Changeset 58233

Timestamp:

05/29/2024 11:40:16 AM (2 months ago)

Author:

dmsnell

Message:

HTML API: Fix token length bug in Tag Processor.

The Tag Processor stores the byte-offsets into its HTML document where
the current token starts and ends, and also for every bookmark. In some
cases for tags, the end offset has been off by one.

In this patch the offset is fixed so that a bookmark always properly
refers to the full span of the token it's bookmarking. Also the current
token byte offsets are properly recorded.

While this is a defect in the Tag Processor, it hasn't been exposed
through the public interface and has not affected any of the working
of the processor. Only subclasses which rely on the length of a bookmark
have been potentially affected, and these are not supported environments
in the ongoing work.

This fix is important for future work and for ensuring that subclasses
performing custom behaviors remain as reliable as the public interface.

Developed in ​https://github.com/WordPress/wordpress-develop/pull/6625
Discussed in https://core.trac.wordpress.org/ticket/61301

Props dmsnell, gziolo, jonsurrell, westonruter.
Fixes #61301.

Location:

trunk

Files:

• src/wp-includes/html-api/class-wp-html-tag-processor.php (modified) (3 diffs)
• src/wp-includes/interactivity-api/class-wp-interactivity-api-directives-processor.php (modified) (2 diffs)
• tests/phpunit/tests/html-api/wpHtmlTagProcessor.php (modified) (2 diffs)

trunk/src/wp-includes/html-api/class-wp-html-tag-processor.php

@@ -927 +927 @@
         }
         $this->parser_state         = self::STATE_MATCHED_TAG;
-        $this->token_length         = $tag_ends_at - $this->token_starts_at;
         $this->bytes_already_parsed = $tag_ends_at + 1;
+
 
         /*
@@ -1014 +1014 @@
         $this->token_starts_at      = $was_at;
         $this->token_length         = $this->bytes_already_parsed - $this->token_starts_at;
-        $this->text_starts_at       = $tag_ends_at + 1;
+        $this->text_starts_at       = $tag_ends_at;
         $this->text_length          = $this->tag_name_starts_at - $this->text_starts_at;
         $this->tag_name_starts_at   = $tag_name_starts_at;
@@ -2688 +2688 @@
          *             ^ this appears one character before the end of the closing ">".
          */
-        return '/' === $this->html[ $this->token_starts_at + $this->token_length - 1 ];
+        return '/' === $this->html[ $this->token_starts_at + $this->token_length -  ];
     }
 

trunk/src/wp-includes/interactivity-api/class-wp-interactivity-api-directives-processor.php

@@ -108 +108 @@
         $bookmark = 'append_content_after_template_tag_closer';
         $this->set_bookmark( $bookmark );
-        $after_closing_tag = $this->bookmarks[ $bookmark ]->start + $this->bookmarks[ $bookmark ]->length + 1;
+        $after_closing_tag = $this->bookmarks[ $bookmark ]->start + $this->bookmarks[ $bookmark ]->length;
         $this->release_bookmark( $bookmark );
 
@@ -141 +141 @@
         list( $opener_tag, $closer_tag ) = $bookmarks;
 
-        $after_opener_tag  = $this->bookmarks[ $opener_tag ]->start + $this->bookmarks[ $opener_tag ]->length + 1;
+        $after_opener_tag  = $this->bookmarks[ $opener_tag ]->start + $this->bookmarks[ $opener_tag ]->length;
         $before_closer_tag = $this->bookmarks[ $closer_tag ]->start;
 

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

@@ -475 +475 @@
 
         $this->assertSame( '<div wonky><img hidden></div>', $processor->get_updated_html() );
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
     }
 
@@ -2747 +2850 @@
                 $this->set_bookmark( 'here' );
                 $this->lexical_updates[] = new WP_HTML_Text_Replacement(
-                    $this->bookmarks['here']->start + $this->bookmarks['here']->length + 1,
+                    $this->bookmarks['here']->start + $this->bookmarks['here']->length,
                     0,
                     $new_html