Skip to content

HTML API: Join successive text nodes in html5lib test representation. #6984

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 3 commits into from
Closed

HTML API: Join successive text nodes in html5lib test representation. #6984

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fab21ab
HTML API: Join successive text nodes in html5lib test representation.
dmsnell Jul 6, 2024
c588ccc
Stop skipping tests which don't need to be skipped.
dmsnell Jul 6, 2024
c45e1dc
Merge branch 'trunk' into html-api/join-text-nodes-in-html5lib-test-r…
dmsnell Jul 12, 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
37 changes: 28 additions & 9 deletions tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,6 @@ class Tests_HtmlApi_Html5lib extends WP_UnitTestCase {
'menuitem-element/line0012' => 'Bug.',
'tests1/line0342' => "Closing P tag implicitly creates opener, which we don't visit.",
'tests1/line0720' => 'Unimplemented: Reconstruction of active formatting elements.',
'tests1/line0833' => 'Bug.',
'tests15/line0001' => 'Unimplemented: Reconstruction of active formatting elements.',
'tests15/line0022' => 'Unimplemented: Reconstruction of active formatting elements.',
'tests2/line0650' => 'Whitespace only test never enters "in body" parsing mode.',
Expand All @@ -51,15 +50,8 @@ class Tests_HtmlApi_Html5lib extends WP_UnitTestCase {
'tests23/line0101' => 'Unimplemented: Reconstruction of active formatting elements.',
'tests25/line0169' => 'Bug.',
'tests26/line0263' => 'Bug: An active formatting element should be created for a trailing text node.',
'tests7/line0354' => 'Bug.',
'tests8/line0001' => 'Bug.',
'tests8/line0020' => 'Bug.',
'tests8/line0037' => 'Bug.',
'tests8/line0052' => 'Bug.',
'webkit01/line0174' => 'Bug.',
);


/**
* Verify the parsing results of the HTML Processor against the
* test cases in the Html5lib tests project.
Expand Down Expand Up @@ -160,12 +152,20 @@ private static function build_tree_representation( ?string $fragment_context, st
// Initially, assume we're 2 levels deep at: html > body > [position]
$indent_level = 2;
$indent = ' ';
$was_text = null;
$text_node = '';

while ( $processor->next_token() ) {
if ( ! is_null( $processor->get_last_error() ) ) {
return null;
}

if ( $was_text && '#text' !== $processor->get_token_name() ) {
$output .= "{$text_node}\"\n";
$was_text = false;
$text_node = '';
}

switch ( $processor->get_token_type() ) {
case '#tag':
$tag_name = strtolower( $processor->get_tag() );
Expand Down Expand Up @@ -198,12 +198,27 @@ private static function build_tree_representation( ?string $fragment_context, st
}
$output .= str_repeat( $indent, $tag_indent + 1 ) . "{$attribute_name}=\"{$val}\"\n";
}

// Self-contained tags contain their inner contents as modifiable text.
$modifiable_text = $processor->get_modifiable_text();
if ( '' !== $modifiable_text ) {
$was_text = true;
if ( '' === $text_node ) {
$text_node = str_repeat( $indent, $indent_level ) . '"';
}
$text_node .= $modifiable_text;
--$indent_level;
}
}

break;

case '#text':
$output .= str_repeat( $indent, $indent_level ) . "\"{$processor->get_modifiable_text()}\"\n";
$was_text = true;
if ( '' === $text_node ) {
$text_node .= str_repeat( $indent, $indent_level ) . '"';
}
$text_node .= $processor->get_modifiable_text();
break;

case '#comment':
Expand Down Expand Up @@ -238,6 +253,10 @@ private static function build_tree_representation( ?string $fragment_context, st
return null;
}

if ( '' !== $text_node ) {
$output .= "${text_node}\"\n";
}

// Tests always end with a trailing newline.
return $output . "\n";
}
Expand Down