voku /
simple_html_dom
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 HtmlDomParser 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 HtmlDomParser, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 22 | class HtmlDomParser |
||
| 23 | { |
||
| 24 | /** |
||
| 25 | * @var array |
||
| 26 | */ |
||
| 27 | protected static $functionAliases = [ |
||
| 28 | 'outertext' => 'html', |
||
| 29 | 'outerhtml' => 'html', |
||
| 30 | 'innertext' => 'innerHtml', |
||
| 31 | 'innerhtml' => 'innerHtml', |
||
| 32 | 'load' => 'loadHtml', |
||
| 33 | 'load_file' => 'loadHtmlFile', |
||
| 34 | ]; |
||
| 35 | |||
| 36 | /** |
||
| 37 | * @var string[][] |
||
| 38 | */ |
||
| 39 | protected static $domLinkReplaceHelper = [ |
||
| 40 | 'orig' => ['[', ']', '{', '}'], |
||
| 41 | 'tmp' => [ |
||
| 42 | '____SIMPLE_HTML_DOM__VOKU__SQUARE_BRACKET_LEFT____', |
||
| 43 | '____SIMPLE_HTML_DOM__VOKU__SQUARE_BRACKET_RIGHT____', |
||
| 44 | '____SIMPLE_HTML_DOM__VOKU__BRACKET_LEFT____', |
||
| 45 | '____SIMPLE_HTML_DOM__VOKU__BRACKET_RIGHT____', |
||
| 46 | ], |
||
| 47 | ]; |
||
| 48 | |||
| 49 | /** |
||
| 50 | * @var array |
||
| 51 | */ |
||
| 52 | protected static $domReplaceHelper = [ |
||
| 53 | 'orig' => ['&', '|', '+', '%', '@'], |
||
| 54 | 'tmp' => [ |
||
| 55 | '____SIMPLE_HTML_DOM__VOKU__AMP____', |
||
| 56 | '____SIMPLE_HTML_DOM__VOKU__PIPE____', |
||
| 57 | '____SIMPLE_HTML_DOM__VOKU__PLUS____', |
||
| 58 | '____SIMPLE_HTML_DOM__VOKU__PERCENT____', |
||
| 59 | '____SIMPLE_HTML_DOM__VOKU__AT____', |
||
| 60 | ], |
||
| 61 | ]; |
||
| 62 | |||
| 63 | protected static $domHtmlWrapperHelper = '____simple_html_dom__voku__html_wrapper____'; |
||
| 64 | |||
| 65 | protected static $domHtmlSpecialScriptHelper = '____simple_html_dom__voku__html_special_sctipt____'; |
||
| 66 | |||
| 67 | /** |
||
| 68 | * @var array |
||
| 69 | */ |
||
| 70 | protected static $domBrokenReplaceHelper = []; |
||
| 71 | |||
| 72 | /** |
||
| 73 | * @var callable |
||
| 74 | */ |
||
| 75 | protected static $callback; |
||
| 76 | |||
| 77 | /** |
||
| 78 | * @var \DOMDocument |
||
| 79 | */ |
||
| 80 | protected $document; |
||
| 81 | |||
| 82 | /** |
||
| 83 | * @var string |
||
| 84 | */ |
||
| 85 | protected $encoding = 'UTF-8'; |
||
| 86 | |||
| 87 | /** |
||
| 88 | * @var bool |
||
| 89 | */ |
||
| 90 | protected $isDOMDocumentCreatedWithoutHtml = false; |
||
| 91 | |||
| 92 | /** |
||
| 93 | * @var bool |
||
| 94 | */ |
||
| 95 | protected $isDOMDocumentCreatedWithoutWrapper = false; |
||
| 96 | |||
| 97 | /** |
||
| 98 | * @var bool |
||
| 99 | */ |
||
| 100 | protected $isDOMDocumentCreatedWithoutHeadWrapper = false; |
||
| 101 | |||
| 102 | /** |
||
| 103 | * @var bool |
||
| 104 | */ |
||
| 105 | protected $isDOMDocumentCreatedWithoutHtmlWrapper = false; |
||
| 106 | |||
| 107 | /** |
||
| 108 | * @var bool |
||
| 109 | */ |
||
| 110 | protected $isDOMDocumentCreatedWithFakeEndScript = false; |
||
| 111 | |||
| 112 | /** |
||
| 113 | * @var bool |
||
| 114 | */ |
||
| 115 | protected $keepBrokenHtml; |
||
| 116 | |||
| 117 | /** |
||
| 118 | * Constructor |
||
| 119 | * |
||
| 120 | * @param \DOMNode|SimpleHtmlDom|string $element HTML code or SimpleHtmlDom, \DOMNode |
||
| 121 | * |
||
| 122 | * @throws \InvalidArgumentException |
||
| 123 | */ |
||
| 124 | 134 | public function __construct($element = null) |
|
| 155 | |||
| 156 | /** |
||
| 157 | * @param $name |
||
| 158 | * @param $arguments |
||
| 159 | * |
||
| 160 | * @return bool|mixed |
||
| 161 | */ |
||
| 162 | 50 | View Code Duplication | public function __call($name, $arguments) |
| 172 | |||
| 173 | /** |
||
| 174 | * @param $name |
||
| 175 | * @param $arguments |
||
| 176 | * |
||
| 177 | * @throws \BadMethodCallException |
||
| 178 | * @throws \RuntimeException |
||
| 179 | * @throws \InvalidArgumentException |
||
| 180 | * |
||
| 181 | * @return HtmlDomParser |
||
| 182 | */ |
||
| 183 | 18 | public static function __callStatic($name, $arguments) |
|
| 209 | |||
| 210 | /** @noinspection MagicMethodsValidityInspection */ |
||
| 211 | |||
| 212 | /** |
||
| 213 | * @param $name |
||
| 214 | * |
||
| 215 | * @return string |
||
| 216 | */ |
||
| 217 | 14 | public function __get($name) |
|
| 235 | |||
| 236 | /** |
||
| 237 | * @param string $selector |
||
| 238 | * @param int $idx |
||
| 239 | * |
||
| 240 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNodeInterface |
||
| 241 | */ |
||
| 242 | 3 | public function __invoke($selector, $idx = null) |
|
| 246 | |||
| 247 | /** |
||
| 248 | * @return string |
||
| 249 | */ |
||
| 250 | 17 | public function __toString() |
|
| 254 | |||
| 255 | /** |
||
| 256 | * does nothing (only for api-compatibility-reasons) |
||
| 257 | * |
||
| 258 | * @deprecated |
||
| 259 | * |
||
| 260 | * @return bool |
||
| 261 | */ |
||
| 262 | 1 | public function clear(): bool |
|
| 266 | |||
| 267 | /** |
||
| 268 | * @param string $html |
||
| 269 | * |
||
| 270 | * @return string |
||
| 271 | */ |
||
| 272 | 123 | public static function replaceToPreserveHtmlEntities(string $html): string |
|
| 307 | |||
| 308 | /** |
||
| 309 | * @param string $html |
||
| 310 | * |
||
| 311 | * @return string |
||
| 312 | */ |
||
| 313 | 79 | public static function putReplacedBackToPreserveHtmlEntities(string $html): string |
|
| 350 | |||
| 351 | /** |
||
| 352 | * Create DOMDocument from HTML. |
||
| 353 | * |
||
| 354 | * @param string $html |
||
| 355 | * @param int|null $libXMLExtraOptions |
||
| 356 | * |
||
| 357 | * @return \DOMDocument |
||
| 358 | */ |
||
| 359 | 122 | private function createDOMDocument(string $html, $libXMLExtraOptions = null): \DOMDocument |
|
| 466 | |||
| 467 | /** |
||
| 468 | * @param string $html |
||
| 469 | */ |
||
| 470 | 1 | protected function keepSpecialScriptTags(string &$html) |
|
| 486 | |||
| 487 | /** |
||
| 488 | * @param string $html |
||
| 489 | * |
||
| 490 | * @return string |
||
| 491 | */ |
||
| 492 | 2 | protected function keepBrokenHtml(string $html): string |
|
| 493 | { |
||
| 494 | do { |
||
| 495 | 2 | $original = $html; |
|
| 496 | |||
| 497 | 2 | $html = (string) \preg_replace_callback( |
|
| 498 | 2 | '/(?<start>.*)<(?<element_start>[a-z]+)(?<element_start_addon> [^>]*)?>(?<value>.*?)<\/(?<element_end>\2)>(?<end>.*)/sui', |
|
| 499 | function ($matches) { |
||
| 500 | 2 | return $matches['start'] . |
|
| 501 | 2 | '°lt_simple_html_dom__voku_°' . $matches['element_start'] . $matches['element_start_addon'] . '°gt_simple_html_dom__voku_°' . |
|
| 502 | 2 | $matches['value'] . |
|
| 503 | 2 | '°lt/_simple_html_dom__voku_°' . $matches['element_end'] . '°gt_simple_html_dom__voku_°' . |
|
| 504 | 2 | $matches['end']; |
|
| 505 | 2 | }, |
|
| 506 | 2 | $html |
|
| 507 | ); |
||
| 508 | 2 | } while ($original !== $html); |
|
| 509 | |||
| 510 | do { |
||
| 511 | 2 | $original = $html; |
|
| 512 | |||
| 513 | 2 | $html = (string) \preg_replace_callback( |
|
| 514 | 2 | '/(?<start>[^<]*)?(?<broken>(?:(?:<\/\w+(?:\s+\w+=\\"[^\"]+\\")*+)(?:[^<]+)>)+)(?<end>.*)/u', |
|
| 515 | function ($matches) { |
||
| 516 | 2 | $matches['broken'] = \str_replace( |
|
| 517 | 2 | ['°lt/_simple_html_dom__voku_°', '°lt_simple_html_dom__voku_°', '°gt_simple_html_dom__voku_°'], |
|
| 518 | 2 | ['</', '<', '>'], |
|
| 519 | 2 | $matches['broken'] |
|
| 520 | ); |
||
| 521 | |||
| 522 | 2 | self::$domBrokenReplaceHelper['orig'][] = $matches['broken']; |
|
| 523 | 2 | self::$domBrokenReplaceHelper['tmp'][] = $matchesHash = '____simple_html_dom__voku__broken_html____' . \crc32($matches['broken']); |
|
| 524 | |||
| 525 | 2 | return $matches['start'] . $matchesHash . $matches['end']; |
|
| 526 | 2 | }, |
|
| 527 | 2 | $html |
|
| 528 | ); |
||
| 529 | 2 | } while ($original !== $html); |
|
| 530 | |||
| 531 | 2 | return \str_replace( |
|
| 532 | 2 | ['°lt/_simple_html_dom__voku_°', '°lt_simple_html_dom__voku_°', '°gt_simple_html_dom__voku_°'], |
|
| 533 | 2 | ['</', '<', '>'], |
|
| 534 | 2 | $html |
|
| 535 | ); |
||
| 536 | } |
||
| 537 | |||
| 538 | /** |
||
| 539 | * Return element by #id. |
||
| 540 | * |
||
| 541 | * @param string $id |
||
| 542 | * |
||
| 543 | * @return SimpleHtmlDom|SimpleHtmlDomNodeBlank |
||
| 544 | */ |
||
| 545 | 2 | public function getElementById(string $id) |
|
| 549 | |||
| 550 | /** |
||
| 551 | * Return element by tag name. |
||
| 552 | * |
||
| 553 | * @param string $name |
||
| 554 | * |
||
| 555 | * @return SimpleHtmlDom|SimpleHtmlDomNodeBlank |
||
| 556 | */ |
||
| 557 | 1 | public function getElementByTagName(string $name) |
|
| 567 | |||
| 568 | /** |
||
| 569 | * Returns elements by #id. |
||
| 570 | * |
||
| 571 | * @param string $id |
||
| 572 | * @param int|null $idx |
||
| 573 | * |
||
| 574 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNodeInterface |
||
| 575 | */ |
||
| 576 | public function getElementsById(string $id, $idx = null) |
||
| 580 | |||
| 581 | /** |
||
| 582 | * Returns elements by tag name. |
||
| 583 | * |
||
| 584 | * @param string $name |
||
| 585 | * @param int|null $idx |
||
| 586 | * |
||
| 587 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNode|SimpleHtmlDomNodeBlank |
||
| 588 | */ |
||
| 589 | 3 | View Code Duplication | public function getElementsByTagName(string $name, $idx = null) |
| 612 | |||
| 613 | /** |
||
| 614 | * Find one node with a CSS selector. |
||
| 615 | * |
||
| 616 | * @param string $selector |
||
| 617 | * |
||
| 618 | * @return SimpleHtmlDom|SimpleHtmlDomNodeInterface |
||
| 619 | */ |
||
| 620 | 2 | public function findOne(string $selector) |
|
| 624 | |||
| 625 | /** |
||
| 626 | * Find list of nodes with a CSS selector. |
||
| 627 | * |
||
| 628 | * @param string $selector |
||
| 629 | * @param int $idx |
||
| 630 | * |
||
| 631 | * @return SimpleHtmlDom|SimpleHtmlDom[]|SimpleHtmlDomNodeInterface |
||
| 632 | */ |
||
| 633 | 85 | public function find(string $selector, $idx = null) |
|
| 658 | |||
| 659 | /** |
||
| 660 | * @param string $content |
||
| 661 | * @param bool $multiDecodeNewHtmlEntity |
||
| 662 | * |
||
| 663 | * @return string |
||
| 664 | */ |
||
| 665 | 70 | public function fixHtmlOutput(string $content, bool $multiDecodeNewHtmlEntity = false): string |
|
| 775 | |||
| 776 | /** |
||
| 777 | * @return \DOMDocument |
||
| 778 | */ |
||
| 779 | 39 | public function getDocument(): \DOMDocument |
|
| 783 | |||
| 784 | /** |
||
| 785 | * Get the encoding to use. |
||
| 786 | * |
||
| 787 | * @return string |
||
| 788 | */ |
||
| 789 | 134 | private function getEncoding(): string |
|
| 793 | |||
| 794 | /** |
||
| 795 | * @return bool |
||
| 796 | */ |
||
| 797 | 9 | public function getIsDOMDocumentCreatedWithoutHtml(): bool |
|
| 801 | |||
| 802 | /** |
||
| 803 | * @return bool |
||
| 804 | */ |
||
| 805 | 45 | public function getIsDOMDocumentCreatedWithoutHtmlWrapper(): bool |
|
| 809 | |||
| 810 | /** |
||
| 811 | * @return bool |
||
| 812 | */ |
||
| 813 | 9 | public function getIsDOMDocumentCreatedWithoutHeadWrapper(): bool |
|
| 817 | |||
| 818 | /** |
||
| 819 | * @return bool |
||
| 820 | */ |
||
| 821 | public function getIsDOMDocumentCreatedWithoutWrapper(): bool |
||
| 825 | |||
| 826 | /** |
||
| 827 | * Get dom node's outer html. |
||
| 828 | * |
||
| 829 | * @param bool $multiDecodeNewHtmlEntity |
||
| 830 | * |
||
| 831 | * @return string |
||
| 832 | */ |
||
| 833 | 45 | public function html(bool $multiDecodeNewHtmlEntity = false): string |
|
| 847 | |||
| 848 | /** |
||
| 849 | * @param bool $keepBrokenHtml |
||
| 850 | * |
||
| 851 | * @return HtmlDomParser |
||
| 852 | */ |
||
| 853 | 2 | public function useKeepBrokenHtml(bool $keepBrokenHtml): self |
|
| 859 | |||
| 860 | /** |
||
| 861 | * Get the HTML as XML. |
||
| 862 | * |
||
| 863 | * @param bool $multiDecodeNewHtmlEntity |
||
| 864 | * |
||
| 865 | * @return string |
||
| 866 | */ |
||
| 867 | 2 | public function xml(bool $multiDecodeNewHtmlEntity = false): string |
|
| 876 | |||
| 877 | /** |
||
| 878 | * Get dom node's inner html. |
||
| 879 | * |
||
| 880 | * @param bool $multiDecodeNewHtmlEntity |
||
| 881 | * |
||
| 882 | * @return string |
||
| 883 | */ |
||
| 884 | 19 | public function innerHtml(bool $multiDecodeNewHtmlEntity = false): string |
|
| 895 | |||
| 896 | /** |
||
| 897 | * Load HTML from string. |
||
| 898 | * |
||
| 899 | * @param string $html |
||
| 900 | * @param int|null $libXMLExtraOptions |
||
| 901 | * |
||
| 902 | * @throws \InvalidArgumentException if argument is not string |
||
| 903 | * |
||
| 904 | * @return HtmlDomParser |
||
| 905 | */ |
||
| 906 | 122 | public function loadHtml(string $html, $libXMLExtraOptions = null): self |
|
| 912 | |||
| 913 | /** |
||
| 914 | * Load HTML from file. |
||
| 915 | * |
||
| 916 | * @param string $filePath |
||
| 917 | * @param int|null $libXMLExtraOptions |
||
| 918 | * |
||
| 919 | * @throws \RuntimeException |
||
| 920 | * @throws \InvalidArgumentException |
||
| 921 | * |
||
| 922 | * @return HtmlDomParser |
||
| 923 | */ |
||
| 924 | 11 | public function loadHtmlFile(string $filePath, $libXMLExtraOptions = null): self |
|
| 951 | |||
| 952 | /** |
||
| 953 | * Save the html-dom as string. |
||
| 954 | * |
||
| 955 | * @param string $filepath |
||
| 956 | * |
||
| 957 | * @return string |
||
| 958 | */ |
||
| 959 | 1 | public function save(string $filepath = ''): string |
|
| 968 | |||
| 969 | /** |
||
| 970 | * @param $functionName |
||
| 971 | */ |
||
| 972 | public function set_callback($functionName) |
||
| 976 | |||
| 977 | /** |
||
| 978 | * Get dom node's plain text. |
||
| 979 | * |
||
| 980 | * @param bool $multiDecodeNewHtmlEntity |
||
| 981 | * |
||
| 982 | * @return string |
||
| 983 | */ |
||
| 984 | 3 | public function text(bool $multiDecodeNewHtmlEntity = false): string |
|
| 988 | |||
| 989 | public function __clone() |
||
| 993 | } |
||
| 994 |
Loading history...
Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation.
You can also find more detailed suggestions in the “Code” section of your repository.