0
0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2024-09-19 10:45:18 +00:00

Implement HTML.Nofollow for external links.

Signed-off-by: Edward Z. Yang <ezyang@mit.edu>
This commit is contained in:
Edward Z. Yang 2010-09-28 12:01:57 -04:00
parent d848c99b74
commit 8c80349f9d
10 changed files with 103 additions and 6 deletions

1
NEWS
View File

@ -10,6 +10,7 @@ NEWS ( CHANGELOG and HISTORY ) HTMLPurifier
========================== ==========================
4.2.1, unknown release date 4.2.1, unknown release date
! Added %HTML.Nofollow to add rel="nofollow" to external links.
- Make removal of conditional IE comments ungreedy; thanks Bernd - Make removal of conditional IE comments ungreedy; thanks Bernd
for reporting. for reporting.

View File

@ -186,15 +186,20 @@
</directive> </directive>
<directive id="HTML.Proprietary"> <directive id="HTML.Proprietary">
<file name="HTMLPurifier/HTMLModuleManager.php"> <file name="HTMLPurifier/HTMLModuleManager.php">
<line>221</line> <line>220</line>
</file> </file>
</directive> </directive>
<directive id="HTML.SafeObject"> <directive id="HTML.SafeObject">
<file name="HTMLPurifier/HTMLModuleManager.php"> <file name="HTMLPurifier/HTMLModuleManager.php">
<line>226</line> <line>223</line>
</file> </file>
</directive> </directive>
<directive id="HTML.SafeEmbed"> <directive id="HTML.SafeEmbed">
<file name="HTMLPurifier/HTMLModuleManager.php">
<line>226</line>
</file>
</directive>
<directive id="HTML.Nofollow">
<file name="HTMLPurifier/HTMLModuleManager.php"> <file name="HTMLPurifier/HTMLModuleManager.php">
<line>229</line> <line>229</line>
</file> </file>

View File

@ -125,6 +125,7 @@ require 'HTMLPurifier/AttrTransform/Lang.php';
require 'HTMLPurifier/AttrTransform/Length.php'; require 'HTMLPurifier/AttrTransform/Length.php';
require 'HTMLPurifier/AttrTransform/Name.php'; require 'HTMLPurifier/AttrTransform/Name.php';
require 'HTMLPurifier/AttrTransform/NameSync.php'; require 'HTMLPurifier/AttrTransform/NameSync.php';
require 'HTMLPurifier/AttrTransform/Nofollow.php';
require 'HTMLPurifier/AttrTransform/SafeEmbed.php'; require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
require 'HTMLPurifier/AttrTransform/SafeObject.php'; require 'HTMLPurifier/AttrTransform/SafeObject.php';
require 'HTMLPurifier/AttrTransform/SafeParam.php'; require 'HTMLPurifier/AttrTransform/SafeParam.php';
@ -151,6 +152,7 @@ require 'HTMLPurifier/HTMLModule/Image.php';
require 'HTMLPurifier/HTMLModule/Legacy.php'; require 'HTMLPurifier/HTMLModule/Legacy.php';
require 'HTMLPurifier/HTMLModule/List.php'; require 'HTMLPurifier/HTMLModule/List.php';
require 'HTMLPurifier/HTMLModule/Name.php'; require 'HTMLPurifier/HTMLModule/Name.php';
require 'HTMLPurifier/HTMLModule/Nofollow.php';
require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php'; require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
require 'HTMLPurifier/HTMLModule/Object.php'; require 'HTMLPurifier/HTMLModule/Object.php';
require 'HTMLPurifier/HTMLModule/Presentation.php'; require 'HTMLPurifier/HTMLModule/Presentation.php';

View File

@ -119,6 +119,7 @@ require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php'; require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php'; require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/NameSync.php'; require_once $__dir . '/HTMLPurifier/AttrTransform/NameSync.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Nofollow.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php'; require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php'; require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php'; require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
@ -145,6 +146,7 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/Image.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php'; require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/List.php'; require_once $__dir . '/HTMLPurifier/HTMLModule/List.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php'; require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Nofollow.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php'; require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php'; require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php'; require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php';

View File

@ -0,0 +1,41 @@
<?php
// must be called POST validation
/**
* Adds rel="nofollow" to all outbound links. This transform is
* only attached if Attr.Nofollow is TRUE.
*/
class HTMLPurifier_AttrTransform_Nofollow extends HTMLPurifier_AttrTransform
{
private $parser;
public function __construct() {
$this->parser = new HTMLPurifier_URIParser();
}
public function transform($attr, $config, $context) {
if (!isset($attr['href'])) {
return $attr;
}
// XXX Kind of inefficient
$url = $this->parser->parse($attr['href']);
$scheme = $url->getSchemeObj($config, $context);
if (!is_null($url->host) && $scheme !== false && $scheme->browsable) {
if (isset($attr['rel'])) {
$attr['rel'] .= ' nofollow';
} else {
$attr['rel'] = 'nofollow';
}
}
return $attr;
}
}
// vim: et sw=4 sts=4

View File

@ -0,0 +1,7 @@
HTML.Nofollow
TYPE: bool
VERSION: 4.2.1
DEFAULT: FALSE
--DESCRIPTION--
If enabled, nofollow rel attributes are added to all outgoing links.
--# vim: et sw=4 sts=4

View File

@ -0,0 +1,19 @@
<?php
/**
* Module adds the nofollow attribute transformation to a tags. It
* is enabled by HTML.Nofollow
*/
class HTMLPurifier_HTMLModule_Nofollow extends HTMLPurifier_HTMLModule
{
public $name = 'Nofollow';
public function setup($config) {
$a = $this->addBlankElement('a');
$a->attr_transform_post[] = new HTMLPurifier_AttrTransform_Nofollow();
}
}
// vim: et sw=4 sts=4

View File

@ -216,19 +216,19 @@ class HTMLPurifier_HTMLModuleManager
} }
} }
// add proprietary module (this gets special treatment because // custom modules
// it is completely removed from doctypes, etc.)
if ($config->get('HTML.Proprietary')) { if ($config->get('HTML.Proprietary')) {
$modules[] = 'Proprietary'; $modules[] = 'Proprietary';
} }
// add SafeObject/Safeembed modules
if ($config->get('HTML.SafeObject')) { if ($config->get('HTML.SafeObject')) {
$modules[] = 'SafeObject'; $modules[] = 'SafeObject';
} }
if ($config->get('HTML.SafeEmbed')) { if ($config->get('HTML.SafeEmbed')) {
$modules[] = 'SafeEmbed'; $modules[] = 'SafeEmbed';
} }
if ($config->get('HTML.Nofollow')) {
$modules[] = 'Nofollow';
}
// merge in custom modules // merge in custom modules
$modules = array_merge($modules, $this->userModules); $modules = array_merge($modules, $this->userModules);

View File

@ -0,0 +1,20 @@
<?php
class HTMLPurifier_HTMLModule_NofollowTest extends HTMLPurifier_HTMLModuleHarness
{
function setUp() {
parent::setUp();
$this->config->set('HTML.Nofollow', true);
}
function testNofollow() {
$this->assertResult(
'<a href="http://google.com">a</a><a href="/local">b</a><a href="mailto:foo@example.com">c</a>',
'<a href="http://google.com" rel="nofollow">a</a><a href="/local">b</a><a href="mailto:foo@example.com">c</a>'
);
}
}
// vim: et sw=4 sts=4