Skip to content

Parse internal DTDs in doctype declaration #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
paulbijnens wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Parse internal DTDs in doctype declaration #10

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
26071fb
Parse internal DTDs in doctype declaration
paulbijnens Jun 1, 2016
2c39f54
correctly parse comments in the internal DTD
paulbijnens Jun 4, 2016
dd630d4
test case internal dtd parsing
paulbijnens Jun 4, 2016
f3f1867
correctly handle comments inside entity decl and inside words
paulbijnens Jun 5, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions Parser.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -810,8 +810,9 @@ Tokens causes a reference to an array of token strings to be passed.
The strings are exactly as they were found in the original text,
no decoding or case changes are applied.

For C<declaration> events, the array contains each word, comment, and
delimited string starting with the declaration type.
For C<declaration> events, the array contains each word, comment,
internal dtd (including square brackets) and delimited string,
starting with the declaration type.

For C<comment> events, this contains each sub-comment. If
$p->strict_comments is disabled, there will be only one sub-comment.
Expand Down Expand Up @@ -885,8 +886,6 @@ Example:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">

DTDs inside <!DOCTYPE ...> will confuse HTML::Parser.

=item C<default>

This event is triggered for events that do not have a specific
Expand Down
137 changes: 137 additions & 0 deletions hparser.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -957,6 +957,88 @@ parse_comment(PSTATE* p_state, char *beg, char *end, U32 utf8, SV* self)
return 0;
}

static char*
skip_to_end_comment(PSTATE* p_state, char *beg, char *end)
{
char *s = beg;

++s;
if (s == end || *s != '!')
return beg;
++s;
if (s == end || *s != '-')
return beg;
++s;
if (s == end || *s != '-')
return beg;

if (p_state->strict_comment) {
char *start_com = s; /* also used to signal inside/outside */

while (1) {
/* try to locate "--" */
FIND_DASH_DASH:
while (s < end && *s != '-' && *s != '>')
s++;

if (s == end)
return beg;

if (*s == '>') {
if (! start_com)
return s;
s++;
goto FIND_DASH_DASH;
}

s++;
if (s == end)
return beg;

if (*s == '-') {
/* two dashes in a row seen */
s++;
if (start_com)
start_com = 0;
else
start_com = s;
}
}
}
else if (p_state->no_dash_dash_comment_end) {
/* a lone '>' signals end-of-comment */
while (s < end && *s != '>')
s++;
if (s == end)
return beg;
return s;
}
else { /* non-strict comment */
/* try to locate /--\s*>/ which signals end-of-comment */
LOCATE_END:
while (s < end && *s != '-')
s++;
if (s < end) {
s++;
if (*s == '-') {
s++;
while (isHSPACE(*s))
s++;
if (*s == '>') {
return s;
}
}
if (s < end)
goto LOCATE_END;
}

if (s == end)
return beg;
}

return 0;
}


#ifdef MARKED_SECTION

Expand Down Expand Up @@ -1184,6 +1266,61 @@ parse_decl(PSTATE* p_state, char *beg, char *end, U32 utf8, SV* self)
s++;
PUSH_TOKEN(str_beg, s);
}
else if (*s == '[') {
/* internal DTD section between square brackets */
char *intdtd_beg = s;
s++;
if (s == end)
goto PREMATURE;
while (s < end && *s != ']') { /* get the internal dtd - beware of nested comments and strings maybe containing a ] and > chars */
if (*s == '"' || *s == '\'' || (*s == '`' && p_state->backquote)) { /* skip over a quoted string */
char *str_beg = s;
s++;
while (s < end && *s != *str_beg)
s++;
if (s == end)
goto PREMATURE;
}
else if (*s == '-') { /* comments inside entity decl <!ENTITY bracket "]" -- a ] char --> */
s++;
if (s == end)
goto PREMATURE;
if (*s != '-')
goto FAIL;
s++;
while (1) {
while (s < end && *s != '-')
s++;
if (s == end)
goto PREMATURE;
s++;
if (s == end)
goto PREMATURE;
if (*s == '-')
break;
}
if (s == end)
goto PREMATURE;
}
else if (*s == '<') { /* and skip over the <!-- commment --> */
s = skip_to_end_comment(p_state, s, end);
}
else if (isALPHA(*s)) { /* skip over any word maybe containing hyphens */
s++;
while (s < end && isHNOT_SPACE_GT(*s))
s++;
if (s == end)
goto PREMATURE;
}
s++;
if (s == end)
goto PREMATURE;
}
s++;
if (s == end)
goto PREMATURE;
PUSH_TOKEN(intdtd_beg, s);
}
else if (*s == '-') {
/* comment */
char *com_beg = s;
Expand Down
28 changes: 27 additions & 1 deletion t/declaration.t
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
use Test::More tests => 2;
use Test::More tests => 3;

use HTML::Parser;
my $res = "";
Expand Down Expand Up @@ -60,3 +60,29 @@ is($res, <<EOT);
<[]>]
EOT

$res = "";
$p->parse(<<EOT)->eof;
<!DOCTYPE pbi SYSTEM "pbi.dtd" [
<!-- the [internal] dtd -->
<!ENTITY brackets "[]">
<!ENTITY my-ent "<!-- [foo] -->" -- [comment] -->
<!ENTITY dbl--bar " -- [bar] -- ">
<!-- end of internal dtd -->
] >
<pbi>[Content]</pbi>
EOT
is($res, <<EOT);
[<DOCTYPE>
<pbi>
<SYSTEM>
<"pbi.dtd">
<[
<!-- the [internal] dtd -->
<!ENTITY brackets "[]">
<!ENTITY my-ent "<!-- [foo] -->" -- [comment] -->
<!ENTITY dbl--bar " -- [bar] -- ">
<!-- end of internal dtd -->
]>]
<pbi>[Content]</pbi>
EOT