Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix _SP/POS=SPACE in strings serialization tests

This commit is contained in:
Adriane Boyd 2020-05-21 19:49:08 +02:00
parent 631e20d0c6
commit 17ee9ab53a
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
spacy/tests/serialize/test_serialize_vocab_strings.py
View File

@ -8,6 +8,7 @@ from ..util import make_tempdir
test_strings = [([], []), (["rats", "are", "cute"], ["i", "like", "rats"])] test_strings = [([], []), (["rats", "are", "cute"], ["i", "like", "rats"])]
test_strings_attrs = [(["rats", "are", "cute"], "Hello")] test_strings_attrs = [(["rats", "are", "cute"], "Hello")]
default_strings = ("_SP", "POS=SPACE")
@pytest.mark.xfail @pytest.mark.xfail
@ -34,8 +35,8 @@ def test_serialize_vocab_roundtrip_bytes(strings1, strings2):
assert vocab1.to_bytes() == vocab1_b assert vocab1.to_bytes() == vocab1_b
new_vocab1 = Vocab().from_bytes(vocab1_b) new_vocab1 = Vocab().from_bytes(vocab1_b)
assert new_vocab1.to_bytes() == vocab1_b assert new_vocab1.to_bytes() == vocab1_b
assert len(new_vocab1.strings) == len(strings1) + 1 # adds _SP assert len(new_vocab1.strings) == len(strings1) + 2 # adds _SP and POS=SPACE
assert sorted([s for s in new_vocab1.strings]) == sorted(strings1 + ["_SP"]) assert sorted([s for s in new_vocab1.strings]) == sorted(strings1 + list(default_strings))
@pytest.mark.parametrize("strings1,strings2", test_strings) @pytest.mark.parametrize("strings1,strings2", test_strings)
@ -50,15 +51,15 @@ def test_serialize_vocab_roundtrip_disk(strings1, strings2):
vocab1_d = Vocab().from_disk(file_path1) vocab1_d = Vocab().from_disk(file_path1)
vocab2_d = Vocab().from_disk(file_path2) vocab2_d = Vocab().from_disk(file_path2)
# check strings rather than lexemes, which are only reloaded on demand # check strings rather than lexemes, which are only reloaded on demand
assert strings1 == [s for s in vocab1_d.strings if s != "_SP"] assert strings1 == [s for s in vocab1_d.strings if s not in default_strings]
assert strings2 == [s for s in vocab2_d.strings if s != "_SP"] assert strings2 == [s for s in vocab2_d.strings if s not in default_strings]
if strings1 == strings2: if strings1 == strings2:
assert [s for s in vocab1_d.strings if s != "_SP"] == [ assert [s for s in vocab1_d.strings if s not in default_strings] == [
s for s in vocab2_d.strings if s != "_SP" s for s in vocab2_d.strings if s not in default_strings
] ]
else: else:
assert [s for s in vocab1_d.strings if s != "_SP"] != [ assert [s for s in vocab1_d.strings if s not in default_strings] != [
s for s in vocab2_d.strings if s != "_SP" s for s in vocab2_d.strings if s not in default_strings
] ]
@ -78,7 +79,7 @@ def test_deserialize_vocab_seen_entries(strings, lex_attr):
# Reported in #2153 # Reported in #2153
vocab = Vocab(strings=strings) vocab = Vocab(strings=strings)
vocab.from_bytes(vocab.to_bytes()) vocab.from_bytes(vocab.to_bytes())
assert len(vocab.strings) == len(strings) + 1 # adds _SP assert len(vocab.strings) == len(strings) + 2 # adds _SP and POS=SPACE
@pytest.mark.parametrize("strings,lex_attr", test_strings_attrs) @pytest.mark.parametrize("strings,lex_attr", test_strings_attrs)