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

Reversed accidental changes.

This commit is contained in:
Gyorgy Orosz 2017-01-14 15:56:41 +01:00
parent 1be5da1ac6
commit be7a7aeb1a
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/hu/tokenizer_exceptions.py
View File

@ -4,7 +4,7 @@ from __future__ import unicode_literals
import re
from spacy.language_data.punctuation import ALPHA_LOWER, CURRENCY
from ..language_data.tokenizer_exceptions import URL_PATTERN
from ..language_data.tokenizer_exceptions import _URL_PATTERN
ABBREVIATIONS = """
AkH.
@ -548,4 +548,4 @@ NUMS = "(({ne})|({t})|({on})|({c}))({s})?".format(
c=CURRENCY, s=_SUFFIES
)
TOKEN_MATCH = re.compile("^({u})|({n})$".format(u=URL_PATTERN, n=NUMS)).match
TOKEN_MATCH = re.compile("^({u})|({n})$".format(u=_URL_PATTERN, n=NUMS)).match

6
spacy/language_data/tokenizer_exceptions.py
View File

@ -2,10 +2,10 @@ from __future__ import unicode_literals
import re
URL_PATTERN = r'''
((([A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)((?:\/[\+~%\/.\w\-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)
_URL_PATTERN = r'''
^((([A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)((?:\/[\+~%\/.\w\-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)$
'''.strip()
TOKEN_MATCH = re.compile("^{}$".format(URL_PATTERN)).match
TOKEN_MATCH = re.compile(_URL_PATTERN).match
__all__ = ['TOKEN_MATCH']