cakephp2-php8/lib/Cake/Utility/Sanitize.php

265 lines
7.4 KiB
PHP
Raw Normal View History

<?php
/**
* Washes strings from unwanted noise.
*
* Helpful methods to make unsafe strings usable.
*
2010-10-03 16:38:58 +00:00
* PHP 5
*
2009-11-06 06:46:59 +00:00
* CakePHP(tm) : Rapid Development Framework (http://cakephp.org)
2012-03-13 02:46:46 +00:00
* Copyright 2005-2012, Cake Software Foundation, Inc. (http://cakefoundation.org)
*
* Licensed under The MIT License
* Redistributions of files must retain the above copyright notice.
*
2012-03-13 02:46:46 +00:00
* @copyright Copyright 2005-2012, Cake Software Foundation, Inc. (http://cakefoundation.org)
2009-11-06 06:00:11 +00:00
* @link http://cakephp.org CakePHP(tm) Project
* @package Cake.Utility
* @since CakePHP(tm) v 0.10.0.1076
2009-11-06 06:51:51 +00:00
* @license MIT License (http://www.opensource.org/licenses/mit-license.php)
*/
2011-12-06 20:52:48 +00:00
App::import('Model', 'ConnectionManager');
/**
* Data Sanitization.
*
2011-12-02 05:58:09 +00:00
* Removal of alphanumeric characters, SQL-safe slash-added strings, HTML-friendly strings,
* and all of the above on arrays.
*
* @package Cake.Utility
*/
class Sanitize {
/**
* Removes any non-alphanumeric characters.
*
* @param string $string String to sanitize
* @param array $allowed An array of additional characters that are not to be removed.
* @return string Sanitized string
*/
2010-04-14 04:29:44 +00:00
public static function paranoid($string, $allowed = array()) {
$allow = null;
if (!empty($allowed)) {
foreach ($allowed as $value) {
$allow .= "\\$value";
}
}
if (is_array($string)) {
$cleaned = array();
foreach ($string as $key => $clean) {
$cleaned[$key] = preg_replace("/[^{$allow}a-zA-Z0-9]/", '', $clean);
}
} else {
$cleaned = preg_replace("/[^{$allow}a-zA-Z0-9]/", '', $string);
}
return $cleaned;
}
/**
* Makes a string SQL-safe.
*
* @param string $string String to sanitize
* @param string $connection Database connection being used
* @return string SQL safe string
*/
2010-04-14 04:29:44 +00:00
public static function escape($string, $connection = 'default') {
$db = ConnectionManager::getDataSource($connection);
if (is_numeric($string) || $string === null || is_bool($string)) {
return $string;
}
2012-01-07 03:53:39 +00:00
$string = $db->value($string, 'string');
if ($string[0] === 'N') {
$string = substr($string, 2);
} else {
$string = substr($string, 1);
2012-01-07 03:53:39 +00:00
}
$string = substr($string, 0, -1);
return $string;
}
/**
* Returns given string safe for display as HTML. Renders entities.
*
* strip_tags() does not validating HTML syntax or structure, so it might strip whole passages
* with broken HTML.
*
* ### Options:
*
* - remove (boolean) if true strips all HTML tags before encoding
* - charset (string) the charset used to encode the string
* - quotes (int) see http://php.net/manual/en/function.htmlentities.php
* - double (boolean) doube encode html entities
*
* @param string $string String from where to strip tags
* @param array $options Array of options to use.
* @return string Sanitized string
*/
2010-04-14 04:29:44 +00:00
public static function html($string, $options = array()) {
static $defaultCharset = false;
if ($defaultCharset === false) {
$defaultCharset = Configure::read('App.encoding');
if ($defaultCharset === null) {
$defaultCharset = 'UTF-8';
}
}
$default = array(
'remove' => false,
'charset' => $defaultCharset,
'quotes' => ENT_QUOTES,
'double' => true
);
$options = array_merge($default, $options);
if ($options['remove']) {
$string = strip_tags($string);
}
return htmlentities($string, $options['quotes'], $options['charset'], $options['double']);
}
/**
* Strips extra whitespace from output
*
* @param string $str String to sanitize
* @return string whitespace sanitized string
*/
2010-04-14 04:29:44 +00:00
public static function stripWhitespace($str) {
$r = preg_replace('/[\n\r\t]+/', '', $str);
return preg_replace('/\s{2,}/u', ' ', $r);
}
/**
* Strips image tags from output
*
* @param string $str String to sanitize
* @return string Sting with images stripped.
*/
2010-04-14 04:29:44 +00:00
public static function stripImages($str) {
$str = preg_replace('/(<a[^>]*>)(<img[^>]+alt=")([^"]*)("[^>]*>)(<\/a>)/i', '$1$3$5<br />', $str);
$str = preg_replace('/(<img[^>]+alt=")([^"]*)("[^>]*>)/i', '$2<br />', $str);
$str = preg_replace('/<img[^>]*>/i', '', $str);
return $str;
}
/**
* Strips scripts and stylesheets from output
*
* @param string $str String to sanitize
* @return string String with <script>, <style>, <link>, <img> elements removed.
*/
2010-04-14 04:29:44 +00:00
public static function stripScripts($str) {
return preg_replace('/(<link[^>]+rel="[^"]*stylesheet"[^>]*>|<img[^>]*>|style="[^"]*")|<script[^>]*>.*?<\/script>|<style[^>]*>.*?<\/style>|<!--.*?-->/is', '', $str);
}
/**
* Strips extra whitespace, images, scripts and stylesheets from output
*
* @param string $str String to sanitize
* @return string sanitized string
*/
2010-04-14 04:29:44 +00:00
public static function stripAll($str) {
$str = Sanitize::stripWhitespace($str);
$str = Sanitize::stripImages($str);
$str = Sanitize::stripScripts($str);
return $str;
}
/**
* Strips the specified tags from output. First parameter is string from
* where to remove tags. All subsequent parameters are tags.
*
* Ex.`$clean = Sanitize::stripTags($dirty, 'b', 'p', 'div');`
*
* Will remove all `<b>`, `<p>`, and `<div>` tags from the $dirty string.
*
* @param string $str,... String to sanitize
* @return string sanitized String
*/
public static function stripTags($str) {
2010-04-24 01:32:39 +00:00
$params = func_get_args();
for ($i = 1, $count = count($params); $i < $count; $i++) {
$str = preg_replace('/<' . $params[$i] . '\b[^>]*>/i', '', $str);
$str = preg_replace('/<\/' . $params[$i] . '[^>]*>/i', '', $str);
}
return $str;
}
/**
* Sanitizes given array or value for safe input. Use the options to specify
* the connection to use, and what filters should be applied (with a boolean
* value). Valid filters:
*
* - odd_spaces - removes any non space whitespace characters
* - encode - Encode any html entities. Encode must be true for the `remove_html` to work.
* - dollar - Escape `$` with `\$`
* - carriage - Remove `\r`
* - unicode -
* - escape - Should the string be SQL escaped.
* - backslash -
* - remove_html - Strip HTML with strip_tags. `encode` must be true for this option to work.
*
* @param string|array $data Data to sanitize
* @param string|array $options If string, DB connection being used, otherwise set of options
* @return mixed Sanitized data
*/
2010-04-14 04:29:44 +00:00
public static function clean($data, $options = array()) {
if (empty($data)) {
return $data;
}
if (is_string($options)) {
$options = array('connection' => $options);
2012-02-23 13:38:02 +00:00
} elseif (!is_array($options)) {
$options = array();
}
$options = array_merge(array(
'connection' => 'default',
'odd_spaces' => true,
'remove_html' => false,
'encode' => true,
'dollar' => true,
'carriage' => true,
'unicode' => true,
'escape' => true,
'backslash' => true
), $options);
if (is_array($data)) {
foreach ($data as $key => $val) {
$data[$key] = Sanitize::clean($val, $options);
}
return $data;
} else {
if ($options['odd_spaces']) {
$data = str_replace(chr(0xCA), '', $data);
}
if ($options['encode']) {
$data = Sanitize::html($data, array('remove' => $options['remove_html']));
}
if ($options['dollar']) {
$data = str_replace("\\\$", "$", $data);
}
if ($options['carriage']) {
$data = str_replace("\r", "", $data);
}
if ($options['unicode']) {
$data = preg_replace("/&amp;#([0-9]+);/s", "&#\\1;", $data);
}
if ($options['escape']) {
$data = Sanitize::escape($data, $options['connection']);
}
if ($options['backslash']) {
$data = preg_replace("/\\\(?!&amp;#|\?#)/", "\\", $data);
}
return $data;
}
}
}