git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v2 02/19] oidset2: create oidset subclass with object length and pathname

From
JHJeff Hostetler <git@jeffhostetler.com>
Date
Jul 13, 2017, 17:34 UTC
Message-ID
<20170713173459.3559-3-git@jeffhostetler.com>
In-Reply-To
<20170713173459.3559-1-git@jeffhostetler.com>
From: Jeff Hostetler <jeffhost@microsoft.com>

Create subclass of oidset where each entry has a field to store the length of the object's content and an optional pathname.

This will be used in a future commit to build a manifest of omitted objects in a partial/narrow clone/fetch.

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
---
 Makefile  |   1 +
 oidset2.c | 101 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 oidset2.h |  56 ++++++++++++++++++++++++++++++++++
 3 files changed, 158 insertions(+)
 create mode 100644 oidset2.c
 create mode 100644 oidset2.h
diff --git a/Makefile b/Makefile
index ffa6da7..d590508 100644
--- a/Makefile
+++ b/Makefile
@@ -791,6 +791,7 @@ LIB_OBJS += notes-merge.o
 LIB_OBJS += notes-utils.o
 LIB_OBJS += object.o
 LIB_OBJS += oidset.o
+LIB_OBJS += oidset2.o
 LIB_OBJS += pack-bitmap.o
 LIB_OBJS += pack-bitmap-write.o
 LIB_OBJS += pack-check.o
diff --git a/oidset2.c b/oidset2.c
new file mode 100644
index 0000000..806d153
--- /dev/null
+++ b/oidset2.c
@@ -0,0 +1,101 @@
+#include "cache.h"
+#include "oidset2.h"
+
+static int oidset2_hashcmp(const void *va, const void *vb,
+			  const void *vkey)
+{
+	const struct oidset2_entry *a = va, *b = vb;
+	const struct object_id *key = vkey;
+	return oidcmp(&a->oid, key ? key : &b->oid);
+}
+
+struct oidset2_entry *oidset2_get(const struct oidset2 *set, const struct object_id *oid)
+{
+	struct hashmap_entry key;
+	struct oidset2_entry *value;
+
+	if (!set->map.cmpfn)
+		return NULL;
+
+	hashmap_entry_init(&key, sha1hash(oid->hash));
+	value = hashmap_get(&set->map, &key, oid);
+
+	return value;
+}
+
+int oidset2_contains(const struct oidset2 *set, const struct object_id *oid)
+{
+	return !!oidset2_get(set, oid);
+}
+
+int oidset2_insert(struct oidset2 *set, const struct object_id *oid,
+		   int64_t object_length, const char *pathname)
+{
+	struct oidset2_entry *entry;
+
+	if (!set->map.cmpfn)
+		hashmap_init(&set->map, oidset2_hashcmp, 0);
+
+	if (oidset2_contains(set, oid))
+		return 1;
+
+	entry = xcalloc(1, sizeof(*entry));
+	hashmap_entry_init(&entry->hash, sha1hash(oid->hash));
+	oidcpy(&entry->oid, oid);
+
+	entry->object_length = object_length;
+	if (pathname)
+	    entry->pathname = strdup(pathname);
+
+	hashmap_add(&set->map, entry);
+	return 0;
+}
+
+void oidset2_remove(struct oidset2 *set, const struct object_id *oid)
+{
+	struct hashmap_entry key;
+	struct oidset2_entry *e;
+
+	hashmap_entry_init(&key, sha1hash(oid->hash));
+	e = hashmap_remove(&set->map, &key, oid);
+
+	free(e->pathname);
+	free(e);
+}
+
+void oidset2_clear(struct oidset2 *set)
+{
+	hashmap_free(&set->map, 1);
+}
+
+static int oidset2_cmp(const void *a, const void *b)
+{
+	const struct oidset2_entry *ae = *((const struct oidset2_entry **)a);
+	const struct oidset2_entry *be = *((const struct oidset2_entry **)b);
+
+	return oidcmp(&ae->oid, &be->oid);
+}
+
+void oidset2_foreach(struct oidset2 *set, oidset2_foreach_cb cb, void *cb_data)
+{
+	struct hashmap_iter iter;
+	struct oidset2_entry **array;
+	struct oidset2_entry *e;
+	int j, k;
+
+	array = xcalloc(set->map.size, sizeof(*e));
+
+	hashmap_iter_init(&set->map, &iter);
+	k = 0;
+	while ((e = hashmap_iter_next(&iter)))
+		array[k++] = e;
+
+	QSORT(array, k, oidset2_cmp);
+
+	for (j = 0; j < k; j++) {
+		e = array[j];
+		cb(j, k, e, cb_data);
+	}
+
+	free(array);
+}
diff --git a/oidset2.h b/oidset2.h
new file mode 100644
index 0000000..c498eae
--- /dev/null
+++ b/oidset2.h
@@ -0,0 +1,56 @@
+#ifndef OIDSET2_H
+#define OIDSET2_H
+
+/**
+ * oidset2 is a variant of oidset, but allows additional fields for each object.
+ */
+
+/**
+ * A single oidset2; should be zero-initialized (or use OIDSET2_INIT).
+ */
+struct oidset2 {
+	struct hashmap map;
+};
+
+#define OIDSET2_INIT { { NULL } }
+
+struct oidset2_entry {
+	struct hashmap_entry hash;
+	struct object_id oid;
+
+	int64_t object_length;	/* This is SIGNED. Use -1 when unknown. */
+	char *pathname;
+};
+
+struct oidset2_entry *oidset2_get(const struct oidset2 *set, const struct object_id *oid);
+
+/**
+ * Returns true iff `set` contains `oid`.
+ */
+int oidset2_contains(const struct oidset2 *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 oidset2_insert(struct oidset2 *set, const struct object_id *oid,
+		   int64_t object_length, const char *pathname);
+
+void oidset2_remove(struct oidset2 *set, const struct object_id *oid);
+
+typedef void (*oidset2_foreach_cb)(
+	int i, int i_limit,
+	struct oidset2_entry *e, void *cb_data);
+
+void oidset2_foreach(struct oidset2 *set, oidset2_foreach_cb cb, void *cb_data);
+
+/**
+ * Remove all entries from the oidset2, freeing any resources associated with
+ * it.
+ */
+void oidset2_clear(struct oidset2 *set);
+
+#endif /* OIDSET2_H */
-- 
2.9.3
Previous: Jeff HostetlerNext: Jeff Hostetler
Message 18 of 20 in “WIP object filtering for partial clone”
  1. 00/19 WIP object filtering for partial cloneJeff Hostetler, Jul 13, 2017
  2. 01/19 dir: refactor add_excludes()Jeff Hostetler, Jul 13, 2017
  3. 03/19 list-objects: filter objects in traverse_commit_listJeff Hostetler, Jul 13, 2017
  4. 06/19 list-objects-filters: add use-sparse-checkout filterJeff Hostetler, Jul 13, 2017
  5. 07/19 object-filter: common declarations for object filteringJeff Hostetler, Jul 13, 2017
  6. 11/19 pack-objects: add object filtering supportJeff Hostetler, Jul 13, 2017
  7. 10/19 t6112: rev-list object filtering testJeff Hostetler, Jul 13, 2017
  8. 13/19 upload-pack: add filter-objects to protocol documentationJeff Hostetler, Jul 13, 2017
  9. 17/19 clone: add filter argumentsJeff Hostetler, Jul 13, 2017
  10. 18/19 index-pack: relax consistency checks for omitted objectsJeff Hostetler, Jul 13, 2017
  11. 12/19 pack-objects: add filtering help textJeff Hostetler, Jul 13, 2017
  12. 14/19 upload-pack: add object filteringJeff Hostetler, Jul 13, 2017
  13. 15/19 fetch-pack: add object filtering supportJeff Hostetler, Jul 13, 2017
  14. 16/19 connected: add filter_allow_omitted option to APIJeff Hostetler, Jul 13, 2017
  15. 19/19 fetch: add object filtering to fetchJeff Hostetler, Jul 13, 2017
  16. 08/19 rev-list: add object filtering supportJeff Hostetler, Jul 13, 2017
  17. 09/19 rev-list: add filtering help textJeff Hostetler, Jul 13, 2017
  18. 02/19 oidset2: create oidset subclass with object length and pathnameJeff Hostetler, Jul 13, 2017
  19. 05/19 list-objects-filters: add omit-large-blobs filterJeff Hostetler, Jul 13, 2017
  20. 04/19 list-objects-filters: add omit-all-blobs filterJeff Hostetler, Jul 13, 2017

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.