vendor/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/DirectLex.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

/**
 * Our in-house implementation of a parser.
 *
 * A pure PHP parser, DirectLex has absolutely no dependencies, making
 * it a reasonably good default for PHP4.  Written with efficiency in mind,
 * it can be four times faster than HTMLPurifier_Lexer_PEARSax3, although it
 * pales in comparison to HTMLPurifier_Lexer_DOMLex.
 *
 * @todo Reread XML spec and document differences.
 */
class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
{
    /**
     * @type bool
     */
    public $tracksLineNumbers = true;

    /**
     * Whitespace characters for str(c)spn.
     * @type string
     */
    protected $_whitespace = "\x20\x09\x0D\x0A";

    /**
     * Callback function for script CDATA fudge
     * @param array $matches, in form of array(opening tag, contents, closing tag)
     * @return string
     */
    protected function scriptCallback($matches)
    {
        return $matches[1] . htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8') . $matches[3];
    }

    /**
     * @param String $html
     * @param HTMLPurifier_Config $config
     * @param HTMLPurifier_Context $context
     * @return array|HTMLPurifier_Token[]
     */
    public function tokenizeHTML($html, $config, $context)
    {
        // special normalization for script tags without any armor
        // our "armor" heurstic is a < sign any number of whitespaces after
        // the first script tag
        if ($config->get('HTML.Trusted')) {
            $html = preg_replace_callback(
                '#(<script[^>]*>)(\s*[^<].+?)(</script>)#si',
                array($this, 'scriptCallback'),
                $html
            );
        }

        $html = $this->normalize($html, $config, $context);

        $cursor = 0; // our location in the text
        $inside_tag = false; // whether or not we're parsing the inside of a tag
        $array = array(); // result array