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

Add test for tokenizer regular expressions

Browse Source
This commit is contained in:
Ines Montani 2016-11-24 13:51:59 +01:00
parent e0712d1b32
commit 07f0efb102
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/tests/tokenizer/test_tokenizer.py
View File

@ -7,6 +7,10 @@ import pickle
import cloudpickle import cloudpickle
import tempfile import tempfile
from ... import util
from ...en.language_data import TOKENIZER_PREFIXES as EN_TOKENIZER_PREFIXES
en_search_prefixes = util.compile_prefix_regex(EN_TOKENIZER_PREFIXES).search
# @pytest.mark.xfail # @pytest.mark.xfail
# def test_pickle(en_tokenizer): # def test_pickle(en_tokenizer):
@ -16,6 +20,10 @@ import tempfile
# loaded = pickle.load(file_) # loaded = pickle.load(file_)
# assert loaded is not None # assert loaded is not None
def test_pre_punct_regex():
string = "(can't"
match = en_search_prefixes(string)
assert match.group() == "("
def test_no_word(en_tokenizer): def test_no_word(en_tokenizer):
tokens = en_tokenizer(u'') tokens = en_tokenizer(u'')
@ -57,10 +65,9 @@ def test_contraction(en_tokenizer):
assert len(tokens) == 5 assert len(tokens) == 5
assert tokens[4].orth == en_tokenizer.vocab['!'].orth assert tokens[4].orth == en_tokenizer.vocab['!'].orth
def test_contraction_punct(en_tokenizer): def test_contraction_punct(en_tokenizer):
tokens = en_tokenizer("(can't") tokens = [w.text for w in en_tokenizer("(can't")]
assert len(tokens) == 3 assert tokens == ['(', 'ca', "n't"]
tokens = en_tokenizer("`ain't") tokens = en_tokenizer("`ain't")
assert len(tokens) == 3 assert len(tokens) == 3
tokens = en_tokenizer('''"isn't''') tokens = en_tokenizer('''"isn't''')