本文整理汇总了Python中mrjob.runner.MRJobRunner类的典型用法代码示例。如果您正苦于以下问题：Python MRJobRunner类的具体用法？Python MRJobRunner怎么用？Python MRJobRunner使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了MRJobRunner类的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_jobconf
def test_jobconf(self):
jobconf = {'FOO': 'bar', 'BAZ': 'qux', 'BAX': 'Arnold'}
runner = MRJobRunner(conf_path=False, jobconf=jobconf)
assert_equal(runner._hadoop_conf_args(0, 1),
['-jobconf', 'BAX=Arnold',
'-jobconf', 'BAZ=qux',
'-jobconf', 'FOO=bar',])示例2: test_cmdenv
def test_cmdenv(self):
cmdenv = {'FOO': 'bar', 'BAZ': 'qux', 'BAX': 'Arnold'}
runner = MRJobRunner(conf_path=False, cmdenv=cmdenv)
assert_equal(runner._hadoop_conf_args(0, 1),
['-cmdenv', 'BAX=Arnold',
'-cmdenv', 'BAZ=qux',
'-cmdenv', 'FOO=bar',])示例3: test_one_file
def test_one_file(self):
runner = MRJobRunner(conf_paths=[])
runner._invoke_sort([self.a], self.out)
self.assertEqual(list(open(self.out)),
['A\n',
'alligator\n',
'apple\n'])示例4: test_two_files
def test_two_files(self):
runner = MRJobRunner(conf_paths=[])
self.addCleanup(runner.cleanup)
runner._invoke_sort([self.a, self.b], self.out)
with open(self.out) as out_f:
self.assertEqual(list(out_f), ["A\n", "B\n", "alligator\n", "apple\n", "ball\n", "banana\n"])示例5: test_hadoop_output_format
def test_hadoop_output_format(self):
format = 'org.apache.hadoop.mapred.SequenceFileOutputFormat'
runner = MRJobRunner(conf_path=False, hadoop_output_format=format)
assert_equal(runner._hadoop_conf_args(0, 1),
['-outputformat', format])
# test multi-step job
assert_equal(runner._hadoop_conf_args(0, 2), [])
assert_equal(runner._hadoop_conf_args(1, 2),
['-outputformat', format])示例6: test_two_files
def test_two_files(self):
runner = MRJobRunner(conf_paths=[])
runner._invoke_sort([self.a, self.b], self.out)
self.assertEqual(list(open(self.out)),
['A\n',
'B\n',
'alligator\n',
'apple\n',
'ball\n',
'banana\n'])示例7: test_one_file
def test_one_file(self):
runner = MRJobRunner(conf_paths=[])
self.addCleanup(runner.cleanup)
runner._invoke_sort([self.a], self.out)
with open(self.out) as out_f:
self.assertEqual(list(out_f),
['A\n',
'alligator\n',
'apple\n'])示例8: test_hadoop_extra_args_comes_first
def test_hadoop_extra_args_comes_first(self):
runner = MRJobRunner(
conf_path=False,
cmdenv={'FOO': 'bar'},
hadoop_input_format='FooInputFormat',
hadoop_output_format='BarOutputFormat',
jobconf={'baz': 'quz'},
hadoop_extra_args=['-libjar', 'qux.jar'])
# hadoop_extra_args should come first
conf_args = runner._hadoop_conf_args(0, 1)
assert_equal(conf_args[:2], ['-libjar', 'qux.jar'])
assert_equal(len(conf_args), 10)示例9: test_interpreter_overrides_steps_python_bin
def test_interpreter_overrides_steps_python_bin(self):
runner = MRJobRunner(interpreter=['ruby'],
steps_python_bin=['python', '-v'])
self.assertEqual(runner._interpreter(), ['ruby'])
self.assertEqual(runner._interpreter(steps=True), ['ruby'])示例10: test_steps_interpreter
def test_steps_interpreter(self):
# including whether steps_interpreter overrides interpreter
runner = MRJobRunner(interpreter=['ruby', '-v'],
steps_interpreter=['ruby'])
self.assertEqual(runner._interpreter(), ['ruby', '-v'])
self.assertEqual(runner._interpreter(steps=True), ['ruby'])示例11: test_interpreter
def test_interpreter(self):
runner = MRJobRunner(interpreter=['ruby'])
self.assertEqual(runner._interpreter(), ['ruby'])
self.assertEqual(runner._interpreter(steps=True), ['ruby'])示例12: test_steps_python_bin
def test_steps_python_bin(self):
runner = MRJobRunner(steps_python_bin=['python', '-v'])
self.assertEqual(runner._interpreter(),
self.default_python_bin())
self.assertEqual(runner._interpreter(steps=True), ['python', '-v'])示例13: test_python_bin
def test_python_bin(self):
runner = MRJobRunner(python_bin=['python', '-v'])
self.assertEqual(runner._interpreter(), ['python', '-v'])
self.assertEqual(runner._interpreter(steps=True), [sys.executable])示例14: test_default
def test_default(self):
runner = MRJobRunner()
self.assertEqual(runner._interpreter(),
self.default_python_bin())
self.assertEqual(runner._interpreter(steps=True),
[sys.executable])示例15: test_environment_variables_windows
def test_environment_variables_windows(self):
runner = MRJobRunner(conf_paths=[])
self.addCleanup(runner.cleanup)
runner._sort_is_windows_sort = True
self.environment_variable_checks(runner, ['TMP'])