def configure_options(self):
"""Define arguments for this script. Called from :py:meth:`__init__()`.
Run ``python -m mrjob.job.MRJob --help`` to see all options.
Re-define to define custom command-line arguments::
def configure_options(self):
super(MRYourJob, self).configure_options
self.add_passthrough_option(...)
self.add_file_option(...)
...
"""
self.option_parser.add_option('--help',
dest='help_main',
action='store_true',
default=False,
help='show this message and exit')
self.option_parser.add_option('--help-emr',
dest='help_emr',
action='store_true',
default=False,
help='show EMR-related options')
self.option_parser.add_option('--help-hadoop',
dest='help_hadoop',
action='store_true',
default=False,
help='show Hadoop-related options')
self.option_parser.add_option(
'--help-local',
dest='help_local',
action='store_true',
default=False,
help='show local/inline runner-related options')
self.option_parser.add_option('--help-runner',
dest='help_runner',
action='store_true',
default=False,
help='show runner-related options')
# protocol stuff
self.proto_opt_group = OptionGroup(self.option_parser, 'Protocols')
self.option_parser.add_option_group(self.proto_opt_group)
_add_protocol_opts(self.proto_opt_group)
# options for running the entire job
self.runner_opt_group = OptionGroup(self.option_parser,
'Running the entire job')
self.option_parser.add_option_group(self.runner_opt_group)
_add_runner_opts(self.runner_opt_group, self._DEFAULT_RUNNER)
_add_basic_opts(self.runner_opt_group)
# options for inline/local runners
self.local_opt_group = OptionGroup(
self.option_parser,
'Running locally (these apply when you set -r inline or -r local)')
self.option_parser.add_option_group(self.local_opt_group)
_add_local_opts(self.local_opt_group)
# options common to Hadoop and EMR
self.hadoop_emr_opt_group = OptionGroup(
self.option_parser,
'Running on Hadoop or EMR (these apply when you set -r hadoop or'
' -r emr)')
self.option_parser.add_option_group(self.hadoop_emr_opt_group)
_add_hadoop_emr_opts(self.hadoop_emr_opt_group)
# options for running the job on Hadoop
self.hadoop_opt_group = OptionGroup(
self.option_parser,
'Running on Hadoop (these apply when you set -r hadoop)')
self.option_parser.add_option_group(self.hadoop_opt_group)
_add_hadoop_opts(self.hadoop_opt_group)
# options for running the job on EMR
self.emr_opt_group = OptionGroup(
self.option_parser,
'Running on EMR (these apply when you set -r emr)')
self.option_parser.add_option_group(self.emr_opt_group)
_add_emr_opts(self.emr_opt_group)
def configure_options(self):
"""Define arguments for this script. Called from :py:meth:`__init__()`.
Run ``python -m mrjob.job.MRJob --help`` to see all options.
Re-define to define custom command-line arguments::
def configure_options(self):
super(MRYourJob, self).configure_options
self.add_passthrough_option(...)
self.add_file_option(...)
...
"""
self.option_parser.add_option(
'--help', dest='help_main', action='store_true', default=False,
help='show this message and exit')
self.option_parser.add_option(
'--help-dataproc', dest='help_dataproc', action='store_true',
default=False,
help='show Dataproc-related options')
self.option_parser.add_option(
'--help-emr', dest='help_emr', action='store_true', default=False,
help='show EMR-related options')
self.option_parser.add_option(
'--help-hadoop', dest='help_hadoop', action='store_true',
default=False,
help='show Hadoop-related options')
self.option_parser.add_option(
'--help-local', dest='help_local', action='store_true',
default=False,
help='show local/inline runner-related options')
self.option_parser.add_option(
'--help-runner', dest='help_runner', action='store_true',
default=False, help='show runner-related options')
# protocol stuff
self.proto_opt_group = OptionGroup(
self.option_parser, 'Protocols')
self.option_parser.add_option_group(self.proto_opt_group)
_add_protocol_opts(self.proto_opt_group)
# options for running the entire job
self.runner_opt_group = OptionGroup(
self.option_parser, 'Running the entire job')
self.option_parser.add_option_group(self.runner_opt_group)
_add_runner_opts(self.runner_opt_group, self._DEFAULT_RUNNER)
_add_basic_opts(self.runner_opt_group)
# options for inline/local runners
self.local_opt_group = OptionGroup(
self.option_parser,
'Running locally (these apply when you set -r inline or -r local)')
self.option_parser.add_option_group(self.local_opt_group)
_add_local_opts(self.local_opt_group)
# options common to Hadoop and EMR
self.hadoop_emr_opt_group = OptionGroup(
self.option_parser,
'Running on Hadoop or EMR (these apply when you set -r hadoop or'
' -r emr)')
self.option_parser.add_option_group(self.hadoop_emr_opt_group)
_add_hadoop_emr_opts(self.hadoop_emr_opt_group)
# options for running the job on Hadoop
self.hadoop_opt_group = OptionGroup(
self.option_parser,
'Running on Hadoop (these apply when you set -r hadoop)')
self.option_parser.add_option_group(self.hadoop_opt_group)
_add_hadoop_opts(self.hadoop_opt_group)
# options for running the job on Dataproc or EMR
self.dataproc_emr_opt_group = OptionGroup(
self.option_parser,
'Running on Dataproc or EMR (these apply when you set -r dataproc'
' or -r emr)')
self.option_parser.add_option_group(self.dataproc_emr_opt_group)
_add_dataproc_emr_opts(self.dataproc_emr_opt_group)
# options for running the job on Dataproc
self.dataproc_opt_group = OptionGroup(
self.option_parser,
'Running on Dataproc (these apply when you set -r dataproc)')
self.option_parser.add_option_group(self.dataproc_opt_group)
_add_dataproc_opts(self.dataproc_opt_group)
# options for running the job on EMR
self.emr_opt_group = OptionGroup(
self.option_parser,
'Running on EMR (these apply when you set -r emr)')
self.option_parser.add_option_group(self.emr_opt_group)
_add_emr_opts(self.emr_opt_group)