mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-30 20:06:30 +03:00
2e31921d0a
* Add base classes for more languages * Add test for language class initialization Make sure language can be initialize – otherwise, it's difficult to catch serious errors in the test suite, because languages are lazy-loaded
62 lines
348 B
Python
62 lines
348 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
# Source: https://github.com/stopwords-iso/stopwords-af
|
|
|
|
STOP_WORDS = set(
|
|
"""
|
|
'n
|
|
aan
|
|
af
|
|
al
|
|
as
|
|
baie
|
|
by
|
|
daar
|
|
dag
|
|
dat
|
|
die
|
|
dit
|
|
een
|
|
ek
|
|
en
|
|
gaan
|
|
gesê
|
|
haar
|
|
het
|
|
hom
|
|
hulle
|
|
hy
|
|
in
|
|
is
|
|
jou
|
|
jy
|
|
kan
|
|
kom
|
|
ma
|
|
maar
|
|
met
|
|
my
|
|
na
|
|
nie
|
|
om
|
|
ons
|
|
op
|
|
saam
|
|
sal
|
|
se
|
|
sien
|
|
so
|
|
sy
|
|
te
|
|
toe
|
|
uit
|
|
van
|
|
vir
|
|
was
|
|
wat
|
|
ʼn
|
|
""".split()
|
|
)
|