X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=src%2FHelper%2FCharset.php;h=4f1103bbb19ca188338eb7981fae3c3797682cd2;hb=d8e180b0ca87bf675d5fda2099d49c9d0043cd42;hp=d7670a13a371425055190505b74c386455edf301;hpb=b081e4541f5728a5f18d15832f0b72e2e133aad2;p=plcapi.git diff --git a/src/Helper/Charset.php b/src/Helper/Charset.php index d7670a1..4f1103b 100644 --- a/src/Helper/Charset.php +++ b/src/Helper/Charset.php @@ -8,6 +8,7 @@ class Charset { // tables used for transcoding different charsets into us-ascii xml protected $xml_iso88591_Entities = array("in" => array(), "out" => array()); + protected $xml_iso88591_utf8 = 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 @@ -68,15 +69,14 @@ class Charset } /** - * 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 @@ -94,25 +94,29 @@ class Charset $srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding; } - switch (strtoupper($srcEncoding . '_' . $destEncoding)) { + $conversion = strtoupper($srcEncoding . '_' . $destEncoding); + switch ($conversion) { case 'ISO-8859-1_': case 'ISO-8859-1_US-ASCII': $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': $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': + //case 'CP1252_CP1252': $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); break; + case 'UTF-8_': case 'UTF-8_US-ASCII': case 'UTF-8_ISO-8859-1': @@ -124,7 +128,7 @@ class Charset for ($nn = 0; $nn < $ns; $nn++) { $ch = $data[$nn]; $ii = ord($ch); - //1 7 0bbbbbbb (127) + // 7 bits: 0bbbbbbb (127) if ($ii < 128) { /// @todo shall we replace this with a (supposedly) faster str_replace? switch ($ii) { @@ -146,7 +150,7 @@ class Charset default: $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]); @@ -155,7 +159,7 @@ class Charset $ent = sprintf('&#%d;', $ii); $escapedData .= $ent; $nn += 1; - } //3 16 1110bbbb 10bbbbbb 10bbbbbb + } // 16 bits: 1110bbbb 10bbbbbb 10bbbbbb elseif ($ii >> 4 == 14) { $b1 = ($ii & 15); $ii = ord($data[$nn + 1]); @@ -166,7 +170,7 @@ class Charset $ent = sprintf('&#%d;', $ii); $escapedData .= $ent; $nn += 2; - } //4 21 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb + } // 21 bits: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb elseif ($ii >> 3 == 30) { $b1 = ($ii & 7); $ii = ord($data[$nn + 1]); @@ -181,7 +185,13 @@ class Charset $nn += 3; } } + + // when converting to latin-1, do not be so eager with using entities for characters 160-255 + if ($conversion == 'UTF-8_ISO-8859-1') { + $escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData); + } break; + /* case 'CP1252_': case 'CP1252_US-ASCII': @@ -201,9 +211,10 @@ class Charset $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); break; */ + default: $escapedData = ''; - error_log("Converting from $srcEncoding to $destEncoding: not supported..."); + error_log('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported..."); } return $escapedData; @@ -237,4 +248,26 @@ 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) + { + switch ($charset) + { + case 'iso88591': + return $this->xml_iso88591_Entities; + default: + throw new \Exception('Unsupported charset: ' . $charset); + } + } + }