Chris@13: <?php declare(strict_types=1);
Chris@0: 
Chris@0: namespace PhpParser\Node\Scalar;
Chris@0: 
Chris@0: use PhpParser\Error;
Chris@0: use PhpParser\Node\Scalar;
Chris@0: 
Chris@0: class String_ extends Scalar
Chris@0: {
Chris@0:     /* For use in "kind" attribute */
Chris@0:     const KIND_SINGLE_QUOTED = 1;
Chris@0:     const KIND_DOUBLE_QUOTED = 2;
Chris@0:     const KIND_HEREDOC = 3;
Chris@0:     const KIND_NOWDOC = 4;
Chris@0: 
Chris@0:     /** @var string String value */
Chris@0:     public $value;
Chris@0: 
Chris@13:     protected static $replacements = [
Chris@0:         '\\' => '\\',
Chris@0:         '$'  =>  '$',
Chris@0:         'n'  => "\n",
Chris@0:         'r'  => "\r",
Chris@0:         't'  => "\t",
Chris@0:         'f'  => "\f",
Chris@0:         'v'  => "\v",
Chris@0:         'e'  => "\x1B",
Chris@13:     ];
Chris@0: 
Chris@0:     /**
Chris@0:      * Constructs a string scalar node.
Chris@0:      *
Chris@0:      * @param string $value      Value of the string
Chris@0:      * @param array  $attributes Additional attributes
Chris@0:      */
Chris@13:     public function __construct(string $value, array $attributes = []) {
Chris@0:         parent::__construct($attributes);
Chris@0:         $this->value = $value;
Chris@0:     }
Chris@0: 
Chris@13:     public function getSubNodeNames() : array {
Chris@13:         return ['value'];
Chris@0:     }
Chris@0: 
Chris@0:     /**
Chris@0:      * @internal
Chris@0:      *
Chris@0:      * Parses a string token.
Chris@0:      *
Chris@0:      * @param string $str String token content
Chris@0:      * @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes
Chris@0:      *
Chris@0:      * @return string The parsed string
Chris@0:      */
Chris@13:     public static function parse(string $str, bool $parseUnicodeEscape = true) : string {
Chris@0:         $bLength = 0;
Chris@0:         if ('b' === $str[0] || 'B' === $str[0]) {
Chris@0:             $bLength = 1;
Chris@0:         }
Chris@0: 
Chris@0:         if ('\'' === $str[$bLength]) {
Chris@0:             return str_replace(
Chris@13:                 ['\\\\', '\\\''],
Chris@13:                 ['\\', '\''],
Chris@0:                 substr($str, $bLength + 1, -1)
Chris@0:             );
Chris@0:         } else {
Chris@0:             return self::parseEscapeSequences(
Chris@0:                 substr($str, $bLength + 1, -1), '"', $parseUnicodeEscape
Chris@0:             );
Chris@0:         }
Chris@0:     }
Chris@0: 
Chris@0:     /**
Chris@0:      * @internal
Chris@0:      *
Chris@0:      * Parses escape sequences in strings (all string types apart from single quoted).
Chris@0:      *
Chris@0:      * @param string      $str   String without quotes
Chris@0:      * @param null|string $quote Quote type
Chris@0:      * @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes
Chris@0:      *
Chris@0:      * @return string String with escape sequences parsed
Chris@0:      */
Chris@13:     public static function parseEscapeSequences(string $str, $quote, bool $parseUnicodeEscape = true) : string {
Chris@0:         if (null !== $quote) {
Chris@0:             $str = str_replace('\\' . $quote, $quote, $str);
Chris@0:         }
Chris@0: 
Chris@0:         $extra = '';
Chris@0:         if ($parseUnicodeEscape) {
Chris@0:             $extra = '|u\{([0-9a-fA-F]+)\}';
Chris@0:         }
Chris@0: 
Chris@0:         return preg_replace_callback(
Chris@0:             '~\\\\([\\\\$nrtfve]|[xX][0-9a-fA-F]{1,2}|[0-7]{1,3}' . $extra . ')~',
Chris@0:             function($matches) {
Chris@0:                 $str = $matches[1];
Chris@0: 
Chris@0:                 if (isset(self::$replacements[$str])) {
Chris@0:                     return self::$replacements[$str];
Chris@0:                 } elseif ('x' === $str[0] || 'X' === $str[0]) {
Chris@0:                     return chr(hexdec($str));
Chris@0:                 } elseif ('u' === $str[0]) {
Chris@0:                     return self::codePointToUtf8(hexdec($matches[2]));
Chris@0:                 } else {
Chris@0:                     return chr(octdec($str));
Chris@0:                 }
Chris@0:             },
Chris@0:             $str
Chris@0:         );
Chris@0:     }
Chris@0: 
Chris@13:     /**
Chris@13:      * Converts a Unicode code point to its UTF-8 encoded representation.
Chris@13:      *
Chris@13:      * @param int $num Code point
Chris@13:      *
Chris@13:      * @return string UTF-8 representation of code point
Chris@13:      */
Chris@13:     private static function codePointToUtf8(int $num) : string {
Chris@0:         if ($num <= 0x7F) {
Chris@0:             return chr($num);
Chris@0:         }
Chris@0:         if ($num <= 0x7FF) {
Chris@0:             return chr(($num>>6) + 0xC0) . chr(($num&0x3F) + 0x80);
Chris@0:         }
Chris@0:         if ($num <= 0xFFFF) {
Chris@0:             return chr(($num>>12) + 0xE0) . chr((($num>>6)&0x3F) + 0x80) . chr(($num&0x3F) + 0x80);
Chris@0:         }
Chris@0:         if ($num <= 0x1FFFFF) {
Chris@0:             return chr(($num>>18) + 0xF0) . chr((($num>>12)&0x3F) + 0x80)
Chris@0:                  . chr((($num>>6)&0x3F) + 0x80) . chr(($num&0x3F) + 0x80);
Chris@0:         }
Chris@0:         throw new Error('Invalid UTF-8 codepoint escape sequence: Codepoint too large');
Chris@0:     }
Chris@13:     
Chris@13:     public function getType() : string {
Chris@13:         return 'Scalar_String';
Chris@13:     }
Chris@0: }