vendor/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.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

// if want to implement error collecting here, we'll need to use some sort
// of global data (probably trigger_error) because it's impossible to pass
// $config or $context to the callback functions.

/**
 * Handles referencing and derefencing character entities
 */
class HTMLPurifier_EntityParser
{

    /**
     * Reference to entity lookup table.
     * @type HTMLPurifier_EntityLookup
     */
    protected $_entity_lookup;

    /**
     * Callback regex string for entities in text.
     * @type string
     */
    protected $_textEntitiesRegex;

    /**
     * Callback regex string for entities in attributes.
     * @type string
     */
    protected $_attrEntitiesRegex;

    /**
     * Tests if the beginning of a string is a semi-optional regex
     */
    protected $_semiOptionalPrefixRegex;

    public function __construct() {
        // From
        // http://stackoverflow.com/questions/15532252/why-is-reg-being-rendered-as-without-the-bounding-semicolon
        $semi_optional = "quot|QUOT|lt|LT|gt|GT|amp|AMP|AElig|Aacute|Acirc|Agrave|Aring|Atilde|Auml|COPY|Ccedil|ETH|Eacute|Ecirc|Egrave|Euml|Iacute|Icirc|Igrave|Iuml|Ntilde|Oacute|Ocirc|Ograve|Oslash|Otilde|Ouml|REG|THORN|Uacute|Ucirc|Ugrave|Uuml|Yacute|aacute|acirc|acute|aelig|agrave|aring|atilde|auml|brvbar|ccedil|cedil|cent|copy|curren|deg|divide|eacute|ecirc|egrave|eth|euml|frac12|frac14|frac34|iacute|icirc|iexcl|igrave|iquest|iuml|laquo|macr|micro|middot|nbsp|not|ntilde|oacute|ocirc|ograve|ordf|ordm|oslash|otilde|ouml|para|plusmn|pound|raquo|reg|sect|shy|sup1|sup2|sup3|szlig|thorn|times|uacute|ucirc|ugrave|uml|uuml|yacute|yen|yuml";

        // NB: three empty captures to put the fourth match in the right
        // place
        $this->_semiOptionalPrefixRegex = "/&()()()($semi_optional)/";

        $this->_textEntitiesRegex =
            '/&(?:'.
            // hex
            '[#]x([a-fA-F0-9]+);?|'.
            // dec
            '[#]0*(\d+);?|'.
            // string (mandatory semicolon)
            // NB: order matters: match semicolon preferentially
            '([A-Za-z_:][A-Za-z0-9.\-_:]*);|'.
            // string (optional semicolon)
            "($semi_optional)".
            ')/';

        $this->_attrEntitiesRegex =
            '/&(?:'.
            // hex