Extract normalize input method

Author: sirreal

src/wp-includes/html-api/class-wp-css-complex-selector-list.php

@@ -43,26 +43,12 @@ class WP_CSS_Complex_Selector_List extends WP_CSS_Compound_Selector_List impleme
 	 * @return static|null
 	 */
 	public static function from_selectors( string $input ) {
-		// > A selector string is a list of one or more complex selectors ([SELECTORS4], section 3.1) that may be surrounded by whitespace…
-		$input = trim( $input, " \t\r\n\r" );
+		$input = self::normalize_selector_input( $input );
 
 		if ( '' === $input ) {
 			return null;
 		}
 
-		/*
-		 * > The input stream consists of the filtered code points pushed into it as the input byte stream is decoded.
-		 * >
-		 * > To filter code points from a stream of (unfiltered) code points input:
-		 * > Replace any U+000D CARRIAGE RETURN (CR) code points, U+000C FORM FEED (FF) code points, or pairs of U+000D CARRIAGE RETURN (CR) followed by U+000A LINE FEED (LF) in input by a single U+000A LINE FEED (LF) code point.
-		 * > Replace any U+0000 NULL or surrogate code points in input with U+FFFD REPLACEMENT CHARACTER (�).
-		 *
-		 * https://www.w3.org/TR/css-syntax-3/#input-preprocessing
-		 */
-		$input = str_replace( array( "\r\n" ), "\n", $input );
-		$input = str_replace( array( "\r", "\f" ), "\n", $input );
-		$input = str_replace( "\0", "\u{FFFD}", $input );
-
 		$offset = 0;
 
 		$selector = self::parse_complex_selector( $input, $offset );

src/wp-includes/html-api/class-wp-css-compound-selector-list.php

@@ -120,25 +120,12 @@ protected function __construct( array $selectors ) {
 	 * @return static|null
 	 */
 	public static function from_selectors( string $input ) {
-		$input = trim( $input, " \t\r\n\r" );
+		$input = self::normalize_selector_input( $input );
 
 		if ( '' === $input ) {
 			return null;
 		}
 
-		/*
-		 * > The input stream consists of the filtered code points pushed into it as the input byte stream is decoded.
-		 * >
-		 * > To filter code points from a stream of (unfiltered) code points input:
-		 * > Replace any U+000D CARRIAGE RETURN (CR) code points, U+000C FORM FEED (FF) code points, or pairs of U+000D CARRIAGE RETURN (CR) followed by U+000A LINE FEED (LF) in input by a single U+000A LINE FEED (LF) code point.
-		 * > Replace any U+0000 NULL or surrogate code points in input with U+FFFD REPLACEMENT CHARACTER (�).
-		 *
-		 * https://www.w3.org/TR/css-syntax-3/#input-preprocessing
-		 */
-		$input = str_replace( array( "\r\n" ), "\n", $input );
-		$input = str_replace( array( "\r", "\f" ), "\n", $input );
-		$input = str_replace( "\0", "\u{FFFD}", $input );
-
 		$offset = 0;
 
 		$selector = self::parse_compound_selector( $input, $offset );
@@ -842,4 +829,32 @@ final protected static function check_if_three_code_points_would_start_an_ident_
 		// >   Return false.
 		return self::is_ident_start_codepoint( $input, $offset );
 	}
+
+	/**
+	 * @todo doc…
+	 */
+	final protected static function normalize_selector_input( string $input ): string {
+		/*
+		 * > A selector string is a list of one or more complex selectors ([SELECTORS4], section 3.1) that may be surrounded by whitespace…
+		 *
+		 * This list includes \f.
+		 * A later step would normalize it to a known whitespace character, but it can be trimmed here as well.
+		 */
+		$input = trim( $input, " \t\r\n\r\f" );
+
+		/*
+		 * > The input stream consists of the filtered code points pushed into it as the input byte stream is decoded.
+		 * >
+		 * > To filter code points from a stream of (unfiltered) code points input:
+		 * > Replace any U+000D CARRIAGE RETURN (CR) code points, U+000C FORM FEED (FF) code points, or pairs of U+000D CARRIAGE RETURN (CR) followed by U+000A LINE FEED (LF) in input by a single U+000A LINE FEED (LF) code point.
+		 * > Replace any U+0000 NULL or surrogate code points in input with U+FFFD REPLACEMENT CHARACTER (�).
+		 *
+		 * https://www.w3.org/TR/css-syntax-3/#input-preprocessing
+		 */
+		$input = str_replace( array( "\r\n" ), "\n", $input );
+		$input = str_replace( array( "\r", "\f" ), "\n", $input );
+		$input = str_replace( "\0", "\u{FFFD}", $input );
+
+		return $input;
+	}
 }