Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
Complex classes like sql_compiler often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use sql_compiler, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 3 | abstract class sql_compiler { |
||
| 4 | protected $skipDefaultOrderBy; |
||
| 5 | protected $store; |
||
| 6 | public $error; |
||
| 7 | protected $join_target_properties; |
||
| 8 | protected $offset; |
||
| 9 | protected $limit; |
||
| 10 | protected $cache; |
||
| 11 | protected $path; |
||
| 12 | protected $_SCAN_WS = array(" " => true, "\t" => true, "\n" => true ,"\r" => true); |
||
| 13 | protected $_SCAN_AZ = array("a" => true, "A" => true, "b" => true, "B" => true, "c" => true, "C" => true, "d" => true, "D" => true, "e" => true, "E" => true, "f" => true, "F" => true, "g" => true, "G" => true, "h" => true, "H" => true, "i" => true, "I" => true, "j" => true, "J" => true, "k" => true, "K" => true, "l" => true, "L" => true, "m" => true, "M" => true, "n" => true, "N" => true, "o" => true, "O" => true, "p" => true, "P" => true, "q" => true, "Q" => true, "r" => true, "R" => true, "s" => true, "S" => true, "t" => true, "T" => true, "u" => true, "U" => true, "v" => true, "V" => true, "w" => true, "W" => true, "x" => true, "X" => true, "y" => true, "Y" => true, "z" => true, "Z" => true); |
||
| 14 | protected $_SCAN_AZ_09 = array("a" => true, "A" => true, "b" => true, "B" => true, "c" => true, "C" => true, "d" => true, "D" => true, "e" => true, "E" => true, "f" => true, "F" => true, "g" => true, "G" => true, "h" => true, "H" => true, "i" => true, "I" => true, "j" => true, "J" => true, "k" => true, "K" => true, "l" => true, "L" => true, "m" => true, "M" => true, "n" => true, "N" => true, "o" => true, "O" => true, "p" => true, "P" => true, "q" => true, "Q" => true, "r" => true, "R" => true, "s" => true, "S" => true, "t" => true, "T" => true, "u" => true, "U" => true, "v" => true, "V" => true, "w" => true, "W" => true, "x" => true, "X" => true, "y" => true, "Y" => true, "z" => true, "Z" => true, "_" => true, "0" => true, "1" => true, "2" => true, "3" => true, "4" => true, "5" => true, "6" => true, "7" => true, "8" => true, "9" => true); |
||
| 15 | protected $_SCAN_NUM = array("0" => true, "1" => true, "2" => true, "3" => true, "4" => true, "5" => true, "6" => true, "7" => true, "8" => true, "9" => true); |
||
| 16 | protected $_SCAN_NUM_START = array("0" => true, "1" => true, "2" => true, "3" => true, "4" => true, "5" => true, "6" => true, "7" => true, "8" => true, "9" => true, "-" => true); |
||
| 17 | protected $_SCAN_CMP = array("~" => array("=" => array("FIN" => true)), "=" => array("=" => array("FIN" => true), "FIN" => true, "~" => array("FIN" => true, "~" => array("FIN" => true)), "*" => array("FIN" => true, "*" => array("FIN" => true)), "/" => array("FIN" => true)), "!" => array("=" => array("FIN" => true), "~" => array("FIN" => true, "~" => array("FIN" => true)), "*" => array("FIN" => true, "*" => array("FIN" => true)), "/" => array("FIN" => true, "/" => array("FIN" => true))), "<" => array("=" => array("FIN" => true), "FIN" => true), ">" => array("=" => array("FIN" => true), "FIN" => true), "/" => array("=" => array("=" => array("FIN" => true)))); |
||
| 18 | |||
| 19 | |||
| 20 | 192 | protected function parse_const(&$YYBUFFER) { |
|
| 73 | |||
| 74 | 197 | protected function parse_ident(&$YYBUFFER) { |
|
| 183 | |||
| 184 | 195 | protected function parse_cmp_expr(&$YYBUFFER) { |
|
| 217 | |||
| 218 | 195 | protected function parse_group_expr(&$YYBUFFER) { |
|
| 246 | |||
| 247 | 195 | View Code Duplication | protected function parse_and_expr(&$YYBUFFER) { |
| 273 | |||
| 274 | 195 | View Code Duplication | protected function parse_or_expr(&$YYBUFFER) { |
| 300 | |||
| 301 | 122 | protected function parse_orderby(&$YYBUFFER) { |
|
| 302 | 50 | $field = $this->parse_ident($YYBUFFER); |
|
| 303 | |||
| 304 | 50 | $YYCURSOR = 0; |
|
| 305 | 86 | while (isset($this->_SCAN_WS[$YYBUFFER[$YYCURSOR]])) { |
|
| 306 | 1 | $YYCURSOR++; |
|
| 307 | 1 | } |
|
| 308 | 50 | $value = ''; |
|
| 309 | 50 | $yych = $YYBUFFER[$YYCURSOR]; |
|
| 310 | 50 | View Code Duplication | if ($this->_SCAN_AZ[$yych]) { |
| 311 | 1 | $value .= $yych; |
|
| 312 | 1 | $yych = $YYBUFFER[++$YYCURSOR]; |
|
| 313 | 1 | while (isset($this->_SCAN_AZ[$yych])) { |
|
| 314 | 1 | $value .= $yych; |
|
| 315 | 1 | $yych = $YYBUFFER[++$YYCURSOR]; |
|
| 316 | 1 | } |
|
| 317 | 1 | $sort_type = strtoupper($value); |
|
| 318 | 1 | if (!($sort_type == 'ASC' || $sort_type == 'DESC')) { // If sort type is anything else than ASC or DESC, it is not part of the order by. |
|
| 319 | 1 | $sort_type = 'ASC'; |
|
| 320 | 1 | $YYCURSOR = $YYCURSOR - strlen($value); |
|
| 321 | 49 | $value = ''; |
|
| 322 | 1 | } |
|
| 323 | 1 | } else { |
|
| 324 | 49 | $sort_type = 'ASC'; |
|
| 325 | } |
||
| 326 | 50 | while (is_array($field)) { |
|
| 327 | $result = array( |
||
| 328 | 86 | 'id' => 'orderbyfield', |
|
| 329 | 50 | 'type' => $sort_type, |
|
| 330 | 50 | 'right' => $field, |
|
| 331 | 12 | 'left' => $result |
|
| 332 | 38 | ); |
|
| 333 | 50 | while (isset($this->_SCAN_WS[$YYBUFFER[$YYCURSOR]])) { |
|
| 334 | $YYCURSOR++; |
||
| 335 | } |
||
| 336 | 50 | $yych = $YYBUFFER[$YYCURSOR]; |
|
| 337 | 50 | if ($yych !== ',') { |
|
| 338 | 50 | $YYBUFFER = substr($YYBUFFER, $YYCURSOR); |
|
| 339 | 50 | unset($field); |
|
| 340 | 38 | } else { |
|
| 341 | 1 | $YYBUFFER = substr($YYBUFFER, $YYCURSOR + 1); |
|
| 342 | 1 | $field = $this->parse_ident($YYBUFFER); |
|
| 343 | 1 | $YYCURSOR = 0; |
|
| 344 | 1 | while (isset($this->_SCAN_WS[$YYBUFFER[$YYCURSOR]])) { |
|
| 345 | 48 | $YYCURSOR++; |
|
| 346 | } |
||
| 347 | 1 | $value = ''; |
|
| 348 | 1 | $yych = $YYBUFFER[$YYCURSOR]; |
|
| 349 | 49 | View Code Duplication | if ($this->_SCAN_AZ[$yych]) { |
| 350 | $value .= $yych; |
||
| 351 | $yych = $YYBUFFER[++$YYCURSOR]; |
||
| 352 | while (isset($this->_SCAN_AZ[$yych])) { |
||
| 353 | $value .= $yych; |
||
| 354 | $yych = $YYBUFFER[++$YYCURSOR]; |
||
| 355 | } |
||
| 356 | $sort_type = strtoupper($value); |
||
| 357 | if (!($sort_type == 'ASC' || $sort_type == 'DESC')) { // If sort type is anything else than ASC or DESC, it is not part of the order by. |
||
| 358 | $sort_type = 'ASC'; |
||
| 359 | $YYCURSOR = $YYCURSOR - strlen($value); |
||
| 360 | $value = ''; |
||
| 361 | } |
||
| 362 | } else { |
||
| 363 | 1 | $sort_type = 'ASC'; |
|
| 364 | } |
||
| 365 | } |
||
| 366 | 38 | } |
|
| 367 | 50 | return $result; |
|
| 368 | } |
||
| 369 | |||
| 370 | |||
| 371 | protected function parse_join_target_properties(&$query) { |
||
| 386 | |||
| 387 | 197 | protected function parse_query(&$query) { |
|
| 388 | |||
| 389 | 197 | if (!preg_match('|^[[:space:]]*order[[:space:]]*by[[:space:]]+|i', $query, $regs)) { |
|
| 390 | 195 | $result=$this->parse_or_expr($query); |
|
| 391 | 147 | } else { |
|
| 392 | 2 | $no_selection = true; |
|
| 393 | } |
||
| 394 | |||
| 395 | /* |
||
| 396 | $YYCURSOR = 0; |
||
| 397 | while ($this->_SCAN_WS[$YYBUFFER[$YYCURSOR]]) { |
||
| 398 | $YYCURSOR++; |
||
| 399 | } |
||
| 400 | |||
| 401 | $yych = $YYBUFFER[$YYCURSOR]; |
||
| 402 | if ($this->_SCAN_AZ[$yych]) { |
||
| 403 | $value = $yych; |
||
| 404 | $yych = $YYBUFFER[++$YYCURSOR]; |
||
| 405 | while ($this->_SCAN_AZ[$yych]) { |
||
| 406 | $value .= $yych; |
||
| 407 | $yych = $YYBUFFER[++$YYCURSOR]; |
||
| 408 | } |
||
| 409 | $value = strtolower($value); |
||
| 410 | if ($value === 'order') { |
||
| 411 | while ($this->_SCAN_WS[$YYBUFFER[$YYCURSOR]]) { |
||
| 412 | $YYCURSOR++; |
||
| 413 | } |
||
| 414 | $yych = $YYBUFFER[$YYCURSOR]; |
||
| 415 | if ($this->_SCAN_AZ[$yych]) { |
||
| 416 | $value = $yych; |
||
| 417 | $yych = $YYBUFFER[++$YYCURSOR]; |
||
| 418 | while ($this->_SCAN_AZ[$yych]) { |
||
| 419 | $value .= $yych; |
||
| 420 | $yych = $YYBUFFER[++$YYCURSOR]; |
||
| 421 | } |
||
| 422 | $value = strtolower($value); |
||
| 423 | if ($value === 'by') { |
||
| 424 | $YYBUFFER = substr($YYBUFFER, $YYCURSOR; |
||
| 425 | $result = $this->parse_or_expr($YYBUFFER); |
||
| 426 | $YYCURSOR = 0; |
||
| 427 | $value = ''; |
||
| 428 | } else { |
||
| 429 | $this->error = "syntax error near: $YYBUFFER"; |
||
| 430 | return false; |
||
| 431 | } |
||
| 432 | } |
||
| 433 | } |
||
| 434 | } |
||
| 435 | |||
| 436 | */ |
||
| 437 | |||
| 438 | 197 | if (preg_match('|^[[:space:]]*join[[:space:]]*target[[:space:]]*on[[:space:]]*|i', $query, $regs)) { |
|
| 439 | $this->join_target_properties = array(); |
||
| 440 | $query = substr($query, strlen($regs[0])); |
||
| 441 | $this->parse_join_target_properties($query); |
||
| 442 | } |
||
| 443 | |||
| 444 | 197 | $matching = preg_match('|^[[:space:]]*order[[:space:]]*by[[:space:]]+|i', $query, $regs); |
|
| 445 | 197 | if ( $matching || $no_selection ) { |
|
| 446 | 50 | $query=substr($query, strlen($regs[0])); |
|
| 447 | 50 | $node["id"]="orderby"; |
|
| 448 | 50 | $node["right"]=$this->parse_orderby($query); |
|
| 449 | 50 | $node["left"]=$result; |
|
| 450 | 50 | $result=$node; |
|
| 451 | 38 | } |
|
| 452 | 197 | if (preg_match('|^[[:space:]]*limit[[:space:]]+([0-9]+)[[:space:]]*([,][[:space:]]*([0-9]+))?|i', $query, $regs)) { |
|
| 453 | 1 | $query=substr($query, strlen($regs[0])); |
|
| 454 | 1 | $limit_s["id"]="limit"; |
|
| 455 | 1 | $limit_s["offset"]=$regs[1]; |
|
| 456 | 1 | $limit_s["limit"]=$regs[3]; |
|
| 457 | 1 | } else { |
|
| 458 | 196 | $limit_s["id"]="limit"; |
|
| 459 | 196 | $limit_s["offset"]=($this->offset) ? $this->offset : 0; |
|
| 460 | 196 | $limit_s["limit"]=($this->limit) ? $this->limit : 0; |
|
| 461 | } |
||
| 462 | 197 | $limit_s["left"]=$result; |
|
| 463 | 197 | $result=$limit_s; |
|
| 464 | |||
| 465 | 197 | return $result; |
|
| 466 | } |
||
| 467 | |||
| 468 | // virtual (&private) method. To be implemented in the sql specific compiler |
||
| 469 | protected abstract function priv_sql_compile($node) ; |
||
| 470 | |||
| 471 | 197 | public function compile($path, $query, $limit=100, $offset=0, $layers = array()) { |
|
| 496 | |||
| 497 | |||
| 498 | } |
||
| 499 |
Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code.
Let’s take a look at an example:
As you can see in this example, the array
$myArrayis initialized the first time when the foreach loop is entered. You can also see that the value of thebarkey is only written conditionally; thus, its value might result from a previous iteration.This might or might not be intended. To make your intention clear, your code more readible and to avoid accidental bugs, we recommend to add an explicit initialization $myArray = array() either outside or inside the foreach loop.