kses.php

完美的在线教育系统

                         'value' => $thisval,
                         'whole' => "$attrname=\"$thisval\"",
                         'vless' => 'n');
                         # We add quotes to conform to W3C's HTML spec.
          $working = 1; $mode = 0;
          $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr);
        }

        break;
    } # switch

    if ($working == 0) # not well formed, remove and try again
    {
      $attr = kses_html_error($attr);
      $mode = 0;
    }
  } # while

  if ($mode == 1)
  # special case, for when the attribute list ends with a valueless
  # attribute like "selected"
    $attrarr[] = array
                  ('name'  => $attrname,
                   'value' => '',
                   'whole' => $attrname,
                   'vless' => 'y');

  return $attrarr;
} # function kses_hair


function kses_check_attr_val($value, $vless, $checkname, $checkvalue)
###############################################################################
# This function performs different checks for attribute values. The currently
# implemented checks are "maxlen", "minlen", "maxval", "minval" and "valueless"
# with even more checks to come soon.
###############################################################################
{
  $ok = true;

  switch (strtolower($checkname))
  {
    case 'maxlen':
    # The maxlen check makes sure that the attribute value has a length not
    # greater than the given value. This can be used to avoid Buffer Overflows
    # in WWW clients and various Internet servers.

      if (strlen($value) > $checkvalue)
        $ok = false;
      break;

    case 'minlen':
    # The minlen check makes sure that the attribute value has a length not
    # smaller than the given value.

      if (strlen($value) < $checkvalue)
        $ok = false;
      break;

    case 'maxval':
    # The maxval check does two things: it checks that the attribute value is
    # an integer from 0 and up, without an excessive amount of zeroes or
    # whitespace (to avoid Buffer Overflows). It also checks that the attribute
    # value is not greater than the given value.
    # This check can be used to avoid Denial of Service attacks.

      if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value))
        $ok = false;
      if ($value > $checkvalue)
        $ok = false;
      break;

    case 'minval':
    # The minval check checks that the attribute value is a positive integer,
    # and that it is not smaller than the given value.

      if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value))
        $ok = false;
      if ($value < $checkvalue)
        $ok = false;
      break;

    case 'valueless':
    # The valueless check checks if the attribute has a value
    # (like <a href="blah">) or not (<option selected>). If the given value
    # is a "y" or a "Y", the attribute must not have a value.
    # If the given value is an "n" or an "N", the attribute must have one.

      if (strtolower($checkvalue) != $vless)
        $ok = false;
      break;
  } # switch

  return $ok;
} # function kses_check_attr_val


function kses_bad_protocol($string, $allowed_protocols)
###############################################################################
# This function removes all non-allowed protocols from the beginning of
# $string. It ignores whitespace and the case of the letters, and it does
# understand HTML entities. It does its work in a while loop, so it won't be
# fooled by a string like "javascript:javascript:alert(57)".
###############################################################################
{
  $string = kses_no_null($string);
  $string = preg_replace('/\xad+/', '', $string); # deals with Opera "feature"
  $string2 = $string.'a';

  while ($string != $string2)
  {
    $string2 = $string;
    $string = kses_bad_protocol_once($string, $allowed_protocols);
  } # while

  return $string;
} # function kses_bad_protocol


function kses_no_null($string)
###############################################################################
# This function removes any NULL characters in $string.
###############################################################################
{
  $string = preg_replace('/\0+/', '', $string);
  $string = preg_replace('/(\\\\0)+/', '', $string);

  return $string;
} # function kses_no_null


function kses_stripslashes($string)
###############################################################################
# This function changes the character sequence  \"  to just  "
# It leaves all other slashes alone. It's really weird, but the quoting from
# preg_replace(//e) seems to require this.
###############################################################################
{
  return preg_replace('%\\\\"%', '"', $string);
} # function kses_stripslashes


function kses_array_lc($inarray)
###############################################################################
# This function goes through an array, and changes the keys to all lower case.
###############################################################################
{
  $outarray = array();

  foreach ($inarray as $inkey => $inval)
  {
    $outkey = strtolower($inkey);
    $outarray[$outkey] = array();

    foreach ($inval as $inkey2 => $inval2)
    {
      $outkey2 = strtolower($inkey2);
      $outarray[$outkey][$outkey2] = $inval2;
    } # foreach $inval
  } # foreach $inarray

  return $outarray;
} # function kses_array_lc


function kses_js_entities($string)
###############################################################################
# This function removes the HTML JavaScript entities found in early versions of
# Netscape 4.
###############################################################################
{
  return preg_replace('%&\s*\{[^}]*(\}\s*;?|$)%', '', $string);
} # function kses_js_entities


function kses_html_error($string)
###############################################################################
# This function deals with parsing errors in kses_hair(). The general plan is
# to remove everything to and including some whitespace, but it deals with
# quotes and apostrophes as well.
###############################################################################
{
  return preg_replace('/^("[^"]*("|$)|\'[^\']*(\'|$)|\S)*\s*/', '', $string);
} # function kses_html_error


function kses_bad_protocol_once($string, $allowed_protocols)
###############################################################################
# This function searches for URL protocols at the beginning of $string, while
# handling whitespace and HTML entities.
###############################################################################
{
	$string2 = preg_split('/:|&#58;|&#x3a;/i', $string, 2);
	if(isset($string2[1]) && !preg_match('%/\?%',$string2[0]))
	{
		$string = kses_bad_protocol_once2($string2[0],$allowed_protocols).trim($string2[1]);
	}
	return $string;
} # function kses_bad_protocol_once


function kses_bad_protocol_once2($string, $allowed_protocols)
###############################################################################
# This function processes URL protocols, checks to see if they're in the white-
# list or not, and returns different data depending on the answer.
###############################################################################
{
  $string2 = kses_decode_entities($string);
  $string2 = preg_replace('/\s/', '', $string2);
  $string2 = kses_no_null($string2);
  $string2 = preg_replace('/\xad+/', '', $string2);
   # deals with Opera "feature"
  $string2 = strtolower($string2);

  $allowed = false;
  foreach ($allowed_protocols as $one_protocol)
    if (strtolower($one_protocol) == $string2)
    {
      $allowed = true;
      break;
    }

  if ($allowed)
    return "$string2:";
  else
    return '';
} # function kses_bad_protocol_once2


function kses_normalize_entities($string)
###############################################################################
# This function normalizes HTML entities. It will convert "AT&T" to the correct
# "AT&amp;T", "&#00058;" to "&#58;", "&#XYZZY;" to "&amp;#XYZZY;" and so on.
###############################################################################
{
# Disarm all entities by converting & to &amp;

  $string = str_replace('&', '&amp;', $string);

# Change back the allowed entities in our entity whitelist

  $string = preg_replace('/&amp;([A-Za-z][A-Za-z0-9]{0,19});/',
                         '&\\1;', $string);
  $string = preg_replace('/&amp;#0*([0-9]{1,5});/e',
                         'kses_normalize_entities2("\\1")', $string);
  $string = preg_replace('/&amp;#([Xx])0*(([0-9A-Fa-f]{2}){1,2});/',
                         '&#\\1\\2;', $string);

  return $string;
} # function kses_normalize_entities


function kses_normalize_entities2($i)
###############################################################################
# This function helps kses_normalize_entities() to only accept 16 bit values
# and nothing more for &#number; entities.
###############################################################################
{
  return (($i > 65535) ? "&amp;#$i;" : "&#$i;");
} # function kses_normalize_entities2


function kses_decode_entities($string)
###############################################################################
# This function decodes numeric HTML entities (&#65; and &#x41;). It doesn't
# do anything with other entities like &auml;, but we don't need them in the
# URL protocol whitelisting system anyway.
###############################################################################
{
  $string = preg_replace('/&#([0-9]+);/e', 'chr("\\1")', $string);
  $string = preg_replace('/&#[Xx]([0-9A-Fa-f]+);/e', 'chr(hexdec("\\1"))',
                         $string);

  return $string;
} # function kses_decode_entities

?>