Bump up Es version

build.gradle

@@ -23,7 +23,7 @@ repositories {
 }
 
 dependencies {
-    implementation 'com.worksap.nlp:sudachi:0.7.0', 'com.github.takawitter:trie4j:0.9.8', 'com.google.guava:guava:27.0.1-jre'
+    implementation 'com.worksap.nlp:sudachi:0.7.4', 'com.github.takawitter:trie4j:0.9.8', 'com.google.guava:guava:27.0.1-jre'
     compileOnly "org.elasticsearch:elasticsearch:${elasticsearchVersion}"
     testImplementation "org.elasticsearch:elasticsearch:${elasticsearchVersion}", "org.elasticsearch.test:framework:${elasticsearchVersion}", 'org.mockito:mockito-core:2.27.0', "org.apache.logging.log4j:log4j-core:2.17.1"
 }

gradle.properties

@@ -1 +1 @@
-elasticsearchVersion=7.17.1
+elasticsearchVersion=8.15.2

src/main/java/com/worksap/nlp/elasticsearch/plugins/analysis/ChikkarSynonymGraphTokenFilterFactory.java

@@ -28,6 +28,7 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.IndexService.IndexCreationContext;
 import org.elasticsearch.index.IndexSettings;
 import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
 import org.elasticsearch.index.analysis.CharFilterFactory;
@@ -64,7 +65,7 @@ public class ChikkarSynonymGraphTokenFilterFactory extends AbstractTokenFilterFa
      */
     public ChikkarSynonymGraphTokenFilterFactory(IndexSettings indexSettings, Environment env, String name,
             Settings settings) {
-        super(indexSettings, name, settings);
+        super(name, settings);
 
         // get the filter setting params
         this.ignoreCase = settings.getAsBoolean("ignore_case", false);
@@ -84,7 +85,7 @@ public TokenStream create(TokenStream tokenStream) {
     }
 
     @Override
-    public TokenFilterFactory getChainAwareTokenFilterFactory(TokenizerFactory tokenizer,
+    public TokenFilterFactory getChainAwareTokenFilterFactory(IndexCreationContext context, TokenizerFactory tokenizer,
             List<CharFilterFactory> charFilters, List<TokenFilterFactory> previousTokenFilters,
             Function<String, TokenFilterFactory> allFilters) {
         final Analyzer analyzer = buildSynonymAnalyzer(tokenizer, charFilters, previousTokenFilters);

src/main/java/com/worksap/nlp/elasticsearch/plugins/analysis/ChikkarSynonymMap.java

@@ -77,8 +77,8 @@ public Builder(boolean dedup) {
         public ChikkarSynonymMap build(Chikkar chikkar) throws IOException {
             ByteSequenceOutputs outputs = ByteSequenceOutputs.getSingleton();
             // TODO: are we using the best sharing options?
-            org.apache.lucene.util.fst.Builder<BytesRef> builder = new org.apache.lucene.util.fst.Builder<>(
-                    FST.INPUT_TYPE.BYTE4, outputs);
+            org.apache.lucene.util.fst.FSTCompiler<BytesRef> fstCompiler =
+                new org.apache.lucene.util.fst.FSTCompiler.Builder<>(FST.INPUT_TYPE.BYTE4, outputs).build();
 
             BytesRefBuilder scratch = new BytesRefBuilder();
             ByteArrayDataOutput scratchOutput = new ByteArrayDataOutput();
@@ -143,10 +143,10 @@ public ChikkarSynonymMap build(Chikkar chikkar) throws IOException {
                 }
 
                 scratch.setLength(scratchOutput.getPosition());
-                builder.add(Util.toUTF32(input, scratchIntsRef), scratch.toBytesRef());
+                fstCompiler.add(Util.toUTF32(input, scratchIntsRef), scratch.toBytesRef());
             }
 
-            FST<BytesRef> fst = builder.finish();
+            FST<BytesRef> fst = FST.fromFSTReader(fstCompiler.compile(), fstCompiler.getFSTReader());
             // remove unused relation manager
             chikkar.clearRelation();
             return new ChikkarSynonymMap(chikkar, fst, maxHorizontalContext);

src/main/java/com/worksap/nlp/elasticsearch/plugins/analysis/ChikkarSynonymTokenFilterFactory.java

@@ -23,6 +23,7 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.IndexService.IndexCreationContext;
 import org.elasticsearch.index.IndexSettings;
 import org.elasticsearch.index.analysis.*;
 
@@ -60,7 +61,7 @@ public class ChikkarSynonymTokenFilterFactory extends AbstractTokenFilterFactory
      */
     public ChikkarSynonymTokenFilterFactory(IndexSettings indexSettings, Environment env, String name,
             Settings settings) {
-        super(indexSettings, name, settings);
+        super(name, settings);
 
         // get the filter setting params
         this.ignoreCase = settings.getAsBoolean("ignore_case", false);
@@ -81,7 +82,7 @@ public TokenStream create(TokenStream tokenStream) {
     }
 
     @Override
-    public TokenFilterFactory getChainAwareTokenFilterFactory(TokenizerFactory tokenizer,
+    public TokenFilterFactory getChainAwareTokenFilterFactory(IndexCreationContext context, TokenizerFactory tokenizer,
             List<CharFilterFactory> charFilters, List<TokenFilterFactory> previousTokenFilters,
             Function<String, TokenFilterFactory> allFilters) {
         final Analyzer analyzer = buildSynonymAnalyzer(tokenizer, charFilters, previousTokenFilters);

src/test/java/com/worksap/nlp/elasticsearch/plugins/AnalysisChikkarPluginTest.java

@@ -41,6 +41,7 @@
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.Index;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.IndexService.IndexCreationContext;
 import org.elasticsearch.index.analysis.CharFilterFactory;
 import org.elasticsearch.index.analysis.CustomAnalyzer;
 import org.elasticsearch.index.analysis.TokenFilterFactory;
@@ -1211,7 +1212,7 @@ TokenFilterFactory createChikkarSynonymGraphFactory(Path configPath, String dict
 
         assertTrue(factory instanceof ChikkarSynonymGraphTokenFilterFactory);
 
-        return factory.getChainAwareTokenFilterFactory(tokenizer, charFilters, tokenFilters, null);
+        return factory.getChainAwareTokenFilterFactory(IndexCreationContext.CREATE_INDEX, tokenizer, charFilters, tokenFilters, null);
     }
 
     TokenFilterFactory createChikkarSynonymFactory(Path configPath, String dictPath, String dictId,
@@ -1237,7 +1238,7 @@ TokenFilterFactory createChikkarSynonymFactory(Path configPath, String dictPath,
 
         assertTrue(factory instanceof ChikkarSynonymTokenFilterFactory);
 
-        return factory.getChainAwareTokenFilterFactory(tokenizer, charFilters, tokenFilters, null);
+        return factory.getChainAwareTokenFilterFactory(IndexCreationContext.CREATE_INDEX, tokenizer, charFilters, tokenFilters, null);
     }
 
     TokenFilterFactory createSynonymFactory(Path configPath, String dictPath, TokenizerFactory tokenizer,
@@ -1257,7 +1258,7 @@ TokenFilterFactory createSynonymFactory(Path configPath, String dictPath, Tokeni
 
         TokenFilterFactory factory = new ModSynonymTokenFilterFactory(indexSettings, env, "mod_synonym", settings);
 
-        return factory.getChainAwareTokenFilterFactory(tokenizer, charFilters, tokenFilters, null);
+        return factory.getChainAwareTokenFilterFactory(IndexCreationContext.CREATE_INDEX, tokenizer, charFilters, tokenFilters, null);
     }
 
     void assertSynonymsEquals(List<TokenAttribute> expected, List<TokenAttribute> actual) {

src/test/java/com/worksap/nlp/elasticsearch/plugins/analysis/ModSynonymTokenFilterFactory.java

@@ -27,6 +27,7 @@
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.IndexService.IndexCreationContext;
 import org.elasticsearch.index.analysis.*;
 
 import java.io.Reader;
@@ -45,7 +46,7 @@ public class ModSynonymTokenFilterFactory extends AbstractTokenFilterFactory {
     protected final AnalysisMode analysisMode;
 
     public ModSynonymTokenFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(name, settings);
         this.settings = settings;
 
         if (settings.get("ignore_case") != null) {
@@ -76,7 +77,7 @@ public TokenStream create(TokenStream tokenStream) {
     }
 
     @Override
-    public TokenFilterFactory getChainAwareTokenFilterFactory(TokenizerFactory tokenizer,
+    public TokenFilterFactory getChainAwareTokenFilterFactory(IndexCreationContext context, TokenizerFactory tokenizer,
             List<CharFilterFactory> charFilters, List<TokenFilterFactory> previousTokenFilters,
             Function<String, TokenFilterFactory> allFilters) {
         final Analyzer analyzer = buildSynonymAnalyzer(tokenizer, charFilters, previousTokenFilters, allFilters);
@@ -140,7 +141,7 @@ Reader getRulesFromSettings(Environment env) {
             }
             rulesReader = new StringReader(sb.toString());
         } else if (settings.get("synonyms_path") != null) {
-            rulesReader = Analysis.getReaderFromFile(env, settings, "synonyms_path");
+            rulesReader = Analysis.getReaderFromFile(env, settings.get("synonyms_path"), "synonyms");
         } else {
             throw new IllegalArgumentException(
                     "synonym requires either `synonyms` or `synonyms_path` to be configured");