Merge branch 'jk/pack-bitmap'

Borrow the bitmap index into packfiles from JGit to speed up
enumeration of objects involved in a commit range without having to
fully traverse the history.

* jk/pack-bitmap: (26 commits)
  ewah: unconditionally ntohll ewah data
  ewah: support platforms that require aligned reads
  read-cache: use get_be32 instead of hand-rolled ntoh_l
  block-sha1: factor out get_be and put_be wrappers
  do not discard revindex when re-preparing packfiles
  pack-bitmap: implement optional name_hash cache
  t/perf: add tests for pack bitmaps
  t: add basic bitmap functionality tests
  count-objects: recognize .bitmap in garbage-checking
  repack: consider bitmaps when performing repacks
  repack: handle optional files created by pack-objects
  repack: turn exts array into array-of-struct
  repack: stop using magic number for ARRAY_SIZE(exts)
  pack-objects: implement bitmap writing
  rev-list: add bitmap mode to speed up object lists
  pack-objects: use bitmaps when packing objects
  pack-objects: split add_object_entry
  pack-bitmap: add support for bitmap indexes
  documentation: add documentation for the bitmap format
  ewah: compressed bitmap implementation
  ...

1 files changed, 68 insertions, 0 deletions

diff --git a/pack-objects.h b/pack-objects.h
new file mode 100644
index 0000000000..d1b98b30ff
--- /dev/null
+++ b/pack-objects.h
@@ -0,0 +1,68 @@
+#ifndef PACK_OBJECTS_H
+#define PACK_OBJECTS_H
+
+struct object_entry {
+	struct pack_idx_entry idx;
+	unsigned long size;	/* uncompressed size */
+	struct packed_git *in_pack;	/* already in pack */
+	off_t in_pack_offset;
+	struct object_entry *delta;	/* delta base object */
+	struct object_entry *delta_child; /* deltified objects who bases me */
+	struct object_entry *delta_sibling; /* other deltified objects who
+					     * uses the same base as me
+					     */
+	void *delta_data;	/* cached delta (uncompressed) */
+	unsigned long delta_size;	/* delta data size (uncompressed) */
+	unsigned long z_delta_size;	/* delta data size (compressed) */
+	enum object_type type;
+	enum object_type in_pack_type;	/* could be delta */
+	uint32_t hash;			/* name hint hash */
+	unsigned int in_pack_pos;
+	unsigned char in_pack_header_size;
+	unsigned preferred_base:1; /*
+				    * we do not pack this, but is available
+				    * to be used as the base object to delta
+				    * objects against.
+				    */
+	unsigned no_try_delta:1;
+	unsigned tagged:1; /* near the very tip of refs */
+	unsigned filled:1; /* assigned write-order */
+};
+
+struct packing_data {
+	struct object_entry *objects;
+	uint32_t nr_objects, nr_alloc;
+
+	int32_t *index;
+	uint32_t index_size;
+};
+
+struct object_entry *packlist_alloc(struct packing_data *pdata,
+				    const unsigned char *sha1,
+				    uint32_t index_pos);
+
+struct object_entry *packlist_find(struct packing_data *pdata,
+				   const unsigned char *sha1,
+				   uint32_t *index_pos);
+
+static inline uint32_t pack_name_hash(const char *name)
+{
+	uint32_t c, hash = 0;
+
+	if (!name)
+		return 0;
+
+	/*
+	 * This effectively just creates a sortable number from the
+	 * last sixteen non-whitespace characters. Last characters
+	 * count "most", so things that end in ".c" sort together.
+	 */
+	while ((c = *name++) != 0) {
+		if (isspace(c))
+			continue;
+		hash = (hash >> 2) + (c << 24);
+	}
+	return hash;
+}
+
+#endif