def postprocess(self, response: Response) -> Response:
from tokenizer_tools.tagset.exceptions import TagSetDecodeError
from tokenizer_tools.tagset.offset.sequence import Sequence
tags_list = response.data
raw_text_list = self.request_query
infer_result = []
for raw_text, tags in zip(raw_text_list, tags_list):
# decode Unicode
tags_seq = [
i.decode() if isinstance(i, bytes) else i for i in tags
]
# BILUO to offset
is_failed = False
exec_msg = None
try:
seq = self.decoder.to_offset(tags_seq, raw_text)
except TagSetDecodeError as e:
exec_msg = str(e)
# invalid tag sequence will raise exception
# so return a empty result to avoid batch fail
seq = Sequence(raw_text)
is_failed = True
infer_result.append(PredictResult(seq, is_failed, exec_msg))
response.update_data(infer_result)
return response
def postprocess(self, response: Response) -> Response:
tag_lookup_table = self.lookup_table_registry["tag"]
data_str_list = []
for data_int in response.data:
data_str = [tag_lookup_table.inverse_lookup(i) for i in data_int]
data_str_list.append(data_str)
response.update_data(data_str_list)
return response