explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-13 02:36:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

Slightly modify test for #3468

Browse Source 
Check for Token.is_sent_start first (which is serialized/deserialized correctly)
This commit is contained in:
Ines Montani 2019-03-23 11:22:44 +01:00
parent 02d9378d8c
commit fbec72b4c3
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/tests/regression/test_issue3468.py
View File

@ -13,11 +13,11 @@ def test_issue3468():
nlp = English() nlp = English()
nlp.add_pipe(nlp.create_pipe("sentencizer")) nlp.add_pipe(nlp.create_pipe("sentencizer"))
doc = nlp("Hello world") doc = nlp("Hello world")
assert doc.is_sentenced
assert doc[0].is_sent_start assert doc[0].is_sent_start
assert doc.is_sentenced
assert len(list(doc.sents)) == 1 assert len(list(doc.sents)) == 1
doc_bytes = doc.to_bytes() doc_bytes = doc.to_bytes()
new_doc = Doc(nlp.vocab).from_bytes(doc_bytes) new_doc = Doc(nlp.vocab).from_bytes(doc_bytes)
assert new_doc.is_sentenced
assert doc[0].is_sent_start assert doc[0].is_sent_start
assert new_doc.is_sentenced
assert len(list(new_doc.sents)) == 1 assert len(list(new_doc.sents)) == 1