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-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)
self.hadoop_opts_opt_group = OptionGroup(
self.option_parser,
'Configuring or emulating Hadoop (these apply when you set -r'
' hadoop, -r emr, or -r local)')
self.option_parser.add_option_group(self.hadoop_opts_opt_group)
add_hadoop_shared_opts(self.hadoop_opts_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 Amazon Elastic MapReduce (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-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-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)
self._passthrough_options.extend(
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)
self.hadoop_opts_opt_group = OptionGroup(
self.option_parser,
'Configuring or emulating Hadoop (these apply when you set -r'
' hadoop, -r emr, or -r local)')
self.option_parser.add_option_group(self.hadoop_opts_opt_group)
add_hadoop_shared_opts(self.hadoop_opts_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 Amazon Elastic MapReduce (these apply when you set -r'
' emr)')
self.option_parser.add_option_group(self.emr_opt_group)
add_emr_opts(self.emr_opt_group)