about summary refs log tree commit diff
path: root/t/helper
diff options
context:
space:
mode:
authorVincent Ambo <Vincent Ambo>2020-01-11T23·36+0000
committerVincent Ambo <Vincent Ambo>2020-01-11T23·36+0000
commit1b593e1ea4d2af0f6444d9a7788d5d99abd6fde5 (patch)
treee3accb9beed5c4c1b5a05c99db71ab2841f0ed04 /t/helper
Squashed 'third_party/git/' content from commit cb71568594
git-subtree-dir: third_party/git
git-subtree-split: cb715685942260375e1eb8153b0768a376e4ece7
Diffstat (limited to 't/helper')
-rw-r--r--t/helper/.gitignore5
-rw-r--r--t/helper/test-chmtime.c148
-rw-r--r--t/helper/test-config.c208
-rw-r--r--t/helper/test-ctype.c43
-rw-r--r--t/helper/test-date.c141
-rw-r--r--t/helper/test-delta.c79
-rw-r--r--t/helper/test-dir-iterator.c65
-rw-r--r--t/helper/test-drop-caches.c157
-rw-r--r--t/helper/test-dump-cache-tree.c69
-rw-r--r--t/helper/test-dump-fsmonitor.c22
-rw-r--r--t/helper/test-dump-split-index.c37
-rw-r--r--t/helper/test-dump-untracked-cache.c66
-rw-r--r--t/helper/test-example-decorate.c75
-rw-r--r--t/helper/test-fake-ssh.c30
-rw-r--r--t/helper/test-genrandom.c34
-rw-r--r--t/helper/test-genzeros.c21
-rw-r--r--t/helper/test-hash-speed.c61
-rw-r--r--t/helper/test-hash.c58
-rw-r--r--t/helper/test-hashmap.c263
-rw-r--r--t/helper/test-index-version.c15
-rw-r--r--t/helper/test-json-writer.c565
-rw-r--r--t/helper/test-lazy-init-name-hash.c265
-rw-r--r--t/helper/test-line-buffer.c81
-rw-r--r--t/helper/test-match-trees.c27
-rw-r--r--t/helper/test-mergesort.c53
-rw-r--r--t/helper/test-mktemp.c15
-rw-r--r--t/helper/test-oidmap.c112
-rw-r--r--t/helper/test-online-cpus.c9
-rw-r--r--t/helper/test-parse-options.c188
-rw-r--r--t/helper/test-path-utils.c361
-rw-r--r--t/helper/test-pkt-line.c98
-rw-r--r--t/helper/test-prio-queue.c50
-rw-r--r--t/helper/test-reach.c168
-rw-r--r--t/helper/test-read-cache.c37
-rw-r--r--t/helper/test-read-midx.c51
-rw-r--r--t/helper/test-ref-store.c299
-rw-r--r--t/helper/test-regex.c76
-rw-r--r--t/helper/test-repository.c98
-rw-r--r--t/helper/test-revision-walking.c69
-rw-r--r--t/helper/test-run-command.c97
-rw-r--r--t/helper/test-scrap-cache-tree.c19
-rw-r--r--t/helper/test-serve-v2.c31
-rw-r--r--t/helper/test-sha1-array.c36
-rw-r--r--t/helper/test-sha1.c7
-rwxr-xr-xt/helper/test-sha1.sh83
-rw-r--r--t/helper/test-sha256.c7
-rw-r--r--t/helper/test-sigchain.c24
-rw-r--r--t/helper/test-strcmp-offset.c23
-rw-r--r--t/helper/test-string-list.c129
-rw-r--r--t/helper/test-submodule-config.c73
-rw-r--r--t/helper/test-submodule-nested-repo-config.c32
-rw-r--r--t/helper/test-subprocess.c20
-rw-r--r--t/helper/test-svn-fe.c52
-rw-r--r--t/helper/test-tool.c116
-rw-r--r--t/helper/test-tool.h65
-rw-r--r--t/helper/test-trace2.c273
-rw-r--r--t/helper/test-urlmatch-normalization.c51
-rw-r--r--t/helper/test-wildmatch.c24
-rw-r--r--t/helper/test-windows-named-pipe.c72
-rw-r--r--t/helper/test-write-cache.c20
-rw-r--r--t/helper/test-xml-encode.c80
61 files changed, 5553 insertions, 0 deletions
diff --git a/t/helper/.gitignore b/t/helper/.gitignore
new file mode 100644
index 000000000000..2bad28af9241
--- /dev/null
+++ b/t/helper/.gitignore
@@ -0,0 +1,5 @@
+*
+!*.sh
+!*.[ch]
+!*.gitignore
+
diff --git a/t/helper/test-chmtime.c b/t/helper/test-chmtime.c
new file mode 100644
index 000000000000..aa22af48c2a6
--- /dev/null
+++ b/t/helper/test-chmtime.c
@@ -0,0 +1,148 @@
+/*
+ * This program can either change modification time of the given
+ * file(s) or just print it. The program does not change atime or
+ * ctime (their values are explicitly preserved).
+ *
+ * The mtime can be changed to an absolute value:
+ *
+ *	test-tool chmtime =<seconds> file...
+ *
+ * Relative to the current time as returned by time(3):
+ *
+ *	test-tool chmtime =+<seconds> (or =-<seconds>) file...
+ *
+ * Or relative to the current mtime of the file:
+ *
+ *	test-tool chmtime <seconds> file...
+ *	test-tool chmtime +<seconds> (or -<seconds>) file...
+ *
+ * Examples:
+ *
+ * To print the mtime and the file name use --verbose and set
+ * the file mtime offset to 0:
+ *
+ *	test-tool chmtime -v +0 file
+ *
+ * To print only the mtime use --get:
+ *
+ *	test-tool chmtime --get file
+ *
+ * To set the mtime to current time:
+ *
+ *	test-tool chmtime =+0 file
+ *
+ * To set the file mtime offset to +1 and print the new value:
+ *
+ *	test-tool chmtime --get +1 file
+ *
+ */
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include <utime.h>
+
+static const char usage_str[] =
+	"(-v|--verbose|-g|--get) (+|=|=+|=-|-)<seconds> <file>...";
+
+static int timespec_arg(const char *arg, long int *set_time, int *set_eq)
+{
+	char *test;
+	const char *timespec = arg;
+	*set_eq = (*timespec == '=') ? 1 : 0;
+	if (*set_eq) {
+		timespec++;
+		if (*timespec == '+') {
+			*set_eq = 2; /* relative "in the future" */
+			timespec++;
+		}
+	}
+	*set_time = strtol(timespec, &test, 10);
+	if (*test) {
+		return 0;
+	}
+	if ((*set_eq && *set_time < 0) || *set_eq == 2) {
+		time_t now = time(NULL);
+		*set_time += now;
+	}
+	return 1;
+}
+
+int cmd__chmtime(int argc, const char **argv)
+{
+	static int verbose;
+	static int get;
+
+	int i = 1;
+	/* no mtime change by default */
+	int set_eq = 0;
+	long int set_time = 0;
+
+	if (argc < 3)
+		goto usage;
+
+	if (strcmp(argv[i], "--get") == 0 || strcmp(argv[i], "-g") == 0) {
+		get = 1;
+		++i;
+	} else if (strcmp(argv[i], "--verbose") == 0 || strcmp(argv[i], "-v") == 0) {
+		verbose = 1;
+		++i;
+	}
+
+	if (i == argc) {
+		goto usage;
+	}
+
+	if (timespec_arg(argv[i], &set_time, &set_eq)) {
+		++i;
+	} else {
+		if (get == 0) {
+			fprintf(stderr, "Not a base-10 integer: %s\n", argv[i] + 1);
+			goto usage;
+		}
+	}
+
+	if (i == argc)
+		goto usage;
+
+	for (; i < argc; i++) {
+		struct stat sb;
+		struct utimbuf utb;
+		uintmax_t mtime;
+
+		if (stat(argv[i], &sb) < 0) {
+			fprintf(stderr, "Failed to stat %s: %s\n",
+			        argv[i], strerror(errno));
+			return 1;
+		}
+
+#ifdef GIT_WINDOWS_NATIVE
+		if (!(sb.st_mode & S_IWUSR) &&
+				chmod(argv[i], sb.st_mode | S_IWUSR)) {
+			fprintf(stderr, "Could not make user-writable %s: %s",
+				argv[i], strerror(errno));
+			return 1;
+		}
+#endif
+
+		utb.actime = sb.st_atime;
+		utb.modtime = set_eq ? set_time : sb.st_mtime + set_time;
+
+		mtime = utb.modtime < 0 ? 0: utb.modtime;
+		if (get) {
+			printf("%"PRIuMAX"\n", mtime);
+		} else if (verbose) {
+			printf("%"PRIuMAX"\t%s\n", mtime, argv[i]);
+		}
+
+		if (utb.modtime != sb.st_mtime && utime(argv[i], &utb) < 0) {
+			fprintf(stderr, "Failed to modify time on %s: %s\n",
+			        argv[i], strerror(errno));
+			return 1;
+		}
+	}
+
+	return 0;
+
+usage:
+	fprintf(stderr, "usage: %s %s\n", argv[0], usage_str);
+	return 1;
+}
diff --git a/t/helper/test-config.c b/t/helper/test-config.c
new file mode 100644
index 000000000000..214003d5b2f9
--- /dev/null
+++ b/t/helper/test-config.c
@@ -0,0 +1,208 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "config.h"
+#include "string-list.h"
+
+/*
+ * This program exposes the C API of the configuration mechanism
+ * as a set of simple commands in order to facilitate testing.
+ *
+ * Reads stdin and prints result of command to stdout:
+ *
+ * get_value -> prints the value with highest priority for the entered key
+ *
+ * get_value_multi -> prints all values for the entered key in increasing order
+ *		     of priority
+ *
+ * get_int -> print integer value for the entered key or die
+ *
+ * get_bool -> print bool value for the entered key or die
+ *
+ * get_string -> print string value for the entered key or die
+ *
+ * configset_get_value -> returns value with the highest priority for the entered key
+ * 			from a config_set constructed from files entered as arguments.
+ *
+ * configset_get_value_multi -> returns value_list for the entered key sorted in
+ * 				ascending order of priority from a config_set
+ * 				constructed from files entered as arguments.
+ *
+ * iterate -> iterate over all values using git_config(), and print some
+ *            data for each
+ *
+ * Examples:
+ *
+ * To print the value with highest priority for key "foo.bAr Baz.rock":
+ * 	test-tool config get_value "foo.bAr Baz.rock"
+ *
+ */
+
+static const char *scope_name(enum config_scope scope)
+{
+	switch (scope) {
+	case CONFIG_SCOPE_SYSTEM:
+		return "system";
+	case CONFIG_SCOPE_GLOBAL:
+		return "global";
+	case CONFIG_SCOPE_REPO:
+		return "repo";
+	case CONFIG_SCOPE_CMDLINE:
+		return "cmdline";
+	default:
+		return "unknown";
+	}
+}
+static int iterate_cb(const char *var, const char *value, void *data)
+{
+	static int nr;
+
+	if (nr++)
+		putchar('\n');
+
+	printf("key=%s\n", var);
+	printf("value=%s\n", value ? value : "(null)");
+	printf("origin=%s\n", current_config_origin_type());
+	printf("name=%s\n", current_config_name());
+	printf("scope=%s\n", scope_name(current_config_scope()));
+
+	return 0;
+}
+
+static int early_config_cb(const char *var, const char *value, void *vdata)
+{
+	const char *key = vdata;
+
+	if (!strcmp(key, var))
+		printf("%s\n", value);
+
+	return 0;
+}
+
+int cmd__config(int argc, const char **argv)
+{
+	int i, val;
+	const char *v;
+	const struct string_list *strptr;
+	struct config_set cs;
+
+	if (argc == 3 && !strcmp(argv[1], "read_early_config")) {
+		read_early_config(early_config_cb, (void *)argv[2]);
+		return 0;
+	}
+
+	setup_git_directory();
+
+	git_configset_init(&cs);
+
+	if (argc < 2) {
+		fprintf(stderr, "Please, provide a command name on the command-line\n");
+		goto exit1;
+	} else if (argc == 3 && !strcmp(argv[1], "get_value")) {
+		if (!git_config_get_value(argv[2], &v)) {
+			if (!v)
+				printf("(NULL)\n");
+			else
+				printf("%s\n", v);
+			goto exit0;
+		} else {
+			printf("Value not found for \"%s\"\n", argv[2]);
+			goto exit1;
+		}
+	} else if (argc == 3 && !strcmp(argv[1], "get_value_multi")) {
+		strptr = git_config_get_value_multi(argv[2]);
+		if (strptr) {
+			for (i = 0; i < strptr->nr; i++) {
+				v = strptr->items[i].string;
+				if (!v)
+					printf("(NULL)\n");
+				else
+					printf("%s\n", v);
+			}
+			goto exit0;
+		} else {
+			printf("Value not found for \"%s\"\n", argv[2]);
+			goto exit1;
+		}
+	} else if (argc == 3 && !strcmp(argv[1], "get_int")) {
+		if (!git_config_get_int(argv[2], &val)) {
+			printf("%d\n", val);
+			goto exit0;
+		} else {
+			printf("Value not found for \"%s\"\n", argv[2]);
+			goto exit1;
+		}
+	} else if (argc == 3 && !strcmp(argv[1], "get_bool")) {
+		if (!git_config_get_bool(argv[2], &val)) {
+			printf("%d\n", val);
+			goto exit0;
+		} else {
+			printf("Value not found for \"%s\"\n", argv[2]);
+			goto exit1;
+		}
+	} else if (argc == 3 && !strcmp(argv[1], "get_string")) {
+		if (!git_config_get_string_const(argv[2], &v)) {
+			printf("%s\n", v);
+			goto exit0;
+		} else {
+			printf("Value not found for \"%s\"\n", argv[2]);
+			goto exit1;
+		}
+	} else if (!strcmp(argv[1], "configset_get_value")) {
+		for (i = 3; i < argc; i++) {
+			int err;
+			if ((err = git_configset_add_file(&cs, argv[i]))) {
+				fprintf(stderr, "Error (%d) reading configuration file %s.\n", err, argv[i]);
+				goto exit2;
+			}
+		}
+		if (!git_configset_get_value(&cs, argv[2], &v)) {
+			if (!v)
+				printf("(NULL)\n");
+			else
+				printf("%s\n", v);
+			goto exit0;
+		} else {
+			printf("Value not found for \"%s\"\n", argv[2]);
+			goto exit1;
+		}
+	} else if (!strcmp(argv[1], "configset_get_value_multi")) {
+		for (i = 3; i < argc; i++) {
+			int err;
+			if ((err = git_configset_add_file(&cs, argv[i]))) {
+				fprintf(stderr, "Error (%d) reading configuration file %s.\n", err, argv[i]);
+				goto exit2;
+			}
+		}
+		strptr = git_configset_get_value_multi(&cs, argv[2]);
+		if (strptr) {
+			for (i = 0; i < strptr->nr; i++) {
+				v = strptr->items[i].string;
+				if (!v)
+					printf("(NULL)\n");
+				else
+					printf("%s\n", v);
+			}
+			goto exit0;
+		} else {
+			printf("Value not found for \"%s\"\n", argv[2]);
+			goto exit1;
+		}
+	} else if (!strcmp(argv[1], "iterate")) {
+		git_config(iterate_cb, NULL);
+		goto exit0;
+	}
+
+	die("%s: Please check the syntax and the function name", argv[0]);
+
+exit0:
+	git_configset_clear(&cs);
+	return 0;
+
+exit1:
+	git_configset_clear(&cs);
+	return 1;
+
+exit2:
+	git_configset_clear(&cs);
+	return 2;
+}
diff --git a/t/helper/test-ctype.c b/t/helper/test-ctype.c
new file mode 100644
index 000000000000..92c4c2313e78
--- /dev/null
+++ b/t/helper/test-ctype.c
@@ -0,0 +1,43 @@
+#include "test-tool.h"
+#include "cache.h"
+
+static int rc;
+
+static void report_error(const char *class, int ch)
+{
+	printf("%s classifies char %d (0x%02x) wrongly\n", class, ch, ch);
+	rc = 1;
+}
+
+static int is_in(const char *s, int ch)
+{
+	/* We can't find NUL using strchr.  It's classless anyway. */
+	if (ch == '\0')
+		return 0;
+	return !!strchr(s, ch);
+}
+
+#define TEST_CLASS(t,s) {			\
+	int i;					\
+	for (i = 0; i < 256; i++) {		\
+		if (is_in(s, i) != t(i))	\
+			report_error(#t, i);	\
+	}					\
+}
+
+#define DIGIT "0123456789"
+#define LOWER "abcdefghijklmnopqrstuvwxyz"
+#define UPPER "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+
+int cmd__ctype(int argc, const char **argv)
+{
+	TEST_CLASS(isdigit, DIGIT);
+	TEST_CLASS(isspace, " \n\r\t");
+	TEST_CLASS(isalpha, LOWER UPPER);
+	TEST_CLASS(isalnum, LOWER UPPER DIGIT);
+	TEST_CLASS(is_glob_special, "*?[\\");
+	TEST_CLASS(is_regex_special, "$()*+.?[\\^{|");
+	TEST_CLASS(is_pathspec_magic, "!\"#%&',-/:;<=>@_`~");
+
+	return rc;
+}
diff --git a/t/helper/test-date.c b/t/helper/test-date.c
new file mode 100644
index 000000000000..585347ea487a
--- /dev/null
+++ b/t/helper/test-date.c
@@ -0,0 +1,141 @@
+#include "test-tool.h"
+#include "cache.h"
+
+static const char *usage_msg = "\n"
+"  test-tool date relative [time_t]...\n"
+"  test-tool date human [time_t]...\n"
+"  test-tool date show:<format> [time_t]...\n"
+"  test-tool date parse [date]...\n"
+"  test-tool date approxidate [date]...\n"
+"  test-tool date timestamp [date]...\n"
+"  test-tool date getnanos [start-nanos]\n"
+"  test-tool date is64bit\n"
+"  test-tool date time_t-is64bit\n";
+
+static void show_relative_dates(const char **argv, struct timeval *now)
+{
+	struct strbuf buf = STRBUF_INIT;
+
+	for (; *argv; argv++) {
+		time_t t = atoi(*argv);
+		show_date_relative(t, now, &buf);
+		printf("%s -> %s\n", *argv, buf.buf);
+	}
+	strbuf_release(&buf);
+}
+
+static void show_human_dates(const char **argv)
+{
+	for (; *argv; argv++) {
+		time_t t = atoi(*argv);
+		printf("%s -> %s\n", *argv, show_date(t, 0, DATE_MODE(HUMAN)));
+	}
+}
+
+static void show_dates(const char **argv, const char *format)
+{
+	struct date_mode mode;
+
+	parse_date_format(format, &mode);
+	for (; *argv; argv++) {
+		char *arg;
+		timestamp_t t;
+		int tz;
+
+		/*
+		 * Do not use our normal timestamp parsing here, as the point
+		 * is to test the formatting code in isolation.
+		 */
+		t = parse_timestamp(*argv, &arg, 10);
+		while (*arg == ' ')
+			arg++;
+		tz = atoi(arg);
+
+		printf("%s -> %s\n", *argv, show_date(t, tz, &mode));
+	}
+}
+
+static void parse_dates(const char **argv)
+{
+	struct strbuf result = STRBUF_INIT;
+
+	for (; *argv; argv++) {
+		timestamp_t t;
+		int tz;
+
+		strbuf_reset(&result);
+		parse_date(*argv, &result);
+		if (sscanf(result.buf, "%"PRItime" %d", &t, &tz) == 2)
+			printf("%s -> %s\n",
+			       *argv, show_date(t, tz, DATE_MODE(ISO8601)));
+		else
+			printf("%s -> bad\n", *argv);
+	}
+	strbuf_release(&result);
+}
+
+static void parse_approxidate(const char **argv, struct timeval *now)
+{
+	for (; *argv; argv++) {
+		timestamp_t t;
+		t = approxidate_relative(*argv, now);
+		printf("%s -> %s\n", *argv, show_date(t, 0, DATE_MODE(ISO8601)));
+	}
+}
+
+static void parse_approx_timestamp(const char **argv, struct timeval *now)
+{
+	for (; *argv; argv++) {
+		timestamp_t t;
+		t = approxidate_relative(*argv, now);
+		printf("%s -> %"PRItime"\n", *argv, t);
+	}
+}
+
+static void getnanos(const char **argv)
+{
+	double seconds = getnanotime() / 1.0e9;
+
+	if (*argv)
+		seconds -= strtod(*argv, NULL);
+	printf("%lf\n", seconds);
+}
+
+int cmd__date(int argc, const char **argv)
+{
+	struct timeval now;
+	const char *x;
+
+	x = getenv("GIT_TEST_DATE_NOW");
+	if (x) {
+		now.tv_sec = atoi(x);
+		now.tv_usec = 0;
+	}
+	else
+		gettimeofday(&now, NULL);
+
+	argv++;
+	if (!*argv)
+		usage(usage_msg);
+	if (!strcmp(*argv, "relative"))
+		show_relative_dates(argv+1, &now);
+	else if (!strcmp(*argv, "human"))
+		show_human_dates(argv+1);
+	else if (skip_prefix(*argv, "show:", &x))
+		show_dates(argv+1, x);
+	else if (!strcmp(*argv, "parse"))
+		parse_dates(argv+1);
+	else if (!strcmp(*argv, "approxidate"))
+		parse_approxidate(argv+1, &now);
+	else if (!strcmp(*argv, "timestamp"))
+		parse_approx_timestamp(argv+1, &now);
+	else if (!strcmp(*argv, "getnanos"))
+		getnanos(argv+1);
+	else if (!strcmp(*argv, "is64bit"))
+		return sizeof(timestamp_t) == 8 ? 0 : 1;
+	else if (!strcmp(*argv, "time_t-is64bit"))
+		return sizeof(time_t) == 8 ? 0 : 1;
+	else
+		usage(usage_msg);
+	return 0;
+}
diff --git a/t/helper/test-delta.c b/t/helper/test-delta.c
new file mode 100644
index 000000000000..e749a49c88e6
--- /dev/null
+++ b/t/helper/test-delta.c
@@ -0,0 +1,79 @@
+/*
+ * test-delta.c: test code to exercise diff-delta.c and patch-delta.c
+ *
+ * (C) 2005 Nicolas Pitre <nico@fluxnic.net>
+ *
+ * This code is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "delta.h"
+#include "cache.h"
+
+static const char usage_str[] =
+	"test-tool delta (-d|-p) <from_file> <data_file> <out_file>";
+
+int cmd__delta(int argc, const char **argv)
+{
+	int fd;
+	struct stat st;
+	void *from_buf, *data_buf, *out_buf;
+	unsigned long from_size, data_size, out_size;
+
+	if (argc != 5 || (strcmp(argv[1], "-d") && strcmp(argv[1], "-p"))) {
+		fprintf(stderr, "usage: %s\n", usage_str);
+		return 1;
+	}
+
+	fd = open(argv[2], O_RDONLY);
+	if (fd < 0 || fstat(fd, &st)) {
+		perror(argv[2]);
+		return 1;
+	}
+	from_size = st.st_size;
+	from_buf = xmalloc(from_size);
+	if (read_in_full(fd, from_buf, from_size) < 0) {
+		perror(argv[2]);
+		close(fd);
+		return 1;
+	}
+	close(fd);
+
+	fd = open(argv[3], O_RDONLY);
+	if (fd < 0 || fstat(fd, &st)) {
+		perror(argv[3]);
+		return 1;
+	}
+	data_size = st.st_size;
+	data_buf = xmalloc(data_size);
+	if (read_in_full(fd, data_buf, data_size) < 0) {
+		perror(argv[3]);
+		close(fd);
+		return 1;
+	}
+	close(fd);
+
+	if (argv[1][1] == 'd')
+		out_buf = diff_delta(from_buf, from_size,
+				     data_buf, data_size,
+				     &out_size, 0);
+	else
+		out_buf = patch_delta(from_buf, from_size,
+				      data_buf, data_size,
+				      &out_size);
+	if (!out_buf) {
+		fprintf(stderr, "delta operation failed (returned NULL)\n");
+		return 1;
+	}
+
+	fd = open (argv[4], O_WRONLY|O_CREAT|O_TRUNC, 0666);
+	if (fd < 0 || write_in_full(fd, out_buf, out_size) < 0) {
+		perror(argv[4]);
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/t/helper/test-dir-iterator.c b/t/helper/test-dir-iterator.c
new file mode 100644
index 000000000000..659b6bfa81df
--- /dev/null
+++ b/t/helper/test-dir-iterator.c
@@ -0,0 +1,65 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "strbuf.h"
+#include "iterator.h"
+#include "dir-iterator.h"
+
+static const char *error_name(int error_number)
+{
+	switch (error_number) {
+	case ENOENT: return "ENOENT";
+	case ENOTDIR: return "ENOTDIR";
+	default: return "ESOMETHINGELSE";
+	}
+}
+
+/*
+ * usage:
+ * tool-test dir-iterator [--follow-symlinks] [--pedantic] directory_path
+ */
+int cmd__dir_iterator(int argc, const char **argv)
+{
+	struct dir_iterator *diter;
+	unsigned int flags = 0;
+	int iter_status;
+
+	for (++argv, --argc; *argv && starts_with(*argv, "--"); ++argv, --argc) {
+		if (strcmp(*argv, "--follow-symlinks") == 0)
+			flags |= DIR_ITERATOR_FOLLOW_SYMLINKS;
+		else if (strcmp(*argv, "--pedantic") == 0)
+			flags |= DIR_ITERATOR_PEDANTIC;
+		else
+			die("invalid option '%s'", *argv);
+	}
+
+	if (!*argv || argc != 1)
+		die("dir-iterator needs exactly one non-option argument");
+
+	diter = dir_iterator_begin(*argv, flags);
+
+	if (!diter) {
+		printf("dir_iterator_begin failure: %s\n", error_name(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	while ((iter_status = dir_iterator_advance(diter)) == ITER_OK) {
+		if (S_ISDIR(diter->st.st_mode))
+			printf("[d] ");
+		else if (S_ISREG(diter->st.st_mode))
+			printf("[f] ");
+		else if (S_ISLNK(diter->st.st_mode))
+			printf("[s] ");
+		else
+			printf("[?] ");
+
+		printf("(%s) [%s] %s\n", diter->relative_path, diter->basename,
+		       diter->path.buf);
+	}
+
+	if (iter_status != ITER_DONE) {
+		printf("dir_iterator_advance failure\n");
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/t/helper/test-drop-caches.c b/t/helper/test-drop-caches.c
new file mode 100644
index 000000000000..f65e301f9ddc
--- /dev/null
+++ b/t/helper/test-drop-caches.c
@@ -0,0 +1,157 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+
+#if defined(GIT_WINDOWS_NATIVE)
+#include "lazyload.h"
+
+static int cmd_sync(void)
+{
+	char Buffer[MAX_PATH];
+	DWORD dwRet;
+	char szVolumeAccessPath[] = "\\\\.\\X:";
+	HANDLE hVolWrite;
+	int success = 0;
+
+	dwRet = GetCurrentDirectory(MAX_PATH, Buffer);
+	if ((0 == dwRet) || (dwRet > MAX_PATH))
+		return error("Error getting current directory");
+
+	if (!has_dos_drive_prefix(Buffer))
+		return error("'%s': invalid drive letter", Buffer);
+
+	szVolumeAccessPath[4] = Buffer[0];
+	hVolWrite = CreateFile(szVolumeAccessPath, GENERIC_READ | GENERIC_WRITE,
+		FILE_SHARE_READ | FILE_SHARE_WRITE, NULL, OPEN_EXISTING, 0, NULL);
+	if (INVALID_HANDLE_VALUE == hVolWrite)
+		return error("Unable to open volume for writing, need admin access");
+
+	success = FlushFileBuffers(hVolWrite);
+	if (!success)
+		error("Unable to flush volume");
+
+	CloseHandle(hVolWrite);
+
+	return !success;
+}
+
+#define STATUS_SUCCESS			(0x00000000L)
+#define STATUS_PRIVILEGE_NOT_HELD	(0xC0000061L)
+
+typedef enum _SYSTEM_INFORMATION_CLASS {
+	SystemMemoryListInformation = 80,
+} SYSTEM_INFORMATION_CLASS;
+
+typedef enum _SYSTEM_MEMORY_LIST_COMMAND {
+	MemoryCaptureAccessedBits,
+	MemoryCaptureAndResetAccessedBits,
+	MemoryEmptyWorkingSets,
+	MemoryFlushModifiedList,
+	MemoryPurgeStandbyList,
+	MemoryPurgeLowPriorityStandbyList,
+	MemoryCommandMax
+} SYSTEM_MEMORY_LIST_COMMAND;
+
+static BOOL GetPrivilege(HANDLE TokenHandle, LPCSTR lpName, int flags)
+{
+	BOOL bResult;
+	DWORD dwBufferLength;
+	LUID luid;
+	TOKEN_PRIVILEGES tpPreviousState;
+	TOKEN_PRIVILEGES tpNewState;
+
+	dwBufferLength = 16;
+	bResult = LookupPrivilegeValueA(0, lpName, &luid);
+	if (bResult) {
+		tpNewState.PrivilegeCount = 1;
+		tpNewState.Privileges[0].Luid = luid;
+		tpNewState.Privileges[0].Attributes = 0;
+		bResult = AdjustTokenPrivileges(TokenHandle, 0, &tpNewState,
+			(DWORD)((LPBYTE)&(tpNewState.Privileges[1]) - (LPBYTE)&tpNewState),
+			&tpPreviousState, &dwBufferLength);
+		if (bResult) {
+			tpPreviousState.PrivilegeCount = 1;
+			tpPreviousState.Privileges[0].Luid = luid;
+			tpPreviousState.Privileges[0].Attributes = flags != 0 ? 2 : 0;
+			bResult = AdjustTokenPrivileges(TokenHandle, 0, &tpPreviousState,
+				dwBufferLength, 0, 0);
+		}
+	}
+	return bResult;
+}
+
+static int cmd_dropcaches(void)
+{
+	HANDLE hProcess = GetCurrentProcess();
+	HANDLE hToken;
+	DECLARE_PROC_ADDR(ntdll.dll, DWORD, NtSetSystemInformation, INT, PVOID, ULONG);
+	SYSTEM_MEMORY_LIST_COMMAND command;
+	int status;
+
+	if (!OpenProcessToken(hProcess, TOKEN_QUERY | TOKEN_ADJUST_PRIVILEGES, &hToken))
+		return error("Can't open current process token");
+
+	if (!GetPrivilege(hToken, "SeProfileSingleProcessPrivilege", 1))
+		return error("Can't get SeProfileSingleProcessPrivilege");
+
+	CloseHandle(hToken);
+
+	if (!INIT_PROC_ADDR(NtSetSystemInformation))
+		return error("Could not find NtSetSystemInformation() function");
+
+	command = MemoryPurgeStandbyList;
+	status = NtSetSystemInformation(
+		SystemMemoryListInformation,
+		&command,
+		sizeof(SYSTEM_MEMORY_LIST_COMMAND)
+	);
+	if (status == STATUS_PRIVILEGE_NOT_HELD)
+		error("Insufficient privileges to purge the standby list, need admin access");
+	else if (status != STATUS_SUCCESS)
+		error("Unable to execute the memory list command %d", status);
+
+	return status;
+}
+
+#elif defined(__linux__)
+
+static int cmd_sync(void)
+{
+	return system("sync");
+}
+
+static int cmd_dropcaches(void)
+{
+	return system("echo 3 | sudo tee /proc/sys/vm/drop_caches");
+}
+
+#elif defined(__APPLE__)
+
+static int cmd_sync(void)
+{
+	return system("sync");
+}
+
+static int cmd_dropcaches(void)
+{
+	return system("sudo purge");
+}
+
+#else
+
+static int cmd_sync(void)
+{
+	return 0;
+}
+
+static int cmd_dropcaches(void)
+{
+	return error("drop caches not implemented on this platform");
+}
+
+#endif
+
+int cmd__drop_caches(int argc, const char **argv)
+{
+	cmd_sync();
+	return cmd_dropcaches();
+}
diff --git a/t/helper/test-dump-cache-tree.c b/t/helper/test-dump-cache-tree.c
new file mode 100644
index 000000000000..6a3f88f5f5d4
--- /dev/null
+++ b/t/helper/test-dump-cache-tree.c
@@ -0,0 +1,69 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "tree.h"
+#include "cache-tree.h"
+
+
+static void dump_one(struct cache_tree *it, const char *pfx, const char *x)
+{
+	if (it->entry_count < 0)
+		printf("%-40s %s%s (%d subtrees)\n",
+		       "invalid", x, pfx, it->subtree_nr);
+	else
+		printf("%s %s%s (%d entries, %d subtrees)\n",
+		       oid_to_hex(&it->oid), x, pfx,
+		       it->entry_count, it->subtree_nr);
+}
+
+static int dump_cache_tree(struct cache_tree *it,
+			   struct cache_tree *ref,
+			   const char *pfx)
+{
+	int i;
+	int errs = 0;
+
+	if (!it || !ref)
+		/* missing in either */
+		return 0;
+
+	if (it->entry_count < 0) {
+		/* invalid */
+		dump_one(it, pfx, "");
+		dump_one(ref, pfx, "#(ref) ");
+	}
+	else {
+		dump_one(it, pfx, "");
+		if (!oideq(&it->oid, &ref->oid) ||
+		    ref->entry_count != it->entry_count ||
+		    ref->subtree_nr != it->subtree_nr) {
+			/* claims to be valid but is lying */
+			dump_one(ref, pfx, "#(ref) ");
+			errs = 1;
+		}
+	}
+
+	for (i = 0; i < it->subtree_nr; i++) {
+		char path[PATH_MAX];
+		struct cache_tree_sub *down = it->down[i];
+		struct cache_tree_sub *rdwn;
+
+		rdwn = cache_tree_sub(ref, down->name);
+		xsnprintf(path, sizeof(path), "%s%.*s/", pfx, down->namelen, down->name);
+		if (dump_cache_tree(down->cache_tree, rdwn->cache_tree, path))
+			errs = 1;
+	}
+	return errs;
+}
+
+int cmd__dump_cache_tree(int ac, const char **av)
+{
+	struct index_state istate;
+	struct cache_tree *another = cache_tree();
+	setup_git_directory();
+	if (read_cache() < 0)
+		die("unable to read index file");
+	istate = the_index;
+	istate.cache_tree = another;
+	cache_tree_update(&istate, WRITE_TREE_DRY_RUN);
+	return dump_cache_tree(active_cache_tree, another, "");
+}
diff --git a/t/helper/test-dump-fsmonitor.c b/t/helper/test-dump-fsmonitor.c
new file mode 100644
index 000000000000..2786f47088e9
--- /dev/null
+++ b/t/helper/test-dump-fsmonitor.c
@@ -0,0 +1,22 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd__dump_fsmonitor(int ac, const char **av)
+{
+	struct index_state *istate = the_repository->index;
+	int i;
+
+	setup_git_directory();
+	if (do_read_index(istate, the_repository->index_file, 0) < 0)
+		die("unable to read index file");
+	if (!istate->fsmonitor_last_update) {
+		printf("no fsmonitor\n");
+		return 0;
+	}
+	printf("fsmonitor last update %"PRIuMAX"\n", (uintmax_t)istate->fsmonitor_last_update);
+
+	for (i = 0; i < istate->cache_nr; i++)
+		printf((istate->cache[i]->ce_flags & CE_FSMONITOR_VALID) ? "+" : "-");
+
+	return 0;
+}
diff --git a/t/helper/test-dump-split-index.c b/t/helper/test-dump-split-index.c
new file mode 100644
index 000000000000..63c689d6ee9d
--- /dev/null
+++ b/t/helper/test-dump-split-index.c
@@ -0,0 +1,37 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "split-index.h"
+#include "ewah/ewok.h"
+
+static void show_bit(size_t pos, void *data)
+{
+	printf(" %d", (int)pos);
+}
+
+int cmd__dump_split_index(int ac, const char **av)
+{
+	struct split_index *si;
+	int i;
+
+	do_read_index(&the_index, av[1], 1);
+	printf("own %s\n", oid_to_hex(&the_index.oid));
+	si = the_index.split_index;
+	if (!si) {
+		printf("not a split index\n");
+		return 0;
+	}
+	printf("base %s\n", oid_to_hex(&si->base_oid));
+	for (i = 0; i < the_index.cache_nr; i++) {
+		struct cache_entry *ce = the_index.cache[i];
+		printf("%06o %s %d\t%s\n", ce->ce_mode,
+		       oid_to_hex(&ce->oid), ce_stage(ce), ce->name);
+	}
+	printf("replacements:");
+	if (si->replace_bitmap)
+		ewah_each_bit(si->replace_bitmap, show_bit, NULL);
+	printf("\ndeletions:");
+	if (si->delete_bitmap)
+		ewah_each_bit(si->delete_bitmap, show_bit, NULL);
+	printf("\n");
+	return 0;
+}
diff --git a/t/helper/test-dump-untracked-cache.c b/t/helper/test-dump-untracked-cache.c
new file mode 100644
index 000000000000..cf0f2c7228e8
--- /dev/null
+++ b/t/helper/test-dump-untracked-cache.c
@@ -0,0 +1,66 @@
+#define USE_THE_INDEX_COMPATIBILITY_MACROS
+#include "test-tool.h"
+#include "cache.h"
+#include "dir.h"
+
+static int compare_untracked(const void *a_, const void *b_)
+{
+	const char *const *a = a_;
+	const char *const *b = b_;
+	return strcmp(*a, *b);
+}
+
+static int compare_dir(const void *a_, const void *b_)
+{
+	const struct untracked_cache_dir *const *a = a_;
+	const struct untracked_cache_dir *const *b = b_;
+	return strcmp((*a)->name, (*b)->name);
+}
+
+static void dump(struct untracked_cache_dir *ucd, struct strbuf *base)
+{
+	int i, len;
+	QSORT(ucd->untracked, ucd->untracked_nr, compare_untracked);
+	QSORT(ucd->dirs, ucd->dirs_nr, compare_dir);
+	len = base->len;
+	strbuf_addf(base, "%s/", ucd->name);
+	printf("%s %s", base->buf,
+	       oid_to_hex(&ucd->exclude_oid));
+	if (ucd->recurse)
+		fputs(" recurse", stdout);
+	if (ucd->check_only)
+		fputs(" check_only", stdout);
+	if (ucd->valid)
+		fputs(" valid", stdout);
+	printf("\n");
+	for (i = 0; i < ucd->untracked_nr; i++)
+		printf("%s\n", ucd->untracked[i]);
+	for (i = 0; i < ucd->dirs_nr; i++)
+		dump(ucd->dirs[i], base);
+	strbuf_setlen(base, len);
+}
+
+int cmd__dump_untracked_cache(int ac, const char **av)
+{
+	struct untracked_cache *uc;
+	struct strbuf base = STRBUF_INIT;
+
+	/* Hack to avoid modifying the untracked cache when we read it */
+	ignore_untracked_cache_config = 1;
+
+	setup_git_directory();
+	if (read_cache() < 0)
+		die("unable to read index file");
+	uc = the_index.untracked;
+	if (!uc) {
+		printf("no untracked cache\n");
+		return 0;
+	}
+	printf("info/exclude %s\n", oid_to_hex(&uc->ss_info_exclude.oid));
+	printf("core.excludesfile %s\n", oid_to_hex(&uc->ss_excludes_file.oid));
+	printf("exclude_per_dir %s\n", uc->exclude_per_dir);
+	printf("flags %08x\n", uc->dir_flags);
+	if (uc->root)
+		dump(uc->root, &base);
+	return 0;
+}
diff --git a/t/helper/test-example-decorate.c b/t/helper/test-example-decorate.c
new file mode 100644
index 000000000000..c8a1cde7d2de
--- /dev/null
+++ b/t/helper/test-example-decorate.c
@@ -0,0 +1,75 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "object.h"
+#include "decorate.h"
+
+int cmd__example_decorate(int argc, const char **argv)
+{
+	struct decoration n;
+	struct object_id one_oid = { {1} };
+	struct object_id two_oid = { {2} };
+	struct object_id three_oid = { {3} };
+	struct object *one, *two, *three;
+
+	int decoration_a, decoration_b;
+
+	void *ret;
+
+	int i, objects_noticed = 0;
+
+	/*
+	 * The struct must be zero-initialized.
+	 */
+	memset(&n, 0, sizeof(n));
+
+	/*
+	 * Add 2 objects, one with a non-NULL decoration and one with a NULL
+	 * decoration.
+	 */
+	one = lookup_unknown_object(&one_oid);
+	two = lookup_unknown_object(&two_oid);
+	ret = add_decoration(&n, one, &decoration_a);
+	if (ret)
+		BUG("when adding a brand-new object, NULL should be returned");
+	ret = add_decoration(&n, two, NULL);
+	if (ret)
+		BUG("when adding a brand-new object, NULL should be returned");
+
+	/*
+	 * When re-adding an already existing object, the old decoration is
+	 * returned.
+	 */
+	ret = add_decoration(&n, one, NULL);
+	if (ret != &decoration_a)
+		BUG("when readding an already existing object, existing decoration should be returned");
+	ret = add_decoration(&n, two, &decoration_b);
+	if (ret)
+		BUG("when readding an already existing object, existing decoration should be returned");
+
+	/*
+	 * Lookup returns the added declarations, or NULL if the object was
+	 * never added.
+	 */
+	ret = lookup_decoration(&n, one);
+	if (ret)
+		BUG("lookup should return added declaration");
+	ret = lookup_decoration(&n, two);
+	if (ret != &decoration_b)
+		BUG("lookup should return added declaration");
+	three = lookup_unknown_object(&three_oid);
+	ret = lookup_decoration(&n, three);
+	if (ret)
+		BUG("lookup for unknown object should return NULL");
+
+	/*
+	 * The user can also loop through all entries.
+	 */
+	for (i = 0; i < n.size; i++) {
+		if (n.entries[i].base)
+			objects_noticed++;
+	}
+	if (objects_noticed != 2)
+		BUG("should have 2 objects");
+
+	return 0;
+}
diff --git a/t/helper/test-fake-ssh.c b/t/helper/test-fake-ssh.c
new file mode 100644
index 000000000000..12beee99ad2f
--- /dev/null
+++ b/t/helper/test-fake-ssh.c
@@ -0,0 +1,30 @@
+#include "git-compat-util.h"
+#include "run-command.h"
+#include "strbuf.h"
+
+int cmd_main(int argc, const char **argv)
+{
+	const char *trash_directory = getenv("TRASH_DIRECTORY");
+	struct strbuf buf = STRBUF_INIT;
+	FILE *f;
+	int i;
+	const char *child_argv[] = { NULL, NULL };
+
+	/* First, print all parameters into $TRASH_DIRECTORY/ssh-output */
+	if (!trash_directory)
+		die("Need a TRASH_DIRECTORY!");
+	strbuf_addf(&buf, "%s/ssh-output", trash_directory);
+	f = fopen(buf.buf, "w");
+	if (!f)
+		die("Could not write to %s", buf.buf);
+	for (i = 0; i < argc; i++)
+		fprintf(f, "%s%s", i > 0 ? " " : "", i > 0 ? argv[i] : "ssh:");
+	fprintf(f, "\n");
+	fclose(f);
+
+	/* Now, evaluate the *last* parameter */
+	if (argc < 2)
+		return 0;
+	child_argv[0] = argv[argc - 1];
+	return run_command_v_opt(child_argv, RUN_USING_SHELL);
+}
diff --git a/t/helper/test-genrandom.c b/t/helper/test-genrandom.c
new file mode 100644
index 000000000000..99b8dc1e2d9c
--- /dev/null
+++ b/t/helper/test-genrandom.c
@@ -0,0 +1,34 @@
+/*
+ * Simple random data generator used to create reproducible test files.
+ * This is inspired from POSIX.1-2001 implementation example for rand().
+ * Copyright (C) 2007 by Nicolas Pitre, licensed under the GPL version 2.
+ */
+
+#include "test-tool.h"
+#include "git-compat-util.h"
+
+int cmd__genrandom(int argc, const char **argv)
+{
+	unsigned long count, next = 0;
+	unsigned char *c;
+
+	if (argc < 2 || argc > 3) {
+		fprintf(stderr, "usage: %s <seed_string> [<size>]\n", argv[0]);
+		return 1;
+	}
+
+	c = (unsigned char *) argv[1];
+	do {
+		next = next * 11 + *c;
+	} while (*c++);
+
+	count = (argc == 3) ? strtoul(argv[2], NULL, 0) : -1L;
+
+	while (count--) {
+		next = next * 1103515245 + 12345;
+		if (putchar((next >> 16) & 0xff) == EOF)
+			return -1;
+	}
+
+	return 0;
+}
diff --git a/t/helper/test-genzeros.c b/t/helper/test-genzeros.c
new file mode 100644
index 000000000000..9532f5bac976
--- /dev/null
+++ b/t/helper/test-genzeros.c
@@ -0,0 +1,21 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+
+int cmd__genzeros(int argc, const char **argv)
+{
+	long count;
+
+	if (argc > 2) {
+		fprintf(stderr, "usage: %s [<count>]\n", argv[0]);
+		return 1;
+	}
+
+	count = argc > 1 ? strtol(argv[1], NULL, 0) : -1L;
+
+	while (count < 0 || count--) {
+		if (putchar(0) == EOF)
+			return -1;
+	}
+
+	return 0;
+}
diff --git a/t/helper/test-hash-speed.c b/t/helper/test-hash-speed.c
new file mode 100644
index 000000000000..432233c7f0e5
--- /dev/null
+++ b/t/helper/test-hash-speed.c
@@ -0,0 +1,61 @@
+#include "test-tool.h"
+#include "cache.h"
+
+#define NUM_SECONDS 3
+
+static inline void compute_hash(const struct git_hash_algo *algo, git_hash_ctx *ctx, uint8_t *final, const void *p, size_t len)
+{
+	algo->init_fn(ctx);
+	algo->update_fn(ctx, p, len);
+	algo->final_fn(final, ctx);
+}
+
+int cmd__hash_speed(int ac, const char **av)
+{
+	git_hash_ctx ctx;
+	unsigned char hash[GIT_MAX_RAWSZ];
+	clock_t initial, start, end;
+	unsigned bufsizes[] = { 64, 256, 1024, 8192, 16384 };
+	int i;
+	void *p;
+	const struct git_hash_algo *algo = NULL;
+
+	if (ac == 2) {
+		for (i = 1; i < GIT_HASH_NALGOS; i++) {
+			if (!strcmp(av[1], hash_algos[i].name)) {
+				algo = &hash_algos[i];
+				break;
+			}
+		}
+	}
+	if (!algo)
+		die("usage: test-tool hash-speed algo_name");
+
+	/* Use this as an offset to make overflow less likely. */
+	initial = clock();
+
+	printf("algo: %s\n", algo->name);
+
+	for (i = 0; i < ARRAY_SIZE(bufsizes); i++) {
+		unsigned long j, kb;
+		double kb_per_sec;
+		p = xcalloc(1, bufsizes[i]);
+		start = end = clock() - initial;
+		for (j = 0; ((end - start) / CLOCKS_PER_SEC) < NUM_SECONDS; j++) {
+			compute_hash(algo, &ctx, hash, p, bufsizes[i]);
+
+			/*
+			 * Only check elapsed time every 128 iterations to avoid
+			 * dominating the runtime with system calls.
+			 */
+			if (!(j & 127))
+				end = clock() - initial;
+		}
+		kb = j * bufsizes[i];
+		kb_per_sec = kb / (1024 * ((double)end - start) / CLOCKS_PER_SEC);
+		printf("size %u: %lu iters; %lu KiB; %0.2f KiB/s\n", bufsizes[i], j, kb, kb_per_sec);
+		free(p);
+	}
+
+	exit(0);
+}
diff --git a/t/helper/test-hash.c b/t/helper/test-hash.c
new file mode 100644
index 000000000000..0a31de66f354
--- /dev/null
+++ b/t/helper/test-hash.c
@@ -0,0 +1,58 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd_hash_impl(int ac, const char **av, int algo)
+{
+	git_hash_ctx ctx;
+	unsigned char hash[GIT_MAX_HEXSZ];
+	unsigned bufsz = 8192;
+	int binary = 0;
+	char *buffer;
+	const struct git_hash_algo *algop = &hash_algos[algo];
+
+	if (ac == 2) {
+		if (!strcmp(av[1], "-b"))
+			binary = 1;
+		else
+			bufsz = strtoul(av[1], NULL, 10) * 1024 * 1024;
+	}
+
+	if (!bufsz)
+		bufsz = 8192;
+
+	while ((buffer = malloc(bufsz)) == NULL) {
+		fprintf(stderr, "bufsz %u is too big, halving...\n", bufsz);
+		bufsz /= 2;
+		if (bufsz < 1024)
+			die("OOPS");
+	}
+
+	algop->init_fn(&ctx);
+
+	while (1) {
+		ssize_t sz, this_sz;
+		char *cp = buffer;
+		unsigned room = bufsz;
+		this_sz = 0;
+		while (room) {
+			sz = xread(0, cp, room);
+			if (sz == 0)
+				break;
+			if (sz < 0)
+				die_errno("test-hash");
+			this_sz += sz;
+			cp += sz;
+			room -= sz;
+		}
+		if (this_sz == 0)
+			break;
+		algop->update_fn(&ctx, buffer, this_sz);
+	}
+	algop->final_fn(hash, &ctx);
+
+	if (binary)
+		fwrite(hash, 1, algop->rawsz, stdout);
+	else
+		puts(hash_to_hex_algop(hash, algop));
+	exit(0);
+}
diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c
new file mode 100644
index 000000000000..aaf17b0ddf9e
--- /dev/null
+++ b/t/helper/test-hashmap.c
@@ -0,0 +1,263 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "hashmap.h"
+#include "strbuf.h"
+
+struct test_entry
+{
+	struct hashmap_entry ent;
+	/* key and value as two \0-terminated strings */
+	char key[FLEX_ARRAY];
+};
+
+static const char *get_value(const struct test_entry *e)
+{
+	return e->key + strlen(e->key) + 1;
+}
+
+static int test_entry_cmp(const void *cmp_data,
+			  const void *entry,
+			  const void *entry_or_key,
+			  const void *keydata)
+{
+	const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
+	const struct test_entry *e1 = entry;
+	const struct test_entry *e2 = entry_or_key;
+	const char *key = keydata;
+
+	if (ignore_case)
+		return strcasecmp(e1->key, key ? key : e2->key);
+	else
+		return strcmp(e1->key, key ? key : e2->key);
+}
+
+static struct test_entry *alloc_test_entry(unsigned int hash,
+					   char *key, char *value)
+{
+	size_t klen = strlen(key);
+	size_t vlen = strlen(value);
+	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
+	hashmap_entry_init(entry, hash);
+	memcpy(entry->key, key, klen + 1);
+	memcpy(entry->key + klen + 1, value, vlen + 1);
+	return entry;
+}
+
+#define HASH_METHOD_FNV 0
+#define HASH_METHOD_I 1
+#define HASH_METHOD_IDIV10 2
+#define HASH_METHOD_0 3
+#define HASH_METHOD_X2 4
+#define TEST_SPARSE 8
+#define TEST_ADD 16
+#define TEST_SIZE 100000
+
+static unsigned int hash(unsigned int method, unsigned int i, const char *key)
+{
+	unsigned int hash = 0;
+	switch (method & 3)
+	{
+	case HASH_METHOD_FNV:
+		hash = strhash(key);
+		break;
+	case HASH_METHOD_I:
+		hash = i;
+		break;
+	case HASH_METHOD_IDIV10:
+		hash = i / 10;
+		break;
+	case HASH_METHOD_0:
+		hash = 0;
+		break;
+	}
+
+	if (method & HASH_METHOD_X2)
+		hash = 2 * hash;
+	return hash;
+}
+
+/*
+ * Test performance of hashmap.[ch]
+ * Usage: time echo "perfhashmap method rounds" | test-tool hashmap
+ */
+static void perf_hashmap(unsigned int method, unsigned int rounds)
+{
+	struct hashmap map;
+	char buf[16];
+	struct test_entry **entries;
+	unsigned int *hashes;
+	unsigned int i, j;
+
+	ALLOC_ARRAY(entries, TEST_SIZE);
+	ALLOC_ARRAY(hashes, TEST_SIZE);
+	for (i = 0; i < TEST_SIZE; i++) {
+		xsnprintf(buf, sizeof(buf), "%i", i);
+		entries[i] = alloc_test_entry(0, buf, "");
+		hashes[i] = hash(method, i, entries[i]->key);
+	}
+
+	if (method & TEST_ADD) {
+		/* test adding to the map */
+		for (j = 0; j < rounds; j++) {
+			hashmap_init(&map, test_entry_cmp, NULL, 0);
+
+			/* add entries */
+			for (i = 0; i < TEST_SIZE; i++) {
+				hashmap_entry_init(entries[i], hashes[i]);
+				hashmap_add(&map, entries[i]);
+			}
+
+			hashmap_free(&map, 0);
+		}
+	} else {
+		/* test map lookups */
+		hashmap_init(&map, test_entry_cmp, NULL, 0);
+
+		/* fill the map (sparsely if specified) */
+		j = (method & TEST_SPARSE) ? TEST_SIZE / 10 : TEST_SIZE;
+		for (i = 0; i < j; i++) {
+			hashmap_entry_init(entries[i], hashes[i]);
+			hashmap_add(&map, entries[i]);
+		}
+
+		for (j = 0; j < rounds; j++) {
+			for (i = 0; i < TEST_SIZE; i++) {
+				hashmap_get_from_hash(&map, hashes[i],
+						      entries[i]->key);
+			}
+		}
+
+		hashmap_free(&map, 0);
+	}
+}
+
+#define DELIM " \t\r\n"
+
+/*
+ * Read stdin line by line and print result of commands to stdout:
+ *
+ * hash key -> strhash(key) memhash(key) strihash(key) memihash(key)
+ * put key value -> NULL / old value
+ * get key -> NULL / value
+ * remove key -> NULL / old value
+ * iterate -> key1 value1\nkey2 value2\n...
+ * size -> tablesize numentries
+ *
+ * perfhashmap method rounds -> test hashmap.[ch] performance
+ */
+int cmd__hashmap(int argc, const char **argv)
+{
+	struct strbuf line = STRBUF_INIT;
+	struct hashmap map;
+	int icase;
+
+	/* init hash map */
+	icase = argc > 1 && !strcmp("ignorecase", argv[1]);
+	hashmap_init(&map, test_entry_cmp, &icase, 0);
+
+	/* process commands from stdin */
+	while (strbuf_getline(&line, stdin) != EOF) {
+		char *cmd, *p1 = NULL, *p2 = NULL;
+		unsigned int hash = 0;
+		struct test_entry *entry;
+
+		/* break line into command and up to two parameters */
+		cmd = strtok(line.buf, DELIM);
+		/* ignore empty lines */
+		if (!cmd || *cmd == '#')
+			continue;
+
+		p1 = strtok(NULL, DELIM);
+		if (p1) {
+			hash = icase ? strihash(p1) : strhash(p1);
+			p2 = strtok(NULL, DELIM);
+		}
+
+		if (!strcmp("add", cmd) && p1 && p2) {
+
+			/* create entry with key = p1, value = p2 */
+			entry = alloc_test_entry(hash, p1, p2);
+
+			/* add to hashmap */
+			hashmap_add(&map, entry);
+
+		} else if (!strcmp("put", cmd) && p1 && p2) {
+
+			/* create entry with key = p1, value = p2 */
+			entry = alloc_test_entry(hash, p1, p2);
+
+			/* add / replace entry */
+			entry = hashmap_put(&map, entry);
+
+			/* print and free replaced entry, if any */
+			puts(entry ? get_value(entry) : "NULL");
+			free(entry);
+
+		} else if (!strcmp("get", cmd) && p1) {
+
+			/* lookup entry in hashmap */
+			entry = hashmap_get_from_hash(&map, hash, p1);
+
+			/* print result */
+			if (!entry)
+				puts("NULL");
+			while (entry) {
+				puts(get_value(entry));
+				entry = hashmap_get_next(&map, entry);
+			}
+
+		} else if (!strcmp("remove", cmd) && p1) {
+
+			/* setup static key */
+			struct hashmap_entry key;
+			hashmap_entry_init(&key, hash);
+
+			/* remove entry from hashmap */
+			entry = hashmap_remove(&map, &key, p1);
+
+			/* print result and free entry*/
+			puts(entry ? get_value(entry) : "NULL");
+			free(entry);
+
+		} else if (!strcmp("iterate", cmd)) {
+
+			struct hashmap_iter iter;
+			hashmap_iter_init(&map, &iter);
+			while ((entry = hashmap_iter_next(&iter)))
+				printf("%s %s\n", entry->key, get_value(entry));
+
+		} else if (!strcmp("size", cmd)) {
+
+			/* print table sizes */
+			printf("%u %u\n", map.tablesize,
+			       hashmap_get_size(&map));
+
+		} else if (!strcmp("intern", cmd) && p1) {
+
+			/* test that strintern works */
+			const char *i1 = strintern(p1);
+			const char *i2 = strintern(p1);
+			if (strcmp(i1, p1))
+				printf("strintern(%s) returns %s\n", p1, i1);
+			else if (i1 == p1)
+				printf("strintern(%s) returns input pointer\n", p1);
+			else if (i1 != i2)
+				printf("strintern(%s) != strintern(%s)", i1, i2);
+			else
+				printf("%s\n", i1);
+
+		} else if (!strcmp("perfhashmap", cmd) && p1 && p2) {
+
+			perf_hashmap(atoi(p1), atoi(p2));
+
+		} else {
+
+			printf("Unknown command %s\n", cmd);
+
+		}
+	}
+
+	strbuf_release(&line);
+	hashmap_free(&map, 1);
+	return 0;
+}
diff --git a/t/helper/test-index-version.c b/t/helper/test-index-version.c
new file mode 100644
index 000000000000..fcd10968cc10
--- /dev/null
+++ b/t/helper/test-index-version.c
@@ -0,0 +1,15 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd__index_version(int argc, const char **argv)
+{
+	struct cache_header hdr;
+	int version;
+
+	memset(&hdr,0,sizeof(hdr));
+	if (read(0, &hdr, sizeof(hdr)) != sizeof(hdr))
+		return 0;
+	version = ntohl(hdr.hdr_version);
+	printf("%d\n", version);
+	return 0;
+}
diff --git a/t/helper/test-json-writer.c b/t/helper/test-json-writer.c
new file mode 100644
index 000000000000..37c452535f8b
--- /dev/null
+++ b/t/helper/test-json-writer.c
@@ -0,0 +1,565 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "json-writer.h"
+
+static const char *expect_obj1 = "{\"a\":\"abc\",\"b\":42,\"c\":true}";
+static const char *expect_obj2 = "{\"a\":-1,\"b\":2147483647,\"c\":0}";
+static const char *expect_obj3 = "{\"a\":0,\"b\":4294967295,\"c\":9223372036854775807}";
+static const char *expect_obj4 = "{\"t\":true,\"f\":false,\"n\":null}";
+static const char *expect_obj5 = "{\"abc\\tdef\":\"abc\\\\def\"}";
+static const char *expect_obj6 = "{\"a\":3.14}";
+
+static const char *pretty_obj1 = ("{\n"
+				  "  \"a\": \"abc\",\n"
+				  "  \"b\": 42,\n"
+				  "  \"c\": true\n"
+				  "}");
+static const char *pretty_obj2 = ("{\n"
+				  "  \"a\": -1,\n"
+				  "  \"b\": 2147483647,\n"
+				  "  \"c\": 0\n"
+				  "}");
+static const char *pretty_obj3 = ("{\n"
+				  "  \"a\": 0,\n"
+				  "  \"b\": 4294967295,\n"
+				  "  \"c\": 9223372036854775807\n"
+				  "}");
+static const char *pretty_obj4 = ("{\n"
+				  "  \"t\": true,\n"
+				  "  \"f\": false,\n"
+				  "  \"n\": null\n"
+				  "}");
+
+static struct json_writer obj1 = JSON_WRITER_INIT;
+static struct json_writer obj2 = JSON_WRITER_INIT;
+static struct json_writer obj3 = JSON_WRITER_INIT;
+static struct json_writer obj4 = JSON_WRITER_INIT;
+static struct json_writer obj5 = JSON_WRITER_INIT;
+static struct json_writer obj6 = JSON_WRITER_INIT;
+
+static void make_obj1(int pretty)
+{
+	jw_object_begin(&obj1, pretty);
+	{
+		jw_object_string(&obj1, "a", "abc");
+		jw_object_intmax(&obj1, "b", 42);
+		jw_object_true(&obj1, "c");
+	}
+	jw_end(&obj1);
+}
+
+static void make_obj2(int pretty)
+{
+	jw_object_begin(&obj2, pretty);
+	{
+		jw_object_intmax(&obj2, "a", -1);
+		jw_object_intmax(&obj2, "b", 0x7fffffff);
+		jw_object_intmax(&obj2, "c", 0);
+	}
+	jw_end(&obj2);
+}
+
+static void make_obj3(int pretty)
+{
+	jw_object_begin(&obj3, pretty);
+	{
+		jw_object_intmax(&obj3, "a", 0);
+		jw_object_intmax(&obj3, "b", 0xffffffff);
+		jw_object_intmax(&obj3, "c", 0x7fffffffffffffffULL);
+	}
+	jw_end(&obj3);
+}
+
+static void make_obj4(int pretty)
+{
+	jw_object_begin(&obj4, pretty);
+	{
+		jw_object_true(&obj4, "t");
+		jw_object_false(&obj4, "f");
+		jw_object_null(&obj4, "n");
+	}
+	jw_end(&obj4);
+}
+
+static void make_obj5(int pretty)
+{
+	jw_object_begin(&obj5, pretty);
+	{
+		jw_object_string(&obj5, "abc" "\x09" "def", "abc" "\\" "def");
+	}
+	jw_end(&obj5);
+}
+
+static void make_obj6(int pretty)
+{
+	jw_object_begin(&obj6, pretty);
+	{
+		jw_object_double(&obj6, "a", 2, 3.14159);
+	}
+	jw_end(&obj6);
+}
+
+static const char *expect_arr1 = "[\"abc\",42,true]";
+static const char *expect_arr2 = "[-1,2147483647,0]";
+static const char *expect_arr3 = "[0,4294967295,9223372036854775807]";
+static const char *expect_arr4 = "[true,false,null]";
+
+static const char *pretty_arr1 = ("[\n"
+				  "  \"abc\",\n"
+				  "  42,\n"
+				  "  true\n"
+				  "]");
+static const char *pretty_arr2 = ("[\n"
+				  "  -1,\n"
+				  "  2147483647,\n"
+				  "  0\n"
+				  "]");
+static const char *pretty_arr3 = ("[\n"
+				  "  0,\n"
+				  "  4294967295,\n"
+				  "  9223372036854775807\n"
+				  "]");
+static const char *pretty_arr4 = ("[\n"
+				  "  true,\n"
+				  "  false,\n"
+				  "  null\n"
+				  "]");
+
+static struct json_writer arr1 = JSON_WRITER_INIT;
+static struct json_writer arr2 = JSON_WRITER_INIT;
+static struct json_writer arr3 = JSON_WRITER_INIT;
+static struct json_writer arr4 = JSON_WRITER_INIT;
+
+static void make_arr1(int pretty)
+{
+	jw_array_begin(&arr1, pretty);
+	{
+		jw_array_string(&arr1, "abc");
+		jw_array_intmax(&arr1, 42);
+		jw_array_true(&arr1);
+	}
+	jw_end(&arr1);
+}
+
+static void make_arr2(int pretty)
+{
+	jw_array_begin(&arr2, pretty);
+	{
+		jw_array_intmax(&arr2, -1);
+		jw_array_intmax(&arr2, 0x7fffffff);
+		jw_array_intmax(&arr2, 0);
+	}
+	jw_end(&arr2);
+}
+
+static void make_arr3(int pretty)
+{
+	jw_array_begin(&arr3, pretty);
+	{
+		jw_array_intmax(&arr3, 0);
+		jw_array_intmax(&arr3, 0xffffffff);
+		jw_array_intmax(&arr3, 0x7fffffffffffffffULL);
+	}
+	jw_end(&arr3);
+}
+
+static void make_arr4(int pretty)
+{
+	jw_array_begin(&arr4, pretty);
+	{
+		jw_array_true(&arr4);
+		jw_array_false(&arr4);
+		jw_array_null(&arr4);
+	}
+	jw_end(&arr4);
+}
+
+static char *expect_nest1 =
+	"{\"obj1\":{\"a\":\"abc\",\"b\":42,\"c\":true},\"arr1\":[\"abc\",42,true]}";
+
+static struct json_writer nest1 = JSON_WRITER_INIT;
+
+static void make_nest1(int pretty)
+{
+	jw_object_begin(&nest1, pretty);
+	{
+		jw_object_sub_jw(&nest1, "obj1", &obj1);
+		jw_object_sub_jw(&nest1, "arr1", &arr1);
+	}
+	jw_end(&nest1);
+}
+
+static char *expect_inline1 =
+	"{\"obj1\":{\"a\":\"abc\",\"b\":42,\"c\":true},\"arr1\":[\"abc\",42,true]}";
+
+static char *pretty_inline1 =
+	("{\n"
+	 "  \"obj1\": {\n"
+	 "    \"a\": \"abc\",\n"
+	 "    \"b\": 42,\n"
+	 "    \"c\": true\n"
+	 "  },\n"
+	 "  \"arr1\": [\n"
+	 "    \"abc\",\n"
+	 "    42,\n"
+	 "    true\n"
+	 "  ]\n"
+	 "}");
+
+static struct json_writer inline1 = JSON_WRITER_INIT;
+
+static void make_inline1(int pretty)
+{
+	jw_object_begin(&inline1, pretty);
+	{
+		jw_object_inline_begin_object(&inline1, "obj1");
+		{
+			jw_object_string(&inline1, "a", "abc");
+			jw_object_intmax(&inline1, "b", 42);
+			jw_object_true(&inline1, "c");
+		}
+		jw_end(&inline1);
+		jw_object_inline_begin_array(&inline1, "arr1");
+		{
+			jw_array_string(&inline1, "abc");
+			jw_array_intmax(&inline1, 42);
+			jw_array_true(&inline1);
+		}
+		jw_end(&inline1);
+	}
+	jw_end(&inline1);
+}
+
+static char *expect_inline2 =
+	"[[1,2],[3,4],{\"a\":\"abc\"}]";
+
+static char *pretty_inline2 =
+	("[\n"
+	 "  [\n"
+	 "    1,\n"
+	 "    2\n"
+	 "  ],\n"
+	 "  [\n"
+	 "    3,\n"
+	 "    4\n"
+	 "  ],\n"
+	 "  {\n"
+	 "    \"a\": \"abc\"\n"
+	 "  }\n"
+	 "]");
+
+static struct json_writer inline2 = JSON_WRITER_INIT;
+
+static void make_inline2(int pretty)
+{
+	jw_array_begin(&inline2, pretty);
+	{
+		jw_array_inline_begin_array(&inline2);
+		{
+			jw_array_intmax(&inline2, 1);
+			jw_array_intmax(&inline2, 2);
+		}
+		jw_end(&inline2);
+		jw_array_inline_begin_array(&inline2);
+		{
+			jw_array_intmax(&inline2, 3);
+			jw_array_intmax(&inline2, 4);
+		}
+		jw_end(&inline2);
+		jw_array_inline_begin_object(&inline2);
+		{
+			jw_object_string(&inline2, "a", "abc");
+		}
+		jw_end(&inline2);
+	}
+	jw_end(&inline2);
+}
+
+/*
+ * When super is compact, we expect subs to be compacted (even if originally
+ * pretty).
+ */
+static const char *expect_mixed1 =
+	("{\"obj1\":{\"a\":\"abc\",\"b\":42,\"c\":true},"
+	 "\"arr1\":[\"abc\",42,true]}");
+
+/*
+ * When super is pretty, a compact sub (obj1) is kept compact and a pretty
+ * sub (arr1) is re-indented.
+ */
+static const char *pretty_mixed1 =
+	("{\n"
+	 "  \"obj1\": {\"a\":\"abc\",\"b\":42,\"c\":true},\n"
+	 "  \"arr1\": [\n"
+	 "    \"abc\",\n"
+	 "    42,\n"
+	 "    true\n"
+	 "  ]\n"
+	 "}");
+
+static struct json_writer mixed1 = JSON_WRITER_INIT;
+
+static void make_mixed1(int pretty)
+{
+	jw_init(&obj1);
+	jw_init(&arr1);
+
+	make_obj1(0); /* obj1 is compact */
+	make_arr1(1); /* arr1 is pretty */
+
+	jw_object_begin(&mixed1, pretty);
+	{
+		jw_object_sub_jw(&mixed1, "obj1", &obj1);
+		jw_object_sub_jw(&mixed1, "arr1", &arr1);
+	}
+	jw_end(&mixed1);
+}
+
+static void cmp(const char *test, const struct json_writer *jw, const char *exp)
+{
+	if (!strcmp(jw->json.buf, exp))
+		return;
+
+	printf("error[%s]: observed '%s' expected '%s'\n",
+	       test, jw->json.buf, exp);
+	exit(1);
+}
+
+#define t(v) do { make_##v(0); cmp(#v, &v, expect_##v); } while (0)
+#define p(v) do { make_##v(1); cmp(#v, &v, pretty_##v); } while (0)
+
+/*
+ * Run some basic regression tests with some known patterns.
+ * These tests also demonstrate how to use the jw_ API.
+ */
+static int unit_tests(void)
+{
+	/* comptact (canonical) forms */
+	t(obj1);
+	t(obj2);
+	t(obj3);
+	t(obj4);
+	t(obj5);
+	t(obj6);
+
+	t(arr1);
+	t(arr2);
+	t(arr3);
+	t(arr4);
+
+	t(nest1);
+
+	t(inline1);
+	t(inline2);
+
+	jw_init(&obj1);
+	jw_init(&obj2);
+	jw_init(&obj3);
+	jw_init(&obj4);
+
+	jw_init(&arr1);
+	jw_init(&arr2);
+	jw_init(&arr3);
+	jw_init(&arr4);
+
+	jw_init(&inline1);
+	jw_init(&inline2);
+
+	/* pretty forms */
+	p(obj1);
+	p(obj2);
+	p(obj3);
+	p(obj4);
+
+	p(arr1);
+	p(arr2);
+	p(arr3);
+	p(arr4);
+
+	p(inline1);
+	p(inline2);
+
+	/* mixed forms */
+	t(mixed1);
+	jw_init(&mixed1);
+	p(mixed1);
+
+	return 0;
+}
+
+static void get_s(int line_nr, char **s_in)
+{
+	*s_in = strtok(NULL, " ");
+	if (!*s_in)
+		die("line[%d]: expected: <s>", line_nr);
+}
+
+static void get_i(int line_nr, intmax_t *s_in)
+{
+	char *s;
+	char *endptr;
+
+	get_s(line_nr, &s);
+
+	*s_in = strtol(s, &endptr, 10);
+	if (*endptr || errno == ERANGE)
+		die("line[%d]: invalid integer value", line_nr);
+}
+
+static void get_d(int line_nr, double *s_in)
+{
+	char *s;
+	char *endptr;
+
+	get_s(line_nr, &s);
+
+	*s_in = strtod(s, &endptr);
+	if (*endptr || errno == ERANGE)
+		die("line[%d]: invalid float value", line_nr);
+}
+
+static int pretty;
+
+#define MAX_LINE_LENGTH (64 * 1024)
+
+static char *get_trimmed_line(char *buf, int buf_size)
+{
+	int len;
+
+	if (!fgets(buf, buf_size, stdin))
+		return NULL;
+
+	len = strlen(buf);
+	while (len > 0) {
+		char c = buf[len - 1];
+		if (c == '\n' || c == '\r' || c == ' ' || c == '\t')
+			buf[--len] = 0;
+		else
+			break;
+	}
+
+	while (*buf == ' ' || *buf == '\t')
+		buf++;
+
+	return buf;
+}
+
+static int scripted(void)
+{
+	struct json_writer jw = JSON_WRITER_INIT;
+	char buf[MAX_LINE_LENGTH];
+	char *line;
+	int line_nr = 0;
+
+	line = get_trimmed_line(buf, MAX_LINE_LENGTH);
+	if (!line)
+		return 0;
+
+	if (!strcmp(line, "object"))
+		jw_object_begin(&jw, pretty);
+	else if (!strcmp(line, "array"))
+		jw_array_begin(&jw, pretty);
+	else
+		die("expected first line to be 'object' or 'array'");
+
+	while ((line = get_trimmed_line(buf, MAX_LINE_LENGTH)) != NULL) {
+		char *verb;
+		char *key;
+		char *s_value;
+		intmax_t i_value;
+		double d_value;
+
+		line_nr++;
+
+		verb = strtok(line, " ");
+
+		if (!strcmp(verb, "end")) {
+			jw_end(&jw);
+		}
+		else if (!strcmp(verb, "object-string")) {
+			get_s(line_nr, &key);
+			get_s(line_nr, &s_value);
+			jw_object_string(&jw, key, s_value);
+		}
+		else if (!strcmp(verb, "object-int")) {
+			get_s(line_nr, &key);
+			get_i(line_nr, &i_value);
+			jw_object_intmax(&jw, key, i_value);
+		}
+		else if (!strcmp(verb, "object-double")) {
+			get_s(line_nr, &key);
+			get_i(line_nr, &i_value);
+			get_d(line_nr, &d_value);
+			jw_object_double(&jw, key, i_value, d_value);
+		}
+		else if (!strcmp(verb, "object-true")) {
+			get_s(line_nr, &key);
+			jw_object_true(&jw, key);
+		}
+		else if (!strcmp(verb, "object-false")) {
+			get_s(line_nr, &key);
+			jw_object_false(&jw, key);
+		}
+		else if (!strcmp(verb, "object-null")) {
+			get_s(line_nr, &key);
+			jw_object_null(&jw, key);
+		}
+		else if (!strcmp(verb, "object-object")) {
+			get_s(line_nr, &key);
+			jw_object_inline_begin_object(&jw, key);
+		}
+		else if (!strcmp(verb, "object-array")) {
+			get_s(line_nr, &key);
+			jw_object_inline_begin_array(&jw, key);
+		}
+		else if (!strcmp(verb, "array-string")) {
+			get_s(line_nr, &s_value);
+			jw_array_string(&jw, s_value);
+		}
+		else if (!strcmp(verb, "array-int")) {
+			get_i(line_nr, &i_value);
+			jw_array_intmax(&jw, i_value);
+		}
+		else if (!strcmp(verb, "array-double")) {
+			get_i(line_nr, &i_value);
+			get_d(line_nr, &d_value);
+			jw_array_double(&jw, i_value, d_value);
+		}
+		else if (!strcmp(verb, "array-true"))
+			jw_array_true(&jw);
+		else if (!strcmp(verb, "array-false"))
+			jw_array_false(&jw);
+		else if (!strcmp(verb, "array-null"))
+			jw_array_null(&jw);
+		else if (!strcmp(verb, "array-object"))
+			jw_array_inline_begin_object(&jw);
+		else if (!strcmp(verb, "array-array"))
+			jw_array_inline_begin_array(&jw);
+		else
+			die("unrecognized token: '%s'", verb);
+	}
+
+	if (!jw_is_terminated(&jw))
+		die("json not terminated: '%s'", jw.json.buf);
+
+	printf("%s\n", jw.json.buf);
+
+	strbuf_release(&jw.json);
+	return 0;
+}
+
+int cmd__json_writer(int argc, const char **argv)
+{
+	argc--; /* skip over "json-writer" arg */
+	argv++;
+
+	if (argc > 0 && argv[0][0] == '-') {
+		if (!strcmp(argv[0], "-u") || !strcmp(argv[0], "--unit"))
+			return unit_tests();
+
+		if (!strcmp(argv[0], "-p") || !strcmp(argv[0], "--pretty"))
+			pretty = 1;
+	}
+
+	return scripted();
+}
diff --git a/t/helper/test-lazy-init-name-hash.c b/t/helper/test-lazy-init-name-hash.c
new file mode 100644
index 000000000000..b99a37080d93
--- /dev/null
+++ b/t/helper/test-lazy-init-name-hash.c
@@ -0,0 +1,265 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "parse-options.h"
+
+static int single;
+static int multi;
+static int count = 1;
+static int dump;
+static int perf;
+static int analyze;
+static int analyze_step;
+
+/*
+ * Dump the contents of the "dir" and "name" hash tables to stdout.
+ * If you sort the result, you can compare it with the other type
+ * mode and verify that both single and multi produce the same set.
+ */
+static void dump_run(void)
+{
+	struct hashmap_iter iter_dir;
+	struct hashmap_iter iter_cache;
+
+	/* Stolen from name-hash.c */
+	struct dir_entry {
+		struct hashmap_entry ent;
+		struct dir_entry *parent;
+		int nr;
+		unsigned int namelen;
+		char name[FLEX_ARRAY];
+	};
+
+	struct dir_entry *dir;
+	struct cache_entry *ce;
+
+	read_cache();
+	if (single) {
+		test_lazy_init_name_hash(&the_index, 0);
+	} else {
+		int nr_threads_used = test_lazy_init_name_hash(&the_index, 1);
+		if (!nr_threads_used)
+			die("non-threaded code path used");
+	}
+
+	dir = hashmap_iter_first(&the_index.dir_hash, &iter_dir);
+	while (dir) {
+		printf("dir %08x %7d %s\n", dir->ent.hash, dir->nr, dir->name);
+		dir = hashmap_iter_next(&iter_dir);
+	}
+
+	ce = hashmap_iter_first(&the_index.name_hash, &iter_cache);
+	while (ce) {
+		printf("name %08x %s\n", ce->ent.hash, ce->name);
+		ce = hashmap_iter_next(&iter_cache);
+	}
+
+	discard_cache();
+}
+
+/*
+ * Run the single or multi threaded version "count" times and
+ * report on the time taken.
+ */
+static uint64_t time_runs(int try_threaded)
+{
+	uint64_t t0, t1, t2;
+	uint64_t sum = 0;
+	uint64_t avg;
+	int nr_threads_used;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		t0 = getnanotime();
+		read_cache();
+		t1 = getnanotime();
+		nr_threads_used = test_lazy_init_name_hash(&the_index, try_threaded);
+		t2 = getnanotime();
+
+		sum += (t2 - t1);
+
+		if (try_threaded && !nr_threads_used)
+			die("non-threaded code path used");
+
+		if (nr_threads_used)
+			printf("%f %f %d multi %d\n",
+				   ((double)(t1 - t0))/1000000000,
+				   ((double)(t2 - t1))/1000000000,
+				   the_index.cache_nr,
+				   nr_threads_used);
+		else
+			printf("%f %f %d single\n",
+				   ((double)(t1 - t0))/1000000000,
+				   ((double)(t2 - t1))/1000000000,
+				   the_index.cache_nr);
+		fflush(stdout);
+
+		discard_cache();
+	}
+
+	avg = sum / count;
+	if (count > 1)
+		printf("avg %f %s\n",
+			   (double)avg/1000000000,
+			   (try_threaded) ? "multi" : "single");
+
+	return avg;
+}
+
+/*
+ * Try a series of runs varying the "istate->cache_nr" and
+ * try to find a good value for the multi-threaded criteria.
+ */
+static void analyze_run(void)
+{
+	uint64_t t1s, t1m, t2s, t2m;
+	int cache_nr_limit;
+	int nr_threads_used = 0;
+	int i;
+	int nr;
+
+	read_cache();
+	cache_nr_limit = the_index.cache_nr;
+	discard_cache();
+
+	nr = analyze;
+	while (1) {
+		uint64_t sum_single = 0;
+		uint64_t sum_multi = 0;
+		uint64_t avg_single;
+		uint64_t avg_multi;
+
+		if (nr > cache_nr_limit)
+			nr = cache_nr_limit;
+
+		for (i = 0; i < count; i++) {
+			read_cache();
+			the_index.cache_nr = nr; /* cheap truncate of index */
+			t1s = getnanotime();
+			test_lazy_init_name_hash(&the_index, 0);
+			t2s = getnanotime();
+			sum_single += (t2s - t1s);
+			the_index.cache_nr = cache_nr_limit;
+			discard_cache();
+
+			read_cache();
+			the_index.cache_nr = nr; /* cheap truncate of index */
+			t1m = getnanotime();
+			nr_threads_used = test_lazy_init_name_hash(&the_index, 1);
+			t2m = getnanotime();
+			sum_multi += (t2m - t1m);
+			the_index.cache_nr = cache_nr_limit;
+			discard_cache();
+
+			if (!nr_threads_used)
+				printf("    [size %8d] [single %f]   non-threaded code path used\n",
+					   nr, ((double)(t2s - t1s))/1000000000);
+			else
+				printf("    [size %8d] [single %f] %c [multi %f %d]\n",
+					   nr,
+					   ((double)(t2s - t1s))/1000000000,
+					   (((t2s - t1s) < (t2m - t1m)) ? '<' : '>'),
+					   ((double)(t2m - t1m))/1000000000,
+					   nr_threads_used);
+			fflush(stdout);
+		}
+		if (count > 1) {
+			avg_single = sum_single / count;
+			avg_multi = sum_multi / count;
+			if (!nr_threads_used)
+				printf("avg [size %8d] [single %f]\n",
+					   nr,
+					   (double)avg_single/1000000000);
+			else
+				printf("avg [size %8d] [single %f] %c [multi %f %d]\n",
+					   nr,
+					   (double)avg_single/1000000000,
+					   (avg_single < avg_multi ? '<' : '>'),
+					   (double)avg_multi/1000000000,
+					   nr_threads_used);
+			fflush(stdout);
+		}
+
+		if (nr >= cache_nr_limit)
+			return;
+		nr += analyze_step;
+	}
+}
+
+int cmd__lazy_init_name_hash(int argc, const char **argv)
+{
+	const char *usage[] = {
+		"test-tool lazy-init-name-hash -d (-s | -m)",
+		"test-tool lazy-init-name-hash -p [-c c]",
+		"test-tool lazy-init-name-hash -a a [--step s] [-c c]",
+		"test-tool lazy-init-name-hash (-s | -m) [-c c]",
+		"test-tool lazy-init-name-hash -s -m [-c c]",
+		NULL
+	};
+	struct option options[] = {
+		OPT_BOOL('s', "single", &single, "run single-threaded code"),
+		OPT_BOOL('m', "multi", &multi, "run multi-threaded code"),
+		OPT_INTEGER('c', "count", &count, "number of passes"),
+		OPT_BOOL('d', "dump", &dump, "dump hash tables"),
+		OPT_BOOL('p', "perf", &perf, "compare single vs multi"),
+		OPT_INTEGER('a', "analyze", &analyze, "analyze different multi sizes"),
+		OPT_INTEGER(0, "step", &analyze_step, "analyze step factor"),
+		OPT_END(),
+	};
+	const char *prefix;
+	uint64_t avg_single, avg_multi;
+
+	prefix = setup_git_directory();
+
+	argc = parse_options(argc, argv, prefix, options, usage, 0);
+
+	/*
+	 * istate->dir_hash is only created when ignore_case is set.
+	 */
+	ignore_case = 1;
+
+	if (dump) {
+		if (perf || analyze > 0)
+			die("cannot combine dump, perf, or analyze");
+		if (count > 1)
+			die("count not valid with dump");
+		if (single && multi)
+			die("cannot use both single and multi with dump");
+		if (!single && !multi)
+			die("dump requires either single or multi");
+		dump_run();
+		return 0;
+	}
+
+	if (perf) {
+		if (analyze > 0)
+			die("cannot combine dump, perf, or analyze");
+		if (single || multi)
+			die("cannot use single or multi with perf");
+		avg_single = time_runs(0);
+		avg_multi = time_runs(1);
+		if (avg_multi > avg_single)
+			die("multi is slower");
+		return 0;
+	}
+
+	if (analyze) {
+		if (analyze < 500)
+			die("analyze must be at least 500");
+		if (!analyze_step)
+			analyze_step = analyze;
+		if (single || multi)
+			die("cannot use single or multi with analyze");
+		analyze_run();
+		return 0;
+	}
+
+	if (!single && !multi)
+		die("require either -s or -m or both");
+
+	if (single)
+		time_runs(0);
+	if (multi)
+		time_runs(1);
+
+	return 0;
+}
diff --git a/t/helper/test-line-buffer.c b/t/helper/test-line-buffer.c
new file mode 100644
index 000000000000..078dd7e29d08
--- /dev/null
+++ b/t/helper/test-line-buffer.c
@@ -0,0 +1,81 @@
+/*
+ * test-line-buffer.c: code to exercise the svn importer's input helper
+ */
+
+#include "git-compat-util.h"
+#include "strbuf.h"
+#include "vcs-svn/line_buffer.h"
+
+static uint32_t strtouint32(const char *s)
+{
+	char *end;
+	uintmax_t n = strtoumax(s, &end, 10);
+	if (*s == '\0' || *end != '\0')
+		die("invalid count: %s", s);
+	return (uint32_t) n;
+}
+
+static void handle_command(const char *command, const char *arg, struct line_buffer *buf)
+{
+	if (starts_with(command, "binary ")) {
+		struct strbuf sb = STRBUF_INIT;
+		strbuf_addch(&sb, '>');
+		buffer_read_binary(buf, &sb, strtouint32(arg));
+		fwrite(sb.buf, 1, sb.len, stdout);
+		strbuf_release(&sb);
+	} else if (starts_with(command, "copy ")) {
+		buffer_copy_bytes(buf, strtouint32(arg));
+	} else if (starts_with(command, "skip ")) {
+		buffer_skip_bytes(buf, strtouint32(arg));
+	} else {
+		die("unrecognized command: %s", command);
+	}
+}
+
+static void handle_line(const char *line, struct line_buffer *stdin_buf)
+{
+	const char *arg = strchr(line, ' ');
+	if (!arg)
+		die("no argument in line: %s", line);
+	handle_command(line, arg + 1, stdin_buf);
+}
+
+int cmd_main(int argc, const char **argv)
+{
+	struct line_buffer stdin_buf = LINE_BUFFER_INIT;
+	struct line_buffer file_buf = LINE_BUFFER_INIT;
+	struct line_buffer *input = &stdin_buf;
+	const char *filename;
+	char *s;
+
+	if (argc == 1)
+		filename = NULL;
+	else if (argc == 2)
+		filename = argv[1];
+	else
+		usage("test-line-buffer [file | &fd] < script");
+
+	if (buffer_init(&stdin_buf, NULL))
+		die_errno("open error");
+	if (filename) {
+		if (*filename == '&') {
+			if (buffer_fdinit(&file_buf, strtouint32(filename + 1)))
+				die_errno("error opening fd %s", filename + 1);
+		} else {
+			if (buffer_init(&file_buf, filename))
+				die_errno("error opening %s", filename);
+		}
+		input = &file_buf;
+	}
+
+	while ((s = buffer_read_line(&stdin_buf)))
+		handle_line(s, input);
+
+	if (filename && buffer_deinit(&file_buf))
+		die("error reading from %s", filename);
+	if (buffer_deinit(&stdin_buf))
+		die("input error");
+	if (ferror(stdout))
+		die("output error");
+	return 0;
+}
diff --git a/t/helper/test-match-trees.c b/t/helper/test-match-trees.c
new file mode 100644
index 000000000000..b9fd427571e6
--- /dev/null
+++ b/t/helper/test-match-trees.c
@@ -0,0 +1,27 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "tree.h"
+
+int cmd__match_trees(int ac, const char **av)
+{
+	struct object_id hash1, hash2, shifted;
+	struct tree *one, *two;
+
+	setup_git_directory();
+
+	if (get_oid(av[1], &hash1))
+		die("cannot parse %s as an object name", av[1]);
+	if (get_oid(av[2], &hash2))
+		die("cannot parse %s as an object name", av[2]);
+	one = parse_tree_indirect(&hash1);
+	if (!one)
+		die("not a tree-ish %s", av[1]);
+	two = parse_tree_indirect(&hash2);
+	if (!two)
+		die("not a tree-ish %s", av[2]);
+
+	shift_tree(the_repository, &one->object.oid, &two->object.oid, &shifted, -1);
+	printf("shifted: %s\n", oid_to_hex(&shifted));
+
+	exit(0);
+}
diff --git a/t/helper/test-mergesort.c b/t/helper/test-mergesort.c
new file mode 100644
index 000000000000..c5cffaa4b73f
--- /dev/null
+++ b/t/helper/test-mergesort.c
@@ -0,0 +1,53 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "mergesort.h"
+
+struct line {
+	char *text;
+	struct line *next;
+};
+
+static void *get_next(const void *a)
+{
+	return ((const struct line *)a)->next;
+}
+
+static void set_next(void *a, void *b)
+{
+	((struct line *)a)->next = b;
+}
+
+static int compare_strings(const void *a, const void *b)
+{
+	const struct line *x = a, *y = b;
+	return strcmp(x->text, y->text);
+}
+
+int cmd__mergesort(int argc, const char **argv)
+{
+	struct line *line, *p = NULL, *lines = NULL;
+	struct strbuf sb = STRBUF_INIT;
+
+	for (;;) {
+		if (strbuf_getwholeline(&sb, stdin, '\n'))
+			break;
+		line = xmalloc(sizeof(struct line));
+		line->text = strbuf_detach(&sb, NULL);
+		if (p) {
+			line->next = p->next;
+			p->next = line;
+		} else {
+			line->next = NULL;
+			lines = line;
+		}
+		p = line;
+	}
+
+	lines = llist_mergesort(lines, get_next, set_next, compare_strings);
+
+	while (lines) {
+		printf("%s", lines->text);
+		lines = lines->next;
+	}
+	return 0;
+}
diff --git a/t/helper/test-mktemp.c b/t/helper/test-mktemp.c
new file mode 100644
index 000000000000..229068894029
--- /dev/null
+++ b/t/helper/test-mktemp.c
@@ -0,0 +1,15 @@
+/*
+ * test-mktemp.c: code to exercise the creation of temporary files
+ */
+#include "test-tool.h"
+#include "git-compat-util.h"
+
+int cmd__mktemp(int argc, const char **argv)
+{
+	if (argc != 2)
+		usage("Expected 1 parameter defining the temporary file template");
+
+	xmkstemp(xstrdup(argv[1]));
+
+	return 0;
+}
diff --git a/t/helper/test-oidmap.c b/t/helper/test-oidmap.c
new file mode 100644
index 000000000000..0acf99931ee1
--- /dev/null
+++ b/t/helper/test-oidmap.c
@@ -0,0 +1,112 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "oidmap.h"
+#include "strbuf.h"
+
+/* key is an oid and value is a name (could be a refname for example) */
+struct test_entry {
+	struct oidmap_entry entry;
+	char name[FLEX_ARRAY];
+};
+
+#define DELIM " \t\r\n"
+
+/*
+ * Read stdin line by line and print result of commands to stdout:
+ *
+ * hash oidkey -> sha1hash(oidkey)
+ * put oidkey namevalue -> NULL / old namevalue
+ * get oidkey -> NULL / namevalue
+ * remove oidkey -> NULL / old namevalue
+ * iterate -> oidkey1 namevalue1\noidkey2 namevalue2\n...
+ *
+ */
+int cmd__oidmap(int argc, const char **argv)
+{
+	struct strbuf line = STRBUF_INIT;
+	struct oidmap map = OIDMAP_INIT;
+
+	setup_git_directory();
+
+	/* init oidmap */
+	oidmap_init(&map, 0);
+
+	/* process commands from stdin */
+	while (strbuf_getline(&line, stdin) != EOF) {
+		char *cmd, *p1 = NULL, *p2 = NULL;
+		struct test_entry *entry;
+		struct object_id oid;
+
+		/* break line into command and up to two parameters */
+		cmd = strtok(line.buf, DELIM);
+		/* ignore empty lines */
+		if (!cmd || *cmd == '#')
+			continue;
+
+		p1 = strtok(NULL, DELIM);
+		if (p1)
+			p2 = strtok(NULL, DELIM);
+
+		if (!strcmp("put", cmd) && p1 && p2) {
+
+			if (get_oid(p1, &oid)) {
+				printf("Unknown oid: %s\n", p1);
+				continue;
+			}
+
+			/* create entry with oid_key = p1, name_value = p2 */
+			FLEX_ALLOC_STR(entry, name, p2);
+			oidcpy(&entry->entry.oid, &oid);
+
+			/* add / replace entry */
+			entry = oidmap_put(&map, entry);
+
+			/* print and free replaced entry, if any */
+			puts(entry ? entry->name : "NULL");
+			free(entry);
+
+		} else if (!strcmp("get", cmd) && p1) {
+
+			if (get_oid(p1, &oid)) {
+				printf("Unknown oid: %s\n", p1);
+				continue;
+			}
+
+			/* lookup entry in oidmap */
+			entry = oidmap_get(&map, &oid);
+
+			/* print result */
+			puts(entry ? entry->name : "NULL");
+
+		} else if (!strcmp("remove", cmd) && p1) {
+
+			if (get_oid(p1, &oid)) {
+				printf("Unknown oid: %s\n", p1);
+				continue;
+			}
+
+			/* remove entry from oidmap */
+			entry = oidmap_remove(&map, &oid);
+
+			/* print result and free entry*/
+			puts(entry ? entry->name : "NULL");
+			free(entry);
+
+		} else if (!strcmp("iterate", cmd)) {
+
+			struct oidmap_iter iter;
+			oidmap_iter_init(&map, &iter);
+			while ((entry = oidmap_iter_next(&iter)))
+				printf("%s %s\n", oid_to_hex(&entry->entry.oid), entry->name);
+
+		} else {
+
+			printf("Unknown command %s\n", cmd);
+
+		}
+	}
+
+	strbuf_release(&line);
+	oidmap_free(&map, 1);
+	return 0;
+}
diff --git a/t/helper/test-online-cpus.c b/t/helper/test-online-cpus.c
new file mode 100644
index 000000000000..8cb0d53840f3
--- /dev/null
+++ b/t/helper/test-online-cpus.c
@@ -0,0 +1,9 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "thread-utils.h"
+
+int cmd__online_cpus(int argc, const char **argv)
+{
+	printf("%d\n", online_cpus());
+	return 0;
+}
diff --git a/t/helper/test-parse-options.c b/t/helper/test-parse-options.c
new file mode 100644
index 000000000000..af82db06ac59
--- /dev/null
+++ b/t/helper/test-parse-options.c
@@ -0,0 +1,188 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "parse-options.h"
+#include "string-list.h"
+#include "trace2.h"
+
+static int boolean = 0;
+static int integer = 0;
+static unsigned long magnitude = 0;
+static timestamp_t timestamp;
+static int abbrev = 7;
+static int verbose = -1; /* unspecified */
+static int dry_run = 0, quiet = 0;
+static char *string = NULL;
+static char *file = NULL;
+static int ambiguous;
+static struct string_list list = STRING_LIST_INIT_NODUP;
+
+static struct {
+	int called;
+	const char *arg;
+	int unset;
+} length_cb;
+
+static int length_callback(const struct option *opt, const char *arg, int unset)
+{
+	length_cb.called = 1;
+	length_cb.arg = arg;
+	length_cb.unset = unset;
+
+	if (unset)
+		return 1; /* do not support unset */
+
+	*(int *)opt->value = strlen(arg);
+	return 0;
+}
+
+static int number_callback(const struct option *opt, const char *arg, int unset)
+{
+	BUG_ON_OPT_NEG(unset);
+	*(int *)opt->value = strtol(arg, NULL, 10);
+	return 0;
+}
+
+static int collect_expect(const struct option *opt, const char *arg, int unset)
+{
+	struct string_list *expect;
+	struct string_list_item *item;
+	struct strbuf label = STRBUF_INIT;
+	const char *colon;
+
+	if (!arg || unset)
+		die("malformed --expect option");
+
+	expect = (struct string_list *)opt->value;
+	colon = strchr(arg, ':');
+	if (!colon)
+		die("malformed --expect option, lacking a colon");
+	strbuf_add(&label, arg, colon - arg);
+	item = string_list_insert(expect, strbuf_detach(&label, NULL));
+	if (item->util)
+		die("malformed --expect option, duplicate %s", label.buf);
+	item->util = (void *)arg;
+	return 0;
+}
+
+__attribute__((format (printf,3,4)))
+static void show(struct string_list *expect, int *status, const char *fmt, ...)
+{
+	struct string_list_item *item;
+	struct strbuf buf = STRBUF_INIT;
+	va_list args;
+
+	va_start(args, fmt);
+	strbuf_vaddf(&buf, fmt, args);
+	va_end(args);
+
+	if (!expect->nr)
+		printf("%s\n", buf.buf);
+	else {
+		char *colon = strchr(buf.buf, ':');
+		if (!colon)
+			die("malformed output format, output lacking colon: %s", fmt);
+		*colon = '\0';
+		item = string_list_lookup(expect, buf.buf);
+		*colon = ':';
+		if (!item)
+			; /* not among entries being checked */
+		else {
+			if (strcmp((const char *)item->util, buf.buf)) {
+				printf("-%s\n", (char *)item->util);
+				printf("+%s\n", buf.buf);
+				*status = 1;
+			}
+		}
+	}
+	strbuf_release(&buf);
+}
+
+int cmd__parse_options(int argc, const char **argv)
+{
+	const char *prefix = "prefix/";
+	const char *usage[] = {
+		"test-tool parse-options <options>",
+		"",
+		"A helper function for the parse-options API.",
+		NULL
+	};
+	struct string_list expect = STRING_LIST_INIT_NODUP;
+	struct option options[] = {
+		OPT_BOOL(0, "yes", &boolean, "get a boolean"),
+		OPT_BOOL('D', "no-doubt", &boolean, "begins with 'no-'"),
+		{ OPTION_SET_INT, 'B', "no-fear", &boolean, NULL,
+		  "be brave", PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
+		OPT_COUNTUP('b', "boolean", &boolean, "increment by one"),
+		OPT_BIT('4', "or4", &boolean,
+			"bitwise-or boolean with ...0100", 4),
+		OPT_NEGBIT(0, "neg-or4", &boolean, "same as --no-or4", 4),
+		OPT_GROUP(""),
+		OPT_INTEGER('i', "integer", &integer, "get a integer"),
+		OPT_INTEGER('j', NULL, &integer, "get a integer, too"),
+		OPT_MAGNITUDE('m', "magnitude", &magnitude, "get a magnitude"),
+		OPT_SET_INT(0, "set23", &integer, "set integer to 23", 23),
+		OPT_CALLBACK('L', "length", &integer, "str",
+			"get length of <str>", length_callback),
+		OPT_FILENAME('F', "file", &file, "set file to <file>"),
+		OPT_GROUP("String options"),
+		OPT_STRING('s', "string", &string, "string", "get a string"),
+		OPT_STRING(0, "string2", &string, "str", "get another string"),
+		OPT_STRING(0, "st", &string, "st", "get another string (pervert ordering)"),
+		OPT_STRING('o', NULL, &string, "str", "get another string"),
+		OPT_NOOP_NOARG(0, "obsolete"),
+		OPT_STRING_LIST(0, "list", &list, "str", "add str to list"),
+		OPT_GROUP("Magic arguments"),
+		OPT_ARGUMENT("quux", NULL, "means --quux"),
+		OPT_NUMBER_CALLBACK(&integer, "set integer to NUM",
+			number_callback),
+		{ OPTION_COUNTUP, '+', NULL, &boolean, NULL, "same as -b",
+		  PARSE_OPT_NOARG | PARSE_OPT_NONEG | PARSE_OPT_NODASH },
+		{ OPTION_COUNTUP, 0, "ambiguous", &ambiguous, NULL,
+		  "positive ambiguity", PARSE_OPT_NOARG | PARSE_OPT_NONEG },
+		{ OPTION_COUNTUP, 0, "no-ambiguous", &ambiguous, NULL,
+		  "negative ambiguity", PARSE_OPT_NOARG | PARSE_OPT_NONEG },
+		OPT_GROUP("Standard options"),
+		OPT__ABBREV(&abbrev),
+		OPT__VERBOSE(&verbose, "be verbose"),
+		OPT__DRY_RUN(&dry_run, "dry run"),
+		OPT__QUIET(&quiet, "be quiet"),
+		OPT_CALLBACK(0, "expect", &expect, "string",
+			     "expected output in the variable dump",
+			     collect_expect),
+		OPT_GROUP("Alias"),
+		OPT_STRING('A', "alias-source", &string, "string", "get a string"),
+		OPT_ALIAS('Z', "alias-target", "alias-source"),
+		OPT_END(),
+	};
+	int i;
+	int ret = 0;
+
+	trace2_cmd_name("_parse_");
+
+	argc = parse_options(argc, (const char **)argv, prefix, options, usage, 0);
+
+	if (length_cb.called) {
+		const char *arg = length_cb.arg;
+		int unset = length_cb.unset;
+		show(&expect, &ret, "Callback: \"%s\", %d",
+		     (arg ? arg : "not set"), unset);
+	}
+	show(&expect, &ret, "boolean: %d", boolean);
+	show(&expect, &ret, "integer: %d", integer);
+	show(&expect, &ret, "magnitude: %lu", magnitude);
+	show(&expect, &ret, "timestamp: %"PRItime, timestamp);
+	show(&expect, &ret, "string: %s", string ? string : "(not set)");
+	show(&expect, &ret, "abbrev: %d", abbrev);
+	show(&expect, &ret, "verbose: %d", verbose);
+	show(&expect, &ret, "quiet: %d", quiet);
+	show(&expect, &ret, "dry run: %s", dry_run ? "yes" : "no");
+	show(&expect, &ret, "file: %s", file ? file : "(not set)");
+
+	for (i = 0; i < list.nr; i++)
+		show(&expect, &ret, "list: %s", list.items[i].string);
+
+	for (i = 0; i < argc; i++)
+		show(&expect, &ret, "arg %02d: %s", i, argv[i]);
+
+	return ret;
+}
diff --git a/t/helper/test-path-utils.c b/t/helper/test-path-utils.c
new file mode 100644
index 000000000000..5d543ad21f89
--- /dev/null
+++ b/t/helper/test-path-utils.c
@@ -0,0 +1,361 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "string-list.h"
+#include "utf8.h"
+
+/*
+ * A "string_list_each_func_t" function that normalizes an entry from
+ * GIT_CEILING_DIRECTORIES.  If the path is unusable for some reason,
+ * die with an explanation.
+ */
+static int normalize_ceiling_entry(struct string_list_item *item, void *unused)
+{
+	char *ceil = item->string;
+
+	if (!*ceil)
+		die("Empty path is not supported");
+	if (!is_absolute_path(ceil))
+		die("Path \"%s\" is not absolute", ceil);
+	if (normalize_path_copy(ceil, ceil) < 0)
+		die("Path \"%s\" could not be normalized", ceil);
+	return 1;
+}
+
+static void normalize_argv_string(const char **var, const char *input)
+{
+	if (!strcmp(input, "<null>"))
+		*var = NULL;
+	else if (!strcmp(input, "<empty>"))
+		*var = "";
+	else
+		*var = input;
+
+	if (*var && (**var == '<' || **var == '('))
+		die("Bad value: %s\n", input);
+}
+
+struct test_data {
+	const char *from;  /* input:  transform from this ... */
+	const char *to;    /* output: ... to this.            */
+	const char *alternative; /* output: ... or this.      */
+};
+
+/*
+ * Compatibility wrappers for OpenBSD, whose basename(3) and dirname(3)
+ * have const parameters.
+ */
+static char *posix_basename(char *path)
+{
+	return basename(path);
+}
+
+static char *posix_dirname(char *path)
+{
+	return dirname(path);
+}
+
+static int test_function(struct test_data *data, char *(*func)(char *input),
+	const char *funcname)
+{
+	int failed = 0, i;
+	char buffer[1024];
+	char *to;
+
+	for (i = 0; data[i].to; i++) {
+		if (!data[i].from)
+			to = func(NULL);
+		else {
+			xsnprintf(buffer, sizeof(buffer), "%s", data[i].from);
+			to = func(buffer);
+		}
+		if (!strcmp(to, data[i].to))
+			continue;
+		if (!data[i].alternative)
+			error("FAIL: %s(%s) => '%s' != '%s'\n",
+				funcname, data[i].from, to, data[i].to);
+		else if (!strcmp(to, data[i].alternative))
+			continue;
+		else
+			error("FAIL: %s(%s) => '%s' != '%s', '%s'\n",
+				funcname, data[i].from, to, data[i].to,
+				data[i].alternative);
+		failed = 1;
+	}
+	return failed;
+}
+
+static struct test_data basename_data[] = {
+	/* --- POSIX type paths --- */
+	{ NULL,              "."    },
+	{ "",                "."    },
+	{ ".",               "."    },
+	{ "..",              ".."   },
+	{ "/",               "/"    },
+	{ "//",              "/", "//" },
+	{ "///",             "/", "//" },
+	{ "////",            "/", "//" },
+	{ "usr",             "usr"  },
+	{ "/usr",            "usr"  },
+	{ "/usr/",           "usr"  },
+	{ "/usr//",          "usr"  },
+	{ "/usr/lib",        "lib"  },
+	{ "usr/lib",         "lib"  },
+	{ "usr/lib///",      "lib"  },
+
+#if defined(__MINGW32__) || defined(_MSC_VER)
+	/* --- win32 type paths --- */
+	{ "\\usr",           "usr"  },
+	{ "\\usr\\",         "usr"  },
+	{ "\\usr\\\\",       "usr"  },
+	{ "\\usr\\lib",      "lib"  },
+	{ "usr\\lib",        "lib"  },
+	{ "usr\\lib\\\\\\",  "lib"  },
+	{ "C:/usr",          "usr"  },
+	{ "C:/usr",          "usr"  },
+	{ "C:/usr/",         "usr"  },
+	{ "C:/usr//",        "usr"  },
+	{ "C:/usr/lib",      "lib"  },
+	{ "C:usr/lib",       "lib"  },
+	{ "C:usr/lib///",    "lib"  },
+	{ "C:",              "."    },
+	{ "C:a",             "a"    },
+	{ "C:/",             "/"    },
+	{ "C:///",           "/"    },
+	{ "\\",              "\\", "/" },
+	{ "\\\\",            "\\", "/" },
+	{ "\\\\\\",          "\\", "/" },
+#endif
+	{ NULL,              NULL   }
+};
+
+static struct test_data dirname_data[] = {
+	/* --- POSIX type paths --- */
+	{ NULL,              "."      },
+	{ "",                "."      },
+	{ ".",               "."      },
+	{ "..",              "."      },
+	{ "/",               "/"      },
+	{ "//",              "/", "//" },
+	{ "///",             "/", "//" },
+	{ "////",            "/", "//" },
+	{ "usr",             "."      },
+	{ "/usr",            "/"      },
+	{ "/usr/",           "/"      },
+	{ "/usr//",          "/"      },
+	{ "/usr/lib",        "/usr"   },
+	{ "usr/lib",         "usr"    },
+	{ "usr/lib///",      "usr"    },
+
+#if defined(__MINGW32__) || defined(_MSC_VER)
+	/* --- win32 type paths --- */
+	{ "\\",              "\\"     },
+	{ "\\\\",            "\\\\"   },
+	{ "\\usr",           "\\"     },
+	{ "\\usr\\",         "\\"     },
+	{ "\\usr\\\\",       "\\"     },
+	{ "\\usr\\lib",      "\\usr"  },
+	{ "usr\\lib",        "usr"    },
+	{ "usr\\lib\\\\\\",  "usr"    },
+	{ "C:a",             "C:."    },
+	{ "C:/",             "C:/"    },
+	{ "C:///",           "C:/"    },
+	{ "C:/usr",          "C:/"    },
+	{ "C:/usr/",         "C:/"    },
+	{ "C:/usr//",        "C:/"    },
+	{ "C:/usr/lib",      "C:/usr" },
+	{ "C:usr/lib",       "C:usr"  },
+	{ "C:usr/lib///",    "C:usr"  },
+	{ "\\\\\\",          "\\"     },
+	{ "\\\\\\\\",        "\\"     },
+	{ "C:",              "C:.", "." },
+#endif
+	{ NULL,              NULL     }
+};
+
+static int is_dotgitmodules(const char *path)
+{
+	return is_hfs_dotgitmodules(path) || is_ntfs_dotgitmodules(path);
+}
+
+static int cmp_by_st_size(const void *a, const void *b)
+{
+	intptr_t x = (intptr_t)((struct string_list_item *)a)->util;
+	intptr_t y = (intptr_t)((struct string_list_item *)b)->util;
+
+	return x > y ? -1 : (x < y ? +1 : 0);
+}
+
+int cmd__path_utils(int argc, const char **argv)
+{
+	if (argc == 3 && !strcmp(argv[1], "normalize_path_copy")) {
+		char *buf = xmallocz(strlen(argv[2]));
+		int rv = normalize_path_copy(buf, argv[2]);
+		if (rv)
+			buf = "++failed++";
+		puts(buf);
+		return 0;
+	}
+
+	if (argc >= 2 && !strcmp(argv[1], "real_path")) {
+		while (argc > 2) {
+			puts(real_path(argv[2]));
+			argc--;
+			argv++;
+		}
+		return 0;
+	}
+
+	if (argc >= 2 && !strcmp(argv[1], "absolute_path")) {
+		while (argc > 2) {
+			puts(absolute_path(argv[2]));
+			argc--;
+			argv++;
+		}
+		return 0;
+	}
+
+	if (argc == 4 && !strcmp(argv[1], "longest_ancestor_length")) {
+		int len;
+		struct string_list ceiling_dirs = STRING_LIST_INIT_DUP;
+		char *path = xstrdup(argv[2]);
+
+		/*
+		 * We have to normalize the arguments because under
+		 * Windows, bash mangles arguments that look like
+		 * absolute POSIX paths or colon-separate lists of
+		 * absolute POSIX paths into DOS paths (e.g.,
+		 * "/foo:/foo/bar" might be converted to
+		 * "D:\Src\msysgit\foo;D:\Src\msysgit\foo\bar"),
+		 * whereas longest_ancestor_length() requires paths
+		 * that use forward slashes.
+		 */
+		if (normalize_path_copy(path, path))
+			die("Path \"%s\" could not be normalized", argv[2]);
+		string_list_split(&ceiling_dirs, argv[3], PATH_SEP, -1);
+		filter_string_list(&ceiling_dirs, 0,
+				   normalize_ceiling_entry, NULL);
+		len = longest_ancestor_length(path, &ceiling_dirs);
+		string_list_clear(&ceiling_dirs, 0);
+		free(path);
+		printf("%d\n", len);
+		return 0;
+	}
+
+	if (argc >= 4 && !strcmp(argv[1], "prefix_path")) {
+		const char *prefix = argv[2];
+		int prefix_len = strlen(prefix);
+		int nongit_ok;
+		setup_git_directory_gently(&nongit_ok);
+		while (argc > 3) {
+			puts(prefix_path(prefix, prefix_len, argv[3]));
+			argc--;
+			argv++;
+		}
+		return 0;
+	}
+
+	if (argc == 4 && !strcmp(argv[1], "strip_path_suffix")) {
+		char *prefix = strip_path_suffix(argv[2], argv[3]);
+		printf("%s\n", prefix ? prefix : "(null)");
+		return 0;
+	}
+
+	if (argc == 3 && !strcmp(argv[1], "print_path")) {
+		puts(argv[2]);
+		return 0;
+	}
+
+	if (argc == 4 && !strcmp(argv[1], "relative_path")) {
+		struct strbuf sb = STRBUF_INIT;
+		const char *in, *prefix, *rel;
+		normalize_argv_string(&in, argv[2]);
+		normalize_argv_string(&prefix, argv[3]);
+		rel = relative_path(in, prefix, &sb);
+		if (!rel)
+			puts("(null)");
+		else
+			puts(strlen(rel) > 0 ? rel : "(empty)");
+		strbuf_release(&sb);
+		return 0;
+	}
+
+	if (argc == 2 && !strcmp(argv[1], "basename"))
+		return test_function(basename_data, posix_basename, argv[1]);
+
+	if (argc == 2 && !strcmp(argv[1], "dirname"))
+		return test_function(dirname_data, posix_dirname, argv[1]);
+
+	if (argc > 2 && !strcmp(argv[1], "is_dotgitmodules")) {
+		int res = 0, expect = 1, i;
+		for (i = 2; i < argc; i++)
+			if (!strcmp("--not", argv[i]))
+				expect = !expect;
+			else if (expect != is_dotgitmodules(argv[i]))
+				res = error("'%s' is %s.gitmodules", argv[i],
+					    expect ? "not " : "");
+			else
+				fprintf(stderr, "ok: '%s' is %s.gitmodules\n",
+					argv[i], expect ? "" : "not ");
+		return !!res;
+	}
+
+	if (argc > 2 && !strcmp(argv[1], "file-size")) {
+		int res = 0, i;
+		struct stat st;
+
+		for (i = 2; i < argc; i++)
+			if (stat(argv[i], &st))
+				res = error_errno("Cannot stat '%s'", argv[i]);
+			else
+				printf("%"PRIuMAX"\n", (uintmax_t)st.st_size);
+		return !!res;
+	}
+
+	if (argc == 4 && !strcmp(argv[1], "skip-n-bytes")) {
+		int fd = open(argv[2], O_RDONLY), offset = atoi(argv[3]);
+		char buffer[65536];
+
+		if (fd < 0)
+			die_errno("could not open '%s'", argv[2]);
+		if (lseek(fd, offset, SEEK_SET) < 0)
+			die_errno("could not skip %d bytes", offset);
+		for (;;) {
+			ssize_t count = read(fd, buffer, sizeof(buffer));
+			if (count < 0)
+				die_errno("could not read '%s'", argv[2]);
+			if (!count)
+				break;
+			if (write(1, buffer, count) < 0)
+				die_errno("could not write to stdout");
+		}
+		close(fd);
+		return 0;
+	}
+
+	if (argc > 5 && !strcmp(argv[1], "slice-tests")) {
+		int res = 0;
+		long offset, stride, i;
+		struct string_list list = STRING_LIST_INIT_NODUP;
+		struct stat st;
+
+		offset = strtol(argv[2], NULL, 10);
+		stride = strtol(argv[3], NULL, 10);
+		if (stride < 1)
+			stride = 1;
+		for (i = 4; i < argc; i++)
+			if (stat(argv[i], &st))
+				res = error_errno("Cannot stat '%s'", argv[i]);
+			else
+				string_list_append(&list, argv[i])->util =
+					(void *)(intptr_t)st.st_size;
+		QSORT(list.items, list.nr, cmp_by_st_size);
+		for (i = offset; i < list.nr; i+= stride)
+			printf("%s\n", list.items[i].string);
+
+		return !!res;
+	}
+
+	fprintf(stderr, "%s: unknown function name: %s\n", argv[0],
+		argv[1] ? argv[1] : "(there was none)");
+	return 1;
+}
diff --git a/t/helper/test-pkt-line.c b/t/helper/test-pkt-line.c
new file mode 100644
index 000000000000..282d53638446
--- /dev/null
+++ b/t/helper/test-pkt-line.c
@@ -0,0 +1,98 @@
+#include "cache.h"
+#include "test-tool.h"
+#include "pkt-line.h"
+
+static void pack_line(const char *line)
+{
+	if (!strcmp(line, "0000") || !strcmp(line, "0000\n"))
+		packet_flush(1);
+	else if (!strcmp(line, "0001") || !strcmp(line, "0001\n"))
+		packet_delim(1);
+	else
+		packet_write_fmt(1, "%s", line);
+}
+
+static void pack(int argc, const char **argv)
+{
+	if (argc) { /* read from argv */
+		int i;
+		for (i = 0; i < argc; i++)
+			pack_line(argv[i]);
+	} else { /* read from stdin */
+		char line[LARGE_PACKET_MAX];
+		while (fgets(line, sizeof(line), stdin)) {
+			pack_line(line);
+		}
+	}
+}
+
+static void unpack(void)
+{
+	struct packet_reader reader;
+	packet_reader_init(&reader, 0, NULL, 0,
+			   PACKET_READ_GENTLE_ON_EOF |
+			   PACKET_READ_CHOMP_NEWLINE);
+
+	while (packet_reader_read(&reader) != PACKET_READ_EOF) {
+		switch (reader.status) {
+		case PACKET_READ_EOF:
+			break;
+		case PACKET_READ_NORMAL:
+			printf("%s\n", reader.line);
+			break;
+		case PACKET_READ_FLUSH:
+			printf("0000\n");
+			break;
+		case PACKET_READ_DELIM:
+			printf("0001\n");
+			break;
+		}
+	}
+}
+
+static void unpack_sideband(void)
+{
+	struct packet_reader reader;
+	packet_reader_init(&reader, 0, NULL, 0,
+			   PACKET_READ_GENTLE_ON_EOF |
+			   PACKET_READ_CHOMP_NEWLINE);
+
+	while (packet_reader_read(&reader) != PACKET_READ_EOF) {
+		int band;
+		int fd;
+
+		switch (reader.status) {
+		case PACKET_READ_EOF:
+			break;
+		case PACKET_READ_NORMAL:
+			band = reader.line[0] & 0xff;
+			if (band < 1 || band > 2)
+				die("unexpected side band %d", band);
+			fd = band;
+
+			write_or_die(fd, reader.line + 1, reader.pktlen - 1);
+			break;
+		case PACKET_READ_FLUSH:
+			return;
+		case PACKET_READ_DELIM:
+			break;
+		}
+	}
+}
+
+int cmd__pkt_line(int argc, const char **argv)
+{
+	if (argc < 2)
+		die("too few arguments");
+
+	if (!strcmp(argv[1], "pack"))
+		pack(argc - 2, argv + 2);
+	else if (!strcmp(argv[1], "unpack"))
+		unpack();
+	else if (!strcmp(argv[1], "unpack-sideband"))
+		unpack_sideband();
+	else
+		die("invalid argument '%s'", argv[1]);
+
+	return 0;
+}
diff --git a/t/helper/test-prio-queue.c b/t/helper/test-prio-queue.c
new file mode 100644
index 000000000000..f4028442e37e
--- /dev/null
+++ b/t/helper/test-prio-queue.c
@@ -0,0 +1,50 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "prio-queue.h"
+
+static int intcmp(const void *va, const void *vb, void *data)
+{
+	const int *a = va, *b = vb;
+	return *a - *b;
+}
+
+static void show(int *v)
+{
+	if (!v)
+		printf("NULL\n");
+	else
+		printf("%d\n", *v);
+	free(v);
+}
+
+int cmd__prio_queue(int argc, const char **argv)
+{
+	struct prio_queue pq = { intcmp };
+
+	while (*++argv) {
+		if (!strcmp(*argv, "get")) {
+			void *peek = prio_queue_peek(&pq);
+			void *get = prio_queue_get(&pq);
+			if (peek != get)
+				BUG("peek and get results do not match");
+			show(get);
+		} else if (!strcmp(*argv, "dump")) {
+			void *peek;
+			void *get;
+			while ((peek = prio_queue_peek(&pq))) {
+				get = prio_queue_get(&pq);
+				if (peek != get)
+					BUG("peek and get results do not match");
+				show(get);
+			}
+		} else if (!strcmp(*argv, "stack")) {
+			pq.compare = NULL;
+		} else {
+			int *v = xmalloc(sizeof(*v));
+			*v = atoi(*argv);
+			prio_queue_put(&pq, v);
+		}
+	}
+
+	return 0;
+}
diff --git a/t/helper/test-reach.c b/t/helper/test-reach.c
new file mode 100644
index 000000000000..a0272178b779
--- /dev/null
+++ b/t/helper/test-reach.c
@@ -0,0 +1,168 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "commit.h"
+#include "commit-reach.h"
+#include "config.h"
+#include "parse-options.h"
+#include "ref-filter.h"
+#include "string-list.h"
+#include "tag.h"
+
+static void print_sorted_commit_ids(struct commit_list *list)
+{
+	int i;
+	struct string_list s = STRING_LIST_INIT_DUP;
+
+	while (list) {
+		string_list_append(&s, oid_to_hex(&list->item->object.oid));
+		list = list->next;
+	}
+
+	string_list_sort(&s);
+
+	for (i = 0; i < s.nr; i++)
+		printf("%s\n", s.items[i].string);
+
+	string_list_clear(&s, 0);
+}
+
+int cmd__reach(int ac, const char **av)
+{
+	struct object_id oid_A, oid_B;
+	struct commit *A, *B;
+	struct commit_list *X, *Y;
+	struct object_array X_obj = OBJECT_ARRAY_INIT;
+	struct commit **X_array, **Y_array;
+	int X_nr, X_alloc, Y_nr, Y_alloc;
+	struct strbuf buf = STRBUF_INIT;
+	struct repository *r = the_repository;
+
+	setup_git_directory();
+
+	if (ac < 2)
+		exit(1);
+
+	A = B = NULL;
+	X = Y = NULL;
+	X_nr = Y_nr = 0;
+	X_alloc = Y_alloc = 16;
+	ALLOC_ARRAY(X_array, X_alloc);
+	ALLOC_ARRAY(Y_array, Y_alloc);
+
+	while (strbuf_getline(&buf, stdin) != EOF) {
+		struct object_id oid;
+		struct object *orig;
+		struct object *peeled;
+		struct commit *c;
+		if (buf.len < 3)
+			continue;
+
+		if (get_oid_committish(buf.buf + 2, &oid))
+			die("failed to resolve %s", buf.buf + 2);
+
+		orig = parse_object(r, &oid);
+		peeled = deref_tag_noverify(orig);
+
+		if (!peeled)
+			die("failed to load commit for input %s resulting in oid %s\n",
+			    buf.buf, oid_to_hex(&oid));
+
+		c = object_as_type(r, peeled, OBJ_COMMIT, 0);
+
+		if (!c)
+			die("failed to load commit for input %s resulting in oid %s\n",
+			    buf.buf, oid_to_hex(&oid));
+
+		switch (buf.buf[0]) {
+			case 'A':
+				oidcpy(&oid_A, &oid);
+				A = c;
+				break;
+
+			case 'B':
+				oidcpy(&oid_B, &oid);
+				B = c;
+				break;
+
+			case 'X':
+				commit_list_insert(c, &X);
+				ALLOC_GROW(X_array, X_nr + 1, X_alloc);
+				X_array[X_nr++] = c;
+				add_object_array(orig, NULL, &X_obj);
+				break;
+
+			case 'Y':
+				commit_list_insert(c, &Y);
+				ALLOC_GROW(Y_array, Y_nr + 1, Y_alloc);
+				Y_array[Y_nr++] = c;
+				break;
+
+			default:
+				die("unexpected start of line: %c", buf.buf[0]);
+		}
+	}
+	strbuf_release(&buf);
+
+	if (!strcmp(av[1], "ref_newer"))
+		printf("%s(A,B):%d\n", av[1], ref_newer(&oid_A, &oid_B));
+	else if (!strcmp(av[1], "in_merge_bases"))
+		printf("%s(A,B):%d\n", av[1], in_merge_bases(A, B));
+	else if (!strcmp(av[1], "is_descendant_of"))
+		printf("%s(A,X):%d\n", av[1], is_descendant_of(A, X));
+	else if (!strcmp(av[1], "get_merge_bases_many")) {
+		struct commit_list *list = get_merge_bases_many(A, X_nr, X_array);
+		printf("%s(A,X):\n", av[1]);
+		print_sorted_commit_ids(list);
+	} else if (!strcmp(av[1], "reduce_heads")) {
+		struct commit_list *list = reduce_heads(X);
+		printf("%s(X):\n", av[1]);
+		print_sorted_commit_ids(list);
+	} else if (!strcmp(av[1], "can_all_from_reach")) {
+		printf("%s(X,Y):%d\n", av[1], can_all_from_reach(X, Y, 1));
+	} else if (!strcmp(av[1], "can_all_from_reach_with_flag")) {
+		struct commit_list *iter = Y;
+
+		while (iter) {
+			iter->item->object.flags |= 2;
+			iter = iter->next;
+		}
+
+		printf("%s(X,_,_,0,0):%d\n", av[1], can_all_from_reach_with_flag(&X_obj, 2, 4, 0, 0));
+	} else if (!strcmp(av[1], "commit_contains")) {
+		struct ref_filter filter;
+		struct contains_cache cache;
+		init_contains_cache(&cache);
+
+		if (ac > 2 && !strcmp(av[2], "--tag"))
+			filter.with_commit_tag_algo = 1;
+		else
+			filter.with_commit_tag_algo = 0;
+
+		printf("%s(_,A,X,_):%d\n", av[1], commit_contains(&filter, A, X, &cache));
+	} else if (!strcmp(av[1], "get_reachable_subset")) {
+		const int reachable_flag = 1;
+		int i, count = 0;
+		struct commit_list *current;
+		struct commit_list *list = get_reachable_subset(X_array, X_nr,
+								Y_array, Y_nr,
+								reachable_flag);
+		printf("get_reachable_subset(X,Y)\n");
+		for (current = list; current; current = current->next) {
+			if (!(list->item->object.flags & reachable_flag))
+				die(_("commit %s is not marked reachable"),
+				    oid_to_hex(&list->item->object.oid));
+			count++;
+		}
+		for (i = 0; i < Y_nr; i++) {
+			if (Y_array[i]->object.flags & reachable_flag)
+				count--;
+		}
+
+		if (count < 0)
+			die(_("too many commits marked reachable"));
+
+		print_sorted_commit_ids(list);
+	}
+
+	exit(0);
+}
diff --git a/t/helper/test-read-cache.c b/t/helper/test-read-cache.c
new file mode 100644
index 000000000000..7e79b555de80
--- /dev/null
+++ b/t/helper/test-read-cache.c
@@ -0,0 +1,37 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "config.h"
+
+int cmd__read_cache(int argc, const char **argv)
+{
+	int i, cnt = 1, namelen;
+	const char *name = NULL;
+
+	if (argc > 1 && skip_prefix(argv[1], "--print-and-refresh=", &name)) {
+		namelen = strlen(name);
+		argc--;
+		argv++;
+	}
+
+	if (argc == 2)
+		cnt = strtol(argv[1], NULL, 0);
+	setup_git_directory();
+	git_config(git_default_config, NULL);
+	for (i = 0; i < cnt; i++) {
+		read_cache();
+		if (name) {
+			int pos;
+
+			refresh_index(&the_index, REFRESH_QUIET,
+				      NULL, NULL, NULL);
+			pos = index_name_pos(&the_index, name, namelen);
+			if (pos < 0)
+				die("%s not in index", name);
+			printf("%s is%s up to date\n", name,
+			       ce_uptodate(the_index.cache[pos]) ? "" : " not");
+			write_file(name, "%d\n", i);
+		}
+		discard_cache();
+	}
+	return 0;
+}
diff --git a/t/helper/test-read-midx.c b/t/helper/test-read-midx.c
new file mode 100644
index 000000000000..831b586d0222
--- /dev/null
+++ b/t/helper/test-read-midx.c
@@ -0,0 +1,51 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "midx.h"
+#include "repository.h"
+#include "object-store.h"
+
+static int read_midx_file(const char *object_dir)
+{
+	uint32_t i;
+	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+
+	if (!m)
+		return 1;
+
+	printf("header: %08x %d %d %d\n",
+	       m->signature,
+	       m->version,
+	       m->num_chunks,
+	       m->num_packs);
+
+	printf("chunks:");
+
+	if (m->chunk_pack_names)
+		printf(" pack-names");
+	if (m->chunk_oid_fanout)
+		printf(" oid-fanout");
+	if (m->chunk_oid_lookup)
+		printf(" oid-lookup");
+	if (m->chunk_object_offsets)
+		printf(" object-offsets");
+	if (m->chunk_large_offsets)
+		printf(" large-offsets");
+
+	printf("\nnum_objects: %d\n", m->num_objects);
+
+	printf("packs:\n");
+	for (i = 0; i < m->num_packs; i++)
+		printf("%s\n", m->pack_names[i]);
+
+	printf("object-dir: %s\n", m->object_dir);
+
+	return 0;
+}
+
+int cmd__read_midx(int argc, const char **argv)
+{
+	if (argc != 2)
+		usage("read-midx <object-dir>");
+
+	return read_midx_file(argv[1]);
+}
diff --git a/t/helper/test-ref-store.c b/t/helper/test-ref-store.c
new file mode 100644
index 000000000000..799fc00aa15b
--- /dev/null
+++ b/t/helper/test-ref-store.c
@@ -0,0 +1,299 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "refs.h"
+#include "worktree.h"
+#include "object-store.h"
+#include "repository.h"
+
+static const char *notnull(const char *arg, const char *name)
+{
+	if (!arg)
+		die("%s required", name);
+	return arg;
+}
+
+static unsigned int arg_flags(const char *arg, const char *name)
+{
+	return atoi(notnull(arg, name));
+}
+
+static const char **get_store(const char **argv, struct ref_store **refs)
+{
+	const char *gitdir;
+
+	if (!argv[0]) {
+		die("ref store required");
+	} else if (!strcmp(argv[0], "main")) {
+		*refs = get_main_ref_store(the_repository);
+	} else if (skip_prefix(argv[0], "submodule:", &gitdir)) {
+		struct strbuf sb = STRBUF_INIT;
+		int ret;
+
+		ret = strbuf_git_path_submodule(&sb, gitdir, "objects/");
+		if (ret)
+			die("strbuf_git_path_submodule failed: %d", ret);
+		add_to_alternates_memory(sb.buf);
+		strbuf_release(&sb);
+
+		*refs = get_submodule_ref_store(gitdir);
+	} else if (skip_prefix(argv[0], "worktree:", &gitdir)) {
+		struct worktree **p, **worktrees = get_worktrees(0);
+
+		for (p = worktrees; *p; p++) {
+			struct worktree *wt = *p;
+
+			if (!wt->id) {
+				/* special case for main worktree */
+				if (!strcmp(gitdir, "main"))
+					break;
+			} else if (!strcmp(gitdir, wt->id))
+				break;
+		}
+		if (!*p)
+			die("no such worktree: %s", gitdir);
+
+		*refs = get_worktree_ref_store(*p);
+	} else
+		die("unknown backend %s", argv[0]);
+
+	if (!*refs)
+		die("no ref store");
+
+	/* consume store-specific optional arguments if needed */
+
+	return argv + 1;
+}
+
+
+static int cmd_pack_refs(struct ref_store *refs, const char **argv)
+{
+	unsigned int flags = arg_flags(*argv++, "flags");
+
+	return refs_pack_refs(refs, flags);
+}
+
+static int cmd_peel_ref(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+	struct object_id oid;
+	int ret;
+
+	ret = refs_peel_ref(refs, refname, &oid);
+	if (!ret)
+		puts(oid_to_hex(&oid));
+	return ret;
+}
+
+static int cmd_create_symref(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+	const char *target = notnull(*argv++, "target");
+	const char *logmsg = *argv++;
+
+	return refs_create_symref(refs, refname, target, logmsg);
+}
+
+static int cmd_delete_refs(struct ref_store *refs, const char **argv)
+{
+	unsigned int flags = arg_flags(*argv++, "flags");
+	const char *msg = *argv++;
+	struct string_list refnames = STRING_LIST_INIT_NODUP;
+
+	while (*argv)
+		string_list_append(&refnames, *argv++);
+
+	return refs_delete_refs(refs, msg, &refnames, flags);
+}
+
+static int cmd_rename_ref(struct ref_store *refs, const char **argv)
+{
+	const char *oldref = notnull(*argv++, "oldref");
+	const char *newref = notnull(*argv++, "newref");
+	const char *logmsg = *argv++;
+
+	return refs_rename_ref(refs, oldref, newref, logmsg);
+}
+
+static int each_ref(const char *refname, const struct object_id *oid,
+		    int flags, void *cb_data)
+{
+	printf("%s %s 0x%x\n", oid_to_hex(oid), refname, flags);
+	return 0;
+}
+
+static int cmd_for_each_ref(struct ref_store *refs, const char **argv)
+{
+	const char *prefix = notnull(*argv++, "prefix");
+
+	return refs_for_each_ref_in(refs, prefix, each_ref, NULL);
+}
+
+static int cmd_resolve_ref(struct ref_store *refs, const char **argv)
+{
+	struct object_id oid;
+	const char *refname = notnull(*argv++, "refname");
+	int resolve_flags = arg_flags(*argv++, "resolve-flags");
+	int flags;
+	const char *ref;
+
+	ref = refs_resolve_ref_unsafe(refs, refname, resolve_flags,
+				      &oid, &flags);
+	printf("%s %s 0x%x\n", oid_to_hex(&oid), ref ? ref : "(null)", flags);
+	return ref ? 0 : 1;
+}
+
+static int cmd_verify_ref(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+	struct strbuf err = STRBUF_INIT;
+	int ret;
+
+	ret = refs_verify_refname_available(refs, refname, NULL, NULL, &err);
+	if (err.len)
+		puts(err.buf);
+	return ret;
+}
+
+static int cmd_for_each_reflog(struct ref_store *refs, const char **argv)
+{
+	return refs_for_each_reflog(refs, each_ref, NULL);
+}
+
+static int each_reflog(struct object_id *old_oid, struct object_id *new_oid,
+		       const char *committer, timestamp_t timestamp,
+		       int tz, const char *msg, void *cb_data)
+{
+	printf("%s %s %s %"PRItime" %d %s\n",
+	       oid_to_hex(old_oid), oid_to_hex(new_oid),
+	       committer, timestamp, tz, msg);
+	return 0;
+}
+
+static int cmd_for_each_reflog_ent(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+
+	return refs_for_each_reflog_ent(refs, refname, each_reflog, refs);
+}
+
+static int cmd_for_each_reflog_ent_reverse(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+
+	return refs_for_each_reflog_ent_reverse(refs, refname, each_reflog, refs);
+}
+
+static int cmd_reflog_exists(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+
+	return !refs_reflog_exists(refs, refname);
+}
+
+static int cmd_create_reflog(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+	int force_create = arg_flags(*argv++, "force-create");
+	struct strbuf err = STRBUF_INIT;
+	int ret;
+
+	ret = refs_create_reflog(refs, refname, force_create, &err);
+	if (err.len)
+		puts(err.buf);
+	return ret;
+}
+
+static int cmd_delete_reflog(struct ref_store *refs, const char **argv)
+{
+	const char *refname = notnull(*argv++, "refname");
+
+	return refs_delete_reflog(refs, refname);
+}
+
+static int cmd_reflog_expire(struct ref_store *refs, const char **argv)
+{
+	die("not supported yet");
+}
+
+static int cmd_delete_ref(struct ref_store *refs, const char **argv)
+{
+	const char *msg = notnull(*argv++, "msg");
+	const char *refname = notnull(*argv++, "refname");
+	const char *sha1_buf = notnull(*argv++, "old-sha1");
+	unsigned int flags = arg_flags(*argv++, "flags");
+	struct object_id old_oid;
+
+	if (get_oid_hex(sha1_buf, &old_oid))
+		die("not sha-1");
+
+	return refs_delete_ref(refs, msg, refname, &old_oid, flags);
+}
+
+static int cmd_update_ref(struct ref_store *refs, const char **argv)
+{
+	const char *msg = notnull(*argv++, "msg");
+	const char *refname = notnull(*argv++, "refname");
+	const char *new_sha1_buf = notnull(*argv++, "new-sha1");
+	const char *old_sha1_buf = notnull(*argv++, "old-sha1");
+	unsigned int flags = arg_flags(*argv++, "flags");
+	struct object_id old_oid;
+	struct object_id new_oid;
+
+	if (get_oid_hex(old_sha1_buf, &old_oid) ||
+	    get_oid_hex(new_sha1_buf, &new_oid))
+		die("not sha-1");
+
+	return refs_update_ref(refs, msg, refname,
+			       &new_oid, &old_oid,
+			       flags, UPDATE_REFS_DIE_ON_ERR);
+}
+
+struct command {
+	const char *name;
+	int (*func)(struct ref_store *refs, const char **argv);
+};
+
+static struct command commands[] = {
+	{ "pack-refs", cmd_pack_refs },
+	{ "peel-ref", cmd_peel_ref },
+	{ "create-symref", cmd_create_symref },
+	{ "delete-refs", cmd_delete_refs },
+	{ "rename-ref", cmd_rename_ref },
+	{ "for-each-ref", cmd_for_each_ref },
+	{ "resolve-ref", cmd_resolve_ref },
+	{ "verify-ref", cmd_verify_ref },
+	{ "for-each-reflog", cmd_for_each_reflog },
+	{ "for-each-reflog-ent", cmd_for_each_reflog_ent },
+	{ "for-each-reflog-ent-reverse", cmd_for_each_reflog_ent_reverse },
+	{ "reflog-exists", cmd_reflog_exists },
+	{ "create-reflog", cmd_create_reflog },
+	{ "delete-reflog", cmd_delete_reflog },
+	{ "reflog-expire", cmd_reflog_expire },
+	/*
+	 * backend transaction functions can't be tested separately
+	 */
+	{ "delete-ref", cmd_delete_ref },
+	{ "update-ref", cmd_update_ref },
+	{ NULL, NULL }
+};
+
+int cmd__ref_store(int argc, const char **argv)
+{
+	struct ref_store *refs;
+	const char *func;
+	struct command *cmd;
+
+	setup_git_directory();
+
+	argv = get_store(argv + 1, &refs);
+
+	func = *argv++;
+	if (!func)
+		die("ref function required");
+	for (cmd = commands; cmd->name; cmd++) {
+		if (!strcmp(func, cmd->name))
+			return cmd->func(refs, argv);
+	}
+	die("unknown function %s", func);
+	return 0;
+}
diff --git a/t/helper/test-regex.c b/t/helper/test-regex.c
new file mode 100644
index 000000000000..10284cc56fa9
--- /dev/null
+++ b/t/helper/test-regex.c
@@ -0,0 +1,76 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "gettext.h"
+
+struct reg_flag {
+	const char *name;
+	int flag;
+};
+
+static struct reg_flag reg_flags[] = {
+	{ "EXTENDED",	 REG_EXTENDED	},
+	{ "NEWLINE",	 REG_NEWLINE	},
+	{ "ICASE",	 REG_ICASE	},
+	{ "NOTBOL",	 REG_NOTBOL	},
+#ifdef REG_STARTEND
+	{ "STARTEND",	 REG_STARTEND	},
+#endif
+	{ NULL, 0 }
+};
+
+static int test_regex_bug(void)
+{
+	char *pat = "[^={} \t]+";
+	char *str = "={}\nfred";
+	regex_t r;
+	regmatch_t m[1];
+
+	if (regcomp(&r, pat, REG_EXTENDED | REG_NEWLINE))
+		die("failed regcomp() for pattern '%s'", pat);
+	if (regexec(&r, str, 1, m, 0))
+		die("no match of pattern '%s' to string '%s'", pat, str);
+
+	/* http://sourceware.org/bugzilla/show_bug.cgi?id=3957  */
+	if (m[0].rm_so == 3) /* matches '\n' when it should not */
+		die("regex bug confirmed: re-build git with NO_REGEX=1");
+
+	return 0;
+}
+
+int cmd__regex(int argc, const char **argv)
+{
+	const char *pat;
+	const char *str;
+	int flags = 0;
+	regex_t r;
+	regmatch_t m[1];
+
+	if (argc == 2 && !strcmp(argv[1], "--bug"))
+		return test_regex_bug();
+	else if (argc < 3)
+		usage("test-tool regex --bug\n"
+		      "test-tool regex <pattern> <string> [<options>]");
+
+	argv++;
+	pat = *argv++;
+	str = *argv++;
+	while (*argv) {
+		struct reg_flag *rf;
+		for (rf = reg_flags; rf->name; rf++)
+			if (!strcmp(*argv, rf->name)) {
+				flags |= rf->flag;
+				break;
+			}
+		if (!rf->name)
+			die("do not recognize %s", *argv);
+		argv++;
+	}
+	git_setup_gettext();
+
+	if (regcomp(&r, pat, flags))
+		die("failed regcomp() for pattern '%s'", pat);
+	if (regexec(&r, str, 1, m, 0))
+		return 1;
+
+	return 0;
+}
diff --git a/t/helper/test-repository.c b/t/helper/test-repository.c
new file mode 100644
index 000000000000..f7f861844560
--- /dev/null
+++ b/t/helper/test-repository.c
@@ -0,0 +1,98 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "commit-graph.h"
+#include "commit.h"
+#include "config.h"
+#include "object-store.h"
+#include "object.h"
+#include "repository.h"
+#include "tree.h"
+
+static void test_parse_commit_in_graph(const char *gitdir, const char *worktree,
+				       const struct object_id *commit_oid)
+{
+	struct repository r;
+	struct commit *c;
+	struct commit_list *parent;
+
+	setup_git_env(gitdir);
+
+	memset(the_repository, 0, sizeof(*the_repository));
+
+	/* TODO: Needed for temporary hack in hashcmp, see 183a638b7da. */
+	repo_set_hash_algo(the_repository, GIT_HASH_SHA1);
+
+	if (repo_init(&r, gitdir, worktree))
+		die("Couldn't init repo");
+
+	c = lookup_commit(&r, commit_oid);
+
+	if (!parse_commit_in_graph(&r, c))
+		die("Couldn't parse commit");
+
+	printf("%"PRItime, c->date);
+	for (parent = c->parents; parent; parent = parent->next)
+		printf(" %s", oid_to_hex(&parent->item->object.oid));
+	printf("\n");
+
+	repo_clear(&r);
+}
+
+static void test_get_commit_tree_in_graph(const char *gitdir,
+					  const char *worktree,
+					  const struct object_id *commit_oid)
+{
+	struct repository r;
+	struct commit *c;
+	struct tree *tree;
+
+	setup_git_env(gitdir);
+
+	memset(the_repository, 0, sizeof(*the_repository));
+
+	/* TODO: Needed for temporary hack in hashcmp, see 183a638b7da. */
+	repo_set_hash_algo(the_repository, GIT_HASH_SHA1);
+
+	if (repo_init(&r, gitdir, worktree))
+		die("Couldn't init repo");
+
+	c = lookup_commit(&r, commit_oid);
+
+	/*
+	 * get_commit_tree_in_graph does not automatically parse the commit, so
+	 * parse it first.
+	 */
+	if (!parse_commit_in_graph(&r, c))
+		die("Couldn't parse commit");
+	tree = get_commit_tree_in_graph(&r, c);
+	if (!tree)
+		die("Couldn't get commit tree");
+
+	printf("%s\n", oid_to_hex(&tree->object.oid));
+
+	repo_clear(&r);
+}
+
+int cmd__repository(int argc, const char **argv)
+{
+	if (argc < 2)
+		die("must have at least 2 arguments");
+	if (!strcmp(argv[1], "parse_commit_in_graph")) {
+		struct object_id oid;
+		if (argc < 5)
+			die("not enough arguments");
+		if (parse_oid_hex(argv[4], &oid, &argv[4]))
+			die("cannot parse oid '%s'", argv[4]);
+		test_parse_commit_in_graph(argv[2], argv[3], &oid);
+	} else if (!strcmp(argv[1], "get_commit_tree_in_graph")) {
+		struct object_id oid;
+		if (argc < 5)
+			die("not enough arguments");
+		if (parse_oid_hex(argv[4], &oid, &argv[4]))
+			die("cannot parse oid '%s'", argv[4]);
+		test_get_commit_tree_in_graph(argv[2], argv[3], &oid);
+	} else {
+		die("unrecognized '%s'", argv[1]);
+	}
+	return 0;
+}
diff --git a/t/helper/test-revision-walking.c b/t/helper/test-revision-walking.c
new file mode 100644
index 000000000000..625b2dbf8226
--- /dev/null
+++ b/t/helper/test-revision-walking.c
@@ -0,0 +1,69 @@
+/*
+ * test-revision-walking.c: test revision walking API.
+ *
+ * (C) 2012 Heiko Voigt <hvoigt@hvoigt.net>
+ *
+ * This code is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "test-tool.h"
+#include "cache.h"
+#include "commit.h"
+#include "diff.h"
+#include "revision.h"
+
+static void print_commit(struct commit *commit)
+{
+	struct strbuf sb = STRBUF_INIT;
+	struct pretty_print_context ctx = {0};
+	ctx.date_mode.type = DATE_NORMAL;
+	format_commit_message(commit, " %m %s", &sb, &ctx);
+	printf("%s\n", sb.buf);
+	strbuf_release(&sb);
+}
+
+static int run_revision_walk(void)
+{
+	struct rev_info rev;
+	struct commit *commit;
+	const char *argv[] = {NULL, "--all", NULL};
+	int argc = ARRAY_SIZE(argv) - 1;
+	int got_revision = 0;
+
+	repo_init_revisions(the_repository, &rev, NULL);
+	setup_revisions(argc, argv, &rev, NULL);
+	if (prepare_revision_walk(&rev))
+		die("revision walk setup failed");
+
+	while ((commit = get_revision(&rev)) != NULL) {
+		print_commit(commit);
+		got_revision = 1;
+	}
+
+	reset_revision_walk();
+	return got_revision;
+}
+
+int cmd__revision_walking(int argc, const char **argv)
+{
+	if (argc < 2)
+		return 1;
+
+	setup_git_directory();
+
+	if (!strcmp(argv[1], "run-twice")) {
+		printf("1st\n");
+		if (!run_revision_walk())
+			return 1;
+		printf("2nd\n");
+		if (!run_revision_walk())
+			return 1;
+
+		return 0;
+	}
+
+	fprintf(stderr, "check usage\n");
+	return 1;
+}
diff --git a/t/helper/test-run-command.c b/t/helper/test-run-command.c
new file mode 100644
index 000000000000..2cc93bb69c52
--- /dev/null
+++ b/t/helper/test-run-command.c
@@ -0,0 +1,97 @@
+/*
+ * test-run-command.c: test run command API.
+ *
+ * (C) 2009 Ilari Liusvaara <ilari.liusvaara@elisanet.fi>
+ *
+ * This code is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "run-command.h"
+#include "argv-array.h"
+#include "strbuf.h"
+#include <string.h>
+#include <errno.h>
+
+static int number_callbacks;
+static int parallel_next(struct child_process *cp,
+			 struct strbuf *err,
+			 void *cb,
+			 void **task_cb)
+{
+	struct child_process *d = cb;
+	if (number_callbacks >= 4)
+		return 0;
+
+	argv_array_pushv(&cp->args, d->argv);
+	strbuf_addstr(err, "preloaded output of a child\n");
+	number_callbacks++;
+	return 1;
+}
+
+static int no_job(struct child_process *cp,
+		  struct strbuf *err,
+		  void *cb,
+		  void **task_cb)
+{
+	strbuf_addstr(err, "no further jobs available\n");
+	return 0;
+}
+
+static int task_finished(int result,
+			 struct strbuf *err,
+			 void *pp_cb,
+			 void *pp_task_cb)
+{
+	strbuf_addstr(err, "asking for a quick stop\n");
+	return 1;
+}
+
+int cmd__run_command(int argc, const char **argv)
+{
+	struct child_process proc = CHILD_PROCESS_INIT;
+	int jobs;
+
+	if (argc < 3)
+		return 1;
+	while (!strcmp(argv[1], "env")) {
+		if (!argv[2])
+			die("env specifier without a value");
+		argv_array_push(&proc.env_array, argv[2]);
+		argv += 2;
+		argc -= 2;
+	}
+	if (argc < 3)
+		return 1;
+	proc.argv = (const char **)argv + 2;
+
+	if (!strcmp(argv[1], "start-command-ENOENT")) {
+		if (start_command(&proc) < 0 && errno == ENOENT)
+			return 0;
+		fprintf(stderr, "FAIL %s\n", argv[1]);
+		return 1;
+	}
+	if (!strcmp(argv[1], "run-command"))
+		exit(run_command(&proc));
+
+	jobs = atoi(argv[2]);
+	proc.argv = (const char **)argv + 3;
+
+	if (!strcmp(argv[1], "run-command-parallel"))
+		exit(run_processes_parallel(jobs, parallel_next,
+					    NULL, NULL, &proc));
+
+	if (!strcmp(argv[1], "run-command-abort"))
+		exit(run_processes_parallel(jobs, parallel_next,
+					    NULL, task_finished, &proc));
+
+	if (!strcmp(argv[1], "run-command-no-jobs"))
+		exit(run_processes_parallel(jobs, no_job,
+					    NULL, task_finished, &proc));
+
+	fprintf(stderr, "check usage\n");
+	return 1;
+}
diff --git a/t/helper/test-scrap-cache-tree.c b/t/helper/test-scrap-cache-tree.c
new file mode 100644
index 000000000000..393f1604ff95
--- /dev/null
+++ b/t/helper/test-scrap-cache-tree.c
@@ -0,0 +1,19 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "lockfile.h"
+#include "tree.h"
+#include "cache-tree.h"
+
+int cmd__scrap_cache_tree(int ac, const char **av)
+{
+	struct lock_file index_lock = LOCK_INIT;
+
+	setup_git_directory();
+	hold_locked_index(&index_lock, LOCK_DIE_ON_ERROR);
+	if (read_cache() < 0)
+		die("unable to read index file");
+	active_cache_tree = NULL;
+	if (write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
+		die("unable to write index file");
+	return 0;
+}
diff --git a/t/helper/test-serve-v2.c b/t/helper/test-serve-v2.c
new file mode 100644
index 000000000000..aee35e5aef40
--- /dev/null
+++ b/t/helper/test-serve-v2.c
@@ -0,0 +1,31 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "parse-options.h"
+#include "serve.h"
+
+static char const * const serve_usage[] = {
+	N_("test-tool serve-v2 [<options>]"),
+	NULL
+};
+
+int cmd__serve_v2(int argc, const char **argv)
+{
+	struct serve_options opts = SERVE_OPTIONS_INIT;
+
+	struct option options[] = {
+		OPT_BOOL(0, "stateless-rpc", &opts.stateless_rpc,
+			 N_("quit after a single request/response exchange")),
+		OPT_BOOL(0, "advertise-capabilities", &opts.advertise_capabilities,
+			 N_("exit immediately after advertising capabilities")),
+		OPT_END()
+	};
+	const char *prefix = setup_git_directory();
+
+	/* ignore all unknown cmdline switches for now */
+	argc = parse_options(argc, argv, prefix, options, serve_usage,
+			     PARSE_OPT_KEEP_DASHDASH |
+			     PARSE_OPT_KEEP_UNKNOWN);
+	serve(&opts);
+
+	return 0;
+}
diff --git a/t/helper/test-sha1-array.c b/t/helper/test-sha1-array.c
new file mode 100644
index 000000000000..ad5e69f9d3b0
--- /dev/null
+++ b/t/helper/test-sha1-array.c
@@ -0,0 +1,36 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "sha1-array.h"
+
+static int print_oid(const struct object_id *oid, void *data)
+{
+	puts(oid_to_hex(oid));
+	return 0;
+}
+
+int cmd__sha1_array(int argc, const char **argv)
+{
+	struct oid_array array = OID_ARRAY_INIT;
+	struct strbuf line = STRBUF_INIT;
+
+	while (strbuf_getline(&line, stdin) != EOF) {
+		const char *arg;
+		struct object_id oid;
+
+		if (skip_prefix(line.buf, "append ", &arg)) {
+			if (get_oid_hex(arg, &oid))
+				die("not a hexadecimal SHA1: %s", arg);
+			oid_array_append(&array, &oid);
+		} else if (skip_prefix(line.buf, "lookup ", &arg)) {
+			if (get_oid_hex(arg, &oid))
+				die("not a hexadecimal SHA1: %s", arg);
+			printf("%d\n", oid_array_lookup(&array, &oid));
+		} else if (!strcmp(line.buf, "clear"))
+			oid_array_clear(&array);
+		else if (!strcmp(line.buf, "for_each_unique"))
+			oid_array_for_each_unique(&array, print_oid, NULL);
+		else
+			die("unknown command: %s", line.buf);
+	}
+	return 0;
+}
diff --git a/t/helper/test-sha1.c b/t/helper/test-sha1.c
new file mode 100644
index 000000000000..d860c387c384
--- /dev/null
+++ b/t/helper/test-sha1.c
@@ -0,0 +1,7 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd__sha1(int ac, const char **av)
+{
+	return cmd_hash_impl(ac, av, GIT_HASH_SHA1);
+}
diff --git a/t/helper/test-sha1.sh b/t/helper/test-sha1.sh
new file mode 100755
index 000000000000..84594885c703
--- /dev/null
+++ b/t/helper/test-sha1.sh
@@ -0,0 +1,83 @@
+#!/bin/sh
+
+dd if=/dev/zero bs=1048576 count=100 2>/dev/null |
+/usr/bin/time t/helper/test-tool sha1 >/dev/null
+
+while read expect cnt pfx
+do
+	case "$expect" in '#'*) continue ;; esac
+	actual=$(
+		{
+			test -z "$pfx" || echo "$pfx"
+			dd if=/dev/zero bs=1048576 count=$cnt 2>/dev/null |
+			perl -pe 'y/\000/g/'
+		} | ./t/helper/test-tool sha1 $cnt
+	)
+	if test "$expect" = "$actual"
+	then
+		echo "OK: $expect $cnt $pfx"
+	else
+		echo >&2 "OOPS: $cnt"
+		echo >&2 "expect: $expect"
+		echo >&2 "actual: $actual"
+		exit 1
+	fi
+done <<EOF
+da39a3ee5e6b4b0d3255bfef95601890afd80709 0
+3f786850e387550fdab836ed7e6dc881de23001b 0 a
+5277cbb45a15902137d332d97e89cf8136545485 0 ab
+03cfd743661f07975fa2f1220c5194cbaff48451 0 abc
+3330b4373640f9e4604991e73c7e86bfd8da2dc3 0 abcd
+ec11312386ad561674f724b8cca7cf1796e26d1d 0 abcde
+bdc37c074ec4ee6050d68bc133c6b912f36474df 0 abcdef
+69bca99b923859f2dc486b55b87f49689b7358c7 0 abcdefg
+e414af7161c9554089f4106d6f1797ef14a73666 0 abcdefgh
+0707f2970043f9f7c22029482db27733deaec029 0 abcdefghi
+a4dd8aa74a5636728fe52451636e2e17726033aa 1
+9986b45e2f4d7086372533bb6953a8652fa3644a 1 frotz
+23d8d4f788e8526b4877548a32577543cbaaf51f 10
+8cd23f822ab44c7f481b8c92d591f6d1fcad431c 10 frotz
+f3b5604a4e604899c1233edb3bf1cc0ede4d8c32 512
+b095bd837a371593048136e429e9ac4b476e1bb3 512 frotz
+08fa81d6190948de5ccca3966340cc48c10cceac 1200 xyzzy
+e33a291f42c30a159733dd98b8b3e4ff34158ca0 4090 4G
+#a3bf783bc20caa958f6cb24dd140a7b21984838d 9999 nitfol
+EOF
+
+exit
+
+# generating test vectors
+# inputs are number of megabytes followed by some random string to prefix.
+
+while read cnt pfx
+do
+	actual=$(
+		{
+			test -z "$pfx" || echo "$pfx"
+			dd if=/dev/zero bs=1048576 count=$cnt 2>/dev/null |
+			perl -pe 'y/\000/g/'
+		} | sha1sum |
+		sed -e 's/ .*//'
+	)
+	echo "$actual $cnt $pfx"
+done <<EOF
+0
+0 a
+0 ab
+0 abc
+0 abcd
+0 abcde
+0 abcdef
+0 abcdefg
+0 abcdefgh
+0 abcdefghi
+1
+1 frotz
+10
+10 frotz
+512
+512 frotz
+1200 xyzzy
+4090 4G
+9999 nitfol
+EOF
diff --git a/t/helper/test-sha256.c b/t/helper/test-sha256.c
new file mode 100644
index 000000000000..0ac6a99d5f2a
--- /dev/null
+++ b/t/helper/test-sha256.c
@@ -0,0 +1,7 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd__sha256(int ac, const char **av)
+{
+	return cmd_hash_impl(ac, av, GIT_HASH_SHA256);
+}
diff --git a/t/helper/test-sigchain.c b/t/helper/test-sigchain.c
new file mode 100644
index 000000000000..d013bccddaeb
--- /dev/null
+++ b/t/helper/test-sigchain.c
@@ -0,0 +1,24 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "sigchain.h"
+
+#define X(f) \
+static void f(int sig) { \
+	puts(#f); \
+	fflush(stdout); \
+	sigchain_pop(sig); \
+	raise(sig); \
+}
+X(one)
+X(two)
+X(three)
+#undef X
+
+int cmd__sigchain(int argc, const char **argv)
+{
+	sigchain_push(SIGTERM, one);
+	sigchain_push(SIGTERM, two);
+	sigchain_push(SIGTERM, three);
+	raise(SIGTERM);
+	return 0;
+}
diff --git a/t/helper/test-strcmp-offset.c b/t/helper/test-strcmp-offset.c
new file mode 100644
index 000000000000..44e4a6d143e2
--- /dev/null
+++ b/t/helper/test-strcmp-offset.c
@@ -0,0 +1,23 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd__strcmp_offset(int argc, const char **argv)
+{
+	int result;
+	size_t offset;
+
+	if (!argv[1] || !argv[2])
+		die("usage: %s <string1> <string2>", argv[0]);
+
+	result = strcmp_offset(argv[1], argv[2], &offset);
+
+	/*
+	 * Because different CRTs behave differently, only rely on signs
+	 * of the result values.
+	 */
+	result = (result < 0 ? -1 :
+			  result > 0 ? 1 :
+			  0);
+	printf("%d %"PRIuMAX"\n", result, (uintmax_t)offset);
+	return 0;
+}
diff --git a/t/helper/test-string-list.c b/t/helper/test-string-list.c
new file mode 100644
index 000000000000..2123dda85bf1
--- /dev/null
+++ b/t/helper/test-string-list.c
@@ -0,0 +1,129 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "string-list.h"
+
+/*
+ * Parse an argument into a string list.  arg should either be a
+ * ':'-separated list of strings, or "-" to indicate an empty string
+ * list (as opposed to "", which indicates a string list containing a
+ * single empty string).  list->strdup_strings must be set.
+ */
+static void parse_string_list(struct string_list *list, const char *arg)
+{
+	if (!strcmp(arg, "-"))
+		return;
+
+	(void)string_list_split(list, arg, ':', -1);
+}
+
+static void write_list(const struct string_list *list)
+{
+	int i;
+	for (i = 0; i < list->nr; i++)
+		printf("[%d]: \"%s\"\n", i, list->items[i].string);
+}
+
+static void write_list_compact(const struct string_list *list)
+{
+	int i;
+	if (!list->nr)
+		printf("-\n");
+	else {
+		printf("%s", list->items[0].string);
+		for (i = 1; i < list->nr; i++)
+			printf(":%s", list->items[i].string);
+		printf("\n");
+	}
+}
+
+static int prefix_cb(struct string_list_item *item, void *cb_data)
+{
+	const char *prefix = (const char *)cb_data;
+	return starts_with(item->string, prefix);
+}
+
+int cmd__string_list(int argc, const char **argv)
+{
+	if (argc == 5 && !strcmp(argv[1], "split")) {
+		struct string_list list = STRING_LIST_INIT_DUP;
+		int i;
+		const char *s = argv[2];
+		int delim = *argv[3];
+		int maxsplit = atoi(argv[4]);
+
+		i = string_list_split(&list, s, delim, maxsplit);
+		printf("%d\n", i);
+		write_list(&list);
+		string_list_clear(&list, 0);
+		return 0;
+	}
+
+	if (argc == 5 && !strcmp(argv[1], "split_in_place")) {
+		struct string_list list = STRING_LIST_INIT_NODUP;
+		int i;
+		char *s = xstrdup(argv[2]);
+		int delim = *argv[3];
+		int maxsplit = atoi(argv[4]);
+
+		i = string_list_split_in_place(&list, s, delim, maxsplit);
+		printf("%d\n", i);
+		write_list(&list);
+		string_list_clear(&list, 0);
+		free(s);
+		return 0;
+	}
+
+	if (argc == 4 && !strcmp(argv[1], "filter")) {
+		/*
+		 * Retain only the items that have the specified prefix.
+		 * Arguments: list|- prefix
+		 */
+		struct string_list list = STRING_LIST_INIT_DUP;
+		const char *prefix = argv[3];
+
+		parse_string_list(&list, argv[2]);
+		filter_string_list(&list, 0, prefix_cb, (void *)prefix);
+		write_list_compact(&list);
+		string_list_clear(&list, 0);
+		return 0;
+	}
+
+	if (argc == 3 && !strcmp(argv[1], "remove_duplicates")) {
+		struct string_list list = STRING_LIST_INIT_DUP;
+
+		parse_string_list(&list, argv[2]);
+		string_list_remove_duplicates(&list, 0);
+		write_list_compact(&list);
+		string_list_clear(&list, 0);
+		return 0;
+	}
+
+	if (argc == 2 && !strcmp(argv[1], "sort")) {
+		struct string_list list = STRING_LIST_INIT_NODUP;
+		struct strbuf sb = STRBUF_INIT;
+		struct string_list_item *item;
+
+		strbuf_read(&sb, 0, 0);
+
+		/*
+		 * Split by newline, but don't create a string_list item
+		 * for the empty string after the last separator.
+		 */
+		if (sb.len && sb.buf[sb.len - 1] == '\n')
+			strbuf_setlen(&sb, sb.len - 1);
+		string_list_split_in_place(&list, sb.buf, '\n', -1);
+
+		string_list_sort(&list);
+
+		for_each_string_list_item(item, &list)
+			puts(item->string);
+
+		string_list_clear(&list, 0);
+		strbuf_release(&sb);
+		return 0;
+	}
+
+	fprintf(stderr, "%s: unknown function name: %s\n", argv[0],
+		argv[1] ? argv[1] : "(there was none)");
+	return 1;
+}
diff --git a/t/helper/test-submodule-config.c b/t/helper/test-submodule-config.c
new file mode 100644
index 000000000000..e2692746dfdb
--- /dev/null
+++ b/t/helper/test-submodule-config.c
@@ -0,0 +1,73 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "config.h"
+#include "submodule-config.h"
+#include "submodule.h"
+
+static void die_usage(int argc, const char **argv, const char *msg)
+{
+	fprintf(stderr, "%s\n", msg);
+	fprintf(stderr, "Usage: %s [<commit> <submodulepath>] ...\n", argv[0]);
+	exit(1);
+}
+
+int cmd__submodule_config(int argc, const char **argv)
+{
+	const char **arg = argv;
+	int my_argc = argc;
+	int output_url = 0;
+	int lookup_name = 0;
+
+	arg++;
+	my_argc--;
+	while (arg[0] && starts_with(arg[0], "--")) {
+		if (!strcmp(arg[0], "--url"))
+			output_url = 1;
+		if (!strcmp(arg[0], "--name"))
+			lookup_name = 1;
+		arg++;
+		my_argc--;
+	}
+
+	if (my_argc % 2 != 0)
+		die_usage(argc, argv, "Wrong number of arguments.");
+
+	setup_git_directory();
+
+	while (*arg) {
+		struct object_id commit_oid;
+		const struct submodule *submodule;
+		const char *commit;
+		const char *path_or_name;
+
+		commit = arg[0];
+		path_or_name = arg[1];
+
+		if (commit[0] == '\0')
+			oidclr(&commit_oid);
+		else if (get_oid(commit, &commit_oid) < 0)
+			die_usage(argc, argv, "Commit not found.");
+
+		if (lookup_name) {
+			submodule = submodule_from_name(the_repository,
+							&commit_oid, path_or_name);
+		} else
+			submodule = submodule_from_path(the_repository,
+							&commit_oid, path_or_name);
+		if (!submodule)
+			die_usage(argc, argv, "Submodule not found.");
+
+		if (output_url)
+			printf("Submodule url: '%s' for path '%s'\n",
+					submodule->url, submodule->path);
+		else
+			printf("Submodule name: '%s' for path '%s'\n",
+					submodule->name, submodule->path);
+
+		arg += 2;
+	}
+
+	submodule_free(the_repository);
+
+	return 0;
+}
diff --git a/t/helper/test-submodule-nested-repo-config.c b/t/helper/test-submodule-nested-repo-config.c
new file mode 100644
index 000000000000..bc97929bbc3a
--- /dev/null
+++ b/t/helper/test-submodule-nested-repo-config.c
@@ -0,0 +1,32 @@
+#include "test-tool.h"
+#include "submodule-config.h"
+
+static void die_usage(int argc, const char **argv, const char *msg)
+{
+	fprintf(stderr, "%s\n", msg);
+	fprintf(stderr, "Usage: %s <submodulepath> <config name>\n", argv[0]);
+	exit(1);
+}
+
+int cmd__submodule_nested_repo_config(int argc, const char **argv)
+{
+	struct repository subrepo;
+	const struct submodule *sub;
+
+	if (argc < 3)
+		die_usage(argc, argv, "Wrong number of arguments.");
+
+	setup_git_directory();
+
+	sub = submodule_from_path(the_repository, &null_oid, argv[1]);
+	if (repo_submodule_init(&subrepo, the_repository, sub)) {
+		die_usage(argc, argv, "Submodule not found.");
+	}
+
+	/* Read the config of _child_ submodules. */
+	print_config_from_gitmodules(&subrepo, argv[2]);
+
+	submodule_free(the_repository);
+
+	return 0;
+}
diff --git a/t/helper/test-subprocess.c b/t/helper/test-subprocess.c
new file mode 100644
index 000000000000..92b69de63529
--- /dev/null
+++ b/t/helper/test-subprocess.c
@@ -0,0 +1,20 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "run-command.h"
+
+int cmd__subprocess(int argc, const char **argv)
+{
+	struct child_process cp = CHILD_PROCESS_INIT;
+	int nogit = 0;
+
+	setup_git_directory_gently(&nogit);
+	if (nogit)
+		die("No git repo found");
+	if (argc > 1 && !strcmp(argv[1], "--setup-work-tree")) {
+		setup_work_tree();
+		argv++;
+	}
+	cp.git_cmd = 1;
+	cp.argv = (const char **)argv + 1;
+	return run_command(&cp);
+}
diff --git a/t/helper/test-svn-fe.c b/t/helper/test-svn-fe.c
new file mode 100644
index 000000000000..7667c0803f12
--- /dev/null
+++ b/t/helper/test-svn-fe.c
@@ -0,0 +1,52 @@
+/*
+ * test-svn-fe: Code to exercise the svn import lib
+ */
+
+#include "git-compat-util.h"
+#include "vcs-svn/svndump.h"
+#include "vcs-svn/svndiff.h"
+#include "vcs-svn/sliding_window.h"
+#include "vcs-svn/line_buffer.h"
+
+static const char test_svnfe_usage[] =
+	"test-svn-fe (<dumpfile> | [-d] <preimage> <delta> <len>)";
+
+static int apply_delta(int argc, const char **argv)
+{
+	struct line_buffer preimage = LINE_BUFFER_INIT;
+	struct line_buffer delta = LINE_BUFFER_INIT;
+	struct sliding_view preimage_view = SLIDING_VIEW_INIT(&preimage, -1);
+
+	if (argc != 5)
+		usage(test_svnfe_usage);
+
+	if (buffer_init(&preimage, argv[2]))
+		die_errno("cannot open preimage");
+	if (buffer_init(&delta, argv[3]))
+		die_errno("cannot open delta");
+	if (svndiff0_apply(&delta, (off_t) strtoumax(argv[4], NULL, 0),
+					&preimage_view, stdout))
+		return 1;
+	if (buffer_deinit(&preimage))
+		die_errno("cannot close preimage");
+	if (buffer_deinit(&delta))
+		die_errno("cannot close delta");
+	strbuf_release(&preimage_view.buf);
+	return 0;
+}
+
+int cmd_main(int argc, const char **argv)
+{
+	if (argc == 2) {
+		if (svndump_init(argv[1]))
+			return 1;
+		svndump_read(NULL, "refs/heads/master", "refs/notes/svn/revs");
+		svndump_deinit();
+		svndump_reset();
+		return 0;
+	}
+
+	if (argc >= 2 && !strcmp(argv[1], "-d"))
+		return apply_delta(argc, argv);
+	usage(test_svnfe_usage);
+}
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
new file mode 100644
index 000000000000..ce7e89028c4a
--- /dev/null
+++ b/t/helper/test-tool.c
@@ -0,0 +1,116 @@
+#include "git-compat-util.h"
+#include "test-tool.h"
+#include "trace2.h"
+#include "parse-options.h"
+
+static const char * const test_tool_usage[] = {
+	"test-tool [-C <directory>] <command [<arguments>...]]",
+	NULL
+};
+
+struct test_cmd {
+	const char *name;
+	int (*fn)(int argc, const char **argv);
+};
+
+static struct test_cmd cmds[] = {
+	{ "chmtime", cmd__chmtime },
+	{ "config", cmd__config },
+	{ "ctype", cmd__ctype },
+	{ "date", cmd__date },
+	{ "delta", cmd__delta },
+	{ "dir-iterator", cmd__dir_iterator },
+	{ "drop-caches", cmd__drop_caches },
+	{ "dump-cache-tree", cmd__dump_cache_tree },
+	{ "dump-fsmonitor", cmd__dump_fsmonitor },
+	{ "dump-split-index", cmd__dump_split_index },
+	{ "dump-untracked-cache", cmd__dump_untracked_cache },
+	{ "example-decorate", cmd__example_decorate },
+	{ "genrandom", cmd__genrandom },
+	{ "genzeros", cmd__genzeros },
+	{ "hashmap", cmd__hashmap },
+	{ "hash-speed", cmd__hash_speed },
+	{ "index-version", cmd__index_version },
+	{ "json-writer", cmd__json_writer },
+	{ "lazy-init-name-hash", cmd__lazy_init_name_hash },
+	{ "match-trees", cmd__match_trees },
+	{ "mergesort", cmd__mergesort },
+	{ "mktemp", cmd__mktemp },
+	{ "oidmap", cmd__oidmap },
+	{ "online-cpus", cmd__online_cpus },
+	{ "parse-options", cmd__parse_options },
+	{ "path-utils", cmd__path_utils },
+	{ "pkt-line", cmd__pkt_line },
+	{ "prio-queue", cmd__prio_queue },
+	{ "reach", cmd__reach },
+	{ "read-cache", cmd__read_cache },
+	{ "read-midx", cmd__read_midx },
+	{ "ref-store", cmd__ref_store },
+	{ "regex", cmd__regex },
+	{ "repository", cmd__repository },
+	{ "revision-walking", cmd__revision_walking },
+	{ "run-command", cmd__run_command },
+	{ "scrap-cache-tree", cmd__scrap_cache_tree },
+	{ "serve-v2", cmd__serve_v2 },
+	{ "sha1", cmd__sha1 },
+	{ "sha1-array", cmd__sha1_array },
+	{ "sha256", cmd__sha256 },
+	{ "sigchain", cmd__sigchain },
+	{ "strcmp-offset", cmd__strcmp_offset },
+	{ "string-list", cmd__string_list },
+	{ "submodule-config", cmd__submodule_config },
+	{ "submodule-nested-repo-config", cmd__submodule_nested_repo_config },
+	{ "subprocess", cmd__subprocess },
+	{ "trace2", cmd__trace2 },
+	{ "urlmatch-normalization", cmd__urlmatch_normalization },
+	{ "xml-encode", cmd__xml_encode },
+	{ "wildmatch", cmd__wildmatch },
+#ifdef GIT_WINDOWS_NATIVE
+	{ "windows-named-pipe", cmd__windows_named_pipe },
+#endif
+	{ "write-cache", cmd__write_cache },
+};
+
+static NORETURN void die_usage(void)
+{
+	size_t i;
+
+	fprintf(stderr, "usage: test-tool <toolname> [args]\n");
+	for (i = 0; i < ARRAY_SIZE(cmds); i++)
+		fprintf(stderr, "  %s\n", cmds[i].name);
+	exit(128);
+}
+
+int cmd_main(int argc, const char **argv)
+{
+	int i;
+	const char *working_directory = NULL;
+	struct option options[] = {
+		OPT_STRING('C', NULL, &working_directory, "directory",
+			   "change the working directory"),
+		OPT_END()
+	};
+
+	BUG_exit_code = 99;
+	argc = parse_options(argc, argv, NULL, options, test_tool_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION |
+			     PARSE_OPT_KEEP_ARGV0);
+
+	if (argc < 2)
+		die_usage();
+
+	if (working_directory && chdir(working_directory) < 0)
+		die("Could not cd to '%s'", working_directory);
+
+	for (i = 0; i < ARRAY_SIZE(cmds); i++) {
+		if (!strcmp(cmds[i].name, argv[1])) {
+			argv++;
+			argc--;
+			trace2_cmd_name(cmds[i].name);
+			trace2_cmd_list_config();
+			return cmds[i].fn(argc, argv);
+		}
+	}
+	error("there is no tool named '%s'", argv[1]);
+	die_usage();
+}
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
new file mode 100644
index 000000000000..f805bb39ae9e
--- /dev/null
+++ b/t/helper/test-tool.h
@@ -0,0 +1,65 @@
+#ifndef TEST_TOOL_H
+#define TEST_TOOL_H
+
+#define USE_THE_INDEX_COMPATIBILITY_MACROS
+#include "git-compat-util.h"
+
+int cmd__chmtime(int argc, const char **argv);
+int cmd__config(int argc, const char **argv);
+int cmd__ctype(int argc, const char **argv);
+int cmd__date(int argc, const char **argv);
+int cmd__delta(int argc, const char **argv);
+int cmd__dir_iterator(int argc, const char **argv);
+int cmd__drop_caches(int argc, const char **argv);
+int cmd__dump_cache_tree(int argc, const char **argv);
+int cmd__dump_fsmonitor(int argc, const char **argv);
+int cmd__dump_split_index(int argc, const char **argv);
+int cmd__dump_untracked_cache(int argc, const char **argv);
+int cmd__example_decorate(int argc, const char **argv);
+int cmd__genrandom(int argc, const char **argv);
+int cmd__genzeros(int argc, const char **argv);
+int cmd__hashmap(int argc, const char **argv);
+int cmd__hash_speed(int argc, const char **argv);
+int cmd__index_version(int argc, const char **argv);
+int cmd__json_writer(int argc, const char **argv);
+int cmd__lazy_init_name_hash(int argc, const char **argv);
+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__online_cpus(int argc, const char **argv);
+int cmd__parse_options(int argc, const char **argv);
+int cmd__path_utils(int argc, const char **argv);
+int cmd__pkt_line(int argc, const char **argv);
+int cmd__prio_queue(int argc, const char **argv);
+int cmd__reach(int argc, const char **argv);
+int cmd__read_cache(int argc, const char **argv);
+int cmd__read_midx(int argc, const char **argv);
+int cmd__ref_store(int argc, const char **argv);
+int cmd__regex(int argc, const char **argv);
+int cmd__repository(int argc, const char **argv);
+int cmd__revision_walking(int argc, const char **argv);
+int cmd__run_command(int argc, const char **argv);
+int cmd__scrap_cache_tree(int argc, const char **argv);
+int cmd__serve_v2(int argc, const char **argv);
+int cmd__sha1(int argc, const char **argv);
+int cmd__sha1_array(int argc, const char **argv);
+int cmd__sha256(int argc, const char **argv);
+int cmd__sigchain(int argc, const char **argv);
+int cmd__strcmp_offset(int argc, const char **argv);
+int cmd__string_list(int argc, const char **argv);
+int cmd__submodule_config(int argc, const char **argv);
+int cmd__submodule_nested_repo_config(int argc, const char **argv);
+int cmd__subprocess(int argc, const char **argv);
+int cmd__trace2(int argc, const char **argv);
+int cmd__urlmatch_normalization(int argc, const char **argv);
+int cmd__xml_encode(int argc, const char **argv);
+int cmd__wildmatch(int argc, const char **argv);
+#ifdef GIT_WINDOWS_NATIVE
+int cmd__windows_named_pipe(int argc, const char **argv);
+#endif
+int cmd__write_cache(int argc, const char **argv);
+
+int cmd_hash_impl(int ac, const char **av, int algo);
+
+#endif
diff --git a/t/helper/test-trace2.c b/t/helper/test-trace2.c
new file mode 100644
index 000000000000..197819c872ee
--- /dev/null
+++ b/t/helper/test-trace2.c
@@ -0,0 +1,273 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "argv-array.h"
+#include "run-command.h"
+#include "exec-cmd.h"
+#include "config.h"
+
+typedef int(fn_unit_test)(int argc, const char **argv);
+
+struct unit_test {
+	fn_unit_test *ut_fn;
+	const char *ut_name;
+	const char *ut_usage;
+};
+
+#define MyOk 0
+#define MyError 1
+
+static int get_i(int *p_value, const char *data)
+{
+	char *endptr;
+
+	if (!data || !*data)
+		return MyError;
+
+	*p_value = strtol(data, &endptr, 10);
+	if (*endptr || errno == ERANGE)
+		return MyError;
+
+	return MyOk;
+}
+
+/*
+ * Cause process to exit with the requested value via "return".
+ *
+ * Rely on test-tool.c:cmd_main() to call trace2_cmd_exit()
+ * with our result.
+ *
+ * Test harness can confirm:
+ * [] the process-exit value.
+ * [] the "code" field in the "exit" trace2 event.
+ * [] the "code" field in the "atexit" trace2 event.
+ * [] the "name" field in the "cmd_name" trace2 event.
+ * [] "def_param" events for all of the "interesting" pre-defined
+ * config settings.
+ */
+static int ut_001return(int argc, const char **argv)
+{
+	int rc;
+
+	if (get_i(&rc, argv[0]))
+		die("expect <exit_code>");
+
+	return rc;
+}
+
+/*
+ * Cause the process to exit with the requested value via "exit()".
+ *
+ * Test harness can confirm:
+ * [] the "code" field in the "exit" trace2 event.
+ * [] the "code" field in the "atexit" trace2 event.
+ * [] the "name" field in the "cmd_name" trace2 event.
+ * [] "def_param" events for all of the "interesting" pre-defined
+ * config settings.
+ */
+static int ut_002exit(int argc, const char **argv)
+{
+	int rc;
+
+	if (get_i(&rc, argv[0]))
+		die("expect <exit_code>");
+
+	exit(rc);
+}
+
+/*
+ * Send an "error" event with each value in argv.  Normally, git only issues
+ * a single "error" event immediately before issuing an "exit" event (such
+ * as in die() or BUG()), but multiple "error" events are allowed.
+ *
+ * Test harness can confirm:
+ * [] a trace2 "error" event for each value in argv.
+ * [] the "name" field in the "cmd_name" trace2 event.
+ * [] (optional) the file:line in the "exit" event refers to this function.
+ */
+static int ut_003error(int argc, const char **argv)
+{
+	int k;
+
+	if (!argv[0] || !*argv[0])
+		die("expect <error_message>");
+
+	for (k = 0; k < argc; k++)
+		error("%s", argv[k]);
+
+	return 0;
+}
+
+/*
+ * Run a child process and wait for it to finish and exit with its return code.
+ * test-tool trace2 004child [<child-command-line>]
+ *
+ * For example:
+ * test-tool trace2 004child git version
+ * test-tool trace2 004child test-tool trace2 001return 0
+ * test-tool trace2 004child test-tool trace2 004child test-tool trace2 004child
+ * test-tool trace2 004child git -c alias.xyz=version xyz
+ *
+ * Test harness can confirm:
+ * [] the "name" field in the "cmd_name" trace2 event.
+ * [] that the outer process has a single component SID (or depth "d0" in
+ *    the PERF stream).
+ * [] that "child_start" and "child_exit" events are generated for the child.
+ * [] if the child process is an instrumented executable:
+ *    [] that "version", "start", ..., "exit", and "atexit" events are
+ *       generated by the child process.
+ *    [] that the child process events have a multiple component SID (or
+ *       depth "dN+1" in the PERF stream).
+ * [] that the child exit code is propagated to the parent process "exit"
+ *    and "atexit" events..
+ * [] (optional) that the "t_abs" field in the child process "atexit" event
+ *    is less than the "t_rel" field in the "child_exit" event of the parent
+ *    process.
+ * [] if the child process is like the alias example above,
+ *    [] (optional) the child process attempts to run "git-xyx" as a dashed
+ *       command.
+ *    [] the child process emits an "alias" event with "xyz" => "version"
+ *    [] the child process runs "git version" as a child process.
+ *    [] the child process has a 3 component SID (or depth "d2" in the PERF
+ *       stream).
+ */
+static int ut_004child(int argc, const char **argv)
+{
+	int result;
+
+	/*
+	 * Allow empty <child_command_line> so we can do arbitrarily deep
+	 * command nesting and let the last one be null.
+	 */
+	if (!argc)
+		return 0;
+
+	result = run_command_v_opt(argv, 0);
+	exit(result);
+}
+
+/*
+ * Exec a git command.  This may either create a child process (Windows)
+ * or replace the existing process.
+ * test-tool trace2 005exec <git_command_args>
+ *
+ * For example:
+ * test-tool trace2 005exec version
+ *
+ * Test harness can confirm (on Windows):
+ * [] the "name" field in the "cmd_name" trace2 event.
+ * [] that the outer process has a single component SID (or depth "d0" in
+ *    the PERF stream).
+ * [] that "exec" and "exec_result" events are generated for the child
+ *    process (since the Windows compatibility layer fakes an exec() with
+ *    a CreateProcess(), WaitForSingleObject(), and exit()).
+ * [] that the child process has multiple component SID (or depth "dN+1"
+ *    in the PERF stream).
+ *
+ * Test harness can confirm (on platforms with a real exec() function):
+ * [] TODO talk about process replacement and how it affects SID.
+ */
+static int ut_005exec(int argc, const char **argv)
+{
+	int result;
+
+	if (!argc)
+		return 0;
+
+	result = execv_git_cmd(argv);
+	return result;
+}
+
+static int ut_006data(int argc, const char **argv)
+{
+	const char *usage_error =
+		"expect <cat0> <k0> <v0> [<cat1> <k1> <v1> [...]]";
+
+	if (argc % 3 != 0)
+		die("%s", usage_error);
+
+	while (argc) {
+		if (!argv[0] || !*argv[0] || !argv[1] || !*argv[1] ||
+		    !argv[2] || !*argv[2])
+			die("%s", usage_error);
+
+		trace2_data_string(argv[0], the_repository, argv[1], argv[2]);
+		argv += 3;
+		argc -= 3;
+	}
+
+	return 0;
+}
+
+/*
+ * Usage:
+ *     test-tool trace2 <ut_name_1> <ut_usage_1>
+ *     test-tool trace2 <ut_name_2> <ut_usage_2>
+ *     ...
+ */
+#define USAGE_PREFIX "test-tool trace2"
+
+/* clang-format off */
+static struct unit_test ut_table[] = {
+	{ ut_001return,   "001return", "<exit_code>" },
+	{ ut_002exit,     "002exit",   "<exit_code>" },
+	{ ut_003error,    "003error",  "<error_message>+" },
+	{ ut_004child,    "004child",  "[<child_command_line>]" },
+	{ ut_005exec,     "005exec",   "<git_command_args>" },
+	{ ut_006data,     "006data",   "[<category> <key> <value>]+" },
+};
+/* clang-format on */
+
+/* clang-format off */
+#define for_each_ut(k, ut_k)			\
+	for (k = 0, ut_k = &ut_table[k];	\
+	     k < ARRAY_SIZE(ut_table);		\
+	     k++, ut_k = &ut_table[k])
+/* clang-format on */
+
+static int print_usage(void)
+{
+	int k;
+	struct unit_test *ut_k;
+
+	fprintf(stderr, "usage:\n");
+	for_each_ut (k, ut_k)
+		fprintf(stderr, "\t%s %s %s\n", USAGE_PREFIX, ut_k->ut_name,
+			ut_k->ut_usage);
+
+	return 129;
+}
+
+/*
+ * Issue various trace2 events for testing.
+ *
+ * We assume that these trace2 routines has already been called:
+ *    [] trace2_initialize()      [common-main.c:main()]
+ *    [] trace2_cmd_start()       [common-main.c:main()]
+ *    [] trace2_cmd_name()        [test-tool.c:cmd_main()]
+ *    [] tracd2_cmd_list_config() [test-tool.c:cmd_main()]
+ * So that:
+ *    [] the various trace2 streams are open.
+ *    [] the process SID has been created.
+ *    [] the "version" event has been generated.
+ *    [] the "start" event has been generated.
+ *    [] the "cmd_name" event has been generated.
+ *    [] this writes various "def_param" events for interesting config values.
+ *
+ * We further assume that if we return (rather than exit()), trace2_cmd_exit()
+ * will be called by test-tool.c:cmd_main().
+ */
+int cmd__trace2(int argc, const char **argv)
+{
+	int k;
+	struct unit_test *ut_k;
+
+	argc--; /* skip over "trace2" arg */
+	argv++;
+
+	if (argc)
+		for_each_ut (k, ut_k)
+			if (!strcmp(argv[0], ut_k->ut_name))
+				return ut_k->ut_fn(argc - 1, argv + 1);
+
+	return print_usage();
+}
diff --git a/t/helper/test-urlmatch-normalization.c b/t/helper/test-urlmatch-normalization.c
new file mode 100644
index 000000000000..8f4d67e64695
--- /dev/null
+++ b/t/helper/test-urlmatch-normalization.c
@@ -0,0 +1,51 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "urlmatch.h"
+
+int cmd__urlmatch_normalization(int argc, const char **argv)
+{
+	const char usage[] = "test-tool urlmatch-normalization [-p | -l] <url1> | <url1> <url2>";
+	char *url1, *url2;
+	int opt_p = 0, opt_l = 0;
+
+	/*
+	 * For one url, succeed if url_normalize succeeds on it, fail otherwise.
+	 * For two urls, succeed only if url_normalize succeeds on both and
+	 * the results compare equal with strcmp.  If -p is given (one url only)
+	 * and url_normalize succeeds, print the result followed by "\n".  If
+	 * -l is given (one url only) and url_normalize succeeds, print the
+	 * returned length in decimal followed by "\n".
+	 */
+
+	if (argc > 1 && !strcmp(argv[1], "-p")) {
+		opt_p = 1;
+		argc--;
+		argv++;
+	} else if (argc > 1 && !strcmp(argv[1], "-l")) {
+		opt_l = 1;
+		argc--;
+		argv++;
+	}
+
+	if (argc < 2 || argc > 3)
+		die("%s", usage);
+
+	if (argc == 2) {
+		struct url_info info;
+		url1 = url_normalize(argv[1], &info);
+		if (!url1)
+			return 1;
+		if (opt_p)
+			printf("%s\n", url1);
+		if (opt_l)
+			printf("%u\n", (unsigned)info.url_len);
+		return 0;
+	}
+
+	if (opt_p || opt_l)
+		die("%s", usage);
+
+	url1 = url_normalize(argv[1], NULL);
+	url2 = url_normalize(argv[2], NULL);
+	return (url1 && url2 && !strcmp(url1, url2)) ? 0 : 1;
+}
diff --git a/t/helper/test-wildmatch.c b/t/helper/test-wildmatch.c
new file mode 100644
index 000000000000..2c103d1824cf
--- /dev/null
+++ b/t/helper/test-wildmatch.c
@@ -0,0 +1,24 @@
+#include "test-tool.h"
+#include "cache.h"
+
+int cmd__wildmatch(int argc, const char **argv)
+{
+	int i;
+	for (i = 2; i < argc; i++) {
+		if (argv[i][0] == '/')
+			die("Forward slash is not allowed at the beginning of the\n"
+			    "pattern because Windows does not like it. Use `XXX/' instead.");
+		else if (!strncmp(argv[i], "XXX/", 4))
+			argv[i] += 3;
+	}
+	if (!strcmp(argv[1], "wildmatch"))
+		return !!wildmatch(argv[3], argv[2], WM_PATHNAME);
+	else if (!strcmp(argv[1], "iwildmatch"))
+		return !!wildmatch(argv[3], argv[2], WM_PATHNAME | WM_CASEFOLD);
+	else if (!strcmp(argv[1], "pathmatch"))
+		return !!wildmatch(argv[3], argv[2], 0);
+	else if (!strcmp(argv[1], "ipathmatch"))
+		return !!wildmatch(argv[3], argv[2], WM_CASEFOLD);
+	else
+		return 1;
+}
diff --git a/t/helper/test-windows-named-pipe.c b/t/helper/test-windows-named-pipe.c
new file mode 100644
index 000000000000..b4b752b01aaf
--- /dev/null
+++ b/t/helper/test-windows-named-pipe.c
@@ -0,0 +1,72 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "strbuf.h"
+
+#ifdef GIT_WINDOWS_NATIVE
+static const char *usage_string = "<pipe-filename>";
+
+#define TEST_BUFSIZE (4096)
+
+int cmd__windows_named_pipe(int argc, const char **argv)
+{
+	const char *filename;
+	struct strbuf pathname = STRBUF_INIT;
+	int err;
+	HANDLE h;
+	BOOL connected;
+	char buf[TEST_BUFSIZE + 1];
+
+	if (argc < 2)
+		goto print_usage;
+	filename = argv[1];
+	if (strchr(filename, '/') || strchr(filename, '\\'))
+		goto print_usage;
+	strbuf_addf(&pathname, "//./pipe/%s", filename);
+
+	/*
+	 * Create a single instance of the server side of the named pipe.
+	 * This will allow exactly one client instance to connect to it.
+	 */
+	h = CreateNamedPipeA(
+		pathname.buf,
+		PIPE_ACCESS_INBOUND | FILE_FLAG_FIRST_PIPE_INSTANCE,
+		PIPE_TYPE_MESSAGE | PIPE_READMODE_MESSAGE | PIPE_WAIT,
+		PIPE_UNLIMITED_INSTANCES,
+		TEST_BUFSIZE, TEST_BUFSIZE, 0, NULL);
+	if (h == INVALID_HANDLE_VALUE) {
+		err = err_win_to_posix(GetLastError());
+		fprintf(stderr, "CreateNamedPipe failed: %s\n",
+			strerror(err));
+		return err;
+	}
+
+	connected = ConnectNamedPipe(h, NULL)
+		? TRUE
+		: (GetLastError() == ERROR_PIPE_CONNECTED);
+	if (!connected) {
+		err = err_win_to_posix(GetLastError());
+		fprintf(stderr, "ConnectNamedPipe failed: %s\n",
+			strerror(err));
+		CloseHandle(h);
+		return err;
+	}
+
+	while (1) {
+		DWORD nbr;
+		BOOL success = ReadFile(h, buf, TEST_BUFSIZE, &nbr, NULL);
+		if (!success || nbr == 0)
+			break;
+		buf[nbr] = 0;
+
+		write(1, buf, nbr);
+	}
+
+	DisconnectNamedPipe(h);
+	CloseHandle(h);
+	return 0;
+
+print_usage:
+	fprintf(stderr, "usage: %s %s\n", argv[0], usage_string);
+	return 1;
+}
+#endif
diff --git a/t/helper/test-write-cache.c b/t/helper/test-write-cache.c
new file mode 100644
index 000000000000..8837717d36a7
--- /dev/null
+++ b/t/helper/test-write-cache.c
@@ -0,0 +1,20 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "lockfile.h"
+
+int cmd__write_cache(int argc, const char **argv)
+{
+	struct lock_file index_lock = LOCK_INIT;
+	int i, cnt = 1;
+	if (argc == 2)
+		cnt = strtol(argv[1], NULL, 0);
+	setup_git_directory();
+	read_cache();
+	for (i = 0; i < cnt; i++) {
+		hold_locked_index(&index_lock, LOCK_DIE_ON_ERROR);
+		if (write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
+			die("unable to write index file");
+	}
+
+	return 0;
+}
diff --git a/t/helper/test-xml-encode.c b/t/helper/test-xml-encode.c
new file mode 100644
index 000000000000..a648bbd961c2
--- /dev/null
+++ b/t/helper/test-xml-encode.c
@@ -0,0 +1,80 @@
+#include "test-tool.h"
+
+static const char *utf8_replace_character = "&#xfffd;";
+
+/*
+ * Encodes (possibly incorrect) UTF-8 on <stdin> to <stdout>, to be embedded
+ * in an XML file.
+ */
+int cmd__xml_encode(int argc, const char **argv)
+{
+	unsigned char buf[1024], tmp[4], *tmp2 = NULL;
+	ssize_t cur = 0, len = 1, remaining = 0;
+	unsigned char ch;
+
+	for (;;) {
+		if (++cur == len) {
+			len = xread(0, buf, sizeof(buf));
+			if (!len)
+				return 0;
+			if (len < 0)
+				die_errno("Could not read <stdin>");
+			cur = 0;
+		}
+		ch = buf[cur];
+
+		if (tmp2) {
+			if ((ch & 0xc0) != 0x80) {
+				fputs(utf8_replace_character, stdout);
+				tmp2 = NULL;
+				cur--;
+				continue;
+			}
+			*tmp2 = ch;
+			tmp2++;
+			if (--remaining == 0) {
+				fwrite(tmp, tmp2 - tmp, 1, stdout);
+				tmp2 = NULL;
+			}
+			continue;
+		}
+
+		if (!(ch & 0x80)) {
+			/* 0xxxxxxx */
+			if (ch == '&')
+				fputs("&amp;", stdout);
+			else if (ch == '\'')
+				fputs("&apos;", stdout);
+			else if (ch == '"')
+				fputs("&quot;", stdout);
+			else if (ch == '<')
+				fputs("&lt;", stdout);
+			else if (ch == '>')
+				fputs("&gt;", stdout);
+			else if (ch >= 0x20)
+				fputc(ch, stdout);
+			else if (ch == 0x09 || ch == 0x0a || ch == 0x0d)
+				fprintf(stdout, "&#x%02x;", ch);
+			else
+				fputs(utf8_replace_character, stdout);
+		} else if ((ch & 0xe0) == 0xc0) {
+			/* 110XXXXx 10xxxxxx */
+			tmp[0] = ch;
+			remaining = 1;
+			tmp2 = tmp + 1;
+		} else if ((ch & 0xf0) == 0xe0) {
+			/* 1110XXXX 10Xxxxxx 10xxxxxx */
+			tmp[0] = ch;
+			remaining = 2;
+			tmp2 = tmp + 1;
+		} else if ((ch & 0xf8) == 0xf0) {
+			/* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */
+			tmp[0] = ch;
+			remaining = 3;
+			tmp2 = tmp + 1;
+		} else
+			fputs(utf8_replace_character, stdout);
+	}
+
+	return 0;
+}