kses.php

是一个优秀的语义个人发布平台

<?php
// Added wp_ prefix to avoid conflicts with existing kses users
# kses 0.2.1 - HTML/XHTML filter that only allows some elements and attributes
# Copyright (C) 2002, 2003  Ulf Harnhammar
# *** CONTACT INFORMATION ***
#
# E-mail:      metaur at users dot sourceforge dot net
# Web page:    http://sourceforge.net/projects/kses
# Paper mail:  (not at the moment)
#
# [kses strips evil scripts!]
if (!defined('CUSTOM_TAGS'))
	define('CUSTOM_TAGS', false);
	
// You can override this in your my-hacks.php file
if (!CUSTOM_TAGS) {
$allowedtags = array(
				'a' => array(
					'href' => array(),
					'title' => array(),
					'rel' => array()),
				'abbr' => array('title' => array()),
				'acronym' => array('title' => array()),
				'b' => array(),
				'blockquote' => array('cite' => array()),
//				'br' => array(),
				'code' => array(),
//				'del' => array('datetime' => array()),
//				'dd' => array(),
//				'dl' => array(),
//				'dt' => array(),
				'em' => array(),
				'i' => array(),
//				'ins' => array('datetime' => array(), 'cite' => array()),
//				'li' => array(),
//				'ol' => array(),
//				'p' => array(),
//				'q' => array(),
				'strike' => array(),
				'strong' => array(),
//				'sub' => array(),
//				'sup' => array(),
//				'u' => array(),
//				'ul' => array(),
				);
}
function wp_kses($string, $allowed_html, $allowed_protocols =
               array('http', 'https', 'ftp', 'news', 'nntp', 'telnet',
                     'gopher', 'mailto'))
###############################################################################
# This function makes sure that only the allowed HTML element names, attribute
# names and attribute values plus only sane HTML entities will occur in
# $string. You have to remove any slashes from PHP's magic quotes before you
# call this function.
###############################################################################
{
  $string = wp_kses_no_null($string);
  $string = wp_kses_js_entities($string);
  $string = wp_kses_normalize_entities($string);
  $string = wp_kses_hook($string);
  $allowed_html_fixed = wp_kses_array_lc($allowed_html);
  return wp_kses_split($string, $allowed_html_fixed, $allowed_protocols);
} # function wp_kses


function wp_kses_hook($string)
###############################################################################
# You add any kses hooks here.
###############################################################################
{
  return $string;
} # function wp_kses_hook


function wp_kses_version()
###############################################################################
# This function returns kses' version number.
###############################################################################
{
  return '0.2.1';
} # function wp_kses_version


function wp_kses_split($string, $allowed_html, $allowed_protocols)
###############################################################################
# This function searches for HTML tags, no matter how malformed. It also
# matches stray ">" characters.
###############################################################################
{
  return preg_replace('%(<'.   # EITHER: <
                      '[^>]*'. # things that aren't >
                      '(>|$)'. # > or end of string
                      '|>)%e', # OR: just a >
                      "wp_kses_split2('\\1', \$allowed_html, ".
                      '$allowed_protocols)',
                      $string);
} # function wp_kses_split


function wp_kses_split2($string, $allowed_html, $allowed_protocols)
###############################################################################
# This function does a lot of work. It rejects some very malformed things
# like <:::>. It returns an empty string, if the element isn't allowed (look
# ma, no strip_tags()!). Otherwise it splits the tag into an element and an
# attribute list.
###############################################################################
{
  $string = wp_kses_stripslashes($string);

  if (substr($string, 0, 1) != '<')
    return '&gt;';
    # It matched a ">" character

  if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches))
    return '';
    # It's seriously malformed

  $slash = trim($matches[1]);
  $elem = $matches[2];
  $attrlist = $matches[3];

  if (!is_array($allowed_html[strtolower($elem)]))
    return '';
    # They are using a not allowed HTML element

  return wp_kses_attr("$slash$elem", $attrlist, $allowed_html,
                   $allowed_protocols);
} # function wp_kses_split2


function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols)
###############################################################################
# This function removes all attributes, if none are allowed for this element.
# If some are allowed it calls wp_kses_hair() to split them further, and then it
# builds up new HTML code from the data that kses_hair() returns. It also
# removes "<" and ">" characters, if there are any left. One more thing it
# does is to check if the tag has a closing XHTML slash, and if it does,
# it puts one in the returned code as well.
###############################################################################
{
# Is there a closing XHTML slash at the end of the attributes?

  $xhtml_slash = '';
  if (preg_match('%\s/\s*$%', $attr))
    $xhtml_slash = ' /';

# Are any attributes allowed at all for this element?

  if (count($allowed_html[strtolower($element)]) == 0)
    return "<$element$xhtml_slash>";

# Split it

  $attrarr = wp_kses_hair($attr, $allowed_protocols);

# Go through $attrarr, and save the allowed attributes for this element
# in $attr2

  $attr2 = '';

  foreach ($attrarr as $arreach)
  {
    $current = $allowed_html[strtolower($element)]
                            [strtolower($arreach['name'])];
    if ($current == '')
      continue; # the attribute is not allowed

    if (!is_array($current))
      $attr2 .= ' '.$arreach['whole'];
    # there are no checks

    else
    {
    # there are some checks
      $ok = true;
      foreach ($current as $currkey => $currval)
        if (!wp_kses_check_attr_val($arreach['value'], $arreach['vless'],
                                 $currkey, $currval))
        { $ok = false; break; }

      if ($ok)
        $attr2 .= ' '.$arreach['whole']; # it passed them
    } # if !is_array($current)
  } # foreach

# Remove any "<" or ">" characters

  $attr2 = preg_replace('/[<>]/', '', $attr2);

  return "<$element$attr2$xhtml_slash>";
} # function wp_kses_attr


function wp_kses_hair($attr, $allowed_protocols)
###############################################################################
# This function does a lot of work. It parses an attribute list into an array
# with attribute data, and tries to do the right thing even if it gets weird
# input. It will add quotes around attribute values that don't have any quotes
# or apostrophes around them, to make it easier to produce HTML code that will
# conform to W3C's HTML specification. It will also remove bad URL protocols
# from attribute values.
###############################################################################
{
  $attrarr = array();
  $mode = 0;
  $attrname = '';

# Loop through the whole attribute list

  while (strlen($attr) != 0)
  {
    $working = 0; # Was the last operation successful?

    switch ($mode)
    {
      case 0: # attribute name, href for instance

        if (preg_match('/^([-a-zA-Z]+)/', $attr, $match))
        {
          $attrname = $match[1];
          $working = $mode = 1;
          $attr = preg_replace('/^[-a-zA-Z]+/', '', $attr);
        }

        break;

      case 1: # equals sign or valueless ("selected")

        if (preg_match('/^\s*=\s*/', $attr)) # equals sign
        {
          $working = 1; $mode = 2;
          $attr = preg_replace('/^\s*=\s*/', '', $attr);
          break;
        }

        if (preg_match('/^\s+/', $attr)) # valueless
        {
          $working = 1; $mode = 0;
          $attrarr[] = array
                        ('name'  => $attrname,
                         'value' => '',
                         'whole' => $attrname,
                         'vless' => 'y');
          $attr = preg_replace('/^\s+/', '', $attr);
        }

        break;

      case 2: # attribute value, a URL after href= for instance

        if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match))
         # "value"
        {
          $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols);

          $attrarr[] = array
                        ('name'  => $attrname,
                         'value' => $thisval,
                         'whole' => "$attrname=\"$thisval\"",
                         'vless' => 'n');
          $working = 1; $mode = 0;
          $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr);
          break;
        }

        if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match))
         # 'value'
        {
          $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols);

          $attrarr[] = array
                        ('name'  => $attrname,
                         'value' => $thisval,
                         'whole' => "$attrname='$thisval'",
                         'vless' => 'n');
          $working = 1; $mode = 0;
          $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr);
          break;
        }

        if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match))
         # value
        {
          $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols);