WordPress-C
/
WordPress
mirror of https://github.com/WordPress/WordPress.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

HTML API: Ensure that NULL and whitespace-only CDATA sections don't forbid FRAMESET. 

When CDATA sections (which can only occur inside SVG and MathML content) consist only of NULL bytes or whitespace characters they should not clear the "frameset ok" flag. Previously they have always been clearing this flag, but in this patch the logic is updated to detect these sequences properly.

Developed in https://github.com/WordPress/wordpress-develop/pull/7230
Discussed in https://core.trac.wordpress.org/ticket/61576

Follow-up to [58867].

Props dmsnell, jonsurrell.
See #61576.

Built from https://develop.svn.wordpress.org/trunk@58977


git-svn-id: http://core.svn.wordpress.org/trunk@58373 1a063a9b-81f0-0310-95a4-ce76da25c4cd
This commit is contained in:
dmsnell 2024-09-03 19:50:14 +00:00
parent 8d1fb4e25a
commit 2ce04ceab9
3 changed files with 66 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
wp-includes/html-api/class-wp-html-processor.php
View File

@ -843,10 +843,7 @@ class WP_HTML_Processor extends WP_HTML_Tag_Processor {
if ( self::PROCESS_NEXT_NODE === $node_to_process ) { if ( self::PROCESS_NEXT_NODE === $node_to_process ) {
parent::next_token(); parent::next_token();
if ( if ( WP_HTML_Tag_Processor::STATE_TEXT_NODE === $this->parser_state ) {
WP_HTML_Tag_Processor::STATE_TEXT_NODE === $this->parser_state ||
WP_HTML_Tag_Processor::STATE_CDATA_NODE === $this->parser_state
) {
parent::subdivide_text_appropriately(); parent::subdivide_text_appropriately();
} }
} }
@ -4375,7 +4372,6 @@ class WP_HTML_Processor extends WP_HTML_Tag_Processor {
} }
switch ( $op ) { switch ( $op ) {
case '#cdata-section':
case '#text': case '#text':
/* /*
* > A character token that is U+0000 NULL * > A character token that is U+0000 NULL
@ -4395,6 +4391,24 @@ class WP_HTML_Processor extends WP_HTML_Tag_Processor {
$this->insert_foreign_element( $this->state->current_token, false ); $this->insert_foreign_element( $this->state->current_token, false );
return true; return true;
/*
* CDATA sections are alternate wrappers for text content and therefore
* ought to follow the same rules as text nodes.
*/
case '#cdata-section':
/*
* NULL bytes and whitespace do not change the frameset-ok flag.
*/
$current_token = $this->bookmarks[ $this->state->current_token->bookmark_name ];
$cdata_content_start = $current_token->start + 9;
$cdata_content_length = $current_token->length - 12;
if ( strspn( $this->html, "\0 \t\n\f\r", $cdata_content_start, $cdata_content_length ) !== $cdata_content_length ) {
$this->state->frameset_ok = false;
}
$this->insert_foreign_element( $this->state->current_token, false );
return true;
/* /*
* > A comment token * > A comment token
*/ */

107
wp-includes/html-api/class-wp-html-tag-processor.php
View File

@ -3337,8 +3337,8 @@ class WP_HTML_Tag_Processor {
} }
/** /**
* Subdivides a matched text node or CDATA text node, splitting NULL byte sequences * Subdivides a matched text node, splitting NULL byte sequences and decoded whitespace as
* and decoded whitespace as distinct prefixes. * distinct nodes prefixes.
* *
* Note that once anything that's neither a NULL byte nor decoded whitespace is * Note that once anything that's neither a NULL byte nor decoded whitespace is
* encountered, then the remainder of the text node is left intact as generic text. * encountered, then the remainder of the text node is left intact as generic text.
@ -3368,70 +3368,55 @@ class WP_HTML_Tag_Processor {
* @return bool Whether the text node was subdivided. * @return bool Whether the text node was subdivided.
*/ */
public function subdivide_text_appropriately(): bool { public function subdivide_text_appropriately(): bool {
$this->text_node_classification = self::TEXT_IS_GENERIC; if ( self::STATE_TEXT_NODE !== $this->parser_state ) {
if ( self::STATE_TEXT_NODE === $this->parser_state ) {
/*
* NULL bytes are treated categorically different than numeric character
* references whose number is zero. `�` is not the same as `"\x00"`.
*/
$leading_nulls = strspn( $this->html, "\x00", $this->text_starts_at, $this->text_length );
if ( $leading_nulls > 0 ) {
$this->token_length = $leading_nulls;
$this->text_length = $leading_nulls;
$this->bytes_already_parsed = $this->token_starts_at + $leading_nulls;
$this->text_node_classification = self::TEXT_IS_NULL_SEQUENCE;
return true;
}
/*
* Start a decoding loop to determine the point at which the
* text subdivides. This entails raw whitespace bytes and any
* character reference that decodes to the same.
*/
$at = $this->text_starts_at;
$end = $this->text_starts_at + $this->text_length;
while ( $at < $end ) {
$skipped = strspn( $this->html, " \t\f\r\n", $at, $end - $at );
$at += $skipped;
if ( $at < $end && '&' === $this->html[ $at ] ) {
$matched_byte_length = null;
$replacement = WP_HTML_Decoder::read_character_reference( 'data', $this->html, $at, $matched_byte_length );
if ( isset( $replacement ) && 1 === strspn( $replacement, " \t\f\r\n" ) ) {
$at += $matched_byte_length;
continue;
}
}
break;
}
if ( $at > $this->text_starts_at ) {
$new_length = $at - $this->text_starts_at;
$this->text_length = $new_length;
$this->token_length = $new_length;
$this->bytes_already_parsed = $at;
$this->text_node_classification = self::TEXT_IS_WHITESPACE;
return true;
}
return false; return false;
} }
// Unlike text nodes, there are no character references within CDATA sections. $this->text_node_classification = self::TEXT_IS_GENERIC;
if ( self::STATE_CDATA_NODE === $this->parser_state ) {
$leading_nulls = strspn( $this->html, "\x00", $this->text_starts_at, $this->text_length ); /*
if ( $leading_nulls === $this->text_length ) { * NULL bytes are treated categorically different than numeric character
$this->text_node_classification = self::TEXT_IS_NULL_SEQUENCE; * references whose number is zero. `&#x00;` is not the same as `"\x00"`.
return true; */
$leading_nulls = strspn( $this->html, "\x00", $this->text_starts_at, $this->text_length );
if ( $leading_nulls > 0 ) {
$this->token_length = $leading_nulls;
$this->text_length = $leading_nulls;
$this->bytes_already_parsed = $this->token_starts_at + $leading_nulls;
$this->text_node_classification = self::TEXT_IS_NULL_SEQUENCE;
return true;
}
/*
* Start a decoding loop to determine the point at which the
* text subdivides. This entails raw whitespace bytes and any
* character reference that decodes to the same.
*/
$at = $this->text_starts_at;
$end = $this->text_starts_at + $this->text_length;
while ( $at < $end ) {
$skipped = strspn( $this->html, " \t\f\r\n", $at, $end - $at );
$at += $skipped;
if ( $at < $end && '&' === $this->html[ $at ] ) {
$matched_byte_length = null;
$replacement = WP_HTML_Decoder::read_character_reference( 'data', $this->html, $at, $matched_byte_length );
if ( isset( $replacement ) && 1 === strspn( $replacement, " \t\f\r\n" ) ) {
$at += $matched_byte_length;
continue;
}
} }
$leading_ws = strspn( $this->html, " \t\f\r\n", $this->text_starts_at, $this->text_length ); break;
if ( $leading_ws === $this->text_length ) { }
$this->text_node_classification = self::TEXT_IS_WHITESPACE;
return true; if ( $at > $this->text_starts_at ) {
} $new_length = $at - $this->text_starts_at;
$this->text_length = $new_length;
$this->token_length = $new_length;
$this->bytes_already_parsed = $at;
$this->text_node_classification = self::TEXT_IS_WHITESPACE;
return true;
} }
return false; return false;

2
wp-includes/version.php
View File

@ -16,7 +16,7 @@
* *
* @global string $wp_version * @global string $wp_version
*/ */
$wp_version = '6.7-alpha-58976'; $wp_version = '6.7-alpha-58977';
/** /**
* Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema. * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.