def __new__(cls, field_name):
return super(FieldNotDefinedErrorData, cls).__new__(
cls, check.str_param(field_name, "field_name")
)
def __init__(self, mode, selector):
self.mode = check.str_param(mode, 'mode')
self.message = 'Mode {mode} not found in pipeline {pipeline}.'.format(
mode=mode, pipeline=selector.name
)
def __init__(self, partition_set_name):
super(DauphinPartitionSetNotFoundError, self).__init__()
self.partition_set_name = check.str_param(partition_set_name, 'partition_set_name')
self.message = 'Partition set {partition_set_name} could not be found.'.format(
partition_set_name=self.partition_set_name
)
def get_step_by_key(self, key):
check.str_param(key, "key")
return self.step_dict[key]
def __init__(self, message, pipeline):
super(DauphinInvalidSubsetError, self).__init__()
self.message = check.str_param(message, 'message')
self.pipeline = pipeline
def __new__(cls, solid_name, output_name):
return super(OutputHandleSnap, cls).__new__(
cls,
solid_name=check.str_param(solid_name, "solid_name"),
output_name=check.str_param(output_name, "output_name"),
)
def get_step_input(plan_builder, solid, input_name, input_def,
dependency_structure, handle, parent_step_inputs):
check.inst_param(plan_builder, "plan_builder", _PlanBuilder)
check.inst_param(solid, "solid", Solid)
check.str_param(input_name, "input_name")
check.inst_param(input_def, "input_def", InputDefinition)
check.inst_param(dependency_structure, "dependency_structure",
DependencyStructure)
check.opt_inst_param(handle, "handle", SolidHandle)
check.opt_list_param(parent_step_inputs,
"parent_step_inputs",
of_type=StepInput)
solid_config = plan_builder.environment_config.solids.get(str(handle))
if solid_config and input_name in solid_config.inputs:
return StepInput(
name=input_name,
dagster_type=input_def.dagster_type,
source_type=StepInputSourceType.CONFIG,
config_data=solid_config.inputs[input_name],
)
input_handle = solid.input_handle(input_name)
if dependency_structure.has_singular_dep(input_handle):
solid_output_handle = dependency_structure.get_singular_dep(
input_handle)
return StepInput(
name=input_name,
dagster_type=input_def.dagster_type,
source_type=StepInputSourceType.SINGLE_OUTPUT,
source_handles=[
plan_builder.get_output_handle(solid_output_handle)
],
)
if dependency_structure.has_multi_deps(input_handle):
solid_output_handles = dependency_structure.get_multi_deps(
input_handle)
return StepInput(
name=input_name,
dagster_type=input_def.dagster_type,
source_type=StepInputSourceType.MULTIPLE_OUTPUTS,
source_handles=[
plan_builder.get_output_handle(solid_output_handle)
for solid_output_handle in solid_output_handles
],
)
if solid.container_maps_input(input_name):
parent_name = solid.container_mapped_input(input_name).definition.name
parent_inputs = {
step_input.name: step_input
for step_input in parent_step_inputs
}
if parent_name in parent_inputs:
parent_input = parent_inputs[parent_name]
return StepInput(
name=input_name,
dagster_type=input_def.dagster_type,
source_type=parent_input.source_type,
source_handles=parent_input.source_handles,
config_data=parent_input.config_data,
)
if solid.definition.input_has_default(input_name):
return StepInput(
name=input_name,
dagster_type=input_def.dagster_type,
source_type=StepInputSourceType.DEFAULT_VALUE,
config_data=solid.definition.default_value_for_input(input_name),
)
# At this point we have an input that is not hooked up to
# the output of another solid or provided via environment config.
# We will allow this for "Nothing" type inputs and continue.
if input_def.dagster_type.kind == DagsterTypeKind.NOTHING:
return None
# Otherwise we throw an error.
raise DagsterInvariantViolationError(
("In pipeline {pipeline_name} solid {solid_name}, input {input_name} "
"must get a value either (a) from a dependency or (b) from the "
"inputs section of its configuration.").format(
pipeline_name=plan_builder.pipeline_name,
solid_name=solid.name,
input_name=input_name))
def validate_solid_fn(decorator_name,
fn_name,
compute_fn,
input_defs,
expected_positionals=None,
exclude_nothing=True):
check.str_param(decorator_name, 'decorator_name')
check.str_param(fn_name, 'fn_name')
check.callable_param(compute_fn, 'compute_fn')
check.list_param(input_defs, 'input_defs', of_type=InputDefinition)
expected_positionals = check.opt_list_param(expected_positionals,
'expected_positionals',
of_type=str)
if exclude_nothing:
names = set(inp.name for inp in input_defs
if not inp.runtime_type.is_nothing)
nothing_names = set(inp.name for inp in input_defs
if inp.runtime_type.is_nothing)
else:
names = set(inp.name for inp in input_defs)
nothing_names = set()
# Currently being super strict about naming. Might be a good idea to relax. Starting strict.
fn_positionals, input_args = split_function_parameters(
compute_fn, expected_positionals)
# Validate Positional Parameters
missing_positional = validate_decorated_fn_positionals(
fn_positionals, expected_positionals)
if missing_positional:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function does not have required positional "
"parameter '{missing_param}'. Solid functions should only have keyword arguments "
"that match input names and a first positional parameter named 'context'."
.format(decorator_name=decorator_name,
solid_name=fn_name,
missing_param=missing_positional))
# Validate non positional parameters
invalid_function_info = validate_decorated_fn_input_args(names, input_args)
if invalid_function_info:
if invalid_function_info.error_type == InvalidDecoratedFunctionInfo.TYPES[
'vararg']:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function has positional vararg parameter "
"'{param}'. Solid functions should only have keyword arguments that match "
"input names and a first positional parameter named 'context'."
.format(
decorator_name=decorator_name,
solid_name=fn_name,
param=invalid_function_info.param,
))
elif invalid_function_info.error_type == InvalidDecoratedFunctionInfo.TYPES[
'missing_name']:
if invalid_function_info.param in nothing_names:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function has parameter '{param}' that is "
"one of the solid input_defs of type 'Nothing' which should not be included since "
"no data will be passed for it. ".format(
decorator_name=decorator_name,
solid_name=fn_name,
param=invalid_function_info.param,
))
else:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function has parameter '{param}' that is not "
"one of the solid input_defs. Solid functions should only have keyword arguments "
"that match input names and a first positional parameter named 'context'."
.format(
decorator_name=decorator_name,
solid_name=fn_name,
param=invalid_function_info.param,
))
elif invalid_function_info.error_type == InvalidDecoratedFunctionInfo.TYPES[
'extra']:
undeclared_inputs_printed = ", '".join(
invalid_function_info.missing_names)
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function does not have parameter(s) "
"'{undeclared_inputs_printed}', which are in solid's input_defs. Solid functions "
"should only have keyword arguments that match input names and a first positional "
"parameter named 'context'.".format(
decorator_name=decorator_name,
solid_name=fn_name,
undeclared_inputs_printed=undeclared_inputs_printed,
))
return positional_arg_name_list(input_args)
def monthly_schedule(
pipeline_name,
start_date,
name=None,
execution_day_of_month=1,
execution_time=datetime.time(0, 0),
tags_fn_for_date=None,
solid_subset=None,
mode="default",
should_execute=None,
environment_vars=None,
):
check.opt_str_param(name, 'name')
check.inst_param(start_date, 'start_date', datetime.datetime)
check.opt_callable_param(tags_fn_for_date, 'tags_fn_for_date')
check.opt_nullable_list_param(solid_subset, 'solid_subset', of_type=str)
mode = check.opt_str_param(mode, 'mode', DEFAULT_MODE_NAME)
check.opt_callable_param(should_execute, 'should_execute')
check.opt_dict_param(environment_vars,
'environment_vars',
key_type=str,
value_type=str)
check.str_param(pipeline_name, 'pipeline_name')
check.inst_param(start_date, 'start_date', datetime.datetime)
check.int_param(execution_day_of_month, 'execution_day')
check.inst_param(execution_time, 'execution_time', datetime.time)
if execution_day_of_month <= 0 or execution_day_of_month > 31:
raise DagsterInvalidDefinitionError(
"`execution_day_of_month={}` is not valid for monthly schedule. Execution day must be between 1 and 31"
.format(execution_day_of_month))
cron_schedule = '{minute} {hour} {day} * *'.format(
minute=execution_time.minute,
hour=execution_time.hour,
day=execution_day_of_month)
partition_fn = date_partition_range(start_date,
delta=relativedelta(months=1),
fmt="%Y-%m")
def inner(fn):
check.callable_param(fn, 'fn')
schedule_name = name or fn.__name__
tags_fn_for_partition_value = lambda partition: {}
if tags_fn_for_date:
tags_fn_for_partition_value = lambda partition: tags_fn_for_date(
partition.value)
partition_set = PartitionSetDefinition(
name='{}_monthly'.format(pipeline_name),
pipeline_name=pipeline_name,
partition_fn=partition_fn,
environment_dict_fn_for_partition=lambda partition: fn(partition.
value),
tags_fn_for_partition=tags_fn_for_partition_value,
mode=mode,
)
return partition_set.create_schedule_definition(
schedule_name,
cron_schedule,
should_execute=should_execute,
environment_vars=environment_vars,
)
return inner
def __new__(cls, output_name, manager_key):
return super(HandledOutputData, cls).__new__(
cls,
output_name=check.str_param(output_name, "output_name"),
manager_key=check.str_param(manager_key, "manager_key"),
)
def hourly_schedule(
pipeline_name,
start_date,
name=None,
execution_time=datetime.time(0, 0),
tags_fn_for_date=None,
solid_subset=None,
mode="default",
should_execute=None,
environment_vars=None,
):
check.opt_str_param(name, 'name')
check.inst_param(start_date, 'start_date', datetime.datetime)
check.opt_callable_param(tags_fn_for_date, 'tags_fn_for_date')
check.opt_nullable_list_param(solid_subset, 'solid_subset', of_type=str)
mode = check.opt_str_param(mode, 'mode', DEFAULT_MODE_NAME)
check.opt_callable_param(should_execute, 'should_execute')
check.opt_dict_param(environment_vars,
'environment_vars',
key_type=str,
value_type=str)
check.str_param(pipeline_name, 'pipeline_name')
check.inst_param(start_date, 'start_date', datetime.datetime)
check.inst_param(execution_time, 'execution_time', datetime.time)
if execution_time.hour != 0:
warnings.warn(
"Hourly schedule {schedule_name} created with:\n"
"\tschedule_time=datetime.time(hour={hour}, minute={minute}, ...)."
"Since this is a hourly schedule, the hour parameter will be ignored and the schedule "
"will run on the {minute} mark for the previous hour interval. Replace "
"datetime.time(hour={hour}, minute={minute}, ...) with datetime.time(minute={minute}, ...)"
"to fix this warning.")
cron_schedule = '{minute} * * * *'.format(minute=execution_time.minute)
partition_fn = date_partition_range(start_date,
delta=datetime.timedelta(hours=1),
fmt="%Y-%m-%d-%H:%M")
def inner(fn):
check.callable_param(fn, 'fn')
schedule_name = name or fn.__name__
tags_fn_for_partition_value = lambda partition: {}
if tags_fn_for_date:
tags_fn_for_partition_value = lambda partition: tags_fn_for_date(
partition.value)
partition_set = PartitionSetDefinition(
name='{}_hourly'.format(pipeline_name),
pipeline_name=pipeline_name,
partition_fn=partition_fn,
environment_dict_fn_for_partition=lambda partition: fn(partition.
value),
tags_fn_for_partition=tags_fn_for_partition_value,
mode=mode,
)
return partition_set.create_schedule_definition(
schedule_name,
cron_schedule,
should_execute=should_execute,
environment_vars=environment_vars,
)
return inner
def docker_service_up(docker_compose_file, service_name, conn_args=None):
check.invariant(
TestPostgresInstance.dagster_postgres_installed(),
"dagster_postgres must be installed to test with postgres",
)
check.str_param(service_name, "service_name")
check.str_param(docker_compose_file, "docker_compose_file")
check.invariant(os.path.isfile(docker_compose_file),
"docker_compose_file must specify a valid file")
conn_args = check.opt_dict_param(conn_args,
"conn_args") if conn_args else {}
from dagster_postgres.utils import wait_for_connection # pylint: disable=import-error
if BUILDKITE:
yield TestPostgresInstance.conn_string(
**conn_args) # buildkite docker is handled in pipeline setup
return
try:
subprocess.check_output([
"docker-compose", "-f", docker_compose_file, "stop",
service_name
])
subprocess.check_output([
"docker-compose", "-f", docker_compose_file, "rm", "-f",
service_name
])
except subprocess.CalledProcessError:
pass
try:
subprocess.check_output(
[
"docker-compose", "-f", docker_compose_file, "up", "-d",
service_name
],
stderr=subprocess.STDOUT, # capture STDERR for error handling
)
except subprocess.CalledProcessError as ex:
err_text = ex.output.decode()
raise PostgresDockerError(
"Failed to launch docker container(s) via docker-compose: {}".
format(err_text),
ex,
)
conn_str = TestPostgresInstance.conn_string(**conn_args)
wait_for_connection(conn_str, retry_limit=10, retry_wait=3)
yield conn_str
try:
subprocess.check_output([
"docker-compose", "-f", docker_compose_file, "stop",
service_name
])
subprocess.check_output([
"docker-compose", "-f", docker_compose_file, "rm", "-f",
service_name
])
except subprocess.CalledProcessError:
pass
def __new__(cls, config_type_snap, value_rep):
check.inst_param(config_type_snap, "config_type", ConfigTypeSnap)
return super(RuntimeMismatchErrorData, cls).__new__(
cls, config_type_snap, check.str_param(value_rep, "value_rep"),
)
def __new__(cls, field_name, field_snap):
return super(MissingFieldErrorData, cls).__new__(
cls,
check.str_param(field_name, "field_name"),
check.inst_param(field_snap, "field_snap", ConfigFieldSnap),
)
def get_invocation(self, solid_name):
check.str_param(solid_name, "solid_name")
return self._invocations_dict[solid_name]
def __new__(cls, step_key, output_name='result'):
return super(StepOutputHandle, cls).__new__(
cls,
step_key=check.str_param(step_key, 'step_key'),
output_name=check.str_param(output_name, 'output_name'),
)
def get_downstream_inputs(self, solid_name, output_name):
check.str_param(solid_name, "solid_name")
check.str_param(output_name, "output_name")
return self._output_to_upstream_index[solid_name][output_name]
def __init__(self, *args, **kwargs):
self.invalid_run_id = check.str_param(kwargs.pop("invalid_run_id"), "invalid_run_id")
super(DagsterRunNotFoundError, self).__init__(*args, **kwargs)
def validate_solid_fn(
decorator_name: str,
fn_name: str,
compute_fn: Callable[..., Any],
input_defs: List[InputDefinition],
expected_positionals: Optional[List[str]] = None,
exclude_nothing: Optional[bool] = True,
) -> List[str]:
check.str_param(decorator_name, "decorator_name")
check.str_param(fn_name, "fn_name")
check.callable_param(compute_fn, "compute_fn")
check.list_param(input_defs, "input_defs", of_type=InputDefinition)
expected_positionals = check.opt_list_param(expected_positionals,
"expected_positionals",
of_type=str)
if exclude_nothing:
names = set(inp.name for inp in input_defs
if not inp.dagster_type.kind == DagsterTypeKind.NOTHING)
nothing_names = set(
inp.name for inp in input_defs
if inp.dagster_type.kind == DagsterTypeKind.NOTHING)
else:
names = set(inp.name for inp in input_defs)
nothing_names = set()
# Currently being super strict about naming. Might be a good idea to relax. Starting strict.
fn_positionals, input_args = split_function_parameters(
compute_fn, expected_positionals)
# Validate Positional Parameters
missing_positional = validate_decorated_fn_positionals(
fn_positionals, expected_positionals)
if missing_positional:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function does not have required positional "
"parameter '{missing_param}'. Solid functions should only have keyword arguments "
"that match input names and a first positional parameter named 'context'."
.format(decorator_name=decorator_name,
solid_name=fn_name,
missing_param=missing_positional))
# Validate non positional parameters
invalid_function_info = validate_decorated_fn_input_args(names, input_args)
if invalid_function_info:
if invalid_function_info.error_type == InvalidDecoratedFunctionInfo.TYPES[
"vararg"]:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function has positional vararg parameter "
"'{param}'. Solid functions should only have keyword arguments that match "
"input names and a first positional parameter named 'context'."
.format(
decorator_name=decorator_name,
solid_name=fn_name,
param=invalid_function_info.param,
))
elif invalid_function_info.error_type == InvalidDecoratedFunctionInfo.TYPES[
"missing_name"]:
if invalid_function_info.param in nothing_names:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function has parameter '{param}' that is "
"one of the solid input_defs of type 'Nothing' which should not be included since "
"no data will be passed for it. ".format(
decorator_name=decorator_name,
solid_name=fn_name,
param=invalid_function_info.param,
))
else:
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function has parameter '{param}' that is not "
"one of the solid input_defs. Solid functions should only have keyword arguments "
"that match input names and a first positional parameter named 'context'."
.format(
decorator_name=decorator_name,
solid_name=fn_name,
param=invalid_function_info.param,
))
elif invalid_function_info.error_type == InvalidDecoratedFunctionInfo.TYPES[
"extra"]:
undeclared_inputs_printed = ", '".join(
invalid_function_info.missing_names)
raise DagsterInvalidDefinitionError(
"{decorator_name} '{solid_name}' decorated function does not have parameter(s) "
"'{undeclared_inputs_printed}', which are in solid's input_defs. Solid functions "
"should only have keyword arguments that match input names and a first positional "
"parameter named 'context'.".format(
decorator_name=decorator_name,
solid_name=fn_name,
undeclared_inputs_printed=undeclared_inputs_printed,
))
return positional_arg_name_list(input_args)
def __init__(self, *args, **kwargs):
self.step_key = check.str_param(kwargs.pop("step_key"), "step_key")
self.output_name = check.str_param(kwargs.pop("output_name"), "output_name")
super(DagsterStepOutputNotFoundError, self).__init__(*args, **kwargs)
def has_step(self, key):
check.str_param(key, "key")
return key in self.step_dict
def __init__(self, *args, **kwargs):
self.step_key = check.str_param(kwargs.pop("step_key"), "step_key")
self.input_name = check.str_param(kwargs.pop("input_name"), "input_name")
super(DagsterExecutionLoadInputError, self).__init__(*args, **kwargs)
def __init__(self, message):
super(DauphinInvalidPipelineRunsFilterError, self).__init__()
self.message = check.str_param(message, 'message')
def __init__(self, *args, **kwargs):
self.step_key = check.str_param(kwargs.pop("step_key"), "step_key")
self.output_name = check.str_param(kwargs.pop("output_name"), "output_name")
super(DagsterExecutionHandleOutputError, self).__init__(*args, **kwargs)
def __init__(self, preset, selector):
self.preset = check.str_param(preset, 'preset')
self.message = 'Preset {preset} not found in pipeline {pipeline}.'.format(
preset=preset, pipeline=selector.name
)
def __init__(self, *args, **kwargs):
self.step_key = check.str_param(kwargs.pop("step_key"), "step_key")
self.solid_name = check.str_param(kwargs.pop("solid_name"), "solid_name")
self.solid_def_name = check.str_param(kwargs.pop("solid_def_name"), "solid_def_name")
super(DagsterExecutionStepExecutionError, self).__init__(*args, **kwargs)
def __init__(self, field_name):
self._field_name = check.str_param(field_name, 'field_name')
super(DauphinEvaluationStackPathEntry, self).__init__()
def __init__(self, run_id):
self.run_id = check.str_param(run_id, "run_id")
super(DagsterEventLogInvalidForRun, self).__init__(
"Event logs invalid for run id {}".format(run_id)
)
def __init__(self, schedule_name):
super(DauphinScheduleNotFoundError, self).__init__()
self.schedule_name = check.str_param(schedule_name, 'schedule_name')
self.message = (
'Schedule {schedule_name} is not present in the currently loaded repository.'
).format(schedule_name=schedule_name)
def __new__(cls, location_name, repository_name):
return super(RepositorySelector, cls).__new__(
cls,
location_name=check.str_param(location_name, "location_name"),
repository_name=check.str_param(repository_name, "repository_name"),
)
