explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add test for Issue #351: Indices off when leading whitespace

Browse Source
This commit is contained in:
Matthew Honnibal 2016-05-04 15:53:17 +02:00
parent 76021cb853
commit b4bfc6ae55
1 changed files with 32 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
spacy/tests/tokenizer/test_whitespace.py
View File

@ -33,3 +33,35 @@ def test_newline_double_space(en_tokenizer):
def test_newline_space_wrap(en_tokenizer):
tokens = en_tokenizer('hello \n possums')
assert len(tokens) == 3
def test_leading_space_offsets(en_tokenizer):
'''Issue #351
# this works
text1 = u"This is a cat."
a = english_spacy(text1)
tok0 = list(a.sents)[0][0]
print tok0, tok0.idx, text1[tok0.idx]
tok1 = list(a.sents)[0][1]
print tok1, tok1.idx, text1[tok1.idx]
print "=="
# this does not work
text2 = u" This is a cat."
b = english_spacy(text2)
tok0 = list(b.sents)[0][0]
print tok0, tok0.idx, text2[tok0.idx]
tok1 = list(b.sents)[0][1]
print tok1, tok1.idx, text2[tok1.idx]
'''
doc = en_tokenizer(u" This is a cat.")
assert doc[0].idx == 0
assert len(doc[0]) == 3
assert doc[1].idx == 3