gggeek /
phpxmlrpc
| Conditions | 37 |
| Paths | 248 |
| Total Lines | 178 |
| Code Lines | 107 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 68 |
| CRAP Score | 59.0911 |
| Changes | 1 | ||
| Bugs | 0 | Features | 0 |
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
| 1 | <?php |
||
| 145 | 689 | public function encodeEntities($data, $srcEncoding = '', $destEncoding = '') |
|
| 146 | 657 | { |
|
| 147 | if ($srcEncoding == '') { |
||
| 148 | // lame, but we know no better... |
||
| 149 | 689 | $srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding; |
|
| 150 | } |
||
| 151 | |||
| 152 | 689 | if ($destEncoding == '') { |
|
| 153 | 689 | $destEncoding = 'US-ASCII'; |
|
| 154 | 688 | } |
|
| 155 | 676 | ||
| 156 | 676 | // in case there is transcoding going on, let's upscale to UTF8 |
|
| 157 | 676 | /// @todo we should do this as well when $srcEncoding == $destEncoding and the encoding is not supported by |
|
| 158 | /// htmlspecialchars |
||
| 159 | 49 | if (!in_array($srcEncoding, array('UTF-8', 'ISO-8859-1', 'US-ASCII')) && $srcEncoding != $destEncoding && |
|
| 160 | 49 | function_exists('mb_convert_encoding')) { |
|
| 161 | $data = mb_convert_encoding($data, 'UTF-8', str_replace('US-ASCII', 'ASCII', $srcEncoding)); |
||
| 162 | 676 | $srcEncoding = 'UTF-8'; |
|
| 163 | 620 | } |
|
| 164 | |||
| 165 | 410 | $conversion = strtoupper($srcEncoding . '_' . $destEncoding); |
|
| 166 | |||
| 167 | 410 | // list ordered with (expected) most common scenarios first |
|
| 168 | 410 | switch ($conversion) { |
|
| 169 | 410 | case 'UTF-8_UTF-8': |
|
| 170 | 410 | case 'ISO-8859-1_ISO-8859-1': |
|
| 171 | 410 | case 'US-ASCII_UTF-8': |
|
| 172 | case 'US-ASCII_US-ASCII': |
||
| 173 | 410 | case 'US-ASCII_ISO-8859-1': |
|
| 174 | 44 | //case 'CP1252_CP1252': |
|
| 175 | 41 | $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
|
| 176 | break; |
||
| 177 | 3 | ||
| 178 | case 'UTF-8_US-ASCII': |
||
| 179 | case 'UTF-8_ISO-8859-1': |
||
| 180 | 410 | // NB: this will choke on invalid UTF-8, going most likely beyond EOF |
|
| 181 | $escapedData = ''; |
||
| 182 | // be kind to users creating string xml-rpc values out of different php types |
||
| 183 | 403 | $data = (string)$data; |
|
| 184 | 403 | $ns = strlen($data); |
|
| 185 | 22 | for ($nn = 0; $nn < $ns; $nn++) { |
|
| 186 | 22 | $ch = $data[$nn]; |
|
| 187 | 403 | $ii = ord($ch); |
|
| 188 | 24 | // 7 bits in 1 byte: 0bbbbbbb (127) |
|
| 189 | 24 | if ($ii < 32) { |
|
| 190 | 403 | if ($conversion == 'UTF-8_US-ASCII') { |
|
| 191 | 24 | $escapedData .= sprintf('&#%d;', $ii); |
|
| 192 | 24 | } else { |
|
| 193 | 403 | $escapedData .= $ch; |
|
| 194 | 23 | } |
|
| 195 | 23 | } |
|
| 196 | 403 | else if ($ii < 128) { |
|
| 197 | 23 | /// @todo shall we replace this with a (supposedly) faster str_replace? |
|
| 198 | 23 | /// @todo to be 'print safe', should we encode as well character 127 (DEL) ? |
|
| 199 | switch ($ii) { |
||
| 200 | 403 | case 34: |
|
| 201 | $escapedData .= '"'; |
||
| 202 | break; |
||
| 203 | 77 | case 38: |
|
| 204 | 73 | $escapedData .= '&'; |
|
| 205 | 73 | break; |
|
| 206 | 73 | case 39: |
|
| 207 | 73 | $escapedData .= '''; |
|
| 208 | 73 | break; |
|
| 209 | case 60: |
||
| 210 | 33 | $escapedData .= '<'; |
|
| 211 | 33 | break; |
|
| 212 | 33 | case 62: |
|
| 213 | 33 | $escapedData .= '>'; |
|
| 214 | 33 | break; |
|
| 215 | 33 | default: |
|
| 216 | 33 | $escapedData .= $ch; |
|
| 217 | } // switch |
||
| 218 | } // 11 bits in 2 bytes: 110bbbbb 10bbbbbb (2047) |
||
| 219 | elseif ($ii >> 5 == 6) { |
||
| 220 | $b1 = ($ii & 31); |
||
| 221 | $b2 = (ord($data[$nn + 1]) & 63); |
||
| 222 | $ii = ($b1 * 64) + $b2; |
||
| 223 | $escapedData .= sprintf('&#%d;', $ii); |
||
| 224 | $nn += 1; |
||
| 225 | } // 16 bits in 3 bytes: 1110bbbb 10bbbbbb 10bbbbbb |
||
| 226 | elseif ($ii >> 4 == 14) { |
||
| 227 | $b1 = ($ii & 15); |
||
| 228 | $b2 = (ord($data[$nn + 1]) & 63); |
||
| 229 | $b3 = (ord($data[$nn + 2]) & 63); |
||
| 230 | 410 | $ii = ((($b1 * 64) + $b2) * 64) + $b3; |
|
| 231 | 25 | $escapedData .= sprintf('&#%d;', $ii); |
|
| 232 | 25 | $nn += 2; |
|
| 233 | } // 21 bits in 4 bytes: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb |
||
| 234 | 410 | elseif ($ii >> 3 == 30) { |
|
| 235 | $b1 = ($ii & 7); |
||
| 236 | 613 | $b2 = (ord($data[$nn + 1]) & 63); |
|
| 237 | 30 | $b3 = (ord($data[$nn + 2]) & 63); |
|
| 238 | 30 | $b4 = (ord($data[$nn + 3]) & 63); |
|
| 239 | 30 | $ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4; |
|
| 240 | $escapedData .= sprintf('&#%d;', $ii); |
||
| 241 | 583 | $nn += 3; |
|
| 242 | 583 | } |
|
| 243 | 583 | } |
|
| 244 | 583 | ||
| 245 | 583 | // when converting to latin-1, do not be so eager with using entities for characters 160-255 |
|
| 246 | if ($conversion == 'UTF-8_ISO-8859-1') { |
||
| 247 | $this->buildConversionTable('xml_iso88591_Entities'); |
||
| 248 | $escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData); |
||
| 249 | } |
||
| 250 | break; |
||
| 251 | |||
| 252 | case 'ISO-8859-1_UTF-8': |
||
| 253 | $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
||
| 254 | /// @todo if on php >= 8.2, prefer using mbstring or iconv. Also: suppress the warning! |
||
| 255 | if (function_exists('mb_convert_encoding')) { |
||
| 256 | $escapedData = mb_convert_encoding($escapedData, 'UTF-8', 'ISO-8859-1'); |
||
| 257 | } else { |
||
| 258 | $escapedData = utf8_encode($escapedData); |
||
| 259 | } |
||
| 260 | break; |
||
| 261 | |||
| 262 | case 'ISO-8859-1_US-ASCII': |
||
| 263 | $this->buildConversionTable('xml_iso88591_Entities'); |
||
| 264 | $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
||
| 265 | $escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData); |
||
| 266 | break; |
||
| 267 | |||
| 268 | /* |
||
| 269 | case 'CP1252_US-ASCII': |
||
| 270 | $this->buildConversionTable('xml_cp1252_Entities'); |
||
| 271 | $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
||
| 272 | $escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData); |
||
| 273 | $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); |
||
| 274 | 689 | break; |
|
| 275 | case 'CP1252_UTF-8': |
||
| 276 | $this->buildConversionTable('xml_cp1252_Entities'); |
||
| 277 | $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
||
| 278 | /// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them) |
||
| 279 | $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); |
||
| 280 | $escapedData = utf8_encode($escapedData); |
||
| 281 | break; |
||
| 282 | case 'CP1252_ISO-8859-1': |
||
| 283 | $this->buildConversionTable('xml_cp1252_Entities'); |
||
| 284 | $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
||
| 285 | // 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... |
||
| 286 | $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); |
||
| 287 | break; |
||
| 288 | */ |
||
| 289 | |||
| 290 | default: |
||
| 291 | if (function_exists('mb_convert_encoding')) { |
||
| 292 | // If reaching where, there are only 2 cases possible: UTF8->XXX or XXX->XXX |
||
| 293 | // If src is UTF8, we run htmlspecialchars before converting to the target charset, as |
||
| 294 | // htmlspecialchars has limited charset support, but it groks utf8 |
||
| 295 | if ($srcEncoding === 'UTF-8') { |
||
| 296 | $data = htmlspecialchars($data, defined('ENT_XML1') ? ENT_XML1 | ENT_QUOTES : ENT_QUOTES, 'UTF-8'); |
||
|
Bug
introduced
by
|
|||
| 297 | } |
||
| 298 | if ($srcEncoding !== $destEncoding) { |
||
| 299 | try { |
||
| 300 | // php 7.4 and lower: a warning is generated. php 8.0 and up: an Error is thrown. So much for BC... |
||
| 301 | $data = @mb_convert_encoding($data, str_replace('US-ASCII', 'ASCII', $destEncoding), str_replace('US-ASCII', 'ASCII', $srcEncoding)); |
||
| 302 | } catch (\ValueError $e) { |
||
| 303 | $data = false; |
||
| 304 | } |
||
| 305 | } |
||
| 306 | if ($data === false) { |
||
| 307 | $escapedData = ''; |
||
| 308 | $this->getLogger()->error('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding via mbstring: failed..."); |
||
| 309 | } else { |
||
| 310 | if ($srcEncoding === 'UTF-8') { |
||
| 311 | $escapedData = $data; |
||
| 312 | } else { |
||
| 313 | $escapedData = htmlspecialchars($data, defined('ENT_XML1') ? ENT_XML1 | ENT_QUOTES : ENT_QUOTES, $destEncoding); |
||
| 314 | } |
||
| 315 | } |
||
| 316 | } else { |
||
| 317 | $escapedData = ''; |
||
| 318 | $this->getLogger()->error('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported..."); |
||
| 319 | } |
||
| 320 | } |
||
| 321 | |||
| 322 | return $escapedData; |
||
| 323 | } |
||
| 396 |
Loading history...