Feature #16534 » indexed_search_4167_v2.diff
typo3/sysext/indexed_search/class.crawler.php (working copy) | ||
---|---|---|
27 | 27 |
/** |
28 | 28 |
* Crawler hook for indexed search. Works with the "crawler" extension |
29 | 29 |
* |
30 |
* @author Kasper Sk?rh?j <kasperYYYY@typo3.com>
|
|
30 |
* @author Kasper Skaarhoj <kasperYYYY@typo3.com>
|
|
31 | 31 |
*/ |
32 | 32 |
/** |
33 | 33 |
* [CLASS/FUNCTION INDEX of SCRIPT] |
... | ... | |
601 | 601 |
* |
602 | 602 |
* @param string URL string to check |
603 | 603 |
* @param array Array of already indexed URLs (input url is looked up here and must not exist already) |
604 |
* @param string Base URL of the indexing process (input URL must be "inside" the base URL!) |
|
604 |
* @param string Base URL of the indexing process (input URL must be "inside" the base URL!). If the base URL is pointing to a file, the path to the file is stripped of for checking.
|
|
605 | 605 |
* @return string Returls the URL if OK, otherwise false |
606 | 606 |
*/ |
607 | 607 |
function checkUrl($url,$urlLog,$baseUrl) { |
... | ... | |
606 | 606 |
*/ |
607 | 607 |
function checkUrl($url,$urlLog,$baseUrl) { |
608 | 608 |
$url = preg_replace('/\/\/$/','/',$url); |
609 | ||
610 |
// just geht the root of the URL like http://www.domain.tld/ |
|
611 |
$baseUrlArray = parse_url($baseUrl); |
|
612 |
$baseUrl = $baseUrlArray['scheme'] . '://'. $baseUrlArray['host'] .'/'; |
|
613 | ||
609 | 614 |
list($url) = explode('#',$url); |
610 | 615 | |
611 | 616 |
if (!strstr($url,'../')) { |
- « Previous
- 1
- 2
- Next »