本文整理汇总了Python中tests.mr_cmd_job.CmdJob类的典型用法代码示例。如果您正苦于以下问题:Python CmdJob类的具体用法?Python CmdJob怎么用?Python CmdJob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CmdJob类的11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,您的评价将有助于我们的系统推荐出更棒的Python代码示例。
示例1: test_multiple_2
def test_multiple_2(self):
data = b"x\ny\nz\n"
job = CmdJob(["--mapper-cmd=cat", "--reducer-cmd-2", "wc -l", "--runner=local", "--no-conf"])
job.sandbox(stdin=BytesIO(data))
with job.make_runner() as r:
r.run()
self.assertEqual(sum(int(l) for l in r.stream_output()), 3)
开发者ID:alanhdu,项目名称:mrjob,代码行数:7,代码来源:test_local.py
示例2: test_multiple_2
def test_multiple_2(self):
data = 'x\ny\nz\n'
job = CmdJob(['--mapper-cmd=cat', '--reducer-cmd-2', 'wc -l',
'--runner=local', '--no-conf'])
job.sandbox(stdin=StringIO(data))
with job.make_runner() as r:
r.run()
self.assertEqual(sum(int(l) for l in r.stream_output()), 3)
开发者ID:eklitzke,项目名称:mrjob,代码行数:8,代码来源:test_local.py
示例3: test_cat_mapper
def test_cat_mapper(self):
data = b"x\ny\nz\n"
job = CmdJob(["--mapper-cmd=cat", "--runner=local"])
job.sandbox(stdin=BytesIO(data))
with job.make_runner() as r:
self.assertEqual(r._get_steps(), [{"type": "streaming", "mapper": {"type": "command", "command": "cat"}}])
r.run()
lines = [line.strip() for line in list(r.stream_output())]
self.assertEqual(sorted(lines), sorted(data.split()))
开发者ID:alanhdu,项目名称:mrjob,代码行数:10,代码来源:test_local.py
示例4: test_cat_mapper
def test_cat_mapper(self):
data = 'x\ny\nz\n'
job = CmdJob(['--mapper-cmd=cat', '--runner=local'])
job.sandbox(stdin=StringIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[{
'type': 'streaming',
'mapper': {
'type': 'command',
'command': 'cat'}}])
r.run()
self.assertEqual(''.join(r.stream_output()), data)
开发者ID:eklitzke,项目名称:mrjob,代码行数:16,代码来源:test_local.py
示例5: test_cat_mapper
def test_cat_mapper(self):
data = 'x\ny\nz\n'
job = CmdJob(['--mapper-cmd=cat', '--runner=local'])
job.sandbox(stdin=StringIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[{
'type': 'streaming',
'mapper': {
'type': 'command',
'command': 'cat'}}])
r.run()
lines = [line.strip() for line in list(r.stream_output())]
self.assertItemsEqual(lines, data.split())
开发者ID:SeanOC,项目名称:mrjob,代码行数:16,代码来源:test_local.py
示例6: test_cat_reducer
def test_cat_reducer(self):
data = 'x\ny\nz\n'
job = CmdJob(['--reducer-cmd', 'cat -e', '--runner=local'])
job.sandbox(stdin=StringIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[{
'type': 'streaming',
'mapper': {
'type': 'script',
},
'reducer': {
'type': 'command',
'command': 'cat -e'}}])
r.run()
lines = list(r.stream_output())
self.assertEqual(lines, ['x$\n', 'y$\n', 'z$\n'])
开发者ID:eklitzke,项目名称:mrjob,代码行数:20,代码来源:test_local.py
示例7: test_cat_reducer
def test_cat_reducer(self):
data = b"x\ny\nz\n"
job = CmdJob(["--reducer-cmd", "cat -e", "--runner=local"])
job.sandbox(stdin=BytesIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[
{
"type": "streaming",
"mapper": {"type": "script"},
"reducer": {"type": "command", "command": "cat -e"},
}
],
)
r.run()
lines = list(r.stream_output())
self.assertEqual(sorted(lines), [b"x$\n", b"y$\n", b"z$\n"])
开发者ID:alanhdu,项目名称:mrjob,代码行数:20,代码来源:test_local.py
示例8: test_uniq_combiner
def test_uniq_combiner(self):
data = 'x\nx\nx\nx\nx\nx\n'
job = CmdJob(['--combiner-cmd=uniq', '--runner=local'])
job.sandbox(stdin=StringIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[{
'type': 'streaming',
'mapper': {
'type': 'script',
},
'combiner': {
'type': 'command',
'command': 'uniq'}}])
r.run()
# there are 2 map tasks, each of which has 1 combiner, and all rows
# are the same, so we should end up with just 2 values
self.assertEqual(''.join(r.stream_output()), 'x\nx\n')
开发者ID:eklitzke,项目名称:mrjob,代码行数:22,代码来源:test_local.py
示例9: test_uniq_combiner
def test_uniq_combiner(self):
data = b"x\nx\nx\nx\nx\nx\n"
job = CmdJob(["--combiner-cmd=uniq", "--runner=local"])
job.sandbox(stdin=BytesIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[
{
"type": "streaming",
"mapper": {"type": "script"},
"combiner": {"type": "command", "command": "uniq"},
}
],
)
r.run()
# there are 2 map tasks, each of which has 1 combiner, and all rows
# are the same, so we should end up with just 2 values
self.assertEqual(b"".join(r.stream_output()), b"x\nx\n")
开发者ID:alanhdu,项目名称:mrjob,代码行数:22,代码来源:test_local.py
示例10: test_multiple
def test_multiple(self):
data = 'x\nx\nx\nx\nx\nx\n'
mapper_cmd = 'cat -e'
reducer_cmd = bash_wrap('wc -l | tr -Cd "[:digit:]"')
job = CmdJob([
'--runner', 'local',
'--mapper-cmd', mapper_cmd,
'--combiner-cmd', 'uniq',
'--reducer-cmd', reducer_cmd])
job.sandbox(stdin=StringIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[{
'type': 'streaming',
'mapper': {'type': 'command', 'command': mapper_cmd},
'combiner': {'type': 'command', 'command': 'uniq'},
'reducer': {'type': 'command', 'command': reducer_cmd},
}])
r.run()
self.assertEqual(list(r.stream_output()), ['2'])
开发者ID:eklitzke,项目名称:mrjob,代码行数:23,代码来源:test_local.py
示例11: test_multiple
def test_multiple(self):
data = b"x\nx\nx\nx\nx\nx\n"
mapper_cmd = "cat -e"
reducer_cmd = bash_wrap('wc -l | tr -Cd "[:digit:]"')
job = CmdJob(
["--runner", "local", "--mapper-cmd", mapper_cmd, "--combiner-cmd", "uniq", "--reducer-cmd", reducer_cmd]
)
job.sandbox(stdin=BytesIO(data))
with job.make_runner() as r:
self.assertEqual(
r._get_steps(),
[
{
"type": "streaming",
"mapper": {"type": "command", "command": mapper_cmd},
"combiner": {"type": "command", "command": "uniq"},
"reducer": {"type": "command", "command": reducer_cmd},
}
],
)
r.run()
self.assertEqual(list(r.stream_output()), [b"2"])
开发者ID:alanhdu,项目名称:mrjob,代码行数:24,代码来源:test_local.py
注:本文中的tests.mr_cmd_job.CmdJob类示例由纯净天空整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论