diff --git a/phpgwapi/inc/class.kses.inc.php b/phpgwapi/inc/class.kses.inc.php
deleted file mode 100644
index 7b478b283b..0000000000
--- a/phpgwapi/inc/class.kses.inc.php
+++ /dev/null
@@ -1,698 +0,0 @@
-_no_null($string);
- $string = $this->_js_entities($string);
- $string = $this->_normalize_entities($string);
- $string = $this->_hook($string);
- return $this->_split($string);
- }
-
- function Protocols()
- {
- $c_args = func_num_args();
- if($c_args != 1)
- {
- return false;
- }
-
- $protocol_data = func_get_arg(0);
-
- if(is_array($protocol_data))
- {
- foreach($protocol_data as $protocol)
- {
- $this->AddProtocol($protocol);
- }
- }
- elseif(is_string($protocol_data))
- {
- $this->AddProtocol($protocol_data);
- return true;
- }
- else
- {
- trigger_error("kses::Protocols() did not receive a string or an array.", E_USER_WARNING);
- return false;
- }
- }
-
- function AddProtocol($protocol = "")
- {
- if(!is_string($protocol))
- {
- trigger_error("kses::AddProtocol() requires a string.", E_USER_WARNING);
- return false;
- }
-
- $protocol = strtolower(trim($protocol));
- if($protocol == "")
- {
- trigger_error("kses::AddProtocol() tried to add an empty/NULL protocol.", E_USER_WARNING);
- return false;
- }
-
- // Remove any inadvertent ':' at the end of the protocol.
- if(substr($protocol, strlen($protocol) - 1, 1) == ":")
- {
- $protocol = substr($protocol, 0, strlen($protocol) - 1);
- }
-
- if(!in_array($protocol, $this->allowed_protocols))
- {
- array_push($this->allowed_protocols, $protocol);
- sort($this->allowed_protocols);
- }
- return true;
- }
-
- function AddHTML($tag = "", $attribs = array())
- {
- if(!is_string($tag))
- {
- trigger_error("kses::AddHTML() requires the tag to be a string", E_USER_WARNING);
- return false;
- }
-
- $tag = strtolower(trim($tag));
- if($tag == "")
- {
- trigger_error("kses::AddHTML() tried to add an empty/NULL tag", E_USER_WARNING);
- return false;
- }
-
- if(!is_array($attribs))
- {
- trigger_error("kses::AddHTML() requires an array (even an empty one) of attributes for '$tag'", E_USER_WARNING);
- return false;
- }
-
- $new_attribs = array();
- foreach($attribs as $idx1 => $val1)
- {
- $new_idx1 = strtolower($idx1);
- $new_val1 = $attribs[$idx1];
-
- if(is_array($new_val1))
- {
- $tmp_val = array();
- foreach($new_val1 as $idx2 => $val2)
- {
- $new_idx2 = strtolower($idx2);
- $tmp_val[$new_idx2] = $val2;
- }
- $new_val1 = $tmp_val;
- }
-
- $new_attribs[$new_idx1] = $new_val1;
- }
-
- $this->allowed_html[$tag] = $new_attribs;
- return true;
- }
-
- ###############################################################################
- # This function removes any NULL or chr(173) characters in $string.
- ###############################################################################
- function _no_null($string)
- {
- $string = preg_replace('/\0+/', '', $string);
- $string = preg_replace('/(\\\\0)+/', '', $string);
- # commented out, because it breaks chinese chars
- #$string = preg_replace('/\xad+/', '', $string); # deals with Opera "feature"
- return $string;
- } # function _no_null
-
- ###############################################################################
- # This function removes the HTML JavaScript entities found in early versions of
- # Netscape 4.
- ###############################################################################
- function _js_entities($string)
- {
- return preg_replace('%&\s*\{[^}]*(\}\s*;?|$)%', '', $string);
- } # function _js_entities
-
-
- ###############################################################################
- # This function normalizes HTML entities. It will convert "AT&T" to the correct
- # "AT&T", ":" to ":", "&#XYZZY;" to "&#XYZZY;" and so on.
- ###############################################################################
- function _normalize_entities($string)
- {
- # Disarm all entities by converting & to &
- $string = str_replace('&', '&', $string);
-
- # Change back the allowed entities in our entity white list
-
- $string = preg_replace('/&([A-Za-z][A-Za-z0-9]{0,19});/', '&\\1;', $string);
- $string = preg_replace('/�*([0-9]{1,5});/e', '\$this->_normalize_entities2("\\1")', $string);
- $string = preg_replace('/&#([Xx])0*(([0-9A-Fa-f]{2}){1,2});/', '&#\\1\\2;', $string);
-
- return $string;
- } # function _normalize_entities
-
-
- ###############################################################################
- # This function helps _normalize_entities() to only accept 16 bit values
- # and nothing more for &#number; entities.
- ###############################################################################
- function _normalize_entities2($i)
- {
- return (($i > 65535) ? "&#$i;" : "&#$i;");
- } # function _normalize_entities2
-
- ###############################################################################
- # You add any kses hooks here.
- ###############################################################################
- function _hook($string)
- {
- return $string;
- } # function _hook
-
- ###############################################################################
- # This function goes through an array, and changes the keys to all lower case.
- ###############################################################################
- function _array_lc($inarray)
- {
- $outarray = array();
-
- foreach ($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 $outarray;
- } # function _array_lc
-
- ###############################################################################
- # This function searches for HTML tags, no matter how malformed. It also
- # matches stray ">" characters.
- ###############################################################################
- function _split($string)
- {
- return preg_replace(
- '%(<'. # EITHER: <
- '[^>]*'. # things that aren't >
- '(>|$)'. # > or end of string
- '|>)%e', # OR: just a >
- "\$this->_split2('\\1')",
- $string);
- } # function _split
-
- function _split2($string)
- ###############################################################################
- # 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 = $this->_stripslashes($string);
-
- if (substr($string, 0, 1) != '<')
- {
- # It matched a ">" character
- return '>';
- }
-
- if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches))
- {
- # It's seriously malformed
- return '';
- }
-
- $slash = trim($matches[1]);
- $elem = $matches[2];
- $attrlist = $matches[3];
-
- if (!is_array($this->allowed_html[strtolower($elem)]))
- {
- # They are using a not allowed HTML element
- return '';
- }
-
- return $this->_attr("$slash$elem", $attrlist);
- } # function _split2
-
- ###############################################################################
- # This function removes all attributes, if none are allowed for this element.
- # If some are allowed it calls s_hair() to split them further, and then it
- # builds up new HTML code from the data that _hair() returns. It also
- # removes "<" and ">" characters, if there are any left. One more thing it
- # does is to check if the tag has a closing XHTML slash, and if it does,
- # it puts one in the returned code as well.
- ###############################################################################
- function _attr($element, $attr)
- {
- # Is there a closing XHTML slash at the end of the attributes?
- $xhtml_slash = '';
- if (preg_match('%\s/\s*$%', $attr))
- {
- $xhtml_slash = ' /';
- }
-
- # Are any attributes allowed at all for this element?
- if (count($this->allowed_html[strtolower($element)]) == 0)
- {
- return "<$element$xhtml_slash>";
- }
-
- # Split it
- //_debug_array($attr);
- $attrarr = $this->_hair($attr);
-
- # Go through $attrarr, and save the allowed attributes for this element
- # in $attr2
- $attr2 = '';
- foreach ($attrarr as $arreach)
- {
- $current = $this->allowed_html[strtolower($element)][strtolower($arreach['name'])];
-
- if ($current == '')
- {
- # the attribute is not allowed
- continue;
- }
-
- if (!is_array($current))
- {
- # there are no checks
- $attr2 .= ' '.$arreach['whole'];
- }
- else
- {
- # there are some checks
- $ok = true;
- foreach ($current as $currkey => $currval)
- {
- if (!$this->_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval))
- {
- $ok = false;
- break;
- }
- }
-
- if ($ok)
- {
- # it passed them
- $attr2 .= ' '.$arreach['whole'];
- }
- } # if !is_array($current)
- } # foreach
-
- # Remove any "<" or ">" characters
- $attr2 = preg_replace('/[<>]/', '', $attr2);
- return "<$element$attr2$xhtml_slash>";
- } # function _attr
-
- ###############################################################################
- # 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.
- ###############################################################################
- function _hair($attr)
- {
- //echo __METHOD__.'called ';
- $attrarr = array();
- $mode = 0;
- $attrname = '';
-
- # Loop through the whole attribute list
-
- while (strlen($attr) != 0)
- {
- # Was the last operation successful?
- $working = 0;
-
- switch ($mode)
- {
- case 0: # attribute name, href for instance
- if (preg_match('/^([-a-zA-Z]+)/', $attr, $match))
- {
- //echo 'mode 0:'.$match[0].' ';
- $attrname = $match[1];
- //echo 'mode 0 -> attrname:'.$attrname.' ';
- $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*/', '', $attr);
- //echo 'mode 1:'.$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+/', '', $attr);
- }
- break;
- case 2: # attribute value, a URL after href= for instance
- //echo 'mode 2 Attrname:'.$attrname.' ';
- if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) # "value"
- {
- $thisval = ($attrname == 'name' ? $match[1] : $this->_bad_protocol($match[1]));
- $attrarr[] = array(
- 'name' => $attrname,
- 'value' => $thisval,
- 'whole' => "$attrname=\"$thisval\"",
- 'vless' => 'n'
- );
- $working = 1;
- $mode = 0;
- $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr);
- //echo 'mode 2:'.$attr.' ';
- break;
- }
- if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) # 'value'
- {
- $thisval = ($attrname == 'name' ? $match[1] : $this->_bad_protocol($match[1]));
- $attrarr[] = array(
- 'name' => $attrname,
- 'value' => $thisval,
- 'whole' => "$attrname='$thisval'",
- 'vless' => 'n'
- );
- $working = 1;
- $mode = 0;
- $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr);
- //echo 'mode 2:'.$attr.' ';
- break;
- }
- if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) # value
- {
- $thisval = ($attrname == 'name' ? $match[1] : $this->_bad_protocol($match[1]));
- $attrarr[] = array(
- 'name' => $attrname,
- '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 = $this->_html_error($attr);
- $mode = 0;
- }
- } # while
-
- # special case, for when the attribute list ends with a valueless
- # attribute like "selected"
- if ($mode == 1)
- {
- $attrarr[] = array(
- 'name' => $attrname,
- 'value' => '',
- 'whole' => $attrname,
- 'vless' => 'y'
- );
- }
-
- return $attrarr;
- } # function _hair
-
- ###############################################################################
- # This function removes all non-allowed protocols from the beginning of
- # $string. It ignores whitespace and the case of the letters, and it does
- # understand HTML entities. It does its work in a while loop, so it won't be
- # fooled by a string like "javascript:javascript:alert(57)".
- ###############################################################################
- function _bad_protocol($string)
- {
- $string = $this->_no_null($string);
- $string2 = $string.'a';
-
- while ($string != $string2)
- {
- $string2 = $string;
- $string = $this->_bad_protocol_once($string);
- } # while
-
- return $string;
- } # function _bad_protocol
-
- ###############################################################################
- # This function searches for URL protocols at the beginning of $string, while
- # handling whitespace and HTML entities.
- ###############################################################################
- function _bad_protocol_once($string)
- {
- if ($string[0]=='#') return $string; // its an anchor, dont check for protocol any further
- $string2 = preg_split('/:|:|:/i', $string, 2);
- if(isset($string2[1]) && !preg_match('%/\?%',$string2[0]))
- {
- return $this->_bad_protocol_once2($string2[0]).trim($string2[1]);
- } else {
- if (!isset($string2[1]))
- {
- return $string2[0];
- } else {
- return '';
- }
- }
- return '';
- } # function _bad_protocol_once
-
-
- ###############################################################################
- # This function processes URL protocols, checks to see if they're in the white-
- # list or not, and returns different data depending on the answer.
- ###############################################################################
- function _bad_protocol_once2($string)
- {
- $string2 = $this->_decode_entities($string);
- $string2 = preg_replace('/\s/', '', $string2);
- $string2 = $this->_no_null($string2);
- $string2 = preg_replace('/\xad+/', '', $string2); # deals with Opera "feature"
- $string2 = strtolower($string2);
-
- $allowed = false;
- if(is_array($this->allowed_protocols) && count($this->allowed_protocols) > 0)
- {
- foreach ($this->allowed_protocols as $one_protocol)
- {
- if (strtolower($one_protocol) == $string2)
- {
- $allowed = true;
- break;
- }
- }
- }
- if ($allowed)
- {
- return "$string2:";
- }
- else
- {
- return '';
- }
- } # function _bad_protocol_once2
-
- ###############################################################################
- # This function performs different checks for attribute values. The currently
- # implemented checks are "maxlen", "minlen", "maxval", "minval" and "valueless"
- # with even more checks to come soon.
- ###############################################################################
- function _check_attr_val($value, $vless, $checkname, $checkvalue)
- {
- $ok = true;
-
- switch (strtolower($checkname))
- {
- # 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.
- case 'maxlen':
- if (strlen($value) > $checkvalue)
- {
- $ok = false;
- }
- break;
-
- # The minlen check makes sure that the attribute value has a length not
- # smaller than the given value.
- case 'minlen':
- if (strlen($value) < $checkvalue)
- {
- $ok = false;
- }
- break;
-
- # The maxval check does two things: it checks that the attribute value is
- # an integer from 0 and up, without an excessive amount of zeroes or
- # whitespace (to avoid Buffer Overflows). It also checks that the attribute
- # value is not greater than the given value.
- # This check can be used to avoid Denial of Service attacks.
- case 'maxval':
- if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value))
- {
- $ok = false;
- }
- if ($value > $checkvalue)
- {
- $ok = false;
- }
- break;
-
- # The minval check checks that the attribute value is a positive integer,
- # and that it is not smaller than the given value.
- case 'minval':
- if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value))
- {
- $ok = false;
- }
- if ($value < $checkvalue)
- {
- $ok = false;
- }
- break;
-
- # The valueless check checks if the attribute has a value
- # (like ) or not (
tag from truncating output, if a second
- is present.
-. Created script maintenance/rename-config.php for renaming a configuration
- directive while maintaining its alias. This script does not change source code.
-. Implement namespace locking for definition construction, to prevent
- bugs where a directive is used for definition construction but is not
- used to construct the cache hash.
-
-3.3.0, released 2009-02-16
-! Implement CSS property 'overflow' when %CSS.AllowTricky is true.
-! Implement generic property list classess
-- Fix bug with testEncodingSupportsASCII() algorithm when iconv() implementation
- does not do the "right thing" with characters not supported in the output
- set.
-- Spellcheck UTF-8: The Secret To Character Encoding
-- Fix improper removal of the contents of elements with only whitespace. Thanks
- Eric Wald for reporting.
-- Fix broken test suite in versions of PHP without spl_autoload_register()
-- Fix degenerate case with YouTube filter involving double hyphens.
- Thanks Pierre Attar for reporting.
-- Fix YouTube rendering problem on certain versions of Firefox.
-- Fix CSSDefinition Printer problems with decorators
-- Add text parameter to unit tests, forces text output
-. Add verbose mode to command line test runner, use (--verbose)
-. Turn on unit tests for UnitConverter
-. Fix missing version number in configuration %Attr.DefaultImageAlt (added 3.2.0)
-. Fix newline errors that caused spurious failures when CRLF HTML Purifier was
- tested on Linux.
-. Removed trailing whitespace from all text files, see
- remote-trailing-whitespace.php maintenance script.
-. Convert configuration to use property list backend.
-
-3.2.0, released 2008-10-31
-# Using %Core.CollectErrors forces line number/column tracking on, whereas
- previously you could theoretically turn it off.
-# HTMLPurifier_Injector->notifyEnd() is formally deprecated. Please
- use handleEnd() instead.
-! %Output.AttrSort for when you need your attributes in alphabetical order to
- deal with a bug in FCKEditor. Requested by frank farmer.
-! Enable HTML comments when %HTML.Trusted is on. Requested by Waldo Jaquith.
-! Proper support for name attribute. It is now allowed and equivalent to the id
- attribute in a and img tags, and is only converted to id when %HTML.TidyLevel
- is heavy (for all doctypes).
-! %AutoFormat.RemoveEmpty to remove some empty tags from documents. Please don't
- use on hand-written HTML.
-! Add error-cases for unsupported elements in MakeWellFormed. This enables
- the strategy to be used, standalone, on untrusted input.
-! %Core.AggressivelyFixLt is on by default. This causes more sensible
- processing of left angled brackets in smileys and other whatnot.
-! Test scripts now have a 'type' parameter, which lets you say 'htmlpurifier',
- 'phpt', 'vtest', etc. in order to only execute those tests. This supercedes
- the --only-phpt parameter, although for backwards-compatibility the flag
- will still work.
-! AutoParagraph auto-formatter will now preserve double-newlines upon output.
- Users who are not performing inbound filtering, this may seem a little
- useless, but as a bonus, the test suite and handling of edge cases is also
- improved.
-! Experimental implementation of forms for %HTML.Trusted
-! Track column numbers when maintain line numbers is on
-! Proprietary 'background' attribute on table-related elements converted into
- corresponding CSS. Thanks Fusemail for sponsoring this feature!
-! Add forward(), forwardUntilEndToken(), backward() and current() to Injector
- supertype.
-! HTMLPurifier_Injector->handleEnd() permits modification to end tokens. The
- time of operation varies slightly from notifyEnd() as *all* end tokens are
- processed by the injector before they are subject to the well-formedness rules.
-! %Attr.DefaultImageAlt allows overriding default behavior of setting alt to
- basename of image when not present.
-! %AutoFormat.DisplayLinkURI neuters