Server : Apache/2.4.41 (Ubuntu) System : Linux journalup 5.4.0-198-generic #218-Ubuntu SMP Fri Sep 27 20:18:53 UTC 2024 x86_64 User : www-data ( 33) 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, Directory :  /var/www/html/lib/pkp/classes/search/

Upload File : current_dir [ Writeable ] document_root [ Writeable ]

<?php

/**
 * @file classes/search/SearchHTMLParser.inc.php
 *
 * Copyright (c) 2014-2020 Simon Fraser University
 * Copyright (c) 2000-2020 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
		$line = fgetss($this->fp, 4096);

		// 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;
	}
}