Skip to content

HTML API: avoid processing incomplete tokens #5725

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

Closed
dmsnell wants to merge 4 commits into from
Closed

HTML API: avoid processing incomplete tokens #5725

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
35502ad
HTML API: Avoid processing incomplete syntax elements.
dmsnell Dec 10, 2023
c3166be
Add ticket number
dmsnell Dec 20, 2023
9e7167a
HTML API: Prevent out-of-bounds string access.
dmsnell Dec 20, 2023
8488317
Fix bug found from HTML5Tests for incomplete SCRIPT tag closer
dmsnell Dec 20, 2023
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
Prev Previous commit
Next Next commit
HTML API: Prevent out-of-bounds string access. 
Rebuild of 8905faf after #5725.

Co-authored-by: Jon Surrell <[email protected]>
Co-authored-by: Bernie Reiter <[email protected]>
  • Loading branch information
@dmsnell @sirreal @ockham
3 people committed Dec 20, 2023
commit 9e7167a3d1b4b4d1e4525072b2f96779788fb92d
21 changes: 13 additions & 8 deletions src/wp-includes/html-api/class-wp-html-tag-processor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1312,7 +1312,7 @@ private function parse_next_tag() {

$this->token_starts_at = $at;

if ( '/' === $this->html[ $at + 1 ] ) {
if ( $at + 1 < $doc_length && '/' === $this->html[ $at + 1 ] ) {
$this->is_closing_tag = true;
++$at;
} else {
Expand Down Expand Up @@ -1346,7 +1346,7 @@ private function parse_next_tag() {
* Abort if no tag is found before the end of
* the document. There is nothing left to parse.
*/
if ( $at + 1 >= strlen( $html ) ) {
if ( $at + 1 >= $doc_length ) {
$this->parser_state = self::STATE_INCOMPLETE;

return false;
Expand All @@ -1368,7 +1368,7 @@ private function parse_next_tag() {
) {
$closer_at = $at + 4;
// If it's not possible to close the comment then there is nothing more to scan.
if ( strlen( $html ) <= $closer_at ) {
if ( $doc_length <= $closer_at ) {
$this->parser_state = self::STATE_INCOMPLETE;

return false;
Expand All @@ -1388,20 +1388,20 @@ private function parse_next_tag() {
* See https://html.spec.whatwg.org/#parse-error-incorrectly-closed-comment
*/
--$closer_at; // Pre-increment inside condition below reduces risk of accidental infinite looping.
while ( ++$closer_at < strlen( $html ) ) {
while ( ++$closer_at < $doc_length ) {
$closer_at = strpos( $html, '--', $closer_at );
if ( false === $closer_at ) {
$this->parser_state = self::STATE_INCOMPLETE;

return false;
}

if ( $closer_at + 2 < strlen( $html ) && '>' === $html[ $closer_at + 2 ] ) {
if ( $closer_at + 2 < $doc_length && '>' === $html[ $closer_at + 2 ] ) {
$at = $closer_at + 3;
continue 2;
}

if ( $closer_at + 3 < strlen( $html ) && '!' === $html[ $closer_at + 2 ] && '>' === $html[ $closer_at + 3 ] ) {
if ( $closer_at + 3 < $doc_length && '!' === $html[ $closer_at + 2 ] && '>' === $html[ $closer_at + 3 ] ) {
$at = $closer_at + 4;
continue 2;
}
Expand All @@ -1414,7 +1414,7 @@ private function parse_next_tag() {
* https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
*/
if (
strlen( $html ) > $at + 8 &&
$doc_length > $at + 8 &&
'[' === $html[ $at + 2 ] &&
'C' === $html[ $at + 3 ] &&
'D' === $html[ $at + 4 ] &&
Expand All @@ -1440,7 +1440,7 @@ private function parse_next_tag() {
* https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
*/
if (
strlen( $html ) > $at + 8 &&
$doc_length > $at + 8 &&
( 'D' === $html[ $at + 2 ] || 'd' === $html[ $at + 2 ] ) &&
( 'O' === $html[ $at + 3 ] || 'o' === $html[ $at + 3 ] ) &&
( 'C' === $html[ $at + 4 ] || 'c' === $html[ $at + 4 ] ) &&
Expand Down Expand Up @@ -1512,6 +1512,11 @@ private function parse_next_tag() {
* See https://html.spec.whatwg.org/#parse-error-invalid-first-character-of-tag-name
*/
if ( $this->is_closing_tag ) {
// No chance of finding a closer.
if ( $at + 3 > $doc_length ) {
return false;
}

$closer_at = strpos( $html, '>', $at + 3 );
if ( false === $closer_at ) {
$this->parser_state = self::STATE_INCOMPLETE;
Expand Down
18 changes: 18 additions & 0 deletions tests/phpunit/tests/html-api/wpHtmlTagProcessor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2691,4 +2691,22 @@ public function data_updating_attributes_in_malformed_html() {
),
);
}

/**
* @covers WP_HTML_Tag_Processor::next_tag
*/
public function test_handles_malformed_taglike_open_short_html() {
$p = new WP_HTML_Tag_Processor( '<' );
$result = $p->next_tag();
$this->assertFalse( $result, 'Did not handle "<" html properly.' );
}

/**
* @covers WP_HTML_Tag_Processor::next_tag
*/
public function test_handles_malformed_taglike_close_short_html() {
$p = new WP_HTML_Tag_Processor( '</ ' );
$result = $p->next_tag();
$this->assertFalse( $result, 'Did not handle "</ " html properly.' );
}
}