/[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 1.72 by wakaba, Sun Mar 2 14:32:26 2008 UTC revision 1.100 by wakaba, Sun Mar 9 04:08:41 2008 UTC
# Line 179  sub parse_string ($$$;$) { Line 179  sub parse_string ($$$;$) {
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 226  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 {    $self->{parse_error} = sub {
233      #      #
# Line 304  sub ROW_IMS ()        { 0b10000000 } Line 304  sub ROW_IMS ()        { 0b10000000 }
304  sub BODY_AFTER_IMS () { 0b100000000 }  sub BODY_AFTER_IMS () { 0b100000000 }
305  sub FRAME_IMS ()      { 0b1000000000 }  sub FRAME_IMS ()      { 0b1000000000 }
306    
307    ## NOTE: "initial" and "before html" insertion modes have no constants.
308    
309    ## NOTE: "after after body" insertion mode.
310  sub AFTER_HTML_BODY_IM () { AFTER_HTML_IMS | BODY_AFTER_IMS }  sub AFTER_HTML_BODY_IM () { AFTER_HTML_IMS | BODY_AFTER_IMS }
311    
312    ## NOTE: "after after frameset" insertion mode.
313  sub AFTER_HTML_FRAMESET_IM () { AFTER_HTML_IMS | FRAME_IMS }  sub AFTER_HTML_FRAMESET_IM () { AFTER_HTML_IMS | FRAME_IMS }
314    
315  sub IN_HEAD_IM () { HEAD_IMS | 0b00 }  sub IN_HEAD_IM () { HEAD_IMS | 0b00 }
316  sub IN_HEAD_NOSCRIPT_IM () { HEAD_IMS | 0b01 }  sub IN_HEAD_NOSCRIPT_IM () { HEAD_IMS | 0b01 }
317  sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 }  sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 }
# Line 333  sub _initialize_tokenizer ($) { Line 339  sub _initialize_tokenizer ($) {
339    undef $self->{last_emitted_start_tag_name};    undef $self->{last_emitted_start_tag_name};
340    undef $self->{last_attribute_value_state};    undef $self->{last_attribute_value_state};
341    $self->{char} = [];    $self->{char} = [];
342    # $self->{next_input_character}    # $self->{next_char}
343    !!!next-input-character;    !!!next-input-character;
344    $self->{token} = [];    $self->{token} = [];
345    # $self->{escape}    # $self->{escape}
# Line 346  sub _initialize_tokenizer ($) { Line 352  sub _initialize_tokenizer ($) {
352  ##   ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN)  ##   ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN)
353  ##   ->{public_identifier} (DOCTYPE_TOKEN)  ##   ->{public_identifier} (DOCTYPE_TOKEN)
354  ##   ->{system_identifier} (DOCTYPE_TOKEN)  ##   ->{system_identifier} (DOCTYPE_TOKEN)
355  ##   ->{correct} == 1 or 0 (DOCTYPE_TOKEN)  ##   ->{quirks} == 1 or 0 (DOCTYPE_TOKEN): "force-quirks" flag
356  ##   ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN)  ##   ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN)
357  ##        ->{name}  ##        ->{name}
358  ##        ->{value}  ##        ->{value}
# Line 384  sub _get_next_token ($) { Line 390  sub _get_next_token ($) {
390    
391    A: {    A: {
392      if ($self->{state} == DATA_STATE) {      if ($self->{state} == DATA_STATE) {
393        if ($self->{next_input_character} == 0x0026) { # &        if ($self->{next_char} == 0x0026) { # &
394          if ($self->{content_model} & CM_ENTITY and # PCDATA | RCDATA          if ($self->{content_model} & CM_ENTITY and # PCDATA | RCDATA
395              not $self->{escape}) {              not $self->{escape}) {
396              !!!cp (1);
397            $self->{state} = ENTITY_DATA_STATE;            $self->{state} = ENTITY_DATA_STATE;
398            !!!next-input-character;            !!!next-input-character;
399            redo A;            redo A;
400          } else {          } else {
401              !!!cp (2);
402            #            #
403          }          }
404        } elsif ($self->{next_input_character} == 0x002D) { # -        } elsif ($self->{next_char} == 0x002D) { # -
405          if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA          if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA
406            unless ($self->{escape}) {            unless ($self->{escape}) {
407              if ($self->{prev_input_character}->[0] == 0x002D and # -              if ($self->{prev_char}->[0] == 0x002D and # -
408                  $self->{prev_input_character}->[1] == 0x0021 and # !                  $self->{prev_char}->[1] == 0x0021 and # !
409                  $self->{prev_input_character}->[2] == 0x003C) { # <                  $self->{prev_char}->[2] == 0x003C) { # <
410                  !!!cp (3);
411                $self->{escape} = 1;                $self->{escape} = 1;
412                } else {
413                  !!!cp (4);
414              }              }
415              } else {
416                !!!cp (5);
417            }            }
418          }          }
419                    
420          #          #
421        } elsif ($self->{next_input_character} == 0x003C) { # <        } elsif ($self->{next_char} == 0x003C) { # <
422          if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA          if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA
423              (($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA              (($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA
424               not $self->{escape})) {               not $self->{escape})) {
425              !!!cp (6);
426            $self->{state} = TAG_OPEN_STATE;            $self->{state} = TAG_OPEN_STATE;
427            !!!next-input-character;            !!!next-input-character;
428            redo A;            redo A;
429          } else {          } else {
430              !!!cp (7);
431            #            #
432          }          }
433        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
434          if ($self->{escape} and          if ($self->{escape} and
435              ($self->{content_model} & CM_LIMITED_MARKUP)) { # RCDATA | CDATA              ($self->{content_model} & CM_LIMITED_MARKUP)) { # RCDATA | CDATA
436            if ($self->{prev_input_character}->[0] == 0x002D and # -            if ($self->{prev_char}->[0] == 0x002D and # -
437                $self->{prev_input_character}->[1] == 0x002D) { # -                $self->{prev_char}->[1] == 0x002D) { # -
438                !!!cp (8);
439              delete $self->{escape};              delete $self->{escape};
440              } else {
441                !!!cp (9);
442            }            }
443            } else {
444              !!!cp (10);
445          }          }
446                    
447          #          #
448        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
449            !!!cp (11);
450          !!!emit ({type => END_OF_FILE_TOKEN});          !!!emit ({type => END_OF_FILE_TOKEN});
451          last A; ## TODO: ok?          last A; ## TODO: ok?
452          } else {
453            !!!cp (12);
454        }        }
455        # Anything else        # Anything else
456        my $token = {type => CHARACTER_TOKEN,        my $token = {type => CHARACTER_TOKEN,
457                     data => chr $self->{next_input_character}};                     data => chr $self->{next_char}};
458        ## Stay in the data state        ## Stay in the data state
459        !!!next-input-character;        !!!next-input-character;
460    
# Line 447  sub _get_next_token ($) { Line 470  sub _get_next_token ($) {
470        # next-input-character is already done        # next-input-character is already done
471    
472        unless (defined $token) {        unless (defined $token) {
473            !!!cp (13);
474          !!!emit ({type => CHARACTER_TOKEN, data => '&'});          !!!emit ({type => CHARACTER_TOKEN, data => '&'});
475        } else {        } else {
476            !!!cp (14);
477          !!!emit ($token);          !!!emit ($token);
478        }        }
479    
480        redo A;        redo A;
481      } elsif ($self->{state} == TAG_OPEN_STATE) {      } elsif ($self->{state} == TAG_OPEN_STATE) {
482        if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA        if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA
483          if ($self->{next_input_character} == 0x002F) { # /          if ($self->{next_char} == 0x002F) { # /
484              !!!cp (15);
485            !!!next-input-character;            !!!next-input-character;
486            $self->{state} = CLOSE_TAG_OPEN_STATE;            $self->{state} = CLOSE_TAG_OPEN_STATE;
487            redo A;            redo A;
488          } else {          } else {
489              !!!cp (16);
490            ## reconsume            ## reconsume
491            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
492    
# Line 468  sub _get_next_token ($) { Line 495  sub _get_next_token ($) {
495            redo A;            redo A;
496          }          }
497        } elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA        } elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA
498          if ($self->{next_input_character} == 0x0021) { # !          if ($self->{next_char} == 0x0021) { # !
499              !!!cp (17);
500            $self->{state} = MARKUP_DECLARATION_OPEN_STATE;            $self->{state} = MARKUP_DECLARATION_OPEN_STATE;
501            !!!next-input-character;            !!!next-input-character;
502            redo A;            redo A;
503          } elsif ($self->{next_input_character} == 0x002F) { # /          } elsif ($self->{next_char} == 0x002F) { # /
504              !!!cp (18);
505            $self->{state} = CLOSE_TAG_OPEN_STATE;            $self->{state} = CLOSE_TAG_OPEN_STATE;
506            !!!next-input-character;            !!!next-input-character;
507            redo A;            redo A;
508          } elsif (0x0041 <= $self->{next_input_character} and          } elsif (0x0041 <= $self->{next_char} and
509                   $self->{next_input_character} <= 0x005A) { # A..Z                   $self->{next_char} <= 0x005A) { # A..Z
510              !!!cp (19);
511            $self->{current_token}            $self->{current_token}
512              = {type => START_TAG_TOKEN,              = {type => START_TAG_TOKEN,
513                 tag_name => chr ($self->{next_input_character} + 0x0020)};                 tag_name => chr ($self->{next_char} + 0x0020)};
514            $self->{state} = TAG_NAME_STATE;            $self->{state} = TAG_NAME_STATE;
515            !!!next-input-character;            !!!next-input-character;
516            redo A;            redo A;
517          } elsif (0x0061 <= $self->{next_input_character} and          } elsif (0x0061 <= $self->{next_char} and
518                   $self->{next_input_character} <= 0x007A) { # a..z                   $self->{next_char} <= 0x007A) { # a..z
519              !!!cp (20);
520            $self->{current_token} = {type => START_TAG_TOKEN,            $self->{current_token} = {type => START_TAG_TOKEN,
521                              tag_name => chr ($self->{next_input_character})};                              tag_name => chr ($self->{next_char})};
522            $self->{state} = TAG_NAME_STATE;            $self->{state} = TAG_NAME_STATE;
523            !!!next-input-character;            !!!next-input-character;
524            redo A;            redo A;
525          } elsif ($self->{next_input_character} == 0x003E) { # >          } elsif ($self->{next_char} == 0x003E) { # >
526              !!!cp (21);
527            !!!parse-error (type => 'empty start tag');            !!!parse-error (type => 'empty start tag');
528            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
529            !!!next-input-character;            !!!next-input-character;
# Line 499  sub _get_next_token ($) { Line 531  sub _get_next_token ($) {
531            !!!emit ({type => CHARACTER_TOKEN, data => '<>'});            !!!emit ({type => CHARACTER_TOKEN, data => '<>'});
532    
533            redo A;            redo A;
534          } elsif ($self->{next_input_character} == 0x003F) { # ?          } elsif ($self->{next_char} == 0x003F) { # ?
535              !!!cp (22);
536            !!!parse-error (type => 'pio');            !!!parse-error (type => 'pio');
537            $self->{state} = BOGUS_COMMENT_STATE;            $self->{state} = BOGUS_COMMENT_STATE;
538            ## $self->{next_input_character} is intentionally left as is            ## $self->{next_char} is intentionally left as is
539            redo A;            redo A;
540          } else {          } else {
541              !!!cp (23);
542            !!!parse-error (type => 'bare stago');            !!!parse-error (type => 'bare stago');
543            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
544            ## reconsume            ## reconsume
# Line 522  sub _get_next_token ($) { Line 556  sub _get_next_token ($) {
556            ## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>            ## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>
557            my @next_char;            my @next_char;
558            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++) {
559              push @next_char, $self->{next_input_character};              push @next_char, $self->{next_char};
560              my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1);              my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1);
561              my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c;              my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c;
562              if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) {              if ($self->{next_char} == $c or $self->{next_char} == $C) {
563                  !!!cp (24);
564                !!!next-input-character;                !!!next-input-character;
565                next TAGNAME;                next TAGNAME;
566              } else {              } else {
567                $self->{next_input_character} = shift @next_char; # reconsume                !!!cp (25);
568                  $self->{next_char} = shift @next_char; # reconsume
569                !!!back-next-input-character (@next_char);                !!!back-next-input-character (@next_char);
570                $self->{state} = DATA_STATE;                $self->{state} = DATA_STATE;
571    
# Line 538  sub _get_next_token ($) { Line 574  sub _get_next_token ($) {
574                redo A;                redo A;
575              }              }
576            }            }
577            push @next_char, $self->{next_input_character};            push @next_char, $self->{next_char};
578                
579            unless ($self->{next_input_character} == 0x0009 or # HT            unless ($self->{next_char} == 0x0009 or # HT
580                    $self->{next_input_character} == 0x000A or # LF                    $self->{next_char} == 0x000A or # LF
581                    $self->{next_input_character} == 0x000B or # VT                    $self->{next_char} == 0x000B or # VT
582                    $self->{next_input_character} == 0x000C or # FF                    $self->{next_char} == 0x000C or # FF
583                    $self->{next_input_character} == 0x0020 or # SP                    $self->{next_char} == 0x0020 or # SP
584                    $self->{next_input_character} == 0x003E or # >                    $self->{next_char} == 0x003E or # >
585                    $self->{next_input_character} == 0x002F or # /                    $self->{next_char} == 0x002F or # /
586                    $self->{next_input_character} == -1) {                    $self->{next_char} == -1) {
587              $self->{next_input_character} = shift @next_char; # reconsume              !!!cp (26);
588                $self->{next_char} = shift @next_char; # reconsume
589              !!!back-next-input-character (@next_char);              !!!back-next-input-character (@next_char);
590              $self->{state} = DATA_STATE;              $self->{state} = DATA_STATE;
591              !!!emit ({type => CHARACTER_TOKEN, data => '</'});              !!!emit ({type => CHARACTER_TOKEN, data => '</'});
592              redo A;              redo A;
593            } else {            } else {
594              $self->{next_input_character} = shift @next_char;              !!!cp (27);
595                $self->{next_char} = shift @next_char;
596              !!!back-next-input-character (@next_char);              !!!back-next-input-character (@next_char);
597              # and consume...              # and consume...
598            }            }
599          } else {          } else {
600            ## No start tag token has ever been emitted            ## No start tag token has ever been emitted
601              !!!cp (28);
602            # next-input-character is already done            # next-input-character is already done
603            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
604            !!!emit ({type => CHARACTER_TOKEN, data => '</'});            !!!emit ({type => CHARACTER_TOKEN, data => '</'});
# Line 567  sub _get_next_token ($) { Line 606  sub _get_next_token ($) {
606          }          }
607        }        }
608                
609        if (0x0041 <= $self->{next_input_character} and        if (0x0041 <= $self->{next_char} and
610            $self->{next_input_character} <= 0x005A) { # A..Z            $self->{next_char} <= 0x005A) { # A..Z
611            !!!cp (29);
612          $self->{current_token} = {type => END_TAG_TOKEN,          $self->{current_token} = {type => END_TAG_TOKEN,
613                            tag_name => chr ($self->{next_input_character} + 0x0020)};                            tag_name => chr ($self->{next_char} + 0x0020)};
614          $self->{state} = TAG_NAME_STATE;          $self->{state} = TAG_NAME_STATE;
615          !!!next-input-character;          !!!next-input-character;
616          redo A;          redo A;
617        } elsif (0x0061 <= $self->{next_input_character} and        } elsif (0x0061 <= $self->{next_char} and
618                 $self->{next_input_character} <= 0x007A) { # a..z                 $self->{next_char} <= 0x007A) { # a..z
619            !!!cp (30);
620          $self->{current_token} = {type => END_TAG_TOKEN,          $self->{current_token} = {type => END_TAG_TOKEN,
621                            tag_name => chr ($self->{next_input_character})};                            tag_name => chr ($self->{next_char})};
622          $self->{state} = TAG_NAME_STATE;          $self->{state} = TAG_NAME_STATE;
623          !!!next-input-character;          !!!next-input-character;
624          redo A;          redo A;
625        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
626            !!!cp (31);
627          !!!parse-error (type => 'empty end tag');          !!!parse-error (type => 'empty end tag');
628          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
629          !!!next-input-character;          !!!next-input-character;
630          redo A;          redo A;
631        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
632            !!!cp (32);
633          !!!parse-error (type => 'bare etago');          !!!parse-error (type => 'bare etago');
634          $self->{state} = DATA_STATE;          $self->{state} = DATA_STATE;
635          # reconsume          # reconsume
# Line 595  sub _get_next_token ($) { Line 638  sub _get_next_token ($) {
638    
639          redo A;          redo A;
640        } else {        } else {
641            !!!cp (33);
642          !!!parse-error (type => 'bogus end tag');          !!!parse-error (type => 'bogus end tag');
643          $self->{state} = BOGUS_COMMENT_STATE;          $self->{state} = BOGUS_COMMENT_STATE;
644          ## $self->{next_input_character} is intentionally left as is          ## $self->{next_char} is intentionally left as is
645          redo A;          redo A;
646        }        }
647      } elsif ($self->{state} == TAG_NAME_STATE) {      } elsif ($self->{state} == TAG_NAME_STATE) {
648        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT
649            $self->{next_input_character} == 0x000A or # LF            $self->{next_char} == 0x000A or # LF
650            $self->{next_input_character} == 0x000B or # VT            $self->{next_char} == 0x000B or # VT
651            $self->{next_input_character} == 0x000C or # FF            $self->{next_char} == 0x000C or # FF
652            $self->{next_input_character} == 0x0020) { # SP            $self->{next_char} == 0x0020) { # SP
653            !!!cp (34);
654          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
655          !!!next-input-character;          !!!next-input-character;
656          redo A;          redo A;
657        } elsif ($self->{next_input_character} == 0x003E) { # >        } elsif ($self->{next_char} == 0x003E) { # >
658          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
659              !!!cp (35);
660            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
661                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
662            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
663          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
664            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
665            if ($self->{current_token}->{attributes}) {            #if ($self->{current_token}->{attributes}) {
666              !!!parse-error (type => 'end tag attribute');            #  ## NOTE: This should never be reached.
667            }            #  !!! cp (36);
668              #  !!! parse-error (type => 'end tag attribute');
669              #} else {
670                !!!cp (37);
671              #}
672          } else {          } else {
673            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
674          }          }
# Line 628  sub _get_next_token ($) { Line 678  sub _get_next_token ($) {
678          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
679    
680          redo A;          redo A;
681        } elsif (0x0041 <= $self->{next_input_character} and        } elsif (0x0041 <= $self->{next_char} and
682                 $self->{next_input_character} <= 0x005A) { # A..Z                 $self->{next_char} <= 0x005A) { # A..Z
683          $self->{current_token}->{tag_name} .= chr ($self->{next_input_character} + 0x0020);          !!!cp (38);
684            $self->{current_token}->{tag_name} .= chr ($self->{next_char} + 0x0020);
685            # start tag or end tag            # start tag or end tag
686          ## Stay in this state          ## Stay in this state
687          !!!next-input-character;          !!!next-input-character;
688          redo A;          redo A;
689        } elsif ($self->{next_input_character} == -1) {        } elsif ($self->{next_char} == -1) {
690          !!!parse-error (type => 'unclosed tag');          !!!parse-error (type => 'unclosed tag');
691          if ($self->{current_token}->{type} == START_TAG_TOKEN) {          if ($self->{current_token}->{type} == START_TAG_TOKEN) {
692              !!!cp (39);
693            $self->{current_token}->{first_start_tag}            $self->{current_token}->{first_start_tag}
694                = not defined $self->{last_emitted_start_tag_name};                = not defined $self->{last_emitted_start_tag_name};
695            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};            $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name};
696          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {          } elsif ($self->{current_token}->{type} == END_TAG_TOKEN) {
697            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST            $self->{content_model} = PCDATA_CONTENT_MODEL; # MUST
698            if ($self->{current_token}->{attributes}) {            #if ($self->{current_token}->{attributes}) {
699              !!!parse-error (type => 'end tag attribute');            #  ## NOTE: This state should never be reached.
700            }            #  !!! cp (40);
701              #  !!! parse-error (type => 'end tag attribute');
702              #} else {
703                !!!cp (41);
704              #}
705          } else {          } else {
706            die "$0: $self->{current_token}->{type}: Unknown token type";            die "$0: $self->{current_token}->{type}: Unknown token type";
707          }          }
# Line 655  sub _get_next_token ($) { Line 711  sub _get_next_token ($) {
711          !!!emit ($self->{current_token}); # start tag or end tag          !!!emit ($self->{current_token}); # start tag or end tag
712    
713          redo A;          redo A;
714        } elsif ($self->{next_input_character} == 0x002F) { # /        } elsif ($self->{next_char} == 0x002F) { # /
715          !!!next-input-character;          !!!next-input-character;
716          if ($self->{next_input_character} == 0x003E and # >          if ($self->{next_char} == 0x003E and # >
717              $self->{current_token}->{type} == START_TAG_TOKEN and              $self->{current_token}->{type} == START_TAG_TOKEN and
718              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {              $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) {
719            # permitted slash            # permitted slash
720              !!!cp (42);
721            #            #
722          } else {          } else {
723              !!!cp (43);
724            !!!parse-error (type => 'nestc');            !!!parse-error (type => 'nestc');
725          }          }
726          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;          $self->{state} = BEFORE_ATTRIBUTE_NAME_STATE;
727          # next-input-character is already done          # next-input-character is already done
728          redo A;          redo A;
729        } else {        } else {
730          $self->{current_token}->{tag_name} .= chr $self->{next_input_character};          !!!cp (44);
731            $self->{current_token}->{tag_name} .= chr $self->{next_char};
732            # start tag or end tag            # start tag or end tag
733          ## Stay in the state          ## Stay in the state
734          !!!next-input-character;          !!!next-input-character;
735          redo A;          redo A;
736        }        }
737      } elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) {      } elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) {
738        if ($self->{next_input_character} == 0x0009 or # HT        if ($self->{next_char} == 0x0009 or # HT