explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-28 04:43:42 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix unicode regex problem for non-English locales in gold standard

Browse Source
This commit is contained in:
Matthew Honnibal 2016-04-28 14:31:14 +02:00
parent 588026fe93
commit 7c37f45e9f
1 changed files with 2 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/gold.pyx
View File

@ -1,3 +1,4 @@
from __future__ import unicode_literals
import numpy
import io
import json
@ -42,7 +43,6 @@ def tags_to_entities(tags):
return entities
def align(cand_words, gold_words):
cost, edit_path = _min_edit_path(cand_words, gold_words)
alignment = []
@ -63,7 +63,7 @@ def align(cand_words, gold_words):
return alignment
punct_re = re.compile(r'\W')
punct_re = re.compile(r'\W', re.UNICODE)
def _min_edit_path(cand_words, gold_words):
cdef:
Pool mem
@ -264,13 +264,3 @@ cdef class GoldParse:
def is_punct_label(label):
return label == 'P' or label.lower() == 'punct'