Changeset 58233 for trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php

Timestamp:

05/29/2024 11:40:16 AM (5 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.

File:

• trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php (modified) (2 diffs)

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

@@ -475 +475 @@
 
         $this->assertSame( '<div wonky><img hidden></div>', $processor->get_updated_html() );
+    }
+
+    /**
+     * Ensures that bookmarks start and length correctly describe a given token in HTML.
+     *
+     * @ticket 61301
+     *
+     * @dataProvider data_html_nth_token_substring
+     *
+     * @param string $html            Input HTML.
+     * @param int    $match_nth_token Which token to inspect from input HTML.
+     * @param string $expected_match  Expected full raw token bookmark should capture.
+     */
+    public function test_token_bookmark_span( string $html, int $match_nth_token, string $expected_match ) {
+        $processor = new class( $html ) extends WP_HTML_Tag_Processor {
+            /**
+             * Returns the raw span of HTML for the currently-matched
+             * token, or null if not paused on any token.
+             *
+             * @return string|null Raw HTML content of currently-matched token,
+             *                     otherwise `null` if not matched.
+             */
+            public function get_raw_token() {
+                if (
+                    WP_HTML_Tag_Processor::STATE_READY === $this->parser_state ||
+                    WP_HTML_Tag_Processor::STATE_INCOMPLETE_INPUT === $this->parser_state ||
+                    WP_HTML_Tag_Processor::STATE_COMPLETE === $this->parser_state
+                ) {
+                    return null;
+                }
+
+                $this->set_bookmark( 'mark' );
+                $mark = $this->bookmarks['mark'];
+
+                return substr( $this->html, $mark->start, $mark->length );
+            }
+        };
+
+        for ( $i = 0; $i < $match_nth_token; $i++ ) {
+            $processor->next_token();
+        }
+
+        $raw_token = $processor->get_raw_token();
+        $this->assertIsString(
+            $raw_token,
+            "Failed to find raw token at position {$match_nth_token}: check test data provider."
+        );
+
+        $this->assertSame(
+            $expected_match,
+            $raw_token,
+            'Bookmarked wrong span of text for full matched token.'
+        );
+    }
+
+    /**
+     * Data provider.
+     *
+     * @return array
+     */
+    public static function data_html_nth_token_substring() {
+        return array(
+            // Tags.
+            'DIV start tag'                 => array( '<div>', 1, '<div>' ),
+            'DIV start tag with attributes' => array( '<div class="x" disabled>', 1, '<div class="x" disabled>' ),
+            'DIV end tag'                   => array( '</div>', 1, '</div>' ),
+            'DIV end tag with attributes'   => array( '</div class="x" disabled>', 1, '</div class="x" disabled>' ),
+            'Nested DIV'                    => array( '<div><div b>', 2, '<div b>' ),
+            'Sibling DIV'                   => array( '<div></div><div b>', 3, '<div b>' ),
+            'DIV after text'                => array( 'text <div>', 2, '<div>' ),
+            'DIV before text'               => array( '<div> text', 1, '<div>' ),
+            'DIV after comment'             => array( '<!-- comment --><div>', 2, '<div>' ),
+            'DIV before comment'            => array( '<div><!-- c --> ', 1, '<div>' ),
+            'Start "self-closing" tag'      => array( '<div />', 1, '<div />' ),
+            'Void tag'                      => array( '<img src="img.png">', 1, '<img src="img.png">' ),
+            'Void tag w/self-closing flag'  => array( '<img src="img.png" />', 1, '<img src="img.png" />' ),
+            'Void tag inside DIV'           => array( '<div><img src="img.png"></div>', 2, '<img src="img.png">' ),
+
+            // Special atomic tags.
+            'SCRIPT tag'                    => array( '<script>inside text</script>', 1, '<script>inside text</script>' ),
+            'SCRIPT double-escape'          => array( '<script><!-- <script> echo "</script>"; </script><div>', 1, '<script><!-- <script> echo "</script>"; </script>' ),
+
+            // Text.
+            'Text'                          => array( 'Just text', 1, 'Just text' ),
+            'Text in DIV'                   => array( '<div>Text<div>', 2, 'Text' ),
+            'Text before DIV'               => array( 'Text<div>', 1, 'Text' ),
+            'Text after DIV'                => array( '<div></div>Text', 3, 'Text' ),
+            'Text after comment'            => array( '<!-- comment -->Text', 2, 'Text' ),
+            'Text before comment'           => array( 'Text<!-- c --> ', 1, 'Text' ),
+
+            // Comments.
+            'Comment'                       => array( '<!-- comment -->', 1, '<!-- comment -->' ),
+            'Comment in DIV'                => array( '<div><!-- comment --><div>', 2, '<!-- comment -->' ),
+            'Comment before DIV'            => array( '<!-- comment --><div>', 1, '<!-- comment -->' ),
+            'Comment after DIV'             => array( '<div></div><!-- comment -->', 3, '<!-- comment -->' ),
+            'Comment after comment'         => array( '<!-- comment --><!-- comment -->', 2, '<!-- comment -->' ),
+            'Comment before comment'        => array( '<!-- comment --><!-- c --> ', 1, '<!-- comment -->' ),
+            'Abruptly closed comment'       => array( '<!-->', 1, '<!-->' ),
+            'Empty comment'                 => array( '<!---->', 1, '<!---->' ),
+            'Funky comment'                 => array( '</_ funk >', 1, '</_ funk >' ),
+            'PI lookalike comment'          => array( '<?processing instruction?>', 1, '<?processing instruction?>' ),
+            'CDATA lookalike comment'       => array( '<![CDATA[ see? data ]]>', 1, '<![CDATA[ see? data ]]>' ),
+        );
     }
 
@@ -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