Convert a string to UTF-8 based on configuration.
| public static convertToUTF8 ( string $str, HTMLPurifier_Config $config, HTMLPurifier_Context $context ) : string | ||
| $str | string | The string to convert |
| $config | HTMLPurifier_Config | |
| $context | HTMLPurifier_Context | |
| return | string | |
/**
* Filters an HTML snippet/document to be XSS-free and standards-compliant.
*
* @param $html String of HTML to purify
* @param $config HTMLPurifier_Config object for this operation, if omitted,
* defaults to the config object specified during this
* object's construction. The parameter can also be any type
* that HTMLPurifier_Config::create() supports.
* @return Purified HTML
*/
public function purify($html, $config = null)
{
// :TODO: make the config merge in, instead of replace
$config = $config ? HTMLPurifier_Config::create($config) : $this->config;
// implementation is partially environment dependant, partially
// configuration dependant
$lexer = HTMLPurifier_Lexer::create($config);
$context = new HTMLPurifier_Context();
// setup HTML generator
$this->generator = new HTMLPurifier_Generator($config, $context);
$context->register('Generator', $this->generator);
// set up global context variables
if ($config->get('Core.CollectErrors')) {
// may get moved out if other facilities use it
$language_factory = HTMLPurifier_LanguageFactory::instance();
$language = $language_factory->create($config, $context);
$context->register('Locale', $language);
$error_collector = new HTMLPurifier_ErrorCollector($context);
$context->register('ErrorCollector', $error_collector);
}
// setup id_accumulator context, necessary due to the fact that
// AttrValidator can be called from many places
$id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
$context->register('IDAccumulator', $id_accumulator);
$html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
// setup filters
$filter_flags = $config->getBatch('Filter');
$custom_filters = $filter_flags['Custom'];
unset($filter_flags['Custom']);
$filters = array();
foreach ($filter_flags as $filter => $flag) {
if (!$flag) {
continue;
}
if (strpos($filter, '.') !== false) {
continue;
}
$class = "HTMLPurifier_Filter_{$filter}";
$filters[] = new $class();
}
foreach ($custom_filters as $filter) {
// maybe "HTMLPurifier_Filter_$filter", but be consistent with AutoFormat
$filters[] = $filter;
}
$filters = array_merge($filters, $this->filters);
// maybe prepare(), but later
for ($i = 0, $filter_size = count($filters); $i < $filter_size; $i++) {
$html = $filters[$i]->preFilter($html, $config, $context);
}
// purified HTML
$html = $this->generator->generateFromTokens($this->strategy->execute($lexer->tokenizeHTML($html, $config, $context), $config, $context));
for ($i = $filter_size - 1; $i >= 0; $i--) {
$html = $filters[$i]->postFilter($html, $config, $context);
}
$html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
$this->context =& $context;
return $html;
}
public function purify($html, $config = null)
{
$config = $config ? HTMLPurifier_Config::create($config) : $this->config;
$lexer = HTMLPurifier_Lexer::create($config);
$context = new HTMLPurifier_Context();
$this->generator = new HTMLPurifier_Generator($config, $context);
$context->register('Generator', $this->generator);
if ($config->get('Core.CollectErrors')) {
$language_factory = HTMLPurifier_LanguageFactory::instance();
$language = $language_factory->create($config, $context);
$context->register('Locale', $language);
$error_collector = new HTMLPurifier_ErrorCollector($context);
$context->register('ErrorCollector', $error_collector);
}
$id_accumulator = HTMLPurifier_IDAccumulator::build($config, $context);
$context->register('IDAccumulator', $id_accumulator);
$html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
$filter_flags = $config->getBatch('Filter');
$custom_filters = $filter_flags['Custom'];
unset($filter_flags['Custom']);
$filters = array();
foreach ($filter_flags as $filter => $flag) {
if (!$flag) {
continue;
}
if (strpos($filter, '.') !== false) {
continue;
}
$class = "HTMLPurifier_Filter_{$filter}";
$filters[] = new $class();
}
foreach ($custom_filters as $filter) {
$filters[] = $filter;
}
$filters = array_merge($filters, $this->filters);
for ($i = 0, $filter_size = count($filters); $i < $filter_size; $i++) {
$html = $filters[$i]->preFilter($html, $config, $context);
}
$html = $this->generator->generateFromTokens($this->strategy->execute($lexer->tokenizeHTML($html, $config, $context), $config, $context));
for ($i = $filter_size - 1; $i >= 0; $i--) {
$html = $filters[$i]->postFilter($html, $config, $context);
}
$html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
$this->context =& $context;
return $html;
}
/**
* Filters an HTML snippet/document to be XSS-free and standards-compliant.
*
* @param $html String of HTML to purify
* @param $config HTMLPurifier_Config object for this operation, if omitted,
* defaults to the config object specified during this
* object's construction. The parameter can also be any type
* that HTMLPurifier_Config::create() supports.
* @return Purified HTML
*/
function purify($html, $config = null)
{
$config = $config ? HTMLPurifier_Config::create($config) : $this->config;
// implementation is partially environment dependant, partially
// configuration dependant
$lexer = HTMLPurifier_Lexer::create($config);
$context = new HTMLPurifier_Context();
// our friendly neighborhood generator, all primed with configuration too!
$this->generator->generateFromTokens(array(), $config, $context);
$context->register('Generator', $this->generator);
// set up global context variables
if ($config->get('Core', 'CollectErrors')) {
// may get moved out if other facilities use it
$language_factory = HTMLPurifier_LanguageFactory::instance();
$language = $language_factory->create($config, $context);
$context->register('Locale', $language);
$error_collector = new HTMLPurifier_ErrorCollector($context);
$context->register('ErrorCollector', $error_collector);
}
$html = HTMLPurifier_Encoder::convertToUTF8($html, $config, $context);
for ($i = 0, $size = count($this->filters); $i < $size; $i++) {
$html = $this->filters[$i]->preFilter($html, $config, $context);
}
// purified HTML
$html = $this->generator->generateFromTokens($this->strategy->execute($lexer->tokenizeHTML($html, $config, $context), $config, $context), $config, $context);
for ($i = $size - 1; $i >= 0; $i--) {
$html = $this->filters[$i]->postFilter($html, $config, $context);
}
$html = HTMLPurifier_Encoder::convertFromUTF8($html, $config, $context);
$this->context =& $context;
return $html;
}
/**
* Attempts to convert a string to UTF-8 and clean any non-valid UTF-8 characters.
*
* @param $string
*
* @return bool|string
*/
public static function convertToUTF8($string)
{
// Don't wrap in a class_exists in case the server already has it's own version of HTMLPurifier and they have
// open_basedir restrictions
require_once Craft::getPathOfAlias('system.vendors.htmlpurifier') . '/HTMLPurifier.standalone.php';
// If it's already a UTF8 string, just clean and return it
if (static::isUTF8($string)) {
return \HTMLPurifier_Encoder::cleanUTF8($string);
}
// Otherwise set HTMLPurifier to the actual string encoding
$config = \HTMLPurifier_Config::createDefault();
$config->set('Core.Encoding', static::getEncoding($string));
// Clean it
$string = \HTMLPurifier_Encoder::cleanUTF8($string);
// Convert it to UTF8 if possible
if (static::checkForIconv()) {
$string = \HTMLPurifier_Encoder::convertToUTF8($string, $config, null);
} else {
$encoding = static::getEncoding($string);
$string = mb_convert_encoding($string, 'utf-8', $encoding);
}
return $string;
}
public function testShiftJIS()
{
if (!HTMLPurifier_Encoder::iconvAvailable()) {
return;
}
$this->config->set('Core.Encoding', 'Shift_JIS');
// This actually looks like a Yen, but we're going to treat it differently
$this->assertIdentical(HTMLPurifier_Encoder::convertFromUTF8('\\~', $this->config, $this->context), '\\~');
$this->assertIdentical(HTMLPurifier_Encoder::convertToUTF8('\\~', $this->config, $this->context), '\\~');
}