def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
if configs.column_format is None:
raise ProcessorConfigError(
"Configuration column_format not provided.")
column_format = configs.column_format
# Validate column format.
seen_fields: Set[str] = set()
# pylint: disable=attribute-defined-outside-init
self._column_format: List[Optional[str]] = []
self._star_pos = None
for idx, field in enumerate(column_format):
if field is None:
self._column_format.append(None)
continue
if field.startswith("*"):
if self._star_pos is not None:
raise ValueError("Only one field can begin with '*'")
field = field[1:]
if field not in self._STAR_FIELDS:
raise ValueError(f"Field '{field}' cannot begin with '*'")
self._star_pos = idx
if field not in self.ParsedFields._fields:
raise ValueError(f"Unsupported field type: '{field}'")
if field in seen_fields:
raise ValueError(f"Duplicate field type: '{field}'")
seen_fields.add(field)
self._column_format.append(field)
# Sanity check: certain fields must be present in format.
for field in self._REQUIRED_FIELDS:
if field not in seen_fields:
raise ValueError(f"'{field}' field is required")
def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
if not self.configs.entry_type:
raise ProcessorConfigError("Please specify an entity mention type!")
self.entry_type = get_class(self.configs.entry_type)
if not issubclass(self.entry_type, Annotation):
raise AttributeError(
f"The entry type to delete [{self.entry_type}] "
f"is not a sub-class of "
f"'forte.data.ontology.top.Annotation' class."
)
def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
if configs.qa_file_extension is None:
raise ProcessorConfigError(
"Configuration qa_file_extension not provided.")