maketank/Froxlor
2
0
Fork 0
Code Pull Requests Releases Activity

Update HTMLPurifier to current stable version 4.5.0

Browse Source
This commit is contained in:
Michael Kaufmann (d00p)
2013-09-21 12:18:55 +02:00
parent fc8bd2b7af
commit 2dfdd6a5f9
87 changed files with 2057 additions and 342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Background.php
View File

@@ -32,7 +32,7 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
$string = $this->mungeRgb($string);
// assumes URI doesn't have spaces in it
$bits = explode(' ', strtolower($string)); // bits to process
$bits = explode(' ', $string); // bits to process
$caught = array();
$caught['color'] = false;

149
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/FontFamily.php
View File

@@ -2,11 +2,43 @@
/**
* Validates a font family list according to CSS spec
* @todo whitelisting allowed fonts would be nice
*/
class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
{
protected $mask = null;
public function __construct() {
$this->mask = '_- ';
for ($c = 'a'; $c <= 'z'; $c++) $this->mask .= $c;
for ($c = 'A'; $c <= 'Z'; $c++) $this->mask .= $c;
for ($c = '0'; $c <= '9'; $c++) $this->mask .= $c; // cast-y, but should be fine
// special bytes used by UTF-8
for ($i = 0x80; $i <= 0xFF; $i++) {
// We don't bother excluding invalid bytes in this range,
// because the our restriction of well-formed UTF-8 will
// prevent these from ever occurring.
$this->mask .= chr($i);
}
/*
PHP's internal strcspn implementation is
O(length of string * length of mask), making it inefficient
for large masks. However, it's still faster than
preg_match 8)
for (p = s1;;) {
spanp = s2;
do {
if (*spanp == c || p == s1_end) {
return p - s1;
}
} while (spanp++ < (s2_end - 1));
c = *++p;
}
*/
// possible optimization: invert the mask.
}
public function validate($string, $config, $context) {
static $generic_names = array(
'serif' => true,
@@ -15,6 +47,7 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
'fantasy' => true,
'cursive' => true
);
$allowed_fonts = $config->get('CSS.AllowedFonts');
// assume that no font names contain commas in them
$fonts = explode(',', $string);
@@ -24,7 +57,9 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
if ($font === '') continue;
// match a generic name
if (isset($generic_names[$font])) {
$final .= $font . ', ';
if ($allowed_fonts === null || isset($allowed_fonts[$font])) {
$final .= $font . ', ';
}
continue;
}
// match a quoted name
@@ -40,6 +75,10 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
// $font is a pure representation of the font name
if ($allowed_fonts !== null && !isset($allowed_fonts[$font])) {
continue;
}
if (ctype_alnum($font) && $font !== '') {
// very simple font, allow it in unharmed
$final .= $font . ', ';
@@ -50,17 +89,103 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
// shouldn't show up regardless
$font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
// These ugly transforms don't pose a security
// risk (as \\ and \" might). We could try to be clever and
// use single-quote wrapping when there is a double quote
// present, but I have choosen not to implement that.
// (warning: this code relies on the selection of quotation
// mark below)
$font = str_replace('\\', '\\5C ', $font);
$font = str_replace('"', '\\22 ', $font);
// Here, there are various classes of characters which need
// to be treated differently:
// - Alphanumeric characters are essentially safe. We
// handled these above.
// - Spaces require quoting, though most parsers will do
// the right thing if there aren't any characters that
// can be misinterpreted
// - Dashes rarely occur, but they fairly unproblematic
// for parsing/rendering purposes.
// The above characters cover the majority of Western font
// names.
// - Arbitrary Unicode characters not in ASCII. Because
// most parsers give little thought to Unicode, treatment
// of these codepoints is basically uniform, even for
// punctuation-like codepoints. These characters can
// show up in non-Western pages and are supported by most
// major browsers, for example: "ＭＳ 明朝" is a
// legitimate font-name
// <http://ja.wikipedia.org/wiki/MS_明朝>. See
// the CSS3 spec for more examples:
// <http://www.w3.org/TR/2011/WD-css3-fonts-20110324/localizedfamilynames.png>
// You can see live samples of these on the Internet:
// <http://www.google.co.jp/search?q=font-family+ＭＳ+明朝|ゴシック>
// However, most of these fonts have ASCII equivalents:
// for example, 'MS Mincho', and it's considered
// professional to use ASCII font names instead of
// Unicode font names. Thanks Takeshi Terada for
// providing this information.
// The following characters, to my knowledge, have not been
// used to name font names.
// - Single quote. While theoretically you might find a
// font name that has a single quote in its name (serving
// as an apostrophe, e.g. Dave's Scribble), I haven't
// been able to find any actual examples of this.
// Internet Explorer's cssText translation (which I
// believe is invoked by innerHTML) normalizes any
// quoting to single quotes, and fails to escape single
// quotes. (Note that this is not IE's behavior for all
// CSS properties, just some sort of special casing for
// font-family). So a single quote *cannot* be used
// safely in the font-family context if there will be an
// innerHTML/cssText translation. Note that Firefox 3.x
// does this too.
// - Double quote. In IE, these get normalized to
// single-quotes, no matter what the encoding. (Fun
// fact, in IE8, the 'content' CSS property gained
// support, where they special cased to preserve encoded
// double quotes, but still translate unadorned double
// quotes into single quotes.) So, because their
// fixpoint behavior is identical to single quotes, they
// cannot be allowed either. Firefox 3.x displays
// single-quote style behavior.
// - Backslashes are reduced by one (so \\ -> \) every
// iteration, so they cannot be used safely. This shows
// up in IE7, IE8 and FF3
// - Semicolons, commas and backticks are handled properly.
// - The rest of the ASCII punctuation is handled properly.
// We haven't checked what browsers do to unadorned
// versions, but this is not important as long as the
// browser doesn't /remove/ surrounding quotes (as IE does
// for HTML).
//
// With these results in hand, we conclude that there are
// various levels of safety:
// - Paranoid: alphanumeric, spaces and dashes(?)
// - International: Paranoid + non-ASCII Unicode
// - Edgy: Everything except quotes, backslashes
// - NoJS: Standards compliance, e.g. sod IE. Note that
// with some judicious character escaping (since certain
// types of escaping doesn't work) this is theoretically
// OK as long as innerHTML/cssText is not called.
// We believe that international is a reasonable default
// (that we will implement now), and once we do more
// extensive research, we may feel comfortable with dropping
// it down to edgy.
// complicated font, requires quoting
$final .= "\"$font\", "; // note that this will later get turned into &quot;
// Edgy: alphanumeric, spaces, dashes, underscores and Unicode. Use of
// str(c)spn assumes that the string was already well formed
// Unicode (which of course it is).
if (strspn($font, $this->mask) !== strlen($font)) {
continue;
}
// Historical:
// In the absence of innerHTML/cssText, these ugly
// transforms don't pose a security risk (as \\ and \"
// might--these escapes are not supported by most browsers).
// We could try to be clever and use single-quote wrapping
// when there is a double quote present, but I have choosen
// not to implement that. (NOTE: you can reduce the amount
// of escapes by one depending on what quoting style you use)
// $font = str_replace('\\', '\\5C ', $font);
// $font = str_replace('"', '\\22 ', $font);
// $font = str_replace("'", '\\27 ', $font);
// font possibly with spaces, requires quoting
$final .= "'$font', ";
}
$final = rtrim($final, ', ');
if ($final === '') return false;

24
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Ident.php Normal file
View File

@@ -0,0 +1,24 @@
<?php
/**
* Validates based on {ident} CSS grammar production
*/
class HTMLPurifier_AttrDef_CSS_Ident extends HTMLPurifier_AttrDef
{
public function validate($string, $config, $context) {
$string = trim($string);
// early abort: '' and '0' (strings that convert to false) are invalid
if (!$string) return false;
$pattern = '/^(-?[A-Za-z_][A-Za-z_\-0-9]*)$/';
if (!preg_match($pattern, $string)) return false;
return $string;
}
}
// vim: et sw=4 sts=4

9
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/URI.php
View File

@@ -43,6 +43,15 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
// extra sanity check; should have been done by URI
$result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result);
// suspicious characters are ()'; we're going to percent encode
// them for safety.
$result = str_replace(array('(', ')', "'"), array('%28', '%29', '%27'), $result);
// there's an extra bug where ampersands lose their escaping on
// an innerHTML cycle, so a very unlucky query parameter could
// then change the meaning of the URL. Unfortunately, there's
// not much we can do about that...
return "url(\"$result\")";
}

28
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/Clone.php Normal file
View File

@@ -0,0 +1,28 @@
<?php
/**
* Dummy AttrDef that mimics another AttrDef, BUT it generates clones
* with make.
*/
class HTMLPurifier_AttrDef_Clone extends HTMLPurifier_AttrDef
{
/**
* What we're cloning
*/
protected $clone;
public function __construct($clone) {
$this->clone = $clone;
}
public function validate($v, $config, $context) {
return $this->clone->validate($v, $config, $context);
}
public function make($string) {
return clone $this->clone;
}
}
// vim: et sw=4 sts=4

3
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/HTML/Color.php
View File

@@ -14,7 +14,8 @@ class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
$string = trim($string);
if (empty($string)) return false;
if (isset($colors[$string])) return $colors[$string];
$lower = strtolower($string);
if (isset($colors[$lower])) return $colors[$lower];
if ($string[0] === '#') $hex = substr($string, 1);
else $hex = $string;

22
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/HTML/ID.php
View File

@@ -12,12 +12,22 @@
class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
{
// ref functionality disabled, since we also have to verify
// whether or not the ID it refers to exists
// selector is NOT a valid thing to use for IDREFs, because IDREFs
// *must* target IDs that exist, whereas selector #ids do not.
/**
* Determines whether or not we're validating an ID in a CSS
* selector context.
*/
protected $selector;
public function __construct($selector = false) {
$this->selector = $selector;
}
public function validate($id, $config, $context) {
if (!$config->get('Attr.EnableID')) return false;
if (!$this->selector && !$config->get('Attr.EnableID')) return false;
$id = trim($id); // trim it first
@@ -33,10 +43,10 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
'%Attr.IDPrefix is set', E_USER_WARNING);
}
//if (!$this->ref) {
if (!$this->selector) {
$id_accumulator =& $context->get('IDAccumulator');
if (isset($id_accumulator->ids[$id])) return false;
//}
}
// we purposely avoid using regex, hopefully this is faster
@@ -56,7 +66,7 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
return false;
}
if (/*!$this->ref && */$result) $id_accumulator->add($id);
if (!$this->selector && $result) $id_accumulator->add($id);
// if no change was made to the ID, return the result
// else, return the new id if stripping whitespace made it

2
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/URI.php
View File

@@ -19,7 +19,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
}
public function make($string) {
$embeds = (bool) $string;
$embeds = ($string === 'embedded');
return new HTMLPurifier_AttrDef_URI($embeds);
}

51
lib/classes/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.php
View File

@@ -23,6 +23,12 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
public function validate($string, $config, $context) {
$length = strlen($string);
// empty hostname is OK; it's usually semantically equivalent:
// the default host as defined by a URI scheme is used:
//
// If the URI scheme defines a default for host, then that
// default applies when the host subcomponent is undefined
// or when the registered name is empty (zero length).
if ($string === '') return '';
if ($length > 1 && $string[0] === '[' && $string[$length-1] === ']') {
//IPv6
@@ -38,9 +44,8 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
// A regular domain name.
// This breaks I18N domain names, but we don't have proper IRI support,
// so force users to insert Punycode. If there's complaining we'll
// try to fix things into an international friendly form.
// This doesn't match I18N domain names, but we don't have proper IRI support,
// so force users to insert Punycode.
// The productions describing this are:
$a = '[a-z]'; // alpha
@@ -51,10 +56,44 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
// toplabel = alpha | alpha *( alphanum | "-" ) alphanum
$toplabel = "$a($and*$an)?";
// hostname = *( domainlabel "." ) toplabel [ "." ]
$match = preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string);
if (!$match) return false;
if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) {
return $string;
}
return $string;
// If we have Net_IDNA2 support, we can support IRIs by
// punycoding them. (This is the most portable thing to do,
// since otherwise we have to assume browsers support
if ($config->get('Core.EnableIDNA')) {
$idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true));
// we need to encode each period separately
$parts = explode('.', $string);
try {
$new_parts = array();
foreach ($parts as $part) {
$encodable = false;
for ($i = 0, $c = strlen($part); $i < $c; $i++) {
if (ord($part[$i]) > 0x7a) {
$encodable = true;
break;
}
}
if (!$encodable) {
$new_parts[] = $part;
} else {
$new_parts[] = $idna->encode($part);
}
}
$string = implode('.', $new_parts);
if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) {
return $string;
}
} catch (Exception $e) {
// XXX error reporting
}
}
return false;
}
}