X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=src%2FHelper%2FXMLParser.php;h=b4798ccf97c21b4b7435b2f2abd53b88d2cd915a;hb=5fc0c8cc5cc3d0579e0e810512ca3b672e720db6;hp=e11d233d8495736aeb4a564625110671d5989f9c;hpb=5be54109b83d6a77f3a2804e7520db9662c53002;p=plcapi.git diff --git a/src/Helper/XMLParser.php b/src/Helper/XMLParser.php index e11d233..b4798cc 100644 --- a/src/Helper/XMLParser.php +++ b/src/Helper/XMLParser.php @@ -40,6 +40,7 @@ class XMLParser 'VALUE' => array('MEMBER', 'DATA', 'PARAM', 'FAULT'), 'BOOLEAN' => array('VALUE'), 'I4' => array('VALUE'), + 'I8' => array('VALUE'), 'INT' => array('VALUE'), 'STRING' => array('VALUE'), 'DOUBLE' => array('VALUE'), @@ -101,6 +102,7 @@ class XMLParser $this->_xh['php_class'] = null; break; case 'I4': + case 'I8': case 'INT': case 'STRING': case 'BOOLEAN': @@ -259,6 +261,7 @@ class XMLParser break; case 'BOOLEAN': case 'I4': + case 'I8': case 'INT': case 'STRING': case 'DOUBLE': @@ -271,7 +274,7 @@ class XMLParser $this->_xh['value'] = $this->_xh['ac']; } elseif ($name == 'DATETIME.ISO8601') { if (!preg_match('/^[0-9]{8}T[0-9]{2}:[0-9]{2}:[0-9]{2}$/', $this->_xh['ac'])) { - error_log('XML-RPC: invalid value received in DATETIME: ' . $this->_xh['ac']); + error_log('XML-RPC: ' . __METHOD__ . ': invalid value received in DATETIME: ' . $this->_xh['ac']); } $this->_xh['vt'] = Value::$xmlrpcDateTime; $this->_xh['value'] = $this->_xh['ac']; @@ -290,7 +293,7 @@ class XMLParser } else { // log if receiving something strange, even though we set the value to false anyway if ($this->_xh['ac'] != '0' && strcasecmp($this->_xh['ac'], 'false') != 0) { - error_log('XML-RPC: invalid value received in BOOLEAN: ' . $this->_xh['ac']); + error_log('XML-RPC: ' . __METHOD__ . ': invalid value received in BOOLEAN: ' . $this->_xh['ac']); } $this->_xh['value'] = false; } @@ -300,7 +303,7 @@ class XMLParser // NOTE: regexp could be much stricter than this... if (!preg_match('/^[+-eE0123456789 \t.]+$/', $this->_xh['ac'])) { /// @todo: find a better way of throwing an error than this! - error_log('XML-RPC: non numeric value received in DOUBLE: ' . $this->_xh['ac']); + error_log('XML-RPC: ' . __METHOD__ . ': non numeric value received in DOUBLE: ' . $this->_xh['ac']); $this->_xh['value'] = 'ERROR_NON_NUMERIC_FOUND'; } else { // it's ok, add it on @@ -311,32 +314,29 @@ class XMLParser // we must check that only 0123456789- are characters here if (!preg_match('/^[+-]?[0123456789 \t]+$/', $this->_xh['ac'])) { /// @todo find a better way of throwing an error than this! - error_log('XML-RPC: non numeric value received in INT: ' . $this->_xh['ac']); + error_log('XML-RPC: ' . __METHOD__ . ': non numeric value received in INT: ' . $this->_xh['ac']); $this->_xh['value'] = 'ERROR_NON_NUMERIC_FOUND'; } else { // it's ok, add it on $this->_xh['value'] = (int)$this->_xh['ac']; } } - //$this->_xh['ac']=''; // is this necessary? $this->_xh['lv'] = 3; // indicate we've found a value break; case 'NAME': $this->_xh['valuestack'][count($this->_xh['valuestack']) - 1]['name'] = $this->_xh['ac']; break; case 'MEMBER': - //$this->_xh['ac']=''; // is this necessary? // add to array in the stack the last element built, // unless no VALUE was found if ($this->_xh['vt']) { $vscount = count($this->_xh['valuestack']); $this->_xh['valuestack'][$vscount - 1]['values'][$this->_xh['valuestack'][$vscount - 1]['name']] = $this->_xh['value']; } else { - error_log('XML-RPC: missing VALUE inside STRUCT in received xml'); + error_log('XML-RPC: ' . __METHOD__ . ': missing VALUE inside STRUCT in received xml'); } break; case 'DATA': - //$this->_xh['ac']=''; // is this necessary? $this->_xh['vt'] = null; // reset this to check for 2 data elements in a row - even if they're empty break; case 'STRUCT': @@ -356,7 +356,7 @@ class XMLParser $this->_xh['params'][] = $this->_xh['value']; $this->_xh['pt'][] = $this->_xh['vt']; } else { - error_log('XML-RPC: missing VALUE inside PARAM in received xml'); + error_log('XML-RPC: ' . __METHOD__ . ': missing VALUE inside PARAM in received xml'); } break; case 'METHODNAME': @@ -402,18 +402,6 @@ class XMLParser // "lookforvalue==3" means that we've found an entire value // and should discard any further character data if ($this->_xh['lv'] != 3) { - // G. Giunta 2006-08-23: useless change of 'lv' from 1 to 2 - //if($this->_xh['lv']==1) - //{ - // if we've found text and we're just in a then - // say we've found a value - //$this->_xh['lv']=2; - //} - // we always initialize the accumulator before starting parsing, anyway... - //if(!@isset($this->_xh['ac'])) - //{ - // $this->_xh['ac'] = ''; - //} $this->_xh['ac'] .= $data; } } @@ -428,11 +416,6 @@ class XMLParser // skip processing if xml fault already detected if ($this->_xh['isf'] < 2) { if (substr($data, 0, 1) == '&' && substr($data, -1, 1) == ';') { - // G. Giunta 2006-08-25: useless change of 'lv' from 1 to 2 - //if($this->_xh['lv']==1) - //{ - // $this->_xh['lv']=2; - //} $this->_xh['ac'] .= $data; } } @@ -440,4 +423,128 @@ class XMLParser return true; } + /** + * xml charset encoding guessing helper function. + * Tries to determine the charset encoding of an XML chunk received over HTTP. + * NB: according to the spec (RFC 3023), if text/xml content-type is received over HTTP without a content-type, + * we SHOULD assume it is strictly US-ASCII. But we try to be more tolerant of non conforming (legacy?) clients/servers, + * which will be most probably using UTF-8 anyway... + * In order of importance checks: + * 1. http headers + * 2. BOM + * 3. XML declaration + * 4. guesses using mb_detect_encoding() + * + * @param string $httpHeader the http Content-type header + * @param string $xmlChunk xml content buffer + * @param string $encodingPrefs comma separated list of character encodings to be used as default (when mb extension is enabled). + * This can also be set globally using PhpXmlRpc::$xmlrpc_detectencodings + * @return string the encoding determined. Null if it can't be determined and mbstring is enabled, + * PhpXmlRpc::$xmlrpc_defencoding if it can't be determined and mbstring is not enabled + * + * @todo explore usage of mb_http_input(): does it detect http headers + post data? if so, use it instead of hand-detection!!! + */ + public static function guessEncoding($httpHeader = '', $xmlChunk = '', $encodingPrefs = null) + { + // discussion: see http://www.yale.edu/pclt/encoding/ + // 1 - test if encoding is specified in HTTP HEADERS + + // Details: + // LWS: (\13\10)?( |\t)+ + // token: (any char but excluded stuff)+ + // quoted string: " (any char but double quotes and control chars)* " + // header: Content-type = ...; charset=value(; ...)* + // where value is of type token, no LWS allowed between 'charset' and value + // Note: we do not check for invalid chars in VALUE: + // this had better be done using pure ereg as below + // Note 2: we might be removing whitespace/tabs that ought to be left in if + // the received charset is a quoted string. But nobody uses such charset names... + + /// @todo this test will pass if ANY header has charset specification, not only Content-Type. Fix it? + $matches = array(); + if (preg_match('/;\s*charset\s*=([^;]+)/i', $httpHeader, $matches)) { + return strtoupper(trim($matches[1], " \t\"")); + } + + // 2 - scan the first bytes of the data for a UTF-16 (or other) BOM pattern + // (source: http://www.w3.org/TR/2000/REC-xml-20001006) + // NOTE: actually, according to the spec, even if we find the BOM and determine + // an encoding, we should check if there is an encoding specified + // in the xml declaration, and verify if they match. + /// @todo implement check as described above? + /// @todo implement check for first bytes of string even without a BOM? (It sure looks harder than for cases WITH a BOM) + if (preg_match('/^(\x00\x00\xFE\xFF|\xFF\xFE\x00\x00|\x00\x00\xFF\xFE|\xFE\xFF\x00\x00)/', $xmlChunk)) { + return 'UCS-4'; + } elseif (preg_match('/^(\xFE\xFF|\xFF\xFE)/', $xmlChunk)) { + return 'UTF-16'; + } elseif (preg_match('/^(\xEF\xBB\xBF)/', $xmlChunk)) { + return 'UTF-8'; + } + + // 3 - test if encoding is specified in the xml declaration + // Details: + // SPACE: (#x20 | #x9 | #xD | #xA)+ === [ \x9\xD\xA]+ + // EQ: SPACE?=SPACE? === [ \x9\xD\xA]*=[ \x9\xD\xA]* + if (preg_match('/^<\?xml\s+version\s*=\s*' . "((?:\"[a-zA-Z0-9_.:-]+\")|(?:'[a-zA-Z0-9_.:-]+'))" . + '\s+encoding\s*=\s*' . "((?:\"[A-Za-z][A-Za-z0-9._-]*\")|(?:'[A-Za-z][A-Za-z0-9._-]*'))/", + $xmlChunk, $matches)) { + return strtoupper(substr($matches[2], 1, -1)); + } + + // 4 - if mbstring is available, let it do the guesswork + if (extension_loaded('mbstring')) { + if ($encodingPrefs == null && PhpXmlRpc::$xmlrpc_detectencodings != null) { + $encodingPrefs = PhpXmlRpc::$xmlrpc_detectencodings; + } + if ($encodingPrefs) { + $enc = mb_detect_encoding($xmlChunk, $encodingPrefs); + } else { + $enc = mb_detect_encoding($xmlChunk); + } + // NB: mb_detect likes to call it ascii, xml parser likes to call it US_ASCII... + // IANA also likes better US-ASCII, so go with it + if ($enc == 'ASCII') { + $enc = 'US-' . $enc; + } + + return $enc; + } else { + // no encoding specified: as per HTTP1.1 assume it is iso-8859-1? + // Both RFC 2616 (HTTP 1.1) and 1945 (HTTP 1.0) clearly state that for text/xxx content types + // this should be the standard. And we should be getting text/xml as request and response. + // BUT we have to be backward compatible with the lib, which always used UTF-8 as default... + return PhpXmlRpc::$xmlrpc_defencoding; + } + } + + /** + * Helper function: checks if an xml chunk as a charset declaration (BOM or in the xml declaration) + * + * @param string $xmlChunk + * @return bool + */ + public static function hasEncoding($xmlChunk) + { + // scan the first bytes of the data for a UTF-16 (or other) BOM pattern + // (source: http://www.w3.org/TR/2000/REC-xml-20001006) + if (preg_match('/^(\x00\x00\xFE\xFF|\xFF\xFE\x00\x00|\x00\x00\xFF\xFE|\xFE\xFF\x00\x00)/', $xmlChunk)) { + return true; + } elseif (preg_match('/^(\xFE\xFF|\xFF\xFE)/', $xmlChunk)) { + return true; + } elseif (preg_match('/^(\xEF\xBB\xBF)/', $xmlChunk)) { + return true; + } + + // test if encoding is specified in the xml declaration + // Details: + // SPACE: (#x20 | #x9 | #xD | #xA)+ === [ \x9\xD\xA]+ + // EQ: SPACE?=SPACE? === [ \x9\xD\xA]*=[ \x9\xD\xA]* + if (preg_match('/^<\?xml\s+version\s*=\s*' . "((?:\"[a-zA-Z0-9_.:-]+\")|(?:'[a-zA-Z0-9_.:-]+'))" . + '\s+encoding\s*=\s*' . "((?:\"[A-Za-z][A-Za-z0-9._-]*\")|(?:'[A-Za-z][A-Za-z0-9._-]*'))/", + $xmlChunk, $matches)) { + return true; + } + + return false; + } }