diff --git a/swh/lister/core/tests/test_lister.py b/swh/lister/core/tests/test_lister.py --- a/swh/lister/core/tests/test_lister.py +++ b/swh/lister/core/tests/test_lister.py @@ -18,32 +18,23 @@ pass -@requests_mock.Mocker() class HttpListerTesterBase(abc.ABC): - """Base testing class for subclasses of + """Base testing class for subclass of + swh.lister.core.page_by_page_lister.PageByPageHttpLister and + contain method comman to both HttpSimpleListerTester and + HttpListerTester classes. - swh.lister.core.indexing_lister.IndexingHttpLister. - swh.lister.core.page_by_page_lister.PageByPageHttpLister - See swh.lister.github.tests.test_gh_lister for an example of how + See swh.lister.gitlab.tests.test_lister for an example of how to customize for a specific listing service. """ + Lister = AbstractAttribute('The lister class to test') - test_re = AbstractAttribute('Compiled regex matching the server url. Must' - ' capture the index value.') lister_subdir = AbstractAttribute('bitbucket, github, etc.') good_api_response_file = AbstractAttribute('Example good response body') bad_api_response_file = AbstractAttribute('Example bad response body') - first_index = AbstractAttribute('First index in good_api_response') - entries_per_page = AbstractAttribute('Number of results in good response') LISTER_NAME = 'fake-lister' - convert_type = str - """static method used to convert the "request_index" to its right type (for - indexing listers for example, this is in accordance with the model's - "indexable" column). - - """ # May need to override this if the headers are used for something def response_headers(self, request): @@ -69,29 +60,6 @@ else: self.run = noop - def request_index(self, request): - m = self.test_re.search(request.path_url) - if m and (len(m.groups()) > 0): - return self.convert_type(m.group(1)) - - def mock_response(self, request, context): - self.fl.reset_backoff() - self.rate_limit = 1 - context.status_code = 200 - custom_headers = self.response_headers(request) - context.headers.update(custom_headers) - req_index = self.request_index(request) - - if req_index == self.first_index: - response_file = self.good_api_response_file - else: - response_file = self.bad_api_response_file - - with open('swh/lister/%s/tests/%s' % (self.lister_subdir, - response_file), - 'r', encoding='utf-8') as r: - return r.read() - def mock_limit_n_response(self, n, request, context): self.fl.reset_backoff() if self.rate_limit <= n: @@ -99,12 +67,15 @@ else: return self.mock_response(request, context) - def mock_limit_once_response(self, request, context): - return self.mock_limit_n_response(1, request, context) - def mock_limit_twice_response(self, request, context): return self.mock_limit_n_response(2, request, context) + def get_api_response(self, identifier): + fl = self.get_fl() + if self.response is None: + self.response = fl.safely_issue_request(identifier) + return self.response + def get_fl(self, override_config=None): """Retrieve an instance of fake lister (fl). @@ -117,12 +88,7 @@ self.fl.reset_backoff() return self.fl - def get_api_response(self): - fl = self.get_fl() - if self.response is None: - self.response = fl.safely_issue_request(self.first_index) - return self.response - + @requests_mock.Mocker() def test_is_within_bounds(self, http_mocker): fl = self.get_fl() self.assertFalse(fl.is_within_bounds(1, 2, 3)) @@ -144,31 +110,6 @@ with self.assertRaises(TypeError): fl.is_within_bounds("A:B", "A::B", None) - def test_api_request(self, http_mocker): - http_mocker.get(self.test_re, text=self.mock_limit_twice_response) - with patch.object(time, 'sleep', wraps=time.sleep) as sleepmock: - self.get_api_response() - self.assertEqual(sleepmock.call_count, 2) - - def test_repos_list(self, http_mocker): - http_mocker.get(self.test_re, text=self.mock_response) - li = self.get_fl().transport_response_simplified( - self.get_api_response() - ) - self.assertIsInstance(li, list) - self.assertEqual(len(li), self.entries_per_page) - - def test_model_map(self, http_mocker): - http_mocker.get(self.test_re, text=self.mock_response) - fl = self.get_fl() - li = fl.transport_response_simplified(self.get_api_response()) - di = li[0] - self.assertIsInstance(di, dict) - pubs = [k for k in vars(fl.MODEL).keys() if not k.startswith('_')] - for k in pubs: - if k not in ['last_seen', 'task_id', 'id']: - self.assertIn(k, di) - def disable_scheduler(self, fl): fl.schedule_missing_tasks = Mock(return_value=None) @@ -177,6 +118,76 @@ fl.db_inject_repo = Mock(return_value=fl.MODEL()) fl.disable_deleted_repo_tasks = Mock(return_value=None) + def init_db(self, db, model): + engine = create_engine(db.url()) + model.metadata.create_all(engine) + + +class HttpListerTester(HttpListerTesterBase, abc.ABC): + """Base testing class for subclass of + + swh.lister.core.indexing_lister.IndexingHttpLister. + + See swh.lister.github.tests.test_gh_lister for an example of how + to customize for a specific listing service. + + """ + last_index = AbstractAttribute('Last index in good_api_response') + first_index = AbstractAttribute('First index in good_api_response') + entries_per_page = AbstractAttribute('Number of results in good response') + test_re = AbstractAttribute('Compiled regex matching the server url. Must' + ' capture the index value.') + convert_type = str + """static method used to convert the "request_index" to its right type (for + indexing listers for example, this is in accordance with the model's + "indexable" column). + + """ + @requests_mock.Mocker() + def test_fetch_multiple_pages_yesdb(self, http_mocker): + http_mocker.get(self.test_re, text=self.mock_response) + initdb_args = Postgresql.DEFAULT_SETTINGS['initdb_args'] + initdb_args = ' '.join([initdb_args, '-E UTF-8']) + db = Postgresql(initdb_args=initdb_args) + + fl = self.get_fl(override_config={ + 'lister': { + 'cls': 'local', + 'args': {'db': db.url()} + } + }) + self.init_db(db, fl.MODEL) + + self.disable_scheduler(fl) + + fl.run(min_bound=self.first_index) + + self.assertEqual(fl.db_last_index(), self.last_index) + partitions = fl.db_partition_indices(5) + self.assertGreater(len(partitions), 0) + for k in partitions: + self.assertLessEqual(len(k), 5) + self.assertGreater(len(k), 0) + + def mock_response(self, request, context): + self.fl.reset_backoff() + self.rate_limit = 1 + context.status_code = 200 + custom_headers = self.response_headers(request) + context.headers.update(custom_headers) + req_index = self.request_index(request) + + if req_index == self.first_index: + response_file = self.good_api_response_file + else: + response_file = self.bad_api_response_file + + with open('swh/lister/%s/tests/%s' % (self.lister_subdir, + response_file), + 'r', encoding='utf-8') as r: + return r.read() + + @requests_mock.Mocker() def test_fetch_none_nodb(self, http_mocker): http_mocker.get(self.test_re, text=self.mock_response) fl = self.get_fl() @@ -186,6 +197,7 @@ fl.run(min_bound=1, max_bound=1) # stores no results + @requests_mock.Mocker() def test_fetch_one_nodb(self, http_mocker): http_mocker.get(self.test_re, text=self.mock_response) fl = self.get_fl() @@ -195,6 +207,7 @@ fl.run(min_bound=self.first_index, max_bound=self.first_index) + @requests_mock.Mocker() def test_fetch_multiple_pages_nodb(self, http_mocker): http_mocker.get(self.test_re, text=self.mock_response) fl = self.get_fl() @@ -204,17 +217,118 @@ fl.run(min_bound=self.first_index) - def init_db(self, db, model): - engine = create_engine(db.url()) - model.metadata.create_all(engine) + @requests_mock.Mocker() + def test_repos_list(self, http_mocker): + http_mocker.get(self.test_re, text=self.mock_response) + li = self.get_fl().transport_response_simplified( + self.get_api_response(self.first_index) + ) + self.assertIsInstance(li, list) + self.assertEqual(len(li), self.entries_per_page) + @requests_mock.Mocker() + def test_model_map(self, http_mocker): + http_mocker.get(self.test_re, text=self.mock_response) + fl = self.get_fl() + li = fl.transport_response_simplified( + self.get_api_response(self.first_index)) + di = li[0] + self.assertIsInstance(di, dict) + pubs = [k for k in vars(fl.MODEL).keys() if not k.startswith('_')] + for k in pubs: + if k not in ['last_seen', 'task_id', 'id']: + self.assertIn(k, di) -class HttpListerTester(HttpListerTesterBase, abc.ABC): - last_index = AbstractAttribute('Last index in good_api_response') + def request_index(self, request): + m = self.test_re.search(request.path_url) + if m and (len(m.groups()) > 0): + return self.convert_type(m.group(1)) + + @requests_mock.Mocker() + def test_api_request(self, http_mocker): + http_mocker.get(self.test_re, text=self.mock_limit_twice_response) + with patch.object(time, 'sleep', wraps=time.sleep) as sleepmock: + self.get_api_response(self.first_index) + self.assertEqual(sleepmock.call_count, 2) + + +class HttpSimpleListerTester(HttpListerTesterBase, abc.ABC): + """Base testing class for subclass of + swh.lister.core.simple)_lister.SimpleLister. + + See swh.lister.pypi.tests.test_lister for an example of how + to customize for a specific listing service. + + """ + entries = AbstractAttribute('Number of results in good response') + PAGE = AbstractAttribute("The server api's unique page to retrieve and " + "parse for information") + + @requests_mock.Mocker() + def test_api_request(self, http_mocker): + http_mocker.get(self.PAGE, text=self.mock_limit_twice_response) + with patch.object(time, 'sleep', wraps=time.sleep) as sleepmock: + self.get_api_response(0) + self.assertEqual(sleepmock.call_count, 2) + + @requests_mock.Mocker() + def test_model_map(self, http_mocker): + http_mocker.get(self.PAGE, text=self.mock_response) + fl = self.get_fl() + li = fl.list_packages(self.get_api_response(0)) + li = fl.transport_response_simplified(li) + di = li[0] + self.assertIsInstance(di, dict) + pubs = [k for k in vars(fl.MODEL).keys() if not k.startswith('_')] + for k in pubs: + if k not in ['last_seen', 'task_id', 'id']: + self.assertIn(k, di) + + def get_fl(self, override_config=None): + """Retrieve an instance of fake lister (fl). + + """ + if override_config or self.fl is None: + self.fl = self.Lister( + override_config=override_config) + self.fl.INITIAL_BACKOFF = 1 + + self.fl.reset_backoff() + return self.fl + + def mock_response(self, request, context): + self.fl.reset_backoff() + self.rate_limit = 1 + context.status_code = 200 + custom_headers = self.response_headers(request) + context.headers.update(custom_headers) + response_file = self.good_api_response_file + + with open('swh/lister/%s/tests/%s' % (self.lister_subdir, + response_file), + 'r', encoding='utf-8') as r: + return r.read() + + @requests_mock.Mocker() + def test_fetch_none_nodb(self, http_mocker): + http_mocker.get(self.PAGE, text=self.mock_response) + fl = self.get_fl() + self.disable_scheduler(fl) + self.disable_db(fl) + fl.run() + + @requests_mock.Mocker() + def test_repos_list(self, http_mocker): + http_mocker.get(self.PAGE, text=self.mock_response) + li = self.get_fl().list_packages( + self.get_api_response(0) + ) + self.assertIsInstance(li, list) + self.assertEqual(len(li), self.entries) @requests_mock.Mocker() def test_fetch_multiple_pages_yesdb(self, http_mocker): - http_mocker.get(self.test_re, text=self.mock_response) + http_mocker.get(self.PAGE, text=self.mock_response) initdb_args = Postgresql.DEFAULT_SETTINGS['initdb_args'] initdb_args = ' '.join([initdb_args, '-E UTF-8']) db = Postgresql(initdb_args=initdb_args) @@ -228,12 +342,4 @@ self.init_db(db, fl.MODEL) self.disable_scheduler(fl) - - fl.run(min_bound=self.first_index) - - self.assertEqual(fl.db_last_index(), self.last_index) - partitions = fl.db_partition_indices(5) - self.assertGreater(len(partitions), 0) - for k in partitions: - self.assertLessEqual(len(k), 5) - self.assertGreater(len(k), 0) + fl.run() diff --git a/swh/lister/pypi/tests/api_response.html b/swh/lister/pypi/tests/api_response.html new file mode 100644 --- /dev/null +++ b/swh/lister/pypi/tests/api_response.html @@ -0,0 +1,12 @@ + + + + Simple index + + + 0lever-so + 0lever-utils + 0-orchestrator + 0wned + + \ No newline at end of file diff --git a/swh/lister/pypi/tests/test_lister.py b/swh/lister/pypi/tests/test_lister.py new file mode 100644 --- /dev/null +++ b/swh/lister/pypi/tests/test_lister.py @@ -0,0 +1,56 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +import requests_mock +import unittest +from unittest.mock import patch +from swh.lister.pypi.lister import PyPILister +from swh.lister.core.tests.test_lister import HttpSimpleListerTester + +lister = PyPILister() + +expected_packages = ['0lever-so', '0lever-utils', '0-orchestrator', '0wned'] + +expected_model = { + 'uid': 'arrow', + 'name': 'arrow', + 'full_name': 'arrow', + 'html_url': 'https://pypi.org/pypi/arrow/json', + 'origin_url': 'https://pypi.org/project/arrow/', + 'origin_type': 'pypi', + } + + +class PyPIListerTester(HttpSimpleListerTester, unittest.TestCase): + Lister = PyPILister + PAGE = 'https://pypi.org/simple/' + lister_subdir = 'pypi' + good_api_response_file = 'api_response.html' + bad_api_response_file = 'api_empty_response.json' + entries = 4 + + @requests_mock.Mocker() + def test_list_packages(self, http_mocker): + http_mocker.get(self.PAGE, text=self.mock_response) + fl = self.get_fl() + packages = fl.list_packages(self.get_api_response(0)) + + for package in expected_packages: + assert package in packages + + def test_transport_response_simplified(self): + fl = self.get_fl() + model = fl.transport_response_simplified(['arrow']) + assert len(model) == 1 + for key, values in model[0].items(): + assert values == expected_model[key] + + def test_task_dict(self): + with patch('swh.lister.pypi.lister.utils.create_task_dict') \ + as mock_create_tasks: + lister.task_dict(origin_type='pypi', origin_url='https://abc', + name='test_pack', html_url='https://def') + mock_create_tasks.assert_called_once_with( + 'load-pypi', 'recurring', 'test_pack', 'https://abc', + project_metadata_url='https://def')