Chris@0: <?php
Chris@0: /**
Chris@0:  * Zend Framework (http://framework.zend.com/)
Chris@0:  *
Chris@0:  * @link      http://github.com/zendframework/zf2 for the canonical source repository
Chris@0:  * @copyright Copyright (c) 2005-2015 Zend Technologies USA Inc. (http://www.zend.com)
Chris@0:  * @license   http://framework.zend.com/license/new-bsd New BSD License
Chris@0:  */
Chris@0: 
Chris@0: namespace Zend\Stdlib\StringWrapper;
Chris@0: 
Chris@0: use Zend\Stdlib\Exception;
Chris@0: 
Chris@0: class Iconv extends AbstractStringWrapper
Chris@0: {
Chris@0:     /**
Chris@0:      * List of supported character sets (upper case)
Chris@0:      *
Chris@0:      * @var string[]
Chris@0:      * @link http://www.gnu.org/software/libiconv/
Chris@0:      */
Chris@0:     protected static $encodings = [
Chris@0:         // European languages
Chris@0:         'ASCII',
Chris@0:         'ISO-8859-1',
Chris@0:         'ISO-8859-2',
Chris@0:         'ISO-8859-3',
Chris@0:         'ISO-8859-4',
Chris@0:         'ISO-8859-5',
Chris@0:         'ISO-8859-7',
Chris@0:         'ISO-8859-9',
Chris@0:         'ISO-8859-10',
Chris@0:         'ISO-8859-13',
Chris@0:         'ISO-8859-14',
Chris@0:         'ISO-8859-15',
Chris@0:         'ISO-8859-16',
Chris@0:         'KOI8-R',
Chris@0:         'KOI8-U',
Chris@0:         'KOI8-RU',
Chris@0:         'CP1250',
Chris@0:         'CP1251',
Chris@0:         'CP1252',
Chris@0:         'CP1253',
Chris@0:         'CP1254',
Chris@0:         'CP1257',
Chris@0:         'CP850',
Chris@0:         'CP866',
Chris@0:         'CP1131',
Chris@0:         'MACROMAN',
Chris@0:         'MACCENTRALEUROPE',
Chris@0:         'MACICELAND',
Chris@0:         'MACCROATIAN',
Chris@0:         'MACROMANIA',
Chris@0:         'MACCYRILLIC',
Chris@0:         'MACUKRAINE',
Chris@0:         'MACGREEK',
Chris@0:         'MACTURKISH',
Chris@0:         'MACINTOSH',
Chris@0: 
Chris@0:         // Semitic languages
Chris@0:         'ISO-8859-6',
Chris@0:         'ISO-8859-8',
Chris@0:         'CP1255',
Chris@0:         'CP1256',
Chris@0:         'CP862',
Chris@0:         'MACHEBREW',
Chris@0:         'MACARABIC',
Chris@0: 
Chris@0:         // Japanese
Chris@0:         'EUC-JP',
Chris@0:         'SHIFT_JIS',
Chris@0:         'CP932',
Chris@0:         'ISO-2022-JP',
Chris@0:         'ISO-2022-JP-2',
Chris@0:         'ISO-2022-JP-1',
Chris@0: 
Chris@0:         // Chinese
Chris@0:         'EUC-CN',
Chris@0:         'HZ',
Chris@0:         'GBK',
Chris@0:         'CP936',
Chris@0:         'GB18030',
Chris@0:         'EUC-TW',
Chris@0:         'BIG5',
Chris@0:         'CP950',
Chris@0:         'BIG5-HKSCS',
Chris@0:         'BIG5-HKSCS:2004',
Chris@0:         'BIG5-HKSCS:2001',
Chris@0:         'BIG5-HKSCS:1999',
Chris@0:         'ISO-2022-CN',
Chris@0:         'ISO-2022-CN-EXT',
Chris@0: 
Chris@0:         // Korean
Chris@0:         'EUC-KR',
Chris@0:         'CP949',
Chris@0:         'ISO-2022-KR',
Chris@0:         'JOHAB',
Chris@0: 
Chris@0:         // Armenian
Chris@0:         'ARMSCII-8',
Chris@0: 
Chris@0:         // Georgian
Chris@0:         'GEORGIAN-ACADEMY',
Chris@0:         'GEORGIAN-PS',
Chris@0: 
Chris@0:         // Tajik
Chris@0:         'KOI8-T',
Chris@0: 
Chris@0:         // Kazakh
Chris@0:         'PT154',
Chris@0:         'RK1048',
Chris@0: 
Chris@0:         // Thai
Chris@0:         'ISO-8859-11',
Chris@0:         'TIS-620',
Chris@0:         'CP874',
Chris@0:         'MACTHAI',
Chris@0: 
Chris@0:         // Laotian
Chris@0:         'MULELAO-1',
Chris@0:         'CP1133',
Chris@0: 
Chris@0:         // Vietnamese
Chris@0:         'VISCII',
Chris@0:         'TCVN',
Chris@0:         'CP1258',
Chris@0: 
Chris@0:         // Platform specifics
Chris@0:         'HP-ROMAN8',
Chris@0:         'NEXTSTEP',
Chris@0: 
Chris@0:         // Full Unicode
Chris@0:         'UTF-8',
Chris@0:         'UCS-2',
Chris@0:         'UCS-2BE',
Chris@0:         'UCS-2LE',
Chris@0:         'UCS-4',
Chris@0:         'UCS-4BE',
Chris@0:         'UCS-4LE',
Chris@0:         'UTF-16',
Chris@0:         'UTF-16BE',
Chris@0:         'UTF-16LE',
Chris@0:         'UTF-32',
Chris@0:         'UTF-32BE',
Chris@0:         'UTF-32LE',
Chris@0:         'UTF-7',
Chris@0:         'C99',
Chris@0:         'JAVA',
Chris@0: 
Chris@0:         /* Commented out because that's internal encodings not existing in real world
Chris@0:         // Full Unicode, in terms of uint16_t or uint32_t (with machine dependent endianness and alignment)
Chris@0:         'UCS-2-INTERNAL',
Chris@0:         'UCS-4-INTERNAL',
Chris@0: 
Chris@0:         // Locale dependent, in terms of `char' or `wchar_t' (with machine dependent endianness and alignment,
Chris@0:         // and with OS and locale dependent semantics)
Chris@0:         'char',
Chris@0:         'wchar_t',
Chris@0:         '', // The empty encoding name is equivalent to "char": it denotes the locale dependent character encoding.
Chris@0:         */
Chris@0: 
Chris@0:         // When configured with the option --enable-extra-encodings,
Chris@0:         // it also provides support for a few extra encodings:
Chris@0: 
Chris@0:         // European languages
Chris@0:         'CP437',
Chris@0:         'CP737',
Chris@0:         'CP775',
Chris@0:         'CP852',
Chris@0:         'CP853',
Chris@0:         'CP855',
Chris@0:         'CP857',
Chris@0:         'CP858',
Chris@0:         'CP860',
Chris@0:         'CP861',
Chris@0:         'CP863',
Chris@0:         'CP865',
Chris@0:         'CP869',
Chris@0:         'CP1125',
Chris@0: 
Chris@0:         // Semitic languages
Chris@0:         'CP864',
Chris@0: 
Chris@0:         // Japanese
Chris@0:         'EUC-JISX0213',
Chris@0:         'Shift_JISX0213',
Chris@0:         'ISO-2022-JP-3',
Chris@0: 
Chris@0:         // Chinese
Chris@0:         'BIG5-2003', // (experimental)
Chris@0: 
Chris@0:         // Turkmen
Chris@0:         'TDS565',
Chris@0: 
Chris@0:         // Platform specifics
Chris@0:         'ATARIST',
Chris@0:         'RISCOS-LATIN1',
Chris@0:     ];
Chris@0: 
Chris@0:     /**
Chris@0:      * Get a list of supported character encodings
Chris@0:      *
Chris@0:      * @return string[]
Chris@0:      */
Chris@0:     public static function getSupportedEncodings()
Chris@0:     {
Chris@0:         return static::$encodings;
Chris@0:     }
Chris@0: 
Chris@0:     /**
Chris@0:      * Constructor
Chris@0:      *
Chris@0:      * @throws Exception\ExtensionNotLoadedException
Chris@0:      */
Chris@0:     public function __construct()
Chris@0:     {
Chris@12:         if (! extension_loaded('iconv')) {
Chris@0:             throw new Exception\ExtensionNotLoadedException(
Chris@0:                 'PHP extension "iconv" is required for this wrapper'
Chris@0:             );
Chris@0:         }
Chris@0:     }
Chris@0: 
Chris@0:     /**
Chris@0:      * Returns the length of the given string
Chris@0:      *
Chris@0:      * @param string $str
Chris@0:      * @return int|false
Chris@0:      */
Chris@0:     public function strlen($str)
Chris@0:     {
Chris@0:         return iconv_strlen($str, $this->getEncoding());
Chris@0:     }
Chris@0: 
Chris@0:     /**
Chris@0:      * Returns the portion of string specified by the start and length parameters
Chris@0:      *
Chris@0:      * @param string   $str
Chris@0:      * @param int      $offset
Chris@0:      * @param int|null $length
Chris@0:      * @return string|false
Chris@0:      */
Chris@0:     public function substr($str, $offset = 0, $length = null)
Chris@0:     {
Chris@0:         return iconv_substr($str, $offset, $length, $this->getEncoding());
Chris@0:     }
Chris@0: 
Chris@0:     /**
Chris@0:      * Find the position of the first occurrence of a substring in a string
Chris@0:      *
Chris@0:      * @param string $haystack
Chris@0:      * @param string $needle
Chris@0:      * @param int    $offset
Chris@0:      * @return int|false
Chris@0:      */
Chris@0:     public function strpos($haystack, $needle, $offset = 0)
Chris@0:     {
Chris@0:         return iconv_strpos($haystack, $needle, $offset, $this->getEncoding());
Chris@0:     }
Chris@0: 
Chris@0:     /**
Chris@0:      * Convert a string from defined encoding to the defined convert encoding
Chris@0:      *
Chris@0:      * @param string  $str
Chris@0:      * @param bool $reverse
Chris@0:      * @return string|false
Chris@0:      */
Chris@0:     public function convert($str, $reverse = false)
Chris@0:     {
Chris@0:         $encoding        = $this->getEncoding();
Chris@0:         $convertEncoding = $this->getConvertEncoding();
Chris@0:         if ($convertEncoding === null) {
Chris@0:             throw new Exception\LogicException(
Chris@0:                 'No convert encoding defined'
Chris@0:             );
Chris@0:         }
Chris@0: 
Chris@0:         if ($encoding === $convertEncoding) {
Chris@0:             return $str;
Chris@0:         }
Chris@0: 
Chris@0:         $fromEncoding = $reverse ? $convertEncoding : $encoding;
Chris@0:         $toEncoding   = $reverse ? $encoding : $convertEncoding;
Chris@0: 
Chris@0:         // automatically add "//IGNORE" to not stop converting on invalid characters
Chris@0:         // invalid characters triggers a notice anyway
Chris@0:         return iconv($fromEncoding, $toEncoding . '//IGNORE', $str);
Chris@0:     }
Chris@0: }