def handle(self):
"""Handles start request."""
mapreduce_name = self._get_required_param("name")
mapper_input_reader_spec = self._get_required_param(
"mapper_input_reader")
mapper_handler_spec = self._get_required_param("mapper_handler")
mapper_output_writer_spec = self.request.get("mapper_output_writer")
mapper_params = self._get_params("mapper_params_validator",
"mapper_params.")
params = self._get_params("params_validator", "params.")
mapper_params["processing_rate"] = int(
mapper_params.get("processing_rate")
or model._DEFAULT_PROCESSING_RATE_PER_SEC)
queue_name = mapper_params["queue_name"] = mapper_params.get(
"queue_name", "default")
mapper_spec = model.MapperSpec(
mapper_handler_spec,
mapper_input_reader_spec,
mapper_params,
int(mapper_params.get("shard_count", model._DEFAULT_SHARD_COUNT)),
output_writer_spec=mapper_output_writer_spec)
mapreduce_id = type(self)._start_map(mapreduce_name,
mapper_spec,
params,
base_path=self.base_path(),
queue_name=queue_name,
_app=mapper_params.get("_app"))
self.json_response["mapreduce_id"] = mapreduce_id
def start_map(name,
handler_spec,
reader_spec,
mapper_parameters,
shard_count=_DEFAULT_SHARD_COUNT,
output_writer_spec=None,
mapreduce_parameters=None,
base_path=_DEFAULT_BASE_PATH,
queue_name="default",
eta=None,
countdown=None,
hooks_class_name=None,
_app=None,
transactional=False):
"""Start a new, mapper-only mapreduce.
Args:
name: mapreduce name. Used only for display purposes.
handler_spec: fully qualified name of mapper handler function/class to call.
reader_spec: fully qualified name of mapper reader to use
mapper_parameters: dictionary of parameters to pass to mapper. These are
mapper-specific and also used for reader initialization.
shard_count: number of shards to create.
mapreduce_parameters: dictionary of mapreduce parameters relevant to the
whole job.
base_path: base path of mapreduce library handler specified in app.yaml.
"/mapreduce" by default.
queue_name: executor queue name to be used for mapreduce tasks.
eta: Absolute time when the MR should execute. May not be specified
if 'countdown' is also supplied. This may be timezone-aware or
timezone-naive.
countdown: Time in seconds into the future that this MR should execute.
Defaults to zero.
hooks_class_name: fully qualified name of a hooks.Hooks subclass.
transactional: Specifies if job should be started as a part of already
opened transaction.
Returns:
mapreduce id as string.
"""
mapper_spec = model.MapperSpec(handler_spec,
reader_spec,
mapper_parameters,
shard_count,
output_writer_spec=output_writer_spec)
return handlers.StartJobHandler._start_map(
name,
mapper_spec,
mapreduce_parameters or {},
base_path=base_path,
queue_name=queue_name,
eta=eta,
countdown=countdown,
hooks_class_name=hooks_class_name,
_app=_app,
transactional=transactional)
def _get_mapper_spec(self):
"""Converts self to model.MapperSpec."""
from google.appengine.ext.mapreduce import model
return model.MapperSpec(
handler_spec=util._obj_to_path(self.mapper),
input_reader_spec=util._obj_to_path(self.input_reader_cls),
params=self._get_mapper_params(),
shard_count=self.shard_count,
output_writer_spec=util._obj_to_path(self.output_writer_cls))
def start_map(name,
handler_spec,
reader_spec,
mapper_parameters,
shard_count=None,
output_writer_spec=None,
mapreduce_parameters=None,
base_path=None,
queue_name=None,
eta=None,
countdown=None,
hooks_class_name=None,
_app=None,
in_xg_transaction=False):
"""Start a new, mapper-only mapreduce.
Args:
name: mapreduce name. Used only for display purposes.
handler_spec: fully qualified name of mapper handler function/class to call.
reader_spec: fully qualified name of mapper reader to use
mapper_parameters: dictionary of parameters to pass to mapper. These are
mapper-specific and also used for reader initialization.
shard_count: number of shards to create.
mapreduce_parameters: dictionary of mapreduce parameters relevant to the
whole job.
base_path: base path of mapreduce library handler specified in app.yaml.
"/mapreduce" by default.
queue_name: taskqueue queue name to be used for mapreduce tasks.
see util.get_queue_name.
eta: absolute time when the MR should execute. May not be specified
if 'countdown' is also supplied. This may be timezone-aware or
timezone-naive.
countdown: time in seconds into the future that this MR should execute.
Defaults to zero.
hooks_class_name: fully qualified name of a hooks.Hooks subclass.
in_xg_transaction: controls what transaction scope to use to start this MR
job. If True, there has to be an already opened cross-group transaction
scope. MR will use one entity group from it.
If False, MR will create an independent transaction to start the job
regardless of any existing transaction scopes.
Returns:
mapreduce id as string.
"""
if shard_count is None:
shard_count = parameters.config.SHARD_COUNT
if base_path is None:
base_path = parameters.config.BASE_PATH
if mapper_parameters:
mapper_parameters = dict(mapper_parameters)
if mapreduce_parameters:
mapreduce_parameters = dict(mapreduce_parameters)
if "base_path" not in mapreduce_parameters:
mapreduce_parameters["base_path"] = base_path
else:
mapreduce_parameters = {"base_path": base_path}
mapper_spec = model.MapperSpec(handler_spec,
reader_spec,
mapper_parameters,
shard_count,
output_writer_spec=output_writer_spec)
if in_xg_transaction and not db.is_in_transaction():
logging.warning("Expects an opened xg transaction to start mapreduce "
"when transactional is True.")
return handlers.StartJobHandler._start_map(
name,
mapper_spec,
mapreduce_parameters or {},
base_path=base_path,
queue_name=util.get_queue_name(queue_name),
eta=eta,
countdown=countdown,
hooks_class_name=hooks_class_name,
_app=_app,
in_xg_transaction=in_xg_transaction)
def start_map(name,
handler_spec,
reader_spec,
mapper_parameters,
shard_count=_DEFAULT_SHARD_COUNT,
output_writer_spec=None,
mapreduce_parameters=None,
base_path=None,
queue_name=None,
eta=None,
countdown=None,
hooks_class_name=None,
_app=None,
transactional=False,
transactional_parent=None):
"""Start a new, mapper-only mapreduce.
Args:
name: mapreduce name. Used only for display purposes.
handler_spec: fully qualified name of mapper handler function/class to call.
reader_spec: fully qualified name of mapper reader to use
mapper_parameters: dictionary of parameters to pass to mapper. These are
mapper-specific and also used for reader initialization.
shard_count: number of shards to create.
mapreduce_parameters: dictionary of mapreduce parameters relevant to the
whole job.
base_path: base path of mapreduce library handler specified in app.yaml.
"/mapreduce" by default.
queue_name: executor queue name to be used for mapreduce tasks. If
unspecified it will be the "default" queue or inherit the queue of
the currently running request.
eta: absolute time when the MR should execute. May not be specified
if 'countdown' is also supplied. This may be timezone-aware or
timezone-naive.
countdown: time in seconds into the future that this MR should execute.
Defaults to zero.
hooks_class_name: fully qualified name of a hooks.Hooks subclass.
transactional: specifies if job should be started as a part of already
opened transaction.
transactional_parent: specifies the entity which is already a part of
transaction. Child entity will be used to store task payload if mapreduce
specification is too big.
Returns:
mapreduce id as string.
"""
if not shard_count:
shard_count = _DEFAULT_SHARD_COUNT
if base_path is None:
base_path = base_handler._DEFAULT_BASE_PATH
if mapper_parameters:
mapper_parameters = dict(mapper_parameters)
if mapreduce_parameters:
mapreduce_parameters = dict(mapreduce_parameters)
mapper_spec = model.MapperSpec(handler_spec,
reader_spec,
mapper_parameters,
shard_count,
output_writer_spec=output_writer_spec)
if transactional and not transactional_parent:
logging.error(
"transactional_parent should be specified for transactional starts."
"Your job will fail to start if mapreduce specification is too big."
)
return handlers.StartJobHandler._start_map(
name,
mapper_spec,
mapreduce_parameters or {},
base_path=base_path,
queue_name=queue_name,
eta=eta,
countdown=countdown,
hooks_class_name=hooks_class_name,
_app=_app,
transactional=transactional,
parent_entity=transactional_parent)
