/**
* Set website url for crawling
*
* @param string $baseUrl []
*
* @return void
*/
public function setBaseUrl($baseUrl)
{
if (strpos($baseUrl, 'http') === false) {
$this->baseUrl = Uri\normalize('http://' . $baseUrl);
} else {
$this->baseUrl = Uri\normalize($baseUrl);
}
}
/**
* Calculates the uri for a request, making sure that the base uri is stripped out
*
* @param string $uri
* @throws Exception\Forbidden A permission denied exception is thrown whenever there was an attempt to supply a uri outside of the base uri
* @return string
*/
function calculateUri($uri) {
if ($uri[0] != '/' && strpos($uri, '://')) {
$uri = parse_url($uri, PHP_URL_PATH);
}
$uri = Uri\normalize(str_replace('//', '/', $uri));
$baseUri = Uri\normalize($this->getBaseUri());
if (strpos($uri, $baseUri) === 0) {
return trim(URLUtil::decodePath(substr($uri, strlen($baseUri))), '/');
// A special case, if the baseUri was accessed without a trailing
// slash, we'll accept it as well.
} elseif ($uri . '/' === $baseUri) {
return '';
} else {
throw new Exception\Forbidden('Requested uri (' . $uri . ') is out of base uri (' . $this->getBaseUri() . ')');
}
}
/**
* Returns the relative path.
*
* This is being calculated using the base url. This path will not start
* with a slash, so it will always return something like
* 'example/path.html'.
*
* If the full path is equal to the base url, this method will return an
* empty string.
*
* This method will also urldecode the path, and if the url was incoded as
* ISO-8859-1, it will convert it to UTF-8.
*
* If the path is outside of the base url, a LogicException will be thrown.
*
* @return string
*/
function getPath()
{
// Removing duplicated slashes.
$uri = str_replace('//', '/', $this->getUrl());
$uri = Uri\normalize($uri);
$baseUri = Uri\normalize($this->getBaseUrl());
if (strpos($uri, $baseUri) === 0) {
// We're not interested in the query part (everything after the ?).
list($uri) = explode('?', $uri);
return trim(URLUtil::decodePath(substr($uri, strlen($baseUri))), '/');
} elseif ($uri . '/' === $baseUri) {
return '';
}
throw new \LogicException('Requested uri (' . $this->getUrl() . ') is out of base uri (' . $this->getBaseUrl() . ')');
}