def process_doc(self, doc: Document) -> Document:
new_entities = []
for ent in doc.entities:
if ent.type in self.__filter:
continue
new_entities.append(ent.with_type(self.__replacements.get(ent.type, ent.type)))
return doc.without_relations().without_entities().with_entities(new_entities)
def process_doc(self, doc: Document) -> Document:
new_entities = []
nes = []
for ent in doc.entities:
if ent.type in self.__filter:
continue
new_ne_type = self.__ne_replacements.get(ent.type, ent.type)
new_ent_type = self.__ents_replacements.get(ent.type, ent.type)
new_entities.append(ent.with_type(new_ent_type))
nes.append(ent.with_type(new_ne_type))
return doc.without_relations().without_entities().with_entities(new_entities). \
with_additional_extras({"ne": SortedSpansSet(nes)})
