| public parse ( $uri ) : HTMLPurifier_URI | ||
| $uri | string URI to parse | |
| return | HTMLPurifier_URI | representation of URI. This representation has not been validated yet and may not conform to RFC. |
public function parse($uri)
{
$uri = $this->percentEncoder->normalize($uri);
// Regexp is as per Appendix B.
// Note that ["<>] are an addition to the RFC's recommended
// characters, because they represent external delimeters.
$r_URI = '!' . '(([a-zA-Z0-9\\.\\+\\-]+):)?' . '(//([^/?#"<>]*))?' . '([^?#"<>]*)' . '(\\?([^#"<>]*))?' . '(#([^"<>]*))?' . '!';
$matches = array();
$result = preg_match($r_URI, $uri, $matches);
if (!$result) {
return false;
}
// *really* invalid URI
// seperate out parts
$scheme = !empty($matches[1]) ? $matches[2] : null;
$authority = !empty($matches[3]) ? $matches[4] : null;
$path = $matches[5];
// always present, can be empty
$query = !empty($matches[6]) ? $matches[7] : null;
$fragment = !empty($matches[8]) ? $matches[9] : null;
// further parse authority
if ($authority !== null) {
$r_authority = "/^((.+?)@)?(\\[[^\\]]+\\]|[^:]*)(:(\\d*))?/";
$matches = array();
preg_match($r_authority, $authority, $matches);
$userinfo = !empty($matches[1]) ? $matches[2] : null;
$host = !empty($matches[3]) ? $matches[3] : '';
$port = !empty($matches[4]) ? (int) $matches[5] : null;
} else {
$port = $host = $userinfo = null;
}
return new HTMLPurifier_URI($scheme, $userinfo, $host, $port, $path, $query, $fragment);
} function testURIDefinitionValidation()
{
$parser = new HTMLPurifier_URIParser();
$uri = $parser->parse('http://example.com');
$this->config->set('URI.DefinitionID', 'HTMLPurifier_AttrDef_URITest->testURIDefinitionValidation');
generate_mock_once('HTMLPurifier_URIDefinition');
$uri_def = new HTMLPurifier_URIDefinitionMock();
$uri_def->expectOnce('filter', array($uri, '*', '*'));
$uri_def->setReturnValue('filter', true, array($uri, '*', '*'));
$uri_def->expectOnce('postFilter', array($uri, '*', '*'));
$uri_def->setReturnValue('postFilter', true, array($uri, '*', '*'));
$uri_def->setup = true;
// Since definitions are no longer passed by reference, we need
// to muck around with the cache to insert our mock. This is
// technically a little bad, since the cache shouldn't change
// behavior, but I don't feel too good about letting users
// overload entire definitions.
generate_mock_once('HTMLPurifier_DefinitionCache');
$cache_mock = new HTMLPurifier_DefinitionCacheMock();
$cache_mock->setReturnValue('get', $uri_def);
generate_mock_once('HTMLPurifier_DefinitionCacheFactory');
$factory_mock = new HTMLPurifier_DefinitionCacheFactoryMock();
$old = HTMLPurifier_DefinitionCacheFactory::instance();
HTMLPurifier_DefinitionCacheFactory::instance($factory_mock);
$factory_mock->setReturnValue('create', $cache_mock);
$this->assertDef('http://example.com');
HTMLPurifier_DefinitionCacheFactory::instance($old);
}
