pack-objects: a bit of document about struct object_entry

[thirdparty/git.git] / pack-objects.h

#ifndef PACK_OBJECTS_H
#define PACK_OBJECTS_H

/*
 * basic object info
 * -----------------
 * idx.oid is filled up before delta searching starts. idx.crc32 is
 * only valid after the object is written out and will be used for
 * generating the index. idx.offset will be both gradually set and
 * used in writing phase (base objects get offset first, then deltas
 * refer to them)
 *
 * "size" is the uncompressed object size. Compressed size of the raw
 * data for an object in a pack is not stored anywhere but is computed
 * and made available when reverse .idx is made.
 *
 * "hash" contains a path name hash which is used for sorting the
 * delta list and also during delta searching. Once prepare_pack()
 * returns it's no longer needed.
 *
 * source pack info
 * ----------------
 * The (in_pack, in_pack_offset) tuple contains the location of the
 * object in the source pack. in_pack_header_size allows quickly
 * skipping the header and going straight to the zlib stream.
 *
 * "type" and "in_pack_type" both describe object type. in_pack_type
 * may contain a delta type, while type is always the canonical type.
 *
 * deltas
 * ------
 * Delta links (delta, delta_child and delta_sibling) are created to
 * reflect that delta graph from the source pack then updated or added
 * during delta searching phase when we find better deltas.
 *
 * delta_child and delta_sibling are last needed in
 * compute_write_order(). "delta" and "delta_size" must remain valid
 * at object writing phase in case the delta is not cached.
 *
 * If a delta is cached in memory and is compressed, delta_data points
 * to the data and z_delta_size contains the compressed size. If it's
 * uncompressed [1], z_delta_size must be zero. delta_size is always
 * the uncompressed size and must be valid even if the delta is not
 * cached.
 *
 * [1] during try_delta phase we don't bother with compressing because
 * the delta could be quickly replaced with a better one.
 */
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 */

	/*
	 * State flags for depth-first search used for analyzing delta cycles.
	 *
	 * The depth is measured in delta-links to the base (so if A is a delta
	 * against B, then A has a depth of 1, and B a depth of 0).
	 */
	enum {
		DFS_NONE = 0,
		DFS_ACTIVE,
		DFS_DONE
	} dfs_state;
	int depth;
};

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