* governing permissions and limitations under the License.
 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.Tokenizer;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenizerFactory;

/**
 * Factory for {@link NGramSynonymTokenizer}.
 */

 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.codelibs.analysis.ja.CharTypeFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

 */
package org.codelibs.opensearch.extension.analysis;

import java.util.regex.Pattern;

import org.apache.lucene.analysis.TokenStream;
import org.codelibs.analysis.ja.PatternConcatenationFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

 */
package org.codelibs.opensearch.extension.analysis;

import org.apache.lucene.analysis.TokenStream;
import org.codelibs.analysis.en.FlexiblePorterStemFilter;
import org.opensearch.common.settings.Settings;
import org.opensearch.env.Environment;
import org.opensearch.index.IndexSettings;
import org.opensearch.index.analysis.AbstractTokenFilterFactory;

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/ca/stopwords.txt
a
abans
ací
ah
així
això
al
als
aleshores
algun
alguna
algunes
alguns
alhora
allà
allí
allò
altra
altre
altres
amb
ambdós
ambdues
apa
aquell
aquella
aquelles
aquells
aquest
aquesta
aquestes
aquests
aquí
baix
cada
cadascú

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/hi/stopwords.txt
अंदर
अत
अपना
अपनी
अपने
अभी
आदि
आप
इत्यादि
इन 
इनका
इन्हीं
इन्हें
इन्हों
इस
इसका
इसकी
इसके
इसमें
इसी
इसे
उन
उनका
उनकी
उनके
उनको
उन्हीं
उन्हें
उन्हों
उस
उसके
उसी
उसे
एक
एवं
एस
ऐसे
और
कई
कर
करता
करते

# https://github.com/apache/lucene-solr/blob/master/lucene/analysis/common/src/resources/org/apache/lucene/analysis/ro/stopwords.txt
acea
aceasta
această
aceea
acei
aceia
acel
acela
acele
acelea
acest
acesta
aceste
acestea
aceşti
aceştia
acolo
acum
ai
aia
aibă
aici
al
ăla
ale
alea
ălea
altceva
altcineva
am
ar
are
aş
aşadar
asemenea
asta
ăsta
astăzi

	"istio.io/istio/istioctl/pkg/util/formatting"
	"istio.io/istio/pkg/cluster"
	"istio.io/istio/pkg/config/analysis"
	"istio.io/istio/pkg/config/analysis/analyzers"
	"istio.io/istio/pkg/config/analysis/diag"
	"istio.io/istio/pkg/config/analysis/local"
	"istio.io/istio/pkg/config/analysis/msg"
	"istio.io/istio/pkg/config/resource"
	"istio.io/istio/pkg/kube"
	"istio.io/istio/pkg/kube/multicluster"

# 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

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;