More docs, remove a binary op in UTF-8 encoding

Author: dmsnell

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

@@ -329,6 +329,11 @@ public static function read_character_reference( $context, $text, $at, &$skip_by
 			 */
 
 			/*
+			 * Code points in the C1 controls area need to be remapped as if they
+			 * were stored in Windows-1252. Note! This transformation only happens
+			 * for numeric character references. The raw code points in the byte
+			 * stream are not translated.
+			 *
 			 * > If the number is one of the numbers in the first column of
 			 * > the following table, then find the row with that number in
 			 * > the first column, and set the character reference code to
@@ -455,27 +460,27 @@ public static function code_point_to_utf8_bytes( $code_point ) {
 			return '�';
 		}
 
-		if ( $code_point < 0x80 ) {
+		if ( $code_point <= 0x7F ) {
 			return chr( $code_point );
 		}
 
-		if ( $code_point < 0x800 ) {
-			$byte1 = ( $code_point >> 6 ) & 0x1F | 0xC0;
+		if ( $code_point <= 0x7FF ) {
+			$byte1 = ( $code_point >> 6 ) | 0xC0;
 			$byte2 = $code_point & 0x3F | 0x80;
 
 			return pack( 'CC', $byte1, $byte2 );
 		}
 
-		if ( $code_point < 0x10000 ) {
-			$byte1 = ( $code_point >> 12 ) & 0x0F | 0xE0;
+		if ( $code_point <= 0xFFFF ) {
+			$byte1 = ( $code_point >> 12 ) | 0xE0;
 			$byte2 = ( $code_point >> 6 ) & 0x3F | 0x80;
 			$byte3 = $code_point & 0x3F | 0x80;
 
 			return pack( 'CCC', $byte1, $byte2, $byte3 );
 		}
 
-		if ( $code_point < 0x110000 ) {
-			$byte1 = ( $code_point >> 18 ) & 0x07 | 0xF0;
+		if ( $code_point <= 0x10FFFF ) {
+			$byte1 = ( $code_point >> 18 ) | 0xF0;
 			$byte2 = ( $code_point >> 12 ) & 0x3F | 0x80;
 			$byte3 = ( $code_point >> 6 ) & 0x3F | 0x80;
 			$byte4 = $code_point & 0x3F | 0x80;