def test_local_jar(self):
fake_jar = os.path.join(self.tmp_dir, 'fake.jar')
open(fake_jar, 'w').close()
job = MRJustAJar(['-r', 'hadoop', '--jar', fake_jar])
job.sandbox()
with job.make_runner() as runner:
runner.run()
hadoop_cmd_args = get_mock_hadoop_cmd_args()
hadoop_jar_cmd_args = [args for args in hadoop_cmd_args if
args and args[0] == 'jar']
self.assertEqual(len(hadoop_jar_cmd_args), 1)
self.assertEqual(hadoop_jar_cmd_args[0], ['jar', fake_jar])
def test_local_jar(self):
fake_jar = os.path.join(self.tmp_dir, 'fake.jar')
open(fake_jar, 'w').close()
job = MRJustAJar(['-r', 'hadoop', '--jar', fake_jar])
job.sandbox()
with job.make_runner() as runner:
runner.run()
hadoop_cmd_args = get_mock_hadoop_cmd_args()
hadoop_jar_cmd_args = [args for args in hadoop_cmd_args if
args and args[0] == 'jar']
self.assertEqual(len(hadoop_jar_cmd_args), 1)
self.assertEqual(hadoop_jar_cmd_args[0], ['jar', fake_jar])
def test_input_output_interpolation(self):
fake_jar = os.path.join(self.tmp_dir, 'fake.jar')
open(fake_jar, 'w').close()
input1 = os.path.join(self.tmp_dir, 'input1')
open(input1, 'w').close()
input2 = os.path.join(self.tmp_dir, 'input2')
open(input2, 'w').close()
job = MRJarAndStreaming(
['-r', 'hadoop', '--jar', fake_jar, input1, input2])
job.sandbox()
add_mock_hadoop_output([b'']) # need this for streaming step
with job.make_runner() as runner:
runner.run()
hadoop_cmd_args = get_mock_hadoop_cmd_args()
hadoop_jar_cmd_args = [
args for args in hadoop_cmd_args if args and args[0] == 'jar'
]
self.assertEqual(len(hadoop_jar_cmd_args), 2)
jar_args, streaming_args = hadoop_jar_cmd_args
self.assertEqual(len(jar_args), 5)
self.assertEqual(jar_args[0], 'jar')
self.assertEqual(jar_args[1], fake_jar)
self.assertEqual(jar_args[2], 'stuff')
# check input is interpolated
input_arg = ','.join(
runner._upload_mgr.uri(path) for path in (input1, input2))
self.assertEqual(jar_args[3], input_arg)
# check output of jar is input of next step
jar_output_arg = jar_args[4]
streaming_input_arg = streaming_args[streaming_args.index('-input')
+ 1]
self.assertEqual(jar_output_arg, streaming_input_arg)
def test_hdfs_jar_uri(self):
# this could change, but for now, we pass URIs straight through
mock_hdfs_jar = os.path.join(get_mock_hdfs_root(), 'fake.jar')
open(mock_hdfs_jar, 'w').close()
jar_uri = 'hdfs:///fake.jar'
job = MRJustAJar(['-r', 'hadoop', '--jar', jar_uri])
job.sandbox()
with job.make_runner() as runner:
with logger_disabled('mrjob.hadoop'):
# `hadoop jar` doesn't actually accept URIs
self.assertRaises(StepFailedException, runner.run)
hadoop_cmd_args = get_mock_hadoop_cmd_args()
hadoop_jar_cmd_args = [args for args in hadoop_cmd_args if
args and args[0] == 'jar']
self.assertEqual(len(hadoop_jar_cmd_args), 1)
self.assertEqual(hadoop_jar_cmd_args[0], ['jar', jar_uri])
def test_hdfs_jar_uri(self):
# this could change, but for now, we pass URIs straight through
mock_hdfs_jar = os.path.join(get_mock_hdfs_root(), 'fake.jar')
open(mock_hdfs_jar, 'w').close()
jar_uri = 'hdfs:///fake.jar'
job = MRJustAJar(['-r', 'hadoop', '--jar', jar_uri])
job.sandbox()
with job.make_runner() as runner:
with logger_disabled('mrjob.hadoop'):
# `hadoop jar` doesn't actually accept URIs
self.assertRaises(StepFailedException, runner.run)
hadoop_cmd_args = get_mock_hadoop_cmd_args()
hadoop_jar_cmd_args = [args for args in hadoop_cmd_args if
args and args[0] == 'jar']
self.assertEqual(len(hadoop_jar_cmd_args), 1)
self.assertEqual(hadoop_jar_cmd_args[0], ['jar', jar_uri])
def test_input_output_interpolation(self):
fake_jar = os.path.join(self.tmp_dir, 'fake.jar')
open(fake_jar, 'w').close()
input1 = os.path.join(self.tmp_dir, 'input1')
open(input1, 'w').close()
input2 = os.path.join(self.tmp_dir, 'input2')
open(input2, 'w').close()
job = MRJarAndStreaming(
['-r', 'hadoop', '--jar', fake_jar, input1, input2])
job.sandbox()
add_mock_hadoop_output([b'']) # need this for streaming step
with job.make_runner() as runner:
runner.run()
hadoop_cmd_args = get_mock_hadoop_cmd_args()
hadoop_jar_cmd_args = [args for args in hadoop_cmd_args if
args and args[0] == 'jar']
self.assertEqual(len(hadoop_jar_cmd_args), 2)
jar_args, streaming_args = hadoop_jar_cmd_args
self.assertEqual(len(jar_args), 5)
self.assertEqual(jar_args[0], 'jar')
self.assertEqual(jar_args[1], fake_jar)
self.assertEqual(jar_args[2], 'stuff')
# check input is interpolated
input_arg = ','.join(
runner._upload_mgr.uri(path) for path in (input1, input2))
self.assertEqual(jar_args[3], input_arg)
# check output of jar is input of next step
jar_output_arg = jar_args[4]
streaming_input_arg = streaming_args[
streaming_args.index('-input') + 1]
self.assertEqual(jar_output_arg, streaming_input_arg)
def _test_end_to_end(self, args=()):
# read from STDIN, a local file, and a remote file
stdin = BytesIO(b'foo\nbar\n')
local_input_path = os.path.join(self.tmp_dir, 'input')
with open(local_input_path, 'w') as local_input_file:
local_input_file.write('bar\nqux\n')
input_to_upload = os.path.join(self.tmp_dir, 'remote_input')
with open(input_to_upload, 'w') as input_to_upload_file:
input_to_upload_file.write('foo\n')
remote_input_path = 'hdfs:///data/foo'
check_call([self.hadoop_bin,
'fs', '-put', input_to_upload, remote_input_path])
# add counters
add_mock_hadoop_counters({'foo': {'bar': 23}})
add_mock_hadoop_counters({'baz': {'qux': 42}})
# doesn't matter what the intermediate output is; just has to exist.
add_mock_hadoop_output([b''])
add_mock_hadoop_output([b'1\t"qux"\n2\t"bar"\n',
b'2\t"foo"\n5\tnull\n'])
mr_job = MRTwoStepJob(['-r', 'hadoop', '-v',
'--no-conf', '--hadoop-arg', '-libjar',
'--hadoop-arg', 'containsJars.jar'] + list(args)
+ ['-', local_input_path, remote_input_path]
+ ['--jobconf', 'x=y'])
mr_job.sandbox(stdin=stdin)
local_tmp_dir = None
results = []
with mr_job.make_runner() as runner:
assert isinstance(runner, HadoopJobRunner)
runner.run()
for line in runner.stream_output():
key, value = mr_job.parse_output_line(line)
results.append((key, value))
local_tmp_dir = runner._get_local_tmp_dir()
# make sure cleanup hasn't happened yet
assert os.path.exists(local_tmp_dir)
assert any(runner.fs.ls(runner.get_output_dir()))
# make sure we're writing to the correct path in HDFS
hdfs_root = get_mock_hdfs_root()
self.assertEqual(sorted(os.listdir(hdfs_root)), ['data', 'user'])
home_dir = os.path.join(hdfs_root, 'user', getpass.getuser())
self.assertEqual(os.listdir(home_dir), ['tmp'])
self.assertEqual(os.listdir(os.path.join(home_dir, 'tmp')),
['mrjob'])
self.assertEqual(runner._opts['hadoop_extra_args'],
['-libjar', 'containsJars.jar'])
# make sure mrjob.tar.gz is was uploaded
self.assertTrue(os.path.exists(runner._mrjob_tar_gz_path))
self.assertIn(runner._mrjob_tar_gz_path,
runner._upload_mgr.path_to_uri())
# make sure setup script exists, and mrjob.tar.gz is added
# to PYTHONPATH in it
self.assertTrue(os.path.exists(runner._setup_wrapper_script_path))
self.assertIn(runner._setup_wrapper_script_path,
runner._upload_mgr.path_to_uri())
mrjob_tar_gz_name = runner._working_dir_mgr.name(
'archive', runner._mrjob_tar_gz_path)
with open(runner._setup_wrapper_script_path) as wrapper:
self.assertTrue(any(
('export PYTHONPATH' in line and mrjob_tar_gz_name in line)
for line in wrapper))
self.assertEqual(runner.counters(),
[{'foo': {'bar': 23}},
{'baz': {'qux': 42}}])
self.assertEqual(sorted(results),
[(1, 'qux'), (2, 'bar'), (2, 'foo'), (5, None)])
# make sure we called hadoop the way we expected
hadoop_cmd_args = get_mock_hadoop_cmd_args()
jar_cmd_args = [cmd_args for cmd_args in hadoop_cmd_args
if cmd_args[:1] == ['jar']]
self.assertEqual(len(jar_cmd_args), 2)
step_0_args, step_1_args = jar_cmd_args
# check input/output format
self.assertIn('-inputformat', step_0_args)
self.assertNotIn('-outputformat', step_0_args)
self.assertNotIn('-inputformat', step_1_args)
self.assertIn('-outputformat', step_1_args)
# make sure -libjar extra arg comes before -mapper
for args in (step_0_args, step_1_args):
self.assertIn('-libjar', args)
self.assertIn('-mapper', args)
self.assertLess(args.index('-libjar'), args.index('-mapper'))
# make sure -jobconf made it through
self.assertIn('-D', step_0_args)
self.assertIn('x=y', step_0_args)
self.assertIn('-D', step_1_args)
# job overrides jobconf in step 1
self.assertIn('x=z', step_1_args)
# make sure cleanup happens
assert not os.path.exists(local_tmp_dir)
assert not any(runner.fs.ls(runner.get_output_dir()))
def _test_end_to_end(self, args=()):
# read from STDIN, a local file, and a remote file
stdin = BytesIO(b'foo\nbar\n')
local_input_path = os.path.join(self.tmp_dir, 'input')
with open(local_input_path, 'w') as local_input_file:
local_input_file.write('bar\nqux\n')
input_to_upload = os.path.join(self.tmp_dir, 'remote_input')
with open(input_to_upload, 'w') as input_to_upload_file:
input_to_upload_file.write('foo\n')
remote_input_path = 'hdfs:///data/foo'
check_call([self.hadoop_bin,
'fs', '-put', input_to_upload, remote_input_path])
# add counters
add_mock_hadoop_counters({'foo': {'bar': 23}})
add_mock_hadoop_counters({'baz': {'qux': 42}})
# doesn't matter what the intermediate output is; just has to exist.
add_mock_hadoop_output([b''])
add_mock_hadoop_output([b'1\t"qux"\n2\t"bar"\n',
b'2\t"foo"\n5\tnull\n'])
mr_job = MRTwoStepJob(['-r', 'hadoop', '-v',
'--no-conf', '--hadoop-arg', '-libjar',
'--hadoop-arg', 'containsJars.jar'] + list(args)
+ ['-', local_input_path, remote_input_path]
+ ['--jobconf', 'x=y'])
mr_job.sandbox(stdin=stdin)
local_tmp_dir = None
results = []
with mr_job.make_runner() as runner:
assert isinstance(runner, HadoopJobRunner)
runner.run()
for line in runner.stream_output():
key, value = mr_job.parse_output_line(line)
results.append((key, value))
local_tmp_dir = runner._get_local_tmp_dir()
# make sure cleanup hasn't happened yet
assert os.path.exists(local_tmp_dir)
assert any(runner.fs.ls(runner.get_output_dir()))
# make sure we're writing to the correct path in HDFS
hdfs_root = get_mock_hdfs_root()
self.assertEqual(sorted(os.listdir(hdfs_root)), ['data', 'user'])
home_dir = os.path.join(hdfs_root, 'user', getpass.getuser())
self.assertEqual(os.listdir(home_dir), ['tmp'])
self.assertEqual(os.listdir(os.path.join(home_dir, 'tmp')),
['mrjob'])
self.assertEqual(runner._opts['hadoop_extra_args'],
['-libjar', 'containsJars.jar'])
# make sure mrjob.tar.gz is was uploaded
self.assertTrue(os.path.exists(runner._mrjob_tar_gz_path))
self.assertIn(runner._mrjob_tar_gz_path,
runner._upload_mgr.path_to_uri())
# make sure setup script exists, and mrjob.tar.gz is added
# to PYTHONPATH in it
self.assertTrue(os.path.exists(runner._setup_wrapper_script_path))
self.assertIn(runner._setup_wrapper_script_path,
runner._upload_mgr.path_to_uri())
mrjob_tar_gz_name = runner._working_dir_mgr.name(
'archive', runner._mrjob_tar_gz_path)
with open(runner._setup_wrapper_script_path) as wrapper:
self.assertTrue(any(
('export PYTHONPATH' in line and mrjob_tar_gz_name in line)
for line in wrapper))
self.assertEqual(runner.counters(),
[{'foo': {'bar': 23}},
{'baz': {'qux': 42}}])
self.assertEqual(sorted(results),
[(1, 'qux'), (2, 'bar'), (2, 'foo'), (5, None)])
# make sure we called hadoop the way we expected
hadoop_cmd_args = get_mock_hadoop_cmd_args()
jar_cmd_args = [cmd_args for cmd_args in hadoop_cmd_args
if cmd_args[:1] == ['jar']]
self.assertEqual(len(jar_cmd_args), 2)
step_0_args, step_1_args = jar_cmd_args
# check input/output format
self.assertIn('-inputformat', step_0_args)
self.assertNotIn('-outputformat', step_0_args)
self.assertNotIn('-inputformat', step_1_args)
self.assertIn('-outputformat', step_1_args)
# make sure -libjar extra arg comes before -mapper
for args in (step_0_args, step_1_args):
self.assertIn('-libjar', args)
self.assertIn('-mapper', args)
self.assertLess(args.index('-libjar'), args.index('-mapper'))
# make sure -D (jobconf) made it through
self.assertIn('-D', step_0_args)
self.assertIn('x=y', step_0_args)
self.assertIn('-D', step_1_args)
# job overrides jobconf in step 1
self.assertIn('x=z', step_1_args)
# make sure cleanup happens
assert not os.path.exists(local_tmp_dir)
assert not any(runner.fs.ls(runner.get_output_dir()))
