explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 09:57:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Move test_home to within tests/

Browse Source
This commit is contained in:
Matthew Honnibal 2015-09-28 19:34:34 +10:00
parent 5ca1646d8a
commit d8276b3792
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
website/tests/test_home.py → tests/website/test_home.py
View File

@ -1,5 +1,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import pytest import pytest
import spacy.en
@pytest.fixture(scope="session") @pytest.fixture(scope="session")
@ -36,7 +37,7 @@ def test_use_integer_ids_for_any_strings(nlp, token):
hello_id = nlp.vocab.strings['Hello'] hello_id = nlp.vocab.strings['Hello']
hello_str = nlp.vocab.strings[hello_id] hello_str = nlp.vocab.strings[hello_id]
assert token.orth == hello_id == 469755 assert token.orth == hello_id == 3404
assert token.orth_ == hello_str == 'Hello' assert token.orth_ == hello_str == 'Hello'
@ -71,7 +72,7 @@ def test_word_vectors(nlp):
doc = nlp("Apples and oranges are similar. Boots and hippos aren't.") doc = nlp("Apples and oranges are similar. Boots and hippos aren't.")
apples = doc[0] apples = doc[0]
oranges = doc[1] oranges = doc[2]
boots = doc[6] boots = doc[6]
hippos = doc[8] hippos = doc[8]
@ -157,10 +158,12 @@ def test_calculate_inline_mark_up_on_original_string():
@pytest.mark.models @pytest.mark.models
def test_efficient_binary_serialization(doc): def test_efficient_binary_serialization(doc):
byte_string = doc.as_bytes() from spacy.tokens.doc import Doc
byte_string = doc.to_bytes()
open('/tmp/moby_dick.bin', 'wb').write(byte_string) open('/tmp/moby_dick.bin', 'wb').write(byte_string)
nlp = spacy.en.English() nlp = spacy.en.English()
for byte_string in Doc.read(open('/tmp/moby_dick.bin', 'rb')): for byte_string in Doc.read_bytes(open('/tmp/moby_dick.bin', 'rb')):
doc = Doc(nlp.vocab) doc = Doc(nlp.vocab)
doc.from_bytes(byte_string) doc.from_bytes(byte_string)