/**
* Adds a rule to the list of rules that decides what types of content should be streamed diretly to a temporary file.
*
* If a content-type of a page or file matches with one of these rules, the content will be streamed directly into a
* temporary file without claiming local RAM.
*
* It's recommendend to add all content-types of files that may be of bigger size to prevent memory-overflows.
* By default the crawler will receive every content to memory!
*
* The content/source of pages and files that were streamed to file are not accessible directly within the overidden method
* {@link handleDocumentInfo()}, instead you get information about the file the content was stored in.
* (see properties {@link PHPCrawlerDocumentInfo::received_to_file} and {@link PHPCrawlerDocumentInfo::content_tmp_file}).
*
* Please note that this setting doesn't effect the link-finding results, also file-streams will be checked for links.
*
* A common setup may look like this example:
* <code>
* // Basically let the crawler receive every content (default-setting)
* $crawler->addReceiveContentType("##");
*
* // Tell the crawler to stream everything but "text/html"-documents to a tmp-file
* $crawler->addStreamToFileContentType("#^((?!text/html).)*$#");
* </code>
*
* @param string $regex The rule as a regular-expression
* @return bool TRUE if the rule was added to the list and the regex is valid.
* @section 10 Other settings
*/
public function addStreamToFileContentType($regex)
{
return $this->PageRequest->addStreamToFileContentType($regex);
}
