| Server IP : 10.10.92.66 / Your IP : 104.23.197.231 Web Server : Apache/2.4.52 (Ubuntu) System : Linux jurnalpolinema 5.15.0-177-generic #187-Ubuntu SMP Sat Apr 11 22:54:33 UTC 2026 x86_64 User : jurnal ( 1001) PHP Version : 7.4.33 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare, MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : ON Directory : /home/jurnal/public_html/lib/pkp/classes/search/ |
Upload File : |
<?php
/**
* @file classes/search/SearchHTMLParser.inc.php
*
* Copyright (c) 2014-2021 Simon Fraser University
* Copyright (c) 2000-2021 John Willinsky
* Distributed under the GNU GPL v3. For full terms see the file docs/COPYING.
*
* @class SearchHTMLParser
* @ingroup search
*
* @brief Class to extract text from an HTML file.
*/
import('lib.pkp.classes.search.SearchFileParser');
import('lib.pkp.classes.core.PKPString');
class SearchHTMLParser extends SearchFileParser {
function doRead() {
// strip HTML tags from the read line
$line = strip_tags(fgets($this->fp));
// convert HTML entities to valid UTF-8 characters
$line = html_entity_decode($line, ENT_COMPAT, 'UTF-8');
// slightly (~10%) faster than above, but not quite as accurate, and requires html_entity_decode()
// $line = html_entity_decode($line, ENT_COMPAT, strtoupper(Config::getVar('i18n', 'client_charset')));
return $line;
}
}