3eb63a887b
stop words can be loaded from files/bytes, closes #19 stop words loaded for large list of languages, closes #20 defined language specific analyzers for as much as possible right now, closes #21 opened new issues for some of the remaining gaps
118 lines
781 B
Go
118 lines
781 B
Go
package stop_words_filter
|
|
|
|
// this content was obtained from:
|
|
// lucene-4.7.2/analysis/common/src/resources/org/apache/lucene/analysis/snowball/
|
|
// ` was changed to ' to allow for literal string
|
|
|
|
var IrishStopWords = []byte(`
|
|
a
|
|
ach
|
|
ag
|
|
agus
|
|
an
|
|
aon
|
|
ar
|
|
arna
|
|
as
|
|
b'
|
|
ba
|
|
beirt
|
|
bhúr
|
|
caoga
|
|
ceathair
|
|
ceathrar
|
|
chomh
|
|
chtó
|
|
chuig
|
|
chun
|
|
cois
|
|
céad
|
|
cúig
|
|
cúigear
|
|
d'
|
|
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
|
|
m'
|
|
mar
|
|
mo
|
|
mé
|
|
na
|
|
nach
|
|
naoi
|
|
naonúr
|
|
ná
|
|
ní
|
|
níor
|
|
nó
|
|
nócha
|
|
ocht
|
|
ochtar
|
|
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
|
|
`)
|