Upgrade Elasticsearch to 9.1.4 + fix plugin name

README.md

@@ -8,14 +8,17 @@ Korean analysis plugin that integrates [open-korean-text](https://github.com/ope
 
 Elasticsearch 4.x 이하의 버전은 지원하지 않습니다.
 
+## Plugin에 사용자 사전을 입력하여 수정이 필요한 경우
+https://github.com/Keunyoung-Jung/sns-tokenizer-whole 로 방문하여 사용자사전을 받을 수 있습니다.
+
 ## Install
 
 ```shell
 $ cd ${ES_HOME}
 $ bin/elasticsearch-plugin install {download URL}
 ```
 
-설치 후 `bin/elasticsearch` 실행 시, `loaded plugin [elasticsearch-analysis-openkoreantext]` 라는 로그가 출력되는지 확인합니다.
+설치 후 `bin/elasticsearch` 실행 시, `loaded plugin [analysis-openkoreantext]` 라는 로그가 출력되는지 확인합니다.
 
 **download URL 은 아래 [Compatible Versions](#compatible-versions)를 참고하여 Elasticsearch 버젼에 맞는 Plugin 버젼을 다운로드 받아야합니다.**
 
@@ -112,12 +115,12 @@ Elasticsearch의 default analyzer를 사용했을 경우
 ## User Dictionary
 [기본사전](https://github.com/open-korean-text/open-korean-text/tree/master/src/main/resources/org/openkoreantext/processor/util) 이외에 사용자가 원하는 단어를 추가하여 사용할 수 있습니다. 예를들어 `말썽쟁이`를 분석하면 `말썽(Noun)`과 `쟁이(suffix)`로 추출되지만, 사전에 `말썽쟁이`를 추가하면 `말썽쟁이(Noun)`로 추출할 수 있습니다.
 
-Analyzer Plugin을 설치하면 `{ES_HOME}/plugins/elasticserach-analysis-openkoreantext` 위치에 `dic/` 디렉토리를 찾을 수 있습니다. 해당 디렉토리 안에 사전 텍스트 파일을 추가하면 됩니다.
+Analyzer Plugin을 설치하면 `{ES_HOME}/plugins/analysis-openkoreantext` 위치에 `dic/` 디렉토리를 찾을 수 있습니다. 해당 디렉토리 안에 사전 텍스트 파일을 추가하면 됩니다.
 
 사전 텍스트 파일은 각 단어들을 줄바꿈하여 넣으면 됩니다. (단, 띄워쓰기는 단어로 인식하지 않습니다.)
 
 ```plain
-# {ES_HOME}/plugins/elasticserach-analysis-openkoreantext/dic/sampledictionary
+# {ES_HOME}/plugins/analysis-openkoreantext/dic/sampledictionary
 말썽쟁이
 뚜쟁이
 욕쟁이할머니

build.gradle

@@ -1,66 +1,70 @@
 group 'org.openkoreantext'
-version '6.5.2.0'
+version '9.1.4.0'
 
 apply plugin: 'java'
-apply plugin: 'maven'
+apply plugin: 'maven-publish'
 apply plugin: 'signing'
 apply plugin: 'jacoco'
+apply plugin: 'idea'
 
-sourceCompatibility = 1.8
+java {
+    sourceCompatibility = JavaVersion.VERSION_21
+    targetCompatibility = JavaVersion.VERSION_21
+}
 
 repositories {
     mavenCentral()
-    jcenter()
 }
 
 configurations {
     distJars {
-        extendsFrom runtime
+        extendsFrom runtimeClasspath
     }
 }
 
 ext {
-    elasticsearchVersion = '6.5.2'
-    openKoreanTextVersion = '2.1.0'
+    elasticsearchVersion = '9.1.4'
+    openKoreanTextVersion = '2.3.1'
 }
 
 dependencies {
-    compile group: 'org.openkoreantext', name: 'open-korean-text', version: openKoreanTextVersion
+    implementation group: 'org.openkoreantext', name: 'open-korean-text', version: openKoreanTextVersion
 
     compileOnly group: 'org.elasticsearch', name: 'elasticsearch', version: elasticsearchVersion
 
-    testCompile group: 'org.elasticsearch.test', name: 'framework', version: elasticsearchVersion
-    testCompile group: 'org.apache.logging.log4j', name: 'log4j-api', version: '2.9.1'
-    testCompile group: 'org.apache.logging.log4j', name: 'log4j-core', version: '2.9.1'
+    testImplementation group: 'org.elasticsearch.test', name: 'framework', version: elasticsearchVersion
+    testImplementation group: 'org.apache.logging.log4j', name: 'log4j-api', version: '2.19.0'
+    testImplementation group: 'org.apache.logging.log4j', name: 'log4j-core', version: '2.19.0'
 }
 
 task makePluginDescriptor(type: Copy) {
     from 'src/main/resources'
     into 'build/tmp/plugin'
     expand([
         'descriptor': [
-            'name': 'elasticsearch-analysis-openkoreantext',
+            'name': 'analysis-openkoreantext',
             'classname': 'org.elasticsearch.plugin.analysis.openkoreantext.AnalysisOpenKoreanTextPlugin',
             'description': 'Korean analysis plugin integrates open-korean-text module into elasticsearch.',
-            'version': '1.0.0',
-            'javaVersion': sourceCompatibility,
+            'version': '9.1.4',
+            'javaVersion': java.sourceCompatibility,
             'elasticsearchVersion' : elasticsearchVersion
         ]
     ])
 }
 
 task buildPluginZip(type: Zip, dependsOn: [':jar', ':makePluginDescriptor']) {
     from configurations.distJars
-    from jar.archivePath
+    from jar.archiveFile
     from 'build/tmp/plugin'
     into '.'
-    classifier = 'plugin'
+    archiveBaseName = 'elasticsearch-analysis-openkoreantext'
+    archiveClassifier = 'plugin'
 }
 
 build.finalizedBy(buildPluginZip)
 
 task javadocJar(type: Jar) {
-    classifier = 'javadoc'
+    archiveClassifier = 'javadoc'
     from javadoc
 }
 
@@ -71,7 +75,7 @@ tasks.withType(Javadoc) {
 }
 
 task sourcesJar(type: Jar) {
-    classifier = 'sources'
+    archiveClassifier = 'sources'
     from sourceSets.main.allSource
 }
 
@@ -86,14 +90,14 @@ test {
 }
 
 jacoco {
-    toolVersion = '0.7.1.201405082137'
+    toolVersion = '0.8.12'
 }
 
 jacocoTestReport {
     reports {
-        html.enabled = true
-        xml.enabled = true
-        csv.enabled = false
+        html.required = true
+        xml.required = true
+        csv.required = false
     }
 }
 
@@ -102,12 +106,8 @@ task jacocoRootReport(type: org.gradle.testing.jacoco.tasks.JacocoReport) {
     classDirectories =  files(sourceSets.main.output)
     executionData = files(jacocoTestReport.executionData)
     reports {
-        html.enabled = true
-        xml.enabled = true
-        csv.enabled = false
+        html.required = true
+        xml.required = true
+        csv.required = false
     }
 }
-
-task wrapper(type: Wrapper) {
-    gradleVersion = '3.4'
-}

gradle/wrapper/gradle-wrapper.properties

@@ -3,4 +3,4 @@ distributionBase=GRADLE_USER_HOME
 distributionPath=wrapper/dists
 zipStoreBase=GRADLE_USER_HOME
 zipStorePath=wrapper/dists
-distributionUrl=https\://services.gradle.org/distributions/gradle-3.4-all.zip
+distributionUrl=https\://services.gradle.org/distributions/gradle-8.10-all.zip

settings.gradle

@@ -1,2 +1,2 @@
-rootProject.name = 'elasticsearch-analysis-openkoreantext'
+rootProject.name = 'analysis-openkoreantext'
 

src/main/java/org/apache/lucene/analysis/ko/OpenKoreanTextAnalyzer.java

@@ -2,7 +2,6 @@
 
 import org.apache.lucene.analysis.*;
 import org.apache.lucene.analysis.miscellaneous.LengthFilter;
-import org.apache.lucene.analysis.standard.ClassicFilter;
 
 import java.io.Reader;
 import java.util.Arrays;
@@ -36,7 +35,6 @@ protected TokenStreamComponents createComponents(String fieldName) {
 
         TokenStream tokenStream = new OpenKoreanTextStemmer(tokenizer);
         tokenStream = new OpenKoreanTextRedundantFilter(tokenStream);
-        tokenStream = new ClassicFilter(tokenStream);
         tokenStream = new LengthFilter(tokenStream, 0, MAX_TOKEN_LENGTH);
         tokenStream = new LowerCaseFilter(tokenStream);
 

src/main/java/org/apache/lucene/analysis/ko/UserDictionaryLoader.java

@@ -10,7 +10,6 @@
 import java.io.*;
 import java.net.URL;
 import java.net.URLConnection;
-import java.security.AccessControlException;
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.List;
@@ -39,7 +38,7 @@ public class UserDictionaryLoader {
             if(dicDirectory.isDirectory()) {
                 dicFiles = dicDirectory.listFiles();
             }
-        } catch (AccessControlException e) {
+        } catch (SecurityException e) {
             logger.error("Can not load dictionary files", e);
         }
     }

src/main/java/org/elasticsearch/index/analysis/OpenKoreanTextAnalyzerProvider.java

@@ -14,7 +14,7 @@ public class OpenKoreanTextAnalyzerProvider extends AbstractIndexAnalyzerProvide
     private final OpenKoreanTextAnalyzer analyzer;
 
     public OpenKoreanTextAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(name);
         analyzer= new OpenKoreanTextAnalyzer();
         UserDictionaryLoader.loadDefaultUserDictionaries();
     }

src/main/java/org/elasticsearch/index/analysis/OpenKoreanTextNormalizerFactory.java

@@ -12,25 +12,20 @@
 /**
  * A ES character-filter factory for {@link OpenKoreanTextNormalizer}.
  */
-public class OpenKoreanTextNormalizerFactory extends AbstractCharFilterFactory implements MultiTermAwareComponent {
+public class OpenKoreanTextNormalizerFactory extends AbstractCharFilterFactory {
 
     public OpenKoreanTextNormalizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name);
+        super(name);
     }
 
     @Override
     public Reader create(Reader reader) {
         return new OpenKoreanTextNormalizer(reader);
     }
 
-    @Override
-    public Object getMultiTermComponent() {
-        return this;
-    }
-
     public static class OpenKoreanTextStemmerFactory extends AbstractTokenFilterFactory {
         public OpenKoreanTextStemmerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-            super(indexSettings, name, settings);
+            super(name);
         }
 
         @Override

src/main/java/org/elasticsearch/index/analysis/OpenKoreanTextPhraseExtractorFactory.java

@@ -12,7 +12,7 @@
 public class OpenKoreanTextPhraseExtractorFactory extends AbstractTokenFilterFactory {
 
     public OpenKoreanTextPhraseExtractorFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(name);
     }
 
     @Override

src/main/java/org/elasticsearch/index/analysis/OpenKoreanTextRedundantFilterFactory.java

@@ -12,7 +12,7 @@
 public class OpenKoreanTextRedundantFilterFactory extends AbstractTokenFilterFactory {
 
     public OpenKoreanTextRedundantFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(name);
     }
 
     @Override

src/main/java/org/elasticsearch/index/analysis/OpenKoreanTextStemmerFactory.java

@@ -12,7 +12,7 @@
 public class OpenKoreanTextStemmerFactory extends AbstractTokenFilterFactory {
 
     public OpenKoreanTextStemmerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(name);
     }
 
     @Override

src/main/java/org/elasticsearch/index/analysis/OpenKoreanTextTokenizerFactory.java

@@ -13,7 +13,7 @@
 public class OpenKoreanTextTokenizerFactory extends AbstractTokenizerFactory {
 
     public OpenKoreanTextTokenizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-        super(indexSettings, name, settings);
+        super(name);
         UserDictionaryLoader.loadDefaultUserDictionaries();
     }
 

src/test/java/org/apache/lucene/analysis/ko/OpenKoreanTextAnalyzerTest.java → src/test/java/org/apache/lucene/analysis/ko/TestOpenKoreanTextAnalyzer.java

@@ -10,7 +10,7 @@
 
 import static org.hamcrest.Matchers.instanceOf;
 
-public class OpenKoreanTextAnalyzerTest extends ESTestCase {
+public class TestOpenKoreanTextAnalyzer extends ESTestCase {
     public void testDefaultComponentsLoading() throws IOException {
         TestAnalysis analysis =  createTestAnalysis(new Index("test", "_na_"), Settings.EMPTY, new AnalysisOpenKoreanTextPlugin());
 

src/test/java/org/apache/lucene/analysis/ko/OpenKoreanTextNormalizerTest.java → src/test/java/org/apache/lucene/analysis/ko/TestOpenKoreanTextNormalizer.java

@@ -6,7 +6,7 @@
 
 import java.io.StringReader;
 
-public class OpenKoreanTextNormalizerTest {
+public class TestOpenKoreanTextNormalizer {
     @Test
     public void testNormalizerCharFilter() throws Exception {
         String query = "한국어를 처리하는 예시입니닼ㅋ. 오픈코리안텍스틓ㅎㅎㅎㅎㅎㅎㅎ";

src/test/java/org/apache/lucene/analysis/ko/OpenKoreanTextPhraseExtractorTest.java → src/test/java/org/apache/lucene/analysis/ko/TestOpenKoreanTextPhraseExtractor.java

@@ -6,8 +6,7 @@
 import java.io.IOException;
 import java.io.StringReader;
 
-public class OpenKoreanTextPhraseExtractorTest {
-
+public class TestOpenKoreanTextPhraseExtractor {
     @Test
     public void testBasicUsage() throws IOException {
         String query = "한국어를 처리하는 예시입니다ㅋㅋ #한국어";

src/test/java/org/apache/lucene/analysis/ko/OpenKoreanTextRedundantFilterTest.java → src/test/java/org/apache/lucene/analysis/ko/TestOpenKoreanTextRedundantFilter.java

@@ -6,7 +6,7 @@
 import java.io.IOException;
 import java.io.StringReader;
 
-public class OpenKoreanTextRedundantFilterTest {
+public class TestOpenKoreanTextRedundantFilter {
     @Test
     public void testBasicUsage() throws IOException {
         String query = "그리고 이것은 예시, 또는 예로써, 한국어를 처리하기 입니다";

src/test/java/org/apache/lucene/analysis/ko/OpenKoreanTextStemmerTest.java → src/test/java/org/apache/lucene/analysis/ko/TestOpenKoreanTextStemmer.java

@@ -6,8 +6,7 @@
 import java.io.IOException;
 import java.io.StringReader;
 
-public class OpenKoreanTextStemmerTest  {
-
+public class TestOpenKoreanTextStemmer  {
     @Test
     public void testBasicUsage() throws IOException {
         String query = "한국어를 처리하는 예시입니다ㅋㅋ";

src/test/java/org/apache/lucene/analysis/ko/OpenKoreanTextTokenizerTest.java → src/test/java/org/apache/lucene/analysis/ko/TestOpenKoreanTextTokenizer.java

@@ -5,12 +5,12 @@
 import java.io.File;
 import java.io.IOException;
 import java.io.StringReader;
+import java.net.URI;
 import java.net.URL;
 import java.util.ArrayList;
 import java.util.List;
 
-public class OpenKoreanTextTokenizerTest {
-
+public class TestOpenKoreanTextTokenizer {
     @Test
     public void testTokenizer() throws IOException {
         String text = "한국어를 처리하는 예시입니다ㅋㅋ";
@@ -61,13 +61,13 @@ public void testUserDictionaryFromFile() throws IOException {
     }
 
     @Test
-    public void testUserDictionaryFromURL() throws IOException {
+    public void testUserDictionaryFromURL() throws Exception {
         String text = "안비빈비빔밥은 맛있다";
         String[] expected = new String[]{"안비빈비빔밥", "은", " ", "맛있다"};
 
         OpenKoreanTextTokenizer tokenizer = new OpenKoreanTextTokenizer();
 
-        URL url = new URL("https://raw.githubusercontent.com/open-korean-text/elasticsearch-analysis-openkoreantext/master/src/test/resources/httpdictionary");
+        URL url = URI.create("https://raw.githubusercontent.com/open-korean-text/elasticsearch-analysis-openkoreantext/master/src/test/resources/httpdictionary").toURL();
         UserDictionaryLoader.addUserDictionary(url);
 
         tokenizer.setReader(new StringReader(text));

src/test/java/org/elasticsesarch/plugin/analysis/openkoreantext/AnalysisOpenKoreanTextPluginTest.java

@@ -2,9 +2,10 @@
 
 import org.elasticsearch.action.admin.cluster.node.info.NodeInfo;
 import org.elasticsearch.action.admin.cluster.node.info.NodesInfoResponse;
+import org.elasticsearch.action.admin.cluster.node.info.PluginsAndModules;
 import org.elasticsearch.plugin.analysis.openkoreantext.AnalysisOpenKoreanTextPlugin;
 import org.elasticsearch.plugins.Plugin;
-import org.elasticsearch.plugins.PluginInfo;
+import org.elasticsearch.plugins.PluginRuntimeInfo;
 import org.elasticsearch.test.ESIntegTestCase;
 import org.junit.Assert;
 
@@ -20,13 +21,16 @@ protected Collection<Class<? extends Plugin>> nodePlugins() {
     public void testPluginIsLoaded() {
         NodesInfoResponse response = client().admin().cluster().prepareNodesInfo().setPlugins(true).get();
         for (NodeInfo node : response.getNodes()) {
-            boolean founded = false;
-            for (PluginInfo pluginInfo : node.getPlugins().getPluginInfos()) {
-                if (pluginInfo.getName().equals(AnalysisOpenKoreanTextPlugin.class.getName())) {
-                    founded = true;
+            boolean found = false;
+            PluginsAndModules plugins = node.getInfo(PluginsAndModules.class);
+            if (plugins != null) {
+                for (PluginRuntimeInfo pluginInfo : plugins.getPluginInfos()) {
+                    if (pluginInfo.descriptor().getClassname().equals(AnalysisOpenKoreanTextPlugin.class.getName())) {
+                        found = true;
+                    }
                 }
             }
-            Assert.assertTrue(founded);
+            Assert.assertTrue(found);
         }
     }
-}
+}