Update model locations in HF

.github/workflows/ci-build-manual.yml

@@ -0,0 +1,65 @@
+name: Build and push a development version on docker 
+
+on:
+  workflow_dispatch:
+    inputs:
+      custom_tag:
+        type: string
+        description: Docker image tag
+        required: true
+        default: "latest-develop"
+
+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"
+          sudo rm -rf /opt/hostedtoolcache
+          sudo rm -rf /opt/google/chrome 
+          sudo rm -rf /opt/microsoft/msedge 
+          sudo rm -rf /opt/microsoft/powershell 
+          sudo rm -rf /opt/pipx 
+          sudo rm -rf /usr/lib/mono 
+          sudo rm -rf /usr/local/julia* 
+          sudo rm -rf /usr/local/lib/android 
+          sudo rm -rf /usr/local/lib/node_modules 
+          sudo rm -rf /usr/local/share/chromium 
+          sudo rm -rf /usr/local/share/powershell 
+          sudo rm -rf /usr/share/dotnet 
+          sudo rm -rf /usr/share/swift
+      - 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, ${{ github.event.inputs.custom_tag}}
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}

.github/workflows/ci-build.yml

@@ -0,0 +1,71 @@
+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
+          sudo rm -rf /opt/google/chrome 
+          sudo rm -rf /opt/microsoft/msedge 
+          sudo rm -rf /opt/microsoft/powershell 
+          sudo rm -rf /opt/pipx 
+          sudo rm -rf /usr/lib/mono 
+          sudo rm -rf /usr/local/julia* 
+          sudo rm -rf /usr/local/lib/android 
+          sudo rm -rf /usr/local/lib/node_modules 
+          sudo rm -rf /usr/local/share/chromium 
+          sudo rm -rf /usr/local/share/powershell 
+          sudo rm -rf /usr/share/dotnet 
+          sudo rm -rf /usr/share/swift
+      - 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 }}

.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
+

.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 }}