177 |
sub DOCTYPE_ATTLIST_ATTRIBUTE_DECLARATION_STATE () { 82 } |
sub DOCTYPE_ATTLIST_ATTRIBUTE_DECLARATION_STATE () { 82 } |
178 |
sub DOCTYPE_ATTLIST_ATTRIBUTE_DECLARATION_AFTER_STATE () { 83 } |
sub DOCTYPE_ATTLIST_ATTRIBUTE_DECLARATION_AFTER_STATE () { 83 } |
179 |
sub AFTER_ATTLIST_ATTR_VALUE_QUOTED_STATE () { 84 } |
sub AFTER_ATTLIST_ATTR_VALUE_QUOTED_STATE () { 84 } |
180 |
sub BOGUS_MD_STATE () { 85 } |
sub BEFORE_NDATA_STATE () { 85 } |
181 |
|
sub NDATA_STATE () { 86 } |
182 |
|
sub AFTER_NDATA_STATE () { 87 } |
183 |
|
sub BEFORE_NOTATION_NAME_STATE () { 88 } |
184 |
|
sub NOTATION_NAME_STATE () { 89 } |
185 |
|
sub DOCTYPE_ENTITY_VALUE_DOUBLE_QUOTED_STATE () { 90 } |
186 |
|
sub DOCTYPE_ENTITY_VALUE_SINGLE_QUOTED_STATE () { 91 } |
187 |
|
sub ENTITY_VALUE_ENTITY_STATE () { 92 } |
188 |
|
sub AFTER_ELEMENT_NAME_STATE () { 93 } |
189 |
|
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) |
2272 |
$self->{kwd} = chr $self->{nc}; |
$self->{kwd} = chr $self->{nc}; |
2273 |
!!!next-input-character; |
!!!next-input-character; |
2274 |
redo A; |
redo A; |
2275 |
## TODO: " and ' for ENTITY |
} elsif ($self->{nc} == 0x0022 and # " |
2276 |
|
($self->{ct}->{type} == GENERAL_ENTITY_TOKEN or |
2277 |
|
$self->{ct}->{type} == PARAMETER_ENTITY_TOKEN)) { |
2278 |
|
!!!cp (167.21); |
2279 |
|
$self->{state} = DOCTYPE_ENTITY_VALUE_DOUBLE_QUOTED_STATE; |
2280 |
|
$self->{ct}->{value} = ''; # ENTITY |
2281 |
|
!!!next-input-character; |
2282 |
|
redo A; |
2283 |
|
} elsif ($self->{nc} == 0x0027 and # ' |
2284 |
|
($self->{ct}->{type} == GENERAL_ENTITY_TOKEN or |
2285 |
|
$self->{ct}->{type} == PARAMETER_ENTITY_TOKEN)) { |
2286 |
|
!!!cp (167.22); |
2287 |
|
$self->{state} = DOCTYPE_ENTITY_VALUE_SINGLE_QUOTED_STATE; |
2288 |
|
$self->{ct}->{value} = ''; # ENTITY |
2289 |
|
!!!next-input-character; |
2290 |
|
redo A; |
2291 |
} elsif ($self->{is_xml} and |
} elsif ($self->{is_xml} and |
2292 |
$self->{ct}->{type} == DOCTYPE_TOKEN and |
$self->{ct}->{type} == DOCTYPE_TOKEN and |
2293 |
$self->{nc} == 0x005B) { # [ |
$self->{nc} == 0x005B) { # [ |
2843 |
} |
} |
2844 |
} elsif ($self->{state} == AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
} elsif ($self->{state} == AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
2845 |
if ($is_space->{$self->{nc}}) { |
if ($is_space->{$self->{nc}}) { |
2846 |
!!!cp (215); |
if ($self->{ct}->{type} == GENERAL_ENTITY_TOKEN) { |
2847 |
## Stay in the state |
!!!cp (215.1); |
2848 |
|
$self->{state} = BEFORE_NDATA_STATE; |
2849 |
|
} else { |
2850 |
|
!!!cp (215); |
2851 |
|
## Stay in the state |
2852 |
|
} |
2853 |
!!!next-input-character; |
!!!next-input-character; |
2854 |
redo A; |
redo A; |
2855 |
} elsif ($self->{nc} == 0x003E) { # > |
} elsif ($self->{nc} == 0x003E) { # > |
2865 |
!!!next-input-character; |
!!!next-input-character; |
2866 |
!!!emit ($self->{ct}); # DOCTYPE/ENTITY/NOTATION |
!!!emit ($self->{ct}); # DOCTYPE/ENTITY/NOTATION |
2867 |
redo A; |
redo A; |
2868 |
## TODO: "NDATA" |
} elsif ($self->{ct}->{type} == GENERAL_ENTITY_TOKEN and |
2869 |
|
($self->{nc} == 0x004E or # N |
2870 |
|
$self->{nc} == 0x006E)) { # n |
2871 |
|
!!!cp (216.2); |
2872 |
|
!!!parse-error (type => 'no space before NDATA'); ## TODO: type |
2873 |
|
$self->{state} = NDATA_STATE; |
2874 |
|
$self->{kwd} = chr $self->{nc}; |
2875 |
|
!!!next-input-character; |
2876 |
|
redo A; |
2877 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
2878 |
if ($self->{ct}->{type} == DOCTYPE_TOKEN) { |
if ($self->{ct}->{type} == DOCTYPE_TOKEN) { |
2879 |
!!!cp (217); |
!!!cp (217); |
2915 |
!!!next-input-character; |
!!!next-input-character; |
2916 |
redo A; |
redo A; |
2917 |
} |
} |
2918 |
|
} elsif ($self->{state} == BEFORE_NDATA_STATE) { |
2919 |
|
if ($is_space->{$self->{nc}}) { |
2920 |
|
!!!cp (218.3); |
2921 |
|
## Stay in the state. |
2922 |
|
!!!next-input-character; |
2923 |
|
redo A; |
2924 |
|
} elsif ($self->{nc} == 0x003E) { # > |
2925 |
|
!!!cp (218.4); |
2926 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2927 |
|
!!!next-input-character; |
2928 |
|
!!!emit ($self->{ct}); # ENTITY |
2929 |
|
redo A; |
2930 |
|
} elsif ($self->{nc} == 0x004E or # N |
2931 |
|
$self->{nc} == 0x006E) { # n |
2932 |
|
!!!cp (218.5); |
2933 |
|
$self->{state} = NDATA_STATE; |
2934 |
|
$self->{kwd} = chr $self->{nc}; |
2935 |
|
!!!next-input-character; |
2936 |
|
redo A; |
2937 |
|
} elsif ($self->{nc} == -1) { |
2938 |
|
!!!cp (218.6); |
2939 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
2940 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
2941 |
|
## reconsume |
2942 |
|
!!!emit ($self->{ct}); # ENTITY |
2943 |
|
redo A; |
2944 |
|
} else { |
2945 |
|
!!!cp (218.7); |
2946 |
|
!!!parse-error (type => 'string after SYSTEM literal'); |
2947 |
|
$self->{state} = BOGUS_MD_STATE; |
2948 |
|
!!!next-input-character; |
2949 |
|
redo A; |
2950 |
|
} |
2951 |
} elsif ($self->{state} == BOGUS_DOCTYPE_STATE) { |
} elsif ($self->{state} == BOGUS_DOCTYPE_STATE) { |
2952 |
if ($self->{nc} == 0x003E) { # > |
if ($self->{nc} == 0x003E) { # > |
2953 |
!!!cp (219); |
!!!cp (219); |
3133 |
redo A; |
redo A; |
3134 |
} |
} |
3135 |
} elsif ($self->{state} == ENTITY_HASH_STATE) { |
} elsif ($self->{state} == ENTITY_HASH_STATE) { |
3136 |
if ($self->{nc} == 0x0078 or # x |
if ($self->{nc} == 0x0078) { # x |
|
$self->{nc} == 0x0058) { # X |
|
3137 |
!!!cp (995); |
!!!cp (995); |
3138 |
$self->{state} = HEXREF_X_STATE; |
$self->{state} = HEXREF_X_STATE; |
3139 |
$self->{kwd} .= chr $self->{nc}; |
$self->{kwd} .= chr $self->{nc}; |
3140 |
!!!next-input-character; |
!!!next-input-character; |
3141 |
redo A; |
redo A; |
3142 |
|
} elsif ($self->{nc} == 0x0058) { # X |
3143 |
|
!!!cp (995.1); |
3144 |
|
if ($self->{is_xml}) { |
3145 |
|
!!!parse-error (type => 'uppercase hcro'); ## TODO: type |
3146 |
|
} |
3147 |
|
$self->{state} = HEXREF_X_STATE; |
3148 |
|
$self->{kwd} .= chr $self->{nc}; |
3149 |
|
!!!next-input-character; |
3150 |
|
redo A; |
3151 |
} elsif (0x0030 <= $self->{nc} and |
} elsif (0x0030 <= $self->{nc} and |
3152 |
$self->{nc} <= 0x0039) { # 0..9 |
$self->{nc} <= 0x0039) { # 0..9 |
3153 |
!!!cp (994); |
!!!cp (994); |
3355 |
redo A; |
redo A; |
3356 |
} |
} |
3357 |
} elsif ($self->{state} == ENTITY_NAME_STATE) { |
} elsif ($self->{state} == ENTITY_NAME_STATE) { |
3358 |
if (length $self->{kwd} < 30 and |
if ((0x0041 <= $self->{nc} and # a |
3359 |
## NOTE: Some number greater than the maximum length of entity name |
$self->{nc} <= 0x005A) or # x |
3360 |
((0x0041 <= $self->{nc} and # a |
(0x0061 <= $self->{nc} and # a |
3361 |
$self->{nc} <= 0x005A) or # x |
$self->{nc} <= 0x007A) or # z |
3362 |
(0x0061 <= $self->{nc} and # a |
(0x0030 <= $self->{nc} and # 0 |
3363 |
$self->{nc} <= 0x007A) or # z |
$self->{nc} <= 0x0039) or # 9 |
3364 |
(0x0030 <= $self->{nc} and # 0 |
$self->{nc} == 0x003B) { # ; |
|
$self->{nc} <= 0x0039) or # 9 |
|
|
$self->{nc} == 0x003B)) { # ; |
|
3365 |
our $EntityChar; |
our $EntityChar; |
3366 |
$self->{kwd} .= chr $self->{nc}; |
$self->{kwd} .= chr $self->{nc}; |
3367 |
if (defined $EntityChar->{$self->{kwd}}) { |
if (defined $EntityChar->{$self->{kwd}} or |
3368 |
|
$self->{ge}->{$self->{kwd}}) { |
3369 |
if ($self->{nc} == 0x003B) { # ; |
if ($self->{nc} == 0x003B) { # ; |
3370 |
!!!cp (1020); |
if (defined $self->{ge}->{$self->{kwd}}) { |
3371 |
$self->{entity__value} = $EntityChar->{$self->{kwd}}; |
if ($self->{ge}->{$self->{kwd}}->{only_text}) { |
3372 |
|
!!!cp (1020.1); |
3373 |
|
$self->{entity__value} = $self->{ge}->{$self->{kwd}}->{value}; |
3374 |
|
} else { |
3375 |
|
if (defined $self->{ge}->{$self->{kwd}}->{notation}) { |
3376 |
|
!!!cp (1020.2); |
3377 |
|
!!!parse-error (type => 'unparsed entity', ## TODO: type |
3378 |
|
value => $self->{kwd}); |
3379 |
|
} else { |
3380 |
|
!!!cp (1020.3); |
3381 |
|
} |
3382 |
|
$self->{entity__value} = '&' . $self->{kwd}; ## TODO: expand |
3383 |
|
} |
3384 |
|
} else { |
3385 |
|
if ($self->{is_xml}) { |
3386 |
|
!!!cp (1020.4); |
3387 |
|
!!!parse-error (type => 'entity not declared', ## TODO: type |
3388 |
|
value => $self->{kwd}, |
3389 |
|
level => { |
3390 |
|
'amp;' => $self->{level}->{warn}, |
3391 |
|
'quot;' => $self->{level}->{warn}, |
3392 |
|
'lt;' => $self->{level}->{warn}, |
3393 |
|
'gt;' => $self->{level}->{warn}, |
3394 |
|
'apos;' => $self->{level}->{warn}, |
3395 |
|
}->{$self->{kwd}} || |
3396 |
|
$self->{level}->{must}); |
3397 |
|
} else { |
3398 |
|
!!!cp (1020); |
3399 |
|
} |
3400 |
|
$self->{entity__value} = $EntityChar->{$self->{kwd}}; |
3401 |
|
} |
3402 |
$self->{entity__match} = 1; |
$self->{entity__match} = 1; |
3403 |
!!!next-input-character; |
!!!next-input-character; |
3404 |
# |
# |
4087 |
if ($self->{ct}->{type} == ATTLIST_TOKEN) { |
if ($self->{ct}->{type} == ATTLIST_TOKEN) { |
4088 |
$self->{state} = DOCTYPE_ATTLIST_NAME_AFTER_STATE; |
$self->{state} = DOCTYPE_ATTLIST_NAME_AFTER_STATE; |
4089 |
} elsif ($self->{ct}->{type} == ELEMENT_TOKEN) { |
} elsif ($self->{ct}->{type} == ELEMENT_TOKEN) { |
4090 |
## TODO: ... |
$self->{state} = AFTER_ELEMENT_NAME_STATE; |
|
$self->{state} = DOCTYPE_ATTLIST_NAME_AFTER_STATE; |
|
4091 |
} else { # ENTITY/NOTATION |
} else { # ENTITY/NOTATION |
4092 |
$self->{state} = AFTER_DOCTYPE_NAME_STATE; |
$self->{state} = AFTER_DOCTYPE_NAME_STATE; |
4093 |
} |
} |
4615 |
## Reconsume. |
## Reconsume. |
4616 |
redo A; |
redo A; |
4617 |
} |
} |
4618 |
|
} elsif ($self->{state} == NDATA_STATE) { |
4619 |
|
## ASCII case-insensitive |
4620 |
|
if ($self->{nc} == [ |
4621 |
|
undef, |
4622 |
|
0x0044, # D |
4623 |
|
0x0041, # A |
4624 |
|
0x0054, # T |
4625 |
|
]->[length $self->{kwd}] or |
4626 |
|
$self->{nc} == [ |
4627 |
|
undef, |
4628 |
|
0x0064, # d |
4629 |
|
0x0061, # a |
4630 |
|
0x0074, # t |
4631 |
|
]->[length $self->{kwd}]) { |
4632 |
|
!!!cp (172.2); |
4633 |
|
## Stay in the state. |
4634 |
|
$self->{kwd} .= chr $self->{nc}; |
4635 |
|
!!!next-input-character; |
4636 |
|
redo A; |
4637 |
|
} elsif ((length $self->{kwd}) == 4 and |
4638 |
|
($self->{nc} == 0x0041 or # A |
4639 |
|
$self->{nc} == 0x0061)) { # a |
4640 |
|
if ($self->{kwd} ne 'NDAT' or $self->{nc} == 0x0061) { # a |
4641 |
|
!!!cp (172.3); |
4642 |
|
!!!parse-error (type => 'lowercase keyword', ## TODO: type |
4643 |
|
text => 'NDATA', |
4644 |
|
line => $self->{line_prev}, |
4645 |
|
column => $self->{column_prev} - 4); |
4646 |
|
} else { |
4647 |
|
!!!cp (172.4); |
4648 |
|
} |
4649 |
|
$self->{state} = AFTER_NDATA_STATE; |
4650 |
|
!!!next-input-character; |
4651 |
|
redo A; |
4652 |
|
} else { |
4653 |
|
!!!parse-error (type => 'string after literal', ## TODO: type |
4654 |
|
line => $self->{line_prev}, |
4655 |
|
column => $self->{column_prev} + 1 |
4656 |
|
- length $self->{kwd}); |
4657 |
|
!!!cp (172.5); |
4658 |
|
$self->{state} = BOGUS_MD_STATE; |
4659 |
|
## Reconsume. |
4660 |
|
redo A; |
4661 |
|
} |
4662 |
|
} elsif ($self->{state} == AFTER_NDATA_STATE) { |
4663 |
|
if ($is_space->{$self->{nc}}) { |
4664 |
|
$self->{state} = BEFORE_NOTATION_NAME_STATE; |
4665 |
|
!!!next-input-character; |
4666 |
|
redo A; |
4667 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4668 |
|
!!!parse-error (type => 'no notation name'); ## TODO: type |
4669 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4670 |
|
!!!next-input-character; |
4671 |
|
!!!emit ($self->{ct}); # ENTITY |
4672 |
|
redo A; |
4673 |
|
} elsif ($self->{nc} == -1) { |
4674 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4675 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4676 |
|
!!!next-input-character; |
4677 |
|
!!!emit ($self->{ct}); # ENTITY |
4678 |
|
redo A; |
4679 |
|
} else { |
4680 |
|
!!!parse-error (type => 'string after literal', ## TODO: type |
4681 |
|
line => $self->{line_prev}, |
4682 |
|
column => $self->{column_prev} + 1 |
4683 |
|
- length $self->{kwd}); |
4684 |
|
$self->{state} = BOGUS_MD_STATE; |
4685 |
|
## Reconsume. |
4686 |
|
redo A; |
4687 |
|
} |
4688 |
|
} elsif ($self->{state} == BEFORE_NOTATION_NAME_STATE) { |
4689 |
|
if ($is_space->{$self->{nc}}) { |
4690 |
|
## Stay in the state. |
4691 |
|
!!!next-input-character; |
4692 |
|
redo A; |
4693 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4694 |
|
!!!parse-error (type => 'no notation name'); ## TODO: type |
4695 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4696 |
|
!!!next-input-character; |
4697 |
|
!!!emit ($self->{ct}); # ENTITY |
4698 |
|
redo A; |
4699 |
|
} elsif ($self->{nc} == -1) { |
4700 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4701 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4702 |
|
!!!next-input-character; |
4703 |
|
!!!emit ($self->{ct}); # ENTITY |
4704 |
|
redo A; |
4705 |
|
} else { |
4706 |
|
$self->{ct}->{notation} = chr $self->{nc}; # ENTITY |
4707 |
|
$self->{state} = NOTATION_NAME_STATE; |
4708 |
|
!!!next-input-character; |
4709 |
|
redo A; |
4710 |
|
} |
4711 |
|
} elsif ($self->{state} == NOTATION_NAME_STATE) { |
4712 |
|
if ($is_space->{$self->{nc}}) { |
4713 |
|
$self->{state} = AFTER_MD_DEF_STATE; |
4714 |
|
!!!next-input-character; |
4715 |
|
redo A; |
4716 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4717 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4718 |
|
!!!next-input-character; |
4719 |
|
!!!emit ($self->{ct}); # ENTITY |
4720 |
|
redo A; |
4721 |
|
} elsif ($self->{nc} == -1) { |
4722 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4723 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4724 |
|
!!!next-input-character; |
4725 |
|
!!!emit ($self->{ct}); # ENTITY |
4726 |
|
redo A; |
4727 |
|
} else { |
4728 |
|
$self->{ct}->{notation} .= chr $self->{nc}; # ENTITY |
4729 |
|
## Stay in the state. |
4730 |
|
!!!next-input-character; |
4731 |
|
redo A; |
4732 |
|
} |
4733 |
|
} elsif ($self->{state} == DOCTYPE_ENTITY_VALUE_DOUBLE_QUOTED_STATE) { |
4734 |
|
if ($self->{nc} == 0x0022) { # " |
4735 |
|
$self->{state} = AFTER_MD_DEF_STATE; |
4736 |
|
!!!next-input-character; |
4737 |
|
redo A; |
4738 |
|
} elsif ($self->{nc} == 0x0026) { # & |
4739 |
|
$self->{prev_state} = $self->{state}; |
4740 |
|
$self->{state} = ENTITY_VALUE_ENTITY_STATE; |
4741 |
|
$self->{entity_add} = 0x0022; # " |
4742 |
|
!!!next-input-character; |
4743 |
|
redo A; |
4744 |
|
## TODO: % |
4745 |
|
} elsif ($self->{nc} == -1) { |
4746 |
|
!!!parse-error (type => 'unclosed entity value'); ## TODO: type |
4747 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4748 |
|
## Reconsume. |
4749 |
|
!!!emit ($self->{ct}); # ENTITY |
4750 |
|
redo A; |
4751 |
|
} else { |
4752 |
|
$self->{ct}->{value} .= chr $self->{nc}; # ENTITY |
4753 |
|
!!!next-input-character; |
4754 |
|
redo A; |
4755 |
|
} |
4756 |
|
} elsif ($self->{state} == DOCTYPE_ENTITY_VALUE_SINGLE_QUOTED_STATE) { |
4757 |
|
if ($self->{nc} == 0x0027) { # ' |
4758 |
|
$self->{state} = AFTER_MD_DEF_STATE; |
4759 |
|
!!!next-input-character; |
4760 |
|
redo A; |
4761 |
|
} elsif ($self->{nc} == 0x0026) { # & |
4762 |
|
$self->{prev_state} = $self->{state}; |
4763 |
|
$self->{state} = ENTITY_VALUE_ENTITY_STATE; |
4764 |
|
$self->{entity_add} = 0x0027; # ' |
4765 |
|
!!!next-input-character; |
4766 |
|
redo A; |
4767 |
|
## TODO: % |
4768 |
|
} elsif ($self->{nc} == -1) { |
4769 |
|
!!!parse-error (type => 'unclosed entity value'); ## TODO: type |
4770 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4771 |
|
## Reconsume. |
4772 |
|
!!!emit ($self->{ct}); # ENTITY |
4773 |
|
redo A; |
4774 |
|
} else { |
4775 |
|
$self->{ct}->{value} .= chr $self->{nc}; # ENTITY |
4776 |
|
!!!next-input-character; |
4777 |
|
redo A; |
4778 |
|
} |
4779 |
|
} elsif ($self->{state} == ENTITY_VALUE_ENTITY_STATE) { |
4780 |
|
## TODO: XMLize |
4781 |
|
|
4782 |
|
if ($is_space->{$self->{nc}} or |
4783 |
|
{ |
4784 |
|
0x003C => 1, 0x0026 => 1, -1 => 1, # <, & |
4785 |
|
$self->{entity_add} => 1, |
4786 |
|
}->{$self->{nc}}) { |
4787 |
|
## Don't consume |
4788 |
|
## No error |
4789 |
|
## Return nothing. |
4790 |
|
# |
4791 |
|
} elsif ($self->{nc} == 0x0023) { # # |
4792 |
|
$self->{ca} = $self->{ct}; |
4793 |
|
$self->{state} = ENTITY_HASH_STATE; |
4794 |
|
$self->{kwd} = '#'; |
4795 |
|
!!!next-input-character; |
4796 |
|
redo A; |
4797 |
|
} elsif ((0x0041 <= $self->{nc} and |
4798 |
|
$self->{nc} <= 0x005A) or # A..Z |
4799 |
|
(0x0061 <= $self->{nc} and |
4800 |
|
$self->{nc} <= 0x007A)) { # a..z |
4801 |
|
# |
4802 |
|
} else { |
4803 |
|
!!!parse-error (type => 'bare ero'); |
4804 |
|
## Return nothing. |
4805 |
|
# |
4806 |
|
} |
4807 |
|
|
4808 |
|
$self->{ct}->{value} .= '&'; |
4809 |
|
$self->{state} = $self->{prev_state}; |
4810 |
|
## Reconsume. |
4811 |
|
redo A; |
4812 |
|
} elsif ($self->{state} == AFTER_ELEMENT_NAME_STATE) { |
4813 |
|
if ($is_space->{$self->{nc}}) { |
4814 |
|
$self->{state} = BEFORE_ELEMENT_CONTENT_STATE; |
4815 |
|
!!!next-input-character; |
4816 |
|
redo A; |
4817 |
|
} elsif ($self->{nc} == 0x0028) { # ( |
4818 |
|
$self->{state} = AFTER_CM_GROUP_OPEN_STATE; |
4819 |
|
$self->{ct}->{content} = ['(']; |
4820 |
|
$self->{group_depth} = 1; |
4821 |
|
!!!next-input-character; |
4822 |
|
redo A; |
4823 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4824 |
|
!!!parse-error (type => 'no md def'); ## TODO: type |
4825 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4826 |
|
!!!next-input-character; |
4827 |
|
!!!emit ($self->{ct}); # ELEMENT |
4828 |
|
redo A; |
4829 |
|
} elsif ($self->{nc} == -1) { |
4830 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4831 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4832 |
|
!!!next-input-character; |
4833 |
|
!!!emit ($self->{ct}); # ELEMENT |
4834 |
|
redo A; |
4835 |
|
} else { |
4836 |
|
$self->{ct}->{content} = [chr $self->{nc}]; |
4837 |
|
$self->{state} = CONTENT_KEYWORD_STATE; |
4838 |
|
!!!next-input-character; |
4839 |
|
redo A; |
4840 |
|
} |
4841 |
|
} elsif ($self->{state} == CONTENT_KEYWORD_STATE) { |
4842 |
|
if ($is_space->{$self->{nc}}) { |
4843 |
|
$self->{state} = AFTER_MD_DEF_STATE; |
4844 |
|
!!!next-input-character; |
4845 |
|
redo A; |
4846 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4847 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4848 |
|
!!!next-input-character; |
4849 |
|
!!!emit ($self->{ct}); # ELEMENT |
4850 |
|
redo A; |
4851 |
|
} elsif ($self->{nc} == -1) { |
4852 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4853 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4854 |
|
!!!next-input-character; |
4855 |
|
!!!emit ($self->{ct}); # ELEMENT |
4856 |
|
redo A; |
4857 |
|
} else { |
4858 |
|
$self->{ct}->{content}->[-1] .= chr $self->{nc}; # ELEMENT |
4859 |
|
## Stay in the state. |
4860 |
|
!!!next-input-character; |
4861 |
|
redo A; |
4862 |
|
} |
4863 |
|
} elsif ($self->{state} == AFTER_CM_GROUP_OPEN_STATE) { |
4864 |
|
if ($is_space->{$self->{nc}}) { |
4865 |
|
## Stay in the state. |
4866 |
|
!!!next-input-character; |
4867 |
|
redo A; |
4868 |
|
} elsif ($self->{nc} == 0x0028) { # ( |
4869 |
|
$self->{group_depth}++; |
4870 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
4871 |
|
## Stay in the state. |
4872 |
|
!!!next-input-character; |
4873 |
|
redo A; |
4874 |
|
} elsif ($self->{nc} == 0x007C or # | |
4875 |
|
$self->{nc} == 0x002C) { # , |
4876 |
|
!!!parse-error (type => 'empty element name'); ## TODO: type |
4877 |
|
## Stay in the state. |
4878 |
|
!!!next-input-character; |
4879 |
|
redo A; |
4880 |
|
} elsif ($self->{nc} == 0x0029) { # ) |
4881 |
|
!!!parse-error (type => 'empty element name'); ## TODO: type |
4882 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
4883 |
|
$self->{group_depth}--; |
4884 |
|
$self->{state} = AFTER_CM_GROUP_CLOSE_STATE; |
4885 |
|
!!!next-input-character; |
4886 |
|
redo A; |
4887 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4888 |
|
!!!parse-error (type => 'unclosed cm group'); ## TODO: type |
4889 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
4890 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4891 |
|
!!!next-input-character; |
4892 |
|
!!!emit ($self->{ct}); # ELEMENT |
4893 |
|
redo A; |
4894 |
|
} elsif ($self->{nc} == -1) { |
4895 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4896 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
4897 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4898 |
|
!!!next-input-character; |
4899 |
|
!!!emit ($self->{ct}); # ELEMENT |
4900 |
|
redo A; |
4901 |
|
} else { |
4902 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
4903 |
|
$self->{state} = CM_ELEMENT_NAME_STATE; |
4904 |
|
!!!next-input-character; |
4905 |
|
redo A; |
4906 |
|
} |
4907 |
|
} elsif ($self->{state} == CM_ELEMENT_NAME_STATE) { |
4908 |
|
if ($is_space->{$self->{nc}}) { |
4909 |
|
$self->{state} = AFTER_CM_ELEMENT_NAME_STATE; |
4910 |
|
!!!next-input-character; |
4911 |
|
redo A; |
4912 |
|
} elsif ($self->{nc} == 0x002A or # * |
4913 |
|
$self->{nc} == 0x002B or # + |
4914 |
|
$self->{nc} == 0x003F) { # ? |
4915 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
4916 |
|
$self->{state} = AFTER_CM_ELEMENT_NAME_STATE; |
4917 |
|
!!!next-input-character; |
4918 |
|
redo A; |
4919 |
|
} elsif ($self->{nc} == 0x007C or # | |
4920 |
|
$self->{nc} == 0x002C) { # , |
4921 |
|
push @{$self->{ct}->{content}}, $self->{nc} == 0x007C ? ' | ' : ', '; |
4922 |
|
$self->{state} = AFTER_CM_GROUP_OPEN_STATE; |
4923 |
|
!!!next-input-character; |
4924 |
|
redo A; |
4925 |
|
} elsif ($self->{nc} == 0x0029) { # ) |
4926 |
|
$self->{group_depth}--; |
4927 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
4928 |
|
$self->{state} = AFTER_CM_GROUP_CLOSE_STATE; |
4929 |
|
!!!next-input-character; |
4930 |
|
redo A; |
4931 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4932 |
|
!!!parse-error (type => 'unclosed cm group'); ## TODO: type |
4933 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
4934 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4935 |
|
!!!next-input-character; |
4936 |
|
!!!emit ($self->{ct}); # ELEMENT |
4937 |
|
redo A; |
4938 |
|
} elsif ($self->{nc} == -1) { |
4939 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4940 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
4941 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4942 |
|
!!!next-input-character; |
4943 |
|
!!!emit ($self->{ct}); # ELEMENT |
4944 |
|
redo A; |
4945 |
|
} else { |
4946 |
|
$self->{ct}->{content}->[-1] .= chr $self->{nc}; |
4947 |
|
## Stay in the state. |
4948 |
|
!!!next-input-character; |
4949 |
|
redo A; |
4950 |
|
} |
4951 |
|
} elsif ($self->{state} == AFTER_CM_ELEMENT_NAME_STATE) { |
4952 |
|
if ($is_space->{$self->{nc}}) { |
4953 |
|
## Stay in the state. |
4954 |
|
!!!next-input-character; |
4955 |
|
redo A; |
4956 |
|
} elsif ($self->{nc} == 0x007C or # | |
4957 |
|
$self->{nc} == 0x002C) { # , |
4958 |
|
push @{$self->{ct}->{content}}, $self->{nc} == 0x007C ? ' | ' : ', '; |
4959 |
|
$self->{state} = AFTER_CM_GROUP_OPEN_STATE; |
4960 |
|
!!!next-input-character; |
4961 |
|
redo A; |
4962 |
|
} elsif ($self->{nc} == 0x0029) { # ) |
4963 |
|
$self->{group_depth}--; |
4964 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
4965 |
|
$self->{state} = AFTER_CM_GROUP_CLOSE_STATE; |
4966 |
|
!!!next-input-character; |
4967 |
|
redo A; |
4968 |
|
} elsif ($self->{nc} == 0x003E) { # > |
4969 |
|
!!!parse-error (type => 'unclosed cm group'); ## TODO: type |
4970 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
4971 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4972 |
|
!!!next-input-character; |
4973 |
|
!!!emit ($self->{ct}); # ELEMENT |
4974 |
|
redo A; |
4975 |
|
} elsif ($self->{nc} == -1) { |
4976 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
4977 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
4978 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
4979 |
|
!!!next-input-character; |
4980 |
|
!!!emit ($self->{ct}); # ELEMENT |
4981 |
|
redo A; |
4982 |
|
} else { |
4983 |
|
!!!parse-error (type => 'after element name'); ## TODO: type |
4984 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
4985 |
|
$self->{state} = BOGUS_MD_STATE; |
4986 |
|
!!!next-input-character; |
4987 |
|
redo A; |
4988 |
|
} |
4989 |
|
} elsif ($self->{state} == AFTER_CM_GROUP_CLOSE_STATE) { |
4990 |
|
if ($is_space->{$self->{nc}}) { |
4991 |
|
if ($self->{group_depth}) { |
4992 |
|
$self->{state} = AFTER_CM_ELEMENT_NAME_STATE; |
4993 |
|
} else { |
4994 |
|
$self->{state} = AFTER_MD_DEF_STATE; |
4995 |
|
} |
4996 |
|
!!!next-input-character; |
4997 |
|
redo A; |
4998 |
|
} elsif ($self->{nc} == 0x002A or # * |
4999 |
|
$self->{nc} == 0x002B or # + |
5000 |
|
$self->{nc} == 0x003F) { # ? |
5001 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
5002 |
|
if ($self->{group_depth}) { |
5003 |
|
$self->{state} = AFTER_CM_ELEMENT_NAME_STATE; |
5004 |
|
} else { |
5005 |
|
$self->{state} = AFTER_MD_DEF_STATE; |
5006 |
|
} |
5007 |
|
!!!next-input-character; |
5008 |
|
redo A; |
5009 |
|
} elsif ($self->{nc} == 0x0029) { # ) |
5010 |
|
if ($self->{group_depth}) { |
5011 |
|
$self->{group_depth}--; |
5012 |
|
push @{$self->{ct}->{content}}, chr $self->{nc}; |
5013 |
|
## Stay in the state. |
5014 |
|
!!!next-input-character; |
5015 |
|
redo A; |
5016 |
|
} else { |
5017 |
|
!!!parse-error (type => 'string after md def'); ## TODO: type |
5018 |
|
$self->{state} = BOGUS_MD_STATE; |
5019 |
|
## Reconsume. |
5020 |
|
redo A; |
5021 |
|
} |
5022 |
|
} elsif ($self->{nc} == 0x003E) { # > |
5023 |
|
if ($self->{group_depth}) { |
5024 |
|
!!!parse-error (type => 'unclosed cm group'); ## TODO: type |
5025 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
5026 |
|
} |
5027 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
5028 |
|
!!!next-input-character; |
5029 |
|
!!!emit ($self->{ct}); # ELEMENT |
5030 |
|
redo A; |
5031 |
|
} elsif ($self->{nc} == -1) { |
5032 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
5033 |
|
push @{$self->{ct}->{content}}, (')') x $self->{group_depth}; |
5034 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
5035 |
|
!!!next-input-character; |
5036 |
|
!!!emit ($self->{ct}); # ELEMENT |
5037 |
|
redo A; |
5038 |
|
} else { |
5039 |
|
if ($self->{group_depth}) { |
5040 |
|
$self->{state} = AFTER_CM_ELEMENT_NAME_STATE; |
5041 |
|
} else { |
5042 |
|
!!!parse-error (type => 'string after md def'); ## TODO: type |
5043 |
|
$self->{state} = BOGUS_MD_STATE; |
5044 |
|
} |
5045 |
|
## Reconsume. |
5046 |
|
redo A; |
5047 |
|
} |
5048 |
|
} elsif ($self->{state} == AFTER_MD_DEF_STATE) { |
5049 |
|
if ($is_space->{$self->{nc}}) { |
5050 |
|
## Stay in the state. |
5051 |
|
!!!next-input-character; |
5052 |
|
redo A; |
5053 |
|
} elsif ($self->{nc} == 0x003E) { # > |
5054 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
5055 |
|
!!!next-input-character; |
5056 |
|
!!!emit ($self->{ct}); # ENTITY/ELEMENT |
5057 |
|
redo A; |
5058 |
|
} elsif ($self->{nc} == -1) { |
5059 |
|
!!!parse-error (type => 'unclosed md'); ## TODO: type |
5060 |
|
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
5061 |
|
!!!next-input-character; |
5062 |
|
!!!emit ($self->{ct}); # ENTITY/ELEMENT |
5063 |
|
redo A; |
5064 |
|
} else { |
5065 |
|
!!!parse-error (type => 'string after md def'); ## TODO: type |
5066 |
|
$self->{state} = BOGUS_MD_STATE; |
5067 |
|
## Reconsume. |
5068 |
|
redo A; |
5069 |
|
} |
5070 |
} elsif ($self->{state} == BOGUS_MD_STATE) { |
} elsif ($self->{state} == BOGUS_MD_STATE) { |
5071 |
if ($self->{nc} == 0x003E) { # > |
if ($self->{nc} == 0x003E) { # > |
5072 |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |
$self->{state} = DOCTYPE_INTERNAL_SUBSET_STATE; |