Update Dockerfile

Dockerfile

@@ -1,9 +1,55 @@
-FROM lfoppiano/grobid-evaluation:latest
+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 mkdir -m 777 -p /opt/grobid/grobid-home/tmp
-RUN mkdir -m 777 -p /opt/grobid/logs
-RUN chmod -R uog+rw /data/db
 
-COPY --chown=lfoppiano grobid.yaml /opt/grobid/grobid-home/config/grobid.yaml
+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 + biblio-glutton
+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
+
+
+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;"]
 
-CMD ["/bin/bash", "-c", "./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/PMC_sample_1943 -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}