explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 01:16:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Restore Doc attr getter values in Doc.to_json (#11700)

Browse Source
This commit is contained in:
Adriane Boyd 2022-11-03 11:49:08 +01:00 committed by GitHub
parent db56600536
commit 40e1000db0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 27 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/tests/doc/test_json_doc_conversion.py
View File

@ -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)

27
spacy/tokens/doc.pyx
View File

@ -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"]: