X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=src%2FHelper%2FCharset.php;h=0ec7de4f74d38e1f9f1bf6c3b83441de8bf350f1;hb=f4978078febfc4289bb4f45db6ca3f9e6c8c4f94;hp=db301cc795fd87be68175c3d490689e491e1bbb8;hpb=64b37dfbd32a7858e729e03eb276a2eaa0f19ccd;p=plcapi.git diff --git a/src/Helper/Charset.php b/src/Helper/Charset.php index db301cc..0ec7de4 100644 --- a/src/Helper/Charset.php +++ b/src/Helper/Charset.php @@ -6,7 +6,6 @@ use PhpXmlRpc\PhpXmlRpc; class Charset { - // tables used for transcoding different charsets into us-ascii xml protected $xml_iso88591_Entities = array("in" => array(), "out" => array()); @@ -27,23 +26,23 @@ class Charset */ protected $charset_supersets = array( - 'US-ASCII' => array ('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', + 'US-ASCII' => array('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-8859-11', 'ISO-8859-12', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8', - 'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN') + 'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',), ); protected static $instance = null; /** - * This class is singleton for performance reasons + * This class is singleton for performance reasons. + * * @return Charset */ public static function instance() { - if(self::$instance === null) - { + if (self::$instance === null) { self::$instance = new self(); } @@ -52,12 +51,12 @@ class Charset private function __construct() { - for($i = 0; $i < 32; $i++) { + for ($i = 0; $i < 32; $i++) { $this->xml_iso88591_Entities["in"][] = chr($i); $this->xml_iso88591_Entities["out"][] = "&#{$i};"; } - for($i = 160; $i < 256; $i++) { + for ($i = 160; $i < 256; $i++) { $this->xml_iso88591_Entities["in"][] = chr($i); $this->xml_iso88591_Entities["out"][] = "&#{$i};"; } @@ -66,46 +65,43 @@ class Charset { $this->xml_cp1252_Entities['in'][] = chr($i); }*/ - } /** - * 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. + * + * 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. * * @todo do a bit of basic benchmarking (strtr vs. str_replace) * @todo make usage of iconv() or recode_string() or mb_string() where available * * @param string $data - * @param string $src_encoding - * @param string $dest_encoding + * @param string $srcEncoding + * @param string $destEncoding + * * @return string */ - public function encode_entities($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)) - { + switch (strtoupper($srcEncoding . '_' . $destEncoding)) { 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); + $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': @@ -113,82 +109,74 @@ class Charset 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 = ''; - // be kind to users creating string xmlrpcvals out of different php types - $data = (string) $data; - $ns = strlen ($data); - for ($nn = 0; $nn < $ns; $nn++) - { + $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 ($ii < 128) - { + if ($ii < 128) { /// @todo shall we replace this with a (supposedly) faster str_replace? - switch($ii){ + switch ($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 .= $ch; } // switch - } - //2 11 110bbbbb 10bbbbbb (2047) - else if ($ii>>5 == 6) - { + } //2 11 110bbbbb 10bbbbbb (2047) + elseif ($ii >> 5 == 6) { $b1 = ($ii & 31); - $ii = ord($data[$nn+1]); + $ii = ord($data[$nn + 1]); $b2 = ($ii & 63); $ii = ($b1 * 64) + $b2; - $ent = sprintf ('&#%d;', $ii); - $escaped_data .= $ent; + $ent = sprintf('&#%d;', $ii); + $escapedData .= $ent; $nn += 1; - } - //3 16 1110bbbb 10bbbbbb 10bbbbbb - else if ($ii>>4 == 14) - { + } //3 16 1110bbbb 10bbbbbb 10bbbbbb + elseif ($ii >> 4 == 14) { $b1 = ($ii & 15); - $ii = ord($data[$nn+1]); + $ii = ord($data[$nn + 1]); $b2 = ($ii & 63); - $ii = ord($data[$nn+2]); + $ii = ord($data[$nn + 2]); $b3 = ($ii & 63); $ii = ((($b1 * 64) + $b2) * 64) + $b3; - $ent = sprintf ('&#%d;', $ii); - $escaped_data .= $ent; + $ent = sprintf('&#%d;', $ii); + $escapedData .= $ent; $nn += 2; - } - //4 21 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb - else if ($ii>>3 == 30) - { + } //4 21 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb + elseif ($ii >> 3 == 30) { $b1 = ($ii & 7); - $ii = ord($data[$nn+1]); + $ii = ord($data[$nn + 1]); $b2 = ($ii & 63); - $ii = ord($data[$nn+2]); + $ii = ord($data[$nn + 2]); $b3 = ($ii & 63); - $ii = ord($data[$nn+3]); + $ii = ord($data[$nn + 3]); $b4 = ($ii & 63); $ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4; - $ent = sprintf ('&#%d;', $ii); - $escaped_data .= $ent; + $ent = sprintf('&#%d;', $ii); + $escapedData .= $ent; $nn += 3; } } @@ -196,51 +184,78 @@ class Charset /* 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); + $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); + $escapedData = 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); + $escapedData = str_replace($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); + $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 = ''; + error_log('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 + * if it is a valid subset of any encoding in the list. + * * @param string $encoding charset to be tested * @param string|array $validList comma separated list of valid charsets (or array of charsets) + * * @return bool */ - public function is_valid_charset($encoding, $validList) + public function isValidCharset($encoding, $validList) { - - if (is_string($validList)) + if (is_string($validList)) { $validList = explode(',', $validList); - if (@in_array(strtoupper($encoding), $validList)) + } + if (@in_array(strtoupper($encoding), $validList)) { return true; - else - { - if (array_key_exists($encoding, $this->charset_supersets)) - foreach ($validList as $allowed) - if (in_array($allowed, $this->charset_supersets[$encoding])) + } else { + if (array_key_exists($encoding, $this->charset_supersets)) { + foreach ($validList as $allowed) { + if (in_array($allowed, $this->charset_supersets[$encoding])) { return true; + } + } + } + return false; } } -} \ No newline at end of file + /** + * Used only for backwards compatibility + * @deprecated + * + * @param string $charset + * + * @return array + * + * @throws \Exception for unknown/unsupported charsets + */ + public function getEntities($charset) + { + switch ($charset) + { + case 'iso88591': + return $this->xml_iso88591_Entities; + default: + throw new \Exception('Unsupported charset: ' . $charset); + } + } + +}