def serialize_doc(doc: Doc) -> Dict[str, any]:
dep = []
return {
'text': doc.text,
'tokens': list(map(serialize_token, doc.__iter__())),
'noun_chunks': list(map(serialize_span, doc.noun_chunks)),
'data': doc.to_json(),
# 'dep': dep,
}
def encode(cls, obj: Doc) -> str:
"""Encode the Doc object.
Args:
obj:
Returns:
"""
# JSON dump the Doc
doc_json = obj.to_json()
if obj._.has("huggingface_neuralcoref"):
# Create a helper function that turns a Span into a dictionary
span_to_dict = lambda span: {
"start": span.start,
"end": span.end,
"text": span.text,
}
# Create a helper function that converts a Cluster (output of
# neuralcoref) into a dictionary
cluster_to_dict = lambda cluster: {
"i": cluster.i,
"main": span_to_dict(cluster.main),
"mentions": [span_to_dict(span) for span in cluster.mentions],
}
# Apply the helper functions to construct a dictionary for the
# neuralcoref information
neuralcoref_dict = {
"neuralcoref":
[cluster_to_dict(cluster) for cluster in obj._.coref_clusters]
}
# Combine the neuralcoref dictionary with the doc_json
doc_json = tz.merge(doc_json, neuralcoref_dict)
# Convert the Spacy Doc to json before caching
return json.dumps(doc_json)
