kbss-cvut · ledsoft · Jun 16, 2026 · Jun 16, 2026 · Jun 16, 2026 · Jun 16, 2026
diff --git a/.github/workflows/before-push-to-main.yml b/.github/workflows/before-push-to-main.yml
@@ -12,12 +12,13 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up JDK 11
-        uses: actions/setup-java@v3
+      - uses: actions/checkout@v6
+      - name: Set up JDK
+        uses: actions/setup-java@v5
         with:
-          java-version: '11'
-          distribution: 'adopt'
+          java-version: '21'
+          distribution: 'temurin'
+          cache: 'gradle'
       - name: Grant execute permission for gradlew
         run: chmod +x gradlew
       - name: Build with Gradle

diff --git a/.github/workflows/on-push-to-main.yml b/.github/workflows/on-push-to-main.yml
@@ -11,7 +11,7 @@ jobs:
   build-and-publish:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Grant execute permission for gradlew
         run: chmod +x gradlew
       - name: Build with Gradle

diff --git a/Dockerfile b/Dockerfile
@@ -1,12 +1,23 @@
-FROM gradle:8.0.2-jdk11-alpine AS build
+FROM gradle:9.5.1-jdk25-alpine AS build
 RUN mkdir annotace
 WORKDIR /annotace
 COPY . .
 RUN gradle bootJar -x test
 
-FROM eclipse-temurin:11-jdk-alpine AS runtime
-COPY --from=build /annotace/core/build/libs/*.jar /
-RUN mv annotace*.jar annotace.jar
+FROM eclipse-temurin:25-jdk-alpine AS runtime
+# Run as a non-root user. Spark NLP downloads pretrained models on startup into
+# its cache folder (defaults to ~/cache_pretrained), and Spark writes runtime
+# artifacts (metastore_db, spark-warehouse) into the working directory, so the
+# user needs a writable home and working directory.
+RUN addgroup -S annotace \
+    && adduser -S -G annotace -h /home/annotace annotace \
+    && mkdir -p /app \
+    && chown -R annotace:annotace /app /home/annotace
+WORKDIR /app
+COPY --from=build --chown=annotace:annotace /annotace/core/build/libs/annotace-*.jar /app/annotace.jar
 
 EXPOSE 8080
-ENTRYPOINT ["java","-jar","/annotace.jar"]
+ENV HOME=/home/annotace
+ENV JDK_JAVA_OPTIONS="--add-opens java.base/sun.nio.ch=ALL-UNNAMED java.base/java.nio=ALL-UNNAMED java.base/java.util=ALL-UNNAMED java.base/java.lang=ALL-UNNAMED java.base/java.lang.invoke=ALL-UNNAMED"
+USER annotace
+ENTRYPOINT ["java","-XX:+UseCompactObjectHeaders","-jar","/app/annotace.jar"]
diff --git a/Dockerfile-morphodita b/Dockerfile-morphodita
@@ -10,20 +10,25 @@ COPY $MORPHODITA_ZIP /morphodita
 WORKDIR /morphodita
 RUN unzip *.zip
 
-FROM gradle:8.0.2-jdk11-alpine AS build
+FROM gradle:9.5.1-jdk25-alpine AS build
 ARG MORPHODITA_ZIP_SO
 RUN mkdir annotace
 WORKDIR /annotace
 COPY . .
 RUN gradle clean bootJar -x test
 
-FROM eclipse-temurin:11-jdk-alpine AS runtime
+FROM eclipse-temurin:25-jdk-alpine AS runtime
 ARG MORPHODITA_ZIP_SO
 # Work around an issue with missing library on Alpine Linux - https://www.svlada.com/fun-times-with-gcc-musl-alpine-linux/
-RUN apk add --update --no-cache libc6-compat
-COPY --from=build /annotace/core/build/libs/annotace-*.jar /
-RUN mv *.jar annotace.jar
-COPY --from=unzip /morphodita/$MORPHODITA_ZIP_SO /lib
+RUN apk add --update --no-cache libc6-compat \
+    && addgroup -S annotace \
+    && adduser -S -G annotace annotace
+WORKDIR /app
+COPY --from=build --chown=annotace:annotace /annotace/core/build/libs/annotace-*.jar /app/annotace.jar
+COPY --from=unzip /morphodita/$MORPHODITA_ZIP_SO /lib/
+# Ensure the MorphoDita native library is readable/executable by the non-root user
+RUN chmod -R a+rX "/lib/$(basename "$MORPHODITA_ZIP_SO")"
 
 EXPOSE 8080
-ENTRYPOINT ["java","-jar","/annotace.jar"]
+USER annotace
+ENTRYPOINT ["java","-XX:+UseCompactObjectHeaders","-jar","/app/annotace.jar"]
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@ Annotace is a text analysis service used e.g. by [TermIt](https://github.com/kbs
 
 ## How to run it?
 
-- Install Java 11
+- Install Java 21
 - Run `./gradlew bootRun` (on Linux/WSL) or `gradlew.bat bootRun` on Windows
 
 ## Lemmatizers
@@ -39,7 +39,7 @@ A complete command line example would be:
 
 1. Download the MorphoDiTa [ZIP archive](https://github.com/ufal/morphodita/releases/download/v1.9.2/morphodita-1.9.2-bin.zip).
 2. Set `MORPHODITA_ZIP` in `docker-compose-morphodita.yml` to path to the downloaded MorphoDiTa ZIP file.
-3. Download and extract taggers (language models). Put them into a single directory.
+3. Download and extract taggers (language models). Put them into a 11single directory.
 4. Set `MORPHODITA_TAGGERS` in `docker-compose-morphodita.yml` to path to the taggers' directory.
 5. Run `docker compose -f docker-compose-morphodita.yml up -d --build` to build and start Annotace wih MorphoDiTa.
 

diff --git a/api/src/main/java/cz/cvut/kbss/textanalysis/exception/AnnotaceException.java b/api/src/main/java/cz/cvut/kbss/textanalysis/exception/AnnotaceException.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/api/src/main/java/cz/cvut/kbss/textanalysis/exception/UnsupportedLanguageException.java b/api/src/main/java/cz/cvut/kbss/textanalysis/exception/UnsupportedLanguageException.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/api/src/main/java/cz/cvut/kbss/textanalysis/keywordextractor/KeywordExtractorAPI.java b/api/src/main/java/cz/cvut/kbss/textanalysis/keywordextractor/KeywordExtractorAPI.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/...rc/main/java/cz/cvut/kbss/textanalysis/keywordextractor/model/KeywordExtractorResult.java b/...rc/main/java/cz/cvut/kbss/textanalysis/keywordextractor/model/KeywordExtractorResult.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/api/src/main/java/cz/cvut/kbss/textanalysis/lemmatizer/LemmatizerApi.java b/api/src/main/java/cz/cvut/kbss/textanalysis/lemmatizer/LemmatizerApi.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/api/src/main/java/cz/cvut/kbss/textanalysis/lemmatizer/model/LemmatizerResult.java b/api/src/main/java/cz/cvut/kbss/textanalysis/lemmatizer/model/LemmatizerResult.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/api/src/main/java/cz/cvut/kbss/textanalysis/lemmatizer/model/SingleLemmaResult.java b/api/src/main/java/cz/cvut/kbss/textanalysis/lemmatizer/model/SingleLemmaResult.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/build.gradle b/build.gradle
@@ -1,45 +1,40 @@
 plugins {
-    id "org.springframework.boot" version "2.7.10" apply false
-    id "io.spring.dependency-management" version "1.0.11.RELEASE" apply false
-    id "com.github.hierynomus.license" version "0.16.1"
+    id "org.springframework.boot" version "4.1.0" apply false
+    id "io.spring.dependency-management" version "1.1.7" apply false
+    id "com.diffplug.spotless" version "7.0.4" apply false
 }
 
-group "cz.cvut.kbss"
-description "Text analysis for Czech language and annotation recommendation service"
-version "0.0.1"
+group = "cz.cvut.kbss"
+description = "Text analysis for Czech language and annotation recommendation service"
+version = "0.1.0"
 
 def revision = "git rev-list --count HEAD".execute().text.trim()
 def hash = "git rev-parse --short HEAD".execute().text.trim()
-version = "0.0.1.r${revision}.${hash}"
-
-ext {
-    junitVersion = "5.9.2"
-}
+version = "0.1.0.r${revision}.${hash}"
 
 subprojects {
     apply plugin: "java"
     apply plugin: "java-library"
-    apply plugin: "com.github.hierynomus.license"
+    apply plugin: "com.diffplug.spotless"
 
     compileJava {
-        sourceCompatibility = "11"
-        targetCompatibility = "11"
+        sourceCompatibility = "21"
+        targetCompatibility = "21"
     }
 
     test {
         useJUnitPlatform()
     }
 
-    license {
-        header = rootProject.file("header.txt")
-        excludes(["**/*.txt", "**/*.yml", "**/*.html", "**/*.xml", "**/*.ttl"])
-        mapping {
-            java = "SLASHSTAR_STYLE"
+    spotless {
+        java {
+            target "src/**/*.java"
+            licenseHeaderFile rootProject.file("header.txt"), "package "
         }
     }
 
-    group parent.group
-    version parent.version
+    group = parent.group
+    version = parent.version
 
     repositories {
         mavenCentral()
@@ -50,13 +45,14 @@ subprojects {
     }
 
     dependencies {
-        implementation "org.slf4j:slf4j-api:1.7.36"
-        implementation "ch.qos.logback:logback-classic:1.2.11"
-        compileOnly "org.projectlombok:lombok:1.18.20"
+        implementation "org.slf4j:slf4j-api:2.0.17"
+        implementation "ch.qos.logback:logback-classic:1.5.34"
+        compileOnly "org.projectlombok:lombok:1.18.32"
 
-        annotationProcessor "org.projectlombok:lombok:1.18.20"
+        annotationProcessor "org.projectlombok:lombok:1.18.32"
 
         testImplementation(libs.junit.api)
         testRuntimeOnly(libs.junit.engine)
+        testRuntimeOnly(libs.junit.platform.launcher)
     }
 }
diff --git a/core/build.gradle b/core/build.gradle
@@ -1,11 +1,13 @@
 apply plugin: "org.springframework.boot"
 apply plugin: "io.spring.dependency-management"
 
-description "Text analysis for Czech language and annotation recommendation service"
+description = "Text analysis for Czech language and annotation recommendation service"
+
+def applicationVersion = project.version
 
 processResources {
     filesMatching("application.yml") {
-        expand(["version": project.version])
+        expand(["version": applicationVersion])
     }
 }
 
@@ -16,23 +18,26 @@ dependencies {
     implementation project(":lemmatizer-morphodita")
 
     implementation(libs.spring.boot.web)
-    implementation("org.jsoup:jsoup:1.15.4")
+    implementation("org.jsoup:jsoup:1.18.1")
 
     implementation(libs.jackson.annotations)
-    implementation("org.apache.jena:apache-jena-libs:3.17.0")
+    implementation("org.apache.jena:jena-arq:6.0.0")
 
-    testImplementation("org.apache.commons:commons-lang3:3.12.0")
-    testImplementation("org.mockito:mockito-junit-jupiter:4.0.0")
+    testImplementation("org.apache.commons:commons-lang3:3.20.0")
     testImplementation("org.springframework.boot:spring-boot-starter-test")
 
 }
 
+test {
+    jvmArgs "--add-opens", "java.base/sun.nio.ch=ALL-UNNAMED", "--add-opens", "java.base/java.nio=ALL-UNNAMED", "--add-opens", "java.base/java.util=ALL-UNNAMED", "--add-opens", "java.base/java.lang=ALL-UNNAMED", "--add-opens", "java.base/java.lang.invoke=ALL-UNNAMED"
+}
+
 allprojects {
     configurations.configureEach {
         resolutionStrategy {
             dependencySubstitution {
-                substitute module("org.codehaus.janino:janino") using module("org.codehaus.janino:janino:3.0.16")
-                substitute module("org.codehaus.janino:commons-compiler") using module("org.codehaus.janino:commons-compiler:3.0.16")
+                substitute module("org.codehaus.janino:janino") using module("org.codehaus.janino:janino:3.1.9")
+                substitute module("org.codehaus.janino:commons-compiler") using module("org.codehaus.janino:commons-compiler:3.1.9")
             }
         }
     }

diff --git a/core/src/main/java/cz/cvut/kbss/textanalysis/App.java b/core/src/main/java/cz/cvut/kbss/textanalysis/App.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/core/src/main/java/cz/cvut/kbss/textanalysis/Constants.java b/core/src/main/java/cz/cvut/kbss/textanalysis/Constants.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/core/src/main/java/cz/cvut/kbss/textanalysis/Stopwords.java b/core/src/main/java/cz/cvut/kbss/textanalysis/Stopwords.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/core/src/main/java/cz/cvut/kbss/textanalysis/config/LemmatizerConfig.java b/core/src/main/java/cz/cvut/kbss/textanalysis/config/LemmatizerConfig.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -25,10 +25,10 @@
 import cz.cvut.kbss.textanalysis.lemmatizer.LemmatizerApi;
 import lombok.extern.slf4j.Slf4j;
 import org.springframework.beans.factory.annotation.Value;
-import org.springframework.boot.web.client.RestTemplateBuilder;
 import org.springframework.context.ApplicationContext;
 import org.springframework.context.annotation.Bean;
 import org.springframework.context.annotation.Configuration;
+import org.springframework.web.client.RestClient;
 
 @Configuration
 @Slf4j
@@ -39,17 +39,20 @@ public class LemmatizerConfig {
 
     @Bean
     public LemmatizerApi lemmatizer(ApplicationContext context) {
-        switch (lemmatizer) {
-            case "morphodita-jni":
+        return switch (lemmatizer) {
+            case "morphodita-jni" -> {
                 log.info("Instantiating MorphoDiTa JNI lemmatizer.");
-                return new MorphoDitaServiceJNI(context.getBean(MorphoditaConf.class));
-            case "morphodita-online":
+                yield new MorphoDitaServiceJNI(context.getBean(MorphoditaConf.class));
+            }
+            case "morphodita-online" -> {
                 log.info("Instantiating MorhoDiTa online lemmatizer.");
-                return new MorphoDitaServiceOnline(context.getBean(RestTemplateBuilder.class), context.getBean(
+                yield new MorphoDitaServiceOnline(RestClient.builder(), context.getBean(
                         MorphoditaConf.class));
-            default:
+            }
+            default -> {
                 log.info("Instantiating Apache Spark lemmatizer.");
-                return new SparkLemmatizer(context.getBean(SparkConf.class));
-        }
+                yield new SparkLemmatizer(context.getBean(SparkConf.class));
+            }
+        };
     }
 }
diff --git a/core/src/main/java/cz/cvut/kbss/textanalysis/dto/TextAnalysisInput.java b/core/src/main/java/cz/cvut/kbss/textanalysis/dto/TextAnalysisInput.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/core/src/main/java/cz/cvut/kbss/textanalysis/model/Phrase.java b/core/src/main/java/cz/cvut/kbss/textanalysis/model/Phrase.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

diff --git a/core/src/main/java/cz/cvut/kbss/textanalysis/model/QueryResult.java b/core/src/main/java/cz/cvut/kbss/textanalysis/model/QueryResult.java
@@ -1,6 +1,6 @@
 /*
  * Annotace
- * Copyright (C) 2024 Czech Technical University in Prague
+ * Copyright (C) 2026 Czech Technical University in Prague
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by