1
0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-07-31 19:30:21 +02:00

[2.1.3] Refine injector algorithm regarding behavior inside nodes that allow paragraphs inside them

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1423 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2007-09-27 00:39:05 +00:00
parent 094b20f58f
commit c8b020879d
4 changed files with 57 additions and 17 deletions

View File

@@ -6,20 +6,28 @@ HTMLPurifier_ConfigSchema::define(
'AutoFormat', 'AutoParagraph', false, 'bool', '
<p>
This directive turns on auto-paragraphing, where double newlines are
converted in to paragraphs whenever possible. Auto-paragraphing
applies when:
converted in to paragraphs whenever possible. Auto-paragraphing:
</p>
<ul>
<li>There are inline elements or text in the root node</li>
<li>There are inline elements or text with double newlines or
block elements in nodes that allow paragraph tags</li>
<li>There are double newlines in paragraph tags</li>
<li>Always applies to inline elements or text in the root node,</li>
<li>Applies to inline elements or text with double newlines in nodes
that allow paragraph tags,</li>
<li>Applies to double newlines in paragraph tags</li>
</ul>
<p>
<code>p</code> tags must be allowed for this directive to take effect.
We do not use <code>br</code> tags for paragraphing, as that is
semantically incorrect.
</p>
<p>
To prevent auto-paragraphing as a content-producer, refrain from using
double-newlines except to specify a new paragraph or in contexts where
it has special meaning (whitespace usually has no meaning except in
tags like <code>pre</code>, so this should not be difficult.) To prevent
the paragraphing of inline text adjacent to block elements, wrap them
in <code>div</code> tags (the behavior is slightly different outside of
the root node.)
</p>
<p>
This directive has been available since 2.0.1.
</p>
@@ -62,19 +70,27 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
$ok = false;
// test if up-coming tokens are either block or have
// a double newline in them
$nesting = 0;
for ($i = $this->inputIndex + 1; isset($this->inputTokens[$i]); $i++) {
if ($this->inputTokens[$i]->type == 'start'){
if (!$this->_isInline($this->inputTokens[$i])) {
$ok = true;
// we haven't found a double-newline, and
// we've hit a block element, so don't paragraph
$ok = false;
break;
}
break;
$nesting++;
}
if ($this->inputTokens[$i]->type == 'end') {
if ($nesting <= 0) break;
$nesting--;
}
if ($this->inputTokens[$i]->type == 'end') break;
if ($this->inputTokens[$i]->type == 'text') {
// found it!
if (strpos($this->inputTokens[$i]->data, "\n\n") !== false) {
$ok = true;
break;
}
if (!$this->inputTokens[$i]->is_whitespace) break;
}
}
if ($ok) {