vendor/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php

这里只显示每个文件的开头 60 行。登录后可以解锁完整代码。

微信扫码关注公众号，代码整理好后第一时间通知你。

<?php

/**
 * Parser that uses PHP 5's DOM extension (part of the core).
 *
 * In PHP 5, the DOM XML extension was revamped into DOM and added to the core.
 * It gives us a forgiving HTML parser, which we use to transform the HTML
 * into a DOM, and then into the tokens.  It is blazingly fast (for large
 * documents, it performs twenty times faster than
 * HTMLPurifier_Lexer_DirectLex,and is the default choice for PHP 5.
 *
 * @note Any empty elements will have empty tokens associated with them, even if
 * this is prohibited by the spec. This is cannot be fixed until the spec
 * comes into play.
 *
 * @note PHP's DOM extension does not actually parse any entities, we use
 *       our own function to do that.
 *
 * @warning DOM tends to drop whitespace, which may wreak havoc on indenting.
 *          If this is a huge problem, due to the fact that HTML is hand
 *          edited and you are unable to get a parser cache that caches the
 *          the output of HTML Purifier while keeping the original HTML lying
 *          around, you may want to run Tidy on the resulting output or use
 *          HTMLPurifier_DirectLex
 */

class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
{

    /**
     * @type HTMLPurifier_TokenFactory
     */
    private $factory;

    public function __construct()
    {
        // setup the factory
        parent::__construct();
        $this->factory = new HTMLPurifier_TokenFactory();
    }

    /**
     * @param string $html
     * @param HTMLPurifier_Config $config
     * @param HTMLPurifier_Context $context
     * @return HTMLPurifier_Token[]
     */
    public function tokenizeHTML($html, $config, $context)
    {
        $html = $this->normalize($html, $config, $context);

        // attempt to armor stray angled brackets that cannot possibly
        // form tags and thus are probably being used as emoticons
        if ($config->get('Core.AggressivelyFixLt')) {
            $char = '[^a-z!\/]';
            $comment = "/<!--(.*?)(-->|\z)/is";
            $html = preg_replace_callback($comment, array($this, 'callbackArmorCommentEntities'), $html);
            do {
                $old = $html;
                $html = preg_replace("/<($char)/i", '&lt;\\1', $html);