Changeset 59464

Timestamp:

11/27/2024 09:55:53 AM (21 months ago)

Author:

cbravobernal

Message:

HTML API: Recognize all uppercase tag names in tag processor.

Fixes a missing "D" in the character list used by strspn to find tag openers, causing tags starting with D to be skipped by the tag processor in some circumstances.

Follow-up to [58613].

Props jonsurrell, santosguillamot, wongjn, cbravobernal.
Fixes #62522.

Location:

trunk

Files:

• src/wp-includes/html-api/class-wp-html-tag-processor.php (modified) (1 diff)
• tests/phpunit/tests/html-api/wpHtmlTagProcessor.php (modified) (1 diff)

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

@@ -1669 +1669 @@
                                  * @see https://html.spec.whatwg.org/#tag-open-state
                                  */
-                                if ( 1 !== strspn( $html, '!/?abcdefghijklmnopqrstuvwxyzABCEFGHIJKLMNOPQRSTUVWXYZ', $at + 1, 1 ) ) {
+                                if ( 1 !== strspn( $html, '!/?abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ', $at + 1, 1 ) ) {
                                         ++$at;
                                         continue;

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

@@ -2985 +2985 @@
                 $this->assertNull( $doctype->system_identifier );
         }
+
+        /**
+         * @ticket 62522
+         *
+         * @dataProvider data_alphabet_by_characters_lowercase
+         */
+        public function test_recognizes_lowercase_tag_name( string $char ) {
+                /*
+                 * The spacing in the HTML string is important to the problematic
+                 * codepath in ticket #62522.
+                 */
+                $html      = " <{$char}> </{$char}>";
+                $processor = new WP_HTML_Tag_Processor( $html );
+                $this->assertTrue( $processor->next_tag(), "Failed to find open tag in '{$html}'." );
+                $this->assertTrue(
+                        $processor->next_tag( array( 'tag_closers' => 'visit' ) ),
+                        "Failed to find close tag in '{$html}'."
+                );
+        }
+
+        /**
+         * @ticket 62522
+         *
+         * @dataProvider data_alphabet_by_characters_uppercase
+         */
+        public function test_recognizes_uppercase_tag_name( string $char ) {
+                /*
+                 * The spacing in the HTML string is important to the problematic
+                 * codepath in ticket #62522.
+                 */
+                $html      = " <{$char}> </{$char}>";
+                $processor = new WP_HTML_Tag_Processor( $html );
+                $this->assertTrue( $processor->next_tag(), "Failed to find open tag in '{$html}'." );
+                $this->assertTrue(
+                        $processor->next_tag( array( 'tag_closers' => 'visit' ) ),
+                        "Failed to find close tag in '{$html}'."
+                );
+        }
+
+        /**
+         * Data provider.
+         *
+         * @return Generator<array>
+         */
+        public static function data_alphabet_by_characters_lowercase() {
+                $char = 'a';
+                while ( $char <= 'z' ) {
+                        yield $char => array( $char );
+                        $char = chr( ord( $char ) + 1 );
+                }
+        }
+
+        /**
+         * Data provider.
+         *
+         * @return Generator<array>
+         */
+        public static function data_alphabet_by_characters_uppercase() {
+                foreach ( self::data_alphabet_by_characters_lowercase() as $data ) {
+                        yield strtoupper( $data[0] ) => array( strtoupper( $data[0] ) );
+                }
+        }
 }