PHP mb_substitute_character函数代码示例

 public static function clean($var, $charset = NULL)
 {
     if (!$charset) {
         // Use the application character set
         $charset = JsonApiApplication::$charset;
     }
     if (is_array($var) or is_object($var)) {
         foreach ($var as $key => $val) {
             // Recursion!
             $var[UTF8::clean($key)] = UTF8::clean($val);
         }
     } elseif (is_string($var) and $var !== "") {
         // Remove control characters
         $var = UTF8::strip_ascii_ctrl($var);
         if (!UTF8::is_ascii($var)) {
             // Temporarily save the mb_substitute_character() value into a variable
             $mb_substitute_character = mb_substitute_character();
             // Disable substituting illegal characters with the default '?' character
             mb_substitute_character("none");
             // convert encoding, this is expensive, used when $var is not ASCII
             $var = mb_convert_encoding($var, $charset, $charset);
             // Reset mb_substitute_character() value back to the original setting
             mb_substitute_character($mb_substitute_character);
         }
     }
     return $var;
 }

 static function initMbstring()
 {
     if (extension_loaded('mbstring')) {
         if (((int) ini_get('mbstring.encoding_translation') || in_array(strtolower(ini_get('mbstring.encoding_translation')), array('on', 'yes', 'true'))) && !in_array(strtolower(ini_get('mbstring.http_input')), array('pass', '8bit', 'utf-8'))) {
             user_error('php.ini settings: Please disable mbstring.encoding_translation or set mbstring.http_input to "pass"', E_USER_WARNING);
         }
         if (MB_OVERLOAD_STRING & (int) ini_get('mbstring.func_overload')) {
             user_error('php.ini settings: Please disable mbstring.func_overload', E_USER_WARNING);
         }
         mb_regex_encoding('UTF-8');
         ini_set('mbstring.script_encoding', 'pass');
         if ('utf-8' !== strtolower(mb_internal_encoding())) {
             mb_internal_encoding('UTF-8');
             ini_set('mbstring.internal_encoding', 'UTF-8');
         }
         if ('none' !== strtolower(mb_substitute_character())) {
             mb_substitute_character('none');
             ini_set('mbstring.substitute_character', 'none');
         }
         if (!in_array(strtolower(mb_http_output()), array('pass', '8bit'))) {
             mb_http_output('pass');
             ini_set('mbstring.http_output', 'pass');
         }
         if (!in_array(strtolower(mb_language()), array('uni', 'neutral'))) {
             mb_language('uni');
             ini_set('mbstring.language', 'uni');
         }
     } else {
         if (!defined('MB_OVERLOAD_MAIL')) {
             extension_loaded('iconv') or static::initIconv();
             require __DIR__ . '/Bootup/mbstring.php';
         }
     }
 }

 function __construct()
 {
     $this->charsets = array("ASMO-708" => gettext("Arabic"), "BIG5" => gettext("Chinese Traditional"), "CP1026" => gettext("IBM EBCDIC (Turkish Latin-5)"), "cp866" => gettext("Cyrillic (DOS)"), "CP870" => gettext("IBM EBCDIC (Multilingual Latin-2)"), "CISO2022JP" => gettext("Japanese (JIS-Allow 1 byte Kana)"), "DOS-720" => gettext("Arabic (DOS)"), "DOS-862" => gettext("Hebrew (DOS)"), "EBCDIC-CP-US" => gettext("IBM EBCDIC (US-Canada)"), "EUC-CN" => gettext("Chinese Simplified (EUC)"), "EUC-JP" => gettext("Japanese (EUC)"), "EUC-KR" => gettext("Korean (EUC)"), "GB2312" => gettext("Chinese Simplified (GB2312)"), "HZ-GB-2312" => gettext("Chinese Simplified (HZ)"), "IBM437" => gettext("OEM United States"), "IBM737" => gettext("Greek (DOS)"), "IBM775" => gettext("Baltic (DOS)"), "IBM850" => gettext("Western European (DOS)"), "IBM852" => gettext("Central European (DOS)"), "IBM857" => gettext("Turkish (DOS)"), "IBM861" => gettext("Icelandic (DOS)"), "IBM869" => gettext("Greek, Modern (DOS)"), "ISO-2022-JP" => gettext("Japanese (JIS)"), "ISO-2022-JP" => gettext("Japanese (JIS-Allow 1 byte Kana - SO/SI)"), "ISO-2022-KR" => gettext("Korean (ISO)"), "ISO-8859-1" => gettext("Western European (ISO)"), "ISO-8859-15" => gettext("Latin 9 (ISO)"), "ISO-8859-2" => gettext("Central European (ISO)"), "ISO-8859-3" => gettext("Latin 3 (ISO)"), "ISO-8859-4" => gettext("Baltic (ISO)"), "ISO-8859-5" => gettext("Cyrillic (ISO)"), "ISO-8859-6" => gettext("Arabic (ISO)"), "ISO-8859-7" => gettext("Greek (ISO)"), "ISO-8859-8" => gettext("Hebrew (ISO-Visual)"), "ISO-8859-8-i" => gettext("Hebrew (ISO-Logical)"), "ISO-8859-9" => gettext("Turkish (ISO)"), "JOHAB" => gettext("Korean (Johab)"), "KOi8-R" => gettext("Cyrillic (KOI8-R)"), "KOi8-U" => gettext("Cyrillic (KOI8-U)"), "KS_C_5601-1987" => gettext("Korean"), "MACINTOSH" => gettext("Western European (MAC)"), "SHIFT_JIS" => gettext("Japanese (Shift-JIS)"), "UNICODE" => gettext("Unicode"), "UNICODEFFFE" => gettext("Unicode (Big-Endian)"), "US-ASCII" => gettext("US-ASCII"), "UTF-7" => gettext("Unicode (UTF-7)"), "UTF-8" => gettext("Unicode (UTF-8)"), "WINDOWS-1250" => gettext("Central European (Windows)"), "WINDOWS-1251" => gettext("Cyrillic (Windows)"), "WINDOWS-1252" => gettext("Western European (Windows)"), "WINDOWS-1253" => gettext("Greek (Windows)"), "WINDOWS-1254" => gettext("Turkish (Windows)"), "WINDOWS-1255" => gettext("Hebrew (Windows)"), "WINDOWS-1256" => gettext("Arabic (Windows)"), "WINDOWS-1257" => gettext("Baltic (Windows)"), "WINDOWS-1258" => gettext("Vietnamese (Windows)"), "WINDOWS-874" => gettext("Thai (Windows)"));
     // prune the list to supported character sets
     $this->iconv_sets = array();
     $this->mb_sets = array();
     if (function_exists('mb_convert_encoding')) {
         @mb_substitute_character('none');
         if (function_exists('mb_list_encodings')) {
             $list = mb_list_encodings();
         } else {
             $list = array("pass", "auto", "byte2be", "byte2le", "byte4be", "byte4le", "BASE64", "UUENCODE", "HTML-ENTITIES", "Quoted-Printable", "7bit", "8bit", "UCS-4", "UCS-4BE", "UCS-4LE", "UCS-2", "UCS-2BE", "UCS-2LE", "UTF-32", "UTF-32BE", "UTF-32LE", "UTF-16", "UTF-16BE", "UTF-16LE", "UTF-8", "UTF-7", "UTF7-IMAP", "ASCII", "EUC-JP", "SJIS", "eucJP-win", "SJIS-win", "CP51932", "JIS", "ISO-2022-JP", "ISO-2022-JP-MS", "Windows-1252", "ISO-8859-1", "ISO-8859-2", "ISO-8859-3", "ISO-8859-4", "ISO-8859-5", "ISO-8859-6", "ISO-8859-7", "ISO-8859-8", "ISO-8859-9", "ISO-8859-10", "ISO-8859-13", "ISO-8859-14", "ISO-8859-15", "ISO-8859-16", "EUC-CN", "CP936", "HZ", "EUC-TW", "BIG-5", "EUC-KR", "UHC", "ISO-2022-KR", "Windows-1251", "CP866", "KOI8-R", "ArmSCII-8");
         }
         foreach ($this->charsets as $key => $encoding) {
             if (in_array($key, $list)) {
                 $this->mb_sets[$key] = $encoding;
             }
         }
     }
     if (function_exists('iconv')) {
         foreach ($this->charsets as $key => $encoding) {
             if (@iconv("UTF-8", $key, "UTF-8") !== false) {
                 $this->iconv_sets[$key] = $encoding;
             }
         }
     }
 }

function smarty_modifier_xoops_html_purifier($html, $ecoding = null, $doctype = null)
{
    require_once XOOPS_LIBRARY_PATH . '/htmlpurifier/library/HTMLPurifier.auto.php';
    $encoding = $encoding ? $encoding : _CHARSET;
    $doctypeArr = array("HTML 4.01 Strict", "HTML 4.01 Transitional", "XHTML 1.0 Strict", "XHTML 1.0 Transitional", "XHTML 1.1");
    $config = HTMLPurifier_Config::createDefault();
    if (in_array($doctype, $doctypeArr)) {
        $config->set('HTML.Doctype', $doctype);
    }
    if ($_conv = $encoding !== 'UTF-8' && function_exists('mb_convert_encoding')) {
        $_substitute = mb_substitute_character();
        mb_substitute_character('none');
        $html = mb_convert_encoding($html, 'UTF-8', $encoding);
        $config->set('Core.Encoding', 'UTF-8');
    } else {
        $config->set('Core.Encoding', $encoding);
    }
    $purifier = new HTMLPurifier($config);
    $html = $purifier->purify($html);
    if ($_conv) {
        $html = mb_convert_encoding($html, $encoding, 'UTF-8');
        mb_substitute_character($_substitute);
    }
    return $html;
}

 function inputFilter($str)
 {
     if (is_array($str)) {
         return array_map(array($this, "inputFilter"), $str);
     }
     // 入力された絵文字はUnicodeで保存するためSJIS-win
     $str = mb_convert_kana($str, 'KVrns', 'SJIS-win');
     $sjismap = array();
     $utf8map = array();
     if ($this->is_ezweb()) {
         $sjismap = array(0xe234, 0xe272, 0xa0c, 0xffff, 0xe273, 0xe2ef, 0xa0d, 0xffff, 0xe2f0, 0xe32e, 0xa50, 0xffff, 0xe32f, 0xe342, 0xa51, 0xffff, 0xe468, 0xe4a6, 0xad8, 0xffff, 0xe4a7, 0xe523, 0xad9, 0xffff, 0xe524, 0xe562, 0xb1c, 0xffff, 0xe563, 0xe5df, 0xb1d, 0xffff);
         $utf8map = array(0xec40, 0xecfc, 0x0, 0xffff, 0xed40, 0xed93, 0x0, 0xffff, 0xef40, 0xeffc, 0x0, 0xffff, 0xf040, 0xf0fc, 0x0, 0xffff);
         $str = mb_encode_numericentity($str, $sjismap, 'SJIS-win');
         $str = mb_convert_encoding($str, "UTF-8", "SJIS-win");
         $str = mb_decode_numericentity($str, $utf8map, 'UTF-8');
     } elseif ($this->is_softbank()) {
         $backup = mb_substitute_character();
         mb_substitute_character('long');
         $str = mb_convert_encoding($str, 'UTF-8', 'SJIS');
         mb_substitute_character($backup);
         $pattern = '/BAD\\+([0-9A-F]{4})/';
         $callback = array($this, '_softbank_fallbackSjisToUtf8');
         $str = preg_replace_callback($pattern, $callback, $str);
     } else {
         $str = mb_convert_encoding($str, "UTF-8", "SJIS-win");
     }
     $str = trim($str);
     //$str = h($str);
     return $str;
 }

 function u2b($str, $charset = 'BIG5')
 {
     mb_regex_encoding($charset);
     //宣告 要進行 regex 的多位元編碼轉換格式 為 $charset
     mb_substitute_character('long');
     //宣告 缺碼字改以U+16進位碼為標記取代
     $str = mb_convert_encoding($str, $charset, 'UTF-8');
     $str = preg_replace('/U\\+([0-9A-F]{4})/e', '"&#".intval("\\1",16).";"', $str);
     //將U+16進位碼標記轉換為UnicodeHTML碼
     return $str;
 }

 /**
  *  コンストラクタ
  *  @param  string  $cat    カテゴリ
  */
 public function __construct($cat)
 {
     mb_internal_encoding(Todo::ENCODING);
     mb_regex_encoding(Todo::ENCODING);
     ini_set('default_charset', Todo::ENCODING);
     //HTTPヘッダーでの文字コード指定
     ini_set('mbstring.strict_detection', true);
     mb_substitute_character(0x5f);
     //変換できない文字は"_"にする
     $this->cat = $this->_encode($cat);
 }

 function __construct($data)
 {
     libxml_use_internal_errors(true);
     libxml_clear_errors();
     $this->doc = new DOMDocument();
     $this->doc->loadXML($data);
     mb_substitute_character("none");
     $error = libxml_get_last_error();
     // libxml compiled without iconv?
     if ($error && $error->code == 32) {
         $data = $this->normalize_encoding($data);
         if ($data) {
             libxml_clear_errors();
             $this->doc = new DOMDocument();
             $this->doc->loadXML($data);
             $error = libxml_get_last_error();
         }
     }
     // some terrible invalid unicode entity?
     if ($error) {
         foreach (libxml_get_errors() as $err) {
             if ($err->code == 9) {
                 // if the source feed is not in utf8, next conversion will fail
                 $data = $this->normalize_encoding($data);
                 // remove dangling bytes
                 $data = mb_convert_encoding($data, 'UTF-8', 'UTF-8');
                 // apparently not all UTF-8 characters are valid for XML
                 $data = preg_replace('/[^\\x{0009}\\x{000a}\\x{000d}\\x{0020}-\\x{D7FF}\\x{E000}-\\x{FFFD}]+/u', ' ', $data);
                 if ($data) {
                     libxml_clear_errors();
                     $this->doc = new DOMDocument();
                     $this->doc->loadXML($data);
                     $error = libxml_get_last_error();
                 }
                 break;
             }
         }
     }
     if ($error) {
         foreach (libxml_get_errors() as $error) {
             if ($error->level == LIBXML_ERR_FATAL) {
                 if (!isset($this->error)) {
                     //currently only the first error is reported
                     $this->error = $this->format_error($error);
                 }
                 $this->libxml_errors[] = $this->format_error($error);
             }
         }
     }
     libxml_clear_errors();
     $this->items = array();
 }

 /**
  * Class constructor
  *
  * Determines if UTF-8 support is to be enabled.
  *
  * @return  void
  */
 public function __construct()
 {
     $charset = strtoupper(Config::get('main')->charset);
     ini_set('default_charset', $charset);
     /*
      * Configure mbstring and/or iconv if they are enabled
      * and set MB_ENABLED and ICONV_ENABLED constants, so
      * that we don't repeatedly do extension_loaded() or
      * function_exists() calls.
      */
     if (extension_loaded('mbstring')) {
         define('MB_ENABLED', TRUE);
         // mbstring.internal_encoding is deprecated starting with PHP 5.6
         // and it's usage triggers E_DEPRECATED messages.
         if (!Core::isPHP('5.6')) {
             @ini_set('mbstring.internal_encoding', $charset);
         } else {
             mb_internal_encoding($charset);
         }
         // This is required for mb_convert_encoding() to strip invalid characters.
         // That's utilized by Utf8, but it's also done for consistency with iconv.
         mb_substitute_character('none');
     } else {
         define('MB_ENABLED', FALSE);
     }
     // There's an ICONV_IMPL constant, but the PHP manual says that using
     // iconv's predefined constants is "strongly discouraged".
     if (extension_loaded('iconv')) {
         define('ICONV_ENABLED', TRUE);
         // iconv.internal_encoding is deprecated starting with PHP 5.6
         // and it's usage triggers E_DEPRECATED messages.
         if (!Core::isPHP(5.6)) {
             @ini_set('iconv.internal_encoding', $charset);
         } else {
             ini_set('default_encoding', $charset);
         }
     } else {
         define('ICONV_ENABLED', FALSE);
     }
     if (Core::isPHP('5.6')) {
         ini_set('php.internal_encoding', $charset);
     }
     if (defined('PREG_BAD_UTF8_ERROR') && (ICONV_ENABLED === TRUE or MB_ENABLED === TRUE) && strtoupper($charset) === 'UTF-8') {
         define('UTF8_ENABLED', TRUE);
         Logger::log('UTF-8 Support Enabled');
     } else {
         define('UTF8_ENABLED', FALSE);
         Logger::log('UTF-8 Support Disabled');
     }
 }

 /**
  * AbstractDiff constructor.
  *
  * @param string     $oldText
  * @param string     $newText
  * @param string     $encoding
  * @param null|array $specialCaseTags
  * @param null|bool  $groupDiffs
  */
 public function __construct($oldText, $newText, $encoding = 'UTF-8', $specialCaseTags = null, $groupDiffs = null)
 {
     mb_substitute_character(0x20);
     $this->setConfig(HtmlDiffConfig::create()->setEncoding($encoding));
     if ($specialCaseTags !== null) {
         $this->config->setSpecialCaseTags($specialCaseTags);
     }
     if ($groupDiffs !== null) {
         $this->config->setGroupDiffs($groupDiffs);
     }
     $this->oldText = $oldText;
     $this->newText = $newText;
     $this->content = '';
 }

 public function format($response)
 {
     $this->inputCharset = @$response->data['inputCharset'] ?: Yii::$app->charset;
     $this->outputCharset = @$response->data['outputCharset'] ?: Yii::$app->charset;
     // 代替文字
     $substitute = new Resource(mb_substitute_character(), function ($old) {
         mb_substitute_character($old);
     });
     mb_substitute_character(0x3013);
     $tmpfile = tmpfile();
     foreach ($response->data['rows'] as $row) {
         fwrite($tmpfile, $this->formatRow($row) . "\r\n");
     }
     fseek($tmpfile, 0, SEEK_SET);
     $response->content = null;
     $response->stream = $tmpfile;
 }

 /**
  * @return string
  *
  * @throws Backend\SourceFileException
  */
 public function getSource()
 {
     $code = file_get_contents($this->fileInfo->getPathname());
     $info = new \finfo();
     $encoding = $info->file($this->fileInfo, FILEINFO_MIME_ENCODING);
     if (strtolower($encoding) != 'utf-8') {
         try {
             $code = iconv($encoding, 'UTF-8//TRANSLIT', $code);
         } catch (\ErrorException $e) {
             throw new SourceFileException('Encoding error - conversion to UTF-8 failed', SourceFileException::BadEncoding, $e);
         }
     }
     // This is a workaround to filter out leftover invalid UTF-8 byte sets
     // even if the source looks like it's UTF-8 already
     mb_substitute_character('none');
     $cleanCode = mb_convert_encoding($code, 'UTF-8', 'UTF-8');
     if ($cleanCode != $code) {
         throw new SourceFileException('Encoding error - invalid UTF-8 bytes found', SourceFileException::InvalidDataBytes);
     }
     return $cleanCode;
 }

 /**
  * Perform initialization required for the string wrapper library.
  * @return null
  */
 static function init()
 {
     $clientCharset = strtolower_codesafe(Config::getVar('i18n', 'client_charset'));
     // Check if mbstring is installed (requires PHP >= 4.3.0)
     if (String::hasMBString()) {
         // mbstring routines are available
         define('ENABLE_MBSTRING', true);
         // Set up required ini settings for mbstring
         // FIXME Do any other mbstring settings need to be set?
         mb_internal_encoding($clientCharset);
         mb_substitute_character('63');
         // question mark
     }
     // Define modifier to be used in regexp_* routines
     // FIXME Should non-UTF-8 encodings be supported with mbstring?
     if ($clientCharset == 'utf-8' && String::hasPCREUTF8()) {
         define('PCRE_UTF8', 'u');
     } else {
         define('PCRE_UTF8', '');
     }
 }

function safeUTF8(&$text)
{
    //when `mb_convert_encoding` is used below, we want it to use the recommended Unicode replacement character
    //rather than just "?" <stackoverflow.com/a/13695364>
    mb_substitute_character(0xfffd);
    //what's given could be any imaginable encoding, normalise it into UTF-8 though it may not yet be web-safe.
    //adapted from <php.net/mb_check_encoding#89286>, with thanks to Zegnat. this works by importing the current byte
    //stream into UTF-32 which has enough scope to contain any other encoding, then downsizing in to UTF-8
    $text = mb_convert_encoding(mb_convert_encoding($text, 'UTF-32', 'UTF-8'), 'UTF-8', 'UTF-32');
    //remove Unicode bytes unsafe for XML: <www.w3.org/TR/REC-xml/#charsets>
    $text = preg_replace('/[^\\x{0009}\\x{000a}\\x{000d}\\x{0020}-\\x{D7FF}\\x{E000}-\\x{FFFD}\\x{10000}-\\x{10FFFF}]+/u', '', $text);
    //remove "compatibility characters" and "permanently undefined Unicode characters",
    //see note proceeding: <www.w3.org/TR/REC-xml/#charsets>
    $text = preg_replace('/[\\x{007f}-\\x{0084}\\x{0086}-\\x{009f}\\x{FDD0}-\\x{FDEF}' . '\\x{200E}\\x{200F}\\x{202A}-\\x{202E}' . '\\x{1FFFE}\\x{1FFFF}\\x{2FFFE}\\x{2FFFF}\\x{3FFFE}\\x{3FFFF}\\x{4FFFE}\\x{4FFFF}' . '\\x{5FFFE}\\x{5FFFF}\\x{6FFFE}\\x{6FFFF}\\x{7FFFE}\\x{7FFFF}\\x{8FFFE}\\x{8FFFF}' . '\\x{9FFFE}\\x{9FFFF}\\x{AFFFE}\\x{AFFFF}\\x{BFFFE}\\x{BFFFF}\\x{CFFFE}\\x{CFFFF}' . '\\x{DFFFE}\\x{DFFFF}\\x{EFFFE}\\x{EFFFF}\\x{FFFFE}\\x{FFFFF}\\x{10FFFE}\\x{10FFFF}]+/u', '', $text);
    //TODO: strip invalid byte-sequences
    //see: http://stackoverflow.com/a/13695364
    //Some interesting references:
    //http://www.php.net/manual/en/reference.pcre.pattern.modifiers.php#54805
    //we still need to return, despite the by-reference parameter because use of anonymous variables and functions
    //for the call will not be by-reference
    return $text;
}

 public static function init()
 {
     self::$utf8validator = (bool) extension_loaded('utf8validator');
     mb_internal_encoding('UTF-8');
     mb_language('uni');
     mb_regex_encoding('UTF-8');
     mb_detect_order(array('UTF-8', 'ISO-8859-1'));
     mb_substitute_character(0xfffd);
     MCached::connect();
     $trans = MCached::get(self::TRANSKEY);
     if ($trans === MCached::NO_RESULT) {
         $win = "€" . implode('', range("‚", "Œ")) . "Ž" . implode('', range("‘", "œ")) . implode('', range("ž", "ÿ"));
         $win_iso = "�����";
         $iso = implode('', range("€", "ÿ"));
         $winlen = strlen($win);
         $winisolen = strlen($win_iso);
         $isolen = strlen($iso);
         $trans = array('iso_to_utf8' => array(), 'win_to_utf8' => array(), 'from_utf8' => array());
         for ($i = 0; $i < $isolen; $i++) {
             $utf8 = mb_convert_encoding($iso[$i], 'UTF-8', 'ISO-8859-1');
             $trans['iso_to_utf8'][$iso[$i]] = $utf8;
             $trans['from_utf8'][$utf8] = $iso[$i];
         }
         for ($i = 0; $i < $winlen; $i++) {
             $utf8 = mb_convert_encoding($win[$i], 'UTF-8', 'Windows-1252');
             $trans['win_to_utf8'][$win[$i]] = $utf8;
             $trans['from_utf8'][$utf8] = $win[$i];
         }
         for ($i = 0; $i < $winisolen; $i++) {
             $utf8 = mb_convert_encoding($win_iso[$i], 'UTF-8', 'ISO-8859-1');
             $trans['win_to_utf8'][$win_iso[$i]] = $utf8;
         }
         MCached::add(self::TRANSKEY, $trans, 86400);
     }
     self::$trans_table = $trans;
 }