def _run_command(cfg_json_uri,
command,
split_ind=None,
num_splits=None,
runner=None):
pipeline_cfg_dict = file_to_json(cfg_json_uri)
rv_config_dict = pipeline_cfg_dict.get('rv_config')
rv_config.reset(
config_overrides=rv_config_dict,
verbosity=rv_config.verbosity,
tmp_dir=rv_config.tmp_dir)
tmp_dir_obj = rv_config.get_tmp_dir()
tmp_dir = tmp_dir_obj.name
cfg = build_config(pipeline_cfg_dict)
pipeline = cfg.build(tmp_dir)
if num_splits is not None and split_ind is None and runner is not None:
runner = registry.get_runner(runner)()
split_ind = runner.get_split_ind()
command_fn = getattr(pipeline, command)
if num_splits is not None and num_splits > 1:
msg = 'Running {} command split {}/{}...'.format(
command, split_ind + 1, num_splits)
click.echo(click.style(msg, fg='green'))
command_fn(split_ind=split_ind, num_splits=num_splits)
else:
msg = 'Running {} command...'.format(command)
click.echo(click.style(msg, fg='green'))
command_fn()
def run(runner, cfg_path, commands, arg, splits):
"""Run commands within pipelines using runner named RUNNER."""
tmp_dir_obj = rv_config.get_tmp_dir()
tmp_dir = tmp_dir_obj.name
cfg_module = importlib.import_module(cfg_path)
args = dict(arg)
args = convert_bool_args(args)
cfgs = get_configs(cfg_module, runner, args)
runner = registry.get_runner(runner)()
for cfg in cfgs:
cfg.update()
cfg.rv_config = rv_config.get_config_dict(registry.rv_config_schema)
cfg.recursive_validate_config()
cfg_dict = cfg.dict()
cfg_json_uri = cfg.get_config_uri()
json_to_file(cfg_dict, cfg_json_uri)
pipeline = cfg.build(tmp_dir)
if not commands:
commands = pipeline.commands
runner.run(cfg_json_uri, pipeline, commands, num_splits=splits)
def run(runner: str, cfg_module: str, commands: List[str],
arg: List[Tuple[str, str]], splits: int):
"""Subcommand to run commands within pipelines using runner named RUNNER.
Args:
runner: name of runner to use
cfg_module: name of module with `get_configs` function that returns
PipelineConfigs
commands: names of commands to run within pipeline. The order in which
to run them is based on the Pipeline.commands attribute. If this is
omitted, all commands will be run.
"""
tmp_dir_obj = rv_config.get_tmp_dir()
tmp_dir = tmp_dir_obj.name
cfg_module = importlib.import_module(cfg_module)
args = dict(arg)
args = convert_bool_args(args)
cfgs = get_configs(cfg_module, runner, args)
runner = registry.get_runner(runner)()
for cfg in cfgs:
cfg.update()
cfg.rv_config = rv_config.get_config_dict(registry.rv_config_schema)
cfg.recursive_validate_config()
cfg_dict = cfg.dict()
cfg_json_uri = cfg.get_config_uri()
json_to_file(cfg_dict, cfg_json_uri)
pipeline = cfg.build(tmp_dir)
if not commands:
commands = pipeline.commands
runner.run(cfg_json_uri, pipeline, commands, num_splits=splits)
def run(runner: str, cfg_module: str, commands: List[str],
arg: List[Tuple[str, str]], splits: int):
"""Run COMMANDS within pipelines in CFG_MODULE using RUNNER.
RUNNER: name of the Runner to use
CFG_MODULE: the module with `get_configs` function that returns PipelineConfigs.
This can either be a Python module path or a local path to a .py file.
COMMANDS: space separated sequence of commands to run within pipeline. The order in
which to run them is based on the Pipeline.commands attribute. If this is omitted,
all commands will be run.
"""
tmp_dir_obj = rv_config.get_tmp_dir()
tmp_dir = tmp_dir_obj.name
args = dict(arg)
args = convert_bool_args(args)
cfgs = get_configs(cfg_module, runner, args)
runner = registry.get_runner(runner)()
for cfg in cfgs:
cfg.update()
cfg.rv_config = rv_config.get_config_dict(registry.rv_config_schema)
cfg.recursive_validate_config()
cfg_dict = cfg.dict()
cfg_json_uri = cfg.get_config_uri()
json_to_file(cfg_dict, cfg_json_uri)
pipeline = cfg.build(tmp_dir)
if not commands:
commands = pipeline.commands
runner.run(cfg_json_uri, pipeline, commands, num_splits=splits)
def _run_command(cfg_json_uri: str,
command: str,
split_ind: Optional[int] = None,
num_splits: Optional[int] = None,
runner: Optional[str] = None):
"""Run a single command using a serialized PipelineConfig.
Args:
cfg_json_uri: URI of a JSON file with a serialized PipelineConfig
command: name of command to run
split_ind: the index that a split command should assume
num_splits: the total number of splits to use
runner: the name of the runner to use
"""
pipeline_cfg_dict = file_to_json(cfg_json_uri)
rv_config_dict = pipeline_cfg_dict.get('rv_config')
rv_config.set_everett_config(profile=rv_config.profile,
config_overrides=rv_config_dict)
tmp_dir_obj = rv_config.get_tmp_dir()
tmp_dir = tmp_dir_obj.name
cfg = build_config(pipeline_cfg_dict)
pipeline = cfg.build(tmp_dir)
if num_splits is not None and split_ind is None and runner is not None:
runner = registry.get_runner(runner)()
split_ind = runner.get_split_ind()
command_fn = getattr(pipeline, command)
if num_splits is not None and num_splits > 1:
msg = 'Running {} command split {}/{}...'.format(
command, split_ind + 1, num_splits)
click.echo(click.style(msg, fg='green'))
command_fn(split_ind=split_ind, num_splits=num_splits)
else:
msg = 'Running {} command...'.format(command)
click.echo(click.style(msg, fg='green'))
command_fn()
def run(runner: str, cfg_module: str, commands: List[str],
arg: List[Tuple[str, str]], splits: int):
"""Run COMMANDS within pipelines in CFG_MODULE using RUNNER.
RUNNER: name of the Runner to use
CFG_MODULE: the module with `get_configs` function that returns PipelineConfigs.
This can either be a Python module path or a local path to a .py file.
COMMANDS: space separated sequence of commands to run within pipeline. The order in
which to run them is based on the Pipeline.commands attribute. If this is omitted,
all commands will be run.
"""
tmp_dir_obj = rv_config.get_tmp_dir()
tmp_dir = tmp_dir_obj.name
args = dict(arg)
args = convert_bool_args(args)
cfgs = get_configs(cfg_module, runner, args)
runner = registry.get_runner(runner)()
for cfg in cfgs:
_run_pipeline(cfg, runner, tmp_dir, splits, commands)
