explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-27 09:44:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add test for regex locale in gold standard

Browse Source
This commit is contained in:
Matthew Honnibal 2016-04-28 14:31:41 +02:00
parent 7c37f45e9f
commit 11bffaa1ab
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/tests/gold/test_alignment.py Normal file
View File

@ -0,0 +1,15 @@
from spacy.gold import _min_edit_path
def test_min_edit_path():
'''Test problem that arose from Chinese parsing, where alignment didn't match
at the start, depending on which direction followed. The solution was that
a regular expression did not have re.UNICODE flag, causing it to over match.
'''
cand_words = [u'\u53cc\u65b9', u'D', u'-', u'RAM']
gold_words = [u'\u53cc\u65b9', u'D-RAM']
cost, alignment = _min_edit_path(cand_words, gold_words)
assert alignment[0] == 'M'
cost, alignment = _min_edit_path(gold_words, cand_words)
assert alignment[0] == 'M'