swh_scheduler = <swh.scheduler.backend.SchedulerBackend object at 0x7f966fea1e10> requests_mock = <requests_mock.mocker.Mocker object at 0x7f966fea19e8> mocker = <pytest_mock.plugin.MockerFixture object at 0x7f966fea1400> maven_index = 'doc 0\n field 0\n name u\n type string\n value al.aldi|sprova4j|0.1.0|sources|jar\n field 1\n name m\n ...e rootGroups\n field 19\n name rootGroupsList\n type string\n value al\nEND\nchecksum 00000000003321211082\n' maven_index_incr = 'doc 0\n field 0\n name u\n type string\n value al.aldi|sprova4j|0.1.0|sources|jar\n field 1\n name m\n ...otGroups\n field 19\n name rootGroupsList\n type string\n value com|al\nEND\nchecksum 00000000004102281591\n' maven_index_incr_3 = 'doc 0\n field 0\n name u\n type string\n value al.aldi|sprova4j|0.1.1|sources|jar\n field 1\n name m\n ...otGroups\n field 20\n name rootGroupsList\n type string\n value com|al\nEND\nchecksum 00000000002844832287\n' maven_pom_1 = '<?xml version="1.0" encoding="UTF-8"?>\n<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.a...actId>\n <version>3.10.0</version>\n <scope>test</scope>\n </dependency>\n </dependencies>\n</project>\n' maven_pom_2 = '<?xml version="1.0" encoding="UTF-8"?>\n<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.a...actId>\n <version>3.10.0</version>\n <scope>test</scope>\n </dependency>\n </dependencies>\n</project>\n' maven_pom_3 = '<?xml version="1.0" encoding="UTF-8"?>\n<!--\n ~ DISCLAIMER\n ~ Copyright 2019 ArangoDB GmbH, Cologne, Germany\n ~...n>\n <name>ArangoDB GmbH</name>\n <url>https://www.arangodb.com</url>\n </organization>\n\n</project>' maven_pom_4 = '<?xml version="1.0" encoding="UTF-8"?>\n<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.o...guicier.git</developerConnection>\n <url>https://github.com/jolira/wicket-guicier\n </url>\n </scm>\n</project>' def test_maven_incremental_listing_3( swh_scheduler, requests_mock, mocker, maven_index, maven_index_incr, maven_index_incr_3, maven_pom_1, maven_pom_2, maven_pom_3, maven_pom_4, ): """Covers full listing of multiple pages, checking page results and listed origins, with a second updated run for statefulness, and a third updated run with deleted artefacts and a parent pom (i.e. without groupId).""" lister = MavenLister( scheduler=swh_scheduler, url=MVN_URL, instance="maven.org", index_url=INDEX_URL, incremental=True, ) # Set up test. requests_mock.get(INDEX_URL, text=maven_index) requests_mock.get(URL_POM_1, text=maven_pom_1) requests_mock.get(URL_POM_2, text=maven_pom_2) # Then run the lister. stats = lister.run() # Start test checks. assert lister.incremental assert lister.updated assert stats.pages == 4 assert stats.origins == 4 # Second execution of the lister, incremental mode lister = MavenLister( scheduler=swh_scheduler, url=MVN_URL, instance="maven.org", index_url=INDEX_URL, incremental=True, ) scheduler_state = lister.get_state_from_scheduler() assert scheduler_state is not None assert scheduler_state.last_seen_doc == 3 # Set up test. requests_mock.get(INDEX_URL, text=maven_index_incr) requests_mock.get(URL_POM_3, text=maven_pom_3) # Then run the lister. stats = lister.run() # Start test checks. assert lister.incremental assert lister.updated assert stats.pages == 1 assert stats.origins == 1 scheduler_origins = swh_scheduler.get_listed_origins(lister.lister_obj.id).results origin_urls = [origin.url for origin in scheduler_origins] assert sorted(origin_urls) == sorted(LIST_SRC + LIST_GIT + LIST_GIT_INCR) for origin in scheduler_origins: if origin.visit_type == "maven": for src in LIST_SRC_DATA: if src.get("url") == origin.url: artifact = origin.extra_loader_arguments["artifacts"][0] > assert src.get("time") == artifact["time"] E AssertionError: assert '2021-07-12 1....335000+00:00' == '2021-07-12 1....335000+00:00' E - 2021-07-12 17:06:59.335000+00:00 E ? ^ E + 2021-07-12 19:06:59.335000+00:00 E ? ^ .tox/py3/lib/python3.7/site-packages/swh/lister/maven/tests/test_lister.py:310: AssertionError