diff --git a/.github/workflows/ci-build-manual.yml b/.github/workflows/ci-build-manual.yml
new file mode 100644
index 0000000..0c7f53a
--- /dev/null
+++ b/.github/workflows/ci-build-manual.yml
@@ -0,0 +1,42 @@
+name: Build and push a development version on docker 
+
+on: 
+  workflow_dispatch: 
+    
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up JDK 17
+      uses: actions/setup-java@v4
+      with:
+        java-version: '17.0.10+7'
+        distribution: 'temurin'
+        cache: 'gradle'
+    - name: Build with Gradle
+      run: ./gradlew build -x test
+
+  docker-build:
+    needs: [ build ]
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Create more disk space
+        run: sudo rm -rf /usr/share/dotnet && sudo rm -rf /opt/ghc && sudo rm -rf "/usr/local/share/boost" && sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+      - uses: actions/checkout@v4
+      - name: Build and push
+        id: docker_build
+        uses: mr-smithers-excellent/docker-build-push@v6
+        with:
+          dockerfile: Dockerfile.datastet
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          image: lfoppiano/datastet
+          registry: docker.io
+          pushImage: true
+          tags: latest-develop
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}
\ No newline at end of file
diff --git a/.github/workflows/ci-build.yml b/.github/workflows/ci-build.yml
new file mode 100644
index 0000000..cc0f192
--- /dev/null
+++ b/.github/workflows/ci-build.yml
@@ -0,0 +1,59 @@
+name: Build unstable
+
+on: [push]
+
+concurrency: 
+  group: gradle
+#  cancel-in-progress: true
+
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up JDK 17
+      uses: actions/setup-java@v4
+      with:
+        java-version: '17.0.10+7'
+        distribution: 'temurin'
+        cache: 'gradle'
+    - name: Build with Gradle
+      run: ./gradlew build -x test
+
+    - name: Test with Gradle Jacoco and Coveralls
+      run: ./gradlew test jacocoTestReport coveralls --no-daemon
+
+    - name: Coveralls GitHub Action
+      uses: coverallsapp/github-action@v2
+      with:
+        github-token: ${{ secrets.GITHUB_TOKEN }}
+        format: jacoco
+
+  docker-build:
+    needs: [ build ]
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Create more disk space
+        run: |
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /opt/ghc
+          sudo rm -rf "/usr/local/share/boost"
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+          sudo rm -rf /opt/hostedtoolcache
+      - uses: actions/checkout@v4
+      - name: Build and push
+        id: docker_build
+        uses: mr-smithers-excellent/docker-build-push@v6
+        with:
+          dockerfile: Dockerfile.datastet
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          image: lfoppiano/datastet
+          registry: docker.io
+          pushImage: ${{ github.event_name != 'pull_request' }}
+          tags: latest-develop
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}
diff --git a/.github/workflows/ci-integration-manual.yml b/.github/workflows/ci-integration-manual.yml
new file mode 100644
index 0000000..c507534
--- /dev/null
+++ b/.github/workflows/ci-integration-manual.yml
@@ -0,0 +1,32 @@
+name: Run integration tests manually
+
+on:
+#  push:
+#    branches:
+#      - master
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout grobid home
+      uses: actions/checkout@v4
+      with:
+        repository: kermitt2/grobid
+        path: ./grobid
+    - name: Checkout Datastet
+      uses: actions/checkout@v4
+      with:
+        path: ./grobid/datastet
+    - name: Set up JDK 17
+      uses: actions/setup-java@v4
+      with:
+        java-version: '17.0.10+7'
+        distribution: 'temurin'
+        cache: 'gradle'
+    - name: Build and run integration tests
+      working-directory: ./grobid/datastet
+      run: ./gradlew copyModels integration --no-daemon
+   
diff --git a/.github/workflows/ci-release.yml b/.github/workflows/ci-release.yml
new file mode 100644
index 0000000..19e59d1
--- /dev/null
+++ b/.github/workflows/ci-release.yml
@@ -0,0 +1,74 @@
+name: Build release
+
+on:
+  workflow_dispatch:
+  push:
+    tags:
+      - 'v*'
+
+concurrency:
+  group: docker
+  cancel-in-progress: true
+
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up JDK 17
+      uses: actions/setup-java@v4
+      with:
+        java-version: '17.0.10+7'
+        distribution: 'temurin'
+        cache: 'gradle'
+    - name: Build with Gradle
+      run: ./gradlew build -x test
+
+    - name: Test with Gradle Jacoco and Coveralls
+      run: ./gradlew test jacocoTestReport coveralls --no-daemon
+
+    - name: Coveralls GitHub Action
+      uses: coverallsapp/github-action@v2
+      with:
+        github-token: ${{ secrets.GITHUB_TOKEN }}
+        format: jacoco
+        
+        
+  docker-build:
+    needs: [build]
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Create more disk space
+        run: sudo rm -rf /usr/share/dotnet && sudo rm -rf /opt/ghc && sudo rm -rf "/usr/local/share/boost" && sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+      - name: Set tags
+        id: set_tags
+        run: |
+          DOCKER_IMAGE=lfoppiano/datastet
+          VERSION=""
+          if [[ $GITHUB_REF == refs/tags/v* ]]; then
+            VERSION=${GITHUB_REF#refs/tags/v}
+          fi
+          if [[ $VERSION =~ ^[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}$ ]]; then
+            TAGS="${VERSION}"
+          else
+            TAGS="latest"
+          fi
+          echo "TAGS=${TAGS}"
+          echo ::set-output name=tags::${TAGS}
+      - uses: actions/checkout@v4
+      - name: Build and push
+        id: docker_build
+        uses: mr-smithers-excellent/docker-build-push@v6
+        with:
+          dockerfile: Dockerfile.local
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          image: lfoppiano/datastet
+          registry: docker.io
+          pushImage: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.set_tags.outputs.tags }}
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}  
diff --git a/Dockerfile.datastet b/Dockerfile.datastet
index 7ec2ada..e28f647 100644
--- a/Dockerfile.datastet
+++ b/Dockerfile.datastet
@@ -6,138 +6,72 @@ FROM openjdk:17-jdk-slim as builder
 
 USER root
 
-ARG GROBID_VERSION
-
 RUN apt-get update && \
-    apt-get -y --no-install-recommends install unzip
-
-WORKDIR /opt/grobid-source
-
-# gradle
-COPY gradle/ ./gradle/
-COPY gradlew ./
-COPY gradle.properties ./
-COPY build.gradle ./
-COPY settings.gradle ./
-
-# source
-COPY grobid-home/ ./grobid-home/
-COPY grobid-core/ ./grobid-core/
-#COPY grobid-service/ ./grobid-service/
-COPY grobid-trainer/ ./grobid-trainer/
-COPY datastet/ ./datastet/
-
-# cleaning unused native libraries before packaging
-RUN rm -rf grobid-home/pdf2xml
-RUN rm -rf grobid-home/pdfalto/lin-32
-RUN rm -rf grobid-home/pdfalto/mac-64
-RUN rm -rf grobid-home/pdfalto/win-*
-RUN rm -rf grobid-home/lib/lin-32
-RUN rm -rf grobid-home/lib/win-*
-RUN rm -rf grobid-home/lib/mac-64
-
-RUN ./gradlew clean assemble install --no-daemon  --info --stacktrace
-
-WORKDIR ./datastet/
-RUN ./gradlew clean install --no-daemon  --info --stacktrace
+    apt-get -y --no-install-recommends install apt-utils libxml2 git unzip wget
+
+WORKDIR /opt/grobid
 
+RUN mkdir -p datastet-source grobid-home/models
+COPY src datastet-source/src
+COPY settings.gradle datastet-source/
+COPY resources/config/config-docker.yml datastet-source/resources/config/config.yml
+COPY resources/models datastet-source/resources/models
+COPY resources/lexicon datastet-source/resources/lexicon
+COPY build.gradle datastet-source/
+COPY gradle.properties datastet-source/
+COPY gradle datastet-source/gradle/
+COPY gradlew datastet-source/
+#COPY .git datastet-source/.git
+#COPY localLibs datastet-source/localLibs
+
+# Preparing models
+WORKDIR /opt/grobid/datastet-source
+RUN rm -rf /opt/grobid/grobid-home/models/*
+RUN ./gradlew clean assemble -x shadowJar --no-daemon  --stacktrace --info
+RUN ./gradlew installModels  --no-daemon --info --stacktrace \
+    && rm -f /opt/grobid/grobid-home/models/*.zip
+
+# Preparing distribution
 WORKDIR /opt/grobid
-#RUN unzip -o /opt/grobid-source/grobid-service/build/distributions/grobid-service-*.zip && \
-#    mv grobid-service* grobid-service
-RUN unzip -o /opt/grobid-source/grobid-home/build/distributions/grobid-home-*.zip && \
-    chmod -R 755 /opt/grobid/grobid-home/pdfalto
-RUN rm -rf grobid-source
+RUN unzip -o /opt/grobid/datastet-source/build/distributions/datastet-*.zip -d datastet_distribution \
+  && mv datastet_distribution/datastet-* datastet \
+  && rm -rf /opt/grobid/datastet-source/build
+
+# install Pub2TEI
+WORKDIR /opt/
+RUN wget https://github.com/kermitt2/Pub2TEI/archive/refs/heads/master.zip && \
+    unzip master.zip &&  \
+    mv Pub2TEI-master Pub2TEI && \
+    rm master.zip
+
 
 # -------------------
 # build runtime image
 # -------------------
 
-# use NVIDIA Container Toolkit to automatically recognize possible GPU drivers on the host machine
-FROM tensorflow/tensorflow:2.7.0-gpu
-CMD nvidia-smi
+FROM lfoppiano/grobid:0.8.1-full as runtime
 
 # setting locale is likely useless but to be sure
 ENV LANG C.UTF-8
 
-# update NVIDIA Cuda key (following a key rotation in April 2022)
-RUN apt-get install -y wget
-RUN apt-key del 7fa2af80
-RUN rm /etc/apt/sources.list.d/cuda.list
-RUN rm /etc/apt/sources.list.d/nvidia-ml.list
-RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-keyring_1.0-1_all.deb
-RUN dpkg -i cuda-keyring_1.0-1_all.deb
-
-# install JRE, python and other dependencies
-RUN apt-get update && \
-    apt-get -y --no-install-recommends install apt-utils build-essential gcc libxml2 libfontconfig unzip curl \
-    openjdk-17-jre-headless openjdk-17-jdk ca-certificates-java \
-    musl gfortran \
-    python3 python3-pip python3-setuptools python3-dev \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /opt/grobid
-
-COPY --from=builder /opt/grobid .
-
-RUN python3 -m pip install pip --upgrade
-
-# install DeLFT via pypi
-RUN pip3 install requests delft==0.3.3
-# link the data directory to /data
-# the current working directory will most likely be /opt/grobid
-RUN mkdir -p /data \
-    && ln -s /data /opt/grobid/data \
-    && ln -s /data ./data
-
-# disable python warnings (and fix logging)
-ENV PYTHONWARNINGS="ignore"
-
 WORKDIR /opt/grobid
+RUN rm -rf /opt/grobid/grobid-home/models/*-with_ELMo \
+    && rm -rf /opt/grobid/grobid-service \
+    && ln -sf datastet/resources/ resources
 
-ENV JAVA_OPTS=-Xmx4g
-
-# install jep (and temporarily the matching JDK)
-ENV JDK_URL=https://download.java.net/java/GA/jdk17.0.2/dfd4a8d0985749f896bed50d7138ee7f/8/GPL/openjdk-17.0.2_linux-x64_bin.tar.gz
-RUN curl --fail --show-error --location -q ${JDK_URL} -o /tmp/openjdk.tar.gz 
-RUN mkdir /tmp/jdk-17 
-RUN tar xvfz /tmp/openjdk.tar.gz --directory /tmp/jdk-17 --strip-components 1 --no-same-owner 
-RUN /tmp/jdk-17/bin/javac -version
-RUN JAVA_HOME=/tmp/jdk-17 pip3 install jep==4.0.2 
-RUN rm -f /tmp/openjdk.tar.gz 
-RUN rm -rf /tmp/jdk-17
-ENV LD_LIBRARY_PATH=/usr/local/lib/python3.8/dist-packages/jep:grobid-home/lib/lin-64:grobid-home/lib/lin-64/jep:${LD_LIBRARY_PATH}
-# remove libjep.so because we are providing our own version in the virtual env above
-RUN rm /opt/grobid/grobid-home/lib/lin-64/jep/libjep.so
-
-# preload embeddings, for GROBID all the RNN models use glove-840B (default for the script), ELMo is currently not loaded 
-# download GROBID fine-tuned models based on SciBERT if selected
-
-COPY --from=builder /opt/grobid-source/grobid-home/scripts/preload_embeddings.py .
-# embeddings will be loaded when building and running tests
-
-RUN ln -s /opt/grobid /opt/delft
+# the last command above is just a hack to make the lexicon loader working
 
-COPY --from=builder /opt/grobid-source/datastet /opt/grobid/datastet
-COPY --from=builder /root/.m2/repository/org /opt/grobid/datastet/lib/org
+COPY --from=builder /opt/grobid/grobid-home/models ./grobid-home/models
+COPY --from=builder /opt/grobid/datastet ./datastet/
+COPY --from=builder /opt/grobid/datastet-source/resources/config/config.yml ./datastet/resources/config/
+COPY --from=builder /opt/grobid/datastet-source/resources/lexicon/ ./datastet/resources/lexicon/
 
-# install Pub2TEI
-WORKDIR /opt/
-RUN wget https://github.com/kermitt2/Pub2TEI/archive/refs/heads/master.zip
-RUN unzip master.zip
-RUN mv Pub2TEI-master Pub2TEI
-
-WORKDIR /opt/grobid/datastet
-
-RUN mkdir /opt/grobid/delft
-RUN mkdir /opt/grobid/delft/delft
-COPY --from=builder /opt/grobid-source/grobid-home/config/resources-registry.json /opt/grobid/delft/delft/resources-registry.json
+COPY --from=builder /opt/grobid/datastet /opt/grobid/datastet
+COPY --from=builder /opt/Pub2TEI /opt/Pub2TEI
 
-WORKDIR /opt/grobid/datastet
+VOLUME ["/opt/grobid/grobid-home/tmp"]
 
-# trigger gradle wrapper install
-RUN ./gradlew --version
-RUN ./gradlew installModels && rm -rf resources/models && rm ../grobid-home/models/dataseer*.zip && rm ../grobid-home/models/context_*.zip
+#WORKDIR /opt/grobid
 
 # install ELMo
 #RUN wget https://s3-us-west-2.amazonaws.com/allennlp/models/elmo/2x4096_512_2048cnn_2xhighway_5.5B/elmo_2x4096_512_2048cnn_2xhighway_5.5B_options.json
@@ -147,16 +81,20 @@ RUN ./gradlew installModels && rm -rf resources/models && rm ../grobid-home/mode
 #RUN mv elmo_2x4096_512_2048cnn_2xhighway_5.5B_weights.hdf5 /opt/elmo/
 
 # this will build and load embeddings on the image forever (only if required by the config) :)
-WORKDIR /opt/grobid/datastet
-#RUN ./gradlew clean build test
-RUN ./gradlew clean assemble --no-daemon --stacktrace --info -x test
+# LF: AFAIK this is not needed at the moment as all the models are running with bert, but might
+# be a solution if we want to support the GRU version
+# RUN python3 preload_embeddings.py --registry ./resources-registry.json --embedding word2vec
+
+ARG GROBID_VERSION
+ENV GROBID_VERSION=${GROBID_VERSION:-latest}
+ENV DATASTET_OPTS "-Djava.library.path=/opt/grobid/grobid-home/lib/lin-64:/usr/local/lib/python3.8/dist-packages/jep --add-opens java.base/java.lang=ALL-UNNAMED"
+
 
-#CMD ["./gradlew", "run"]
-CMD ["sh", "-c", "java --add-opens java.base/java.lang=ALL-UNNAMED -jar build/libs/datastet-0.8.0-onejar.jar server resources/config/config.yml"]
+CMD ["./datastet/bin/datastet", "server", "datastet/resources/config/config.yml"]
 
 LABEL \
     authors="The contributors" \
     org.label-schema.name="datastet" \
     org.label-schema.description="Image with DataStet service" \
-    org.label-schema.url="https://github.com/kermitt2/datastet" \
+    org.label-schema.url="https://github.com/DataSeer/datastet" \
     org.label-schema.version=${GROBID_VERSION}
\ No newline at end of file
diff --git a/build.gradle b/build.gradle
index 15232c4..b1d6e18 100644
--- a/build.gradle
+++ b/build.gradle
@@ -7,19 +7,18 @@ buildscript {
     dependencies {
         classpath 'gradle.plugin.org.kt3k.gradle.plugin:coveralls-gradle-plugin:2.12.0'
         classpath "gradle.plugin.com.github.jengelman.gradle.plugins:shadow:7.0.0"
+        classpath group: 'org.yaml', name: 'snakeyaml', version: '1.19'
     }
 }
 
 plugins {
     id 'com.github.johnrengelman.shadow' version '7.0.0'
-    id "de.undercouch.download" version "4.1.1"
+    id "de.undercouch.download" version "5.6.0"
+    id "jacoco"
+    id 'distribution'
+    id 'application'
 }
 
-apply plugin: 'jacoco'
-
-jacoco {
-    toolVersion = '0.8.8'
-}
 
 apply plugin: 'java-library'
 apply plugin: 'base'
@@ -30,8 +29,8 @@ version = '0.8.0'
 
 description = """datastet"""
 
-sourceCompatibility = 1.11
-targetCompatibility = 1.11
+sourceCompatibility = 1.17
+targetCompatibility = 1.17
 
 import org.apache.tools.ant.taskdefs.condition.Os
 
@@ -67,12 +66,12 @@ dependencies {
 
     //Apache commons
     implementation group: 'commons-pool', name: 'commons-pool', version: '1.6'
-    implementation group: 'commons-io', name: 'commons-io', version: '2.5'
+    implementation group: 'commons-io', name: 'commons-io', version: '2.9.0'
     //implementation group: 'commons-logging', name: 'commons-logging', version: '1.2'
-    implementation group: 'org.apache.httpcomponents', name: 'httpclient', version: '4.5.3'
+    implementation group: 'org.apache.httpcomponents', name: 'httpclient', version: '4.5.14'
     implementation group: 'org.apache.httpcomponents', name: 'httpmime', version: '4.5.3'
     implementation group: 'org.apache.commons', name: 'commons-lang3', version: '3.6'
-    implementation group: 'org.apache.commons', name: 'commons-collections4', version: '4.1'
+    implementation group: 'org.apache.commons', name: 'commons-collections4', version: '4.4'
     implementation group: 'org.apache.commons', name: 'commons-csv', version: '1.5'
 
     implementation group: 'com.google.guava', name: 'guava', version: '28.2-jre'
@@ -119,19 +118,21 @@ dependencies {
     implementation 'org.apache.opennlp:opennlp-tools:1.9.1'
 
     //Grobid
-    implementation group: 'org.grobid', name: 'grobid-core', version: '0.8.0'
-    implementation group: 'org.grobid', name: 'grobid-trainer', version: '0.8.0'
+    implementation group: 'org.grobid', name: 'grobid-core', version: '0.8.1'
+    implementation group: 'org.grobid', name: 'grobid-trainer', version: '0.8.1'
 
     //Tests
     testImplementation group: 'junit', name: 'junit', version: '4.12'
     testImplementation group: 'org.hamcrest', name: 'hamcrest-all', version: '1.3'
+    testImplementation 'org.powermock:powermock-module-junit4:2.0.9'
+    testImplementation 'org.powermock:powermock-api-easymock:2.0.9'
 }
 
-configurations.all { 
+configurations.all {
     resolutionStrategy {
         force 'xml-apis:xml-apis:1.4.01'
     }
-    
+
     exclude group: 'org.slf4j', module: "slf4j-log4j12"
     exclude group: 'org.slf4j', module: "slf4j-jdk14"
     exclude group: 'log4j', module: "log4j"
@@ -143,14 +144,14 @@ configurations.all {
 def libraries = ""
 if (Os.isFamily(Os.FAMILY_MAC)) {
     if (Os.OS_ARCH.equals("aarch64")) {
-        libraries = "${file("../grobid-home/lib/mac_arm-64").absolutePath}"    
+        libraries = "${file("../grobid-home/lib/mac_arm-64").absolutePath}"
     } else {
         libraries = "${file("../grobid-home/lib/mac-64").absolutePath}"
     }
 } else if (Os.isFamily(Os.FAMILY_UNIX)) {
     libraries = "${file("../grobid-home/lib/lin-64/jep").absolutePath}:" +
-        "${file("../grobid-home/lib/lin-64").absolutePath}:"
-} else  {
+            "${file("../grobid-home/lib/lin-64").absolutePath}:"
+} else {
     throw new RuntimeException("Unsupported platform!")
 }
 
@@ -161,10 +162,10 @@ test {
     exclude '**/**IntegrationTest**'
 
     if (JavaVersion.current().compareTo(JavaVersion.VERSION_1_8) > 0) {
-        jvmArgs "--add-opens", "java.base/java.util.stream=ALL-UNNAMED", 
-        "--add-opens", "java.base/java.io=ALL-UNNAMED"
+        jvmArgs "--add-opens", "java.base/java.util.stream=ALL-UNNAMED",
+                "--add-opens", "java.base/java.io=ALL-UNNAMED"
     }
-    systemProperty "java.library.path","${System.getProperty('java.library.path')}:" + libraries
+    systemProperty "java.library.path", "${System.getProperty('java.library.path')}:" + libraries
 }
 
 // return the default value if the property has not been specified in command line
@@ -172,6 +173,17 @@ ext.getArg = { propName, defaultVal ->
     return project.hasProperty(propName) ? project.getProperty(propName) : defaultVal;
 }
 
+task integration(type: Test) {
+    include '**'
+    maxHeapSize = "1024m"
+
+    if (JavaVersion.current().compareTo(JavaVersion.VERSION_1_8) > 0) {
+        jvmArgs "--add-opens", "java.base/java.util.stream=ALL-UNNAMED",
+                "--add-opens", "java.base/java.io=ALL-UNNAMED"
+    }
+    systemProperty "java.library.path", "${System.getProperty('java.library.path')}:" + libraries
+}
+
 import com.github.jengelman.gradle.plugins.shadow.tasks.ShadowJar
 
 apply plugin: 'java'
@@ -190,116 +202,78 @@ publishing {
 
 task install(dependsOn: publishToMavenLocal)
 
-task mainJar(type: ShadowJar) {
-    zip64 true
-    from sourceSets.main.output
-
-    configurations = [project.configurations.runtimeClasspath]
-
-    from {
-        project.configurations.implementation.collect {
-            it.isDirectory() ? [] : localLibs.contains(it.getName()) ? zipTree(it) : []
-        }
-    }
-}
+//task mainJar(type: ShadowJar) {
+//    zip64 true
+//    from sourceSets.main.output
+//
+//    configurations = [project.configurations.runtimeClasspath]
+//
+//    from {
+//        project.configurations.implementation.collect {
+//            it.isDirectory() ? [] : localLibs.contains(it.getName()) ? zipTree(it) : []
+//        }
+//    }
+//}
 
 shadowJar {
-    classifier = 'onejar'
+    archiveClassifier = 'onejar'
     mergeServiceFiles()
     zip64 true
     manifest {
         attributes 'Main-Class': 'org.grobid.core.main.batch.DatastetMain'
     }
-
+    from sourceSets.main.output
     configurations = [project.configurations.runtimeClasspath]
-
-    from {
-        project.configurations.implementation.collect {
-            it.isDirectory() ? [] : localLibs.contains(it.getName()) ? zipTree(it) : []
-        }
-    }
 }
 
 jar {
-    dependsOn mainJar
+//    dependsOn mainJar
     enabled true
 }
 
-tasks.withType(Tar){
-    duplicatesStrategy = DuplicatesStrategy.EXCLUDE
-}
-
-tasks.withType(Zip){
-    duplicatesStrategy = DuplicatesStrategy.EXCLUDE
-}
+distZip.enabled = true
+distTar.enabled = false
+shadowDistZip.enabled = false
+shadowDistTar.enabled = false
 
 artifacts {
-    archives jar
     archives shadowJar
 }
 
-task installModels(type: Copy) {
-    from "${rootDir}/resources/models/"
-    include "**"
-    into "${rootDir}/../grobid-home/models/"
-
-    doLast {
-        download {
-            src "https://grobid.s3.amazonaws.com/dataseer-binary_bert-0.3.1.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/dataseer-binary_bert-0.3.1.zip", dest: "${rootDir}/../grobid-home/models/")
-        
-        download {
-            src "https://grobid.s3.amazonaws.com/dataseer-first_bert-0.3.1.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/dataseer-first_bert-0.3.1.zip", dest: "${rootDir}/../grobid-home/models/")
-        
-        download {
-            src "https://grobid.s3.amazonaws.com/dataseer-reuse_bert-0.3.1.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/dataseer-reuse_bert-0.3.1.zip", dest: "${rootDir}/../grobid-home/models/")
+def conf = new org.yaml.snakeyaml.Yaml().load(new File("resources/config/config.yml").newInputStream())
+def grobidHome = conf.grobidHome.replace("\$", "").replace('{', "").replace("GROBID_HOME:- ", "").replace("}", "")
+if (grobidHome.startsWith("../")) {
+    grobidHome = "${rootProject.rootDir}/${grobidHome}"
+}
 
-        download {
-            src "https://grobid.s3.amazonaws.com/datasets-BERT_CRF-0.3.2.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/datasets-BERT_CRF-0.3.2.zip", dest: "${rootDir}/../grobid-home/models/")
+def models = [
+        'https://grobid.s3.amazonaws.com/dataseer-binary_bert-0.3.1.zip',
+        'https://grobid.s3.amazonaws.com/dataseer-first_bert-0.3.1.zip',
+        'https://grobid.s3.amazonaws.com/dataseer-reuse_bert-0.3.1.zip',
+        'https://grobid.s3.amazonaws.com/datasets-BERT_CRF-0.3.2.zip',
+        'https://grobid.s3.amazonaws.com/context_bert-0.3.2.zip',
+        'https://grobid.s3.amazonaws.com/context_bert_used-0.3.2.zip',
+        'https://grobid.s3.amazonaws.com/context_bert_creation-0.3.2.zip',
+        'https://grobid.s3.amazonaws.com/context_bert_shared-0.3.2.zip'
+]
+
+def installModels = tasks.register("installModels")
+
+models.eachWithIndex { model, index ->
+    def downloadTask = tasks.register("downloadModel_$index", Download) {
+        src(model)
+        dest "${grobidHome}/models/"
+        onlyIfNewer true
+        // overwrite true
+    }
 
-        download {
-            src "https://grobid.s3.amazonaws.com/context_bert-0.3.2.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/context_bert-0.3.2.zip", dest: "${rootDir}/../grobid-home/models/")
-        
-        download {
-            src "https://grobid.s3.amazonaws.com/context_bert_used-0.3.2.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/context_bert_used-0.3.2.zip", dest: "${rootDir}/../grobid-home/models/")
-        
-        download {
-            src "https://grobid.s3.amazonaws.com/context_bert_creation-0.3.2.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/context_bert_creation-0.3.2.zip", dest: "${rootDir}/../grobid-home/models/")
-        
-        download {
-            src "https://grobid.s3.amazonaws.com/context_bert_shared-0.3.2.zip"
-            dest "${rootDir}/../grobid-home/models/"
-            overwrite false
-        }
-        ant.unzip(src: "${rootDir}/../grobid-home/models/context_bert_shared-0.3.2.zip", dest: "${rootDir}/../grobid-home/models/")
+    def unzipTask = tasks.register("unzipModel_$index", Copy) {
+        dependsOn downloadTask
+        from zipTree(downloadTask.get().outputs.files.first())
+        into "${grobidHome}/models/"
     }
+
+    installModels.get().dependsOn(unzipTask)
 }
 
 //tasks.withType(JavaCompile) {
@@ -323,7 +297,7 @@ task(train_dataseer, dependsOn: 'classes', type: JavaExec, group: 'training') {
     } else {
         jvmArgs '-Xmx3072m'
     }
-    systemProperty "java.library.path","${System.getProperty('java.library.path')}:" + libraries
+    systemProperty "java.library.path", "${System.getProperty('java.library.path')}:" + libraries
 //    jvmArgs '-Xms2g', '-Xmx8g'
 }
 
@@ -345,7 +319,7 @@ task(eval_dataseer, dependsOn: 'classes', type: JavaExec, group: 'evaluation') {
     } else {
         jvmArgs '-Xmx3072m'
     }
-    systemProperty "java.library.path","${System.getProperty('java.library.path')}:" + libraries
+    systemProperty "java.library.path", "${System.getProperty('java.library.path')}:" + libraries
 //    jvmArgs '-Xms2g', '-Xmx8g'
 }
 
@@ -360,7 +334,7 @@ task(eval_dataseer_split, dependsOn: 'classes', type: JavaExec, group: 'evaluati
     } else {
         jvmArgs '-Xms2g', '-Xmx8g'
     }
-    systemProperty "java.library.path","${System.getProperty('java.library.path')}:" + libraries
+    systemProperty "java.library.path", "${System.getProperty('java.library.path')}:" + libraries
 }
 
 // Run like this: ./gradlew eval_dataseer_nfold -PgH=/path/grobid/home -Pt=10
@@ -373,7 +347,7 @@ task(eval_dataseer_nfold, dependsOn: 'classes', type: JavaExec, group: 'evaluati
     } else {
         jvmArgs '-Xms2g', '-Xmx8g'
     }
-    systemProperty "java.library.path","${System.getProperty('java.library.path')}:" + libraries
+    systemProperty "java.library.path", "${System.getProperty('java.library.path')}:" + libraries
 }
 
 // Run like this: ./gradlew annotated_corpus_generator_csv -Pfull=/path/input/fulltext -Ppdf=/path/input/pdf -Pcsv=/path/csv -Pxml=/output/directory
@@ -386,7 +360,7 @@ task(annotated_corpus_generator_csv, dependsOn: 'classes', type: JavaExec, group
     } else {
         jvmArgs '-Xms2g', '-Xmx8g'
     }
-    systemProperty "java.library.path","${System.getProperty('java.library.path')}:" + libraries
+    systemProperty "java.library.path", "${System.getProperty('java.library.path')}:" + libraries
 }
 
 //////////
@@ -406,3 +380,15 @@ application {
         args = ['server', 'resources/config/config.yml']
     }
 }
+
+jacocoTestReport {
+    reports {
+        xml.enabled = true // coveralls plugin depends on xml format report
+        html.enabled = true
+    }
+    dependsOn test // tests are required to run before generating the report
+}
+
+coveralls {
+    jacocoReportPath 'build/reports/jacoco/test/jacocoTestReport.xml'
+}
diff --git a/gradle.properties b/gradle.properties
new file mode 100644
index 0000000..dd48123
--- /dev/null
+++ b/gradle.properties
@@ -0,0 +1,3 @@
+org.gradle.caching=false
+org.gradle.daemon=false
+org.gradle.jvmargs= --add-exports=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-exports=jdk.unsupported/sun.misc=ALL-UNNAMED
\ No newline at end of file
diff --git a/resources/config/config.yml b/resources/config/config.yml
index 917e307..cfb4524 100644
--- a/resources/config/config.yml
+++ b/resources/config/config.yml
@@ -19,7 +19,7 @@ entityFishingPort: 443
 #entityFishingPort: 8090
 
 # if true we use binary classifiers for the contexts, otherwise use a single multi-label classifier
-# binary classifiers perform better, but havier to use
+# binary classifiers perform better, but heavier to use
 useBinaryContextClassifiers: false
 
 # sequence labeling model (identify data-related sections)
@@ -153,7 +153,7 @@ logging:
     com.squarespace.jersey2.guice.JerseyGuiceUtils: "OFF"
   appenders:
     - type: console
-      threshold: WARN
+      threshold: INFO
       timeZone: UTC
       # uncomment to have the logs in json format
       #layout:
diff --git a/src/main/java/org/grobid/core/analyzers/DatastetAnalyzer.java b/src/main/java/org/grobid/core/analyzers/DatastetAnalyzer.java
index 8fc06a8..b089324 100644
--- a/src/main/java/org/grobid/core/analyzers/DatastetAnalyzer.java
+++ b/src/main/java/org/grobid/core/analyzers/DatastetAnalyzer.java
@@ -88,6 +88,11 @@ public List<LayoutToken> tokenizeWithLayoutToken(String text) {
         return result;
     }
 
+    @Override
+    public List<LayoutToken> retokenizeFromLayoutToken(List<LayoutToken> tokens) {
+        throw new UnsupportedOperationException("Method retokenizeFromLayoutToken not yet implemented");
+    }
+
     public List<String> retokenize(List<String> chunks) {
         List<String> result = new ArrayList<>();
         for (String chunk : chunks) {
diff --git a/src/test/java/org/grobid/core/engines/DataseerClassifierTest.java b/src/test/java/org/grobid/core/engines/DataseerClassifierTest.java
index 115b8d6..8940913 100644
--- a/src/test/java/org/grobid/core/engines/DataseerClassifierTest.java
+++ b/src/test/java/org/grobid/core/engines/DataseerClassifierTest.java
@@ -1,49 +1,40 @@
 package org.grobid.core.engines;
 
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.dataformat.yaml.YAMLFactory;
 import org.apache.commons.io.IOUtils;
-import org.grobid.core.document.Document;
-import org.grobid.core.factory.GrobidFactory;
-import org.grobid.core.utilities.GrobidProperties;
-import org.grobid.core.utilities.DataseerConfiguration;
 import org.grobid.core.main.GrobidHomeFinder;
-import org.grobid.core.utilities.GrobidConfig.ModelParameters;
 import org.grobid.core.main.LibraryLoader;
+import org.grobid.core.utilities.DatastetConfiguration;
+import org.grobid.core.utilities.GrobidConfig.ModelParameters;
+import org.grobid.core.utilities.GrobidProperties;
 import org.junit.Before;
 import org.junit.BeforeClass;
-import org.junit.Test;
 import org.junit.Ignore;
+import org.junit.Test;
 
 import java.io.File;
 import java.nio.charset.StandardCharsets;
-import java.util.List;
-import java.util.Arrays;
 import java.util.ArrayList;
-
-import org.apache.commons.lang3.tuple.Pair;
-
-import com.fasterxml.jackson.databind.ObjectMapper;
-import com.fasterxml.jackson.dataformat.yaml.YAMLFactory;
-
-import static org.hamcrest.MatcherAssert.assertThat;
-import static org.hamcrest.Matchers.hasSize;
-import static org.junit.Assert.assertNotNull;
+import java.util.Arrays;
+import java.util.List;
 
 /**
  * @author Patrice
  */
 @Ignore
 public class DataseerClassifierTest {
-    private static DataseerConfiguration configuration;
+    private static DatastetConfiguration configuration;
 
     @BeforeClass
     public static void setUpClass() throws Exception {
-        DataseerConfiguration dataseerConfiguration = null;
+        DatastetConfiguration dataseerConfiguration = null;
         try {
             ObjectMapper mapper = new ObjectMapper(new YAMLFactory());
 
             File yamlFile = new File("resources/config/dataseer-ml.yml").getAbsoluteFile();
             yamlFile = new File(yamlFile.getAbsolutePath());
-            dataseerConfiguration = mapper.readValue(yamlFile, DataseerConfiguration.class);
+            dataseerConfiguration = mapper.readValue(yamlFile, DatastetConfiguration.class);
 
             String pGrobidHome = dataseerConfiguration.getGrobidHome();
 
diff --git a/src/test/java/org/grobid/core/engines/DatasetParserTest.java b/src/test/java/org/grobid/core/engines/DatasetParserTest.java
index 8864128..80d31c1 100644
--- a/src/test/java/org/grobid/core/engines/DatasetParserTest.java
+++ b/src/test/java/org/grobid/core/engines/DatasetParserTest.java
@@ -1,50 +1,41 @@
 package org.grobid.core.engines;
 
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.dataformat.yaml.YAMLFactory;
 import org.apache.commons.io.IOUtils;
-import org.grobid.core.document.Document;
 import org.grobid.core.data.Dataset;
-import org.grobid.core.factory.GrobidFactory;
-import org.grobid.core.utilities.GrobidProperties;
-import org.grobid.core.utilities.DataseerConfiguration;
 import org.grobid.core.main.GrobidHomeFinder;
-import org.grobid.core.utilities.GrobidConfig.ModelParameters;
 import org.grobid.core.main.LibraryLoader;
+import org.grobid.core.utilities.DatastetConfiguration;
+import org.grobid.core.utilities.GrobidConfig.ModelParameters;
+import org.grobid.core.utilities.GrobidProperties;
 import org.junit.Before;
 import org.junit.BeforeClass;
-import org.junit.Test;
 import org.junit.Ignore;
+import org.junit.Test;
 
 import java.io.File;
 import java.nio.charset.StandardCharsets;
-import java.util.List;
-import java.util.Arrays;
 import java.util.ArrayList;
-
-import org.apache.commons.lang3.tuple.Pair;
-
-import com.fasterxml.jackson.databind.ObjectMapper;
-import com.fasterxml.jackson.dataformat.yaml.YAMLFactory;
-
-import static org.hamcrest.MatcherAssert.assertThat;
-import static org.hamcrest.Matchers.hasSize;
-import static org.junit.Assert.assertNotNull;
+import java.util.Arrays;
+import java.util.List;
 
 /**
  * @author Patrice
  */
 @Ignore
 public class DatasetParserTest {
-    private static DataseerConfiguration configuration;
+    private static DatastetConfiguration configuration;
 
     @BeforeClass
     public static void setUpClass() throws Exception {
-        DataseerConfiguration dataseerConfiguration = null;
+        DatastetConfiguration dataseerConfiguration = null;
         try {
             ObjectMapper mapper = new ObjectMapper(new YAMLFactory());
 
             File yamlFile = new File("resources/config/dataseer-ml.yml").getAbsoluteFile();
             yamlFile = new File(yamlFile.getAbsolutePath());
-            dataseerConfiguration = mapper.readValue(yamlFile, DataseerConfiguration.class);
+            dataseerConfiguration = mapper.readValue(yamlFile, DatastetConfiguration.class);
 
             String pGrobidHome = dataseerConfiguration.getGrobidHome();
 
diff --git a/src/test/java/org/grobid/core/lexicon/DatasetLexiconTest.java b/src/test/java/org/grobid/core/lexicon/DatasetLexiconTest.java
index 7e5c736..9e788fb 100644
--- a/src/test/java/org/grobid/core/lexicon/DatasetLexiconTest.java
+++ b/src/test/java/org/grobid/core/lexicon/DatasetLexiconTest.java
@@ -1,48 +1,32 @@
 package org.grobid.core.lexicon;
 
-import org.apache.commons.io.IOUtils;
-import org.grobid.core.analyzers.DataseerAnalyzer;
-import org.grobid.core.data.Dataset;
-import org.grobid.core.document.Document;
-import org.grobid.core.factory.GrobidFactory;
-import org.grobid.core.layout.LayoutToken;
-import org.grobid.core.utilities.GrobidProperties;
-import org.grobid.core.utilities.DataseerConfiguration;
-import org.grobid.core.utilities.OffsetPosition;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.dataformat.yaml.YAMLFactory;
 import org.grobid.core.main.GrobidHomeFinder;
+import org.grobid.core.utilities.DatastetConfiguration;
 import org.grobid.core.utilities.GrobidConfig.ModelParameters;
-import org.grobid.core.main.LibraryLoader;
-import org.grobid.core.utilities.Pair;
-import org.junit.Before;
+import org.grobid.core.utilities.GrobidProperties;
 import org.junit.BeforeClass;
 import org.junit.Test;
 
 import java.io.File;
-import java.nio.charset.StandardCharsets;
-import java.util.List;
-import java.util.ArrayList;
 import java.util.Arrays;
 
 import static org.hamcrest.MatcherAssert.assertThat;
-import static org.hamcrest.Matchers.hasSize;
 import static org.hamcrest.Matchers.is;
-import static org.junit.Assert.assertNotNull;
-
-import com.fasterxml.jackson.databind.ObjectMapper;
-import com.fasterxml.jackson.dataformat.yaml.YAMLFactory;
 
 /**
  * @author Patrice
  */
 public class DatasetLexiconTest {
-    private static DataseerLexicon dataseerLexicon;
+    private static DatastetLexicon dataseerLexicon;
 
     @BeforeClass
     public static void setUpClass() throws Exception {
-        DataseerConfiguration dataseerConfiguration = null;
+        DatastetConfiguration dataseerConfiguration = null;
         try {
             ObjectMapper mapper = new ObjectMapper(new YAMLFactory());
-            dataseerConfiguration = mapper.readValue(new File("resources/config/dataseer-ml.yml").getAbsoluteFile(), DataseerConfiguration.class);
+            dataseerConfiguration = mapper.readValue(new File("resources/config/dataseer-ml.yml").getAbsoluteFile(), DatastetConfiguration.class);
 
             String pGrobidHome = dataseerConfiguration.getGrobidHome();
 
@@ -57,7 +41,7 @@ public static void setUpClass() throws Exception {
             }
             //LibraryLoader.load();
 
-            dataseerLexicon = DataseerLexicon.getInstance();
+            dataseerLexicon = DatastetLexicon.getInstance();
 
         } catch (final Exception exp) {
             System.err.println("GROBID dataset initialisation failed: " + exp);
@@ -71,9 +55,9 @@ public void testDatasetDOISuccess() throws Exception {
         String testStringDryad = "https://doi.org/10.5061/DRYAD.0SN63/7";
         String testStringFigshare = "https://doi.org/10.6084/m9.figshare.10275182";
         
-        boolean zenodoCheck = DataseerLexicon.getInstance().isDatasetDOI(testStringZenodo);
-        boolean dryadCheck = DataseerLexicon.getInstance().isDatasetDOI(testStringDryad);
-        boolean figshareCheck = DataseerLexicon.getInstance().isDatasetDOI(testStringFigshare);
+        boolean zenodoCheck = DatastetLexicon.getInstance().isDatasetDOI(testStringZenodo);
+        boolean dryadCheck = DatastetLexicon.getInstance().isDatasetDOI(testStringDryad);
+        boolean figshareCheck = DatastetLexicon.getInstance().isDatasetDOI(testStringFigshare);
 
         assertThat(zenodoCheck, is(true));
         assertThat(dryadCheck, is(true));
@@ -86,9 +70,9 @@ public void testDatasetDOIFail() throws Exception {
         String testStringSecond = "https://doi.org/10.1371/journal.pone.0263302";
         String testStringThird = "https://doi.org/10.1186/s13064-019-0127-z";
         
-        boolean firstCheck = DataseerLexicon.getInstance().isDatasetDOI(testStringFirst);
-        boolean secondCheck = DataseerLexicon.getInstance().isDatasetDOI(testStringSecond);
-        boolean thirdCheck = DataseerLexicon.getInstance().isDatasetDOI(testStringThird);
+        boolean firstCheck = DatastetLexicon.getInstance().isDatasetDOI(testStringFirst);
+        boolean secondCheck = DatastetLexicon.getInstance().isDatasetDOI(testStringSecond);
+        boolean thirdCheck = DatastetLexicon.getInstance().isDatasetDOI(testStringThird);
 
         assertThat(firstCheck, is(false));
         assertThat(secondCheck, is(false));
@@ -101,9 +85,9 @@ public void testDatasetUrlSuccess() throws Exception {
         String testStringGithub = "https://github.com/leonfodoulian/SARS_CoV_2_anosmia";
         String testStringOsf = "https://osf.io/5r72u";
 
-        boolean idCheck = DataseerLexicon.getInstance().isDatasetURL(testStringId);
-        boolean githubCheck = DataseerLexicon.getInstance().isDatasetURL(testStringGithub);
-        boolean osfCheck = DataseerLexicon.getInstance().isDatasetURL(testStringOsf);
+        boolean idCheck = DatastetLexicon.getInstance().isDatasetURL(testStringId);
+        boolean githubCheck = DatastetLexicon.getInstance().isDatasetURL(testStringGithub);
+        boolean osfCheck = DatastetLexicon.getInstance().isDatasetURL(testStringOsf);
 
         assertThat(idCheck, is(true));
         assertThat(githubCheck, is(true));
@@ -116,9 +100,9 @@ public void testDatasetUrlFail() throws Exception {
         String testStringSecond = "https://nlp.johnsnowlabs.com/api/com/johnsnowlabs/nlp/annotators/LemmatizerModel.html";
         String testStringThird = "https://stackoverflow.com/questions/11976393/get-github-username-by-id";
 
-        boolean firstCheck = DataseerLexicon.getInstance().isDatasetURL(testStringFirst);
-        boolean secondCheck = DataseerLexicon.getInstance().isDatasetURL(testStringSecond);
-        boolean thirdCheck = DataseerLexicon.getInstance().isDatasetURL(testStringThird);
+        boolean firstCheck = DatastetLexicon.getInstance().isDatasetURL(testStringFirst);
+        boolean secondCheck = DatastetLexicon.getInstance().isDatasetURL(testStringSecond);
+        boolean thirdCheck = DatastetLexicon.getInstance().isDatasetURL(testStringThird);
 
         assertThat(firstCheck, is(false));
         assertThat(secondCheck, is(false));
@@ -130,8 +114,8 @@ public void testLeadingStopwords() throws Exception {
         String testStringFirst = "and the dataset TOTO";
         String testStringSecond = "and the dataset TOTO of";
 
-        String firstCheck = DataseerLexicon.getInstance().removeLeadingEnglishStopwords(testStringFirst);
-        String secondCheck = DataseerLexicon.getInstance().removeLeadingEnglishStopwords(testStringSecond);
+        String firstCheck = DatastetLexicon.getInstance().removeLeadingEnglishStopwords(testStringFirst);
+        String secondCheck = DatastetLexicon.getInstance().removeLeadingEnglishStopwords(testStringSecond);
 
         assertThat(firstCheck, is("dataset TOTO"));
         assertThat(secondCheck, is("dataset TOTO of"));