15 |
CHARACTER_TOKEN |
CHARACTER_TOKEN |
16 |
PI_TOKEN |
PI_TOKEN |
17 |
ABORT_TOKEN |
ABORT_TOKEN |
18 |
|
END_OF_DOCTYPE_TOKEN |
19 |
|
ATTLIST_TOKEN |
20 |
|
ELEMENT_TOKEN |
21 |
|
GENERAL_ENTITY_TOKEN |
22 |
|
PARAMETER_ENTITY_TOKEN |
23 |
|
NOTATION_TOKEN |
24 |
); |
); |
25 |
|
|
26 |
our %EXPORT_TAGS = ( |
our %EXPORT_TAGS = ( |
33 |
CHARACTER_TOKEN |
CHARACTER_TOKEN |
34 |
PI_TOKEN |
PI_TOKEN |
35 |
ABORT_TOKEN |
ABORT_TOKEN |
36 |
|
END_OF_DOCTYPE_TOKEN |
37 |
|
ATTLIST_TOKEN |
38 |
|
ELEMENT_TOKEN |
39 |
|
GENERAL_ENTITY_TOKEN |
40 |
|
PARAMETER_ENTITY_TOKEN |
41 |
|
NOTATION_TOKEN |
42 |
)], |
)], |
43 |
); |
); |
44 |
} |
} |
55 |
sub CHARACTER_TOKEN () { 6 } |
sub CHARACTER_TOKEN () { 6 } |
56 |
sub PI_TOKEN () { 7 } ## NOTE: XML only. |
sub PI_TOKEN () { 7 } ## NOTE: XML only. |
57 |
sub ABORT_TOKEN () { 8 } ## NOTE: For internal processing. |
sub ABORT_TOKEN () { 8 } ## NOTE: For internal processing. |
58 |
|
sub END_OF_DOCTYPE_TOKEN () { 9 } ## NOTE: XML only. |
59 |
|
sub ATTLIST_TOKEN () { 10 } ## NOTE: XML only. |
60 |
|
sub ELEMENT_TOKEN () { 11 } ## NOTE: XML only. |
61 |
|
sub GENERAL_ENTITY_TOKEN () { 12 } ## NOTE: XML only. |
62 |
|
sub PARAMETER_ENTITY_TOKEN () { 13 } ## NOTE: XML only. |
63 |
|
sub NOTATION_TOKEN () { 14 } ## NOTE: XML only. |
64 |
|
|
65 |
## XML5: XML5 has "empty tag token". In this implementation, it is |
## XML5: XML5 has "empty tag token". In this implementation, it is |
66 |
## represented as a start tag token with $self->{self_closing} flag |
## represented as a start tag token with $self->{self_closing} flag |
151 |
sub PI_DATA_AFTER_STATE () { 56 } |
sub PI_DATA_AFTER_STATE () { 56 } |
152 |
sub DOCTYPE_INTERNAL_SUBSET_STATE () { 57 } |
sub DOCTYPE_INTERNAL_SUBSET_STATE () { 57 } |
153 |
sub DOCTYPE_INTERNAL_SUBSET_AFTER_STATE () { 58 } |
sub DOCTYPE_INTERNAL_SUBSET_AFTER_STATE () { 58 } |
154 |
|
sub BOGUS_DOCTYPE_INTERNAL_SUBSET_AFTER_STATE () { 59 } |
155 |
|
sub DOCTYPE_TAG_STATE () { 60 } |
156 |
|
sub DOCTYPE_MARKUP_DECLARATION_OPEN_STATE () { 61 } |
157 |
|
sub MD_ATTLIST_STATE () { 62 } |
158 |
|
sub MD_E_STATE () { 63 } |
159 |
|
sub MD_ELEMENT_STATE () { 64 } |
160 |
|
sub MD_ENTITY_STATE () { 65 } |
161 |
|
sub MD_NOTATION_STATE () { 66 } |
162 |
|
sub DOCTYPE_MD_STATE () { 67 } |
163 |
|
sub BEFORE_MD_NAME_STATE () { 68 } |
164 |
|
sub MD_NAME_STATE () { 69 } |
165 |
|
sub DOCTYPE_ENTITY_PARAMETER_BEFORE_STATE () { 70 } |
166 |
|
sub DOCTYPE_ATTLIST_NAME_AFTER_STATE () { 71 } |
167 |
|
|
168 |
## Tree constructor state constants (see Whatpm::HTML for the full |
## Tree constructor state constants (see Whatpm::HTML for the full |
169 |
## list and descriptions) |
## list and descriptions) |
1594 |
redo A; |
redo A; |
1595 |
} |
} |
1596 |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
1597 |
## (only happen if PCDATA state) |
## XML5: "Bogus comment state" and "DOCTYPE bogus comment state". |
1598 |
|
|
1599 |
## NOTE: Unlike spec's "bogus comment state", this implementation |
## NOTE: Unlike spec's "bogus comment state", this implementation |
1600 |
## consumes characters one-by-one basis. |
## consumes characters one-by-one basis. |
1601 |
|
|
1602 |
if ($self->{nc} == 0x003E) { # > |
if ($self->{nc} == 0x003E) { # > |
1603 |
!!!cp (124); |
if ($self->{in_subset}) { |
1604 |
$self->{state} = DATA_STATE; |
!!!cp (123); |
1605 |
$self->{s_kwd} = ''; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1606 |
|
} else { |
1607 |
|
!!!cp (124); |
1608 |
|
$self->{state} = DATA_STATE; |
1609 |
|
$self->{s_kwd} = ''; |
1610 |
|
} |
1611 |
!!!next-input-character; |
!!!next-input-character; |
1612 |
|
|
1613 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1614 |
redo A; |
redo A; |
1615 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
1616 |
!!!cp (125); |
if ($self->{in_subset}) { |
1617 |
$self->{state} = DATA_STATE; |
!!!cp (125.1); |
1618 |
$self->{s_kwd} = ''; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1619 |
|
} else { |
1620 |
|
!!!cp (125); |
1621 |
|
$self->{state} = DATA_STATE; |
1622 |
|
$self->{s_kwd} = ''; |
1623 |
|
} |
1624 |
## reconsume |
## reconsume |
1625 |
|
|
1626 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1637 |
redo A; |
redo A; |
1638 |
} |
} |
1639 |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
1640 |
## (only happen if PCDATA state) |
## XML5: "Markup declaration state". |
1641 |
|
|
1642 |
if ($self->{nc} == 0x002D) { # - |
if ($self->{nc} == 0x002D) { # - |
1643 |
!!!cp (133); |
!!!cp (133); |
1813 |
!!!next-input-character; |
!!!next-input-character; |
1814 |
redo A; |
redo A; |
1815 |
} elsif ($self->{nc} == 0x003E) { # > |
} elsif ($self->{nc} == 0x003E) { # > |
|
!!!cp (138); |
|
1816 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
1817 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
1818 |
$self->{s_kwd} = ''; |
!!!cp (138.1); |
1819 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1820 |
|
} else { |
1821 |
|
!!!cp (138); |
1822 |
|
$self->{state} = DATA_STATE; |
1823 |
|
$self->{s_kwd} = ''; |
1824 |
|
} |
1825 |
!!!next-input-character; |
!!!next-input-character; |
1826 |
|
|
1827 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1828 |
|
|
1829 |
redo A; |
redo A; |
1830 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
|
!!!cp (139); |
|
1831 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
1832 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
1833 |
$self->{s_kwd} = ''; |
!!!cp (139.1); |
1834 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1835 |
|
} else { |
1836 |
|
!!!cp (139); |
1837 |
|
$self->{state} = DATA_STATE; |
1838 |
|
$self->{s_kwd} = ''; |
1839 |
|
} |
1840 |
## reconsume |
## reconsume |
1841 |
|
|
1842 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1857 |
!!!next-input-character; |
!!!next-input-character; |
1858 |
redo A; |
redo A; |
1859 |
} elsif ($self->{nc} == 0x003E) { # > |
} elsif ($self->{nc} == 0x003E) { # > |
|
!!!cp (142); |
|
1860 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
1861 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
1862 |
$self->{s_kwd} = ''; |
!!!cp (142.1); |
1863 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1864 |
|
} else { |
1865 |
|
!!!cp (142); |
1866 |
|
$self->{state} = DATA_STATE; |
1867 |
|
$self->{s_kwd} = ''; |
1868 |
|
} |
1869 |
!!!next-input-character; |
!!!next-input-character; |
1870 |
|
|
1871 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1872 |
|
|
1873 |
redo A; |
redo A; |
1874 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
|
!!!cp (143); |
|
1875 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
1876 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
1877 |
$self->{s_kwd} = ''; |
!!!cp (143.1); |
1878 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1879 |
|
} else { |
1880 |
|
!!!cp (143); |
1881 |
|
$self->{state} = DATA_STATE; |
1882 |
|
$self->{s_kwd} = ''; |
1883 |
|
} |
1884 |
## reconsume |
## reconsume |
1885 |
|
|
1886 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1895 |
redo A; |
redo A; |
1896 |
} |
} |
1897 |
} elsif ($self->{state} == COMMENT_STATE) { |
} elsif ($self->{state} == COMMENT_STATE) { |
1898 |
|
## XML5: "Comment state" and "DOCTYPE comment state". |
1899 |
|
|
1900 |
if ($self->{nc} == 0x002D) { # - |
if ($self->{nc} == 0x002D) { # - |
1901 |
!!!cp (145); |
!!!cp (145); |
1902 |
$self->{state} = COMMENT_END_DASH_STATE; |
$self->{state} = COMMENT_END_DASH_STATE; |
1903 |
!!!next-input-character; |
!!!next-input-character; |
1904 |
redo A; |
redo A; |
1905 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
|
!!!cp (146); |
|
1906 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
1907 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
1908 |
$self->{s_kwd} = ''; |
!!!cp (146.1); |
1909 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1910 |
|
} else { |
1911 |
|
!!!cp (146); |
1912 |
|
$self->{state} = DATA_STATE; |
1913 |
|
$self->{s_kwd} = ''; |
1914 |
|
} |
1915 |
## reconsume |
## reconsume |
1916 |
|
|
1917 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1929 |
redo A; |
redo A; |
1930 |
} |
} |
1931 |
} elsif ($self->{state} == COMMENT_END_DASH_STATE) { |
} elsif ($self->{state} == COMMENT_END_DASH_STATE) { |
1932 |
## XML5: "comment dash state". |
## XML5: "Comment dash state" and "DOCTYPE comment dash state". |
1933 |
|
|
1934 |
if ($self->{nc} == 0x002D) { # - |
if ($self->{nc} == 0x002D) { # - |
1935 |
!!!cp (148); |
!!!cp (148); |
1937 |
!!!next-input-character; |
!!!next-input-character; |
1938 |
redo A; |
redo A; |
1939 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
|
!!!cp (149); |
|
1940 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
1941 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
1942 |
$self->{s_kwd} = ''; |
!!!cp (149.1); |
1943 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1944 |
|
} else { |
1945 |
|
!!!cp (149); |
1946 |
|
$self->{state} = DATA_STATE; |
1947 |
|
$self->{s_kwd} = ''; |
1948 |
|
} |
1949 |
## reconsume |
## reconsume |
1950 |
|
|
1951 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1959 |
redo A; |
redo A; |
1960 |
} |
} |
1961 |
} elsif ($self->{state} == COMMENT_END_STATE) { |
} elsif ($self->{state} == COMMENT_END_STATE) { |
1962 |
|
## XML5: "Comment end state" and "DOCTYPE comment end state". |
1963 |
|
|
1964 |
if ($self->{nc} == 0x003E) { # > |
if ($self->{nc} == 0x003E) { # > |
1965 |
!!!cp (151); |
if ($self->{in_subset}) { |
1966 |
$self->{state} = DATA_STATE; |
!!!cp (151.1); |
1967 |
$self->{s_kwd} = ''; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1968 |
|
} else { |
1969 |
|
!!!cp (151); |
1970 |
|
$self->{state} = DATA_STATE; |
1971 |
|
$self->{s_kwd} = ''; |
1972 |
|
} |
1973 |
!!!next-input-character; |
!!!next-input-character; |
1974 |
|
|
1975 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
1986 |
!!!next-input-character; |
!!!next-input-character; |
1987 |
redo A; |
redo A; |
1988 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
|
!!!cp (153); |
|
1989 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
1990 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
1991 |
$self->{s_kwd} = ''; |
!!!cp (153.1); |
1992 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
1993 |
|
} else { |
1994 |
|
!!!cp (153); |
1995 |
|
$self->{state} = DATA_STATE; |
1996 |
|
$self->{s_kwd} = ''; |
1997 |
|
} |
1998 |
## reconsume |
## reconsume |
1999 |
|
|
2000 |
!!!emit ($self->{ct}); # comment |
!!!emit ($self->{ct}); # comment |
2058 |
!!!cp (159.1); |
!!!cp (159.1); |
2059 |
!!!parse-error (type => 'no DOCTYPE name'); |
!!!parse-error (type => 'no DOCTYPE name'); |
2060 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2061 |
|
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2062 |
|
$self->{in_subset} = 1; |
2063 |
!!!next-input-character; |
!!!next-input-character; |
2064 |
|
!!!emit ($self->{ct}); # DOCTYPE |
2065 |
redo A; |
redo A; |
2066 |
} else { |
} else { |
2067 |
!!!cp (160); |
!!!cp (160); |
2104 |
} elsif ($self->{is_xml} and $self->{nc} == 0x005B) { # [ |
} elsif ($self->{is_xml} and $self->{nc} == 0x005B) { # [ |
2105 |
!!!cp (163.1); |
!!!cp (163.1); |
2106 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2107 |
|
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2108 |
|
$self->{in_subset} = 1; |
2109 |
!!!next-input-character; |
!!!next-input-character; |
2110 |
|
!!!emit ($self->{ct}); # DOCTYPE |
2111 |
redo A; |
redo A; |
2112 |
} else { |
} else { |
2113 |
!!!cp (164); |
!!!cp (164); |
2164 |
!!!cp (167.3); |
!!!cp (167.3); |
2165 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2166 |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2167 |
|
$self->{in_subset} = 1; |
2168 |
!!!next-input-character; |
!!!next-input-character; |
2169 |
|
!!!emit ($self->{ct}); # DOCTYPE |
2170 |
redo A; |
redo A; |
2171 |
} else { |
} else { |
2172 |
!!!cp (180); |
!!!cp (180); |
2320 |
!!!parse-error (type => 'no PUBLIC literal'); |
!!!parse-error (type => 'no PUBLIC literal'); |
2321 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2322 |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2323 |
|
$self->{in_subset} = 1; |
2324 |
!!!next-input-character; |
!!!next-input-character; |
2325 |
|
!!!emit ($self->{ct}); # DOCTYPE |
2326 |
redo A; |
redo A; |
2327 |
} else { |
} else { |
2328 |
!!!cp (186); |
!!!cp (186); |
2464 |
!!!parse-error (type => 'no SYSTEM literal'); |
!!!parse-error (type => 'no SYSTEM literal'); |
2465 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2466 |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2467 |
|
$self->{in_subset} = 1; |
2468 |
!!!next-input-character; |
!!!next-input-character; |
2469 |
|
!!!emit ($self->{ct}); # DOCTYPE |
2470 |
redo A; |
redo A; |
2471 |
} else { |
} else { |
2472 |
!!!cp (200); |
!!!cp (200); |
2524 |
|
|
2525 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2526 |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2527 |
|
$self->{in_subset} = 1; |
2528 |
!!!next-input-character; |
!!!next-input-character; |
2529 |
|
!!!emit ($self->{ct}); # DOCTYPE |
2530 |
redo A; |
redo A; |
2531 |
} else { |
} else { |
2532 |
!!!cp (206); |
!!!cp (206); |
2649 |
!!!cp (218.1); |
!!!cp (218.1); |
2650 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2651 |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2652 |
|
$self->{in_subset} = 1; |
2653 |
!!!next-input-character; |
!!!next-input-character; |
2654 |
|
!!!emit ($self->{ct}); # DOCTYPE |
2655 |
redo A; |
redo A; |
2656 |
} else { |
} else { |
2657 |
!!!cp (218); |
!!!cp (218); |
2673 |
|
|
2674 |
redo A; |
redo A; |
2675 |
} elsif ($self->{is_xml} and $self->{nc} == 0x005B) { # [ |
} elsif ($self->{is_xml} and $self->{nc} == 0x005B) { # [ |
2676 |
if ($self->{ct}->{has_internal_subset}) { # DOCTYPE |
!!!cp (220.1); |
2677 |
!!!cp (220.2); |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2678 |
## Stay in the state. |
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
2679 |
!!!next-input-character; |
$self->{in_subset} = 1; |
2680 |
redo A; |
!!!next-input-character; |
2681 |
} else { |
!!!emit ($self->{ct}); # DOCTYPE |
2682 |
!!!cp (220.1); |
redo A; |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
|
|
$self->{ct}->{has_internal_subset} = 1; # DOCTYPE |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
2683 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
2684 |
!!!cp (220); |
!!!cp (220); |
2685 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
3161 |
## XML-only states |
## XML-only states |
3162 |
|
|
3163 |
} elsif ($self->{state} == PI_STATE) { |
} elsif ($self->{state} == PI_STATE) { |
3164 |
|
## XML5: "Pi state" and "DOCTYPE pi state". |
3165 |
|
|
3166 |
if ($is_space->{$self->{nc}} or |
if ($is_space->{$self->{nc}} or |
3167 |
$self->{nc} == 0x003F or # ? ## XML5: Same as "Anything else" |
$self->{nc} == 0x003F or # ? |
3168 |
$self->{nc} == -1) { |
$self->{nc} == -1) { |
3169 |
|
## XML5: U+003F: "pi state": Same as "Anything else"; "DOCTYPE |
3170 |
|
## pi state": Switch to the "DOCTYPE pi after state". EOF: |
3171 |
|
## "DOCTYPE pi state": Parse error, switch to the "data |
3172 |
|
## state". |
3173 |
!!!parse-error (type => 'bare pio', ## TODO: type |
!!!parse-error (type => 'bare pio', ## TODO: type |
3174 |
line => $self->{line_prev}, |
line => $self->{line_prev}, |
3175 |
column => $self->{column_prev} |
column => $self->{column_prev} |
3184 |
}; |
}; |
3185 |
redo A; |
redo A; |
3186 |
} else { |
} else { |
3187 |
|
## XML5: "DOCTYPE pi state": Stay in the state. |
3188 |
$self->{ct} = {type => PI_TOKEN, |
$self->{ct} = {type => PI_TOKEN, |
3189 |
target => chr $self->{nc}, |
target => chr $self->{nc}, |
3190 |
data => '', |
data => '', |
3202 |
redo A; |
redo A; |
3203 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
3204 |
!!!parse-error (type => 'no pic'); ## TODO: type |
!!!parse-error (type => 'no pic'); ## TODO: type |
3205 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
3206 |
$self->{s_kwd} = ''; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3207 |
|
} else { |
3208 |
|
$self->{state} = DATA_STATE; |
3209 |
|
$self->{s_kwd} = ''; |
3210 |
|
} |
3211 |
## Reconsume. |
## Reconsume. |
3212 |
!!!emit ($self->{ct}); # pi |
!!!emit ($self->{ct}); # pi |
3213 |
redo A; |
redo A; |
3238 |
redo A; |
redo A; |
3239 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
3240 |
!!!parse-error (type => 'no pic'); ## TODO: type |
!!!parse-error (type => 'no pic'); ## TODO: type |
3241 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
3242 |
$self->{s_kwd} = ''; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; ## XML5: "Data state" |
3243 |
|
} else { |
3244 |
|
$self->{state} = DATA_STATE; |
3245 |
|
$self->{s_kwd} = ''; |
3246 |
|
} |
3247 |
## Reprocess. |
## Reprocess. |
3248 |
!!!emit ($self->{ct}); # pi |
!!!emit ($self->{ct}); # pi |
3249 |
redo A; |
redo A; |
3257 |
redo A; |
redo A; |
3258 |
} |
} |
3259 |
} elsif ($self->{state} == PI_AFTER_STATE) { |
} elsif ($self->{state} == PI_AFTER_STATE) { |
3260 |
|
## XML5: Part of "Pi after state". |
3261 |
|
|
3262 |
if ($self->{nc} == 0x003E) { # > |
if ($self->{nc} == 0x003E) { # > |
3263 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
3264 |
$self->{s_kwd} = ''; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3265 |
|
} else { |
3266 |
|
$self->{state} = DATA_STATE; |
3267 |
|
$self->{s_kwd} = ''; |
3268 |
|
} |
3269 |
!!!next-input-character; |
!!!next-input-character; |
3270 |
!!!emit ($self->{ct}); # pi |
!!!emit ($self->{ct}); # pi |
3271 |
redo A; |
redo A; |
3288 |
redo A; |
redo A; |
3289 |
} |
} |
3290 |
} elsif ($self->{state} == PI_DATA_AFTER_STATE) { |
} elsif ($self->{state} == PI_DATA_AFTER_STATE) { |
3291 |
## XML5: Same as "pi after state" in XML5 |
## XML5: Same as "pi after state" and "DOCTYPE pi after state". |
3292 |
|
|
3293 |
if ($self->{nc} == 0x003E) { # > |
if ($self->{nc} == 0x003E) { # > |
3294 |
$self->{state} = DATA_STATE; |
if ($self->{in_subset}) { |
3295 |
$self->{s_kwd} = ''; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3296 |
|
} else { |
3297 |
|
$self->{state} = DATA_STATE; |
3298 |
|
$self->{s_kwd} = ''; |
3299 |
|
} |
3300 |
!!!next-input-character; |
!!!next-input-character; |
3301 |
!!!emit ($self->{ct}); # pi |
!!!emit ($self->{ct}); # pi |
3302 |
redo A; |
redo A; |
3314 |
|
|
3315 |
} elsif ($self->{state} == DOCTYPE_INTERNAL_SUBSET_STATE) { |
} elsif ($self->{state} == DOCTYPE_INTERNAL_SUBSET_STATE) { |
3316 |
if ($self->{nc} == 0x003C) { # < |
if ($self->{nc} == 0x003C) { # < |
3317 |
## TODO: |
$self->{state} = DOCTYPE_TAG_STATE; |
3318 |
!!!next-input-character; |
!!!next-input-character; |
3319 |
redo A; |
redo A; |
3320 |
} elsif ($self->{nc} == 0x0025) { # % |
} elsif ($self->{nc} == 0x0025) { # % |
3324 |
!!!next-input-character; |
!!!next-input-character; |
3325 |
redo A; |
redo A; |
3326 |
} elsif ($self->{nc} == 0x005D) { # ] |
} elsif ($self->{nc} == 0x005D) { # ] |
3327 |
|
delete $self->{in_subset}; |
3328 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_AFTER_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_AFTER_STATE; |
3329 |
!!!next-input-character; |
!!!next-input-character; |
3330 |
redo A; |
redo A; |
3334 |
redo A; |
redo A; |
3335 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
3336 |
!!!parse-error (type => 'unclosed internal subset'); ## TODO: type |
!!!parse-error (type => 'unclosed internal subset'); ## TODO: type |
3337 |
|
delete $self->{in_subset}; |
3338 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
3339 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
3340 |
## Reconsume. |
## Reconsume. |
3341 |
!!!emit ($self->{ct}); # DOCTYPE |
!!!emit ({type => END_OF_DOCTYPE_TOKEN}); |
3342 |
redo A; |
redo A; |
3343 |
} else { |
} else { |
3344 |
unless ($self->{internal_subset_tainted}) { |
unless ($self->{internal_subset_tainted}) { |
3355 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
3356 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
3357 |
!!!next-input-character; |
!!!next-input-character; |
3358 |
!!!emit ($self->{ct}); # DOCTYPE |
!!!emit ({type => END_OF_DOCTYPE_TOKEN}); |
3359 |
redo A; |
redo A; |
3360 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
3361 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
3362 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
3363 |
$self->{s_kwd} = ''; |
$self->{s_kwd} = ''; |
3364 |
## Reconsume. |
## Reconsume. |
3365 |
!!!emit ($self->{ct}); # DOCTYPE |
!!!emit ({type => END_OF_DOCTYPE_TOKEN}); |
3366 |
redo A; |
redo A; |
3367 |
} else { |
} else { |
3368 |
## XML5: No parse error and stay in the state. |
## XML5: No parse error and stay in the state. |
3369 |
!!!parse-error (type => 'string after internal subset'); ## TODO: type |
!!!parse-error (type => 'string after internal subset'); ## TODO: type |
3370 |
|
|
3371 |
$self->{state} = BOGUS_DOCTYPE_STATE; |
$self->{state} = BOGUS_DOCTYPE_INTERNAL_SUBSET_AFTER_STATE; |
3372 |
!!!next-input-character; |
!!!next-input-character; |
3373 |
redo A; |
redo A; |
3374 |
} |
} |
3375 |
|
} elsif ($self->{state} == BOGUS_DOCTYPE_INTERNAL_SUBSET_AFTER_STATE) { |
3376 |
|
if ($self->{nc} == 0x003E) { # > |
3377 |
|
$self->{state} = DATA_STATE; |
3378 |
|
$self->{s_kwd} = ''; |
3379 |
|
!!!next-input-character; |
3380 |
|
!!!emit ({type => END_OF_DOCTYPE_TOKEN}); |
3381 |
|
redo A; |
3382 |
|
} elsif ($self->{nc} == -1) { |
3383 |
|
$self->{state} = DATA_STATE; |
3384 |
|
$self->{s_kwd} = ''; |
3385 |
|
## Reconsume. |
3386 |
|
!!!emit ({type => END_OF_DOCTYPE_TOKEN}); |
3387 |
|
redo A; |
3388 |
|
} else { |
3389 |
|
## Stay in the state. |
3390 |
|
!!!next-input-character; |
3391 |
|
redo A; |
3392 |
|
} |
3393 |
|
} elsif ($self->{state} == DOCTYPE_TAG_STATE) { |
3394 |
|
if ($self->{nc} == 0x0021) { # ! |
3395 |
|
$self->{state} = DOCTYPE_MARKUP_DECLARATION_OPEN_STATE; |
3396 |
|
!!!next-input-character; |
3397 |
|
redo A; |
3398 |
|
} elsif ($self->{nc} == 0x003F) { # ? |
3399 |
|
$self->{state} = PI_STATE; |
3400 |
|
!!!next-input-character; |
3401 |
|
redo A; |
3402 |
|
} elsif ($self->{nc} == -1) { |
3403 |
|
!!!parse-error (type => 'bare stago'); |
3404 |
|
$self->{state} = DATA_STATE; |
3405 |
|
$self->{s_kwd} = ''; |
3406 |
|
## Reconsume. |
3407 |
|
redo A; |
3408 |
|
} else { |
3409 |
|
!!!parse-error (type => 'bare stago', ## XML5: Not a parse error. |
3410 |
|
line => $self->{line_prev}, |
3411 |
|
column => $self->{column_prev}); |
3412 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3413 |
|
$self->{ct} = {type => COMMENT_TOKEN, |
3414 |
|
data => '', |
3415 |
|
}; ## NOTE: Will be discarded. |
3416 |
|
!!!next-input-character; |
3417 |
|
redo A; |
3418 |
|
} |
3419 |
|
} elsif ($self->{state} == DOCTYPE_MARKUP_DECLARATION_OPEN_STATE) { |
3420 |
|
## XML5: "DOCTYPE markup declaration state". |
3421 |
|
|
3422 |
|
if ($self->{nc} == 0x002D) { # - |
3423 |
|
$self->{state} = MD_HYPHEN_STATE; |
3424 |
|
!!!next-input-character; |
3425 |
|
redo A; |
3426 |
|
} elsif ($self->{nc} == 0x0045) { # E |
3427 |
|
$self->{state} = MD_E_STATE; |
3428 |
|
$self->{kwd} = chr $self->{nc}; |
3429 |
|
!!!next-input-character; |
3430 |
|
redo A; |
3431 |
|
} elsif ($self->{nc} == 0x0041) { # A |
3432 |
|
$self->{state} = MD_ATTLIST_STATE; |
3433 |
|
$self->{kwd} = chr $self->{nc}; |
3434 |
|
!!!next-input-character; |
3435 |
|
redo A; |
3436 |
|
} elsif ($self->{nc} == 0x004E) { # N |
3437 |
|
$self->{state} = MD_NOTATION_STATE; |
3438 |
|
$self->{kwd} = chr $self->{nc}; |
3439 |
|
!!!next-input-character; |
3440 |
|
redo A; |
3441 |
|
} else { |
3442 |
|
# |
3443 |
|
} |
3444 |
|
|
3445 |
|
## XML5: No parse error. |
3446 |
|
!!!parse-error (type => 'bogus comment', |
3447 |
|
line => $self->{line_prev}, |
3448 |
|
column => $self->{column_prev} - 1); |
3449 |
|
## Reconsume. |
3450 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3451 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded. |
3452 |
|
redo A; |
3453 |
|
} elsif ($self->{state} == MD_E_STATE) { |
3454 |
|
if ($self->{nc} == 0x004E) { # N |
3455 |
|
$self->{state} = MD_ENTITY_STATE; |
3456 |
|
$self->{kwd} .= chr $self->{nc}; |
3457 |
|
!!!next-input-character; |
3458 |
|
redo A; |
3459 |
|
} elsif ($self->{nc} == 0x004C) { # L |
3460 |
|
## XML5: <!ELEMENT> not supported. |
3461 |
|
$self->{state} = MD_ELEMENT_STATE; |
3462 |
|
$self->{kwd} .= chr $self->{nc}; |
3463 |
|
!!!next-input-character; |
3464 |
|
redo A; |
3465 |
|
} else { |
3466 |
|
## XML5: No parse error. |
3467 |
|
!!!parse-error (type => 'bogus comment', |
3468 |
|
line => $self->{line_prev}, |
3469 |
|
column => $self->{column_prev} - 2 |
3470 |
|
+ 1 * ($self->{nc} == -1)); |
3471 |
|
## Reconsume. |
3472 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3473 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded |
3474 |
|
redo A; |
3475 |
|
} |
3476 |
|
} elsif ($self->{state} == MD_ENTITY_STATE) { |
3477 |
|
if ($self->{nc} == { |
3478 |
|
'EN' => 0x0054, # T |
3479 |
|
'ENT' => 0x0049, # I |
3480 |
|
'ENTI' => 0x0054, # T |
3481 |
|
}->{$self->{kwd}}) { |
3482 |
|
## Stay in the state. |
3483 |
|
$self->{kwd} .= chr $self->{nc}; |
3484 |
|
!!!next-input-character; |
3485 |
|
redo A; |
3486 |
|
} elsif ($self->{kwd} eq 'ENTIT' and |
3487 |
|
$self->{nc} == 0x0059) { # Y |
3488 |
|
$self->{ct} = {type => GENERAL_ENTITY_TOKEN, name => '', text => '', |
3489 |
|
line => $self->{line_prev}, |
3490 |
|
column => $self->{column_prev} - 6}; |
3491 |
|
$self->{state} = DOCTYPE_MD_STATE; |
3492 |
|
!!!next-input-character; |
3493 |
|
redo A; |
3494 |
|
} else { |
3495 |
|
!!!parse-error (type => 'bogus comment', |
3496 |
|
line => $self->{line_prev}, |
3497 |
|
column => $self->{column_prev} - 1 |
3498 |
|
- (length $self->{kwd}) |
3499 |
|
+ 1 * ($self->{nc} == -1)); |
3500 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3501 |
|
## Reconsume. |
3502 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded |
3503 |
|
redo A; |
3504 |
|
} |
3505 |
|
} elsif ($self->{state} == MD_ELEMENT_STATE) { |
3506 |
|
if ($self->{nc} == { |
3507 |
|
'EL' => 0x0045, # E |
3508 |
|
'ELE' => 0x004D, # M |
3509 |
|
'ELEM' => 0x0045, # E |
3510 |
|
'ELEME' => 0x004E, # N |
3511 |
|
}->{$self->{kwd}}) { |
3512 |
|
## Stay in the state. |
3513 |
|
$self->{kwd} .= chr $self->{nc}; |
3514 |
|
!!!next-input-character; |
3515 |
|
redo A; |
3516 |
|
} elsif ($self->{kwd} eq 'ELEMEN' and |
3517 |
|
$self->{nc} == 0x0054) { # T |
3518 |
|
$self->{ct} = {type => ELEMENT_TOKEN, name => '', |
3519 |
|
line => $self->{line_prev}, |
3520 |
|
column => $self->{column_prev} - 6}; |
3521 |
|
$self->{state} = DOCTYPE_MD_STATE; |
3522 |
|
!!!next-input-character; |
3523 |
|
redo A; |
3524 |
|
} else { |
3525 |
|
!!!parse-error (type => 'bogus comment', |
3526 |
|
line => $self->{line_prev}, |
3527 |
|
column => $self->{column_prev} - 1 |
3528 |
|
- (length $self->{kwd}) |
3529 |
|
+ 1 * ($self->{nc} == -1)); |
3530 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3531 |
|
## Reconsume. |
3532 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded |
3533 |
|
redo A; |
3534 |
|
} |
3535 |
|
} elsif ($self->{state} == MD_ATTLIST_STATE) { |
3536 |
|
if ($self->{nc} == { |
3537 |
|
'A' => 0x0054, # T |
3538 |
|
'AT' => 0x0054, # T |
3539 |
|
'ATT' => 0x004C, # L |
3540 |
|
'ATTL' => 0x0049, # I |
3541 |
|
'ATTLI' => 0x0053, # S |
3542 |
|
}->{$self->{kwd}}) { |
3543 |
|
## Stay in the state. |
3544 |
|
$self->{kwd} .= chr $self->{nc}; |
3545 |
|
!!!next-input-character; |
3546 |
|
redo A; |
3547 |
|
} elsif ($self->{kwd} eq 'ATTLIS' and |
3548 |
|
$self->{nc} == 0x0054) { # T |
3549 |
|
$self->{ct} = {type => ATTLIST_TOKEN, name => '', |
3550 |
|
line => $self->{line_prev}, |
3551 |
|
column => $self->{column_prev} - 6}; |
3552 |
|
$self->{state} = DOCTYPE_MD_STATE; |
3553 |
|
!!!next-input-character; |
3554 |
|
redo A; |
3555 |
|
} else { |
3556 |
|
!!!parse-error (type => 'bogus comment', |
3557 |
|
line => $self->{line_prev}, |
3558 |
|
column => $self->{column_prev} - 1 |
3559 |
|
- (length $self->{kwd}) |
3560 |
|
+ 1 * ($self->{nc} == -1)); |
3561 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3562 |
|
## Reconsume. |
3563 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded |
3564 |
|
redo A; |
3565 |
|
} |
3566 |
|
} elsif ($self->{state} == MD_NOTATION_STATE) { |
3567 |
|
if ($self->{nc} == { |
3568 |
|
'N' => 0x004F, # O |
3569 |
|
'NO' => 0x0054, # T |
3570 |
|
'NOT' => 0x0041, # A |
3571 |
|
'NOTA' => 0x0054, # T |
3572 |
|
'NOTAT' => 0x0049, # I |
3573 |
|
'NOTATI' => 0x004F, # O |
3574 |
|
}->{$self->{kwd}}) { |
3575 |
|
## Stay in the state. |
3576 |
|
$self->{kwd} .= chr $self->{nc}; |
3577 |
|
!!!next-input-character; |
3578 |
|
redo A; |
3579 |
|
} elsif ($self->{kwd} eq 'NOTATIO' and |
3580 |
|
$self->{nc} == 0x004E) { # N |
3581 |
|
$self->{ct} = {type => NOTATION_TOKEN, name => '', |
3582 |
|
line => $self->{line_prev}, |
3583 |
|
column => $self->{column_prev} - 6}; |
3584 |
|
$self->{state} = DOCTYPE_MD_STATE; |
3585 |
|
!!!next-input-character; |
3586 |
|
redo A; |
3587 |
|
} else { |
3588 |
|
!!!parse-error (type => 'bogus comment', |
3589 |
|
line => $self->{line_prev}, |
3590 |
|
column => $self->{column_prev} - 1 |
3591 |
|
- (length $self->{kwd}) |
3592 |
|
+ 1 * ($self->{nc} == -1)); |
3593 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3594 |
|
## Reconsume. |
3595 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded |
3596 |
|
redo A; |
3597 |
|
} |
3598 |
|
} elsif ($self->{state} == DOCTYPE_MD_STATE) { |
3599 |
|
## XML5: "DOCTYPE ENTITY state", "DOCTYPE ATTLIST state", and |
3600 |
|
## "DOCTYPE NOTATION state". |
3601 |
|
|
3602 |
|
if ($is_space->{$self->{nc}}) { |
3603 |
|
## XML5: [NOTATION] Switch to the "DOCTYPE NOTATION identifier state". |
3604 |
|
$self->{state} = BEFORE_MD_NAME_STATE; |
3605 |
|
!!!next-input-character; |
3606 |
|
redo A; |
3607 |
|
} elsif ($self->{ct}->{type} == GENERAL_ENTITY_TOKEN and |
3608 |
|
$self->{nc} == 0x0025) { # % |
3609 |
|
## XML5: Switch to the "DOCTYPE bogus comment state". |
3610 |
|
!!!parse-error (type => 'no space before md name'); ## TODO: type |
3611 |
|
$self->{state} = DOCTYPE_ENTITY_PARAMETER_BEFORE_STATE; |
3612 |
|
!!!next-input-character; |
3613 |
|
redo A; |
3614 |
|
} elsif ($self->{nc} == -1) { |
3615 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
3616 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; ## XML5: "Data state". |
3617 |
|
## Reconsume. |
3618 |
|
redo A; |
3619 |
|
} elsif ($self->{nc} == 0x003E) { # > |
3620 |
|
## XML5: Switch to the "DOCTYPE bogus comment state". |
3621 |
|
!!!parse-error (type => 'no md name'); ## TODO: type |
3622 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3623 |
|
!!!next-input-character; |
3624 |
|
redo A; |
3625 |
|
} else { |
3626 |
|
## XML5: Switch to the "DOCTYPE bogus comment state". |
3627 |
|
!!!parse-error (type => 'no space before md name'); ## TODO: type |
3628 |
|
$self->{state} = BEFORE_MD_NAME_STATE; |
3629 |
|
redo A; |
3630 |
|
} |
3631 |
|
} elsif ($self->{state} == BEFORE_MD_NAME_STATE) { |
3632 |
|
## XML5: "DOCTYPE ENTITY parameter state", "DOCTYPE ENTITY type |
3633 |
|
## before state", "DOCTYPE ATTLIST name before state". |
3634 |
|
|
3635 |
|
if ($is_space->{$self->{nc}}) { |
3636 |
|
## Stay in the state. |
3637 |
|
!!!next-input-character; |
3638 |
|
redo A; |
3639 |
|
} elsif ($self->{ct}->{type} == GENERAL_ENTITY_TOKEN and |
3640 |
|
$self->{nc} == 0x0025) { # % |
3641 |
|
$self->{state} = DOCTYPE_ENTITY_PARAMETER_BEFORE_STATE; |
3642 |
|
!!!next-input-character; |
3643 |
|
redo A; |
3644 |
|
} elsif ($self->{nc} == 0x003E) { # > |
3645 |
|
## XML5: Same as "Anything else". |
3646 |
|
!!!parse-error (type => 'no md name'); ## TODO: type |
3647 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3648 |
|
!!!next-input-character; |
3649 |
|
redo A; |
3650 |
|
} elsif ($self->{nc} == -1) { |
3651 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
3652 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; ## XML5: "Data state". |
3653 |
|
## Reconsume. |
3654 |
|
redo A; |
3655 |
|
} else { |
3656 |
|
## XML5: [ATTLIST] Not defined yet. |
3657 |
|
$self->{ct}->{name} .= chr $self->{nc}; |
3658 |
|
$self->{state} = MD_NAME_STATE; |
3659 |
|
!!!next-input-character; |
3660 |
|
redo A; |
3661 |
|
} |
3662 |
|
} elsif ($self->{state} == DOCTYPE_ENTITY_PARAMETER_BEFORE_STATE) { |
3663 |
|
if ($is_space->{$self->{nc}}) { |
3664 |
|
## XML5: Switch to the "DOCTYPE ENTITY parameter state". |
3665 |
|
$self->{ct}->{type} = PARAMETER_ENTITY_TOKEN; |
3666 |
|
$self->{state} = BEFORE_MD_NAME_STATE; |
3667 |
|
!!!next-input-character; |
3668 |
|
redo A; |
3669 |
|
} elsif ($self->{nc} == 0x003E) { # > |
3670 |
|
## XML5: Same as "Anything else". |
3671 |
|
!!!parse-error (type => 'no md name'); ## TODO: type |
3672 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3673 |
|
!!!next-input-character; |
3674 |
|
redo A; |
3675 |
|
} elsif ($self->{nc} == -1) { |
3676 |
|
!!!parse-error (type => 'unclosed md'); |
3677 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; ## XML5: "Data state". |
3678 |
|
## Reconsume. |
3679 |
|
redo A; |
3680 |
|
} else { |
3681 |
|
## XML5: No parse error. |
3682 |
|
!!!parse-error (type => 'no space after ENTITY percent'); ## TODO: type |
3683 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3684 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded |
3685 |
|
## Reconsume. |
3686 |
|
redo A; |
3687 |
|
} |
3688 |
|
} elsif ($self->{state} == MD_NAME_STATE) { |
3689 |
|
## XML5: "DOCTYPE ENTITY name state" and "DOCTYPE ATTLIST name state". |
3690 |
|
|
3691 |
|
if ($is_space->{$self->{nc}}) { |
3692 |
|
## TODO: |
3693 |
|
$self->{state} = DOCTYPE_ATTLIST_NAME_AFTER_STATE; |
3694 |
|
!!!next-input-character; |
3695 |
|
redo A; |
3696 |
|
} elsif ($self->{nc} == 0x003E) { # > |
3697 |
|
if ($self->{ct}->{type} == ATTLIST_TOKEN) { |
3698 |
|
# |
3699 |
|
} else { |
3700 |
|
!!!parse-error (type => 'no md body'); ## TODO: type |
3701 |
|
} |
3702 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3703 |
|
!!!next-input-character; |
3704 |
|
!!!emit ($self->{ct}); # ELEMENT/ENTITY/ATTLIST/NOTATION |
3705 |
|
redo A; |
3706 |
|
} elsif ($self->{nc} == -1) { |
3707 |
|
## XML5: [ATTLIST] No parse error. |
3708 |
|
!!!parse-error (type => 'unclosed md'); |
3709 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; ## XML5: "Data state". |
3710 |
|
## Reconsume. |
3711 |
|
!!!emit ($self->{ct}); # ELEMENT/ENTITY/ATTLIST/NOTATION |
3712 |
|
redo A; |
3713 |
|
} else { |
3714 |
|
## XML5: [ATTLIST] Not defined yet. |
3715 |
|
$self->{ct}->{name} .= chr $self->{nc}; |
3716 |
|
## Stay in the state. |
3717 |
|
!!!next-input-character; |
3718 |
|
redo A; |
3719 |
|
} |
3720 |
|
} elsif ($self->{state} == DOCTYPE_ATTLIST_NAME_AFTER_STATE) { |
3721 |
|
if ($is_space->{$self->{nc}}) { |
3722 |
|
## Stay in the state. |
3723 |
|
!!!next-input-character; |
3724 |
|
redo A; |
3725 |
|
} elsif ($self->{nc} == 0x003E) { # > |
3726 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
3727 |
|
!!!next-input-character; |
3728 |
|
!!!emit ($self->{ct}); # ATTLIST |
3729 |
|
redo A; |
3730 |
|
} elsif ($self->{nc} == -1) { |
3731 |
|
## XML5: No parse error. |
3732 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
3733 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; ## XML5: "Data state". |
3734 |
|
redo A; |
3735 |
|
} else { |
3736 |
|
## XML5: Not defined yet. |
3737 |
|
|
3738 |
|
## TODO: ... |
3739 |
|
|
3740 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
3741 |
|
$self->{ct} = {type => COMMENT_TOKEN, data => ''}; ## Will be discarded |
3742 |
|
## Reconsume. |
3743 |
|
redo A; |
3744 |
|
} |
3745 |
|
|
3746 |
} else { |
} else { |
3747 |
die "$0: $self->{state}: Unknown state"; |
die "$0: $self->{state}: Unknown state"; |
3748 |
} |
} |