MDL-16668 import htmlpurifier 3.1.1 to HEAD

This commit is contained in:
skodak
2008-09-24 21:32:10 +00:00
parent 165a2c9efe
commit 67d7aa437a
70 changed files with 1441 additions and 292 deletions
@@ -29,6 +29,12 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
$declarations = explode(';', $css);
$propvalues = array();
/**
* Name of the current CSS property being validated.
*/
$property = false;
$context->register('CurrentCSSProperty', $property);
foreach ($declarations as $declaration) {
if (!$declaration) continue;
if (!strpos($declaration, ':')) continue;
@@ -61,6 +67,8 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
$propvalues[$property] = $result;
}
$context->destroy('CurrentCSSProperty');
// procedure does not write the new CSS simultaneously, so it's
// slightly inefficient, but it's the only way of getting rid of
// duplicates. Perhaps config to optimize it, but not now.
@@ -16,7 +16,6 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
'cursive' => true
);
$string = $this->parseCDATA($string);
// assume that no font names contain commas in them
$fonts = explode(',', $string);
$final = '';
@@ -35,13 +34,40 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
$quote = $font[0];
if ($font[$length - 1] !== $quote) continue;
$font = substr($font, 1, $length - 2);
// double-backslash processing is buggy
$font = str_replace("\\$quote", $quote, $font); // de-escape quote
$font = str_replace("\\\n", "\n", $font); // de-escape newlines
$new_font = '';
for ($i = 0, $c = strlen($font); $i < $c; $i++) {
if ($font[$i] === '\\') {
$i++;
if ($i >= $c) {
$new_font .= '\\';
break;
}
if (ctype_xdigit($font[$i])) {
$code = $font[$i];
for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
if (!ctype_xdigit($font[$i])) break;
$code .= $font[$i];
}
// We have to be extremely careful when adding
// new characters, to make sure we're not breaking
// the encoding.
$char = HTMLPurifier_Encoder::unichr(hexdec($code));
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
$new_font .= $char;
if ($i < $c && trim($font[$i]) !== '') $i--;
continue;
}
if ($font[$i] === "\n") continue;
}
$new_font .= $font[$i];
}
$font = $new_font;
}
// $font is a pure representation of the font name
if (ctype_alnum($font)) {
if (ctype_alnum($font) && $font !== '') {
// very simple font, allow it in unharmed
$final .= $font . ', ';
continue;
@@ -50,8 +76,8 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
// complicated font, requires quoting
// armor single quotes and new lines
$font = str_replace("\\", "\\\\", $font);
$font = str_replace("'", "\\'", $font);
$font = str_replace("\n", "\\\n", $font);
$final .= "'$font', ";
}
$final = rtrim($final, ', ');
@@ -6,46 +6,40 @@
class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
{
/**
* Valid unit lookup table.
* @warning The code assumes all units are two characters long. Be careful
* if we have to change this behavior!
*/
protected $units = array('em' => true, 'ex' => true, 'px' => true, 'in' => true,
'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true);
/**
* Instance of HTMLPurifier_AttrDef_Number to defer number validation to
*/
protected $number_def;
protected $min, $max;
/**
* @param $non_negative Bool indication whether or not negative values are
* allowed.
* @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
* @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
*/
public function __construct($non_negative = false) {
$this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
public function __construct($min = null, $max = null) {
$this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
$this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
}
public function validate($length, $config, $context) {
public function validate($string, $config, $context) {
$string = $this->parseCDATA($string);
$length = $this->parseCDATA($length);
if ($length === '') return false;
if ($length === '0') return '0';
$strlen = strlen($length);
if ($strlen === 1) return false; // impossible!
// Optimizations
if ($string === '') return false;
if ($string === '0') return '0';
if (strlen($string) === 1) return false;
// we assume all units are two characters
$unit = substr($length, $strlen - 2);
if (!ctype_lower($unit)) $unit = strtolower($unit);
$number = substr($length, 0, $strlen - 2);
$length = HTMLPurifier_Length::make($string);
if (!$length->isValid()) return false;
if (!isset($this->units[$unit])) return false;
$number = $this->number_def->validate($number, $config, $context);
if ($number === false) return false;
return $number . $unit;
if ($this->min) {
$c = $length->compareTo($this->min);
if ($c === false) return false;
if ($c < 0) return false;
}
if ($this->max) {
$c = $length->compareTo($this->max);
if ($c === false) return false;
if ($c > 0) return false;
}
return $length->toString();
}
}
@@ -18,6 +18,10 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef
$this->non_negative = $non_negative;
}
/**
* @warning Some contexts do not pass $config, $context. These
* variables should not be used without checking HTMLPurifier_Length
*/
public function validate($number, $config, $context) {
$number = $this->parseCDATA($number);
@@ -13,10 +13,13 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef
static $allowed_values = array(
'line-through' => true,
'overline' => true,
'underline' => true
'underline' => true,
);
$string = strtolower($this->parseCDATA($string));
if ($string === 'none') return $string;
$parts = explode(' ', $string);
$final = '';
foreach ($parts as $part) {
@@ -6,6 +6,12 @@
class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
{
protected $max;
public function __construct($max = null) {
$this->max = $max;
}
public function validate($string, $config, $context) {
$string = trim($string);
@@ -24,11 +30,18 @@ class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
// crash operating systems, see <http://ha.ckers.org/imagecrash.html>
// WARNING, above link WILL crash you if you're using Windows
if ($int > 1200) return '1200';
if ($this->max !== null && $int > $this->max) return (string) $this->max;
return (string) $int;
}
public function make($string) {
if ($string === '') $max = null;
else $max = (int) $string;
$class = get_class($this);
return new $class($max);
}
}
@@ -0,0 +1,32 @@
<?php
/**
* Decorator that, depending on a token, switches between two definitions.
*/
class HTMLPurifier_AttrDef_Switch
{
protected $tag;
protected $withTag, $withoutTag;
/**
* @param string $tag Tag name to switch upon
* @param HTMLPurifier_AttrDef $with_tag Call if token matches tag
* @param HTMLPurifier_AttrDef $without_tag Call if token doesn't match, or there is no token
*/
public function __construct($tag, $with_tag, $without_tag) {
$this->tag = $tag;
$this->withTag = $with_tag;
$this->withoutTag = $without_tag;
}
public function validate($string, $config, $context) {
$token = $context->get('CurrentToken', true);
if (!$token || $token->name !== $this->tag) {
return $this->withoutTag->validate($string, $config, $context);
} else {
return $this->withTag->validate($string, $config, $context);
}
}
}
+10 -12
View File
@@ -18,6 +18,11 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
$this->embedsResource = (bool) $embeds_resource;
}
public function make($string) {
$embeds = (bool) $string;
return new HTMLPurifier_AttrDef_URI($embeds);
}
public function validate($uri, $config, $context) {
if ($config->get('URI', 'Disable')) return false;
@@ -50,6 +55,10 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
$result = $scheme_obj->validate($uri, $config, $context);
if (!$result) break;
// Post chained filtering
$result = $uri_def->postFilter($uri, $config, $context);
if (!$result) break;
// survived gauntlet
$ok = true;
@@ -59,18 +68,7 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef
if (!$ok) return false;
// back to string
$result = $uri->toString();
// munge entire URI if necessary
if (
!is_null($uri->host) && // indicator for authority
!empty($scheme_obj->browsable) &&
!is_null($munge = $config->get('URI', 'Munge'))
) {
$result = str_replace('%s', rawurlencode($result), $munge);
}
return $result;
return $uri->toString();
}