diff --git a/spacy/tests/doc/test_json_doc_conversion.py b/spacy/tests/doc/test_json_doc_conversion.py index 19698cfb2..11a1817e6 100644 --- a/spacy/tests/doc/test_json_doc_conversion.py +++ b/spacy/tests/doc/test_json_doc_conversion.py @@ -370,3 +370,12 @@ def test_json_to_doc_validation_error(doc): doc_json.pop("tokens") with pytest.raises(ValueError): Doc(doc.vocab).from_json(doc_json, validate=True) + + +def test_to_json_underscore_doc_getters(doc): + def get_text_length(doc): + return len(doc.text) + + Doc.set_extension("text_length", getter=get_text_length) + doc_json = doc.to_json(underscore=["text_length"]) + assert doc_json["_"]["text_length"] == get_text_length(doc) diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index 295f91c28..f2621292c 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -1668,6 +1668,20 @@ cdef class Doc: if underscore: user_keys = set() + # Handle doc attributes with .get to include values from getters + # and not only values stored in user_data, for backwards + # compatibility + for attr in underscore: + if self.has_extension(attr): + if "_" not in data: + data["_"] = {} + value = self._.get(attr) + if not srsly.is_json_serializable(value): + raise ValueError(Errors.E107.format(attr=attr, value=repr(value))) + data["_"][attr] = value + user_keys.add(attr) + # Token and span attributes only include values stored in user_data + # and not values generated by getters if self.user_data: for data_key, value in self.user_data.copy().items(): if type(data_key) == tuple and len(data_key) >= 4 and data_key[0] == "._.": @@ -1678,20 +1692,15 @@ cdef class Doc: user_keys.add(attr) if not srsly.is_json_serializable(value): raise ValueError(Errors.E107.format(attr=attr, value=repr(value))) - # Check if doc attribute - if start is None: - if "_" not in data: - data["_"] = {} - data["_"][attr] = value - # Check if token attribute - elif end is None: + # Token attribute + if start is not None and end is None: if "underscore_token" not in data: data["underscore_token"] = {} if attr not in data["underscore_token"]: data["underscore_token"][attr] = [] data["underscore_token"][attr].append({"start": start, "value": value}) - # Else span attribute - else: + # Span attribute + elif start is not None and end is not None: if "underscore_span" not in data: data["underscore_span"] = {} if attr not in data["underscore_span"]: