locutus/php/strings/strip_tags.js

Locutus other languages' standard libraries to JavaScript for fun and educational purposes

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.strip_tags = strip_tags;
const _phpCastString_ts_1 = require("../_helpers/_phpCastString.js");
function strip_tags(input, allowed) {
    //      discuss at: https://locutus.io/php/strip_tags/
    // parity verified: PHP 8.3
    //     original by: Kevin van Zonneveld (https://kvz.io)
    //     improved by: Luke Godfrey
    //     improved by: Kevin van Zonneveld (https://kvz.io)
    //        input by: Pul
    //        input by: Alex
    //        input by: Marc Palau
    //        input by: Brett Zamir (https://brett-zamir.me)
    //        input by: Bobby Drake
    //        input by: Evertjan Garretsen
    //     bugfixed by: Kevin van Zonneveld (https://kvz.io)
    //     bugfixed by: Onno Marsman (https://twitter.com/onnomarsman)
    //     bugfixed by: Kevin van Zonneveld (https://kvz.io)
    //     bugfixed by: Kevin van Zonneveld (https://kvz.io)
    //     bugfixed by: Eric Nagel
    //     bugfixed by: Kevin van Zonneveld (https://kvz.io)
    //     bugfixed by: Tomasz Wesolowski
    //     bugfixed by: Tymon Sturgeon (https://scryptonite.com)
    //     bugfixed by: Tim de Koning (https://www.kingsquare.nl)
    //      revised by: Rafał Kukawski (https://blog.kukawski.pl)
    //       example 1: strip_tags('<p>Kevin</p> <br /><b>van</b> <i>Zonneveld</i>', '<i><b>')
    //       returns 1: 'Kevin <b>van</b> <i>Zonneveld</i>'
    //       example 2: strip_tags('<p>Kevin <img src="someimage.png" onmouseover="someFunction()">van <i>Zonneveld</i></p>', '<p>')
    //       returns 2: '<p>Kevin van Zonneveld</p>'
    //       example 3: strip_tags("<a href='https://kvz.io'>Kevin van Zonneveld</a>", "<a>")
    //       returns 3: "<a href='https://kvz.io'>Kevin van Zonneveld</a>"
    //       example 4: strip_tags('1 < 5 5 > 1')
    //       returns 4: '1 < 5 5 > 1'
    //       example 5: strip_tags('1 <br/> 1')
    //       returns 5: '1  1'
    //       example 6: strip_tags('1 <br/> 1', '<br>')
    //       returns 6: '1 <br/> 1'
    //       example 7: strip_tags('1 <br/> 1', '<br><br/>')
    //       returns 7: '1 <br/> 1'
    //       example 8: strip_tags('<i>hello</i> <<foo>script>world<</foo>/script>')
    //       returns 8: 'hello world'
    //       example 9: strip_tags(4)
    //       returns 9: '4'
    // making sure the allowed arg is a string containing only tags in lowercase (<a><b><c>)
    allowed = (((allowed || '') + '').toLowerCase().match(/<[a-z][a-z0-9]*>/g) || []).join('');
    const tags = /<\/?([a-z0-9]*)\b[^>]*>?/gi;
    const commentsAndPhpTags = /<!--[\s\S]*?-->|<\?(?:php)?[\s\S]*?\?>/gi;
    let after = (0, _phpCastString_ts_1._phpCastString)(input);
    // removes tha '<' char at the end of the string to replicate PHP's behaviour
    after = after.endsWith('<') ? after.slice(0, -1) : after;
    // recursively remove tags to ensure that the returned string doesn't contain forbidden tags after previous passes (e.g. '<<bait/>switch/>')
    while (true) {
        const before = after;
        after = before.replace(commentsAndPhpTags, '').replace(tags, function ($0, $1) {
            return allowed.includes('<' + $1.toLowerCase() + '>') ? $0 : '';
        });
        // return once no more tags are removed
        if (before === after) {
            return after;
        }
    }
}