# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/snowball/italian_stop.txt
ad
al
allo
ai
agli
all
agl
alla
alle
con
col
coi
da
dal
dallo
dai
dagli
dall
dagl
dalla
dalle
di
del
dello
dei
degli
dell
degl
della
delle
in
nel
nello
nei
negli
nell
negl
nella
nelle
su
sul

import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.TokenizerFactory;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.opensearch.core.common.Strings;

import com.ibm.icu.text.Transliterator;

/**

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java
a
an
and
are
as
at
be
but
by
for
if
in
into
is
it
no
not
of
on
or
such
that
the
their
then
there
these
they
this
to
was
will

  schedule:
    - cron: '45 9 * * 0'
  push:
    branches: [ "master" ]

# Declare default permissions as read only.
permissions: read-all

jobs:
  analysis:
    name: Scorecard analysis
    runs-on: ubuntu-latest
    permissions:
      # Needed to upload the results to code-scanning dashboard.
      security-events: write

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/ga/stopwords.txt
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

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/ckb/stopwords.txt
و
کە
ی
کرد
ئەوەی
سەر
دوو
هەروەها
لەو
دەکات
چەند
هەر
ئەو
ئەم
من
ئێمە
تۆ
ئێوە
ئەو
ئەوان
بە
پێ
بەبێ
بەدەم
بەلای
بەپێی
بەرلە
بەرەوی
بەرەوە
بەردەم
بێ
بێجگە
بۆ
دە
تێ
دەگەڵ
دوای
جگە
لە
لێ
لەبەر
لەبەینی

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/lt/stopwords.txt
ant
apie
ar
arba
aš
be
bei
bet
bus
būti
būtų
buvo
dėl
gali
į
iki
ir
iš
ja
ją
jai
jais
jam
jame
jas
jei
ji
jį
jie
jiedu
jiedvi
jiedviem
jiedviese
jiems
jis
jo
jodviem
jog
joje
jomis
joms
jos
jose

import java.util.Comparator;
import java.util.List;
import java.util.PriorityQueue;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.synonym.SynonymMap;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.store.ByteArrayDataInput;

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/lv/stopwords.txt
aiz
ap
ar
apakš
ārpus
augšpus
bez
caur
dēļ
gar
iekš
iz
kopš
labad
lejpus
līdz
no
otrpus
pa
par
pār
pēc
pie
pirms
pret
priekš
starp
šaipus
uz
viņpus
virs
virspus
zem
apakšpus
# Conjunctions
un
bet
jo
ja
ka

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/gl/stopwords.txt
a
aínda
alí
aquel
aquela
aquelas
aqueles
aquilo
aquí
ao
aos
as
así
á
ben
cando
che
co
coa
comigo
con
connosco
contigo
convosco
coas
cos
cun
cuns
cunha
cunhas
da
dalgunha
dalgunhas
dalgún
dalgúns
das
de
del
dela