tests: optionally write results as JUnit-style .xml

This will come in handy when publishing the results of Git's test suite
during an automated Azure DevOps run.

Note: we need to make extra sure that invalid UTF-8 encoding is turned
into valid UTF-8 (using the Replacement Character, \uFFFD) because
t9902's trace contains such invalid byte sequences, and the task in the
Azure Pipeline that uploads the test results would refuse to do anything
if it was asked to parse an .xml file with invalid UTF-8 in it.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Makefile

@@ -754,6 +754,7 @@ TEST_BUILTINS_OBJS += test-submodule-config.o
 TEST_BUILTINS_OBJS += test-submodule-nested-repo-config.o
 TEST_BUILTINS_OBJS += test-subprocess.o
 TEST_BUILTINS_OBJS += test-urlmatch-normalization.o
+TEST_BUILTINS_OBJS += test-xml-encode.o
 TEST_BUILTINS_OBJS += test-wildmatch.o
 TEST_BUILTINS_OBJS += test-windows-named-pipe.o
 TEST_BUILTINS_OBJS += test-write-cache.o

t/.gitignore

@@ -2,3 +2,4 @@
 /test-results
 /.prove
 /chainlinttmp
+/out/

t/helper/test-tool.c

@@ -49,6 +49,7 @@ static struct test_cmd cmds[] = {
 	{ "submodule-nested-repo-config", cmd__submodule_nested_repo_config },
 	{ "subprocess", cmd__subprocess },
 	{ "urlmatch-normalization", cmd__urlmatch_normalization },
+	{ "xml-encode", cmd__xml_encode },
 	{ "wildmatch", cmd__wildmatch },
 #ifdef GIT_WINDOWS_NATIVE
 	{ "windows-named-pipe", cmd__windows_named_pipe },

t/helper/test-tool.h

@@ -45,6 +45,7 @@ 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__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);

t/helper/test-xml-encode.c

@@ -0,0 +1,80 @@
+#include "test-tool.h"
+
+static const char *utf8_replace_character = "�";
+
+/*
+ * 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;
+}

t/test-lib.sh

@@ -139,6 +139,9 @@ do
 		verbose_log=t
 		tee=t
 		;;
+	--write-junit-xml)
+		write_junit_xml=t
+		;;
 	--stress)
 		stress=t ;;
 	--stress=*)
@@ -622,11 +625,24 @@ trap 'exit $?' INT TERM HUP
 # the test_expect_* functions instead.
 
 test_ok_ () {
+	if test -n "$write_junit_xml"
+	then
+		write_junit_xml_testcase "$*"
+	fi
 	test_success=$(($test_success + 1))
 	say_color "" "ok $test_count - $@"
 }
 
 test_failure_ () {
+	if test -n "$write_junit_xml"
+	then
+		junit_insert="<failure message=\"not ok $test_count -"
+		junit_insert="$junit_insert $(xml_attr_encode "$1")\">"
+		junit_insert="$junit_insert $(xml_attr_encode \
+			"$(printf '%s\n' "$@" | sed 1d)")"
+		junit_insert="$junit_insert</failure>"
+		write_junit_xml_testcase "$1" "      $junit_insert"
+	fi
 	test_failure=$(($test_failure + 1))
 	say_color error "not ok $test_count - $1"
 	shift
@@ -635,11 +651,19 @@ test_failure_ () {
 }
 
 test_known_broken_ok_ () {
+	if test -n "$write_junit_xml"
+	then
+		write_junit_xml_testcase "$* (breakage fixed)"
+	fi
 	test_fixed=$(($test_fixed+1))
 	say_color error "ok $test_count - $@ # TODO known breakage vanished"
 }
 
 test_known_broken_failure_ () {
+	if test -n "$write_junit_xml"
+	then
+		write_junit_xml_testcase "$* (known breakage)"
+	fi
 	test_broken=$(($test_broken+1))
 	say_color warn "not ok $test_count - $@ # TODO known breakage"
 }
@@ -897,6 +921,10 @@ test_start_ () {
 	test_count=$(($test_count+1))
 	maybe_setup_verbose
 	maybe_setup_valgrind
+	if test -n "$write_junit_xml"
+	then
+		junit_start=$(test-tool date getnanos)
+	fi
 }
 
 test_finish_ () {
@@ -934,6 +962,13 @@ test_skip () {
 
 	case "$to_skip" in
 	t)
+		if test -n "$write_junit_xml"
+		then
+			message="$(xml_attr_encode "$skipped_reason")"
+			write_junit_xml_testcase "$1" \
+				"      <skipped message=\"$message\" />"
+		fi
+
 		say_color skip >&3 "skipping test: $@"
 		say_color skip "ok $test_count # skip $1 ($skipped_reason)"
 		: true
@@ -949,9 +984,51 @@ test_at_end_hook_ () {
 	:
 }
 
+write_junit_xml () {
+	case "$1" in
+	--truncate)
+		>"$junit_xml_path"
+		junit_have_testcase=
+		shift
+		;;
+	esac
+	printf '%s\n' "$@" >>"$junit_xml_path"
+}
+
+xml_attr_encode () {
+	printf '%s\n' "$@" | test-tool xml-encode
+}
+
+write_junit_xml_testcase () {
+	junit_attrs="name=\"$(xml_attr_encode "$this_test.$test_count $1")\""
+	shift
+	junit_attrs="$junit_attrs classname=\"$this_test\""
+	junit_attrs="$junit_attrs time=\"$(test-tool \
+		date getnanos $junit_start)\""
+	write_junit_xml "$(printf '%s\n' \
+		"    <testcase $junit_attrs>" "$@" "    </testcase>")"
+	junit_have_testcase=t
+}
+
 test_done () {
 	GIT_EXIT_OK=t
 
+	if test -n "$write_junit_xml" && test -n "$junit_xml_path"
+	then
+		test -n "$junit_have_testcase" || {
+			junit_start=$(test-tool date getnanos)
+			write_junit_xml_testcase "all tests skipped"
+		}
+
+		# adjust the overall time
+		junit_time=$(test-tool date getnanos $junit_suite_start)
+		sed "s/<testsuite [^>]*/& time=\"$junit_time\"/" \
+			<"$junit_xml_path" >"$junit_xml_path.new"
+		mv "$junit_xml_path.new" "$junit_xml_path"
+
+		write_junit_xml "  </testsuite>" "</testsuites>"
+	fi
+
 	if test -z "$HARNESS_ACTIVE"
 	then
 		mkdir -p "$TEST_RESULTS_DIR"
@@ -1178,6 +1255,7 @@ then
 else
 	mkdir -p "$TRASH_DIRECTORY"
 fi
+
 # Use -P to resolve symlinks in our working directory so that the cwd
 # in subprocesses like git equals our $PWD (for pathname comparisons).
 cd -P "$TRASH_DIRECTORY" || exit 1
@@ -1191,6 +1269,19 @@ then
 	test_done
 fi
 
+if test -n "$write_junit_xml"
+then
+	junit_xml_dir="$TEST_OUTPUT_DIRECTORY/out"
+	mkdir -p "$junit_xml_dir"
+	junit_xml_base=${0##*/}
+	junit_xml_path="$junit_xml_dir/TEST-${junit_xml_base%.sh}.xml"
+	junit_attrs="name=\"${junit_xml_base%.sh}\""
+	junit_attrs="$junit_attrs timestamp=\"$(TZ=UTC \
+		date +%Y-%m-%dT%H:%M:%S)\""
+	write_junit_xml --truncate "<testsuites>" "  <testsuite $junit_attrs>"
+	junit_suite_start=$(test-tool date getnanos)
+fi
+
 # Provide an implementation of the 'yes' utility
 yes () {
 	if test $# = 0