Merge pull request #1255 from kermitt2/docker-evaluation-image

Enable running end 2 end evaluation via a docker container

Author: lfoppiano

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

@@ -0,0 +1,47 @@
+name: Build and push a full docker image
+
+on:
+  workflow_dispatch:
+    inputs:
+      custom_tag:
+        type: string
+        description: Docker image tag
+        required: true
+        default: "latest"
+
+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-full:
+    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@v5
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_LFOPPIANO }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_LFOPPIANO }}
+          image: lfoppiano/grobid-evaluation
+          registry: docker.io
+          pushImage: true
+          tags: latest, ${{ github.event.inputs.custom_tag}}
+          dockerfile: Dockerfile.evaluation
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}

Dockerfile.evaluation

@@ -0,0 +1,63 @@
+## Grobid evaluation image
+## ------
+# https://grobid.readthedocs.io/en/latest/End-to-end-evaluation/
+# NOTE: To match the exact evaluation published in the Grobid documentation is necessary to have a running Biblio-glutton instance
+
+FROM lfoppiano/grobid:0.8.2-RC1-full as runtime
+
+# setting locale is likely useless but to be sure
+ENV LANG C.UTF-8
+
+USER root
+
+RUN apt-get update && \
+    apt-get -y --no-install-recommends install unzip wget
+
+WORKDIR /opt/grobid
+
+# gradle
+COPY gradle/ ./gradle/
+COPY gradlew ./
+COPY gradle.properties ./
+COPY build.gradle ./
+COPY settings.gradle ./
+
+# source
+COPY grobid-core/ ./grobid-core/
+COPY grobid-service/ ./grobid-service/
+COPY grobid-trainer/ ./grobid-trainer/
+
+# Setting DL-powered configuration
+COPY grobid-home/config/grobid-evaluation.yaml grobid-home/config/config.yaml
+
+RUN rm -rf /opt/grobid/grobid-home/models/*-with_ELMo \
+    && mkdir /opt/grobid/evaluation
+
+# Download evaluation data
+WORKDIR /opt/grobid/evaluation
+RUN wget https://zenodo.org/records/3873702/files/biorxiv-10k-test-2000.zip -O biorxiv-10k-test-2000.zip \
+    && unzip biorxiv-10k-test-2000.zip -d biorxiv-10k-test-2000 \
+    && wget https://zenodo.org/records/7708580/files/eLife_984.zip -O eLife_984.zip \
+    && unzip eLife_984.zip -d eLife_984 \
+    && wget https://zenodo.org/records/7708580/files/PLOS_1000.zip -O PLOS_1000.zip \
+    && unzip PLOS_1000.zip -d PLOS_1000 \
+    && wget https://zenodo.org/records/7708580/files/PMC_sample_1943.zip -O PMC_sample_1943.zip \
+    && unzip PMC_sample_1943.zip -d PMC_sample_1943 \
+    && rm *.zip
+
+#RUN wget -q https://zenodo.org/records/7708580/files/PMC_sample_1943.zip -O PMC_sample_1943.zip \
+#    && unzip PMC_sample_1943.zip -d PMC_sample_1943 \
+#    && rm *.zip
+
+VOLUME ["/opt/grobid/grobid-home/tmp"]
+
+WORKDIR /opt/grobid
+
+CMD ["/bin/bash", "-c", "./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/PMC_sample_1943 -Prun=1 -PfileRatio=1; ./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/biorxiv-10k-test-2000 -Prun=1 -PfileRatio=1; ./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/eLife_984 -Prun=1 -PfileRatio=1; ./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/PLOS_1000 -Prun=1 -PfileRatio=1;"]
+
+LABEL \
+    authors="The contributors" \
+    org.label-schema.name="Grobid" \
+    org.label-schema.description="Image running the Grobid End 2 end evaluation" \
+    org.label-schema.url="https://github.com/kermitt2/Grobid" \
+    org.label-schema.version=${GROBID_VERSION}