1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-11-05 08:47:56 +01:00
git/oidset.h
Jeff King 29c2bd5fa8 add oidset API
This is similar to many of our uses of sha1-array, but it
overcomes one limitation of a sha1-array: when you are
de-duplicating a large input with relatively few unique
entries, sha1-array uses 20 bytes per non-unique entry.
Whereas this set will use memory linear in the number of
unique entries (albeit a few more than 20 bytes due to
hashmap overhead).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-02-08 15:39:55 -08:00

45 lines
1.2 KiB
C

#ifndef OIDSET_H
#define OIDSET_H
/**
* This API is similar to sha1-array, in that it maintains a set of object ids
* in a memory-efficient way. The major differences are:
*
* 1. It uses a hash, so we can do online duplicate removal, rather than
* sort-and-uniq at the end. This can reduce memory footprint if you have
* a large list of oids with many duplicates.
*
* 2. The per-unique-oid memory footprint is slightly higher due to hash
* table overhead.
*/
/**
* A single oidset; should be zero-initialized (or use OIDSET_INIT).
*/
struct oidset {
struct hashmap map;
};
#define OIDSET_INIT { { NULL } }
/**
* Returns true iff `set` contains `oid`.
*/
int oidset_contains(const struct oidset *set, const struct object_id *oid);
/**
* Insert the oid into the set; a copy is made, so "oid" does not need
* to persist after this function is called.
*
* Returns 1 if the oid was already in the set, 0 otherwise. This can be used
* to perform an efficient check-and-add.
*/
int oidset_insert(struct oidset *set, const struct object_id *oid);
/**
* Remove all entries from the oidset, freeing any resources associated with
* it.
*/
void oidset_clear(struct oidset *set);
#endif /* OIDSET_H */