[WORK-IN-PROGRESS] Introduce the path walk API into Git for Windows

Documentation/git-backfill.txt

@@ -9,7 +9,7 @@ git-backfill - Download missing objects in a partial clone
 SYNOPSIS
 --------
 [verse]
-'git backfill' [--batch-size=<n>]
+'git backfill' [--batch-size=<n>] [--[no-]sparse]
 
 DESCRIPTION
 -----------
@@ -46,6 +46,10 @@ OPTIONS
 	from the server. This size may be exceeded by the last set of
 	blobs seen at a given path. Default batch size is 16,000.
 
+--[no-]sparse::
+	Only download objects if they appear at a path that matches the
+	current sparse-checkout.
+
 SEE ALSO
 --------
 linkgit:git-clone[1].

builtin/backfill.c

@@ -4,6 +4,7 @@
 #include "parse-options.h"
 #include "repository.h"
 #include "commit.h"
+#include "dir.h"
 #include "hex.h"
 #include "tree.h"
 #include "tree-walk.h"
@@ -21,14 +22,15 @@
 #include "path-walk.h"
 
 static const char * const builtin_backfill_usage[] = {
-	N_("git backfill [--batch-size=<n>]"),
+	N_("git backfill [--batch-size=<n>] [--[no-]sparse]"),
 	NULL
 };
 
 struct backfill_context {
 	struct repository *repo;
 	struct oid_array current_batch;
 	size_t batch_size;
+	int sparse;
 };
 
 static void clear_backfill_context(struct backfill_context *ctx)
@@ -84,6 +86,12 @@ static int do_backfill(struct backfill_context *ctx)
 	struct path_walk_info info = PATH_WALK_INFO_INIT;
 	int ret;
 
+	if (ctx->sparse) {
+		CALLOC_ARRAY(info.pl, 1);
+		if (get_sparse_checkout_patterns(info.pl))
+			return error(_("problem loading sparse-checkout"));
+	}
+
 	repo_init_revisions(ctx->repo, &revs, "");
 	handle_revision_arg("HEAD", &revs, 0, 0);
 
@@ -107,10 +115,13 @@ int cmd_backfill(int argc, const char **argv, const char *prefix)
 		.repo = the_repository,
 		.current_batch = OID_ARRAY_INIT,
 		.batch_size = 16000,
+		.sparse = 0,
 	};
 	struct option options[] = {
 		OPT_INTEGER(0, "batch-size", &ctx.batch_size,
 			    N_("Minimun number of objects to request at a time")),
+		OPT_BOOL(0, "sparse", &ctx.sparse,
+			 N_("Restrict the missing objects to the current sparse-checkout")),
 		OPT_END(),
 	};
 

path-walk.c

@@ -10,6 +10,7 @@
 #include "hex.h"
 #include "object.h"
 #include "oid-array.h"
+#include "repository.h"
 #include "revision.h"
 #include "string-list.h"
 #include "strmap.h"
@@ -111,6 +112,23 @@ static int add_children(struct path_walk_context *ctx,
 		if (type == OBJ_TREE)
 			strbuf_addch(&path, '/');
 
+		if (ctx->info->pl) {
+			int dtype;
+			enum pattern_match_result match;
+			match = path_matches_pattern_list(path.buf, path.len,
+							  path.buf + base_len, &dtype,
+							  ctx->info->pl,
+							  ctx->repo->index);
+
+			if (ctx->info->pl->use_cone_patterns &&
+			    match == NOT_MATCHED)
+				continue;
+			else if (!ctx->info->pl->use_cone_patterns &&
+				 type == OBJ_BLOB &&
+				 match != MATCHED)
+				continue;
+		}
+
 		if (!(list = strmap_get(&ctx->paths_to_lists, path.buf))) {
 			CALLOC_ARRAY(list, 1);
 			list->type = type;

path-walk.h

@@ -6,6 +6,7 @@
 
 struct rev_info;
 struct oid_array;
+struct pattern_list;
 
 /**
  * The type of a function pointer for the method that is called on a list of
@@ -30,6 +31,16 @@ struct path_walk_info {
 	 */
 	path_fn path_fn;
 	void *path_fn_data;
+
+	/**
+	 * Specify a sparse-checkout definition to match our paths to. Do not
+	 * walk outside of this sparse definition. If the patterns are in
+	 * cone mode, then the search may prune directories that are outside
+	 * of the cone. If not in cone mode, then all tree paths will be
+	 * explored but the path_fn will only be called when the path matches
+	 * the sparse-checkout patterns.
+	 */
+	struct pattern_list *pl;
 };
 
 #define PATH_WALK_INFO_INIT { 0 }

t/t5620-backfill.sh

@@ -80,6 +80,61 @@ test_expect_success 'do partial clone 2, backfill batch size' '
 	test_line_count = 0 revs2
 '
 
+test_expect_success 'backfill --sparse' '
+	git clone --sparse --filter=blob:none		\
+		--single-branch --branch=main 		\
+		"file://$(pwd)/srv.bare" backfill3 &&
+
+	# Initial checkout includes four files at root.
+	git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 44 missing &&
+
+	# Initial sparse-checkout is just the files at root, so we get the
+	# older versions of the four files at tip.
+	GIT_TRACE2_EVENT="$(pwd)/sparse-trace1" git \
+		-C backfill3 backfill --sparse &&
+	test_trace2_data promisor fetch_count 4 <sparse-trace1 &&
+	test_trace2_data path-walk paths 5 <sparse-trace1 &&
+	git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 40 missing &&
+
+	# Expand the sparse-checkout to include 'd' recursively. This
+	# engages the algorithm to skip the trees for 'a'. Note that
+	# the "sparse-checkout set" command downloads the objects at tip
+	# to satisfy the current checkout.
+	git -C backfill3 sparse-checkout set d &&
+	GIT_TRACE2_EVENT="$(pwd)/sparse-trace2" git \
+		-C backfill3 backfill --sparse &&
+	test_trace2_data promisor fetch_count 8 <sparse-trace2 &&
+	test_trace2_data path-walk paths 15 <sparse-trace2 &&
+	git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 24 missing
+'
+
+test_expect_success 'backfill --sparse without cone mode' '
+	git clone --no-checkout --filter=blob:none		\
+		--single-branch --branch=main 		\
+		"file://$(pwd)/srv.bare" backfill4 &&
+
+	# No blobs yet
+	git -C backfill4 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	# Define sparse-checkout by filename regardless of parent directory.
+	# This downloads 6 blobs to satisfy the checkout.
+	git -C backfill4 sparse-checkout set --no-cone "**/file.1.txt" &&
+	git -C backfill4 checkout main &&
+
+	GIT_TRACE2_EVENT="$(pwd)/no-cone-trace1" git \
+		-C backfill4 backfill --sparse &&
+	test_trace2_data promisor fetch_count 6 <no-cone-trace1 &&
+
+	# This walk needed to visit all directories to search for these paths.
+	test_trace2_data path-walk paths 12 <no-cone-trace1 &&
+	git -C backfill4 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 36 missing
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd