kunit: tool: parse KTAP compliant test output

Change the KUnit parser to be able to parse test output that complies with
the KTAP version 1 specification format found here:
https://kernel.org/doc/html/latest/dev-tools/ktap.html. Ensure the parser
is able to parse tests with the original KUnit test output format as
well.

KUnit parser now accepts any of the following test output formats:

Original KUnit test output format:

 TAP version 14
 1..1
   # Subtest: kunit-test-suite
   1..3
   ok 1 - kunit_test_1
   ok 2 - kunit_test_2
   ok 3 - kunit_test_3
 # kunit-test-suite: pass:3 fail:0 skip:0 total:3
 # Totals: pass:3 fail:0 skip:0 total:3
 ok 1 - kunit-test-suite

KTAP version 1 test output format:

 KTAP version 1
 1..1
   KTAP version 1
   1..3
   ok 1 kunit_test_1
   ok 2 kunit_test_2
   ok 3 kunit_test_3
 ok 1 kunit-test-suite

New KUnit test output format (changes made in the next patch of
this series):

 KTAP version 1
 1..1
   KTAP version 1
   # Subtest: kunit-test-suite
   1..3
   ok 1 kunit_test_1
   ok 2 kunit_test_2
   ok 3 kunit_test_3
 # kunit-test-suite: pass:3 fail:0 skip:0 total:3
 # Totals: pass:3 fail:0 skip:0 total:3
 ok 1 kunit-test-suite

Signed-off-by: Rae Moar <rmoar@google.com>
Reviewed-by: Daniel Latypov <dlatypov@google.com>
Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>

4 files changed, 80 insertions, 28 deletions

diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index d0ed5dd5cfc4..4cc2f8b7ecd0 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -441,6 +441,7 @@ def parse_diagnostic(lines: LineStream) -> List[str]:
 	- '# Subtest: [test name]'
 	- '[ok|not ok] [test number] [-] [test name] [optional skip
 		directive]'
+	- 'KTAP version [version number]'
 
 	Parameters:
 	lines - LineStream of KTAP output to parse
@@ -449,8 +450,9 @@ def parse_diagnostic(lines: LineStream) -> List[str]:
 	Log of diagnostic lines
 	"""
 	log = []  # type: List[str]
-	while lines and not TEST_RESULT.match(lines.peek()) and not \
-			TEST_HEADER.match(lines.peek()):
+	non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START]
+	while lines and not any(re.match(lines.peek())
+			for re in non_diagnostic_lines):
 		log.append(lines.pop())
 	return log
 
@@ -496,11 +498,15 @@ def print_test_header(test: Test) -> None:
 	test - Test object representing current test being printed
 	"""
 	message = test.name
+	if message != "":
+		# Add a leading space before the subtest counts only if a test name
+		# is provided using a "# Subtest" header line.
+		message += " "
 	if test.expected_count:
 		if test.expected_count == 1:
-			message += ' (1 subtest)'
+			message += '(1 subtest)'
 		else:
-			message += f' ({test.expected_count} subtests)'
+			message += f'({test.expected_count} subtests)'
 	stdout.print_with_timestamp(format_test_divider(message, len(message)))
 
 def print_log(log: Iterable[str]) -> None:
@@ -647,7 +653,7 @@ def bubble_up_test_results(test: Test) -> None:
 	elif test.counts.get_status() == TestStatus.TEST_CRASHED:
 		test.status = TestStatus.TEST_CRASHED
 
-def parse_test(lines: LineStream, expected_num: int, log: List[str]) -> Test:
+def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: bool) -> Test:
 	"""
 	Finds next test to parse in LineStream, creates new Test object,
 	parses any subtests of the test, populates Test object with all
@@ -665,15 +671,32 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str]) -> Test:
 	1..4
 	[subtests]
 
-	- Subtest header line
+	- Subtest header (must include either the KTAP version line or
+	  "# Subtest" header line)
 
-	Example:
+	Example (preferred format with both KTAP version line and
+	"# Subtest" line):
+
+	KTAP version 1
+	# Subtest: name
+	1..3
+	[subtests]
+	ok 1 name
+
+	Example (only "# Subtest" line):
 
 	# Subtest: name
 	1..3
 	[subtests]
 	ok 1 name
 
+	Example (only KTAP version line, compliant with KTAP v1 spec):
+
+	KTAP version 1
+	1..3
+	[subtests]
+	ok 1 name
+
 	- Test result line
 
 	Example:
@@ -685,28 +708,29 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str]) -> Test:
 	expected_num - expected test number for test to be parsed
 	log - list of strings containing any preceding diagnostic lines
 		corresponding to the current test
+	is_subtest - boolean indicating whether test is a subtest
 
 	Return:
 	Test object populated with characteristics and any subtests
 	"""
 	test = Test()
 	test.log.extend(log)
-	parent_test = False
-	main = parse_ktap_header(lines, test)
-	if main:
-		# If KTAP/TAP header is found, attempt to parse
+	if not is_subtest:
+		# If parsing the main/top-level test, parse KTAP version line and
 		# test plan
 		test.name = "main"
+		ktap_line = parse_ktap_header(lines, test)
 		parse_test_plan(lines, test)
 		parent_test = True
 	else:
-		# If KTAP/TAP header is not found, test must be subtest
-		# header or test result line so parse attempt to parser
-		# subtest header
-		parent_test = parse_test_header(lines, test)
+		# If not the main test, attempt to parse a test header containing
+		# the KTAP version line and/or subtest header line
+		ktap_line = parse_ktap_header(lines, test)
+		subtest_line = parse_test_header(lines, test)
+		parent_test = (ktap_line or subtest_line)
 		if parent_test:
-			# If subtest header is found, attempt to parse
-			# test plan and print header
+			# If KTAP version line and/or subtest header is found, attempt
+			# to parse test plan and print test header
 			parse_test_plan(lines, test)
 			print_test_header(test)
 	expected_count = test.expected_count
@@ -721,7 +745,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str]) -> Test:
 		sub_log = parse_diagnostic(lines)
 		sub_test = Test()
 		if not lines or (peek_test_name_match(lines, test) and
-				not main):
+				is_subtest):
 			if expected_count and test_num <= expected_count:
 				# If parser reaches end of test before
 				# parsing expected number of subtests, print
@@ -735,20 +759,19 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str]) -> Test:
 				test.log.extend(sub_log)
 				break
 		else:
-			sub_test = parse_test(lines, test_num, sub_log)
+			sub_test = parse_test(lines, test_num, sub_log, True)
 		subtests.append(sub_test)
 		test_num += 1
 	test.subtests = subtests
-	if not main:
+	if is_subtest:
 		# If not main test, look for test result line
 		test.log.extend(parse_diagnostic(lines))
-		if (parent_test and peek_test_name_match(lines, test)) or \
-				not parent_test:
-			parse_test_result(lines, test, expected_num)
-		else:
+		if test.name != "" and not peek_test_name_match(lines, test):
 			test.add_error('missing subtest result line!')
+		else:
+			parse_test_result(lines, test, expected_num)
 
-	# Check for there being no tests
+	# Check for there being no subtests within parent test
 	if parent_test and len(subtests) == 0:
 		# Don't override a bad status if this test had one reported.
 		# Assumption: no subtests means CRASHED is from Test.__init__()
@@ -758,11 +781,11 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str]) -> Test:
 
 	# Add statuses to TestCounts attribute in Test object
 	bubble_up_test_results(test)
-	if parent_test and not main:
+	if parent_test and is_subtest:
 		# If test has subtests and is not the main test object, print
 		# footer.
 		print_test_footer(test)
-	elif not main:
+	elif is_subtest:
 		print_test_result(test)
 	return test
 
@@ -785,7 +808,7 @@ def parse_run_tests(kernel_output: Iterable[str]) -> Test:
 		test.add_error('Could not find any KTAP output. Did any KUnit tests run?')
 		test.status = TestStatus.FAILURE_TO_PARSE_TESTS
 	else:
-		test = parse_test(lines, 0, [])
+		test = parse_test(lines, 0, [], False)
 		if test.status != TestStatus.NO_TESTS:
 			test.status = test.counts.get_status()
 	stdout.print_with_timestamp(DIVIDER)
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index 84a08cf07242..d7f669cbf2a8 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -312,6 +312,20 @@ class KUnitParserTest(unittest.TestCase):
 		self.assertEqual(kunit_parser._summarize_failed_tests(result),
 			'Failures: all_failed_suite, some_failed_suite.test2')
 
+	def test_ktap_format(self):
+		ktap_log = test_data_path('test_parse_ktap_output.log')
+		with open(ktap_log) as file:
+			result = kunit_parser.parse_run_tests(file.readlines())
+		self.assertEqual(result.counts, kunit_parser.TestCounts(passed=3))
+		self.assertEqual('suite', result.subtests[0].name)
+		self.assertEqual('case_1', result.subtests[0].subtests[0].name)
+		self.assertEqual('case_2', result.subtests[0].subtests[1].name)
+
+	def test_parse_subtest_header(self):
+		ktap_log = test_data_path('test_parse_subtest_header.log')
+		with open(ktap_log) as file:
+			result = kunit_parser.parse_run_tests(file.readlines())
+		self.print_mock.assert_any_call(StrContains('suite (1 subtest)'))
 
 def line_stream_from_strs(strs: Iterable[str]) -> kunit_parser.LineStream:
 	return kunit_parser.LineStream(enumerate(strs, start=1))
diff --git a/tools/testing/kunit/test_data/test_parse_ktap_output.log b/tools/testing/kunit/test_data/test_parse_ktap_output.log
new file mode 100644
index 000000000000..ccdf244e5303
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_parse_ktap_output.log
@@ -0,0 +1,8 @@
+KTAP version 1
+1..1
+  KTAP version 1
+  1..3
+  ok 1 case_1
+  ok 2 case_2
+  ok 3 case_3
+ok 1 suite
diff --git a/tools/testing/kunit/test_data/test_parse_subtest_header.log b/tools/testing/kunit/test_data/test_parse_subtest_header.log
new file mode 100644
index 000000000000..216631092e7b
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_parse_subtest_header.log
@@ -0,0 +1,7 @@
+KTAP version 1
+1..1
+  KTAP version 1
+  # Subtest: suite
+  1..1
+  ok 1 test
+ok 1 suite
\ No newline at end of file