git/list-objects-filter.c

#define USE_THE_REPOSITORY_VARIABLE

#include "git-compat-util.h"
#include "dir.h"
#include "gettext.h"
#include "hex.h"
#include "commit.h"
#include "diff.h"
#include "revision.h"
#include "list-objects-filter.h"
#include "list-objects-filter-options.h"
#include "oidmap.h"
#include "oidset.h"
#include "object-name.h"
#include "odb.h"

/* Remember to update object flag allocation in object.h */
/*
 * FILTER_SHOWN_BUT_REVISIT -- we set this bit on tree objects
 * that have been shown, but should be revisited if they appear
 * in the traversal (until we mark it SEEN).  This is a way to
 * let us silently de-dup calls to show() in the caller.  This
 * is subtly different from the "revision.h:SHOWN" and the
 * "object-name.c:ONELINE_SEEN" bits.  And also different from
 * the non-de-dup usage in pack-bitmap.c
 */
#define FILTER_SHOWN_BUT_REVISIT (1<<21)

struct subfilter {
	struct filter *filter;
	struct oidset seen;
	struct oidset omits;
	struct object_id skip_tree;
	unsigned is_skipping_tree : 1;
};

struct filter {
	enum list_objects_filter_result (*filter_object_fn)(
		struct repository *r,
		enum list_objects_filter_situation filter_situation,
		struct object *obj,
		const char *pathname,
		const char *filename,
		struct oidset *omits,
		void *filter_data);

	/*
	 * Optional. If this function is supplied and the filter needs
	 * to collect omits, then this function is called once before
	 * free_fn is called.
	 *
	 * This is required because the following two conditions hold:
	 *
	 *   a. A tree filter can add and remove objects as an object
	 *      graph is traversed.
	 *   b. A combine filter's omit set is the union of all its
	 *      subfilters, which may include tree: filters.
	 *
	 * As such, the omits sets must be separate sets, and can only
	 * be unioned after the traversal is completed.
	 */
	void (*finalize_omits_fn)(struct oidset *omits, void *filter_data);

	void (*free_fn)(void *filter_data);

	void *filter_data;

	/* If non-NULL, the filter collects a list of the omitted OIDs here. */
	struct oidset *omits;
};

static enum list_objects_filter_result filter_blobs_none(
	struct repository *r UNUSED,
	enum list_objects_filter_situation filter_situation,
	struct object *obj,
	const char *pathname UNUSED,
	const char *filename UNUSED,
	struct oidset *omits,
	void *filter_data_ UNUSED)
{
	switch (filter_situation) {
	default:
		BUG("unknown filter_situation: %d", filter_situation);

	case LOFS_TAG:
		assert(obj->type == OBJ_TAG);
		/* always include all tag objects */
		return LOFR_MARK_SEEN | LOFR_DO_SHOW;

	case LOFS_COMMIT:
		assert(obj->type == OBJ_COMMIT);
		/* always include all commit objects */
		return LOFR_MARK_SEEN | LOFR_DO_SHOW;

	case LOFS_BEGIN_TREE:
		assert(obj->type == OBJ_TREE);
		/* always include all tree objects */
		return LOFR_MARK_SEEN | LOFR_DO_SHOW;

	case LOFS_END_TREE:
		assert(obj->type == OBJ_TREE);
		return LOFR_ZERO;

	case LOFS_BLOB:
		assert(obj->type == OBJ_BLOB);
		assert((obj->flags & SEEN) == 0);

		if (omits)
			oidset_insert(omits, &obj->oid);
		return LOFR_MARK_SEEN; /* but not LOFR_DO_SHOW (hard omit) */
	}
}

static void filter_blobs_none__init(
	struct list_objects_filter_options *filter_options UNUSED,
	struct filter *filter)
{
	filter->filter_object_fn = filter_blobs_none;
	filter->free_fn = free;
}

/*
 * A filter for list-objects to omit ALL trees and blobs from the traversal.
 * Can OPTIONALLY collect a list of the omitted OIDs.
 */
struct filter_trees_depth_data {
	/*
	 * Maps trees to the minimum depth at which they were seen. It is not
	 * necessary to re-traverse a tree at deeper or equal depths than it has
	 * already been traversed.
	 *
	 * We can't use LOFR_MARK_SEEN for tree objects since this will prevent
	 * it from being traversed at shallower depths.
	 */
	struct oidmap seen_at_depth;

	unsigned long exclude_depth;
	unsigned long current_depth;
};

struct seen_map_entry {
	struct oidmap_entry base;
	size_t depth;
};

/* Returns 1 if the oid was in the omits set before it was invoked. */
static int filter_trees_update_omits(
	struct object *obj,
	struct oidset *omits,
	int include_it)
{
	if (!omits)
		return 0;

	if (include_it)
		return oidset_remove(omits, &obj->oid);
	else
		return oidset_insert(omits, &obj->oid);
}

static enum list_objects_filter_result filter_trees_depth(
	struct repository *r UNUSED,
	enum list_objects_filter_situation filter_situation,
	struct object *obj,
	const char *pathname UNUSED,
	const char *filename UNUSED,
	struct oidset *omits,
	void *filter_data_)
{
	struct filter_trees_depth_data *filter_data = filter_data_;
	struct seen_map_entry *seen_info;
	int include_it = filter_data->current_depth <
		filter_data->exclude_depth;
	int filter_res;
	int already_seen;

	/*
	 * Note that we do not use _MARK_SEEN in order to allow re-traversal in
	 * case we encounter a tree or blob again at a shallower depth.
	 */

	switch (filter_situation) {
	default:
		BUG("unknown filter_situation: %d", filter_situation);

	case LOFS_TAG:
		assert(obj->type == OBJ_TAG);
		/* always include all tag objects */
		return LOFR_MARK_SEEN | LOFR_DO_SHOW;

	case LOFS_COMMIT:
		assert(obj->type == OBJ_COMMIT);
		/* always include all commit objects */
		return LOFR_MARK_SEEN | LOFR_DO_SHOW;

	case LOFS_END_TREE:
		assert(obj->type == OBJ_TREE);
		filter_data->current_depth--;
		return LOFR_ZERO;

	case LOFS_BLOB:
		filter_trees_update_omits(obj, omits, include_it);
		return include_it ? LOFR_MARK_SEEN | LOFR_DO_SHOW : LOFR_ZERO;

	case LOFS_BEGIN_TREE:
		seen_info = oidmap_get(
			&filter_data->seen_at_depth, &obj->oid);
		if (!seen_info) {
			CALLOC_ARRAY(seen_info, 1);
			oidcpy(&seen_info->base.oid, &obj->oid);
			seen_info->depth = filter_data->current_depth;
			oidmap_put(&filter_data->seen_at_depth, seen_info);
			already_seen = 0;
		} else {
			already_seen =
				filter_data->current_depth >= seen_info->depth;
		}

		if (already_seen) {
			filter_res = LOFR_SKIP_TREE;
		} else {
			int been_omitted = filter_trees_update_omits(
				obj, omits, include_it);
			seen_info->depth = filter_data->current_depth;

			if (include_it)
				filter_res = LOFR_DO_SHOW;
			else if (omits && !been_omitted)
				/*
				 * Must update omit information of children
				 * recursively; they have not been omitted yet.
				 */
				filter_res = LOFR_ZERO;
			else
				filter_res = LOFR_SKIP_TREE;
		}

		filter_data->current_depth++;
		return filter_res;
	}
}

static void filter_trees_free(void *filter_data) {
	struct filter_trees_depth_data *d = filter_data;
	if (!d)
		return;
	oidmap_clear(&d->seen_at_depth, 1);
	free(d);
}

static void filter_trees_depth__init(
	struct list_objects_filter_options *filter_options,
	struct filter *filter)
{
	struct filter_trees_depth_data *d = xcalloc(1, sizeof(