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 <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: peff

Makefile

@@ -781,6 +781,7 @@ LIB_OBJS += notes-cache.o
 LIB_OBJS += notes-merge.o
 LIB_OBJS += notes-utils.o
 LIB_OBJS += object.o
+LIB_OBJS += oidset.o
 LIB_OBJS += pack-bitmap.o
 LIB_OBJS += pack-bitmap-write.o
 LIB_OBJS += pack-check.o

oidset.c

@@ -0,0 +1,49 @@
+#include "cache.h"
+#include "oidset.h"
+
+struct oidset_entry {
+	struct hashmap_entry hash;
+	struct object_id oid;
+};
+
+static int oidset_hashcmp(const void *va, const void *vb,
+			  const void *vkey)
+{
+	const struct oidset_entry *a = va, *b = vb;
+	const struct object_id *key = vkey;
+	return oidcmp(&a->oid, key ? key : &b->oid);
+}
+
+int oidset_contains(const struct oidset *set, const struct object_id *oid)
+{
+	struct hashmap_entry key;
+
+	if (!set->map.cmpfn)
+		return 0;
+
+	hashmap_entry_init(&key, sha1hash(oid->hash));
+	return !!hashmap_get(&set->map, &key, oid);
+}
+
+int oidset_insert(struct oidset *set, const struct object_id *oid)
+{
+	struct oidset_entry *entry;
+
+	if (!set->map.cmpfn)
+		hashmap_init(&set->map, oidset_hashcmp, 0);
+
+	if (oidset_contains(set, oid))
+		return 1;
+
+	entry = xmalloc(sizeof(*entry));
+	hashmap_entry_init(&entry->hash, sha1hash(oid->hash));
+	oidcpy(&entry->oid, oid);
+
+	hashmap_add(&set->map, entry);
+	return 0;
+}
+
+void oidset_clear(struct oidset *set)
+{
+	hashmap_free(&set->map, 1);
+}

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 */