Classes related to the Indexing infrastructure:

/**
* An interface to a cache of data for jobs.
*/
public interface JobIndexCache {
/**
* Get an index for the given list of job IDs. The resulting file contains a suitably sorted list. This method
* should always be safe for asynchronous calling. This method may use a cached version of the file.
*
* @param jobIDs Set of job IDs to generate index for.
* @return An index, consisting of a file and the set this is an index for. This file must not be modified or
* deleted, since it is part of the cache of data.
*/
Index<Set<Long>> getIndex(Set<Long> jobIDs);


/**
* Request an index from the indexserver. Prepare the index but don't give it to me.
*
* @param jobSet Set of job IDs to generate index for.
* @param harvestId Harvestdefinition associated with this set of jobs
*/
void requestIndex(Set<Long> jobSet, Long harvestId);
}

public enum RequestType {
	CDX, DEDUP_CRAWL_LOG, FULL_CRAWL_LOG
}

/**
* Get the filename for the file containing the combined data for a set of IDs.
*
* @param ids A set of IDs to generate a filename for
* @return A filename that uniquely identifies this set of IDs within the cache. It is considered acceptable to have
* collisions at a likelihood the order of 1/2^128 (i.e. use MD5 to abbreviate long lists).
*/
public File getCacheFile(Set<T> ids) {
	String fileName = FileUtils.generateFileNameFromSet(ids, "-cache");
	return new File(getCacheDir(), fileName);
}