From 29c2bd5fa8cb97eedcd463d49cfc7e753feb3145 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Wed, 8 Feb 2017 15:53:07 -0500 Subject: 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 Signed-off-by: Junio C Hamano --- oidset.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 oidset.h (limited to 'oidset.h') diff --git a/oidset.h b/oidset.h new file mode 100644 index 0000000000..b7eaab5b88 --- /dev/null +++ b/oidset.h @@ -0,0 +1,45 @@ +#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 */ -- cgit v1.3