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 } |
862 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
863 |
# reconsume |
# reconsume |
864 |
|
|
865 |
!!!emit ($self->{ct}); # start tag or end tag |
## Discard the token. |
866 |
|
#!!!emit ($self->{ct}); # start tag or end tag |
867 |
|
|
868 |
redo A; |
redo A; |
869 |
} elsif ($self->{nc} == 0x002F) { # / |
} elsif ($self->{nc} == 0x002F) { # / |
944 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
945 |
# reconsume |
# reconsume |
946 |
|
|
947 |
!!!emit ($self->{ct}); # start tag or end tag |
## Discard the token. |
948 |
|
#!!!emit ($self->{ct}); # start tag or end tag |
949 |
|
|
950 |
redo A; |
redo A; |
951 |
} else { |
} else { |
952 |
if ({ |
if ({ |
953 |
0x0022 => 1, # " |
0x0022 => 1, # " |
954 |
0x0027 => 1, # ' |
0x0027 => 1, # ' |
955 |
|
0x003C => 1, # < |
956 |
0x003D => 1, # = |
0x003D => 1, # = |
957 |
}->{$self->{nc}}) { |
}->{$self->{nc}}) { |
958 |
!!!cp (55); |
!!!cp (55); |
1071 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1072 |
# reconsume |
# reconsume |
1073 |
|
|
1074 |
!!!emit ($self->{ct}); # start tag or end tag |
## Discard the token. |
1075 |
|
#!!!emit ($self->{ct}); # start tag or end tag |
1076 |
|
|
1077 |
redo A; |
redo A; |
1078 |
} else { |
} else { |
1079 |
if ($self->{nc} == 0x0022 or # " |
if ({ |
1080 |
$self->{nc} == 0x0027) { # ' |
0x0022 => 1, # " |
1081 |
|
0x0027 => 1, # ' |
1082 |
|
0x003C => 1, # < |
1083 |
|
}->{$self->{nc}}) { |
1084 |
!!!cp (69); |
!!!cp (69); |
1085 |
## XML5: Not a parse error. |
## XML5: Not a parse error. |
1086 |
!!!parse-error (type => 'bad attribute name'); |
!!!parse-error (type => 'bad attribute name'); |
1179 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1180 |
# reconsume |
# reconsume |
1181 |
|
|
1182 |
!!!emit ($self->{ct}); # start tag or end tag |
## Discard the token. |
1183 |
|
#!!!emit ($self->{ct}); # start tag or end tag |
1184 |
|
|
1185 |
redo A; |
redo A; |
1186 |
} else { |
} else { |
1192 |
!!!cp (78.2); |
!!!cp (78.2); |
1193 |
} |
} |
1194 |
|
|
1195 |
if ($self->{nc} == 0x0022 or # " |
if ({ |
1196 |
$self->{nc} == 0x0027) { # ' |
0x0022 => 1, # " |
1197 |
|
0x0027 => 1, # ' |
1198 |
|
0x003C => 1, # < |
1199 |
|
}->{$self->{nc}}) { |
1200 |
!!!cp (78); |
!!!cp (78); |
1201 |
## XML5: Not a parse error. |
## XML5: Not a parse error. |
1202 |
!!!parse-error (type => 'bad attribute name'); |
!!!parse-error (type => 'bad attribute name'); |
1279 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1280 |
## reconsume |
## reconsume |
1281 |
|
|
1282 |
!!!emit ($self->{ct}); # start tag or end tag |
## Discard the token. |
1283 |
|
#!!!emit ($self->{ct}); # start tag or end tag |
1284 |
|
|
1285 |
redo A; |
redo A; |
1286 |
} else { |
} else { |
1361 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1362 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1363 |
## reconsume |
## reconsume |
1364 |
!!!emit ($self->{ct}); # end tag |
|
1365 |
|
## Discard the token. |
1366 |
|
#!!!emit ($self->{ct}); # end tag |
1367 |
|
|
1368 |
redo A; |
redo A; |
1369 |
} elsif ($self->{ct}->{type} == ATTLIST_TOKEN) { |
} elsif ($self->{ct}->{type} == ATTLIST_TOKEN) { |
1370 |
## XML5: No parse error above; not defined yet. |
## XML5: No parse error above; not defined yet. |
1371 |
push @{$self->{ct}->{attrdefs}}, $self->{ca}; |
push @{$self->{ct}->{attrdefs}}, $self->{ca}; |
1372 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1373 |
## Reconsume. |
## Reconsume. |
1374 |
!!!emit ($self->{ct}); # ATTLIST |
|
1375 |
|
## Discard the token. |
1376 |
|
#!!!emit ($self->{ct}); # ATTLIST |
1377 |
|
|
1378 |
redo A; |
redo A; |
1379 |
} else { |
} else { |
1380 |
die "$0: $self->{ct}->{type}: Unknown token type"; |
die "$0: $self->{ct}->{type}: Unknown token type"; |
1443 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1444 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1445 |
## reconsume |
## reconsume |
1446 |
!!!emit ($self->{ct}); # start tag |
|
1447 |
|
## Discard the token. |
1448 |
|
#!!!emit ($self->{ct}); # start tag |
1449 |
|
|
1450 |
redo A; |
redo A; |
1451 |
} elsif ($self->{ct}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{ct}->{type} == END_TAG_TOKEN) { |
1452 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
1461 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1462 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1463 |
## reconsume |
## reconsume |
1464 |
!!!emit ($self->{ct}); # end tag |
|
1465 |
|
## Discard the token. |
1466 |
|
#!!!emit ($self->{ct}); # end tag |
1467 |
|
|
1468 |
redo A; |
redo A; |
1469 |
} elsif ($self->{ct}->{type} == ATTLIST_TOKEN) { |
} elsif ($self->{ct}->{type} == ATTLIST_TOKEN) { |
1470 |
## XML5: No parse error above; not defined yet. |
## XML5: No parse error above; not defined yet. |
1471 |
push @{$self->{ct}->{attrdefs}}, $self->{ca}; |
push @{$self->{ct}->{attrdefs}}, $self->{ca}; |
1472 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1473 |
## Reconsume. |
## Reconsume. |
1474 |
!!!emit ($self->{ct}); # ATTLIST |
|
1475 |
|
## Discard the token. |
1476 |
|
#!!!emit ($self->{ct}); # ATTLIST |
1477 |
|
|
1478 |
redo A; |
redo A; |
1479 |
} else { |
} else { |
1480 |
die "$0: $self->{ct}->{type}: Unknown token type"; |
die "$0: $self->{ct}->{type}: Unknown token type"; |
1569 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1570 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1571 |
## reconsume |
## reconsume |
1572 |
!!!emit ($self->{ct}); # start tag |
|
1573 |
|
## Discard the token. |
1574 |
|
#!!!emit ($self->{ct}); # start tag |
1575 |
|
|
1576 |
redo A; |
redo A; |
1577 |
} elsif ($self->{ct}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{ct}->{type} == END_TAG_TOKEN) { |
1578 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
1588 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1589 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1590 |
## reconsume |
## reconsume |
1591 |
!!!emit ($self->{ct}); # end tag |
|
1592 |
|
## Discard the token. |
1593 |
|
#!!!emit ($self->{ct}); # end tag |
1594 |
|
|
1595 |
redo A; |
redo A; |
1596 |
} elsif ($self->{ct}->{type} == ATTLIST_TOKEN) { |
} elsif ($self->{ct}->{type} == ATTLIST_TOKEN) { |
1597 |
!!!parse-error (type => 'unclosed md'); ## TODO: type |
!!!parse-error (type => 'unclosed md'); ## TODO: type |
1598 |
push @{$self->{ct}->{attrdefs}}, $self->{ca}; |
push @{$self->{ct}->{attrdefs}}, $self->{ca}; |
1599 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1600 |
## Reconsume. |
## Reconsume. |
1601 |
!!!emit ($self->{ct}); # ATTLIST |
|
1602 |
|
## Discard the token. |
1603 |
|
#!!!emit ($self->{ct}); # ATTLIST |
1604 |
|
|
1605 |
redo A; |
redo A; |
1606 |
} else { |
} else { |
1607 |
die "$0: $self->{ct}->{type}: Unknown token type"; |
die "$0: $self->{ct}->{type}: Unknown token type"; |
1681 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1682 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1683 |
## Reconsume. |
## Reconsume. |
1684 |
!!!emit ($self->{ct}); # start tag or end tag |
|
1685 |
|
## Discard the token. |
1686 |
|
#!!!emit ($self->{ct}); # start tag or end tag |
1687 |
|
|
1688 |
redo A; |
redo A; |
1689 |
} else { |
} else { |
1690 |
!!!cp ('124.1'); |
!!!cp ('124.1'); |
1741 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
1742 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
1743 |
## Reconsume. |
## Reconsume. |
1744 |
!!!emit ($self->{ct}); # start tag or end tag |
|
1745 |
|
## Discard the token. |
1746 |
|
#!!!emit ($self->{ct}); # start tag or end tag |
1747 |
|
|
1748 |
redo A; |
redo A; |
1749 |
} else { |
} else { |
1750 |
!!!cp ('124.4'); |
!!!cp ('124.4'); |
2119 |
!!!next-input-character; |
!!!next-input-character; |
2120 |
redo A; |
redo A; |
2121 |
} |
} |
2122 |
} elsif ($self->{state} == COMMENT_END_STATE) { |
} elsif ($self->{state} == COMMENT_END_STATE or |
2123 |
|
$self->{state} == COMMENT_END_BANG_STATE) { |
2124 |
## XML5: "Comment end state" and "DOCTYPE comment end state". |
## XML5: "Comment end state" and "DOCTYPE comment end state". |
2125 |
|
## (No comment end bang state.) |
2126 |
|
|
2127 |
if ($self->{nc} == 0x003E) { # > |
if ($self->{nc} == 0x003E) { # > |
2128 |
if ($self->{in_subset}) { |
if ($self->{in_subset}) { |
2139 |
|
|
2140 |
redo A; |
redo A; |
2141 |
} elsif ($self->{nc} == 0x002D) { # - |
} elsif ($self->{nc} == 0x002D) { # - |
2142 |
!!!cp (152); |
if ($self->{state} == COMMENT_END_BANG_STATE) { |
2143 |
## XML5: Not a parse error. |
!!!cp (154.3); |
2144 |
!!!parse-error (type => 'dash in comment', |
$self->{ct}->{data} .= '--!'; # comment |
2145 |
line => $self->{line_prev}, |
$self->{state} = COMMENT_END_DASH_STATE; |
2146 |
column => $self->{column_prev}); |
} else { |
2147 |
$self->{ct}->{data} .= '-'; # comment |
!!!cp (152); |
2148 |
## Stay in the state |
## XML5: Not a parse error. |
2149 |
|
!!!parse-error (type => 'dash in comment', |
2150 |
|
line => $self->{line_prev}, |
2151 |
|
column => $self->{column_prev}); |
2152 |
|
$self->{ct}->{data} .= '-'; # comment |
2153 |
|
## Stay in the state |
2154 |
|
} |
2155 |
|
!!!next-input-character; |
2156 |
|
redo A; |
2157 |
|
} elsif ($self->{state} != COMMENT_END_BANG_STATE and |
2158 |
|
$is_space->{$self->{nc}}) { |
2159 |
|
!!!cp (152.1); |
2160 |
|
!!!parse-error (type => 'comment end space'); # XXX error type |
2161 |
|
$self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment |
2162 |
|
$self->{state} = COMMENT_END_SPACE_STATE; |
2163 |
|
!!!next-input-character; |
2164 |
|
redo A; |
2165 |
|
} elsif ($self->{state} != COMMENT_END_BANG_STATE and |
2166 |
|
$self->{nc} == 0x0021) { # ! |
2167 |
|
!!!cp (152.2); |
2168 |
|
!!!parse-error (type => 'comment end bang'); # XXX error type |
2169 |
|
$self->{state} = COMMENT_END_BANG_STATE; |
2170 |
!!!next-input-character; |
!!!next-input-character; |
2171 |
redo A; |
redo A; |
2172 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
2179 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
2180 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
2181 |
} |
} |
2182 |
## reconsume |
## Reconsume. |
2183 |
|
|
2184 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
2185 |
|
|
2186 |
redo A; |
redo A; |
2187 |
} else { |
} else { |
2188 |
!!!cp (154); |
!!!cp (154); |
2189 |
## XML5: Not a parse error. |
if ($self->{state} == COMMENT_END_BANG_STATE) { |
2190 |
!!!parse-error (type => 'dash in comment', |
$self->{ct}->{data} .= '--!' . chr ($self->{nc}); # comment |
2191 |
line => $self->{line_prev}, |
} else { |
2192 |
column => $self->{column_prev}); |
$self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment |
2193 |
$self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment |
} |
2194 |
$self->{state} = COMMENT_STATE; |
$self->{state} = COMMENT_STATE; |
2195 |
!!!next-input-character; |
!!!next-input-character; |
2196 |
redo A; |
redo A; |
2197 |
} |
} |
2198 |
|
} elsif ($self->{state} == COMMENT_END_SPACE_STATE) { |
2199 |
|
## XML5: Not exist. |
2200 |
|
|
2201 |
|
if ($self->{nc} == 0x003E) { # > |
2202 |
|
if ($self->{in_subset}) { |
2203 |
|
!!!cp (154.4); |
2204 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2205 |
|
} else { |
2206 |
|
!!!cp (154.5); |
2207 |
|
$self->{state} = DATA_STATE; |
2208 |
|
$self->{s_kwd} = ''; |
2209 |
|
} |
2210 |
|
!!!next-input-character; |
2211 |
|
|
2212 |
|
!!!emit ($self->{ct}); # comment |
2213 |
|
|
2214 |
|
redo A; |
2215 |
|
} elsif ($is_space->{$self->{nc}}) { |
2216 |
|
!!!cp (154.6); |
2217 |
|
$self->{ct}->{data} .= chr ($self->{nc}); # comment |
2218 |
|
## Stay in the state. |
2219 |
|
!!!next-input-character; |
2220 |
|
redo A; |
2221 |
|
} elsif ($self->{nc} == -1) { |
2222 |
|
!!!parse-error (type => 'unclosed comment'); |
2223 |
|
if ($self->{in_subset}) { |
2224 |
|
!!!cp (154.7); |
2225 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2226 |
|
} else { |
2227 |
|
!!!cp (154.8); |
2228 |
|
$self->{state} = DATA_STATE; |
2229 |
|
$self->{s_kwd} = ''; |
2230 |
|
} |
2231 |
|
## Reconsume. |
2232 |
|
|
2233 |
|
!!!emit ($self->{ct}); # comment |
2234 |
|
|
2235 |
|
redo A; |
2236 |
|
} else { |
2237 |
|
!!!cp (154.9); |
2238 |
|
$self->{ct}->{data} .= chr ($self->{nc}); # comment |
2239 |
|
$self->{state} = COMMENT_STATE; |
2240 |
|
!!!next-input-character; |
2241 |
|
redo A; |
2242 |
|
} |
2243 |
} elsif ($self->{state} == DOCTYPE_STATE) { |
} elsif ($self->{state} == DOCTYPE_STATE) { |
2244 |
if ($is_space->{$self->{nc}}) { |
if ($is_space->{$self->{nc}}) { |
2245 |
!!!cp (155); |
!!!cp (155); |
2246 |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
2247 |
!!!next-input-character; |
!!!next-input-character; |
2248 |
redo A; |
redo A; |
2249 |
|
} elsif ($self->{nc} == -1) { |
2250 |
|
!!!cp (155.1); |
2251 |
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
2252 |
|
$self->{ct}->{quirks} = 1; |
2253 |
|
|
2254 |
|
$self->{state} = DATA_STATE; |
2255 |
|
## Reconsume. |
2256 |
|
!!!emit ($self->{ct}); # DOCTYPE (quirks) |
2257 |
|
|
2258 |
|
redo A; |
2259 |
} else { |
} else { |
2260 |
!!!cp (156); |
!!!cp (156); |
2261 |
## XML5: Unless EOF, swith to the bogus comment state. |
## XML5: Swith to the bogus comment state. |
2262 |
!!!parse-error (type => 'no space before DOCTYPE name'); |
!!!parse-error (type => 'no space before DOCTYPE name'); |
2263 |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
2264 |
## reconsume |
## reconsume |
2283 |
!!!emit ($self->{ct}); # DOCTYPE (quirks) |
!!!emit ($self->{ct}); # DOCTYPE (quirks) |
2284 |
|
|
2285 |
redo A; |
redo A; |
2286 |
|
} elsif (0x0041 <= $self->{nc} and $self->{nc} <= 0x005A) { # A..Z |
2287 |
|
!!!cp (158.1); |
2288 |
|
$self->{ct}->{name} # DOCTYPE |
2289 |
|
= chr ($self->{nc} + ($self->{is_xml} ? 0 : 0x0020)); |
2290 |
|
delete $self->{ct}->{quirks}; |
2291 |
|
$self->{state} = DOCTYPE_NAME_STATE; |
2292 |
|
!!!next-input-character; |
2293 |
|
redo A; |
2294 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
2295 |
!!!cp (159); |
!!!cp (159); |
2296 |
!!!parse-error (type => 'no DOCTYPE name'); |
!!!parse-error (type => 'no DOCTYPE name'); |
2337 |
!!!emit ($self->{ct}); # DOCTYPE |
!!!emit ($self->{ct}); # DOCTYPE |
2338 |
|
|
2339 |
redo A; |
redo A; |
2340 |
|
} elsif (0x0041 <= $self->{nc} and $self->{nc} <= 0x005A) { # A..Z |
2341 |
|
!!!cp (162.1); |
2342 |
|
$self->{ct}->{name} # DOCTYPE |
2343 |
|
.= chr ($self->{nc} + ($self->{is_xml} ? 0 : 0x0020)); |
2344 |
|
delete $self->{ct}->{quirks}; |
2345 |
|
## Stay in the state. |
2346 |
|
!!!next-input-character; |
2347 |
|
redo A; |
2348 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
2349 |
!!!cp (163); |
!!!cp (163); |
2350 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
2366 |
redo A; |
redo A; |
2367 |
} else { |
} else { |
2368 |
!!!cp (164); |
!!!cp (164); |
2369 |
$self->{ct}->{name} |
$self->{ct}->{name} .= chr ($self->{nc}); # DOCTYPE |
2370 |
.= chr ($self->{nc}); # DOCTYPE |
## Stay in the state. |
|
## Stay in the state |
|
2371 |
!!!next-input-character; |
!!!next-input-character; |
2372 |
redo A; |
redo A; |
2373 |
} |
} |