mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2024-12-22 08:21:52 +00:00
0767bbc12d
This mega-patch rips out the FixNesting implementation and the related ChildDef components. The primary algorithmic change is to convert from use of tokens to tree nodes, which are far more amenable to the style of processing that FixNesting uses. Additionally, FixNesting has been changed to go bottom-up rather than top-down, in order to avoid needing to implement backtracking. This patch simplifies a good deal of the relevant logic, since we no longer need to continually recalculate the nesting structure when processing things. However, the conversion to the alternate format incurs some overhead, so for small inputs these changes are not a win. One possibility to greatly reduce the constant factors here is to switch to entirely using libxml's representation, and never serializing tokens; this would require one to rewrite injectors, however. The iterative post-order traversal in FixNesting is a bit subtle, but we have essentially reified the stack and continuations. We've removed support for %Core.EscapeInvalidChildren. Signed-off-by: Edward Z. Yang <ezyang@mit.edu>
100 lines
3.2 KiB
PHP
100 lines
3.2 KiB
PHP
<?php
|
|
|
|
class HTMLPurifier_ChildDef_CustomTest extends HTMLPurifier_ChildDefHarness
|
|
{
|
|
|
|
public function setUp()
|
|
{
|
|
parent::setUp();
|
|
}
|
|
|
|
public function test()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('(a,b?,c*,d+,(a,b)*)');
|
|
|
|
$this->assertEqual($this->obj->elements, array('a' => true,
|
|
'b' => true, 'c' => true, 'd' => true));
|
|
|
|
$this->assertResult('', false);
|
|
$this->assertResult('<a /><a />', false);
|
|
|
|
$this->assertResult('<a /><b /><c /><d /><a /><b />');
|
|
$this->assertResult('<a /><d>Dob</d><a /><b>foo</b>'.
|
|
'<a href="moo" /><b>foo</b>');
|
|
|
|
}
|
|
|
|
public function testNesting()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('(a,b,(c|d))+');
|
|
$this->assertEqual($this->obj->elements, array('a' => true,
|
|
'b' => true, 'c' => true, 'd' => true));
|
|
$this->assertResult('', false);
|
|
$this->assertResult('<a /><b /><c /><a /><b /><d />');
|
|
$this->assertResult('<a /><b /><c /><d />', false);
|
|
}
|
|
|
|
public function testNestedEitherOr()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('b,(a|(c|d))+');
|
|
$this->assertEqual($this->obj->elements, array('a' => true,
|
|
'b' => true, 'c' => true, 'd' => true));
|
|
$this->assertResult('', false);
|
|
$this->assertResult('<b /><a /><c /><d />');
|
|
$this->assertResult('<b /><d /><a /><a />');
|
|
$this->assertResult('<b /><a />');
|
|
$this->assertResult('<acd />', false);
|
|
}
|
|
|
|
public function testNestedQuantifier()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('(b,c+)*');
|
|
$this->assertEqual($this->obj->elements, array('b' => true, 'c' => true));
|
|
$this->assertResult('');
|
|
$this->assertResult('<b /><c />');
|
|
$this->assertResult('<b /><c /><c /><c />');
|
|
$this->assertResult('<b /><c /><b /><c />');
|
|
$this->assertResult('<b /><c /><b />', false);
|
|
}
|
|
|
|
public function testEitherOr()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('a|b');
|
|
$this->assertEqual($this->obj->elements, array('a' => true, 'b' => true));
|
|
$this->assertResult('', false);
|
|
$this->assertResult('<a />');
|
|
$this->assertResult('<b />');
|
|
$this->assertResult('<a /><b />', false);
|
|
|
|
}
|
|
|
|
public function testCommafication()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('a,b');
|
|
$this->assertEqual($this->obj->elements, array('a' => true, 'b' => true));
|
|
$this->assertResult('<a /><b />');
|
|
$this->assertResult('<ab />', false);
|
|
|
|
}
|
|
|
|
public function testPcdata()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('#PCDATA,a');
|
|
$this->assertEqual($this->obj->elements, array('#PCDATA' => true, 'a' => true));
|
|
$this->assertResult('foo<a />');
|
|
$this->assertResult('<a />', false);
|
|
}
|
|
|
|
public function testWhitespace()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Custom('a');
|
|
$this->assertEqual($this->obj->elements, array('a' => true));
|
|
$this->assertResult('foo<a />', false);
|
|
$this->assertResult('<a />');
|
|
$this->assertResult(' <a />');
|
|
}
|
|
|
|
}
|
|
|
|
// vim: et sw=4 sts=4
|