def test_default_protocol(self):
job = MRJob()
data = iter([b'1\t2', b'\n{"3": ', b'4}\t"fi', b've"\n'])
self.assertEqual(
list(job.parse_output(data)),
[(1, 2), ({'3': 4}, 'five')])
def test_default_protocol(self):
job = MRJob()
data = iter([b'1\t2', b'\n{"3": ', b'4}\t"fi', b've"\n'])
self.assertEqual(
list(job.parse_output(data)),
[(1, 2), ({'3': 4}, 'five')])
def test_default(self):
# test parsing JSON
mr_job = MRJob()
output = '0\t1\n"a"\t"b"\n'
mr_job.stdout = StringIO(output)
self.assertEqual(mr_job.parse_output(), [(0, 1), ('a', 'b')])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_default(self):
# test parsing JSON
mr_job = MRJob()
output = '0\t1\n"a"\t"b"\n'
mr_job.stdout = StringIO(output)
self.assertEqual(mr_job.parse_output(), [(0, 1), ('a', 'b')])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_protocol_instance(self):
# see if we can use the repr protocol
mr_job = MRJob()
output = "0\t1\n['a', 'b']\tset(['c', 'd'])\n"
mr_job.stdout = StringIO(output)
self.assertEqual(mr_job.parse_output(ReprProtocol()), [(0, 1), (["a", "b"], set(["c", "d"]))])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_protocol_instance(self):
# see if we can use the repr protocol
mr_job = MRJob()
output = "0\t1\n['a', 'b']\tset(['c', 'd'])\n"
mr_job.stdout = StringIO(output)
self.assertEqual(mr_job.parse_output(ReprProtocol()),
[(0, 1), (['a', 'b'], set(['c', 'd']))])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_bytes_value_protocol(self):
job = MRJob()
job.OUTPUT_PROTOCOL = BytesValueProtocol
data = iter([b'one\nt', b'wo\nthree\n', b'four\nfive\n'])
self.assertEqual(list(job.parse_output(data)), [(None, b'one\n'),
(None, b'two\n'),
(None, b'three\n'),
(None, b'four\n'),
(None, b'five\n')])
def test_parse_output(self):
# test parsing JSON
mr_job = MRJob()
output = b'0\t1\n"a"\t"b"\n'
mr_job.stdout = BytesIO(output)
with logger_disabled('mrjob.job'):
self.assertEqual(mr_job.parse_output(), [(0, 1), ('a', 'b')])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_deprecated_protocol_aliases(self):
# see if we can use the repr protocol
mr_job = MRJob()
output = "0\t1\n['a', 'b']\tset(['c', 'd'])\n"
mr_job.stdout = StringIO(output)
assert_equal(mr_job.parse_output('repr'),
[(0, 1), (['a', 'b'], set(['c', 'd']))])
# verify that stdout is not cleared
assert_equal(mr_job.stdout.getvalue(), output)
def test_deprecated_protocol_aliases(self):
# see if we can use the repr protocol
mr_job = MRJob()
output = "0\t1\n['a', 'b']\tset(['c', 'd'])\n"
mr_job.stdout = StringIO(output)
assert_equal(mr_job.parse_output('repr'),
[(0, 1), (['a', 'b'], set(['c', 'd']))])
# verify that stdout is not cleared
assert_equal(mr_job.stdout.getvalue(), output)
def test_parse_output(self):
# test parsing JSON
mr_job = MRJob()
output = b'0\t1\n"a"\t"b"\n'
mr_job.stdout = BytesIO(output)
with logger_disabled('mrjob.job'):
self.assertEqual(mr_job.parse_output(), [(0, 1), ('a', 'b')])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_parse_output_with_protocol_instance(self):
# see if we can use the repr protocol
mr_job = MRJob()
output = b"0\t1\n['a', 'b']\tset(['c', 'd'])\n"
mr_job.stdout = BytesIO(output)
with logger_disabled('mrjob.job'):
self.assertEqual(mr_job.parse_output(ReprProtocol()),
[(0, 1), (['a', 'b'], set(['c', 'd']))])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_parse_output_with_protocol_instance(self):
# see if we can use the repr protocol
mr_job = MRJob()
output = b"0\t1\n['a', 'b']\tset(['c', 'd'])\n"
mr_job.stdout = BytesIO(output)
with logger_disabled('mrjob.job'):
self.assertEqual(mr_job.parse_output(ReprProtocol()),
[(0, 1), (['a', 'b'], set(['c', 'd']))])
# verify that stdout is not cleared
self.assertEqual(mr_job.stdout.getvalue(), output)
def test_bytes_value_protocol(self):
job = MRJob()
job.OUTPUT_PROTOCOL = BytesValueProtocol
data = iter([b'one\nt', b'wo\nthree\n', b'four\nfive\n'])
self.assertEqual(
list(job.parse_output(data)),
[(None, b'one\n'),
(None, b'two\n'),
(None, b'three\n'),
(None, b'four\n'),
(None, b'five\n')])
