X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=src%2FHelper%2FCharset.php;h=a72016e4b9dbe4a93882b35bc226b83b2f037255;hb=5d63c263e763338952815b6724ffa4469061afc4;hp=cbf00a906a59b10d1dbecf460f963a9ca994cd12;hpb=8f01888ce85ef2e3748b236e55bbab62a363c2a1;p=plcapi.git diff --git a/src/Helper/Charset.php b/src/Helper/Charset.php index cbf00a9..a72016e 100644 --- a/src/Helper/Charset.php +++ b/src/Helper/Charset.php @@ -4,26 +4,23 @@ namespace PhpXmlRpc\Helper; use PhpXmlRpc\PhpXmlRpc; +/** + * @todo implement an interface + */ class Charset { // tables used for transcoding different charsets into us-ascii xml protected $xml_iso88591_Entities = array("in" => array(), "out" => array()); - /// @todo add to iso table the characters from cp_1252 range, i.e. 128 to 159? - /// These will NOT be present in true ISO-8859-1, but will save the unwary - /// windows user from sending junk (though no luck when receiving them...) - /* - protected $xml_cp1252_Entities = array('in' => array(), out' => array( - '€', '?', '‚', 'ƒ', - '„', '…', '†', '‡', - 'ˆ', '‰', 'Š', '‹', - 'Œ', '?', 'Ž', '?', - '?', '‘', '’', '“', - '”', '•', '–', '—', - '˜', '™', 'š', '›', - 'œ', '?', 'ž', 'Ÿ' - )); - */ + /// @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ? + /// Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk + /// (though no luck when receiving them...) + /// Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159, + /// IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says: + /// "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes from ISO/IEC 6429." + /// Check what mbstring/iconv do by default with those? + // + //protected $xml_cp1252_Entities = array('in' => array(), out' => array()); protected $charset_supersets = array( 'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', @@ -33,185 +30,240 @@ class Charset 'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',), ); + /** @var Charset $instance */ protected static $instance = null; /** * This class is singleton for performance reasons. + * @todo should we just make $xml_iso88591_Entities a static variable instead ? * * @return Charset */ public static function instance() { if (self::$instance === null) { - self::$instance = new self(); + self::$instance = new static(); } return self::$instance; } - private function __construct() + /** + * Force usage as singleton + */ + protected function __construct() { - for ($i = 0; $i < 32; $i++) { - $this->xml_iso88591_Entities["in"][] = chr($i); - $this->xml_iso88591_Entities["out"][] = "&#{$i};"; - } + } - for ($i = 160; $i < 256; $i++) { - $this->xml_iso88591_Entities["in"][] = chr($i); - $this->xml_iso88591_Entities["out"][] = "&#{$i};"; - } + /** + * @param string $tableName + * @throws \Exception for unsupported $tableName + */ + protected function buildConversionTable($tableName) + { + switch($tableName) { + case 'xml_iso88591_Entities': + if (count($this->xml_iso88591_Entities['in'])) { + return; + } + for ($i = 0; $i < 32; $i++) { + $this->xml_iso88591_Entities["in"][] = chr($i); + $this->xml_iso88591_Entities["out"][] = "&#{$i};"; + } - /*for ($i = 128; $i < 160; $i++) - { - $this->xml_cp1252_Entities['in'][] = chr($i); - }*/ + for ($i = 160; $i < 256; $i++) { + $this->xml_iso88591_Entities["in"][] = chr($i); + $this->xml_iso88591_Entities["out"][] = "&#{$i};"; + } + break; + /*case 'xml_cp1252_Entities': + if (count($this->xml_cp1252_Entities['in'])) { + return; + } + for ($i = 128; $i < 160; $i++) + { + $this->xml_cp1252_Entities['in'][] = chr($i); + } + $this->xml_cp1252_Entities['out'] = array( + '€', '?', '‚', 'ƒ', + '„', '…', '†', '‡', + 'ˆ', '‰', 'Š', '‹', + 'Œ', '?', 'Ž', '?', + '?', '‘', '’', '“', + '”', '•', '–', '—', + '˜', '™', 'š', '›', + 'œ', '?', 'ž', 'Ÿ' + ); + $this->buildConversionTable('xml_iso88591_Entities'); + break;*/ + default: + throw new \Exception('Unsupported table: ' . $tableName); + } } /** - * Convert a string to the correct XML representation in a target charset - * To help correct communication of non-ascii chars inside strings, regardless - * of the charset used when sending requests, parsing them, sending responses - * and parsing responses, an option is to convert all non-ascii chars present in the message - * into their equivalent 'charset entity'. Charset entities enumerated this way - * are independent of the charset encoding used to transmit them, and all XML - * parsers are bound to understand them. - * Note that in the std case we are not sending a charset encoding mime type - * along with http headers, so we are bound by RFC 3023 to emit strict us-ascii. + * Convert a string to the correct XML representation in a target charset. + * This involves: + * - character transformation for all characters which have a different representation in source and dest charsets + * - using 'charset entity' representation for all characters which are outside of the target charset + * + * To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending + * requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars + * present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are + * independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them. + * + * Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit + * strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...) * * @todo do a bit of basic benchmarking (strtr vs. str_replace) - * @todo make usage of iconv() or recode_string() or mb_string() where available + * @todo make usage of iconv() or mb_string() where available + * @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list) * * @param string $data - * @param string $src_encoding - * @param string $dest_encoding + * @param string $srcEncoding + * @param string $destEncoding * * @return string */ - public function encodeEntities($data, $src_encoding = '', $dest_encoding = '') + public function encodeEntities($data, $srcEncoding = '', $destEncoding = '') { - if ($src_encoding == '') { + if ($srcEncoding == '') { // lame, but we know no better... - $src_encoding = PhpXmlRpc::$xmlrpc_internalencoding; + $srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding; } - switch (strtoupper($src_encoding . '_' . $dest_encoding)) { + $conversion = strtoupper($srcEncoding . '_' . $destEncoding); + switch ($conversion) { case 'ISO-8859-1_': case 'ISO-8859-1_US-ASCII': - $escaped_data = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); - $escaped_data = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escaped_data); + $this->buildConversionTable('xml_iso88591_Entities'); + $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); + $escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData); break; + case 'ISO-8859-1_UTF-8': - $escaped_data = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); - $escaped_data = utf8_encode($escaped_data); + $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); + $escapedData = utf8_encode($escapedData); break; + case 'ISO-8859-1_ISO-8859-1': case 'US-ASCII_US-ASCII': case 'US-ASCII_UTF-8': case 'US-ASCII_': case 'US-ASCII_ISO-8859-1': case 'UTF-8_UTF-8': - //case 'CP1252_CP1252': - $escaped_data = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); + //case 'CP1252_CP1252': + $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); break; + case 'UTF-8_': case 'UTF-8_US-ASCII': case 'UTF-8_ISO-8859-1': // NB: this will choke on invalid UTF-8, going most likely beyond EOF - $escaped_data = ''; + $escapedData = ''; // be kind to users creating string xmlrpc values out of different php types $data = (string)$data; $ns = strlen($data); for ($nn = 0; $nn < $ns; $nn++) { $ch = $data[$nn]; $ii = ord($ch); - //1 7 0bbbbbbb (127) - if ($ii < 128) { + // 7 bits: 0bbbbbbb (127) + if ($ii < 32) { + if ($conversion == 'UTF-8_' || $conversion == 'UTF-8_US-ASCII') { + $escapedData .= sprintf('&#%d;', $ii); + } else { + $escapedData .= $ch; + } + } + else if ($ii < 128) { /// @todo shall we replace this with a (supposedly) faster str_replace? switch ($ii) { case 34: - $escaped_data .= '"'; + $escapedData .= '"'; break; case 38: - $escaped_data .= '&'; + $escapedData .= '&'; break; case 39: - $escaped_data .= '''; + $escapedData .= '''; break; case 60: - $escaped_data .= '<'; + $escapedData .= '<'; break; case 62: - $escaped_data .= '>'; + $escapedData .= '>'; break; default: - $escaped_data .= $ch; + $escapedData .= $ch; } // switch - } //2 11 110bbbbb 10bbbbbb (2047) + } // 11 bits: 110bbbbb 10bbbbbb (2047) elseif ($ii >> 5 == 6) { $b1 = ($ii & 31); - $ii = ord($data[$nn + 1]); - $b2 = ($ii & 63); + $b2 = (ord($data[$nn + 1]) & 63); $ii = ($b1 * 64) + $b2; - $ent = sprintf('&#%d;', $ii); - $escaped_data .= $ent; + $escapedData .= sprintf('&#%d;', $ii); $nn += 1; - } //3 16 1110bbbb 10bbbbbb 10bbbbbb + } // 16 bits: 1110bbbb 10bbbbbb 10bbbbbb elseif ($ii >> 4 == 14) { $b1 = ($ii & 15); - $ii = ord($data[$nn + 1]); - $b2 = ($ii & 63); - $ii = ord($data[$nn + 2]); - $b3 = ($ii & 63); + $b2 = (ord($data[$nn + 1]) & 63); + $b3 = (ord($data[$nn + 2]) & 63); $ii = ((($b1 * 64) + $b2) * 64) + $b3; - $ent = sprintf('&#%d;', $ii); - $escaped_data .= $ent; + $escapedData .= sprintf('&#%d;', $ii); $nn += 2; - } //4 21 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb + } // 21 bits: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb elseif ($ii >> 3 == 30) { $b1 = ($ii & 7); - $ii = ord($data[$nn + 1]); - $b2 = ($ii & 63); - $ii = ord($data[$nn + 2]); - $b3 = ($ii & 63); - $ii = ord($data[$nn + 3]); - $b4 = ($ii & 63); + $b2 = (ord($data[$nn + 1]) & 63); + $b3 = (ord($data[$nn + 2]) & 63); + $b4 = (ord($data[$nn + 3]) & 63); $ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4; - $ent = sprintf('&#%d;', $ii); - $escaped_data .= $ent; + $escapedData .= sprintf('&#%d;', $ii); $nn += 3; } } + + // when converting to latin-1, do not be so eager with using entities for characters 160-255 + if ($conversion == 'UTF-8_ISO-8859-1') { + $this->buildConversionTable('xml_iso88591_Entities'); + $escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData); + } break; + /* case 'CP1252_': case 'CP1252_US-ASCII': - $escaped_data = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); - $escaped_data = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escaped_data); - $escaped_data = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escaped_data); + $this->buildConversionTable('xml_cp1252_Entities'); + $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); + $escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData); + $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); break; case 'CP1252_UTF-8': - $escaped_data = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); - /// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all allone will NOT convert them) - $escaped_data = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escaped_data); - $escaped_data = utf8_encode($escaped_data); + $this->buildConversionTable('xml_cp1252_Entities'); + $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); + /// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them) + $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); + $escapedData = utf8_encode($escapedData); break; case 'CP1252_ISO-8859-1': - $escaped_data = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); + $this->buildConversionTable('xml_cp1252_Entities'); + $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); // we might as well replace all funky chars with a '?' here, but we are kind and leave it to the receiving application layer to decide what to do with these weird entities... - $escaped_data = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escaped_data); + $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); break; */ + default: - $escaped_data = ''; - error_log("Converting from $src_encoding to $dest_encoding: not supported..."); + $escapedData = ''; + Logger::instance()->errorLog('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported..."); } - return $escaped_data; + return $escapedData; } /** - * Checks if a given charset encoding is present in a list of encodings or - * if it is a valid subset of any encoding in the list. + * Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding + * in the list. * * @param string $encoding charset to be tested * @param string|array $validList comma separated list of valid charsets (or array of charsets) @@ -237,4 +289,27 @@ class Charset return false; } } + + /** + * Used only for backwards compatibility + * @deprecated + * + * @param string $charset + * + * @return array + * + * @throws \Exception for unknown/unsupported charsets + */ + public function getEntities($charset) + { + //trigger_error('Method ' . __METHOD__ . ' is deprecated', E_USER_DEPRECATED); + + switch ($charset) + { + case 'iso88591': + return $this->xml_iso88591_Entities; + default: + throw new \Exception('Unsupported charset: ' . $charset); + } + } }