mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-03 20:58:11 +02:00
Code Issues Releases Wiki Activity

Implement Injector->handleEnd, with lots of refactoring for injector.

Browse Source 
Previous design of injector streaming involved editability only to start, empty
and text tokens, because they could be safely modified without causing formedness
errors.  By modifying notifyEnd to operate before MakeWellFormed's safeguards
kick into effect, it can be converted into a handle function, allowing for
arbitrary modification of end tags.

This change involved quite a bit of restructuring of the MakeWellFormed code,
including the moving of end of document tags to inside the loop, so rewinding
on those tags would be functional, increased reuse of the end tag codepath by
code that inserts end tags (as they could be changed out from under you), and
processToken modified to have an extra parameter to force re-processing of
a token if the original token was an end token.

We're not exactly sure if handleEnd works at this point, but the important
talking point about this refactoring is that nothing else broke. Also, a number
of convenience functions were moved from AutoParagraph to the Injector
supertype (specifically: forward, forwardToEndToken, backward, and current).

Signed-off-by: Edward Z. Yang <edwardzyang@thewritingpot.com>
This commit is contained in:
Edward Z. Yang
2008-10-01 00:54:51 -04:00
parent d0fdcc103e
commit fa413e96ac
6 changed files with 184 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
library/HTMLPurifier/Injector/AutoParagraph.php
View File

@@ -29,7 +29,7 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
// if it doesn't, see the next if-block if you're in the document.
$i = $nesting = null;
if (!$this->_forwardUntilEndToken($i, $current, $nesting) && $token->is_whitespace) {
if (!$this->forwardUntilEndToken($i, $current, $nesting) && $token->is_whitespace) {
// State 1.1: ... ^ (whitespace, then document end)
// ----
// This is a degenerate case
@@ -101,7 +101,7 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
// Check if this token is adjacent to the parent token
// (seek backwards until token isn't whitespace)
$i = null;
$this->_backward($i, $prev);
$this->backward($i, $prev);
if (!$prev instanceof HTMLPurifier_Token_Start) {
// Token wasn't adjacent
@@ -160,7 +160,7 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
}
$i = null;
if ($this->_backward($i, $prev)) {
if ($this->backward($i, $prev)) {
if (
!$prev instanceof HTMLPurifier_Token_Text
) {
@@ -296,11 +296,11 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
* to insert a <p> tag.
*/
private function _pLookAhead() {
$this->_current($i, $current);
$this->current($i, $current);
if ($current instanceof HTMLPurifier_Token_Start) $nesting = 1;
else $nesting = 0;
$ok = false;
while ($this->_forwardUntilEndToken($i, $current, $nesting)) {
while ($this->forwardUntilEndToken($i, $current, $nesting)) {
$result = $this->_checkNeedsP($current);
if ($result !== null) {
$ok = $result;
@@ -310,69 +310,6 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector
return $ok;
}
/**
* Iterator function, which starts with the next token and continues until
* you reach the end of the input tokens.
* @warning Please prevent previous references from interfering with this
* functions by setting $i = null beforehand!
* @param &$i Current integer index variable for inputTokens
* @param &$current Current token variable. Do NOT use $token, as that variable is also a reference
*/
private function _forward(&$i, &$current) {
if ($i === null) $i = $this->inputIndex + 1;
else $i++;
if (!isset($this->inputTokens[$i])) return false;
$current = $this->inputTokens[$i];
return true;
}
/**
* Similar to _forward, but accepts a third parameter $nesting (which
* should be initialized at 0) and stops when we hit the end tag
* for the node $this->inputIndex starts in.
*/
private function _forwardUntilEndToken(&$i, &$current, &$nesting) {
$result = $this->_forward($i, $current);
if (!$result) return false;
if ($nesting === null) $nesting = 0;
if ($current instanceof HTMLPurifier_Token_Start) $nesting++;
elseif ($current instanceof HTMLPurifier_Token_End) {
if ($nesting <= 0) return false;
$nesting--;
}
return true;
}
/**
* Iterator function, starts with the previous token and continues until
* you reach the beginning of input tokens.
* @warning Please prevent previous references from interfering with this
* functions by setting $i = null beforehand!
* @param &$i Current integer index variable for inputTokens
* @param &$current Current token variable. Do NOT use $token, as that variable is also a reference
*/
private function _backward(&$i, &$current) {
if ($i === null) $i = $this->inputIndex - 1;
else $i--;
if ($i < 0) return false;
$current = $this->inputTokens[$i];
return true;
}
/**
* Initializes the iterator at the current position. Use in a do {} while;
* loop to force the _forward and _backward functions to start at the
* current location.
* @warning Please prevent previous references from interfering with this
* functions by setting $i = null beforehand!
* @param &$i Current integer index variable for inputTokens
* @param &$current Current token variable. Do NOT use $token, as that variable is also a reference
*/
private function _current(&$i, &$current) {
if ($i === null) $i = $this->inputIndex;
$current = $this->inputTokens[$i];
}
/**
* Determines if a particular token requires an earlier inline token
* to get a paragraph. This should be used with _forwardUntilEndToken

5
library/HTMLPurifier/Injector/SafeObject.php
View File

@@ -72,7 +72,10 @@ class HTMLPurifier_Injector_SafeObject extends HTMLPurifier_Injector
}
}
public function notifyEnd($token) {
public function handleEnd(&$token) {
// This is the WRONG way of handling the object and param stacks;
// we should be inserting them directly on the relevant object tokens
// so that the global stack handling handles it.
if ($token->name == 'object') {
array_pop($this->objectStack);
array_pop($this->paramStack);