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

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

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

revision 1.28 by wakaba, Sun Jul 5 04:38:45 2009 UTC revision 1.32 by wakaba, Sat Sep 5 09:57:55 2009 UTC
# Line 105  sub COMMENT_START_STATE () { 14 } Line 105  sub COMMENT_START_STATE () { 14 }
105  sub COMMENT_START_DASH_STATE () { 15 }  sub COMMENT_START_DASH_STATE () { 15 }
106  sub COMMENT_STATE () { 16 }  sub COMMENT_STATE () { 16 }
107  sub COMMENT_END_STATE () { 17 }  sub COMMENT_END_STATE () { 17 }
108    sub COMMENT_END_BANG_STATE () { 102 }
109    sub COMMENT_END_SPACE_STATE () { 103 } ## LAST
110  sub COMMENT_END_DASH_STATE () { 18 }  sub COMMENT_END_DASH_STATE () { 18 }
111  sub BOGUS_COMMENT_STATE () { 19 }  sub BOGUS_COMMENT_STATE () { 19 }
112  sub DOCTYPE_STATE () { 20 }  sub DOCTYPE_STATE () { 20 }
# Line 948  sub _get_next_token ($) { Line 950  sub _get_next_token ($) {
950          if ({          if ({
951               0x0022 => 1, # "               0x0022 => 1, # "
952               0x0027 => 1, # '               0x0027 => 1, # '
953                 0x003C => 1, # <
954               0x003D => 1, # =               0x003D => 1, # =
955              }->{$self->{nc}}) {              }->{$self->{nc}}) {
956            !!!cp (55);            !!!cp (55);
# Line 1070  sub _get_next_token ($) { Line 1073  sub _get_next_token ($) {
1073    
1074          redo A;          redo A;
1075        } else {        } else {
1076          if ($self->{nc} == 0x0022 or # "          if ({
1077              $self->{nc} == 0x0027) { # '               0x0022 => 1, # "
1078                 0x0027 => 1, # '
1079                 0x003C => 1, # <
1080                }->{$self->{nc}}) {
1081            !!!cp (69);            !!!cp (69);
1082            ## XML5: Not a parse error.            ## XML5: Not a parse error.
1083            !!!parse-error (type => 'bad attribute name');            !!!parse-error (type => 'bad attribute name');
# Line 1182  sub _get_next_token ($) { Line 1188  sub _get_next_token ($) {
1188            !!!cp (78.2);            !!!cp (78.2);
1189          }          }
1190    
1191          if ($self->{nc} == 0x0022 or # "          if ({
1192              $self->{nc} == 0x0027) { # '               0x0022 => 1, # "
1193                 0x0027 => 1, # '
1194                 0x003C => 1, # <
1195                }->{$self->{nc}}) {
1196            !!!cp (78);            !!!cp (78);
1197            ## XML5: Not a parse error.            ## XML5: Not a parse error.
1198            !!!parse-error (type => 'bad attribute name');            !!!parse-error (type => 'bad attribute name');
# Line 2075  sub _get_next_token ($) { Line 2084  sub _get_next_token ($) {
2084          !!!next-input-character;          !!!next-input-character;
2085          redo A;          redo A;
2086        }        }
2087      } elsif ($self->{state} == COMMENT_END_STATE) {      } elsif ($self->{state} == COMMENT_END_STATE or
2088                 $self->{state} == COMMENT_END_BANG_STATE) {
2089        ## XML5: "Comment end state" and "DOCTYPE comment end state".        ## XML5: "Comment end state" and "DOCTYPE comment end state".
2090          ## (No comment end bang state.)
2091    
2092        if ($self->{nc} == 0x003E) { # >        if ($self->{nc} == 0x003E) { # >
2093          if ($self->{in_subset}) {          if ($self->{in_subset}) {
# Line 2093  sub _get_next_token ($) { Line 2104  sub _get_next_token ($) {
2104    
2105          redo A;          redo A;
2106        } elsif ($self->{nc} == 0x002D) { # -        } elsif ($self->{nc} == 0x002D) { # -
2107          !!!cp (152);          if ($self->{state} == COMMENT_END_BANG_STATE) {
2108          ## XML5: Not a parse error.            !!!cp (154.3);
2109          !!!parse-error (type => 'dash in comment',            $self->{ct}->{data} .= '--!'; # comment
2110                          line => $self->{line_prev},            $self->{state} = COMMENT_END_DASH_STATE;
2111                          column => $self->{column_prev});          } else {
2112          $self->{ct}->{data} .= '-'; # comment            !!!cp (152);
2113          ## Stay in the state            ## XML5: Not a parse error.
2114              !!!parse-error (type => 'dash in comment',
2115                              line => $self->{line_prev},
2116                              column => $self->{column_prev});
2117              $self->{ct}->{data} .= '-'; # comment
2118              ## Stay in the state
2119            }
2120            !!!next-input-character;
2121            redo A;
2122          } elsif ($self->{state} != COMMENT_END_BANG_STATE and
2123                   $is_space->{$self->{nc}}) {
2124            !!!cp (152.1);
2125            !!!parse-error (type => 'comment end space'); # XXX error type
2126            $self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment
2127            $self->{state} = COMMENT_END_SPACE_STATE;
2128            !!!next-input-character;
2129            redo A;
2130          } elsif ($self->{state} != COMMENT_END_BANG_STATE and
2131                   $self->{nc} == 0x0021) { # !
2132            !!!cp (152.2);
2133            !!!parse-error (type => 'comment end bang'); # XXX error type
2134            $self->{state} = COMMENT_END_BANG_STATE;
2135          !!!next-input-character;          !!!next-input-character;
2136          redo A;          redo A;
2137        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
# Line 2112  sub _get_next_token ($) { Line 2144  sub _get_next_token ($) {
2144            $self->{state} = DATA_STATE;            $self->{state} = DATA_STATE;
2145            $self->{s_kwd} = '';            $self->{s_kwd} = '';
2146          }          }
2147          ## reconsume          ## Reconsume.
2148    
2149          !!!emit ($self->{ct}); # comment          !!!emit ($self->{ct}); # comment
2150    
2151          redo A;          redo A;
2152        } else {        } else {
2153          !!!cp (154);          !!!cp (154);
2154          $self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment          if ($self->{state} == COMMENT_END_BANG_STATE) {
2155              $self->{ct}->{data} .= '--!' . chr ($self->{nc}); # comment
2156            } else {
2157              $self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment
2158            }
2159          $self->{state} = COMMENT_STATE;          $self->{state} = COMMENT_STATE;
2160          !!!next-input-character;          !!!next-input-character;
2161          redo A;          redo A;
2162        }        }
2163        } elsif ($self->{state} == COMMENT_END_SPACE_STATE) {
2164          ## XML5: Not exist.
2165    
2166          if ($self->{nc} == 0x003E) { # >
2167            if ($self->{in_subset}) {
2168              !!!cp (154.4);
2169              $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
2170            } else {
2171              !!!cp (154.5);
2172              $self->{state} = DATA_STATE;
2173              $self->{s_kwd} = '';
2174            }
2175            !!!next-input-character;
2176    
2177            !!!emit ($self->{ct}); # comment
2178    
2179            redo A;
2180          } elsif ($is_space->{$self->{nc}}) {
2181            !!!cp (154.6);
2182            $self->{ct}->{data} .= chr ($self->{nc}); # comment
2183            ## Stay in the state.
2184            !!!next-input-character;
2185            redo A;
2186          } elsif ($self->{nc} == -1) {
2187            !!!parse-error (type => 'unclosed comment');
2188            if ($self->{in_subset}) {
2189              !!!cp (154.7);
2190              $self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE;
2191            } else {
2192              !!!cp (154.8);
2193              $self->{state} = DATA_STATE;
2194              $self->{s_kwd} = '';
2195            }
2196            ## Reconsume.
2197    
2198            !!!emit ($self->{ct}); # comment
2199    
2200            redo A;
2201          } else {
2202            !!!cp (154.9);
2203            $self->{ct}->{data} .= chr ($self->{nc}); # comment
2204            $self->{state} = COMMENT_STATE;
2205            !!!next-input-character;
2206            redo A;
2207          }
2208      } elsif ($self->{state} == DOCTYPE_STATE) {      } elsif ($self->{state} == DOCTYPE_STATE) {
2209        if ($is_space->{$self->{nc}}) {        if ($is_space->{$self->{nc}}) {
2210          !!!cp (155);          !!!cp (155);
# Line 2167  sub _get_next_token ($) { Line 2248  sub _get_next_token ($) {
2248          !!!emit ($self->{ct}); # DOCTYPE (quirks)          !!!emit ($self->{ct}); # DOCTYPE (quirks)
2249    
2250          redo A;          redo A;
2251          } elsif (0x0041 <= $self->{nc} and $self->{nc} <= 0x005A) { # A..Z
2252            !!!cp (158.1);
2253            $self->{ct}->{name} # DOCTYPE
2254                = chr ($self->{nc} + ($self->{is_xml} ? 0 : 0x0020));
2255            delete $self->{ct}->{quirks};
2256            $self->{state} = DOCTYPE_NAME_STATE;
2257            !!!next-input-character;
2258            redo A;
2259        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
2260          !!!cp (159);          !!!cp (159);
2261          !!!parse-error (type => 'no DOCTYPE name');          !!!parse-error (type => 'no DOCTYPE name');
# Line 2213  sub _get_next_token ($) { Line 2302  sub _get_next_token ($) {
2302          !!!emit ($self->{ct}); # DOCTYPE          !!!emit ($self->{ct}); # DOCTYPE
2303    
2304          redo A;          redo A;
2305          } elsif (0x0041 <= $self->{nc} and $self->{nc} <= 0x005A) { # A..Z
2306            !!!cp (162.1);
2307            $self->{ct}->{name} # DOCTYPE
2308                .= chr ($self->{nc} + ($self->{is_xml} ? 0 : 0x0020));
2309            delete $self->{ct}->{quirks};
2310            ## Stay in the state.
2311            !!!next-input-character;
2312            redo A;
2313        } elsif ($self->{nc} == -1) {        } elsif ($self->{nc} == -1) {
2314          !!!cp (163);          !!!cp (163);
2315          !!!parse-error (type => 'unclosed DOCTYPE');          !!!parse-error (type => 'unclosed DOCTYPE');
# Line 2234  sub _get_next_token ($) { Line 2331  sub _get_next_token ($) {
2331          redo A;          redo A;
2332        } else {        } else {
2333          !!!cp (164);          !!!cp (164);
2334          $self->{ct}->{name}          $self->{ct}->{name} .= chr ($self->{nc}); # DOCTYPE
2335            .= chr ($self->{nc}); # DOCTYPE          ## Stay in the state.
         ## Stay in the state  
2336          !!!next-input-character;          !!!next-input-character;
2337          redo A;          redo A;
2338        }        }
Legend:
Removed from v.1.28  
changed lines
  Added in v.1.32
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24