kses.php

完美的在线教育系统

<?php

# kses 0.2.2 - HTML/XHTML filter that only allows some elements and attributes
# Copyright (C) 2002, 2003, 2005  Ulf Harnhammar
#
# This program is free software and open source software; you can redistribute
# it and/or modify it under the terms of the GNU General Public License as
# published by the Free Software Foundation; either version 2 of the License,
# or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
# more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA  or visit
# http://www.gnu.org/licenses/gpl.html
#
# *** CONTACT INFORMATION ***
#
# E-mail:      metaur at users dot sourceforge dot net
# Web page:    http://sourceforge.net/projects/kses
# Paper mail:  Ulf Harnhammar
#              Ymergatan 17 C
#              753 25  Uppsala
#              SWEDEN
#
# [kses strips evil scripts!]


function 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.
###############################################################################
{
  $string = kses_no_null($string);
  $string = kses_js_entities($string);
  $string = kses_normalize_entities($string);
  $string = kses_hook($string);
  $allowed_html_fixed = kses_array_lc($allowed_html);
  return kses_split($string, $allowed_html_fixed, $allowed_protocols);
} # function kses


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


function kses_version()
###############################################################################
# This function returns kses' version number.
###############################################################################
{
  return '0.2.2';
} # function kses_version


function 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 >
                      "kses_split2('\\1', \$allowed_html, ".
                      '$allowed_protocols)',
                      $string);
} # function kses_split


function 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.
###############################################################################
{
  $string = kses_stripslashes($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 (!@isset($allowed_html[strtolower($elem)]))
    return '';
    # They are using a not allowed HTML element

  if ($slash != '')
    return "<$slash$elem>";
  # No attributes are allowed for closing elements

  return kses_attr("$slash$elem", $attrlist, $allowed_html,
                   $allowed_protocols);
} # function kses_split2


function 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 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

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

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

  $attr2 = '';

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

    $current = $allowed_html[strtolower($element)]
                            [strtolower($arreach['name'])];

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

    else
    {
    # there are some checks
      $ok = true;
      foreach ($current as $currkey => $currval)
        if (!kses_check_attr_val($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 kses_attr


function 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"
        {
          $thisval = kses_bad_protocol($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'
        {
          $thisval = kses_bad_protocol($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
        {
          $thisval = kses_bad_protocol($match[1], $allowed_protocols);

          $attrarr[] = array
                        ('name'  => $attrname,