swh_scheduler = <swh.scheduler.backend.SchedulerBackend object at 0x7f06480d0048> requests_mock = <requests_mock.mocker.Mocker object at 0x7f06480d0da0> maven_pom_1_malformed = b'<?xml version="1.0" encoding="UTF-8"?>\n<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven....actId>\n <version>3.10.0</version>\n <scope>test</scope>\n </dependency>\n </dependencies>\n</project>\n' def test_maven_full_listing_malformed( swh_scheduler, requests_mock, maven_pom_1_malformed, ): """Covers full listing of multiple pages, checking page results with a malformed scm entry in pom.""" lister = MavenLister( scheduler=swh_scheduler, url=MVN_URL, instance="maven.org", index_url=INDEX_URL, incremental=False, ) # Set up test. requests_mock.get(URL_POM_1, content=maven_pom_1_malformed) # Then run the lister. stats = lister.run() # Start test checks. assert stats.pages == 5 scheduler_origins = swh_scheduler.get_listed_origins(lister.lister_obj.id).results origin_urls = [origin.url for origin in scheduler_origins] # 2 git origins + 1 maven origin with 2 releases (one per jar) assert len(origin_urls) == 3 > assert sorted(origin_urls) == sorted(LIST_GIT + LIST_GIT_INCR + LIST_SRC) E AssertionError: assert ['git://githu...ldi/sprova4j'] == ['https://git...ldi/sprova4j'] E At index 0 diff: 'git://github.com/ArangoDB-Community/arangodb-graphql-java.git' != 'https://github.com/ArangoDB-Community/arangodb-graphql-java' E Full diff: E [ E - 'https://github.com/ArangoDB-Community/arangodb-graphql-java', E ? ^ --- E + 'git://github.com/ArangoDB-Community/arangodb-graphql-java.git', E ? ^^ ++++... E E ...Full output truncated (4 lines hidden), use '-vv' to show .tox/py3/lib/python3.7/site-packages/swh/lister/maven/tests/test_lister.py:186: AssertionError