new croatian stemmer

.github/workflows/build.yml

@@ -9,7 +9,7 @@ jobs:
         runs-on: ubuntu-latest
         strategy:
             matrix:
-                es_version: [8.9.2, 8.15.2]
+                es_version: [8.15.2]
         steps:
             - name: Checkout project sources
               uses: actions/checkout@v2

.gitignore

@@ -1,5 +1,8 @@
 .gradle
 /build/
+/bin/
+*.class
+
 
 # Ignore Gradle GUI config
 gradle-app.setting

Makefile

@@ -0,0 +1,12 @@
+ES_VERSION ?= 8.15.2
+JAVA_HOME ?= /usr/lib/jvm/java-17-openjdk-amd64
+
+.PHONY: all build
+
+all: build
+
+build:
+	@echo "Building with Elasticsearch version $(ES_VERSION)"
+	@export JAVA_HOME=$(JAVA_HOME) && \
+	export PATH=$$JAVA_HOME/bin:$$PATH && \
+	./gradlew build -Pelasticsearch.version=$(ES_VERSION)

README.md

@@ -12,12 +12,17 @@ in the [release](https://github.com/monitora-media/es-utils/releases/latest).
 
 ## Build
 
-    ES_VERSION=8.9.2
+    ES_VERSION=8.15.2
     ./gradlew build -Pelasticsearch.version=$ES_VERSION
 
+    export JAVA_HOME=/usr/lib/jvm/java-17-openjdk-amd64
+    export PATH=$JAVA_HOME/bin:$PATH
+    JAVA_HOME=/usr/lib/jvm/java-17-openjdk-amd64 PATH=$JAVA_HOME/bin:$PATH ./gradlew build -Pelasticsearch.version=8.15.2
+
+
 ## Testing
 
-    gradle test --debug
+    gradle test --info --tests "Croatian*"
 
 ## Install
 

gradle.properties

@@ -1,2 +1,2 @@
-elasticsearch.version=8.5.3
+elasticsearch.version=8.15.2
 plugin.version=1.2.0-SNAPSHOT

src/main/java/cz/monitora/elasticsearch/MonitoraESPlugin.java

@@ -1,5 +1,6 @@
 package cz.monitora.elasticsearch;
 
+import cz.monitora.elasticsearch.analyzer.croatian.CroatianStemFilterFactory;
 import cz.monitora.elasticsearch.analyzer.czech.CzechStemFilterFactory;
 import cz.monitora.elasticsearch.analyzer.lowercase.LowerCaseTokenFilterFactory;
 import cz.monitora.elasticsearch.analyzer.slovak.SlovakStemFilterFactory;
@@ -20,6 +21,7 @@ public Map<String, AnalysisModule.AnalysisProvider<TokenFilterFactory>> getToken
         AnalysisPlugin.requiresAnalysisSettings(LowerCaseTokenFilterFactory::new));
     extra.put("monitora_czech_stem", CzechStemFilterFactory::new);
     extra.put("monitora_slovak_stem", SlovakStemFilterFactory::new);
+    extra.put("monitora_croatian_stem", CroatianStemFilterFactory::new);
     return extra;
   }
 }

src/main/java/cz/monitora/elasticsearch/analyzer/croatian/CroatianStemFilter.java

@@ -0,0 +1,58 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package cz.monitora.elasticsearch.analyzer.croatian;
+
+import java.io.IOException;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter; // for javadoc
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
+
+/**
+ * A {@link TokenFilter} that applies {@link CroatianStemmer} to stem Croatian words.
+ *
+ * <p>To prevent terms from being stemmed use an instance of {@link SetKeywordMarkerFilter} or a
+ * custom {@link TokenFilter} that sets the {@link KeywordAttribute} before this {@link
+ * TokenStream}.
+ *
+ * <p><b>NOTE</b>: Input is expected to be in lowercase, but with diacritical marks
+ *
+ * @see SetKeywordMarkerFilter
+ */
+public final class CroatianStemFilter extends TokenFilter {
+  private final CroatianStemmer stemmer = new CroatianStemmer();
+  private final CharTermAttribute termAttr = addAttribute(CharTermAttribute.class);
+  private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
+
+  public CroatianStemFilter(TokenStream input) {
+    super(input);
+  }
+
+  @Override
+  public boolean incrementToken() throws IOException {
+    if (input.incrementToken()) {
+      if (!keywordAttr.isKeyword()) {
+        final int newlen = stemmer.stem(termAttr.buffer(), termAttr.length());
+        termAttr.setLength(newlen);
+      }
+      return true;
+    } else {
+      return false;
+    }
+  }
+}

src/main/java/cz/monitora/elasticsearch/analyzer/croatian/CroatianStemFilterFactory.java

@@ -0,0 +1,21 @@
+package cz.monitora.elasticsearch.analyzer.croatian;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
+
+public class CroatianStemFilterFactory extends AbstractTokenFilterFactory {
+
+  /** Creates a new CroatianStemFilterFactory */
+  public CroatianStemFilterFactory(
+      IndexSettings indexSettings, Environment env, String name, Settings settings) {
+    super(name, settings);
+  }
+
+  @Override
+  public TokenStream create(TokenStream input) {
+    return new CroatianStemFilter(input);
+  }
+}