Merge pull request #128 from kermitt2/feature/docker-image

Add docker image

Dockerfile

@@ -0,0 +1,117 @@
+## Docker GROBID-quantities image using deep learning models and/or CRF models, and various python modules
+## Borrowed from https://github.com/kermitt2/grobid/blob/master/Dockerfile.delft
+## See https://grobid.readthedocs.io/en/latest/Grobid-docker/
+
+## usage example with grobid: https://github.com/kermitt2/grobid/blob/master/Dockerfile.delft
+
+## docker build -t lfoppiano/grobid-quantities:0.7.0 --build-arg GROBID_VERSION=0.7.0 --file Dockerfile .
+
+## no GPU:
+## docker run -t --rm --init -p 8072:8072 -p 8073:8073 -v config.yml:/opt/grobid/grobid-quantities:ro  lfoppiano/grobid-quantities:0.7.0
+
+## allocate all available GPUs (only Linux with proper nvidia driver installed on host machine):
+## docker run --rm --gpus all --init -p 8072:8072 -p 8073:8073 -v grobid.yaml:/opt/grobid/grobid-home/config/grobid.yaml:ro  lfoppiano/grobid-superconductors:0.3.0-SNAPSHOT
+
+# -------------------
+# build builder image
+# -------------------
+
+FROM openjdk:8u275-jdk as builder
+
+USER root
+
+RUN apt-get update && \
+    apt-get -y --no-install-recommends install apt-utils libxml2 git
+
+RUN git clone https://github.com/kermitt2/grobid.git /opt/grobid-source && cd /opt/grobid-source && git checkout 0.7.0
+WORKDIR /opt/grobid-source
+COPY gradle.properties .
+
+RUN git clone https://github.com/kermitt2/grobid-quantities.git ./grobid-quantities && cd grobid-quantities && git checkout 0.7.0
+WORKDIR /opt/grobid-source/grobid-quantities
+COPY gradle.properties .
+
+# Adjust config
+RUN sed -i '/#Docker-ignore-log-start/,/#Docker-ignore-log-end/d'  ./resources/config/config.yml
+
+# Preparing models
+RUN rm -rf /opt/grobid-source/grobid-home/models/*
+
+WORKDIR /opt/grobid-source/grobid-quantities
+RUN ./gradlew clean assemble --no-daemon  --info --stacktrace
+#RUN ./gradlew installScibert --no-daemon --info --stacktrace && rm -f /opt/grobid-source/grobid-home/models/*.zip
+RUN ./gradlew copyModels --no-daemon --info --stacktrace && rm -f /opt/grobid-source/grobid-home/models/*.tar.gz
+
+
+WORKDIR /opt
+
+# -------------------
+# build runtime image
+# -------------------
+
+FROM grobid/grobid:0.7.0
+
+# setting locale is likely useless but to be sure
+ENV LANG C.UTF-8
+
+# install JRE 8, python and other dependencies
+RUN apt-get update && \
+    apt-get -y --no-install-recommends install git wget
+#    apt-get -y remove python3.6 && \
+#    DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends tzdata && \
+#    apt-get -y --no-install-recommends install git python3.7 python3.7-venv python3.7-dev python3.7-distutil
+
+WORKDIR /opt/grobid
+
+RUN mkdir -p /opt/grobid/grobid-quantities/resources/clearnlp/models /opt/grobid/grobid-quantities/resources/clearnlp/config
+COPY --from=builder /opt/grobid-source/grobid-home/models ./grobid-home/models
+COPY --from=builder /opt/grobid-source/grobid-quantities/build/libs/* ./grobid-quantities/
+COPY --from=builder /opt/grobid-source/grobid-quantities/resources/config/config.yml ./grobid-quantities/
+COPY --from=builder /opt/grobid-source/grobid-quantities/resources/clearnlp/config/* ./grobid-quantities/resources/clearnlp/config
+COPY --from=builder /opt/grobid-source/grobid-quantities/resources/clearnlp/models/* ./grobid-quantities/resources/clearnlp/models
+
+VOLUME ["/opt/grobid/grobid-home/tmp"]
+
+# Install requirements
+WORKDIR /opt/grobid/grobid-quantities
+
+RUN sed -i 's/pythonVirtualEnv:.*/pythonVirtualEnv: /g' config.yml
+RUN sed -i 's/grobidHome:.*/grobidHome: ..\/grobid-home/g' config.yml
+
+# JProfiler
+#RUN wget https://download-gcdn.ej-technologies.com/jprofiler/jprofiler_linux_12_0_2.tar.gz -P /tmp/ && \
+#  tar -xzf /tmp/jprofiler_linux_12_0_2.tar.gz -C /usr/local &&\
+#  rm /tmp/jprofiler_linux_12_0_2.tar.gz
+
+EXPOSE 8060 8061
+#EXPOSE 8080 8081
+
+#CMD ["java", "-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:5005", "-jar", "grobid-superconductors/grobid-superconductors-0.2.1-SNAPSHOT-onejar.jar", "server", "grobid-superconductors/config.yml"]
+#CMD ["java", "-agentpath:/usr/local/jprofiler12.0.2/bin/linux-x64/libjprofilerti.so=port=8849", "-jar", "grobid-superconductors/grobid-superconductors-0.2.1-SNAPSHOT-onejar.jar", "server", "grobid-superconductors/config.yml"]
+CMD ["java", "-jar", "grobid-quantities-0.7.0-onejar.jar", "server", "config.yml"]
+
+ARG GROBID_VERSION
+
+
+LABEL \
+    authors="Luca Foppiano, Patrice Lopez" \
+    org.label-schema.name="grobid-quantities" \
+    org.label-schema.description="Docker image for grobid-quantities service" \
+    org.label-schema.url="https://github.com/kermitt2/grobid-quantities" \
+    org.label-schema.version=${GROBID_VERSION}
+
+
+## Docker tricks:
+
+# - remove all stopped containers
+# > docker rm $(docker ps -a -q)
+
+# - remove all unused images
+# > docker rmi $(docker images --filter "dangling=true" -q --no-trunc)
+
+# - remove all untagged images
+# > docker rmi $(docker images | grep "^<none>" | awk "{print $3}")
+
+# - "Cannot connect to the Docker daemon. Is the docker daemon running on this host?"
+# > docker-machine restart
+

doc/gettingStarted.rst

@@ -10,6 +10,22 @@ Grobid-quantities requires *JDK 1.8 or greater* and Grobid to be installed.
 Install and build
 ~~~~~~~~~~~~~~~~~
 
+Docker containers
+~~~~~~~~~~~~~~~~~
+The simplest way to run grobid-quantities is via docker containers.
+To run the container with the default configuration:
+::
+     docker run --rm --init -p 8060:8060 -p 8061:8061  lfoppiano/grobid-quantities:0.7.0
+
+To run the container with custom configuration, is possible by providing a configuration file with the parameter ``-v``
+Grobid quantities repository provides already the file `resources/config/config-docker.yml` that contains the correct grobidHome and can be modified to best suits ones's needs: 
+::
+     docker run --rm --init -p 8060:8060 -p 8061:8061 -v resources/config/config-docker.yml:/opt/grobid/grobid-quantities/config.yml:ro  lfoppiano/grobid-quantities:0.7.0
+
+
+Local installation 
+~~~~~~~~~~~~~~~~~~~~~
+
 First install the latest development version of GROBID as explained by the `documentation <http://grobid.readthedocs.org>`_.
 
 Grobid-quantities root directory needs to be placed as sibling sub-project inside Grobid directory:

resources/config/config-docker.yml

@@ -0,0 +1,91 @@
+grobidHome: /opt/grobid/grobid-home
+
+corsAllowedOrigins: "*"
+corsAllowedMethods: "OPTIONS,GET,PUT,POST,DELETE,HEAD"
+corsAllowedHeaders: "X-Requested-With,Content-Type,Accept,Origin"
+
+# Limit the maximum number of requests
+maxParallelRequests: 0
+
+models:
+  - name: "quantities"
+    engine: "wapiti"
+    #engine: "delft"
+    wapiti:
+      # wapiti training parameters, they will be used at training time only
+      epsilon: 0.00001
+      window: 30
+      nbMaxIterations: 2000
+    delft:
+      # deep learning parameters
+      architecture: "BidLSTM_CRF"
+      #architecture: "scibert"
+      useELMo: false
+      embeddings_name: "glove-840B"
+
+  - name: "units"
+    engine: "wapiti"
+    #engine: "delft"
+    wapiti:
+      # wapiti training parameters, they will be used at training time only
+      epsilon: 0.00001
+      window: 30
+      nbMaxIterations: 2000
+    delft:
+      # deep learning parameters
+      architecture: "BidLSTM_CRF"
+      #architecture: "scibert"
+      useELMo: false
+      embeddings_name: "glove-840B"
+
+  - name: "values"
+    engine: "wapiti"
+    #engine: "delft"
+    wapiti:
+      # wapiti training parameters, they will be used at training time only
+      epsilon: 0.00001
+      window: 30
+      nbMaxIterations: 2000
+    delft:
+      # deep learning parameters
+      architecture: "BidLSTM_CRF"
+      #architecture: "scibert"
+      useELMo: false
+      embeddings_name: "glove-840B"
+
+
+views:
+  .mustache:
+    cache: false
+
+server:
+  type: custom
+  idleTimeout: 120 seconds
+  applicationConnectors:
+    - type: http
+      port: 8060
+  adminConnectors:
+    - type: http
+      port: 8061
+  registerDefaultExceptionMappers: false
+  maxThreads: 2048
+  maxQueuedRequests: 2048
+  acceptQueueSize: 2048
+
+logging:
+  level: INFO
+  appenders:
+    - type: console
+      threshold: INFO
+#Docker-ignore-log-start      
+    - type: file
+      threshold: DEBUG
+      logFormat: "%-6level [%d{HH:mm:ss.SSS}] [%t] %logger{5} - %X{code} %msg %n"
+      currentLogFilename: logs/grobid-quantities.log
+      archivedLogFilenamePattern: logs/grobid-quantities-%d{yyyy-MM-dd}-%i.log.gz
+      archivedFileCount: 7
+      timeZone: UTC
+      maxFileSize: 10MB
+#Docker-ignore-log-end
+timeZone: UTC
+

resources/config/config.yml

@@ -77,6 +77,7 @@ logging:
   appenders:
     - type: console
       threshold: INFO
+#Docker-ignore-log-start      
     - type: file
       threshold: DEBUG
       logFormat: "%-6level [%d{HH:mm:ss.SSS}] [%t] %logger{5} - %X{code} %msg %n"
@@ -85,4 +86,6 @@ logging:
       archivedFileCount: 7
       timeZone: UTC
       maxFileSize: 10MB
+#Docker-ignore-log-end
 timeZone: UTC
+