spaCy/spacy/tests/regression/test_issue4903.py

41 lines
1.1 KiB
Python
Raw Normal View History

2020-02-12 11:26:27 +00:00
from spacy.lang.en import English
2020-02-12 11:00:13 +00:00
from spacy.tokens import Span, Doc
class CustomPipe:
name = "my_pipe"
def __init__(self):
Span.set_extension("my_ext", getter=self._get_my_ext)
Doc.set_extension("my_ext", default=None)
def __call__(self, doc):
gathered_ext = []
for sent in doc.sents:
sent_ext = self._get_my_ext(sent)
sent._.set("my_ext", sent_ext)
gathered_ext.append(sent_ext)
doc._.set("my_ext", "\n".join(gathered_ext))
return doc
@staticmethod
def _get_my_ext(span):
return str(span.end)
def test_issue4903():
# ensures that this runs correctly and doesn't hang or crash on Windows / macOS
2020-02-12 11:26:27 +00:00
nlp = English()
2020-02-12 11:00:13 +00:00
custom_component = CustomPipe()
2020-02-12 11:26:27 +00:00
nlp.add_pipe(nlp.create_pipe("sentencizer"))
nlp.add_pipe(custom_component, after="sentencizer")
2020-02-12 11:00:13 +00:00
text = ["I like bananas.", "Do you like them?", "No, I prefer wasabi."]
2020-02-12 11:12:52 +00:00
docs = list(nlp.pipe(text, n_process=2))
assert docs[0].text == "I like bananas."
assert docs[1].text == "Do you like them?"
assert docs[2].text == "No, I prefer wasabi."