Dumb Remove Scripts

remove-scripts-from-string-php.php

<?php

    // ps this does not work, use HTML Purifier
    // I mean this works, but it's not guaranteed to fix the problem
    // wth nested functions don't work as expected hmm
    // probably time to learn OOP, look at that $GLOBAL, could not get the final output out of the function
    // tried passing it in as parameter, regular global
    // another note, to avoid case sensitivity use str_ireplace so you can match script, SCRIPT, ScRiPt, without 
    // worrying about exact str index position, or just don't do this entirely

    $str = $content;
    $str_lc_copy = strtolower($str);
    $alphanums = str_split('abcdefghijklmnopqrstuvwxyz0123456789`~!@#$%^&*()-_=+[]/:;",.? ' . "'");
    $html_replace = [
        '<ul>'      => 'a___',
        '</ul>'     => 'b____',
        '<li>'      => 'c___',
        '</li>'     => 'd____',
        '<b>'       => 'e__',
        '</b>'      => 'f___',
        '<u>'       => 'g__',
        '</u>'      => 'h___',
        '<i>'       => 'j__',
        '</i>'      => 'k___',
        '<strong>'  => 'l_______',
        '</strong>' => 'm________'
    ];
    $test_str = '';
    $script_count = substr_count($str_lc_copy, 'script');
    $last_offset = 0;
    $run_count = 0;
    $GLOBALS['exp_str'] = '';
    
    // replace known wanted html with placeholders
    foreach ($html_replace as $wanted_html => $html_placeholder) {
        $str_lc_copy = str_replace($wanted_html, $html_placeholder, $str_lc_copy);
    }

    // &lt; &gt; replace
    // $str_lc_copy = str_replace('&lt;', '<   ', $str_lc_copy);
    // $str_lc_copy = str_replace('&gt;', '>   ', $str_lc_copy);
    
    function removeScript($inp_str, $script_count, $run_count, $alphanums, $last_offset, $str) {
    
        if ($run_count < $script_count) {
            
            $cur_script_pos = strpos($inp_str, 'script', $last_offset);
            
            if ($cur_script_pos !== false) {
                $prior_script_char = $inp_str[$cur_script_pos - 1];
                if ($prior_script_char) {
                    $left_str = substr($inp_str, 0, $cur_script_pos);
                    $right_str = substr($inp_str, $cur_script_pos + strlen('script'), strlen($inp_str));
                    if (!in_array($prior_script_char, $alphanums) || $prior_script_char === '/' ||  strpos($left_str, '&lt;') !== false || strpos($right_str, '&gt;') !== false) {
                        $inp_str = substr_replace($inp_str, '      ', $cur_script_pos, 6);
                        $str = substr_replace($inp_str, '      ', $cur_script_pos, 6);
                    }
                }
            }

            $last_offset = $cur_script_pos;
            
            $run_count += 1;
            
            $test_str = $inp_str;
            
            removeScript($test_str, $script_count, $run_count, $alphanums, $last_offset, $str);
        }
        else {
            $GLOBALS['exp_str'] = $inp_str;
        }
    }
    
    removeScript($str_lc_copy, $script_count, $run_count, $alphanums, $last_offset, $str);
    
    function removeHtmlPlaceholders($inp_str, $html_replace) {
        
        foreach ($html_replace as $html => $placeholder) {
            $inp_str = str_replace($placeholder, $html, $inp_str);
        }
        
        return $inp_str;
    }

    $str = $GLOBALS['exp_str'];
    
    $str = removeHtmlPlaceholders($str, $html_replace);

    // &lt; &gt; replace
    // $str = str_replace('<   ', '&lt;', $str);
    // $str = str_replace('>   ', '&gt;', $str);
    
    // duplicate spaces
    $str = preg_replace('!\s+!', ' ', $str);

    $content = $str;