Changeset 58712

Timestamp:

07/12/2024 09:58:20 PM (3 months ago)

Author:

dmsnell

Message:

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

Many tests from the html5lib test suite fail because of differences in
text handling between a DOM API and the HTML API, even though the
semantics of the parse are equivalent. For example, it's possible in
the HTML API to read multiple successive text nodes when the tokens
between them are ignored.

The test suite didn't account for this and so was failing tests. This
patch improves the construction of the representation to compare
against the test suite so that those tests don't fail inaccurately.

Developed in ​https://github.com/WordPress/wordpress-develop/pull/6984
Discussed in https://core.trac.wordpress.org/ticket/61576

Props bernhard-reiter, dmsnell, jonsurrell.
See #61576.

File:

• trunk/tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php (modified) (6 diffs)

trunk/tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php

@@ -41 +41 @@
         '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.',
@@ -52 +51 @@
         '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.',
     );
-
 
     /**
@@ -161 +153 @@
         $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 = '';
             }
 
@@ -199 +199 @@
                             $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;
+                        }
                     }
 
@@ -204 +215 @@
 
                 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;
 
@@ -237 +252 @@
         if ( $processor->paused_at_incomplete_token() ) {
             return null;
+        }
+
+        if ( '' !== $text_node ) {
+            $output .= "${text_node}\"\n";
         }