explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-29 09:23:12 +03:00
Code Issues Packages Projects Releases Wiki Activity

Test user_data deserialization, re #1085

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-17 19:28:54 +02:00
parent e35a83d142
commit 374819edf8
1 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
spacy/tests/doc/test_pickle_doc.py
View File

@ -24,3 +24,20 @@ def test_list_of_docs_pickles_efficiently():
assert many_unpickled[0].text == '0' assert many_unpickled[0].text == '0'
assert many_unpickled[-1].text == '99' assert many_unpickled[-1].text == '99'
assert len(many_unpickled) == 100 assert len(many_unpickled) == 100
def test_user_data_from_disk():
nlp = Language()
doc = nlp(u'Hello')
doc.user_data[(0, 1)] = False
b = doc.to_bytes()
doc2 = doc.__class__(doc.vocab).from_bytes(b)
assert doc2.user_data[(0, 1)] == False
def test_user_data_unpickles():
nlp = Language()
doc = nlp(u'Hello')
doc.user_data[(0, 1)] = False
b = pickle.dumps(doc)
doc2 = pickle.loads(b)
assert doc2.user_data[(0, 1)] == False