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>
79 lines
2.0 KiB
PHP
79 lines
2.0 KiB
PHP
<?php
|
|
|
|
class HTMLPurifier_ChildDef_RequiredTest extends HTMLPurifier_ChildDefHarness
|
|
{
|
|
|
|
public function testPrepareString()
|
|
{
|
|
$def = new HTMLPurifier_ChildDef_Required('foobar | bang |gizmo');
|
|
$this->assertIdentical($def->elements,
|
|
array(
|
|
'foobar' => true
|
|
,'bang' => true
|
|
,'gizmo' => true
|
|
));
|
|
}
|
|
|
|
public function testPrepareArray()
|
|
{
|
|
$def = new HTMLPurifier_ChildDef_Required(array('href', 'src'));
|
|
$this->assertIdentical($def->elements,
|
|
array(
|
|
'href' => true
|
|
,'src' => true
|
|
));
|
|
}
|
|
|
|
public function setUp()
|
|
{
|
|
parent::setUp();
|
|
$this->obj = new HTMLPurifier_ChildDef_Required('dt | dd');
|
|
}
|
|
|
|
public function testEmptyInput()
|
|
{
|
|
$this->assertResult('', false);
|
|
}
|
|
|
|
public function testRemoveIllegalTagsAndElements()
|
|
{
|
|
$this->assertResult(
|
|
'<dt>Term</dt>Text in an illegal location'.
|
|
'<dd>Definition</dd><b>Illegal tag</b>',
|
|
'<dt>Term</dt><dd>Definition</dd>');
|
|
$this->assertResult('How do you do!', false);
|
|
}
|
|
|
|
public function testIgnoreWhitespace()
|
|
{
|
|
// whitespace shouldn't trigger it
|
|
$this->assertResult("\n<dd>Definition</dd> ");
|
|
}
|
|
|
|
public function testPreserveWhitespaceAfterRemoval()
|
|
{
|
|
$this->assertResult(
|
|
'<dd>Definition</dd> <b></b> ',
|
|
'<dd>Definition</dd> '
|
|
);
|
|
}
|
|
|
|
public function testDeleteNodeIfOnlyWhitespace()
|
|
{
|
|
$this->assertResult("\t ", false);
|
|
}
|
|
|
|
public function testPCDATAAllowed()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Required('#PCDATA | b');
|
|
$this->assertResult('Out <b>Bold text</b><img />', 'Out <b>Bold text</b>');
|
|
}
|
|
public function testPCDATAAllowedJump()
|
|
{
|
|
$this->obj = new HTMLPurifier_ChildDef_Required('#PCDATA | b');
|
|
$this->assertResult('A <i>foo</i>', 'A foo');
|
|
}
|
|
}
|
|
|
|
// vim: et sw=4 sts=4
|