emit ({type => DOCTYPE_TOKEN}); # incorrect          !!!emit ({type => DOCTYPE_TOKEN, quirks => 1});
1665    
1666          redo A;          redo A;
1667        } else {        } else {
1668            !!!cp (160);
1669          $self->{current_token}          $self->{current_token}
1670              = {type => DOCTYPE_TOKEN,              = {type => DOCTYPE_TOKEN,
1671                 name => chr ($self->{next_input_character}),                 name => chr ($self->{next_char}),
1672                 correct => 1};                 #quirks => 0,
1673                  };
1674  ## ISSUE: "Set the token's name name to the" in the spec  ## ISSUE: "Set the token's name name to the" in the spec
1675          $self->{state} = DOCTYPE_NAME_STATE;          $self->{state} = DOCTYPE_NAME_STATE;
1676          !!!next-input-character;          !!!next-input-character;
# Line 1281  sub _get_next_token ($) { Line 1678  sub _get_next_token ($) {
1678        }        }
1679      } elsif ($self->{state} == DOCTYPE_NAME_STATE) {      } elsif ($self->{state} == DOCTYPE_NAME_STATE) {
1680  ## ISSUE: Redundant "First," in the spec.  ## ISSUE: Redundant "First," in the spec.
1681        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1682            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1683            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1684            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1685            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1686            !!!cp (161);
1687          $self->{state} = AFTER_DOCTYPE_NAME_STATE;          $self->{state} = AFTER_DOCTYPE_NAME_STATE;
1688          !!!next-input-character;          !!!next-input-character;
1689          redo A;          redo A;
1690        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1691            !!!cp (162);
1692          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1693          !!!next-input-character;          !!!next-input-character;
1694    
1695          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1696    
1697          redo A;          redo A;
1698        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1699            !!!cp (163);
1700          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
1701          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1702          ## reconsume          ## reconsume
1703    
1704          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1705          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1706    
1707          redo A;          redo A;
1708        } else {        } else {
1709            !!!cp (164);
1710          $self->{current_token}->{name}          $self->{current_token}->{name}
1711            .= chr ($self->{next_input_character}); # DOCTYPE            .= chr ($self->{next_char}); # DOCTYPE
1712          ## Stay in the state          ## Stay in the state
1713          !!!next-input-character;          !!!next-input-character;
1714          redo A;          redo A;
1715        }        }
1716      } elsif ($self->{state} == AFTER_DOCTYPE_NAME_STATE) {      } elsif ($self->{state} == AFTER_DOCTYPE_NAME_STATE) {
1717        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
1718            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
1719            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
1720            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
1721            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
1722            !!!cp (165);
1723          ## Stay in the state          ## Stay in the state
1724          !!!next-input-character;          !!!next-input-character;
1725          redo A;          redo A;
1726        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1727            !!!cp (166);
1728          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1729          !!!next-input-character;          !!!next-input-character;
1730    
1731          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1732    
1733          redo A;          redo A;
1734        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1735            !!!cp (167);
1736          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
1737          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1738          ## reconsume          ## reconsume
1739    
1740          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1741          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1742    
1743          redo A;          redo A;
1744        } elsif ($self->{next_input_character} == 0x0050 or # P        } elsif ($self->{next_char} == 0x0050 or # P
1745                 $self->{next_input_character} == 0x0070) { # p                 $self->{next_char} == 0x0070) { # p
1746          !!!next-input-character;          !!!next-input-character;
1747          if ($self->{next_input_character} == 0x0055 or # U          if ($self->{next_char} == 0x0055 or # U
1748              $self->{next_input_character} == 0x0075) { # u              $self->{next_char} == 0x0075) { # u
1749            !!!next-input-character;            !!!next-input-character;
1750            if ($self->{next_input_character} == 0x0042 or # B            if ($self->{next_char} == 0x0042 or # B
1751                $self->{next_input_character} == 0x0062) { # b                $self->{next_char} == 0x0062) { # b
1752              !!!next-input-character;              !!!next-input-character;
1753              if ($self->{next_input_character} == 0x004C or # L              if ($self->{next_char} == 0x004C or # L
1754                  $self->{next_input_character} == 0x006C) { # l                  $self->{next_char} == 0x006C) { # l
1755                !!!next-input-character;                !!!next-input-character;
1756                if ($self->{next_input_character} == 0x0049 or # I                if ($self->{next_char} == 0x0049 or # I
1757                    $self->{next_input_character} == 0x0069) { # i                    $self->{next_char} == 0x0069) { # i
1758                  !!!next-input-character;                  !!!next-input-character;
1759                  if ($self->{next_input_character} == 0x0043 or # C                  if ($self->{next_char} == 0x0043 or # C
1760                      $self->{next_input_character} == 0x0063) { # c                      $self->{next_char} == 0x0063) { # c
1761                      !!!cp (168);
1762                    $self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE;                    $self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE;
1763                    !!!next-input-character;                    !!!next-input-character;
1764                    redo A;                    redo A;
1765                    } else {
1766                      !!!cp (169);
1767                  }                  }
1768                  } else {
1769                    !!!cp (170);
1770                }                }
1771                } else {
1772                  !!!cp (171);
1773              }              }
1774              } else {
1775                !!!cp (172);
1776            }            }
1777            } else {
1778              !!!cp (173);
1779          }          }
1780    
1781          #          #
1782        } elsif ($self->{next_input_character} == 0x0053 or # S        } elsif ($self->{next_char} == 0x0053 or # S
1783                 $self->{next_input_character} == 0x0073) { # s                 $self->{next_char} == 0x0073) { # s
1784          !!!next-input-character;          !!!next-input-character;
1785          if ($self->{next_input_character} == 0x0059 or # Y          if ($self->{next_char} == 0x0059 or # Y
1786              $self->{next_input_character} == 0x0079) { # y              $self->{next_char} == 0x0079) { # y
1787            !!!next-input-character;            !!!next-input-character;
1788            if ($self->{next_input_character} == 0x0053 or # S            if ($self->{next_char} == 0x0053 or # S
1789                $self->{next_input_character} == 0x0073) { # s                $self->{next_char} == 0x0073) { # s
1790              !!!next-input-character;              !!!next-input-character;
1791              if ($self->{next_input_character} == 0x0054 or # T              if ($self->{next_char} == 0x0054 or # T
1792                  $self->{next_input_character} == 0x0074) { # t                  $self->{next_char} == 0x0074) { # t
1793                !!!next-input-character;                !!!next-input-character;
1794                if ($self->{next_input_character} == 0x0045 or # E                if ($self->{next_char} == 0x0045 or # E
1795                    $self->{next_input_character} == 0x0065) { # e                    $self->{next_char} == 0x0065) { # e
1796                  !!!next-input-character;                  !!!next-input-character;
1797                  if ($self->{next_input_character} == 0x004D or # M                  if ($self->{next_char} == 0x004D or # M
1798                      $self->{next_input_character} == 0x006D) { # m                      $self->{next_char} == 0x006D) { # m
1799                      !!!cp (174);
1800                    $self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE;                    $self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
1801                    !!!next-input-character;                    !!!next-input-character;
1802                    redo A;                    redo A;
1803                    } else {
1804                      !!!cp (175);
1805                  }                  }
1806                  } else {
1807                    !!!cp (176);
1808                }                }
1809                } else {
1810                  !!!cp (177);
1811              }              }
1812              } else {
1813                !!!cp (178);
1814            }            }
1815            } else {
1816              !!!cp (179);
1817          }          }
1818    
1819          #          #
1820        } else {        } else {
1821            !!!cp (180);
1822          !!!next-input-character;          !!!next-input-character;
1823          #          #
1824        }        }
1825    
1826        !!!parse-error (type => 'string after DOCTYPE name');        !!!parse-error (type => 'string after DOCTYPE name');
1827          $self->{current_token}->{quirks} = 1;
1828    
1829        $self->{state} = BOGUS_DOCTYPE_STATE;        $self->{state} = BOGUS_DOCTYPE_STATE;
1830        # next-input-character is already done        # next-input-character is already done
1831        redo A;        redo A;
# Line 1404  sub _get_next_token ($) { Line 1833  sub _get_next_token ($) {
1833        if ({        if ({
1834              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
1835              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
1836            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
1837            !!!cp (181);
1838          ## Stay in the state          ## Stay in the state
1839          !!!next-input-character;          !!!next-input-character;
1840          redo A;          redo A;
1841        } elsif ($self->{next_input_character} eq 0x0022) { # "        } elsif ($self->{next_char} eq 0x0022) { # "
1842            !!!cp (182);
1843          $self->{current_token}->{public_identifier} = ''; # DOCTYPE          $self->{current_token}->{public_identifier} = ''; # DOCTYPE
1844          $self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE;          $self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE;
1845          !!!next-input-character;          !!!next-input-character;
1846          redo A;          redo A;
1847        } elsif ($self->{next_input_character} eq 0x0027) { # '        } elsif ($self->{next_char} eq 0x0027) { # '
1848            !!!cp (183);
1849          $self->{current_token}->{public_identifier} = ''; # DOCTYPE          $self->{current_token}->{public_identifier} = ''; # DOCTYPE
1850          $self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE;          $self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE;
1851          !!!next-input-character;          !!!next-input-character;
1852          redo A;          redo A;
1853        } elsif ($self->{next_input_character} eq 0x003E) { # >        } elsif ($self->{next_char} eq 0x003E) { # >
1854            !!!cp (184);
1855          !!!parse-error (type => 'no PUBLIC literal');          !!!parse-error (type => 'no PUBLIC literal');
1856    
1857          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1858          !!!next-input-character;          !!!next-input-character;
1859    
1860          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1861          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1862    
1863          redo A;          redo A;
1864        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1865            !!!cp (185);
1866          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
1867    
1868          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1869          ## reconsume          ## reconsume
1870    
1871          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1872          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1873    
1874          redo A;          redo A;
1875        } else {        } else {
1876            !!!cp (186);
1877          !!!parse-error (type => 'string after PUBLIC');          !!!parse-error (type => 'string after PUBLIC');
1878            $self->{current_token}->{quirks} = 1;
1879    
1880          $self->{state} = BOGUS_DOCTYPE_STATE;          $self->{state} = BOGUS_DOCTYPE_STATE;
1881          !!!next-input-character;          !!!next-input-character;
1882          redo A;          redo A;
1883        }        }
1884      } elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE) {      } elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE) {
1885        if ($self->{next_input_character} == 0x0022) { # "        if ($self->{next_char} == 0x0022) { # "
1886            !!!cp (187);
1887          $self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE;          $self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE;
1888          !!!next-input-character;          !!!next-input-character;
1889          redo A;          redo A;
1890        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == 0x003E) { # >
1891            !!!cp (188);
1892            !!!parse-error (type => 'unclosed PUBLIC literal');
1893    
1894            $self->{state} = DATA_STATE;
1895            !!!next-input-character;
1896    
1897            $self->{current_token}->{quirks} = 1;
1898            !!!emit ($self->{current_token}); # DOCTYPE
1899    
1900            redo A;
1901          } elsif ($self->{next_char} == -1) {
1902            !!!cp (189);
1903          !!!parse-error (type => 'unclosed PUBLIC literal');          !!!parse-error (type => 'unclosed PUBLIC literal');
1904    
1905          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1906          ## reconsume          ## reconsume
1907    
1908          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1909          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1910    
1911          redo A;          redo A;
1912        } else {        } else {
1913            !!!cp (190);
1914          $self->{current_token}->{public_identifier} # DOCTYPE          $self->{current_token}->{public_identifier} # DOCTYPE
1915              .= chr $self->{next_input_character};              .= chr $self->{next_char};
1916          ## Stay in the state          ## Stay in the state
1917          !!!next-input-character;          !!!next-input-character;
1918          redo A;          redo A;
1919        }        }
1920      } elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE) {      } elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE) {
1921        if ($self->{next_input_character} == 0x0027) { # '        if ($self->{next_char} == 0x0027) { # '
1922            !!!cp (191);
1923          $self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE;          $self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE;
1924          !!!next-input-character;          !!!next-input-character;
1925          redo A;          redo A;
1926        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == 0x003E) { # >
1927            !!!cp (192);
1928            !!!parse-error (type => 'unclosed PUBLIC literal');
1929    
1930            $self->{state} = DATA_STATE;
1931            !!!next-input-character;
1932    
1933            $self->{current_token}->{quirks} = 1;
1934            !!!emit ($self->{current_token}); # DOCTYPE
1935    
1936            redo A;
1937          } elsif ($self->{next_char} == -1) {
1938            !!!cp (193);
1939          !!!parse-error (type => 'unclosed PUBLIC literal');          !!!parse-error (type => 'unclosed PUBLIC literal');
1940    
1941          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1942          ## reconsume          ## reconsume
1943    
1944          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1945          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1946    
1947          redo A;          redo A;
1948        } else {        } else {
1949            !!!cp (194);
1950          $self->{current_token}->{public_identifier} # DOCTYPE          $self->{current_token}->{public_identifier} # DOCTYPE
1951              .= chr $self->{next_input_character};              .= chr $self->{next_char};
1952          ## Stay in the state          ## Stay in the state
1953          !!!next-input-character;          !!!next-input-character;
1954          redo A;          redo A;
# Line 1492  sub _get_next_token ($) { Line 1957  sub _get_next_token ($) {
1957        if ({        if ({
1958              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
1959              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
1960            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
1961            !!!cp (195);
1962          ## Stay in the state          ## Stay in the state
1963          !!!next-input-character;          !!!next-input-character;
1964          redo A;          redo A;
1965        } elsif ($self->{next_input_character} == 0x0022) { # "        } elsif ($self->{next_char} == 0x0022) { # "
1966            !!!cp (196);
1967          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
1968          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;
1969          !!!next-input-character;          !!!next-input-character;
1970          redo A;          redo A;
1971        } elsif ($self->{next_input_character} == 0x0027) { # '        } elsif ($self->{next_char} == 0x0027) { # '
1972            !!!cp (197);
1973          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
1974          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;
1975          !!!next-input-character;          !!!next-input-character;
1976          redo A;          redo A;
1977        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
1978            !!!cp (198);
1979          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1980          !!!next-input-character;          !!!next-input-character;
1981    
1982          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1983    
1984          redo A;          redo A;
1985        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
1986            !!!cp (199);
1987          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
1988    
1989          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
1990          ## reconsume          ## reconsume
1991    
1992          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
1993          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
1994    
1995          redo A;          redo A;
1996        } else {        } else {
1997            !!!cp (200);
1998          !!!parse-error (type => 'string after PUBLIC literal');          !!!parse-error (type => 'string after PUBLIC literal');
1999            $self->{current_token}->{quirks} = 1;
2000    
2001          $self->{state} = BOGUS_DOCTYPE_STATE;          $self->{state} = BOGUS_DOCTYPE_STATE;
2002          !!!next-input-character;          !!!next-input-character;
2003          redo A;          redo A;
# Line 1533  sub _get_next_token ($) { Line 2006  sub _get_next_token ($) {
2006        if ({        if ({
2007              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
2008              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
2009            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
2010            !!!cp (201);
2011          ## Stay in the state          ## Stay in the state
2012          !!!next-input-character;          !!!next-input-character;
2013          redo A;          redo A;
2014        } elsif ($self->{next_input_character} == 0x0022) { # "        } elsif ($self->{next_char} == 0x0022) { # "
2015            !!!cp (202);
2016          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
2017          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;
2018          !!!next-input-character;          !!!next-input-character;
2019          redo A;          redo A;
2020        } elsif ($self->{next_input_character} == 0x0027) { # '        } elsif ($self->{next_char} == 0x0027) { # '
2021            !!!cp (203);
2022          $self->{current_token}->{system_identifier} = ''; # DOCTYPE          $self->{current_token}->{system_identifier} = ''; # DOCTYPE
2023          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;          $self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;
2024          !!!next-input-character;          !!!next-input-character;
2025          redo A;          redo A;
2026        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
2027            !!!cp (204);
2028          !!!parse-error (type => 'no SYSTEM literal');          !!!parse-error (type => 'no SYSTEM literal');
2029          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2030          !!!next-input-character;          !!!next-input-character;
2031    
2032          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2033          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2034    
2035          redo A;          redo A;
2036        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2037            !!!cp (205);
2038          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2039    
2040          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2041          ## reconsume          ## reconsume
2042    
2043          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2044          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2045    
2046          redo A;          redo A;
2047        } else {        } else {
2048            !!!cp (206);
2049          !!!parse-error (type => 'string after SYSTEM');          !!!parse-error (type => 'string after SYSTEM');
2050            $self->{current_token}->{quirks} = 1;
2051    
2052          $self->{state} = BOGUS_DOCTYPE_STATE;          $self->{state} = BOGUS_DOCTYPE_STATE;
2053          !!!next-input-character;          !!!next-input-character;
2054          redo A;          redo A;
2055        }        }
2056      } elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE) {      } elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE) {
2057        if ($self->{next_input_character} == 0x0022) { # "        if ($self->{next_char} == 0x0022) { # "
2058            !!!cp (207);
2059          $self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;          $self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
2060          !!!next-input-character;          !!!next-input-character;
2061          redo A;          redo A;
2062        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == 0x003E) { # >
2063            !!!cp (208);
2064            !!!parse-error (type => 'unclosed PUBLIC literal');
2065    
2066            $self->{state} = DATA_STATE;
2067            !!!next-input-character;
2068    
2069            $self->{current_token}->{quirks} = 1;
2070            !!!emit ($self->{current_token}); # DOCTYPE
2071    
2072            redo A;
2073          } elsif ($self->{next_char} == -1) {
2074            !!!cp (209);
2075          !!!parse-error (type => 'unclosed SYSTEM literal');          !!!parse-error (type => 'unclosed SYSTEM literal');
2076    
2077          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2078          ## reconsume          ## reconsume
2079    
2080          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2081          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2082    
2083          redo A;          redo A;
2084        } else {        } else {
2085            !!!cp (210);
2086          $self->{current_token}->{system_identifier} # DOCTYPE          $self->{current_token}->{system_identifier} # DOCTYPE
2087              .= chr $self->{next_input_character};              .= chr $self->{next_char};
2088          ## Stay in the state          ## Stay in the state
2089          !!!next-input-character;          !!!next-input-character;
2090          redo A;          redo A;
2091        }        }
2092      } elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE) {      } elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE) {
2093        if ($self->{next_input_character} == 0x0027) { # '        if ($self->{next_char} == 0x0027) { # '
2094            !!!cp (211);
2095          $self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;          $self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
2096          !!!next-input-character;          !!!next-input-character;
2097          redo A;          redo A;
2098        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == 0x003E) { # >
2099            !!!cp (212);
2100            !!!parse-error (type => 'unclosed PUBLIC literal');
2101    
2102            $self->{state} = DATA_STATE;
2103            !!!next-input-character;
2104    
2105            $self->{current_token}->{quirks} = 1;
2106            !!!emit ($self->{current_token}); # DOCTYPE
2107    
2108            redo A;
2109          } elsif ($self->{next_char} == -1) {
2110            !!!cp (213);
2111          !!!parse-error (type => 'unclosed SYSTEM literal');          !!!parse-error (type => 'unclosed SYSTEM literal');
2112    
2113          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2114          ## reconsume          ## reconsume
2115    
2116          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2117          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2118    
2119          redo A;          redo A;
2120        } else {        } else {
2121            !!!cp (214);
2122          $self->{current_token}->{system_identifier} # DOCTYPE          $self->{current_token}->{system_identifier} # DOCTYPE
2123              .= chr $self->{next_input_character};              .= chr $self->{next_char};
2124          ## Stay in the state          ## Stay in the state
2125          !!!next-input-character;          !!!next-input-character;
2126          redo A;          redo A;
# Line 1620  sub _get_next_token ($) { Line 2129  sub _get_next_token ($) {
2129        if ({        if ({
2130              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,              0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1,
2131              #0x000D => 1, # HT, LF, VT, FF, SP, CR              #0x000D => 1, # HT, LF, VT, FF, SP, CR
2132            }->{$self->{next_input_character}}) {            }->{$self->{next_char}}) {
2133            !!!cp (215);
2134          ## Stay in the state          ## Stay in the state
2135          !!!next-input-character;          !!!next-input-character;
2136          redo A;          redo A;
2137        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
2138            !!!cp (216);
2139          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2140          !!!next-input-character;          !!!next-input-character;
2141    
2142          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2143    
2144          redo A;          redo A;
2145        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2146            !!!cp (217);
2147          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2148    
2149          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2150          ## reconsume          ## reconsume
2151    
2152          delete $self->{current_token}->{correct};          $self->{current_token}->{quirks} = 1;
2153          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2154    
2155          redo A;          redo A;
2156        } else {        } else {
2157            !!!cp (218);
2158          !!!parse-error (type => 'string after SYSTEM literal');          !!!parse-error (type => 'string after SYSTEM literal');
2159            #$self->{current_token}->{quirks} = 1;
2160    
2161          $self->{state} = BOGUS_DOCTYPE_STATE;          $self->{state} = BOGUS_DOCTYPE_STATE;
2162          !!!next-input-character;          !!!next-input-character;
2163          redo A;          redo A;
2164        }        }
2165      } elsif ($self->{state} == BOGUS_DOCTYPE_STATE) {      } elsif ($self->{state} == BOGUS_DOCTYPE_STATE) {
2166        if ($self->{next_input_character} == 0x003E) { # >        if ($self->{next_char} == 0x003E) { # >
2167            !!!cp (219);
2168          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2169          !!!next-input-character;          !!!next-input-character;
2170    
         delete $self->{current_token}->{correct};  
2171          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2172    
2173          redo A;          redo A;
2174        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
2175            !!!cp (220);
2176          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
2177          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
2178          ## reconsume          ## reconsume
2179    
         delete $self->{current_token}->{correct};  
2180          !!!emit ($self->{current_token}); # DOCTYPE          !!!emit ($self->{current_token}); # DOCTYPE
2181    
2182          redo A;          redo A;
2183        } else {        } else {
2184            !!!cp (221);
2185          ## Stay in the state          ## Stay in the state
2186          !!!next-input-character;          !!!next-input-character;
2187          redo A;          redo A;
# Line 1678  sub _get_next_token ($) { Line 2194  sub _get_next_token ($) {
2194    die "$0: _get_next_token: unexpected case";    die "$0: _get_next_token: unexpected case";
2195  } # _get_next_token  } # _get_next_token
2196    
2197  sub _tokenize_attempt_to_consume_an_entity ($$) {  sub _tokenize_attempt_to_consume_an_entity ($$$) {
2198    my ($self, $in_attr) = @_;    my ($self, $in_attr, $additional) = @_;
2199    
2200    if ({    if ({
2201         0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF,         0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF,
2202         0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR         0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR
2203        }->{$self->{next_input_character}}) {         $additional => 1,
2204          }->{$self->{next_char}}) {
2205        !!!cp (1001);
2206      ## Don't consume      ## Don't consume
2207      ## No error      ## No error
2208      return undef;      return undef;
2209    } elsif ($self->{next_input_character} == 0x0023) { # #    } elsif ($self->{next_char} == 0x0023) { # #
2210      !!!next-input-character;      !!!next-input-character;
2211      if ($self->{next_input_character} == 0x0078 or # x      if ($self->{next_char} == 0x0078 or # x
2212          $self->{next_input_character} == 0x0058) { # X          $self->{next_char} == 0x0058) { # X
2213        my $code;        my $code;
2214        X: {        X: {
2215          my $x_char = $self->{next_input_character};          my $x_char = $self->{next_char};
2216          !!!next-input-character;          !!!next-input-character;
2217          if (0x0030 <= $self->{next_input_character} and          if (0x0030 <= $self->{next_char} and
2218              $self->{next_input_character} <= 0x0039) { # 0..9              $self->{next_char} <= 0x0039) { # 0..9
2219              !!!cp (1002);
2220            $code ||= 0;            $code ||= 0;
2221            $code *= 0x10;            $code *= 0x10;
2222            $code += $self->{next_input_character} - 0x0030;            $code += $self->{next_char} - 0x0030;
2223            redo X;            redo X;
2224          } elsif (0x0061 <= $self->{next_input_character} and          } elsif (0x0061 <= $self->{next_char} and
2225                   $self->{next_input_character} <= 0x0066) { # a..f                   $self->{next_char} <= 0x0066) { # a..f
2226              !!!cp (1003);
2227            $code ||= 0;            $code ||= 0;
2228            $code *= 0x10;            $code *= 0x10;
2229            $code += $self->{next_input_character} - 0x0060 + 9;            $code += $self->{next_char} - 0x0060 + 9;
2230            redo X;            redo X;
2231          } elsif (0x0041 <= $self->{next_input_character} and          } elsif (0x0041 <= $self->{next_char} and
2232                   $self->{next_input_character} <= 0x0046) { # A..F                   $self->{next_char} <= 0x0046) { # A..F
2233              !!!cp (1004);
2234            $code ||= 0;            $code ||= 0;
2235            $code *= 0x10;            $code *= 0x10;
2236            $code += $self->{next_input_character} - 0x0040 + 9;            $code += $self->{next_char} - 0x0040 + 9;
2237            redo X;            redo X;
2238          } elsif (not defined $code) { # no hexadecimal digit          } elsif (not defined $code) { # no hexadecimal digit
2239              !!!cp (1005);
2240            !!!parse-error (type => 'bare hcro');            !!!parse-error (type => 'bare hcro');
2241            !!!back-next-input-character ($x_char, $self->{next_input_character});            !!!back-next-input-character ($x_char, $self->{next_char});
2242            $self->{next_input_character} = 0x0023; # #            $self->{next_char} = 0x0023; # #
2243            return undef;            return undef;
2244          } elsif ($self->{next_input_character} == 0x003B) { # ;          } elsif ($self->{next_char} == 0x003B) { # ;
2245              !!!cp (1006);
2246            !!!next-input-character;            !!!next-input-character;
2247          } else {          } else {
2248              !!!cp (1007);
2249            !!!parse-error (type => 'no refc');            !!!parse-error (type => 'no refc');
2250          }          }
2251    
2252          if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {          if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {
2253              !!!cp (1008);
2254            !!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code);            !!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code);
2255            $code = 0xFFFD;            $code = 0xFFFD;
2256          } elsif ($code > 0x10FFFF) {          } elsif ($code > 0x10FFFF) {
2257              !!!cp (1009);
2258            !!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code);            !!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code);
2259            $code = 0xFFFD;            $code = 0xFFFD;
2260          } elsif ($code == 0x000D) {          } elsif ($code == 0x000D) {
2261              !!!cp (1010);
2262            !!!parse-error (type => 'CR character reference');            !!!parse-error (type => 'CR character reference');
2263            $code = 0x000A;            $code = 0x000A;
2264          } elsif (0x80 <= $code and $code <= 0x9F) {          } elsif (0x80 <= $code and $code <= 0x9F) {
2265              !!!cp (1011);
2266            !!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code);            !!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code);
2267            $code = $c1_entity_char->{$code};            $code = $c1_entity_char->{$code};
2268          }          }
2269    
2270          return {type => CHARACTER_TOKEN, data => chr $code};          return {type => CHARACTER_TOKEN, data => chr $code,
2271                    has_reference => 1};
2272        } # X        } # X
2273      } elsif (0x0030 <= $self->{next_input_character} and      } elsif (0x0030 <= $self->{next_char} and
2274               $self->{next_input_character} <= 0x0039) { # 0..9               $self->{next_char} <= 0x0039) { # 0..9
2275        my $code = $self->{next_input_character} - 0x0030;        my $code = $self->{next_char} - 0x0030;
2276        !!!next-input-character;        !!!next-input-character;
2277                
2278        while (0x0030 <= $self->{next_input_character} and        while (0x0030 <= $self->{next_char} and
2279                  $self->{next_input_character} <= 0x0039) { # 0..9                  $self->{next_char} <= 0x0039) { # 0..9
2280            !!!cp (1012);
2281          $code *= 10;          $code *= 10;
2282          $code += $self->{next_input_character} - 0x0030;          $code += $self->{next_char} - 0x0030;
2283                    
2284          !!!next-input-character;          !!!next-input-character;
2285        }        }
2286    
2287        if ($self->{next_input_character} == 0x003B) { # ;        if ($self->{next_char} == 0x003B) { # ;
2288            !!!cp (1013);
2289          !!!next-input-character;          !!!next-input-character;
2290        } else {        } else {
2291            !!!cp (1014);
2292          !!!parse-error (type => 'no refc');          !!!parse-error (type => 'no refc');
2293        }        }
2294    
2295        if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {        if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) {
2296            !!!cp (1015);
2297          !!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code);          !!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code);
2298          $code = 0xFFFD;          $code = 0xFFFD;
2299        } elsif ($code > 0x10FFFF) {        } elsif ($code > 0x10FFFF) {
2300            !!!cp (1016);
2301          !!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code);          !!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code);
2302          $code = 0xFFFD;          $code = 0xFFFD;
2303        } elsif ($code == 0x000D) {        } elsif ($code == 0x000D) {
2304            !!!cp (1017);
2305          !!!parse-error (type => 'CR character reference');          !!!parse-error (type => 'CR character reference');
2306          $code = 0x000A;          $code = 0x000A;
2307        } elsif (0x80 <= $code and $code <= 0x9F) {        } elsif (0x80 <= $code and $code <= 0x9F) {
2308            !!!cp (1018);
2309          !!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code);          !!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code);
2310          $code = $c1_entity_char->{$code};          $code = $c1_entity_char->{$code};
2311        }        }
2312                
2313        return {type => CHARACTER_TOKEN, data => chr $code};        return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1};
2314      } else {      } else {
2315          !!!cp (1019);
2316        !!!parse-error (type => 'bare nero');        !!!parse-error (type => 'bare nero');
2317        !!!back-next-input-character ($self->{next_input_character});        !!!back-next-input-character ($self->{next_char});
2318        $self->{next_input_character} = 0x0023; # #        $self->{next_char} = 0x0023; # #
2319        return undef;        return undef;
2320      }      }
2321    } elsif ((0x0041 <= $self->{next_input_character} and    } elsif ((0x0041 <= $self->{next_char} and
2322              $self->{next_input_character} <= 0x005A) or              $self->{next_char} <= 0x005A) or
2323             (0x0061 <= $self->{next_input_character} and             (0x0061 <= $self->{next_char} and
2324              $self->{next_input_character} <= 0x007A)) {              $self->{next_char} <= 0x007A)) {
2325      my $entity_name = chr $self->{next_input_character};      my $entity_name = chr $self->{next_char};
2326      !!!next-input-character;      !!!next-input-character;
2327    
2328      my $value = $entity_name;      my $value = $entity_name;
# Line 1795  sub _tokenize_attempt_to_consume_an_enti Line 2332  sub _tokenize_attempt_to_consume_an_enti
2332    
2333      while (length $entity_name < 10 and      while (length $entity_name < 10 and
2334             ## NOTE: Some number greater than the maximum length of entity name             ## NOTE: Some number greater than the maximum length of entity name
2335             ((0x0041 <= $self->{next_input_character} and # a             ((0x0041 <= $self->{next_char} and # a
2336               $self->{next_input_character} <= 0x005A) or # x               $self->{next_char} <= 0x005A) or # x
2337              (0x0061 <= $self->{next_input_character} and # a              (0x0061 <= $self->{next_char} and # a
2338               $self->{next_input_character} <= 0x007A) or # z               $self->{next_char} <= 0x007A) or # z
2339              (0x0030 <= $self->{next_input_character} and # 0              (0x0030 <= $self->{next_char} and # 0
2340               $self->{next_input_character} <= 0x0039) or # 9               $self->{next_char} <= 0x0039) or # 9
2341              $self->{next_input_character} == 0x003B)) { # ;              $self->{next_char} == 0x003B)) { # ;
2342        $entity_name .= chr $self->{next_input_character};        $entity_name .= chr $self->{next_char};
2343        if (defined $EntityChar->{$entity_name}) {        if (defined $EntityChar->{$entity_name}) {
2344          if ($self->{next_input_character} == 0x003B) { # ;          if ($self->{next_char} == 0x003B) { # ;
2345              !!!cp (1020);
2346            $value = $EntityChar->{$entity_name};            $value = $EntityChar->{$entity_name};
2347            $match = 1;            $match = 1;
2348            !!!next-input-character;            !!!next-input-character;
2349            last;            last;
2350          } else {          } else {
2351              !!!cp (1021);
2352            $value = $EntityChar->{$entity_name};            $value = $EntityChar->{$entity_name};
2353            $match = -1;            $match = -1;
2354            !!!next-input-character;            !!!next-input-character;
2355          }          }
2356        } else {        } else {
2357          $value .= chr $self->{next_input_character};          !!!cp (1022);
2358            $value .= chr $self->{next_char};
2359          $match *= 2;          $match *= 2;
2360          !!!next-input-character;          !!!next-input-character;
2361        }        }
2362      }      }
2363            
2364      if ($match > 0) {      if ($match > 0) {
2365        return {type => CHARACTER_TOKEN, data => $value};        !!!cp (1023);
2366          return {type => CHARACTER_TOKEN, data => $value, has_reference => 1};
2367      } elsif ($match < 0) {      } elsif ($match < 0) {
2368        !!!parse-error (type => 'no refc');        !!!parse-error (type => 'no refc');
2369        if ($in_attr and $match < -1) {        if ($in_attr and $match < -1) {
2370            !!!cp (1024);
2371          return {type => CHARACTER_TOKEN, data => '&'.$entity_name};          return {type => CHARACTER_TOKEN, data => '&'.$entity_name};
2372        } else {        } else {
2373          return {type => CHARACTER_TOKEN, data => $value};          !!!cp (1025);
2374            return {type => CHARACTER_TOKEN, data => $value, has_reference => 1};
2375        }        }
2376      } else {      } else {
2377          !!!cp (1026);
2378        !!!parse-error (type => 'bare ero');        !!!parse-error (type => 'bare ero');
2379        ## NOTE: No characters are consumed in the spec.        ## NOTE: "No characters are consumed" in the spec.
2380        return {type => CHARACTER_TOKEN, data => '&'.$value};        return {type => CHARACTER_TOKEN, data => '&'.$value};
2381      }      }
2382    } else {    } else {
2383        !!!cp (1027);
2384      ## no characters are consumed      ## no characters are consumed
2385      !!!parse-error (type => 'bare ero');      !!!parse-error (type => 'bare ero');
2386      return undef;      return undef;
# Line 1915  sub _tree_construction_initial ($) { Line 2460  sub _tree_construction_initial ($) {
2460        ## ISSUE: internalSubset = null??        ## ISSUE: internalSubset = null??
2461        $self->{document}->append_child ($doctype);        $self->{document}->append_child ($doctype);
2462                
2463        if (not $token->{correct} or $doctype_name ne 'HTML') {        if ($token->{quirks} or $doctype_name ne 'HTML') {
2464          $self->{document}->manakai_compat_mode ('quirks');          $self->{document}->manakai_compat_mode ('quirks');
2465        } elsif (defined $token->{public_identifier}) {        } elsif (defined $token->{public_identifier}) {
2466          my $pubid = $token->{public_identifier};          my $pubid = $token->{public_identifier};
# Line 1969  sub _tree_construction_initial ($) { Line 2514  sub _tree_construction_initial ($) {
2514            "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1,            "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1,
2515            "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1,            "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1,
2516            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1,            "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1,
2517              "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1,
2518              "-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1,
2519              "-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1,
2520            "-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1,            "-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1,
2521            "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1,            "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1,
2522            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1,            "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1,
# Line 2080  sub _tree_construction_root_element ($) Line 2628  sub _tree_construction_root_element ($)
2628              redo B;              redo B;
2629            }            }
2630          }          }
2631    
2632            $self->{application_cache_selection}->(undef);
2633    
2634            #
2635          } elsif ($token->{type} == START_TAG_TOKEN) {
2636            if ($token->{tag_name} eq 'html' and
2637                $token->{attributes}->{manifest}) {
2638              $self->{application_cache_selection}
2639                   ->($token->{attributes}->{manifest}->{value});
2640              ## ISSUE: No relative reference resolution?
2641            } else {
2642              $self->{application_cache_selection}->(undef);
2643            }
2644    
2645            ## ISSUE: There is an issue in the spec
2646          #          #
2647        } elsif ({        } elsif ({
                 START_TAG_TOKEN, 1,  
2648                  END_TAG_TOKEN, 1,                  END_TAG_TOKEN, 1,
2649                  END_OF_FILE_TOKEN, 1,                  END_OF_FILE_TOKEN, 1,
2650                 }->{$token->{type}}) {                 }->{$token->{type}}) {
2651            $self->{application_cache_selection}->(undef);
2652    
2653          ## ISSUE: There is an issue in the spec          ## ISSUE: There is an issue in the spec
2654          #          #
2655        } else {        } else {
2656          die "$0: $token->{type}: Unknown token type";          die "$0: $token->{type}: Unknown token type";
2657        }        }
2658    
2659        my $root_element; !!!create-element ($root_element, 'html');        my $root_element; !!!create-element ($root_element, 'html');
2660        $self->{document}->append_child ($root_element);        $self->{document}->append_child ($root_element);
2661        push @{$self->{open_elements}}, [$root_element, 'html'];        push @{$self->{open_elements}}, [$root_element, 'html'];
# Line 2747  sub _tree_construction_main ($) { Line 3312  sub _tree_construction_main ($) {
3312                  push @{$self->{open_elements}}, [$self->{head_element}, 'head'];                  push @{$self->{open_elements}}, [$self->{head_element}, 'head'];
3313                }                }
3314                !!!insert-element ($token->{tag_name}, $token->{attributes});                !!!insert-element ($token->{tag_name}, $token->{attributes});
3315                pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec.                my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec.
3316    
3317                unless ($self->{confident}) {                unless ($self->{confident}) {
                 my $charset;  
3318                  if ($token->{attributes}->{charset}) { ## TODO: And if supported                  if ($token->{attributes}->{charset}) { ## TODO: And if supported
3319                    $charset = $token->{attributes}->{charset}->{value};                    $self->{change_encoding}
3320                  }                        ->($self, $token->{attributes}->{charset}->{value});
3321                  if ($token->{attributes}->{'http-equiv'}) {                    
3322                      $meta_el->[0]->get_attribute_node_ns (undef, 'charset')
3323                          ->set_user_data (manakai_has_reference =>
3324                                               $token->{attributes}->{charset}
3325                                                   ->{has_reference});
3326                    } elsif ($token->{attributes}->{content}) {
3327                    ## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition.                    ## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition.
3328                    if ($token->{attributes}->{'http-equiv'}->{value}                    if ($token->{attributes}->{content}->{value}
3329                        =~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*=                        =~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt]
3330                              [\x09-\x0D\x20]*=
3331                            [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|                            [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|
3332                            ([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) {                            ([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) {
3333                      $charset = defined $1 ? $1 : defined $2 ? $2 : $3;                      $self->{change_encoding}
3334                    } ## TODO: And if supported                          ->($self, defined $1 ? $1 : defined $2 ? $2 : $3);
3335                        $meta_el->[0]->get_attribute_node_ns (undef, 'content')
3336                            ->set_user_data (manakai_has_reference =>
3337                                                 $token->{attributes}->{content}
3338                                                       ->{has_reference});
3339                      }
3340                    }
3341                  } else {
3342                    if ($token->{attributes}->{charset}) {
3343                      $meta_el->[0]->get_attribute_node_ns (undef, 'charset')
3344                          ->set_user_data (manakai_has_reference =>
3345                                               $token->{attributes}->{charset}
3346                                                   ->{has_reference});
3347                    }
3348                    if ($token->{attributes}->{content}) {
3349                      $meta_el->[0]->get_attribute_node_ns (undef, 'content')
3350                          ->set_user_data (manakai_has_reference =>
3351                                               $token->{attributes}->{content}
3352                                                   ->{has_reference});
3353                  }                  }
                 ## TODO: Change the encoding  
3354                }                }
3355    
               ## TODO: Extracting |charset| from |meta|.  
3356                pop @{$self->{open_elements}}                pop @{$self->{open_elements}}
3357                    if $self->{insertion_mode} == AFTER_HEAD_IM;                    if $self->{insertion_mode} == AFTER_HEAD_IM;
3358                !!!next-token;                !!!next-token;
# Line 4337  sub _tree_construction_main ($) { Line 4923  sub _tree_construction_main ($) {
4923        } elsif ($token->{tag_name} eq 'meta') {        } elsif ($token->{tag_name} eq 'meta') {
4924          ## NOTE: This is an "as if in head" code clone, only "-t" differs          ## NOTE: This is an "as if in head" code clone, only "-t" differs
4925          !!!insert-element-t ($token->{tag_name}, $token->{attributes});          !!!insert-element-t ($token->{tag_name}, $token->{attributes});
4926          pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec.          my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec.
4927    
4928          unless ($self->{confident}) {          unless ($self->{confident}) {
           my $charset;  
4929            if ($token->{attributes}->{charset}) { ## TODO: And if supported            if ($token->{attributes}->{charset}) { ## TODO: And if supported
4930              $charset = $token->{attributes}->{charset}->{value};              $self->{change_encoding}
4931            }                  ->($self, $token->{attributes}->{charset}->{value});
4932            if ($token->{attributes}->{'http-equiv'}) {              
4933                $meta_el->[0]->get_attribute_node_ns (undef, 'charset')
4934                    ->set_user_data (manakai_has_reference =>
4935                                         $token->{attributes}->{charset}
4936                                             ->{has_reference});
4937              } elsif ($token->{attributes}->{content}) {
4938              ## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition.              ## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition.
4939              if ($token->{attributes}->{'http-equiv'}->{value}              if ($token->{attributes}->{content}->{value}
4940                  =~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*=                  =~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt]
4941                        [\x09-\x0D\x20]*=
4942                      [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|                      [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'|
4943                      ([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) {                      ([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) {
4944                $charset = defined $1 ? $1 : defined $2 ? $2 : $3;                $self->{change_encoding}
4945              } ## TODO: And if supported                    ->($self, defined $1 ? $1 : defined $2 ? $2 : $3);
4946                  $meta_el->[0]->get_attribute_node_ns (undef, 'content')
4947                      ->set_user_data (manakai_has_reference =>
4948                                           $token->{attributes}->{content}
4949                                                 ->{has_reference});
4950                }
4951              }
4952            } else {
4953              if ($token->{attributes}->{charset}) {
4954                $meta_el->[0]->get_attribute_node_ns (undef, 'charset')
4955                    ->set_user_data (manakai_has_reference =>
4956                                         $token->{attributes}->{charset}
4957                                             ->{has_reference});
4958              }
4959              if ($token->{attributes}->{content}) {
4960                $meta_el->[0]->get_attribute_node_ns (undef, 'content')
4961                    ->set_user_data (manakai_has_reference =>
4962                                         $token->{attributes}->{content}
4963                                             ->{has_reference});
4964            }            }
           ## TODO: Change the encoding  
4965          }          }
4966    
4967          !!!next-token;          !!!next-token;
# Line 5179  sub set_inner_html ($$$) { Line 5787  sub set_inner_html ($$$) {
5787    my $s = \$_[0];    my $s = \$_[0];
5788    my $onerror = $_[1];    my $onerror = $_[1];
5789    
5790      ## ISSUE: Should {confident} be true?
5791    
5792    my $nt = $node->node_type;    my $nt = $node->node_type;
5793    if ($nt == 9) {    if ($nt == 9) {
5794      # MUST      # MUST
# Line 5211  sub set_inner_html ($$$) { Line 5821  sub set_inner_html ($$$) {
5821      my $i = 0;      my $i = 0;
5822      my $line = 1;      my $line = 1;
5823      my $column = 0;      my $column = 0;
5824      $p->{set_next_input_character} = sub {      $p->{set_next_char} = sub {
5825        my $self = shift;        my $self = shift;
5826    
5827        pop @{$self->{prev_input_character}};        pop @{$self->{prev_char}};
5828        unshift @{$self->{prev_input_character}}, $self->{next_input_character};        unshift @{$self->{prev_char}}, $self->{next_char};
5829    
5830        $self->{next_input_character} = -1 and return if $i >= length $$s;        $self->{next_char} = -1 and return if $i >= length $$s;
5831        $self->{next_input_character} = ord substr $$s, $i++, 1;        $self->{next_char} = ord substr $$s, $i++, 1;
5832        $column++;        $column++;
5833    
5834        if ($self->{next_input_character} == 0x000A) { # LF        if ($self->{next_char} == 0x000A) { # LF
5835          $line++;          $line++;
5836          $column = 0;          $column = 0;
5837        } elsif ($self->{next_input_character} == 0x000D) { # CR        } elsif ($self->{next_char} == 0x000D) { # CR
5838          $i++ if substr ($$s, $i, 1) eq "\x0A";          $i++ if substr ($$s, $i, 1) eq "\x0A";
5839          $self->{next_input_character} = 0x000A; # LF # MUST          $self->{next_char} = 0x000A; # LF # MUST
5840          $line++;          $line++;
5841          $column = 0;          $column = 0;
5842        } elsif ($self->{next_input_character} > 0x10FFFF) {        } elsif ($self->{next_char} > 0x10FFFF) {
5843          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST          $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
5844        } elsif ($self->{next_input_character} == 0x0000) { # NULL        } elsif ($self->{next_char} == 0x0000) { # NULL
5845          !!!parse-error (type => 'NULL');          !!!parse-error (type => 'NULL');
5846          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST          $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
5847        }        }
5848      };      };
5849      $p->{prev_input_character} = [-1, -1, -1];      $p->{prev_char} = [-1, -1, -1];
5850      $p->{next_input_character} = -1;      $p->{next_char} = -1;
5851            
5852      my $ponerror = $onerror || sub {      my $ponerror = $onerror || sub {
5853        my (%opt) = @_;        my (%opt) = @_;
# Line 5251  sub set_inner_html ($$$) { Line 5861  sub set_inner_html ($$$) {
5861      $p->_initialize_tree_constructor;      $p->_initialize_tree_constructor;
5862    
5863      ## Step 2      ## Step 2
5864      my $node_ln = $node->local_name;      my $node_ln = $node->manakai_local_name;
5865      $p->{content_model} = {      $p->{content_model} = {
5866        title => RCDATA_CONTENT_MODEL,        title => RCDATA_CONTENT_MODEL,
5867        textarea => RCDATA_CONTENT_MODEL,        textarea => RCDATA_CONTENT_MODEL,
# Line 5291  sub set_inner_html ($$$) { Line 5901  sub set_inner_html ($$$) {
5901        if ($anode->node_type == 1) {        if ($anode->node_type == 1) {
5902          my $nsuri = $anode->namespace_uri;          my $nsuri = $anode->namespace_uri;
5903          if (defined $nsuri and $nsuri eq 'http://www.w3.org/1999/xhtml') {          if (defined $nsuri and $nsuri eq 'http://www.w3.org/1999/xhtml') {
5904            if ($anode->local_name eq 'form') { ## TODO: case?            if ($anode->manakai_local_name eq 'form') {
5905              $p->{form_element} = $anode;              $p->{form_element} = $anode;
5906              last AN;              last AN;
5907            }            }
# Line 5331  sub set_inner_html ($$$) { Line 5941  sub set_inner_html ($$$) {
5941    
5942  } # tree construction stage  } # tree construction stage
5943    
5944  sub get_inner_html ($$$) {  package Whatpm::HTML::RestartParser;
5945    my (undef, $node, $on_error) = @_;  push our @ISA, 'Error';
   
   ## Step 1  
   my $s = '';  
   
   my $in_cdata;  
   my $parent = $node;  
   while (defined $parent) {  
     if ($parent->node_type == 1 and  
         $parent->namespace_uri eq 'http://www.w3.org/1999/xhtml' and  
         {  
           style => 1, script => 1, xmp => 1, iframe => 1,  
           noembed => 1, noframes => 1, noscript => 1,  
         }->{$parent->local_name}) { ## TODO: case thingy  
       $in_cdata = 1;  
     }  
     $parent = $parent->parent_node;  
   }  
   
   ## Step 2  
   my @node = @{$node->child_nodes};  
   C: while (@node) {  
     my $child = shift @node;  
     unless (ref $child) {  
       if ($child eq 'cdata-out') {  
         $in_cdata = 0;  
       } else {  
         $s .= $child; # end tag  
       }  
       next C;  
     }  
       
     my $nt = $child->node_type;  
     if ($nt == 1) { # Element  
       my $tag_name = $child->tag_name; ## TODO: manakai_tag_name  
       $s .= '<' . $tag_name;  
       ## NOTE: Non-HTML case:  
       ## <http://permalink.gmane.org/gmane.org.w3c.whatwg.discuss/11191>  
   
       my @attrs = @{$child->attributes}; # sort order MUST be stable  
       for my $attr (@attrs) { # order is implementation dependent  
         my $attr_name = $attr->name; ## TODO: manakai_name  
         $s .= ' ' . $attr_name . '="';  
         my $attr_value = $attr->value;  
         ## escape  
         $attr_value =~ s/&/&amp;/g;  
         $attr_value =~ s/</&lt;/g;  
         $attr_value =~ s/>/&gt;/g;  
         $attr_value =~ s/"/&quot;/g;  
         $s .= $attr_value . '"';  
       }  
       $s .= '>';  
         
       next C if {  
         area => 1, base => 1, basefont => 1, bgsound => 1,  
         br => 1, col => 1, embed => 1, frame => 1, hr => 1,  
         img => 1, input => 1, link => 1, meta => 1, param => 1,  
         spacer => 1, wbr => 1,  
       }->{$tag_name};  
   
       $s .= "\x0A" if $tag_name eq 'pre' or $tag_name eq 'textarea';  
   
       if (not $in_cdata and {  
         style => 1, script => 1, xmp => 1, iframe => 1,  
         noembed => 1, noframes => 1, noscript => 1,  
         plaintext => 1,  
       }->{$tag_name}) {  
         unshift @node, 'cdata-out';  
         $in_cdata = 1;  
       }  
   
       unshift @node, @{$child->child_nodes}, '</' . $tag_name . '>';  
     } elsif ($nt == 3 or $nt == 4) {  
       if ($in_cdata) {  
         $s .= $child->data;  
       } else {  
         my $value = $child->data;  
         $value =~ s/&/&amp;/g;  
         $value =~ s/</&lt;/g;  
         $value =~ s/>/&gt;/g;  
         $value =~ s/"/&quot;/g;  
         $s .= $value;  
       }  
     } elsif ($nt == 8) {  
       $s .= '<!--' . $child->data . '-->';  
     } elsif ($nt == 10) {  
       $s .= '<!DOCTYPE ' . $child->name . '>';  
     } elsif ($nt == 5) { # entrefs  
       push @node, @{$child->child_nodes};  
     } else {  
       $on_error->($child) if defined $on_error;  
     }  
     ## ISSUE: This code does not support PIs.  
   } # C  
     
   ## Step 3  
   return \$s;  
 } # get_inner_html  
5946    
5947  1;  1;
5948  # $Date$  # $Date$
Legend:
Removed from v.1.58  
changed lines
  Added in v.1.78
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24