mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
24 lines
907 B
Python
24 lines
907 B
Python
coding: utf8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
# Stop words
|
|
STOP_WORDS = set("""
|
|
ke gareng ga selekanyo tlhwatlhwa yo mongwe se
|
|
sengwe fa go le jalo gongwe ba na mo tikologong
|
|
jaaka kwa morago nna gonne ka sa pele nako teng
|
|
tlase fela ntle magareng tsona feta bobedi kgabaganya
|
|
moo gape kgatlhanong botlhe tsotlhe bokana e esi
|
|
setseng mororo dinako golo kgolo nnye wena gago
|
|
o ntse ntle tla goreng gangwe mang yotlhe gore
|
|
eo yona tseraganyo eng ne sentle re rona thata
|
|
godimo fitlha pedi masomamabedi lesomepedi mmogo
|
|
tharo tseo boraro tseno yone jaanong bobona bona
|
|
lesome tsaya tsamaiso nngwe masomethataro thataro
|
|
tsa mmatota tota sale thoko supa dira tshwanetse di mmalwa masisi
|
|
bonala e tshwanang bogolo tsenya tsweetswee karolo
|
|
sepe tlhalosa dirwa robedi robongwe lesomenngwe gaisa
|
|
tlhano lesometlhano botlalo lekgolo
|
|
""".split())
|
|
print(STOP_WORDS) |