Changeset 62485 for trunk/tests/phpunit/tests/unicode/wpHasNoncharacters.php

Timestamp:

06/11/2026 03:16:43 AM (4 months ago)

Author:

dmsnell

Message:

Charset: Replace polyfill wp_has_noncharacters() with direct PCRE version.

Found during fuzzing work on the HTML API and adjacent code. The previous version of this function used a Unicode PCRE to detect noncharacter code points, but that invocation failed if the input string contained sequences of invalid UTF-8 bytes.

This patch replaces the Unicode PCRE with a mapped sequence of raw bytes. This version works in environments without Unicode support and it works when invalid bytes are present, making it possible to remove the fallback function as well.

Developed in: ​https://github.com/WordPress/wordpress-develop/pull/12148
Discussed in: https://core.trac.wordpress.org/ticket/65372

Follow-up to [61000].

Props dmsnell, jonsurrell.
See #65372.

File:

• trunk/tests/phpunit/tests/unicode/wpHasNoncharacters.php (modified) (2 diffs)

trunk/tests/phpunit/tests/unicode/wpHasNoncharacters.php

@@ -42 +42 @@
 
         /**
-         * Ensures that a noncharacter inside a string will be properly detected
-         * using the fallback function when Unicode PCRE support is missing.
+         * Ensures that invalid UTF-8 does not prevent noncharacter detection.
          *
-         * @ticket 63863
-         *
-         * @dataProvider data_noncharacters
-         *
-         * @param string $noncharacter Noncharacter as a UTF-8 string.
+         * @ticket 65372
          */
-        public function test_fallback_detects_non_characters( string $noncharacter ) {
+        public function test_detects_non_characters_when_string_contains_invalid_utf8() {
                 $this->assertTrue(
-                        _wp_has_noncharacters_fallback( $noncharacter ),
-                        'Failed to detect entire string as noncharacter.'
+                        wp_has_noncharacters( "Invalid byte \xF1 before \u{FDD0}." ),
+                        'Failed to detect noncharacter after invalid UTF-8.'
                 );
 
                 $this->assertTrue(
-                        _wp_has_noncharacters_fallback( "{$noncharacter} and more." ),
-                        'Failed to detect noncharacter prefix.'
+                        wp_has_noncharacters( "Noncharacter \u{10FFFF} before invalid byte \xF1." ),
+                        'Failed to detect noncharacter before invalid UTF-8.'
                 );
 
-                $this->assertTrue(
-                        _wp_has_noncharacters_fallback( "Some text and then a {$noncharacter} and more." ),
-                        'Failed to detect medial noncharacter.'
-                );
-
-                $this->assertTrue(
-                        _wp_has_noncharacters_fallback( "Some text and a {$noncharacter}." ),
-                        'Failed to detect noncharacter suffix.'
+                $this->assertFalse(
+                        wp_has_noncharacters( "Invalid byte \xF1 without noncharacters." ),
+                        'Falsely detected noncharacter in invalid UTF-8.'
                 );
         }
@@ -119 +109 @@
 
         /**
-         * Ensures that Unicode characters are not falsely detect as noncharacters
-         * using the fallback function when Unicode PCRE support is missing.
-         *
-         * @ticket 63863
-         */
-        public function test_fallback_avoids_false_positives() {
-                // Get all the noncharacters in one long string, each surrounded on both sides by null bytes.
-                $noncharacters = implode(
-                        "\x00",
-                        array_map(
-                                static function ( $c ) {
-                                        return "\x00{$c}";
-                                },
-                                array_column( array_values( iterator_to_array( self::data_noncharacters() ) ), 0 )
-                        )
-                ) . "\x00";
-
-                $this->assertFalse(
-                        _wp_has_noncharacters_fallback( "\x00" ),
-                        'Falsely detected noncharacter in U+0000'
-                );
-
-                for ( $code_point = 1; $code_point <= 0x10FFFF; $code_point++ ) {
-                        // Surrogate halves are invalid UTF-8.
-                        if ( $code_point >= 0xD800 && $code_point <= 0xDFFF ) {
-                                continue;
-                        }
-
-                        $char     = mb_chr( $code_point );
-                        $hex_char = strtoupper( str_pad( dechex( $code_point ), 4, '0', STR_PAD_LEFT ) );
-
-                        if ( str_contains( $noncharacters, $char ) ) {
-                                $this->assertTrue(
-                                        _wp_has_noncharacters_fallback( $char ),
-                                        "Failed to detect noncharacter as test verification for U+{$hex_char}"
-                                );
-                        } else {
-                                $this->assertFalse(
-                                        _wp_has_noncharacters_fallback( $char ),
-                                        "Falsely detected noncharacter in U+{$hex_char}."
-                                );
-                        }
-                }
-        }
-
-        /**
          * Data provider
          *