t/: migrate helper/test-oidtree.c to unit-tests/t-oidtree.c

helper/test-oidtree.c along with t0069-oidtree.sh test the oidtree.h
library, which is a wrapper around crit-bit tree. Migrate them to
the unit testing framework for better debugging and runtime
performance. Along with the migration, add an extra check for
oidtree_each() test, which showcases how multiple expected matches can
be given to check_each() helper.

To achieve this, introduce a new library called 'lib-oid.h'
exclusively for the unit tests to use. It currently mainly includes
utility to generate object_id from an arbitrary hex string
(i.e. '12a' -> '12a0000000000000000000000000000000000000'). This also
handles the hash algo selection based on GIT_TEST_DEFAULT_HASH.
This library will also be helpful when we port other unit tests such
as oid-array, oidset etc.

Helped-by: Junio C Hamano <[email protected]>
Mentored-by: Christian Couder <[email protected]>
Mentored-by: Kaartic Sivaraam <[email protected]>
Signed-off-by: Ghanshyam Thakkar <[email protected]>
[jc: small fixlets squashed in]
Signed-off-by: Junio C Hamano <[email protected]>

Author: spectre10

Makefile

@@ -811,7 +811,6 @@ TEST_BUILTINS_OBJS += test-mergesort.o
 TEST_BUILTINS_OBJS += test-mktemp.o
 TEST_BUILTINS_OBJS += test-oid-array.o
 TEST_BUILTINS_OBJS += test-oidmap.o
-TEST_BUILTINS_OBJS += test-oidtree.o
 TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-pack-mtimes.o
 TEST_BUILTINS_OBJS += test-parse-options.o
@@ -1335,6 +1334,7 @@ THIRD_PARTY_SOURCES += sha1dc/%
 
 UNIT_TEST_PROGRAMS += t-ctype
 UNIT_TEST_PROGRAMS += t-mem-pool
+UNIT_TEST_PROGRAMS += t-oidtree
 UNIT_TEST_PROGRAMS += t-prio-queue
 UNIT_TEST_PROGRAMS += t-strbuf
 UNIT_TEST_PROGRAMS += t-strcmp-offset
@@ -1343,6 +1343,7 @@ UNIT_TEST_PROGRAMS += t-trailer
 UNIT_TEST_PROGS = $(patsubst %,$(UNIT_TEST_BIN)/%$X,$(UNIT_TEST_PROGRAMS))
 UNIT_TEST_OBJS = $(patsubst %,$(UNIT_TEST_DIR)/%.o,$(UNIT_TEST_PROGRAMS))
 UNIT_TEST_OBJS += $(UNIT_TEST_DIR)/test-lib.o
+UNIT_TEST_OBJS += $(UNIT_TEST_DIR)/lib-oid.o
 
 # xdiff and reftable libs may in turn depend on what is in libgit.a
 GITLIBS = common-main.o $(LIB_FILE) $(XDIFF_LIB) $(REFTABLE_LIB) $(LIB_FILE)
@@ -3883,7 +3884,10 @@ $(FUZZ_PROGRAMS): %: %.o oss-fuzz/dummy-cmd-main.o $(GITLIBS) GIT-LDFLAGS
 		-Wl,--allow-multiple-definition \
 		$(filter %.o,$^) $(filter %.a,$^) $(LIBS) $(LIB_FUZZING_ENGINE)
 
-$(UNIT_TEST_PROGS): $(UNIT_TEST_BIN)/%$X: $(UNIT_TEST_DIR)/%.o $(UNIT_TEST_DIR)/test-lib.o $(GITLIBS) GIT-LDFLAGS
+$(UNIT_TEST_PROGS): $(UNIT_TEST_BIN)/%$X: $(UNIT_TEST_DIR)/%.o \
+	$(UNIT_TEST_DIR)/test-lib.o \
+	$(UNIT_TEST_DIR)/lib-oid.o \
+	$(GITLIBS) GIT-LDFLAGS
 	$(call mkdir_p_parent_template)
 	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) \
 		$(filter %.o,$^) $(filter %.a,$^) $(LIBS)

t/helper/test-oidtree.c

@@ -46,7 +46,6 @@ static struct test_cmd cmds[] = {
 	{ "mktemp", cmd__mktemp },
 	{ "oid-array", cmd__oid_array },
 	{ "oidmap", cmd__oidmap },
-	{ "oidtree", cmd__oidtree },
 	{ "online-cpus", cmd__online_cpus },
 	{ "pack-mtimes", cmd__pack_mtimes },
 	{ "parse-options", cmd__parse_options },

t/helper/test-tool.c

@@ -39,7 +39,6 @@ int cmd__match_trees(int argc, const char **argv);
 int cmd__mergesort(int argc, const char **argv);
 int cmd__mktemp(int argc, const char **argv);
 int cmd__oidmap(int argc, const char **argv);
-int cmd__oidtree(int argc, const char **argv);
 int cmd__online_cpus(int argc, const char **argv);
 int cmd__pack_mtimes(int argc, const char **argv);
 int cmd__parse_options(int argc, const char **argv);

t/helper/test-tool.h

@@ -0,0 +1,52 @@
+#include "test-lib.h"
+#include "lib-oid.h"
+#include "strbuf.h"
+#include "hex.h"
+
+static int init_hash_algo(void)
+{
+	static int algo = -1;
+
+	if (algo < 0) {
+		const char *algo_name = getenv("GIT_TEST_DEFAULT_HASH");
+		algo = algo_name ? hash_algo_by_name(algo_name) : GIT_HASH_SHA1;
+
+		if (!check(algo != GIT_HASH_UNKNOWN))
+			test_msg("BUG: invalid GIT_TEST_DEFAULT_HASH value ('%s')",
+				 algo_name);
+	}
+	return algo;
+}
+
+static int get_oid_arbitrary_hex_algop(const char *hex, struct object_id *oid,
+				       const struct git_hash_algo *algop)
+{
+	int ret;
+	size_t sz = strlen(hex);
+	struct strbuf buf = STRBUF_INIT;
+
+	if (!check(sz <= algop->hexsz)) {
+		test_msg("BUG: hex string (%s) bigger than maximum allowed (%lu)",
+			 hex, (unsigned long)algop->hexsz);
+		return -1;
+	}
+
+	strbuf_add(&buf, hex, sz);
+	strbuf_addchars(&buf, '0', algop->hexsz - sz);
+
+	ret = get_oid_hex_algop(buf.buf, oid, algop);
+	if (!check_int(ret, ==, 0))
+		test_msg("BUG: invalid hex input (%s) provided", hex);
+
+	strbuf_release(&buf);
+	return ret;
+}
+
+int get_oid_arbitrary_hex(const char *hex, struct object_id *oid)
+{
+	int hash_algo = init_hash_algo();
+
+	if (!check_int(hash_algo, !=, GIT_HASH_UNKNOWN))
+		return -1;
+	return get_oid_arbitrary_hex_algop(hex, oid, &hash_algos[hash_algo]);
+}

t/t0069-oidtree.sh

@@ -0,0 +1,17 @@
+#ifndef LIB_OID_H
+#define LIB_OID_H
+
+#include "hash-ll.h"
+
+/*
+ * Convert arbitrary hex string to object_id.
+ * For example, passing "abc12" will generate
+ * "abc1200000000000000000000000000000000000" hex of length 40 for SHA-1 and
+ * create object_id with that.
+ * WARNING: passing a string of length more than the hexsz of respective hash
+ * algo is not allowed. The hash algo is decided based on GIT_TEST_DEFAULT_HASH
+ * environment variable.
+ */
+int get_oid_arbitrary_hex(const char *s, struct object_id *oid);
+
+#endif /* LIB_OID_H */

t/unit-tests/lib-oid.c

@@ -0,0 +1,122 @@
+#include "test-lib.h"
+#include "lib-oid.h"
+#include "oidtree.h"
+#include "hash.h"
+#include "hex.h"
+#include "strvec.h"
+
+#define FILL_TREE(tree, ...)                                       \
+	do {                                                       \
+		const char *hexes[] = { __VA_ARGS__ };             \
+		if (fill_tree_loc(tree, hexes, ARRAY_SIZE(hexes))) \
+			return;                                    \
+	} while (0)
+
+static int fill_tree_loc(struct oidtree *ot, const char *hexes[], size_t n)
+{
+	for (size_t i = 0; i < n; i++) {
+		struct object_id oid;
+		if (!check_int(get_oid_arbitrary_hex(hexes[i], &oid), ==, 0))
+			return -1;
+		oidtree_insert(ot, &oid);
+	}
+	return 0;
+}
+
+static void check_contains(struct oidtree *ot, const char *hex, int expected)
+{
+	struct object_id oid;
+
+	if (!check_int(get_oid_arbitrary_hex(hex, &oid), ==, 0))
+		return;
+	if (!check_int(oidtree_contains(ot, &oid), ==, expected))
+		test_msg("oid: %s", oid_to_hex(&oid));
+}
+
+struct expected_hex_iter {
+	size_t i;
+	struct strvec expected_hexes;
+	const char *query;
+};
+
+static enum cb_next check_each_cb(const struct object_id *oid, void *data)
+{
+	struct expected_hex_iter *hex_iter = data;
+	struct object_id expected;
+
+	if (!check_int(hex_iter->i, <, hex_iter->expected_hexes.nr)) {
+		test_msg("error: extraneous callback for query: ('%s'), object_id: ('%s')",
+			 hex_iter->query, oid_to_hex(oid));
+		return CB_BREAK;
+	}
+
+	if (!check_int(get_oid_arbitrary_hex(hex_iter->expected_hexes.v[hex_iter->i],
+					     &expected), ==, 0))
+		; /* the data is bogus and cannot be used */
+	else if (!check(oideq(oid, &expected)))
+		test_msg("expected: %s\n       got: %s\n     query: %s",
+			 oid_to_hex(&expected), oid_to_hex(oid), hex_iter->query);
+
+	hex_iter->i += 1;
+	return CB_CONTINUE;
+}
+
+LAST_ARG_MUST_BE_NULL
+static void check_each(struct oidtree *ot, const char *query, ...)
+{
+	struct object_id oid;
+	struct expected_hex_iter hex_iter = { .expected_hexes = STRVEC_INIT,
+					      .query = query };
+	const char *arg;
+	va_list hex_args;
+
+	va_start(hex_args, query);
+	while ((arg = va_arg(hex_args, const char *)))
+		strvec_push(&hex_iter.expected_hexes, arg);
+	va_end(hex_args);
+
+	if (!check_int(get_oid_arbitrary_hex(query, &oid), ==, 0))
+		return;
+	oidtree_each(ot, &oid, strlen(query), check_each_cb, &hex_iter);
+
+	if (!check_int(hex_iter.i, ==, hex_iter.expected_hexes.nr))
+		test_msg("error: could not find some 'object_id's for query ('%s')", query);
+	strvec_clear(&hex_iter.expected_hexes);
+}
+
+static void setup(void (*f)(struct oidtree *ot))
+{
+	struct oidtree ot;
+
+	oidtree_init(&ot);
+	f(&ot);
+	oidtree_clear(&ot);
+}
+
+static void t_contains(struct oidtree *ot)
+{
+	FILL_TREE(ot, "444", "1", "2", "3", "4", "5", "a", "b", "c", "d", "e");
+	check_contains(ot, "44", 0);
+	check_contains(ot, "441", 0);
+	check_contains(ot, "440", 0);
+	check_contains(ot, "444", 1);
+	check_contains(ot, "4440", 1);
+	check_contains(ot, "4444", 0);
+}
+
+static void t_each(struct oidtree *ot)
+{
+	FILL_TREE(ot, "f", "9", "8", "123", "321", "320", "a", "b", "c", "d", "e");
+	check_each(ot, "12300", "123", NULL);
+	check_each(ot, "3211", NULL); /* should not reach callback */
+	check_each(ot, "3210", "321", NULL);
+	check_each(ot, "32100", "321", NULL);
+	check_each(ot, "32", "320", "321", NULL);
+}
+
+int cmd_main(int argc UNUSED, const char **argv UNUSED)
+{
+	TEST(setup(t_contains), "oidtree insert and contains works");
+	TEST(setup(t_each), "oidtree each works");
+	return test_done();
+}