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

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

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

revision 1.19 by wakaba, Sun Oct 19 07:19:00 2008 UTC revision 1.29 by wakaba, Sun Aug 16 04:06:34 2009 UTC
# Line 182  sub NDATA_STATE () { 86 } Line 182  sub NDATA_STATE () { 86 }
182  sub AFTER_NDATA_STATE () { 87 }  sub AFTER_NDATA_STATE () { 87 }
183  sub BEFORE_NOTATION_NAME_STATE () { 88 }  sub BEFORE_NOTATION_NAME_STATE () { 88 }
184  sub NOTATION_NAME_STATE () { 89 }  sub NOTATION_NAME_STATE () { 89 }
185  sub AFTER_NOTATION_NAME_STATE () { 90 }  sub DOCTYPE_ENTITY_VALUE_DOUBLE_QUOTED_STATE () { 90 }
186  sub DOCTYPE_ENTITY_VALUE_DOUBLE_QUOTED_STATE () { 91 }  sub DOCTYPE_ENTITY_VALUE_SINGLE_QUOTED_STATE () { 91 }
187  sub DOCTYPE_ENTITY_VALUE_SINGLE_QUOTED_STATE () { 92 }  sub ENTITY_VALUE_ENTITY_STATE () { 92 }
188  sub ENTITY_VALUE_ENTITY_STATE () { 93 }  sub AFTER_ELEMENT_NAME_STATE () { 93 }
189  sub BOGUS_MD_STATE () { 94 }  sub BEFORE_ELEMENT_CONTENT_STATE () { 94 }
190    sub CONTENT_KEYWORD_STATE () { 95 }
191    sub AFTER_CM_GROUP_OPEN_STATE () { 96 }
192    sub CM_ELEMENT_NAME_STATE () { 97 }
193    sub AFTER_CM_ELEMENT_NAME_STATE () { 98 }
194    sub AFTER_CM_GROUP_CLOSE_STATE () { 99 }
195    sub AFTER_MD_DEF_STATE () { 100 }
196    sub BOGUS_MD_STATE () { 101 }
197    
198  ## Tree constructor state constants (see Whatpm::HTML for the full  ## Tree constructor state constants (see Whatpm::HTML for the full
199  ## list and descriptions)  ## list and descriptions)
# Line 1733  sub _get_next_token ($) { Line 1740  sub _get_next_token ($) {
1740    
1741          redo A;          redo A;
1742        } else {        } else {
1743          if ($self->{nc} == 0x003D) { # =          if ($self->{nc} == 0x003D or $self->{nc} == 0x003C) { # =, <
1744                        
1745            ## XML5: Not a parse error.            ## XML5: Not a parse error.
1746            $self->{parse_error}->(level => $self->{level}->{must}, type => 'bad attribute value');            $self->{parse_error}->(level => $self->{level}->{must}, type => 'bad attribute value');
# Line 1809  sub _get_next_token ($) { Line 1816  sub _get_next_token ($) {
1816      }      }
1817        
1818          redo A;          redo A;
1819          } elsif ($self->{is_xml} and
1820                   $is_space->{$self->{nc}}) {
1821            
1822            $self->{ca}->{value} .= ' ';
1823            ## Stay in the state.
1824            
1825        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
1826          $self->{line_prev} = $self->{line};
1827          $self->{column_prev} = $self->{column};
1828          $self->{column}++;
1829          $self->{nc}
1830              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
1831        } else {
1832          $self->{set_nc}->($self);
1833        }
1834      
1835            redo A;
1836        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
1837          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed attribute value');          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed attribute value');
1838          if ($self->{ct}->{type} == START_TAG_TOKEN) {          if ($self->{ct}->{type} == START_TAG_TOKEN) {
# Line 1856  sub _get_next_token ($) { Line 1880  sub _get_next_token ($) {
1880          }          }
1881          $self->{ca}->{value} .= chr ($self->{nc});          $self->{ca}->{value} .= chr ($self->{nc});
1882          $self->{read_until}->($self->{ca}->{value},          $self->{read_until}->($self->{ca}->{value},
1883                                q["&<],                                qq["&<\x09\x0C\x20],
1884                                length $self->{ca}->{value});                                length $self->{ca}->{value});
1885    
1886          ## Stay in the state          ## Stay in the state
# Line 1923  sub _get_next_token ($) { Line 1947  sub _get_next_token ($) {
1947      }      }
1948        
1949          redo A;          redo A;
1950          } elsif ($self->{is_xml} and
1951                   $is_space->{$self->{nc}}) {
1952            
1953            $self->{ca}->{value} .= ' ';
1954            ## Stay in the state.
1955            
1956        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
1957          $self->{line_prev} = $self->{line};
1958          $self->{column_prev} = $self->{column};
1959          $self->{column}++;
1960          $self->{nc}
1961              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
1962        } else {
1963          $self->{set_nc}->($self);
1964        }
1965      
1966            redo A;
1967        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
1968          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed attribute value');          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed attribute value');
1969          if ($self->{ct}->{type} == START_TAG_TOKEN) {          if ($self->{ct}->{type} == START_TAG_TOKEN) {
# Line 1970  sub _get_next_token ($) { Line 2011  sub _get_next_token ($) {
2011          }          }
2012          $self->{ca}->{value} .= chr ($self->{nc});          $self->{ca}->{value} .= chr ($self->{nc});
2013          $self->{read_until}->($self->{ca}->{value},          $self->{read_until}->($self->{ca}->{value},
2014                                q['&<],                                qq['&<\x09\x0C\x20],
2015                                length $self->{ca}->{value});                                length $self->{ca}->{value});
2016    
2017          ## Stay in the state          ## Stay in the state
# Line 2142  sub _get_next_token ($) { Line 2183  sub _get_next_token ($) {
2183               0x0022 => 1, # "               0x0022 => 1, # "
2184               0x0027 => 1, # '               0x0027 => 1, # '
2185               0x003D => 1, # =               0x003D => 1, # =
2186                 0x003C => 1, # <
2187              }->{$self->{nc}}) {              }->{$self->{nc}}) {
2188                        
2189            ## XML5: Not a parse error.            ## XML5: Not a parse error.
# Line 2151  sub _get_next_token ($) { Line 2193  sub _get_next_token ($) {
2193          }          }
2194          $self->{ca}->{value} .= chr ($self->{nc});          $self->{ca}->{value} .= chr ($self->{nc});
2195          $self->{read_until}->($self->{ca}->{value},          $self->{read_until}->($self->{ca}->{value},
2196                                q["'=& >],                                qq["'=& \x09\x0C>],
2197                                length $self->{ca}->{value});                                length $self->{ca}->{value});
2198    
2199          ## Stay in the state          ## Stay in the state
# Line 2957  sub _get_next_token ($) { Line 2999  sub _get_next_token ($) {
2999          redo A;          redo A;
3000        } else {        } else {
3001                    
         ## XML5: Not a parse error.  
         $self->{parse_error}->(level => $self->{level}->{must}, type => 'dash in comment',  
                         line => $self->{line_prev},  
                         column => $self->{column_prev});  
3002          $self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment          $self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment
3003          $self->{state} = COMMENT_STATE;          $self->{state} = COMMENT_STATE;
3004                    
# Line 2992  sub _get_next_token ($) { Line 3030  sub _get_next_token ($) {
3030      }      }
3031        
3032          redo A;          redo A;
3033          } elsif ($self->{nc} == -1) {
3034            
3035            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed DOCTYPE');
3036            $self->{ct}->{quirks} = 1;
3037    
3038            $self->{state} = DATA_STATE;
3039            ## Reconsume.
3040            return  ($self->{ct}); # DOCTYPE (quirks)
3041    
3042            redo A;
3043        } else {        } else {
3044                    
3045          ## XML5: Unless EOF, swith to the bogus comment state.          ## XML5: Swith to the bogus comment state.
3046          $self->{parse_error}->(level => $self->{level}->{must}, type => 'no space before DOCTYPE name');          $self->{parse_error}->(level => $self->{level}->{must}, type => 'no space before DOCTYPE name');
3047          $self->{state} = BEFORE_DOCTYPE_NAME_STATE;          $self->{state} = BEFORE_DOCTYPE_NAME_STATE;
3048          ## reconsume          ## reconsume
# Line 3039  sub _get_next_token ($) { Line 3087  sub _get_next_token ($) {
3087          return  ($self->{ct}); # DOCTYPE (quirks)          return  ($self->{ct}); # DOCTYPE (quirks)
3088    
3089          redo A;          redo A;
3090          } elsif (0x0041 <= $self->{nc} and $self->{nc} <= 0x005A) { # A..Z
3091            
3092            $self->{ct}->{name} # DOCTYPE
3093                = chr ($self->{nc} + ($self->{is_xml} ? 0 : 0x0020));
3094            delete $self->{ct}->{quirks};
3095            $self->{state} = DOCTYPE_NAME_STATE;
3096            
3097        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
3098          $self->{line_prev} = $self->{line};
3099          $self->{column_prev} = $self->{column};
3100          $self->{column}++;
3101          $self->{nc}
3102              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
3103        } else {
3104          $self->{set_nc}->($self);
3105        }
3106      
3107            redo A;
3108        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
3109                    
3110          $self->{parse_error}->(level => $self->{level}->{must}, type => 'no DOCTYPE name');          $self->{parse_error}->(level => $self->{level}->{must}, type => 'no DOCTYPE name');
# Line 3125  sub _get_next_token ($) { Line 3191  sub _get_next_token ($) {
3191          return  ($self->{ct}); # DOCTYPE          return  ($self->{ct}); # DOCTYPE
3192    
3193          redo A;          redo A;
3194          } elsif (0x0041 <= $self->{nc} and $self->{nc} <= 0x005A) { # A..Z
3195            
3196            $self->{ct}->{name} # DOCTYPE
3197                .= chr ($self->{nc} + ($self->{is_xml} ? 0 : 0x0020));
3198            delete $self->{ct}->{quirks};
3199            ## Stay in the state.
3200            
3201        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
3202          $self->{line_prev} = $self->{line};
3203          $self->{column_prev} = $self->{column};
3204          $self->{column}++;
3205          $self->{nc}
3206              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
3207        } else {
3208          $self->{set_nc}->($self);
3209        }
3210      
3211            redo A;
3212        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
3213                    
3214          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed DOCTYPE');          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed DOCTYPE');
# Line 3156  sub _get_next_token ($) { Line 3240  sub _get_next_token ($) {
3240          redo A;          redo A;
3241        } else {        } else {
3242                    
3243          $self->{ct}->{name}          $self->{ct}->{name} .= chr ($self->{nc}); # DOCTYPE
3244            .= chr ($self->{nc}); # DOCTYPE          ## Stay in the state.
         ## Stay in the state  
3245                    
3246      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
3247        $self->{line_prev} = $self->{line};        $self->{line_prev} = $self->{line};
# Line 4621  sub _get_next_token ($) { Line 4704  sub _get_next_token ($) {
4704              0x003C => 1, 0x0026 => 1, -1 => 1, # <, &              0x003C => 1, 0x0026 => 1, -1 => 1, # <, &
4705              $self->{entity_add} => 1,              $self->{entity_add} => 1,
4706            }->{$self->{nc}}) {            }->{$self->{nc}}) {
4707                    if ($self->{is_xml}) {
4708              
4709              $self->{parse_error}->(level => $self->{level}->{must}, type => 'bare ero',
4710                              line => $self->{line_prev},
4711                              column => $self->{column_prev}
4712                                  + ($self->{nc} == -1 ? 1 : 0));
4713            } else {
4714              
4715              ## No error
4716            }
4717          ## Don't consume          ## Don't consume
         ## No error  
4718          ## Return nothing.          ## Return nothing.
4719          #          #
4720        } elsif ($self->{nc} == 0x0023) { # #        } elsif ($self->{nc} == 0x0023) { # #
# Line 4642  sub _get_next_token ($) { Line 4733  sub _get_next_token ($) {
4733      }      }
4734        
4735          redo A;          redo A;
4736        } elsif ((0x0041 <= $self->{nc} and        } elsif ($self->{is_xml} or
4737                   (0x0041 <= $self->{nc} and
4738                  $self->{nc} <= 0x005A) or # A..Z                  $self->{nc} <= 0x005A) or # A..Z
4739                 (0x0061 <= $self->{nc} and                 (0x0061 <= $self->{nc} and
4740                  $self->{nc} <= 0x007A)) { # a..z                  $self->{nc} <= 0x007A)) { # a..z
# Line 4696  sub _get_next_token ($) { Line 4788  sub _get_next_token ($) {
4788          redo A;          redo A;
4789        }        }
4790      } elsif ($self->{state} == ENTITY_HASH_STATE) {      } elsif ($self->{state} == ENTITY_HASH_STATE) {
4791        if ($self->{nc} == 0x0078 or # x        if ($self->{nc} == 0x0078) { # x
4792            $self->{nc} == 0x0058) { # X          
4793            $self->{state} = HEXREF_X_STATE;
4794            $self->{kwd} .= chr $self->{nc};
4795            
4796        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
4797          $self->{line_prev} = $self->{line};
4798          $self->{column_prev} = $self->{column};
4799          $self->{column}++;
4800          $self->{nc}
4801              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
4802        } else {
4803          $self->{set_nc}->($self);
4804        }
4805      
4806            redo A;
4807          } elsif ($self->{nc} == 0x0058) { # X
4808                    
4809            if ($self->{is_xml}) {
4810              $self->{parse_error}->(level => $self->{level}->{must}, type => 'uppercase hcro'); ## TODO: type
4811            }
4812          $self->{state} = HEXREF_X_STATE;          $self->{state} = HEXREF_X_STATE;
4813          $self->{kwd} .= chr $self->{nc};          $self->{kwd} .= chr $self->{nc};
4814                    
# Line 4803  sub _get_next_token ($) { Line 4913  sub _get_next_token ($) {
4913        my $code = $self->{kwd};        my $code = $self->{kwd};
4914        my $l = $self->{line_prev};        my $l = $self->{line_prev};
4915        my $c = $self->{column_prev};        my $c = $self->{column_prev};
4916        if ($charref_map->{$code}) {        if ((not $self->{is_xml} and $charref_map->{$code}) or
4917              ($self->{is_xml} and 0xD800 <= $code and $code <= 0xDFFF) or
4918              ($self->{is_xml} and $code == 0x0000)) {
4919                    
4920          $self->{parse_error}->(level => $self->{level}->{must}, type => 'invalid character reference',          $self->{parse_error}->(level => $self->{level}->{must}, type => 'invalid character reference',
4921                          text => (sprintf 'U+%04X', $code),                          text => (sprintf 'U+%04X', $code),
# Line 4956  sub _get_next_token ($) { Line 5068  sub _get_next_token ($) {
5068        my $code = $self->{kwd};        my $code = $self->{kwd};
5069        my $l = $self->{line_prev};        my $l = $self->{line_prev};
5070        my $c = $self->{column_prev};        my $c = $self->{column_prev};
5071        if ($charref_map->{$code}) {        if ((not $self->{is_xml} and $charref_map->{$code}) or
5072              ($self->{is_xml} and 0xD800 <= $code and $code <= 0xDFFF) or
5073              ($self->{is_xml} and $code == 0x0000)) {
5074                    
5075          $self->{parse_error}->(level => $self->{level}->{must}, type => 'invalid character reference',          $self->{parse_error}->(level => $self->{level}->{must}, type => 'invalid character reference',
5076                          text => (sprintf 'U+%04X', $code),                          text => (sprintf 'U+%04X', $code),
# Line 4990  sub _get_next_token ($) { Line 5104  sub _get_next_token ($) {
5104          redo A;          redo A;
5105        }        }
5106      } elsif ($self->{state} == ENTITY_NAME_STATE) {      } elsif ($self->{state} == ENTITY_NAME_STATE) {
5107        if (length $self->{kwd} < 30 and        if ((0x0041 <= $self->{nc} and # a
5108            ## NOTE: Some number greater than the maximum length of entity name             $self->{nc} <= 0x005A) or # x
5109            ((0x0041 <= $self->{nc} and # a            (0x0061 <= $self->{nc} and # a
5110              $self->{nc} <= 0x005A) or # x             $self->{nc} <= 0x007A) or # z
5111             (0x0061 <= $self->{nc} and # a            (0x0030 <= $self->{nc} and # 0
5112              $self->{nc} <= 0x007A) or # z             $self->{nc} <= 0x0039) or # 9
5113             (0x0030 <= $self->{nc} and # 0            $self->{nc} == 0x003B or # ;
5114              $self->{nc} <= 0x0039) or # 9            ($self->{is_xml} and
5115             $self->{nc} == 0x003B)) { # ;             not ($is_space->{$self->{nc}} or
5116                    {
5117                      0x003C => 1, 0x0026 => 1, -1 => 1, # <, &
5118                      $self->{entity_add} => 1,
5119                    }->{$self->{nc}}))) {
5120          our $EntityChar;          our $EntityChar;
5121          $self->{kwd} .= chr $self->{nc};          $self->{kwd} .= chr $self->{nc};
5122          if (defined $EntityChar->{$self->{kwd}}) {          if (defined $EntityChar->{$self->{kwd}} or
5123                $self->{ge}->{$self->{kwd}}) {
5124            if ($self->{nc} == 0x003B) { # ;            if ($self->{nc} == 0x003B) { # ;
5125                            if (defined $self->{ge}->{$self->{kwd}}) {
5126              $self->{entity__value} = $EntityChar->{$self->{kwd}};                if ($self->{ge}->{$self->{kwd}}->{only_text}) {
5127                    
5128                    $self->{entity__value} = $self->{ge}->{$self->{kwd}}->{value};
5129                  } else {
5130                    if (defined $self->{ge}->{$self->{kwd}}->{notation}) {
5131                      
5132                      $self->{parse_error}->(level => $self->{level}->{must}, type => 'unparsed entity', ## TODO: type
5133                                      value => $self->{kwd});
5134                    } else {
5135                      
5136                    }
5137                    $self->{entity__value} = '&' . $self->{kwd}; ## TODO: expand
5138                  }
5139                } else {
5140                  if ($self->{is_xml}) {
5141                    
5142                    $self->{parse_error}->(level => $self->{level}->{must}, type => 'entity not declared', ## TODO: type
5143                                    value => $self->{kwd},
5144                                    level => {
5145                                              'amp;' => $self->{level}->{warn},
5146                                              'quot;' => $self->{level}->{warn},
5147                                              'lt;' => $self->{level}->{warn},
5148                                              'gt;' => $self->{level}->{warn},
5149                                              'apos;' => $self->{level}->{warn},
5150                                             }->{$self->{kwd}} ||
5151                                             $self->{level}->{must});
5152                  } else {
5153                    
5154                  }
5155                  $self->{entity__value} = $EntityChar->{$self->{kwd}};
5156                }
5157              $self->{entity__match} = 1;              $self->{entity__match} = 1;
5158                            
5159      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
# Line 5400  sub _get_next_token ($) { Line 5549  sub _get_next_token ($) {
5549          ## XML5: Not defined yet.          ## XML5: Not defined yet.
5550    
5551          ## TODO:          ## TODO:
5552    
5553            if (not $self->{stop_processing} and
5554                not $self->{document}->xml_standalone) {
5555              $self->{parse_error}->(level => $self->{level}->{must}, type => 'stop processing', ## TODO: type
5556                              level => $self->{level}->{info});
5557              $self->{stop_processing} = 1;
5558            }
5559    
5560                    
5561      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
5562        $self->{line_prev} = $self->{line};        $self->{line_prev} = $self->{line};
# Line 5834  sub _get_next_token ($) { Line 5991  sub _get_next_token ($) {
5991          }          }
5992          $self->{ct} = {type => ELEMENT_TOKEN, name => '',          $self->{ct} = {type => ELEMENT_TOKEN, name => '',
5993                         line => $self->{line_prev},                         line => $self->{line_prev},
5994                         column => $self->{column_prev} - 6};                         column => $self->{column_prev} - 7};
5995          $self->{state} = DOCTYPE_MD_STATE;          $self->{state} = DOCTYPE_MD_STATE;
5996                    
5997      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
# Line 5902  sub _get_next_token ($) { Line 6059  sub _get_next_token ($) {
6059          $self->{ct} = {type => ATTLIST_TOKEN, name => '',          $self->{ct} = {type => ATTLIST_TOKEN, name => '',
6060                         attrdefs => [],                         attrdefs => [],
6061                         line => $self->{line_prev},                         line => $self->{line_prev},
6062                         column => $self->{column_prev} - 6};                         column => $self->{column_prev} - 7};
6063          $self->{state} = DOCTYPE_MD_STATE;          $self->{state} = DOCTYPE_MD_STATE;
6064                    
6065      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
# Line 5971  sub _get_next_token ($) { Line 6128  sub _get_next_token ($) {
6128          }          }
6129          $self->{ct} = {type => NOTATION_TOKEN, name => '',          $self->{ct} = {type => NOTATION_TOKEN, name => '',
6130                         line => $self->{line_prev},                         line => $self->{line_prev},
6131                         column => $self->{column_prev} - 6};                         column => $self->{column_prev} - 8};
6132          $self->{state} = DOCTYPE_MD_STATE;          $self->{state} = DOCTYPE_MD_STATE;
6133                    
6134      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
# Line 6183  sub _get_next_token ($) { Line 6340  sub _get_next_token ($) {
6340          if ($self->{ct}->{type} == ATTLIST_TOKEN) {          if ($self->{ct}->{type} == ATTLIST_TOKEN) {
6341            $self->{state} = DOCTYPE_ATTLIST_NAME_AFTER_STATE;            $self->{state} = DOCTYPE_ATTLIST_NAME_AFTER_STATE;
6342          } elsif ($self->{ct}->{type} == ELEMENT_TOKEN) {          } elsif ($self->{ct}->{type} == ELEMENT_TOKEN) {
6343            ## TODO: ...            $self->{state} = AFTER_ELEMENT_NAME_STATE;
           $self->{state} = DOCTYPE_ATTLIST_NAME_AFTER_STATE;  
6344          } else { # ENTITY/NOTATION          } else { # ENTITY/NOTATION
6345            $self->{state} = AFTER_DOCTYPE_NAME_STATE;            $self->{state} = AFTER_DOCTYPE_NAME_STATE;
6346          }          }
# Line 7667  sub _get_next_token ($) { Line 7823  sub _get_next_token ($) {
7823        }        }
7824      } elsif ($self->{state} == NOTATION_NAME_STATE) {      } elsif ($self->{state} == NOTATION_NAME_STATE) {
7825        if ($is_space->{$self->{nc}}) {        if ($is_space->{$self->{nc}}) {
7826          $self->{state} = AFTER_NOTATION_NAME_STATE;          $self->{state} = AFTER_MD_DEF_STATE;
7827                    
7828      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
7829        $self->{line_prev} = $self->{line};        $self->{line_prev} = $self->{line};
# Line 7729  sub _get_next_token ($) { Line 7885  sub _get_next_token ($) {
7885        }        }
7886      } elsif ($self->{state} == DOCTYPE_ENTITY_VALUE_DOUBLE_QUOTED_STATE) {      } elsif ($self->{state} == DOCTYPE_ENTITY_VALUE_DOUBLE_QUOTED_STATE) {
7887        if ($self->{nc} == 0x0022) { # "        if ($self->{nc} == 0x0022) { # "
7888          $self->{state} = AFTER_NOTATION_NAME_STATE;          $self->{state} = AFTER_MD_DEF_STATE;
7889                    
7890      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
7891        $self->{line_prev} = $self->{line};        $self->{line_prev} = $self->{line};
# Line 7782  sub _get_next_token ($) { Line 7938  sub _get_next_token ($) {
7938        }        }
7939      } elsif ($self->{state} == DOCTYPE_ENTITY_VALUE_SINGLE_QUOTED_STATE) {      } elsif ($self->{state} == DOCTYPE_ENTITY_VALUE_SINGLE_QUOTED_STATE) {
7940        if ($self->{nc} == 0x0027) { # '        if ($self->{nc} == 0x0027) { # '
7941          $self->{state} = AFTER_NOTATION_NAME_STATE;          $self->{state} = AFTER_MD_DEF_STATE;
7942                    
7943      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
7944        $self->{line_prev} = $self->{line};        $self->{line_prev} = $self->{line};
# Line 7834  sub _get_next_token ($) { Line 7990  sub _get_next_token ($) {
7990          redo A;          redo A;
7991        }        }
7992      } elsif ($self->{state} == ENTITY_VALUE_ENTITY_STATE) {      } elsif ($self->{state} == ENTITY_VALUE_ENTITY_STATE) {
       ## TODO: XMLize  
   
7993        if ($is_space->{$self->{nc}} or        if ($is_space->{$self->{nc}} or
7994            {            {
7995              0x003C => 1, 0x0026 => 1, -1 => 1, # <, &              0x003C => 1, 0x0026 => 1, -1 => 1, # <, &
7996              $self->{entity_add} => 1,              $self->{entity_add} => 1,
7997            }->{$self->{nc}}) {            }->{$self->{nc}}) {
7998            $self->{parse_error}->(level => $self->{level}->{must}, type => 'bare ero',
7999                            line => $self->{line_prev},
8000                            column => $self->{column_prev}
8001                                + ($self->{nc} == -1 ? 1 : 0));
8002          ## Don't consume          ## Don't consume
         ## No error  
8003          ## Return nothing.          ## Return nothing.
8004          #          #
8005        } elsif ($self->{nc} == 0x0023) { # #        } elsif ($self->{nc} == 0x0023) { # #
# Line 7861  sub _get_next_token ($) { Line 8018  sub _get_next_token ($) {
8018      }      }
8019        
8020          redo A;          redo A;
       } elsif ((0x0041 <= $self->{nc} and  
                 $self->{nc} <= 0x005A) or # A..Z  
                (0x0061 <= $self->{nc} and  
                 $self->{nc} <= 0x007A)) { # a..z  
         #  
8021        } else {        } else {
         $self->{parse_error}->(level => $self->{level}->{must}, type => 'bare ero');  
         ## Return nothing.  
8022          #          #
8023        }        }
8024    
# Line 7876  sub _get_next_token ($) { Line 8026  sub _get_next_token ($) {
8026        $self->{state} = $self->{prev_state};        $self->{state} = $self->{prev_state};
8027        ## Reconsume.        ## Reconsume.
8028        redo A;        redo A;
8029      } elsif ($self->{state} == AFTER_NOTATION_NAME_STATE) {      } elsif ($self->{state} == AFTER_ELEMENT_NAME_STATE) {
8030        if ($is_space->{$self->{nc}}) {        if ($is_space->{$self->{nc}}) {
8031            $self->{state} = BEFORE_ELEMENT_CONTENT_STATE;
8032            
8033        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8034          $self->{line_prev} = $self->{line};
8035          $self->{column_prev} = $self->{column};
8036          $self->{column}++;
8037          $self->{nc}
8038              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8039        } else {
8040          $self->{set_nc}->($self);
8041        }
8042      
8043            redo A;
8044          } elsif ($self->{nc} == 0x0028) { # (
8045            $self->{state} = AFTER_CM_GROUP_OPEN_STATE;
8046            $self->{ct}->{content} = ['('];
8047            $self->{group_depth} = 1;
8048            
8049        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8050          $self->{line_prev} = $self->{line};
8051          $self->{column_prev} = $self->{column};
8052          $self->{column}++;
8053          $self->{nc}
8054              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8055        } else {
8056          $self->{set_nc}->($self);
8057        }
8058      
8059            redo A;
8060          } elsif ($self->{nc} == 0x003E) { # >
8061            $self->{parse_error}->(level => $self->{level}->{must}, type => 'no md def'); ## TODO: type
8062            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8063            
8064        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8065          $self->{line_prev} = $self->{line};
8066          $self->{column_prev} = $self->{column};
8067          $self->{column}++;
8068          $self->{nc}
8069              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8070        } else {
8071          $self->{set_nc}->($self);
8072        }
8073      
8074            return  ($self->{ct}); # ELEMENT
8075            redo A;
8076          } elsif ($self->{nc} == -1) {
8077            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type
8078            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8079            
8080        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8081          $self->{line_prev} = $self->{line};
8082          $self->{column_prev} = $self->{column};
8083          $self->{column}++;
8084          $self->{nc}
8085              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8086        } else {
8087          $self->{set_nc}->($self);
8088        }
8089      
8090            return  ($self->{ct}); # ELEMENT
8091            redo A;
8092          } else {
8093            $self->{ct}->{content} = [chr $self->{nc}];
8094            $self->{state} = CONTENT_KEYWORD_STATE;
8095            
8096        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8097          $self->{line_prev} = $self->{line};
8098          $self->{column_prev} = $self->{column};
8099          $self->{column}++;
8100          $self->{nc}
8101              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8102        } else {
8103          $self->{set_nc}->($self);
8104        }
8105      
8106            redo A;
8107          }
8108        } elsif ($self->{state} == CONTENT_KEYWORD_STATE) {
8109          if ($is_space->{$self->{nc}}) {
8110            $self->{state} = AFTER_MD_DEF_STATE;
8111            
8112        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8113          $self->{line_prev} = $self->{line};
8114          $self->{column_prev} = $self->{column};
8115          $self->{column}++;
8116          $self->{nc}
8117              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8118        } else {
8119          $self->{set_nc}->($self);
8120        }
8121      
8122            redo A;
8123          } elsif ($self->{nc} == 0x003E) { # >
8124            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8125            
8126        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8127          $self->{line_prev} = $self->{line};
8128          $self->{column_prev} = $self->{column};
8129          $self->{column}++;
8130          $self->{nc}
8131              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8132        } else {
8133          $self->{set_nc}->($self);
8134        }
8135      
8136            return  ($self->{ct}); # ELEMENT
8137            redo A;
8138          } elsif ($self->{nc} == -1) {
8139            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type
8140            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8141            
8142        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8143          $self->{line_prev} = $self->{line};
8144          $self->{column_prev} = $self->{column};
8145          $self->{column}++;
8146          $self->{nc}
8147              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8148        } else {
8149          $self->{set_nc}->($self);
8150        }
8151      
8152            return  ($self->{ct}); # ELEMENT
8153            redo A;
8154          } else {
8155            $self->{ct}->{content}->[-1] .= chr $self->{nc}; # ELEMENT
8156            ## Stay in the state.
8157            
8158        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8159          $self->{line_prev} = $self->{line};
8160          $self->{column_prev} = $self->{column};
8161          $self->{column}++;
8162          $self->{nc}
8163              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8164        } else {
8165          $self->{set_nc}->($self);
8166        }
8167      
8168            redo A;
8169          }
8170        } elsif ($self->{state} == AFTER_CM_GROUP_OPEN_STATE) {
8171          if ($is_space->{$self->{nc}}) {
8172            ## Stay in the state.
8173            
8174        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8175          $self->{line_prev} = $self->{line};
8176          $self->{column_prev} = $self->{column};
8177          $self->{column}++;
8178          $self->{nc}
8179              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8180        } else {
8181          $self->{set_nc}->($self);
8182        }
8183      
8184            redo A;
8185          } elsif ($self->{nc} == 0x0028) { # (
8186            $self->{group_depth}++;
8187            push @{$self->{ct}->{content}}, chr $self->{nc};
8188            ## Stay in the state.
8189            
8190        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8191          $self->{line_prev} = $self->{line};
8192          $self->{column_prev} = $self->{column};
8193          $self->{column}++;
8194          $self->{nc}
8195              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8196        } else {
8197          $self->{set_nc}->($self);
8198        }
8199      
8200            redo A;
8201          } elsif ($self->{nc} == 0x007C or # |
8202                   $self->{nc} == 0x002C) { # ,
8203            $self->{parse_error}->(level => $self->{level}->{must}, type => 'empty element name'); ## TODO: type
8204          ## Stay in the state.          ## Stay in the state.
8205                    
8206      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
# Line 7891  sub _get_next_token ($) { Line 8214  sub _get_next_token ($) {
8214      }      }
8215        
8216          redo A;          redo A;
8217          } elsif ($self->{nc} == 0x0029) { # )
8218            $self->{parse_error}->(level => $self->{level}->{must}, type => 'empty element name'); ## TODO: type
8219            push @{$self->{ct}->{content}}, chr $self->{nc};
8220            $self->{group_depth}--;
8221            $self->{state} = AFTER_CM_GROUP_CLOSE_STATE;
8222            
8223        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8224          $self->{line_prev} = $self->{line};
8225          $self->{column_prev} = $self->{column};
8226          $self->{column}++;
8227          $self->{nc}
8228              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8229        } else {
8230          $self->{set_nc}->($self);
8231        }
8232      
8233            redo A;
8234        } elsif ($self->{nc} == 0x003E) { # >        } elsif ($self->{nc} == 0x003E) { # >
8235            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed cm group'); ## TODO: type
8236            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8237          $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;          $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8238                    
8239      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
# Line 7904  sub _get_next_token ($) { Line 8246  sub _get_next_token ($) {
8246        $self->{set_nc}->($self);        $self->{set_nc}->($self);
8247      }      }
8248        
8249          return  ($self->{ct}); # ENTITY          return  ($self->{ct}); # ELEMENT
8250          redo A;          redo A;
8251        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
8252          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type          $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type
8253            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8254          $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;          $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8255                    
8256      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {      if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
# Line 7920  sub _get_next_token ($) { Line 8263  sub _get_next_token ($) {
8263        $self->{set_nc}->($self);        $self->{set_nc}->($self);
8264      }      }
8265        
8266          return  ($self->{ct}); # ENTITY          return  ($self->{ct}); # ELEMENT
8267            redo A;
8268          } else {
8269            push @{$self->{ct}->{content}}, chr $self->{nc};
8270            $self->{state} = CM_ELEMENT_NAME_STATE;
8271            
8272        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8273          $self->{line_prev} = $self->{line};
8274          $self->{column_prev} = $self->{column};
8275          $self->{column}++;
8276          $self->{nc}
8277              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8278        } else {
8279          $self->{set_nc}->($self);
8280        }
8281      
8282            redo A;
8283          }
8284        } elsif ($self->{state} == CM_ELEMENT_NAME_STATE) {
8285          if ($is_space->{$self->{nc}}) {
8286            $self->{state} = AFTER_CM_ELEMENT_NAME_STATE;
8287            
8288        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8289          $self->{line_prev} = $self->{line};
8290          $self->{column_prev} = $self->{column};
8291          $self->{column}++;
8292          $self->{nc}
8293              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8294        } else {
8295          $self->{set_nc}->($self);
8296        }
8297      
8298            redo A;
8299          } elsif ($self->{nc} == 0x002A or # *
8300                   $self->{nc} == 0x002B or # +
8301                   $self->{nc} == 0x003F) { # ?
8302            push @{$self->{ct}->{content}}, chr $self->{nc};
8303            $self->{state} = AFTER_CM_ELEMENT_NAME_STATE;
8304            
8305        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8306          $self->{line_prev} = $self->{line};
8307          $self->{column_prev} = $self->{column};
8308          $self->{column}++;
8309          $self->{nc}
8310              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8311        } else {
8312          $self->{set_nc}->($self);
8313        }
8314      
8315            redo A;
8316          } elsif ($self->{nc} == 0x007C or # |
8317                   $self->{nc} == 0x002C) { # ,
8318            push @{$self->{ct}->{content}}, $self->{nc} == 0x007C ? ' | ' : ', ';
8319            $self->{state} = AFTER_CM_GROUP_OPEN_STATE;
8320            
8321        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8322          $self->{line_prev} = $self->{line};
8323          $self->{column_prev} = $self->{column};
8324          $self->{column}++;
8325          $self->{nc}
8326              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8327        } else {
8328          $self->{set_nc}->($self);
8329        }
8330      
8331            redo A;
8332          } elsif ($self->{nc} == 0x0029) { # )
8333            $self->{group_depth}--;
8334            push @{$self->{ct}->{content}}, chr $self->{nc};
8335            $self->{state} = AFTER_CM_GROUP_CLOSE_STATE;
8336            
8337        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8338          $self->{line_prev} = $self->{line};
8339          $self->{column_prev} = $self->{column};
8340          $self->{column}++;
8341          $self->{nc}
8342              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8343        } else {
8344          $self->{set_nc}->($self);
8345        }
8346      
8347            redo A;
8348          } elsif ($self->{nc} == 0x003E) { # >
8349            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed cm group'); ## TODO: type
8350            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8351            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8352            
8353        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8354          $self->{line_prev} = $self->{line};
8355          $self->{column_prev} = $self->{column};
8356          $self->{column}++;
8357          $self->{nc}
8358              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8359        } else {
8360          $self->{set_nc}->($self);
8361        }
8362      
8363            return  ($self->{ct}); # ELEMENT
8364            redo A;
8365          } elsif ($self->{nc} == -1) {
8366            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type
8367            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8368            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8369            
8370        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8371          $self->{line_prev} = $self->{line};
8372          $self->{column_prev} = $self->{column};
8373          $self->{column}++;
8374          $self->{nc}
8375              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8376        } else {
8377          $self->{set_nc}->($self);
8378        }
8379      
8380            return  ($self->{ct}); # ELEMENT
8381            redo A;
8382          } else {
8383            $self->{ct}->{content}->[-1] .= chr $self->{nc};
8384            ## Stay in the state.
8385            
8386        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8387          $self->{line_prev} = $self->{line};
8388          $self->{column_prev} = $self->{column};
8389          $self->{column}++;
8390          $self->{nc}
8391              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8392        } else {
8393          $self->{set_nc}->($self);
8394        }
8395      
8396            redo A;
8397          }
8398        } elsif ($self->{state} == AFTER_CM_ELEMENT_NAME_STATE) {
8399          if ($is_space->{$self->{nc}}) {
8400            ## Stay in the state.
8401            
8402        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8403          $self->{line_prev} = $self->{line};
8404          $self->{column_prev} = $self->{column};
8405          $self->{column}++;
8406          $self->{nc}
8407              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8408        } else {
8409          $self->{set_nc}->($self);
8410        }
8411      
8412            redo A;
8413          } elsif ($self->{nc} == 0x007C or # |
8414                   $self->{nc} == 0x002C) { # ,
8415            push @{$self->{ct}->{content}}, $self->{nc} == 0x007C ? ' | ' : ', ';
8416            $self->{state} = AFTER_CM_GROUP_OPEN_STATE;
8417            
8418        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8419          $self->{line_prev} = $self->{line};
8420          $self->{column_prev} = $self->{column};
8421          $self->{column}++;
8422          $self->{nc}
8423              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8424        } else {
8425          $self->{set_nc}->($self);
8426        }
8427      
8428            redo A;
8429          } elsif ($self->{nc} == 0x0029) { # )
8430            $self->{group_depth}--;
8431            push @{$self->{ct}->{content}}, chr $self->{nc};
8432            $self->{state} = AFTER_CM_GROUP_CLOSE_STATE;
8433            
8434        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8435          $self->{line_prev} = $self->{line};
8436          $self->{column_prev} = $self->{column};
8437          $self->{column}++;
8438          $self->{nc}
8439              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8440        } else {
8441          $self->{set_nc}->($self);
8442        }
8443      
8444            redo A;
8445          } elsif ($self->{nc} == 0x003E) { # >
8446            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed cm group'); ## TODO: type
8447            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8448            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8449            
8450        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8451          $self->{line_prev} = $self->{line};
8452          $self->{column_prev} = $self->{column};
8453          $self->{column}++;
8454          $self->{nc}
8455              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8456        } else {
8457          $self->{set_nc}->($self);
8458        }
8459      
8460            return  ($self->{ct}); # ELEMENT
8461            redo A;
8462          } elsif ($self->{nc} == -1) {
8463            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type
8464            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8465            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8466            
8467        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8468          $self->{line_prev} = $self->{line};
8469          $self->{column_prev} = $self->{column};
8470          $self->{column}++;
8471          $self->{nc}
8472              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8473        } else {
8474          $self->{set_nc}->($self);
8475        }
8476      
8477            return  ($self->{ct}); # ELEMENT
8478            redo A;
8479          } else {
8480            $self->{parse_error}->(level => $self->{level}->{must}, type => 'after element name'); ## TODO: type
8481            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8482            $self->{state} = BOGUS_MD_STATE;
8483            
8484        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8485          $self->{line_prev} = $self->{line};
8486          $self->{column_prev} = $self->{column};
8487          $self->{column}++;
8488          $self->{nc}
8489              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8490        } else {
8491          $self->{set_nc}->($self);
8492        }
8493      
8494            redo A;
8495          }
8496        } elsif ($self->{state} == AFTER_CM_GROUP_CLOSE_STATE) {
8497          if ($is_space->{$self->{nc}}) {
8498            if ($self->{group_depth}) {
8499              $self->{state} = AFTER_CM_ELEMENT_NAME_STATE;
8500            } else {
8501              $self->{state} = AFTER_MD_DEF_STATE;
8502            }
8503            
8504        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8505          $self->{line_prev} = $self->{line};
8506          $self->{column_prev} = $self->{column};
8507          $self->{column}++;
8508          $self->{nc}
8509              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8510        } else {
8511          $self->{set_nc}->($self);
8512        }
8513      
8514            redo A;
8515          } elsif ($self->{nc} == 0x002A or # *
8516                   $self->{nc} == 0x002B or # +
8517                   $self->{nc} == 0x003F) { # ?
8518            push @{$self->{ct}->{content}}, chr $self->{nc};
8519            if ($self->{group_depth}) {
8520              $self->{state} = AFTER_CM_ELEMENT_NAME_STATE;
8521            } else {
8522              $self->{state} = AFTER_MD_DEF_STATE;
8523            }
8524            
8525        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8526          $self->{line_prev} = $self->{line};
8527          $self->{column_prev} = $self->{column};
8528          $self->{column}++;
8529          $self->{nc}
8530              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8531        } else {
8532          $self->{set_nc}->($self);
8533        }
8534      
8535            redo A;
8536          } elsif ($self->{nc} == 0x0029) { # )
8537            if ($self->{group_depth}) {
8538              $self->{group_depth}--;
8539              push @{$self->{ct}->{content}}, chr $self->{nc};
8540              ## Stay in the state.
8541              
8542        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8543          $self->{line_prev} = $self->{line};
8544          $self->{column_prev} = $self->{column};
8545          $self->{column}++;
8546          $self->{nc}
8547              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8548        } else {
8549          $self->{set_nc}->($self);
8550        }
8551      
8552              redo A;
8553            } else {
8554              $self->{parse_error}->(level => $self->{level}->{must}, type => 'string after md def'); ## TODO: type
8555              $self->{state} = BOGUS_MD_STATE;
8556              ## Reconsume.
8557              redo A;
8558            }
8559          } elsif ($self->{nc} == 0x003E) { # >
8560            if ($self->{group_depth}) {
8561              $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed cm group'); ## TODO: type
8562              push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8563            }
8564            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8565            
8566        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8567          $self->{line_prev} = $self->{line};
8568          $self->{column_prev} = $self->{column};
8569          $self->{column}++;
8570          $self->{nc}
8571              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8572        } else {
8573          $self->{set_nc}->($self);
8574        }
8575      
8576            return  ($self->{ct}); # ELEMENT
8577            redo A;
8578          } elsif ($self->{nc} == -1) {
8579            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type
8580            push @{$self->{ct}->{content}}, (')') x $self->{group_depth};
8581            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8582            
8583        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8584          $self->{line_prev} = $self->{line};
8585          $self->{column_prev} = $self->{column};
8586          $self->{column}++;
8587          $self->{nc}
8588              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8589        } else {
8590          $self->{set_nc}->($self);
8591        }
8592      
8593            return  ($self->{ct}); # ELEMENT
8594            redo A;
8595          } else {
8596            if ($self->{group_depth}) {
8597              $self->{state} = AFTER_CM_ELEMENT_NAME_STATE;
8598            } else {
8599              $self->{parse_error}->(level => $self->{level}->{must}, type => 'string after md def'); ## TODO: type
8600              $self->{state} = BOGUS_MD_STATE;
8601            }
8602            ## Reconsume.
8603            redo A;
8604          }
8605        } elsif ($self->{state} == AFTER_MD_DEF_STATE) {
8606          if ($is_space->{$self->{nc}}) {
8607            ## Stay in the state.
8608            
8609        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8610          $self->{line_prev} = $self->{line};
8611          $self->{column_prev} = $self->{column};
8612          $self->{column}++;
8613          $self->{nc}
8614              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8615        } else {
8616          $self->{set_nc}->($self);
8617        }
8618      
8619            redo A;
8620          } elsif ($self->{nc} == 0x003E) { # >
8621            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8622            
8623        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8624          $self->{line_prev} = $self->{line};
8625          $self->{column_prev} = $self->{column};
8626          $self->{column}++;
8627          $self->{nc}
8628              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8629        } else {
8630          $self->{set_nc}->($self);
8631        }
8632      
8633            return  ($self->{ct}); # ENTITY/ELEMENT
8634            redo A;
8635          } elsif ($self->{nc} == -1) {
8636            $self->{parse_error}->(level => $self->{level}->{must}, type => 'unclosed md'); ## TODO: type
8637            $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
8638            
8639        if ($self->{char_buffer_pos} < length $self->{char_buffer}) {
8640          $self->{line_prev} = $self->{line};
8641          $self->{column_prev} = $self->{column};
8642          $self->{column}++;
8643          $self->{nc}
8644              = ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1);
8645        } else {
8646          $self->{set_nc}->($self);
8647        }
8648      
8649            return  ($self->{ct}); # ENTITY/ELEMENT
8650          redo A;          redo A;
8651        } else {        } else {
8652          $self->{parse_error}->(level => $self->{level}->{must}, type => 'string after notation name'); ## TODO: type          $self->{parse_error}->(level => $self->{level}->{must}, type => 'string after md def'); ## TODO: type
8653          $self->{state} = BOGUS_MD_STATE;          $self->{state} = BOGUS_MD_STATE;
8654          ## Reconsume.          ## Reconsume.
8655          redo A;          redo A;
Legend:
Removed from v.1.19  
changed lines
  Added in v.1.29
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24