t6601: add helper for testing path-walk API

Add some tests based on the current behavior, doing interesting checks
for different sets of branches, ranges, and the --boundary option. This
sets a baseline for the behavior and we can extend it as new options are
introduced.

Store and output a 'batch_nr' value so we can demonstrate that the paths are
grouped together in a batch and not following some other ordering. This
allows us to test the depth-first behavior of the path-walk API. However, we
purposefully do not test the order of the objects in the batch, so the
output is compared to the expected output through a sort.

It is important to mention that the behavior of the API will change soon as
we start to handle UNINTERESTING objects differently, but these tests will
demonstrate the change in behavior.

Signed-off-by: Derrick Stolee <stolee@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/technical/api-path-walk.txt

@@ -42,4 +42,5 @@ commits.
 Examples
 --------
 
-See example usages in future changes.
+See example usages in:
+	`t/helper/test-path-walk.c`

Makefile

@@ -822,6 +822,7 @@ TEST_BUILTINS_OBJS += test-parse-options.o
 TEST_BUILTINS_OBJS += test-parse-pathspec-file.o
 TEST_BUILTINS_OBJS += test-partial-clone.o
 TEST_BUILTINS_OBJS += test-path-utils.o
+TEST_BUILTINS_OBJS += test-path-walk.o
 TEST_BUILTINS_OBJS += test-pcre2-config.o
 TEST_BUILTINS_OBJS += test-pkt-line.o
 TEST_BUILTINS_OBJS += test-proc-receive.o

t/helper/test-path-walk.c

@@ -0,0 +1,84 @@
+#define USE_THE_REPOSITORY_VARIABLE
+
+#include "test-tool.h"
+#include "environment.h"
+#include "hex.h"
+#include "object-name.h"
+#include "object.h"
+#include "pretty.h"
+#include "revision.h"
+#include "setup.h"
+#include "parse-options.h"
+#include "path-walk.h"
+#include "oid-array.h"
+
+static const char * const path_walk_usage[] = {
+	N_("test-tool path-walk <options> -- <revision-options>"),
+	NULL
+};
+
+struct path_walk_test_data {
+	uintmax_t batch_nr;
+	uintmax_t tree_nr;
+	uintmax_t blob_nr;
+};
+
+static int emit_block(const char *path, struct oid_array *oids,
+		      enum object_type type, void *data)
+{
+	struct path_walk_test_data *tdata = data;
+	const char *typestr;
+
+	if (type == OBJ_TREE)
+		tdata->tree_nr += oids->nr;
+	else if (type == OBJ_BLOB)
+		tdata->blob_nr += oids->nr;
+	else
+		BUG("we do not understand this type");
+
+	typestr = type_name(type);
+
+	for (size_t i = 0; i < oids->nr; i++)
+		printf("%"PRIuMAX":%s:%s:%s\n",
+		       tdata->batch_nr, typestr, path,
+		       oid_to_hex(&oids->oid[i]));
+
+	tdata->batch_nr++;
+	return 0;
+}
+
+int cmd__path_walk(int argc, const char **argv)
+{
+	int res;
+	struct rev_info revs = REV_INFO_INIT;
+	struct path_walk_info info = PATH_WALK_INFO_INIT;
+	struct path_walk_test_data data = { 0 };
+	struct option options[] = {
+		OPT_END(),
+	};
+
+	setup_git_directory();
+	revs.repo = the_repository;
+
+	argc = parse_options(argc, argv, NULL,
+			     options, path_walk_usage,
+			     PARSE_OPT_KEEP_UNKNOWN_OPT | PARSE_OPT_KEEP_ARGV0);
+
+	if (argc > 1)
+		setup_revisions(argc, argv, &revs, NULL);
+	else
+		usage(path_walk_usage[0]);
+
+	info.revs = &revs;
+	info.path_fn = emit_block;
+	info.path_fn_data = &data;
+
+	res = walk_objects_by_path(&info);
+
+	printf("trees:%" PRIuMAX "\n"
+	       "blobs:%" PRIuMAX "\n",
+	       data.tree_nr, data.blob_nr);
+
+	release_revisions(&revs);
+	return res;
+}

t/helper/test-tool.c

@@ -52,6 +52,7 @@ static struct test_cmd cmds[] = {
 	{ "parse-subcommand", cmd__parse_subcommand },
 	{ "partial-clone", cmd__partial_clone },
 	{ "path-utils", cmd__path_utils },
+	{ "path-walk", cmd__path_walk },
 	{ "pcre2-config", cmd__pcre2_config },
 	{ "pkt-line", cmd__pkt_line },
 	{ "proc-receive", cmd__proc_receive },

t/helper/test-tool.h

@@ -45,6 +45,7 @@ int cmd__parse_pathspec_file(int argc, const char** argv);
 int cmd__parse_subcommand(int argc, const char **argv);
 int cmd__partial_clone(int argc, const char **argv);
 int cmd__path_utils(int argc, const char **argv);
+int cmd__path_walk(int argc, const char **argv);
 int cmd__pcre2_config(int argc, const char **argv);
 int cmd__pkt_line(int argc, const char **argv);
 int cmd__proc_receive(int argc, const char **argv);

t/t6601-path-walk.sh

@@ -0,0 +1,120 @@
+#!/bin/sh
+
+TEST_PASSES_SANITIZE_LEAK=true
+
+test_description='direct path-walk API tests'
+
+. ./test-lib.sh
+
+test_expect_success 'setup test repository' '
+	git checkout -b base &&
+
+	mkdir left &&
+	mkdir right &&
+	echo a >a &&
+	echo b >left/b &&
+	echo c >right/c &&
+	git add . &&
+	git commit -m "first" &&
+
+	echo d >right/d &&
+	git add right &&
+	git commit -m "second" &&
+
+	echo bb >left/b &&
+	git commit -a -m "third" &&
+
+	git checkout -b topic HEAD~1 &&
+	echo cc >right/c &&
+	git commit -a -m "topic"
+'
+
+test_expect_success 'all' '
+	test-tool path-walk -- --all >out &&
+
+	cat >expect <<-EOF &&
+	0:tree::$(git rev-parse topic^{tree})
+	0:tree::$(git rev-parse base^{tree})
+	0:tree::$(git rev-parse base~1^{tree})
+	0:tree::$(git rev-parse base~2^{tree})
+	1:tree:right/:$(git rev-parse topic:right)
+	1:tree:right/:$(git rev-parse base~1:right)
+	1:tree:right/:$(git rev-parse base~2:right)
+	2:blob:right/d:$(git rev-parse base~1:right/d)
+	3:blob:right/c:$(git rev-parse base~2:right/c)
+	3:blob:right/c:$(git rev-parse topic:right/c)
+	4:tree:left/:$(git rev-parse base:left)
+	4:tree:left/:$(git rev-parse base~2:left)
+	5:blob:left/b:$(git rev-parse base~2:left/b)
+	5:blob:left/b:$(git rev-parse base:left/b)
+	6:blob:a:$(git rev-parse base~2:a)
+	blobs:6
+	trees:9
+	EOF
+
+	test_cmp_sorted expect out
+'
+
+test_expect_success 'topic only' '
+	test-tool path-walk -- topic >out &&
+
+	cat >expect <<-EOF &&
+	0:tree::$(git rev-parse topic^{tree})
+	0:tree::$(git rev-parse base~1^{tree})
+	0:tree::$(git rev-parse base~2^{tree})
+	1:tree:right/:$(git rev-parse topic:right)
+	1:tree:right/:$(git rev-parse base~1:right)
+	1:tree:right/:$(git rev-parse base~2:right)
+	2:blob:right/d:$(git rev-parse base~1:right/d)
+	3:blob:right/c:$(git rev-parse base~2:right/c)
+	3:blob:right/c:$(git rev-parse topic:right/c)
+	4:tree:left/:$(git rev-parse base~2:left)
+	5:blob:left/b:$(git rev-parse base~2:left/b)
+	6:blob:a:$(git rev-parse base~2:a)
+	blobs:5
+	trees:7
+	EOF
+
+	test_cmp_sorted expect out
+'
+
+test_expect_success 'topic, not base' '
+	test-tool path-walk -- topic --not base >out &&
+
+	cat >expect <<-EOF &&
+	0:tree::$(git rev-parse topic^{tree})
+	1:tree:right/:$(git rev-parse topic:right)
+	2:blob:right/d:$(git rev-parse topic:right/d)
+	3:blob:right/c:$(git rev-parse topic:right/c)
+	4:tree:left/:$(git rev-parse topic:left)
+	5:blob:left/b:$(git rev-parse topic:left/b)
+	6:blob:a:$(git rev-parse topic:a)
+	blobs:4
+	trees:3
+	EOF
+
+	test_cmp_sorted expect out
+'
+
+test_expect_success 'topic, not base, boundary' '
+	test-tool path-walk -- --boundary topic --not base >out &&
+
+	cat >expect <<-EOF &&
+	0:tree::$(git rev-parse topic^{tree})
+	0:tree::$(git rev-parse base~1^{tree})
+	1:tree:right/:$(git rev-parse topic:right)
+	1:tree:right/:$(git rev-parse base~1:right)
+	2:blob:right/d:$(git rev-parse base~1:right/d)
+	3:blob:right/c:$(git rev-parse base~1:right/c)
+	3:blob:right/c:$(git rev-parse topic:right/c)
+	4:tree:left/:$(git rev-parse base~1:left)
+	5:blob:left/b:$(git rev-parse base~1:left/b)
+	6:blob:a:$(git rev-parse base~1:a)
+	blobs:5
+	trees:5
+	EOF
+
+	test_cmp_sorted expect out
+'
+
+test_done