mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
46 lines
661 B
Python
46 lines
661 B
Python
|
# encoding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
|
||
|
|
STOP_WORDS = set("""
|
||
|
|
a ach ag agus an aon ar arna as
|
||
|
|
|
||
|
|
ba beirt bhúr
|
||
|
|
|
||
|
|
caoga ceathair ceathrar chomh chuig chun cois céad cúig cúigear
|
||
|
|
|
||
|
|
daichead dar de deich deichniúr den dhá do don dtí dá dár dó
|
||
|
|
|
||
|
|
faoi faoin faoina faoinár fara fiche
|
||
|
|
|
||
|
|
gach gan go gur
|
||
|
|
|
||
|
|
haon hocht
|
||
|
|
|
||
|
|
i iad idir in ina ins inár is
|
||
|
|
|
||
|
|
le leis lena lenár
|
||
|
|
|
||
|
|
mar mo muid mé
|
||
|
|
|
||
|
|
na nach naoi naonúr ná ní níor nó nócha
|
||
|
|
|
||
|
|
ocht ochtar ochtó os
|
||
|
|
|
||
|
|
roimh
|
||
|
|
|
||
|
|
sa seacht seachtar seachtó seasca seisear siad sibh sinn sna sé sí
|
||
|
|
|
||
|
|
tar thar thú triúr trí trína trínár tríocha tú
|
||
|
|
|
||
|
|
um
|
||
|
|
|
||
|
|
ár
|
||
|
|
|
||
|
|
é éis
|
||
|
|
|
||
|
|
í
|
||
|
|
|
||
|
|
ó ón óna ónár
|
||
|
|
""".split())
|