mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 02:46:35 +03:00
e2b70df012
* Use isort with Black profile * isort all the things * Fix import cycles as a result of import sorting * Add DOCBIN_ALL_ATTRS type definition * Add isort to requirements * Remove isort from build dependencies check * Typo
25 lines
880 B
Python
25 lines
880 B
Python
import srsly
|
|
|
|
from ...lang.xx import MultiLanguage
|
|
from ...util import load_model
|
|
from ..example import (
|
|
_fix_legacy_dict_data,
|
|
_parse_example_dict_data,
|
|
annotations_to_doc,
|
|
)
|
|
from ..gold_io import json_iterate, json_to_annotations
|
|
|
|
|
|
def json_to_docs(input_data, model=None, **kwargs):
|
|
nlp = load_model(model) if model is not None else MultiLanguage()
|
|
if not isinstance(input_data, bytes):
|
|
if not isinstance(input_data, str):
|
|
input_data = srsly.json_dumps(input_data)
|
|
input_data = input_data.encode("utf8")
|
|
for json_doc in json_iterate(input_data):
|
|
for json_para in json_to_annotations(json_doc):
|
|
example_dict = _fix_legacy_dict_data(json_para)
|
|
tok_dict, doc_dict = _parse_example_dict_data(example_dict)
|
|
doc = annotations_to_doc(nlp.vocab, tok_dict, doc_dict)
|
|
yield doc
|