More documentation and a change from boolean to context indicator

Author: dmsnell

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

@@ -152,15 +152,33 @@ public static function decode_attribute( $text, $at = 0, $length = null ) {
 	}
 
 	/**
-	 * Decodes a span of HTML text, respecting the ambiguous ampersand rule.
+	 * Decodes a span of HTML text, depending on the context in which it's found.
 	 *
-	 * @param $allow_ambiguous_ampersands
-	 * @param $text
-	 * @param $at
-	 * @param $length
-	 * @return mixed|string
+	 * This is a low-level method; prefer calling WP_HTML_Decoder::decode_attribute() or
+	 * WP_HTML_Decoder::decode_text_node() instead.
+	 *
+	 * Example:
+	 *
+	 *     '©' = WP_HTML_Decoder::decode( 'data', '©' );
+	 *
+	 * Use the `$at` and `$length` parameters to avoid string allocations when decoding a span
+	 * of text found within a larger document.
+	 *
+	 * Example:
+	 *
+	 *     $link = WP_HTML_Decoder::decode( 'attribute', '<a href="http&colon;//wordpress.org">Click</a>', 9, 26 );
+	 *     $link === 'http://wordpress.org';
+	 *
+	 * @since 6.6.0
+	 *
+	 * @param string $context `attribute` for decoding attribute values, `data` otherwise.
+	 * @param string $text    Text document containing span of text to decode.
+	 * @param ?int   $at      Byte offset into text where span begins, defaults to the beginning.
+	 * @param ?int   $length  How many bytes the portion of the text spans.
+	 *                        The default value spans to the end of the text.
+	 * @return string Decoded string.
 	 */
-	public static function decode( $allow_ambiguous_ampersands, $text, $at = 0, $length = null ) {
+	public static function decode( $context, $text, $at = 0, $length = null ) {
 		$decoded = '';
 		$end     = isset( $length ) ? $at + $length : strlen( $text );
 		$was_at  = $at;
@@ -171,7 +189,7 @@ public static function decode( $allow_ambiguous_ampersands, $text, $at = 0, $len
 				break;
 			}
 
-			$character_reference = self::read_character_reference( $text, $next_character_reference_at, $allow_ambiguous_ampersands, $skip_bytes );
+			$character_reference = self::read_character_reference( $context, $text, $next_character_reference_at, $skip_bytes );
 			if ( isset( $character_reference ) ) {
 				$at       = $next_character_reference_at;
 				$decoded .= substr( $text, $was_at, $at - $was_at );
@@ -195,7 +213,36 @@ public static function decode( $allow_ambiguous_ampersands, $text, $at = 0, $len
 		return $decoded;
 	}
 
-	public static function read_character_reference( $text, $at, $allow_ambiguous_ampersand, &$skip_bytes ) {
+	/**
+	 * Attempt to read a character reference at the given location in a given string,
+	 * depending on the context in which it's found.
+	 *
+	 * If a character reference is found, this function will return the translated value
+	 * that the reference maps to. It will then set in `$skip_bytes` how many bytes of
+	 * input it read while consuming the character reference. This gives calling code the
+	 * opportunity to advance its cursor when traversing a string and decoding. It
+	 * indicates how long the character reference was.
+	 *
+	 * Example:
+	 *
+	 *     null === WP_HTML_Decoder::read_character_reference( 'attribute', 'Ships&hellip;', 0 );
+	 *     '…'  === WP_HTML_Decoder::read_character_reference( 'attribute', 'Ships&hellip;', 5, $skip_bytes );
+	 *     8    === $skip_bytes;
+	 *
+	 *     null === WP_HTML_Decoder::read_character_reference( 'attribute', '&notin;', 0 );
+	 *     '¬'  === WP_HTML_Decoder::read_character_reference( 'attribute', '&notin;', 0, $skip_bytes );
+	 *     4    === $skip_bytes;
+	 *
+	 * @since 6.6.0
+	 *
+	 * @param string $context    `attribute` for decoding attribute values, `data` otherwise.
+	 * @param string $text       Text document containing span of text to decode.
+	 * @param ?int   $at         Byte offset into text where span begins, defaults to the beginning.
+	 * @param ?int   $skip_bytes How many bytes the decodable portion of the text spans.
+	 *                           The default value spans to the end of the text.
+	 * @return string|null Decoded character reference if found, otherwise `false`.
+	 */
+	public static function read_character_reference( $context, $text, $at, &$skip_bytes = null ) {
 		global $html5_named_character_entity_set;
 
 		$length = strlen( $text );
@@ -375,9 +422,9 @@ public static function read_character_reference( $text, $at, $allow_ambiguous_am
 		}
 
 		/*
-		 * At this point though have matched an entry in the named
+		 * At this point though there's a match for an entry in the named
 		 * character reference table but the match doesn't end in `;`.
-		 * We need to determine if the next letter makes it an ambiguous.
+		 * It may be allowed if it's followed by something unambiguous.
 		 */
 		$ambiguous_follower = (
 			$after_name < $length &&
@@ -394,7 +441,7 @@ public static function read_character_reference( $text, $at, $allow_ambiguous_am
 			return $name;
 		}
 
-		if ( ! $allow_ambiguous_ampersand ) {
+		if ( 'attribute' === $context ) {
 			return null;
 		}