More documentation, removed a benign-error-only if

Author: dmsnell

src/wp-includes/html-api/class-wp-html-decoder.php

@@ -276,7 +276,7 @@ public static function read_character_reference( $context, $text, $at, &$skip_by
 				$numeric_base   = 16;
 				$numeric_digits = '0123456789abcdefABCDEF';
 				$max_digits     = 6; // 
-				$digits_at     += 1;
+				++$digits_at;
 			} else {
 				$numeric_base   = 10;
 				$numeric_digits = '0123456789';
@@ -308,49 +308,25 @@ public static function read_character_reference( $context, $text, $at, &$skip_by
 			$digits     = substr( $text, $digits_at + $zero_count, $digit_count );
 			$code_point = intval( $digits, $numeric_base );
 
-			if (
-				// Null character.
-				0 === $code_point ||
-
-				// Outside Unicode range.
-				$code_point > 0x10FFFF ||
-
-				// Surrogate.
-				( $code_point >= 0xD800 && $code_point <= 0xDFFF )
-			) {
-				$skip_bytes = $end_of_span - $at;
-				return '�';
-			}
-
-			if (
-				/*
-				 * Noncharacters.
-				 *
-				 * > A noncharacter is a code point that is in the range U+FDD0 to U+FDEF,
-				 * > inclusive, or U+FFFE, U+FFFF, U+1FFFE, U+1FFFF, U+2FFFE, U+2FFFF,
-				 * > U+3FFFE, U+3FFFF, U+4FFFE, U+4FFFF, U+5FFFE, U+5FFFF, U+6FFFE,
-				 * > U+6FFFF, U+7FFFE, U+7FFFF, U+8FFFE, U+8FFFF, U+9FFFE, U+9FFFF,
-				 * > U+AFFFE, U+AFFFF, U+BFFFE, U+BFFFF, U+CFFFE, U+CFFFF, U+DFFFE,
-				 * > U+DFFFF, U+EFFFE, U+EFFFF, U+FFFFE, U+FFFFF, U+10FFFE, or U+10FFFF.
-				 *
-				 * @see https://infra.spec.whatwg.org/#noncharacter
-				 */
-				( $code_point >= 0xFDD0 && $code_point <= 0xFDEF ) ||
-				( 0xFFFE === ( $code_point & 0xFFFE ) ) ||
-
-				// 0x0D or non-ASCII-whitespace control
-				0x0D === $code_point ||
-				(
-					$code_point >= 0 &&
-					$code_point <= 0x1F &&
-					0x9 !== $code_point &&
-					0xA !== $code_point &&
-					0xC !== $code_point &&
-					0xD !== $code_point
-				)
-			) {
-				// @todo This is an error but the code point passes through.
-			}
+			/*
+			 * Noncharacters, 0x0D, and non-ASCII-whitespace control characters.
+			 *
+			 * > A noncharacter is a code point that is in the range U+FDD0 to U+FDEF,
+			 * > inclusive, or U+FFFE, U+FFFF, U+1FFFE, U+1FFFF, U+2FFFE, U+2FFFF,
+			 * > U+3FFFE, U+3FFFF, U+4FFFE, U+4FFFF, U+5FFFE, U+5FFFF, U+6FFFE,
+			 * > U+6FFFF, U+7FFFE, U+7FFFF, U+8FFFE, U+8FFFF, U+9FFFE, U+9FFFF,
+			 * > U+AFFFE, U+AFFFF, U+BFFFE, U+BFFFF, U+CFFFE, U+CFFFF, U+DFFFE,
+			 * > U+DFFFF, U+EFFFE, U+EFFFF, U+FFFFE, U+FFFFF, U+10FFFE, or U+10FFFF.
+			 *
+			 * A C0 control is a code point that is in the range of U+00 to U+1F,
+			 * but ASCII whitespace includes U+09, U+0A, U+0C, and U+0D.
+			 *
+			 * These characters are invalid but still decode as any valid character.
+			 * This comment is here to note and explain why there's no check to
+			 * remove these characters or replace them.
+			 *
+			 * @see https://infra.spec.whatwg.org/#noncharacter
+			 */
 
 			/*
 			 * > If the number is one of the numbers in the first column of
@@ -449,7 +425,36 @@ public static function read_character_reference( $context, $text, $at, &$skip_by
 		return $name;
 	}
 
+	/**
+	 * Encode a code point number into the UTF-8 encoding.
+	 *
+	 * This encoder implements the encoding algorithm for converting a number
+	 * into a byte sequence, but if it receives an invalid code point it will
+	 * return the Unicode Replacement Character U+FFFD `�`.
+	 *
+	 * Example:
+	 *
+	 *     '🅰' === WP_HTML_Decoder::code_point_to_utf8_bytes( 0x1f170 );
+	 *
+	 *     // Half of a surrogate pair is an invalid code point.
+	 *     '�' === WP_HTML_Decoder::code_point_to_utf8_bytes( 0xd83c );
+	 *
+	 * @since 6.6.0
+	 *
+	 * @see https://www.rfc-editor.org/rfc/rfc3629 UTF-8
+	 *
+	 * @param int $code_point Which code point to convert.
+	 * @return string Converted code point, or `�` if invalid.
+	 */
 	public static function code_point_to_utf8_bytes( $code_point ) {
+		if (
+			$code_point <= 0 ||
+			( $code_point >= 0xD800 && $code_point <= 0xDFFF ) ||
+			$code_point > 0x10FFFF
+		) {
+			return '�';
+		}
+
 		if ( $code_point < 0x80 ) {
 			return chr( $code_point );
 		}