1 files changed, 212 insertions, 75 deletions

diff --git a/list-objects.c b/list-objects.c
index b3931fa434..4e2789768d 100644
--- a/list-objects.c
+++ b/list-objects.c
@@ -7,28 +7,62 @@
 #include "tree-walk.h"
 #include "revision.h"
 #include "list-objects.h"
+#include "list-objects-filter.h"
+#include "list-objects-filter-options.h"
+#include "packfile.h"
+#include "object-store.h"
+#include "trace.h"
 
-static void process_blob(struct rev_info *revs,
+struct traversal_context {
+	struct rev_info *revs;
+	show_object_fn show_object;
+	show_commit_fn show_commit;
+	void *show_data;
+	filter_object_fn filter_fn;
+	void *filter_data;
+};
+
+static void process_blob(struct traversal_context *ctx,
 			 struct blob *blob,
-			 show_object_fn show,
 			 struct strbuf *path,
-			 const char *name,
-			 void *cb_data)
+			 const char *name)
 {
 	struct object *obj = &blob->object;
 	size_t pathlen;
+	enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
 
-	if (!revs->blob_objects)
+	if (!ctx->revs->blob_objects)
 		return;
 	if (!obj)
 		die("bad blob object");
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
-	obj->flags |= SEEN;
+
+	/*
+	 * Pre-filter known-missing objects when explicitly requested.
+	 * Otherwise, a missing object error message may be reported
+	 * later (depending on other filtering criteria).
+	 *
+	 * Note that this "--exclude-promisor-objects" pre-filtering
+	 * may cause the actual filter to report an incomplete list
+	 * of missing objects.
+	 */
+	if (ctx->revs->exclude_promisor_objects &&
+	    !has_object_file(&obj->oid) &&
+	    is_promisor_object(&obj->oid))
+		return;
 
 	pathlen = path->len;
 	strbuf_addstr(path, name);
-	show(obj, path->buf, cb_data);
+	if ((obj->flags & NOT_USER_GIVEN) && ctx->filter_fn)
+		r = ctx->filter_fn(ctx->revs->repo,
+				   LOFS_BLOB, obj,
+				   path->buf, &path->buf[pathlen],
+				   ctx->filter_data);
+	if (r & LOFR_MARK_SEEN)
+		obj->flags |= SEEN;
+	if (r & LOFR_DO_SHOW)
+		ctx->show_object(obj, path->buf, ctx->show_data);
 	strbuf_setlen(path, pathlen);
 }
 
@@ -54,29 +88,67 @@ static void process_blob(struct rev_info *revs,
  * the link, and how to do it. Whether it necessarily makes
  * any sense what-so-ever to ever do that is another issue.
  */
-static void process_gitlink(struct rev_info *revs,
+static void process_gitlink(struct traversal_context *ctx,
 			    const unsigned char *sha1,
-			    show_object_fn show,
 			    struct strbuf *path,
-			    const char *name,
-			    void *cb_data)
+			    const char *name)
 {
 	/* Nothing to do */
 }
 
-static void process_tree(struct rev_info *revs,
+static void process_tree(struct traversal_context *ctx,
 			 struct tree *tree,
-			 show_object_fn show,
 			 struct strbuf *base,
-			 const char *name,
-			 void *cb_data)
+			 const char *name);
+
+static void process_tree_contents(struct traversal_context *ctx,
+				  struct tree *tree,
+				  struct strbuf *base)
 {
-	struct object *obj = &tree->object;
 	struct tree_desc desc;
 	struct name_entry entry;
-	enum interesting match = revs->diffopt.pathspec.nr == 0 ?
-		all_entries_interesting: entry_not_interesting;
+	enum interesting match = ctx->revs->diffopt.pathspec.nr == 0 ?
+		all_entries_interesting : entry_not_interesting;
+
+	init_tree_desc(&desc, tree->buffer, tree->size);
+
+	while (tree_entry(&desc, &entry)) {
+		if (match != all_entries_interesting) {
+			match = tree_entry_interesting(ctx->revs->repo->index,
+						       &entry, base, 0,
+						       &ctx->revs->diffopt.pathspec);
+			if (match == all_entries_not_interesting)
+				break;
+			if (match == entry_not_interesting)
+				continue;
+		}
+
+		if (S_ISDIR(entry.mode)) {
+			struct tree *t = lookup_tree(ctx->revs->repo, entry.oid);
+			t->object.flags |= NOT_USER_GIVEN;
+			process_tree(ctx, t, base, entry.path);
+		}
+		else if (S_ISGITLINK(entry.mode))
+			process_gitlink(ctx, entry.oid->hash,
+					base, entry.path);
+		else {
+			struct blob *b = lookup_blob(ctx->revs->repo, entry.oid);
+			b->object.flags |= NOT_USER_GIVEN;
+			process_blob(ctx, b, base, entry.path);
+		}
+	}
+}
+
+static void process_tree(struct traversal_context *ctx,
+			 struct tree *tree,
+			 struct strbuf *base,
+			 const char *name)
+{
+	struct object *obj = &tree->object;
+	struct rev_info *revs = ctx->revs;
 	int baselen = base->len;
+	enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
+	int failed_parse;
 
 	if (!revs->tree_objects)
 		return;
@@ -84,45 +156,54 @@ static void process_tree(struct rev_info *revs,
 		die("bad tree object");
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
-	if (parse_tree_gently(tree, revs->ignore_missing_links) < 0) {
+
+	failed_parse = parse_tree_gently(tree, 1);
+	if (failed_parse) {
 		if (revs->ignore_missing_links)
 			return;
-		die("bad tree object %s", oid_to_hex(&obj->oid));
+
+		/*
+		 * Pre-filter known-missing tree objects when explicitly
+		 * requested.  This may cause the actual filter to report
+		 * an incomplete list of missing objects.
+		 */
+		if (revs->exclude_promisor_objects &&
+		    is_promisor_object(&obj->oid))
+			return;
+
+		if (!revs->do_not_die_on_missing_tree)
+			die("bad tree object %s", oid_to_hex(&obj->oid));
 	}
 
-	obj->flags |= SEEN;
 	strbuf_addstr(base, name);
-	show(obj, base->buf, cb_data);
+	if ((obj->flags & NOT_USER_GIVEN) && ctx->filter_fn)
+		r = ctx->filter_fn(ctx->revs->repo,
+				   LOFS_BEGIN_TREE, obj,
+				   base->buf, &base->buf[baselen],
+				   ctx->filter_data);
+	if (r & LOFR_MARK_SEEN)
+		obj->flags |= SEEN;
+	if (r & LOFR_DO_SHOW)
+		ctx->show_object(obj, base->buf, ctx->show_data);
 	if (base->len)
 		strbuf_addch(base, '/');
 
-	init_tree_desc(&desc, tree->buffer, tree->size);
+	if (r & LOFR_SKIP_TREE)
+		trace_printf("Skipping contents of tree %s...\n", base->buf);
+	else if (!failed_parse)
+		process_tree_contents(ctx, tree, base);
 
-	while (tree_entry(&desc, &entry)) {
-		if (match != all_entries_interesting) {
-			match = tree_entry_interesting(&entry, base, 0,
-						       &revs->diffopt.pathspec);
-			if (match == all_entries_not_interesting)
-				break;
-			if (match == entry_not_interesting)
-				continue;
-		}
-
-		if (S_ISDIR(entry.mode))
-			process_tree(revs,
-				     lookup_tree(entry.oid),
-				     show, base, entry.path,
-				     cb_data);
-		else if (S_ISGITLINK(entry.mode))
-			process_gitlink(revs, entry.oid->hash,
-					show, base, entry.path,
-					cb_data);
-		else
-			process_blob(revs,
-				     lookup_blob(entry.oid),
-				     show, base, entry.path,
-				     cb_data);
+	if ((obj->flags & NOT_USER_GIVEN) && ctx->filter_fn) {
+		r = ctx->filter_fn(ctx->revs->repo,
+				   LOFS_END_TREE, obj,
+				   base->buf, &base->buf[baselen],
+				   ctx->filter_data);
+		if (r & LOFR_MARK_SEEN)
+			obj->flags |= SEEN;
+		if (r & LOFR_DO_SHOW)
+			ctx->show_object(obj, base->buf, ctx->show_data);
 	}
+
 	strbuf_setlen(base, baselen);
 	free_tree_buffer(tree);
 }
@@ -137,7 +218,7 @@ static void mark_edge_parents_uninteresting(struct commit *commit,
 		struct commit *parent = parents->item;
 		if (!(parent->object.flags & UNINTERESTING))
 			continue;
-		mark_tree_uninteresting(parent->tree);
+		mark_tree_uninteresting(revs->repo, get_commit_tree(parent));
 		if (revs->edge_hint && !(parent->object.flags & SHOWN)) {
 			parent->object.flags |= SHOWN;
 			show_edge(parent);
@@ -154,7 +235,8 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge)
 		struct commit *commit = list->item;
 
 		if (commit->object.flags & UNINTERESTING) {
-			mark_tree_uninteresting(commit->tree);
+			mark_tree_uninteresting(revs->repo,
+						get_commit_tree(commit));
 			if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) {
 				commit->object.flags |= SHOWN;
 				show_edge(commit);
@@ -169,7 +251,8 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge)
 			struct commit *commit = (struct commit *)obj;
 			if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING))
 				continue;
-			mark_tree_uninteresting(commit->tree);
+			mark_tree_uninteresting(revs->repo,
+						get_commit_tree(commit));
 			if (!(obj->flags & SHOWN)) {
 				obj->flags |= SHOWN;
 				show_edge(commit);
@@ -183,27 +266,15 @@ static void add_pending_tree(struct rev_info *revs, struct tree *tree)
 	add_pending_object(revs, &tree->object, "");
 }
 
-void traverse_commit_list(struct rev_info *revs,
-			  show_commit_fn show_commit,
-			  show_object_fn show_object,
-			  void *data)
+static void traverse_trees_and_blobs(struct traversal_context *ctx,
+				     struct strbuf *base)
 {
 	int i;
-	struct commit *commit;
-	struct strbuf base;
 
-	strbuf_init(&base, PATH_MAX);
-	while ((commit = get_revision(revs)) != NULL) {
-		/*
-		 * an uninteresting boundary commit may not have its tree
-		 * parsed yet, but we are not going to show them anyway
-		 */
-		if (commit->tree)
-			add_pending_tree(revs, commit->tree);
-		show_commit(commit, data);
-	}
-	for (i = 0; i < revs->pending.nr; i++) {
-		struct object_array_entry *pending = revs->pending.objects + i;
+	assert(base->len == 0);
+
+	for (i = 0; i < ctx->revs->pending.nr; i++) {
+		struct object_array_entry *pending = ctx->revs->pending.objects + i;
 		struct object *obj = pending->item;
 		const char *name = pending->name;
 		const char *path = pending->path;
@@ -211,24 +282,90 @@ void traverse_commit_list(struct rev_info *revs,
 			continue;
 		if (obj->type == OBJ_TAG) {
 			obj->flags |= SEEN;
-			show_object(obj, name, data);
+			ctx->show_object(obj, name, ctx->show_data);
 			continue;
 		}
 		if (!path)
 			path = "";
 		if (obj->type == OBJ_TREE) {
-			process_tree(revs, (struct tree *)obj, show_object,
-				     &base, path, data);
+			process_tree(ctx, (struct tree *)obj, base, path);
 			continue;
 		}
 		if (obj->type == OBJ_BLOB) {
-			process_blob(revs, (struct blob *)obj, show_object,
-				     &base, path, data);
+			process_blob(ctx, (struct blob *)obj, base, path);
 			continue;
 		}
 		die("unknown pending object %s (%s)",
 		    oid_to_hex(&obj->oid), name);
 	}
-	object_array_clear(&revs->pending);
-	strbuf_release(&base);
+	object_array_clear(&ctx->revs->pending);
+}
+
+static void do_traverse(struct traversal_context *ctx)
+{
+	struct commit *commit;
+	struct strbuf csp; /* callee's scratch pad */
+	strbuf_init(&csp, PATH_MAX);
+
+	while ((commit = get_revision(ctx->revs)) != NULL) {
+		/*
+		 * an uninteresting boundary commit may not have its tree
+		 * parsed yet, but we are not going to show them anyway
+		 */
+		if (get_commit_tree(commit)) {
+			struct tree *tree = get_commit_tree(commit);
+			tree->object.flags |= NOT_USER_GIVEN;
+			add_pending_tree(ctx->revs, tree);
+		}
+		ctx->show_commit(commit, ctx->show_data);
+
+		if (ctx->revs->tree_blobs_in_commit_order)
+			/*
+			 * NEEDSWORK: Adding the tree and then flushing it here
+			 * needs a reallocation for each commit. Can we pass the
+			 * tree directory without allocation churn?
+			 */
+			traverse_trees_and_blobs(ctx, &csp);
+	}
+	traverse_trees_and_blobs(ctx, &csp);
+	strbuf_release(&csp);
+}
+
+void traverse_commit_list(struct rev_info *revs,
+			  show_commit_fn show_commit,
+			  show_object_fn show_object,
+			  void *show_data)
+{
+	struct traversal_context ctx;
+	ctx.revs = revs;
+	ctx.show_commit = show_commit;
+	ctx.show_object = show_object;
+	ctx.show_data = show_data;
+	ctx.filter_fn = NULL;
+	ctx.filter_data = NULL;
+	do_traverse(&ctx);
+}
+
+void traverse_commit_list_filtered(
+	struct list_objects_filter_options *filter_options,
+	struct rev_info *revs,
+	show_commit_fn show_commit,
+	show_object_fn show_object,
+	void *show_data,
+	struct oidset *omitted)
+{
+	struct traversal_context ctx;
+	filter_free_fn filter_free_fn = NULL;
+
+	ctx.revs = revs;
+	ctx.show_object = show_object;
+	ctx.show_commit = show_commit;
+	ctx.show_data = show_data;
+	ctx.filter_fn = NULL;
+
+	ctx.filter_data = list_objects_filter__init(omitted, filter_options,
+						    &ctx.filter_fn, &filter_free_fn);
+	do_traverse(&ctx);
+	if (ctx.filter_data && filter_free_fn)
+		filter_free_fn(ctx.filter_data);
 }