def test_find_given_only_two_results(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
results = [person for person in self.dao.find("Thomas")]
self.assertEqual(2, len(results))
sorted(results, key=lambda person: person.id)
self.assertEqual(
[(p.id, p.given, p.middle, p.family) for p in results],
[(4, "Thomas", "", "Addison"), (5, "Thomas", "", "Sydenham")])
def test_find_given_arg_only_two_results() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
results = [person for person in dao.find("Thomas")]
assert 2 == len(results)
sorted(results, key=lambda person: person.id)
assert [(p.id, p.given, p.middle, p.family) for p in results] == \
[(4, "Thomas", "", "Addison"),
(5, "Thomas", "", "Sydenham")]
def test_find_given_only(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
results = [person for person in self.dao.find("Elizabeth")]
self.assertEqual(1, len(results))
p = results[0]
self.assertIsInstance(p, Person)
self.assertEqual((2, "Elizabeth", "", "Blackwell"),
(p.id, p.given_name, p.middle_name, p.family_name))
self.assertTrue(p.created_time < datetime.utcnow())
def test_find_by_id_csv(self) -> None:
self.init_test_data("""\
1,Vivien,Theodore,Thomas,1576109811
2,Hippocrates,,1576109812
3,Thomas,,Addison,1576109813
""")
self.dao = PersonDaoSpark(self.temp_file_path, "csv")
person: Person = self.dao.find_by_id(2)
self.assertEqual("Hippocrates", person.given_name)
def test_find_by_id_duplicate_id(self) -> None:
self.init_test_data("""\
{"id": 1, "given": "Vivien", "middle": "Theodore", "family": "Thomas", "created_time": 1576109811}
{"id": 2, "given": "Hippocrates", "created_time": 1576109813}
{"id": 2, "given": "Thomas", "family": "Addison", "created_time": 1576109814}
""")
self.dao = PersonDaoSpark(self.temp_file_path)
with self.assertRaisesRegex(ValueError, r"duplicate.*([Ii][Dd]|[Kk]ey)"):
self.dao.find_by_id(2)
def test_find_given_arg_only() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
results = [person for person in dao.find("Elizabeth")]
assert 1 == len(results)
p = results[0]
assert isinstance(p, Person)
assert (2, "Elizabeth", "", "Blackwell") == \
(p.id, p.given, p.middle, p.family)
assert p.created_time < datetime.utcnow()
def test_find_by_id_json(self) -> None:
self.init_test_data("""
{"id": 1, "given": "Vivien", "middle": "Theodore", "family": "Thomas", "created_time": 1576109811}
{"id": 2, "given": "Hippocrates", "created_time": 1576109813}
{"id": 3, "given": "Thomas", "family": "Addison", "created_time": 1576109814}
""")
self.dao = PersonDaoSpark(self.temp_file_path)
person: Person = self.dao.find_by_id(2)
self.assertEqual("Hippocrates", person.given_name)
def test_find_all_parts(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
# self.dao.df.printSchema()
results = [person for person in self.dao.find(
"Vivien", "Theodore", "Thomas")]
self.assertEqual(1, len(results))
p = results[0]
self.assertIsInstance(p, Person)
self.assertEqual((1, "Vivien", "Theodore", "Thomas"),
(p.id, p.given_name, p.middle_name, p.family_name))
self.assertTrue(p.created_time < datetime.utcnow())
def test_find_all_args_supplied() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
# dao.df.printSchema()
results = [person for person in dao.find("Vivien", "Theodore", "Thomas")]
assert 1 == len(results)
p = results[0]
assert isinstance(p, Person)
assert (1, "Vivien", "Theodore", "Thomas") == \
(p.id, p.given, p.middle, p.family)
assert p.created_time < datetime.utcnow()
def test_find_by_id_duplicate_id_raises_exception() -> None:
global dao
init_test_data("""\
{"id": 1, "given": "Vivien", "middle": "Theodore", "family": "Thomas", "created_time": 1576109811}
{"id": 2, "given": "Hippocrates", "created_time": 1576109813}
{"id": 2, "given": "Thomas", "family": "Addison", "created_time": 1576109814}
""")
dao = PersonDaoSpark(temp_file_path)
with raises(ValueError, match=r"duplicate.*([Ii][Dd]|[Kk]ey)"):
dao.find_by_id(2)
def test_find_by_id_csv() -> None:
global dao
init_test_data("""\
1,Vivien,Theodore,Thomas,1576109811
2,Hippocrates,,1576109812
3,Thomas,,Addison,1576109813
""")
dao = PersonDaoSpark(temp_file_path, "csv")
person: Person = dao.find_by_id(2)
assert "Hippocrates" == person.given
def test_find_by_id_json() -> None:
global dao
init_test_data("""
{"id": 1, "given": "Vivien", "middle": "Theodore", "family": "Thomas", "created_time": 1576109811}
{"id": 2, "given": "Hippocrates", "created_time": 1576109813}
{"id": 3, "given": "Thomas", "family": "Addison", "created_time": 1576109814}
""")
dao = PersonDaoSpark(temp_file_path)
person: Person = dao.find_by_id(2)
assert "Hippocrates" == person.given
def test_find_several_queries() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
# next(iter(...)) performs one iteration of the Iterable argument
p: Person = next(iter(dao.find("Vivien", "Theodore", "Thomas")))
assert ("Vivien", "Theodore", "Thomas") == (p.given, p.middle, p.family)
p = next(iter(dao.find("Elizabeth", family="Blackwell")))
assert ("Elizabeth", "", "Blackwell") == (p.given, p.middle, p.family)
p = next(iter(dao.find("Hippocrates")))
assert ("Hippocrates", "", "") == (p.given, p.middle, p.family)
def test_find_several_queries(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
# next(iter(...)) performs one iteration of the Iterable argument
p: Person = next(iter(self.dao.find("Vivien", "Theodore", "Thomas")))
self.assertEqual(("Vivien", "Theodore", "Thomas"),
(p.given_name, p.middle_name, p.family_name))
p = next(iter(self.dao.find("Elizabeth", family="Blackwell")))
self.assertEqual(("Elizabeth", "", "Blackwell"),
(p.given_name, p.middle_name, p.family_name))
p = next(iter(self.dao.find("Hippocrates")))
self.assertEqual(("Hippocrates", "", ""),
(p.given_name, p.middle_name, p.family_name))
def test_find_by_id_success(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
person: Person = self.dao.find_by_id(3)
self.assertEqual("Hippocrates", person.given_name)
def test_find_by_id_success() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
person: Person = dao.find_by_id(3)
assert "Hippocrates" == person.given
def test_find_by_id_not_present() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
assert dao.find_by_id(0) is None
def test_find_not_present(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
results: List[Person] = [person for person in self.dao.find("NotThere")]
self.assertEqual(0, len(results))
def test_find_no_args_raises_exception() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
with raises(ValueError, match=r"arguments.*empty"):
next(iter(dao.find()))
def test_find_by_id_not_present(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
self.assertIsNone(self.dao.find_by_id(0))
def test_find_no_args(self) -> None:
self.dao = PersonDaoSpark(PersonDaoSparkTest.data_file)
with self.assertRaisesRegex(ValueError, r"arguments.*empty"):
next(iter(self.dao.find()))
def test_find_person_not_present() -> None:
global dao
dao = PersonDaoSpark(data_file_path)
results: List[Person] = [person for person in dao.find("NotThere")]
assert 0 == len(results)