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

Remove trailing whitespace.

Browse Source 
Signed-off-by: Edward Z. Yang <edwardzyang@thewritingpot.com>
This commit is contained in:
Edward Z. Yang
2008-12-06 02:28:20 -05:00
parent 3a6b63dff1
commit 2c955af135
476 changed files with 5595 additions and 5547 deletions
Download Patch File Download Diff File Expand all files Collapse all files

134
library/HTMLPurifier/Strategy/FixNesting.php
View File

@@ -2,89 +2,89 @@
/**
* Takes a well formed list of tokens and fixes their nesting.
*
*
* HTML elements dictate which elements are allowed to be their children,
* for example, you can't have a p tag in a span tag. Other elements have
* much more rigorous definitions: tables, for instance, require a specific
* order for their elements. There are also constraints not expressible by
* document type definitions, such as the chameleon nature of ins/del
* tags and global child exclusions.
*
*
* The first major objective of this strategy is to iterate through all the
* nodes (not tokens) of the list of tokens and determine whether or not
* their children conform to the element's definition. If they do not, the
* child definition may optionally supply an amended list of elements that
* is valid or require that the entire node be deleted (and the previous
* node rescanned).
*
*
* The second objective is to ensure that explicitly excluded elements of
* an element do not appear in its children. Code that accomplishes this
* task is pervasive through the strategy, though the two are distinct tasks
* and could, theoretically, be seperated (although it's not recommended).
*
*
* @note Whether or not unrecognized children are silently dropped or
* translated into text depends on the child definitions.
*
*
* @todo Enable nodes to be bubbled out of the structure.
*/
class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
{
public function execute($tokens, $config, $context) {
//####################################################################//
// Pre-processing
// get a copy of the HTML definition
$definition = $config->getHTMLDefinition();
// insert implicit "parent" node, will be removed at end.
// DEFINITION CALL
$parent_name = $definition->info_parent;
array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name));
$tokens[] = new HTMLPurifier_Token_End($parent_name);
// setup the context variable 'IsInline', for chameleon processing
// is 'false' when we are not inline, 'true' when it must always
// be inline, and an integer when it is inline for a certain
// branch of the document tree
$is_inline = $definition->info_parent_def->descendants_are_inline;
$context->register('IsInline', $is_inline);
// setup error collector
$e =& $context->get('ErrorCollector', true);
//####################################################################//
// Loop initialization
// stack that contains the indexes of all parents,
// $stack[count($stack)-1] being the current parent
$stack = array();
// stack that contains all elements that are excluded
// it is organized by parent elements, similar to $stack,
// it is organized by parent elements, similar to $stack,
// but it is only populated when an element with exclusions is
// processed, i.e. there won't be empty exclusions.
$exclude_stack = array();
// variable that contains the start token while we are processing
// nodes. This enables error reporting to do its job
$start_token = false;
$context->register('CurrentToken', $start_token);
//####################################################################//
// Loop
// iterate through all start nodes. Determining the start node
// is complicated so it has been omitted from the loop construct
for ($i = 0, $size = count($tokens) ; $i < $size; ) {
//################################################################//
// Gather information on children
// child token accumulator
$child_tokens = array();
// scroll to the end of this node, report number, and collect
// all children
for ($j = $i, $depth = 0; ; $j++) {
@@ -101,15 +101,15 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
}
$child_tokens[] = $tokens[$j];
}
// $i is index of start token
// $j is index of end token
$start_token = $tokens[$i]; // to make token available via CurrentToken
//################################################################//
// Gather information on parent
// calculate parent information
if ($count = count($stack)) {
$parent_index = $stack[$count-1];
@@ -122,11 +122,11 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
} else {
// processing as if the parent were the "root" node
// unknown info, it won't be used anyway, in the future,
// we may want to enforce one element only (this is
// we may want to enforce one element only (this is
// necessary for HTML Purifier to clean entire documents
$parent_index = $parent_name = $parent_def = null;
}
// calculate context
if ($is_inline === false) {
// check if conditions make it inline
@@ -139,10 +139,10 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
$is_inline = false;
}
}
//################################################################//
// Determine whether element is explicitly excluded SGML-style
// determine whether or not element is excluded by checking all
// parent exclusions. The array should not be very large, two
// elements at most.
@@ -156,10 +156,10 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
}
}
}
//################################################################//
// Perform child validation
if ($excluded) {
// there is an exclusion, remove the entire node
$result = false;
@@ -171,9 +171,9 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
$def = $definition->info_parent_def;
} else {
$def = $definition->info[$tokens[$i]->name];
}
if (!empty($def->child)) {
// have DTD child def validate children
$result = $def->child->validateChildren(
@@ -182,31 +182,31 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
// weird, no child definition, get rid of everything
$result = false;
}
// determine whether or not this element has any exclusions
$excludes = $def->excludes;
}
// $result is now a bool or array
//################################################################//
// Process result by interpreting $result
if ($result === true || $child_tokens === $result) {
// leave the node as is
// register start token as a parental node start
$stack[] = $i;
// register exclusions if there are any
if (!empty($excludes)) $exclude_stack[] = $excludes;
// move cursor to next possible start node
$i++;
} elseif($result === false) {
// remove entire node
if ($e) {
if ($excluded) {
$e->send(E_ERROR, 'Strategy_FixNesting: Node excluded');
@@ -214,20 +214,20 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
$e->send(E_ERROR, 'Strategy_FixNesting: Node removed');
}
}
// calculate length of inner tokens and current tokens
$length = $j - $i + 1;
// perform removal
array_splice($tokens, $i, $length);
// update size
$size -= $length;
// there is no start token to register,
// current node is now the next possible start node
// unless it turns out that we need to do a double-check
// this is a rought heuristic that covers 100% of HTML's
// cases and 99% of all other cases. A child definition
// that would be tricked by this would be something like:
@@ -239,16 +239,16 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
$i = $parent_index;
array_pop($stack);
}
// PROJECTED OPTIMIZATION: Process all children elements before
// reprocessing parent node.
} else {
// replace node with $result
// calculate length of inner tokens
$length = $j - $i - 1;
if ($e) {
if (empty($result) && $length) {
$e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed');
@@ -256,31 +256,31 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
$e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized');
}
}
// perform replacement
array_splice($tokens, $i + 1, $length, $result);
// update size
$size -= $length;
$size += count($result);
// register start token as a parental node start
$stack[] = $i;
// register exclusions if there are any
if (!empty($excludes)) $exclude_stack[] = $excludes;
// move cursor to next possible start node
$i++;
}
//################################################################//
// Scroll to next start node
// We assume, at this point, that $i is the index of the token
// that is the first possible new start point for a node.
// Test if the token indeed is a start tag, if not, move forward
// and test again.
$size = count($tokens);
@@ -302,27 +302,27 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
}
$i++;
}
}
//####################################################################//
// Post-processing
// remove implicit parent tokens at the beginning and end
array_shift($tokens);
array_pop($tokens);
// remove context variables
$context->destroy('IsInline');
$context->destroy('CurrentToken');
//####################################################################//
// Return
return $tokens;
}
}