Skip to content

HTML API: Handle area, br, embed, keygen, wbr #5895

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
sirreal wants to merge 11 commits into from
Closed

HTML API: Handle area, br, embed, keygen, wbr #5895

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
c28ea1d
Add "area", "br", "embed", "img", "keygen", "wbr" tag rules
sirreal Jan 18, 2024
2a80cd2
Test tweaks
sirreal Jan 18, 2024
41f9527
Mention ticket, add unsupported test
sirreal Jan 18, 2024
839a715
Add unnestable test
sirreal Jan 18, 2024
4a50cc1
Fix void nesting tests
sirreal Jan 18, 2024
fd26b12
Fix lints
sirreal Jan 18, 2024
94e0ff8
Fix lints
sirreal Jan 18, 2024
8e3b3f2
Remove implemented tags from unsupported list
sirreal Jan 18, 2024
02ffaae
Merge branch 'trunk' into html-api/handle-tags-area_br_embed_keygen_wbr
dmsnell Jan 19, 2024
6f6e09b
Update tests, code styling, comments.
dmsnell Jan 19, 2024
15658e2
Remove superfluous mention of being "incomplete" in test comment.
dmsnell Jan 19, 2024
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
29 changes: 24 additions & 5 deletions src/wp-includes/html-api/class-wp-html-processor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -934,12 +934,29 @@ private function step_in_body() {
$this->run_adoption_agency_algorithm();
return true;


/*
* > An end tag whose tag name is "br"
* > Parse error. Drop the attributes from the token, and act as described in the next
* > entry; i.e. act as if this was a "br" start tag token with no attributes, rather
* > than the end tag token that it actually is.
*/
case '-BR':
$this->last_error = self::ERROR_UNSUPPORTED;
throw new WP_HTML_Unsupported_Exception( "Closing BR tags require unimplemented special handling." );

/*
* > A start tag whose tag name is one of: "area", "br", "embed", "img", "keygen", "wbr"
*/
case '+AREA':
case '+BR':
case '+EMBED':
case '+IMG':
case '+KEYGEN':
case '+WBR':
$this->reconstruct_active_formatting_elements();
$this->insert_html_element( $this->state->current_token );
$this->state->frameset_ok = false;
return true;
}

Expand All @@ -966,13 +983,11 @@ private function step_in_body() {
case 'BASEFONT':
case 'BGSOUND':
case 'BODY':
case 'BR':
case 'CAPTION':
case 'COL':
case 'COLGROUP':
case 'DD':
case 'DT':
case 'EMBED':
case 'FORM':
case 'FRAME':
case 'FRAMESET':
Expand All @@ -981,7 +996,6 @@ private function step_in_body() {
case 'HTML':
case 'IFRAME':
case 'INPUT':
case 'KEYGEN':
case 'LI':
case 'LINK':
case 'LISTING':
Expand Down Expand Up @@ -1021,7 +1035,6 @@ private function step_in_body() {
case 'TR':
case 'TRACK':
case 'UL':
case 'WBR':
case 'XMP':
$this->last_error = self::ERROR_UNSUPPORTED;
throw new WP_HTML_Unsupported_Exception( "Cannot process {$tag_name} element." );
Expand Down Expand Up @@ -1685,7 +1698,13 @@ public static function is_void( $tag_name ) {
'META' === $tag_name ||
'SOURCE' === $tag_name ||
'TRACK' === $tag_name ||
'WBR' === $tag_name
'WBR' === $tag_name ||

// Obsolete
//
// This does not appear in https://html.spec.whatwg.org/#void-elements
// but it was a void tag and browsers treat it as such.
'KEYGEN' === $tag_name
Copy link
Copy Markdown
Member Author

@sirreal sirreal Jan 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Demo

Screenshot 2024-01-18 at 16 37 32

);
}

Expand Down
65 changes: 60 additions & 5 deletions tests/phpunit/tests/html-api/wpHtmlProcessor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,6 +132,66 @@ public function test_fails_to_reconstruct_formatting_elements() {
$this->assertFalse( $p->next_tag( 'EM' ), 'Should have aborted before finding second EM as it required reconstructing the first EM.' );
}

/**
* Ensure non-nesting tags do not nest
*
* @ticket 60283
*
* @covers WP_HTML_Processor::step_in_body
* @covers WP_HTML_Processor::is_void
*
* @dataProvider data_void_tags
*/
public function test_cannot_nest_void_tags( $tag ) {
$p = WP_HTML_Processor::create_fragment( "{$tag}<div>" );

// We should have this structure:
// <html>
// <body>
// <$TAG />
// <$TAG />
// </body>
// </html>
//
// The breadcrumbs should be:
// HTML > BODY > $TAG

$result = $p->next_tag();

if ( WP_HTML_Processor::ERROR_UNSUPPORTED === $p->get_last_error() ) {
$this->markTestSkipped( "{$tag} is unsupported." );
}

$this->assertTrue( $result, "Could not find first {$tag}." );
$this->assertCount( 3, $p->get_breadcrumbs(), "{$tag} was not nested correctly." );
$this->assertTrue( $p->next_tag( 'DIV' ), "Could not find <div> tag." );
$this->assertCount( 3, $p->get_breadcrumbs(), "Following <div> was not nested correctly." );
}

/**
* Data provider.
*
* @return array[]
*/
public function data_void_tags() {
return array(
'AREA' => array( '<area>' ),
'BASE' => array( '<base>' ),
'BR' => array( '<br>' ),
'COL' => array( '<col>' ),
'EMBED' => array( '<embed>' ),
'HR' => array( '<hr>' ),
'IMG' => array( '<img>' ),
'INPUT' => array( '<input>' ),
'KEYGEN' => array( '<keygen>' ),
'LINK' => array( '<link>' ),
'META' => array( '<meta>' ),
'SOURCE' => array( '<source>' ),
'TRACK' => array( '<track>' ),
'WBR' => array( '<wbr>' ),
);
}

/**
* Ensures that special handling of unsupported tags is cleaned up
* as handling is implemented. Otherwise there's risk of leaving special
Expand Down Expand Up @@ -159,16 +219,13 @@ public function test_step_in_body_fails_on_unsupported_tags( $tag_name ) {
public function data_unsupported_special_in_body_tags() {
return array(
'APPLET' => array( 'APPLET' ),
'AREA' => array( 'AREA' ),
'BASE' => array( 'BASE' ),
'BASEFONT' => array( 'BASEFONT' ),
'BGSOUND' => array( 'BGSOUND' ),
'BODY' => array( 'BODY' ),
'BR' => array( 'BR' ),
'CAPTION' => array( 'CAPTION' ),
'COL' => array( 'COL' ),
'COLGROUP' => array( 'COLGROUP' ),
'EMBED' => array( 'EMBED' ),
'FORM' => array( 'FORM' ),
'FRAME' => array( 'FRAME' ),
'FRAMESET' => array( 'FRAMESET' ),
Expand All @@ -177,7 +234,6 @@ public function data_unsupported_special_in_body_tags() {
'HTML' => array( 'HTML' ),
'IFRAME' => array( 'IFRAME' ),
'INPUT' => array( 'INPUT' ),
'KEYGEN' => array( 'KEYGEN' ),
'LINK' => array( 'LINK' ),
'LISTING' => array( 'LISTING' ),
'MARQUEE' => array( 'MARQUEE' ),
Expand Down Expand Up @@ -214,7 +270,6 @@ public function data_unsupported_special_in_body_tags() {
'TITLE' => array( 'TITLE' ),
'TR' => array( 'TR' ),
'TRACK' => array( 'TRACK' ),
'WBR' => array( 'WBR' ),
'XMP' => array( 'XMP' ),
);
}
Expand Down
52 changes: 52 additions & 0 deletions tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -376,4 +376,56 @@ public function test_in_body_any_other_end_tag_with_unclosed_non_special_element
$this->assertSame( 'DIV', $p->get_tag(), "Expected to find DIV element, but found {$p->get_tag()} instead." );
$this->assertSame( array( 'HTML', 'BODY', 'DIV', 'DIV' ), $p->get_breadcrumbs(), 'Failed to produce expected DOM nesting: SPAN should be closed and DIV should be its sibling.' );
}

/**
* Verifies that when "in body" and encountering a BR end tag `</br …>`:
*
* > An end tag whose tag name is "br"
* > Parse error. Drop the attributes from the token, and act as described in the next entry;
* > i.e. act as if this was a "br" start tag token with no attributes, rather than the end
* > tag token that it actually is.
*
* When this handling is implemented, this test should be removed and
* `test_br_end_tag_special_behavior` should not be marked incomplete.
*
* @covers WP_HTML_Processor::step_in_body
*
* @ticket 60283
*
* @since 6.4.0
*/
public function test_br_end_tag_unsupported() {
$p = WP_HTML_Processor::create_fragment( '</br>' );

$this->assertFalse( $p->next_tag(), 'Found a BR tag that should not be handled.' );
$this->assertSame( WP_HTML_Processor::ERROR_UNSUPPORTED, $p->get_last_error() );
}

/**
* Verifies that when "in body" and encountering a BR end tag `</br …>`:
*
* > An end tag whose tag name is "br"
* > Parse error. Drop the attributes from the token, and act as described in the next entry;
* > i.e. act as if this was a "br" start tag token with no attributes, rather than the end
* > tag token that it actually is.
*
* @covers WP_HTML_Processor::step_in_body
*
* @ticket 60283
*
* @since 6.4.0
*/
public function test_br_end_tag_special_behavior() {
$this->markTestIncomplete( 'BR end tag special handling is unimplemented' );

$p = WP_HTML_Processor::create_fragment( '</br attribute="must be removed">' );

$this->assertTrue( $p->next_tag(), 'No BR tag found.' );
$this->assertFalse( $p->is_tag_closer(), '</br> should not be treated as an end tag.' );
$this->assertNull( $p->get_attribute_names_with_prefix( '' ), 'BR end tag had attributes.' );
$this->assertFalse( $p->set_attribute( 'new-attribute', 'added' ), 'BR end tag becomes an opener' );
$this->assertCount( 1, $p->get_attribute_names_with_prefix( '' ), 'Tag should have 1 attribute.' );
$this->assertSame( 'added', $p->get_attribute( 'new-attribute' ), 'Tag did not set attribute value correctly.' );
$this->assertSame( '<br new-attribute="added">', $p->get_updated_html(), 'Tag HTML was not updated correctly.' );
}
}