Clean validation of Tavern files is required to allow using it in a productive way

[hsq125]

I'm stuck for hours with a simple test with one config file and one external stage file.

Each time there is a single mistake, I'm left with a stack trace of 500 line without clear indication about what is wrong.

to_verify = {'test_name': 'Full path, from client sync to period renewal.', 'includes': [{'test_name': 'Database delete stage', 'i...prod/command/SynchronizeClients'}, 'response': {'status_code': 502, 'headers': {'content-type': 'application/json'}}}]}
schema = {'name': 'Test schema', 'desc': 'Matches test blocks', 'schema;any_request_json': {'func': 'validate_request_json', 't... 'map', 'mapping': {'username': {'type': 'str', 'required': True}, 'password': {'type': 'str', 'required': False}}}}}}}

    def verify_generic(to_verify, schema):
        """Verify a generic file against a given schema
    
        Args:
            to_verify (dict): Filename of source tests to check
            schema (dict): Schema to verify against
    
        Raises:
            BadSchemaError: Schema did not match
        """
        logger.debug("Verifying %s against %s", to_verify, schema)
    
        here = os.path.dirname(os.path.abspath(__file__))
        extension_module_filename = os.path.join(here, "extensions.py")
    
        verifier = core.Core(
            source_data=to_verify,
            schema_data=schema,
            extensions=[extension_module_filename],
        )
    
        try:
>           verifier.validate()

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/tavern/schemas/files.py:106: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <pykwalify.core.Core object at 0x7f0663c92490>, raise_exception = True

    def validate(self, raise_exception=True):
        """
        """
        log.debug(u"starting core")
    
        self._start_validate(self.source)
        self.validation_errors = [unicode(error) for error in self.errors]
        self.validation_errors_exceptions = self.errors
    
        if self.errors is None or len(self.errors) == 0:
            log.info(u"validation.valid")
        else:
            log.error(u"validation.invalid")
            log.error(u" --- All found errors ---")
            log.error(self.validation_errors)
            if raise_exception:
>               raise SchemaError(u"Schema validation failed:\n - {error_msg}.".format(
                    error_msg=u'.\n - '.join(self.validation_errors)))
E               pykwalify.errors.SchemaError: <SchemaError: error code 2: Schema validation failed:
E                - Cannot find required key 'name'. Path: '/includes/0'.
E                - Cannot find required key 'description'. Path: '/includes/0'.
E                - Key 'test_name' was not defined. Path: '/includes/0'.
E                - Key 'includes' was not defined. Path: '/includes/0'.: Path: '/'>

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/pykwalify/core.py:194: SchemaError

The above exception was the direct cause of the following exception:

cls = <class '_pytest.runner.CallInfo'>
func = <function call_runtest_hook.<locals>.<lambda> at 0x7f0662a263a0>
when = 'call'
reraise = (<class '_pytest.outcomes.Exit'>, <class 'KeyboardInterrupt'>)

    @classmethod
    def from_call(
        cls,
        func: "Callable[[], TResult]",
        when: "Literal['collect', 'setup', 'call', 'teardown']",
        reraise: Optional[
            Union[Type[BaseException], Tuple[Type[BaseException], ...]]
        ] = None,
    ) -> "CallInfo[TResult]":
        excinfo = None
        start = timing.time()
        precise_start = timing.perf_counter()
        try:
>           result: Optional[TResult] = func()

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/_pytest/runner.py:311: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

>       lambda: ihook(item=item, **kwds), when=when, reraise=reraise
    )

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/_pytest/runner.py:255: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <_HookCaller 'pytest_runtest_call'>, args = ()
kwargs = {'item': <YamlItem Full path, from client sync to period renewal.>}
notincall = set()

    def __call__(self, *args, **kwargs):
        if args:
            raise TypeError("hook calling supports only keyword arguments")
        assert not self.is_historic()
        if self.spec and self.spec.argnames:
            notincall = (
                set(self.spec.argnames) - set(["__multicall__"]) - set(kwargs.keys())
            )
            if notincall:
                warnings.warn(
                    "Argument(s) {} which are declared in the hookspec "
                    "can not be found in this hook call".format(tuple(notincall)),
                    stacklevel=2,
                )
>       return self._hookexec(self, self.get_hookimpls(), kwargs)

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/pluggy/hooks.py:286: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <_pytest.config.PytestPluginManager object at 0x7f066319fac0>
hook = <_HookCaller 'pytest_runtest_call'>
methods = [<HookImpl plugin_name='runner', plugin=<module '_pytest.runner' from '/home/detailoc/dev/dependencies/python/aws38/li...xception' from '/home/detailoc/dev/dependencies/python/aws38/lib/python3.8/site-packages/_pytest/threadexception.py'>>]
kwargs = {'item': <YamlItem Full path, from client sync to period renewal.>}

    def _hookexec(self, hook, methods, kwargs):
        # called from all hookcaller instances.
        # enable_tracing will set its own wrapping function at self._inner_hookexec
>       return self._inner_hookexec(hook, methods, kwargs)

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/pluggy/manager.py:93: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

hook = <_HookCaller 'pytest_runtest_call'>
methods = [<HookImpl plugin_name='runner', plugin=<module '_pytest.runner' from '/home/detailoc/dev/dependencies/python/aws38/li...xception' from '/home/detailoc/dev/dependencies/python/aws38/lib/python3.8/site-packages/_pytest/threadexception.py'>>]
kwargs = {'item': <YamlItem Full path, from client sync to period renewal.>}

>   self._inner_hookexec = lambda hook, methods, kwargs: hook.multicall(
        methods,
        kwargs,
        firstresult=hook.spec.opts.get("firstresult") if hook.spec else False,
    )

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/pluggy/manager.py:84: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

hook_impls = [<HookImpl plugin_name='runner', plugin=<module '_pytest.runner' from '/home/detailoc/dev/dependencies/python/aws38/li...xception' from '/home/detailoc/dev/dependencies/python/aws38/lib/python3.8/site-packages/_pytest/threadexception.py'>>]
caller_kwargs = {'item': <YamlItem Full path, from client sync to period renewal.>}
firstresult = False

    def _multicall(hook_impls, caller_kwargs, firstresult=False):
        """Execute a call into multiple python functions/methods and return the
        result(s).
    
        ``caller_kwargs`` comes from _HookCaller.__call__().
        """
        __tracebackhide__ = True
        results = []
        excinfo = None
        try:  # run impl and wrapper setup functions in a loop
            teardowns = []
            try:
                for hook_impl in reversed(hook_impls):
                    try:
                        args = [caller_kwargs[argname] for argname in hook_impl.argnames]
                    except KeyError:
                        for argname in hook_impl.argnames:
                            if argname not in caller_kwargs:
                                raise HookCallError(
                                    "hook call must provide argument %r" % (argname,)
                                )
    
                    if hook_impl.hookwrapper:
                        try:
                            gen = hook_impl.function(*args)
                            next(gen)  # first yield
                            teardowns.append(gen)
                        except StopIteration:
                            _raise_wrapfail(gen, "did not yield")
                    else:
                        res = hook_impl.function(*args)
                        if res is not None:
                            results.append(res)
                            if firstresult:  # halt further impl calls
                                break
            except BaseException:
                excinfo = sys.exc_info()
        finally:
            if firstresult:  # first result hooks return a single value
                outcome = _Result(results[0] if results else None, excinfo)
            else:
                outcome = _Result(results, excinfo)
    
            # run all wrapper post-yield blocks
            for gen in reversed(teardowns):
                try:
                    gen.send(outcome)
                    _raise_wrapfail(gen, "has second yield")
                except StopIteration:
                    pass
    
>           return outcome.get_result()

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/pluggy/callers.py:208: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <pluggy.callers._Result object at 0x7f0663c92640>

    def get_result(self):
        """Get the result(s) for this hook call.
    
        If the hook was marked as a ``firstresult`` only a single value
        will be returned otherwise a list of results.
        """
        __tracebackhide__ = True
        if self._excinfo is None:
            return self._result
        else:
            ex = self._excinfo
            if _py3:
>               raise ex[1].with_traceback(ex[2])

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/pluggy/callers.py:80: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

hook_impls = [<HookImpl plugin_name='runner', plugin=<module '_pytest.runner' from '/home/detailoc/dev/dependencies/python/aws38/li...xception' from '/home/detailoc/dev/dependencies/python/aws38/lib/python3.8/site-packages/_pytest/threadexception.py'>>]
caller_kwargs = {'item': <YamlItem Full path, from client sync to period renewal.>}
firstresult = False

    def _multicall(hook_impls, caller_kwargs, firstresult=False):
        """Execute a call into multiple python functions/methods and return the
        result(s).
    
        ``caller_kwargs`` comes from _HookCaller.__call__().
        """
        __tracebackhide__ = True
        results = []
        excinfo = None
        try:  # run impl and wrapper setup functions in a loop
            teardowns = []
            try:
                for hook_impl in reversed(hook_impls):
                    try:
                        args = [caller_kwargs[argname] for argname in hook_impl.argnames]
                    except KeyError:
                        for argname in hook_impl.argnames:
                            if argname not in caller_kwargs:
                                raise HookCallError(
                                    "hook call must provide argument %r" % (argname,)
                                )
    
                    if hook_impl.hookwrapper:
                        try:
                            gen = hook_impl.function(*args)
                            next(gen)  # first yield
                            teardowns.append(gen)
                        except StopIteration:
                            _raise_wrapfail(gen, "did not yield")
                    else:
>                       res = hook_impl.function(*args)

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/pluggy/callers.py:187: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

item = <YamlItem Full path, from client sync to period renewal.>

    def pytest_runtest_call(item: Item) -> None:
        _update_current_test_var(item, "call")
        try:
            del sys.last_type
            del sys.last_value
            del sys.last_traceback
        except AttributeError:
            pass
        try:
            item.runtest()
        except Exception as e:
            # Store trace info to allow postmortem debugging
            sys.last_type = type(e)
            sys.last_value = e
            assert e.__traceback__ is not None
            # Skip *this* frame
            sys.last_traceback = e.__traceback__.tb_next
>           raise e

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/_pytest/runner.py:170: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

item = <YamlItem Full path, from client sync to period renewal.>

    def pytest_runtest_call(item: Item) -> None:
        _update_current_test_var(item, "call")
        try:
            del sys.last_type
            del sys.last_value
            del sys.last_traceback
        except AttributeError:
            pass
        try:
>           item.runtest()

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/_pytest/runner.py:162: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <YamlItem Full path, from client sync to period renewal.>

    def runtest(self):
        # Do a deep copy because this sometimes still retains things from previous tests(?)
        self.global_cfg = copy.deepcopy(load_global_cfg(self.config))
    
        self.global_cfg.setdefault("variables", {})
    
        load_plugins(self.global_cfg)
    
        self.global_cfg["tavern_internal"] = {"pytest_hook_caller": self.config.hook}
    
        # INTERNAL
        # NOTE - now that we can 'mark' tests, we could use pytest.mark.xfail
        # instead. This doesn't differentiate between an error in verification
        # and an error when running the test though.
        xfail = self.spec.get("_xfail", False)
    
        try:
            fixture_values = self._load_fixture_values()
            self.global_cfg["variables"].update(fixture_values)
    
            call_hook(
                self.global_cfg,
                "pytest_tavern_beta_before_every_test_run",
                test_dict=self.spec,
                variables=self.global_cfg["variables"],
            )
    
>           verify_tests(self.spec)

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/tavern/testutils/pytesthook/item.py:184: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

test_spec = {'test_name': 'Full path, from client sync to period renewal.', 'includes': [{'test_name': 'Database delete stage', 'i...prod/command/SynchronizeClients'}, 'response': {'status_code': 502, 'headers': {'content-type': 'application/json'}}}]}
with_plugins = True

    def verify_tests(test_spec, with_plugins=True):
        """Verify that a specific test block is correct
    
        Todo:
            Load schema file once. Requires some caching of the file
    
        Args:
            test_spec (dict): Test in dictionary form
    
        Raises:
            BadSchemaError: Schema did not match
        """
        here = os.path.dirname(os.path.abspath(__file__))
    
        schema_filename = os.path.join(here, "tests.schema.yaml")
        schema = load_schema_file(schema_filename, with_plugins)
    
>       verify_generic(test_spec, schema)

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/tavern/schemas/files.py:152: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

to_verify = {'test_name': 'Full path, from client sync to period renewal.', 'includes': [{'test_name': 'Database delete stage', 'i...prod/command/SynchronizeClients'}, 'response': {'status_code': 502, 'headers': {'content-type': 'application/json'}}}]}
schema = {'name': 'Test schema', 'desc': 'Matches test blocks', 'schema;any_request_json': {'func': 'validate_request_json', 't... 'map', 'mapping': {'username': {'type': 'str', 'required': True}, 'password': {'type': 'str', 'required': False}}}}}}}

    def verify_generic(to_verify, schema):
        """Verify a generic file against a given schema
    
        Args:
            to_verify (dict): Filename of source tests to check
            schema (dict): Schema to verify against
    
        Raises:
            BadSchemaError: Schema did not match
        """
        logger.debug("Verifying %s against %s", to_verify, schema)
    
        here = os.path.dirname(os.path.abspath(__file__))
        extension_module_filename = os.path.join(here, "extensions.py")
    
        verifier = core.Core(
            source_data=to_verify,
            schema_data=schema,
            extensions=[extension_module_filename],
        )
    
        try:
            verifier.validate()
        except pykwalify.errors.PyKwalifyException as e:
            logger.exception("Error validating %s", to_verify)
>           raise BadSchemaError() from e
E           tavern.util.exceptions.BadSchemaError

../../../../../dependencies/python/aws38/lib/python3.8/site-packages/tavern/schemas/files.py:109: BadSchemaError


========================= 1 failed, 1 passed in 0.76s ==========================

Process finished with exit code 1

This is just an example, but Tavern crashes here and there depending on the issue. That is not possible to use this in a productive way.

[michaelboulton]

This is partially the reason I'm switching to using jsonschema in the next release, it should be able to provide more useful errors like

../../.tox/py38-generic/lib/python3.8/site-packages/tavern/_core/schema/jsonschema.py:134: in verify_jsonschema
    raise BadSchemaError(msg) from e
E   tavern._core.exceptions.BadSchemaError:
E   ---
E
E   Additional properties are not allowed ('blllblbb' was unexpected)
E
E     - name: Send with basic auth
E       blllblbb: gg
E       request:
E         url: "{global_host}/authtest/basic"
E         method: GET
E         auth:
E           - "fakeuser"
E           - "fakepass"
E       response:
E         status_code: 200
E         json:
E           auth_type: basic
E           auth_user: fakeuser
E           auth_pass: fakepass

For the time being you can also use the pytest -q flag which won't print so many lines of code in each traceback