mirror of
https://github.com/JHUAPL/PINE.git
synced 2026-01-10 13:08:08 -05:00
ca3266f530
This includes two major features: 1. HTML view of CDA documents 2. simpletransformers-based NLP pipeline
118 lines
3.3 KiB
Docker
118 lines
3.3 KiB
Docker
# (C) 2019 The Johns Hopkins University Applied Physics Laboratory LLC.
|
|
|
|
FROM ubuntu:20.04
|
|
|
|
ENV LC_ALL C.UTF-8
|
|
ENV LANG C.UTF-8
|
|
ENV DEBIAN_FRONTEND noninteractive
|
|
|
|
# Install basic dependencies
|
|
RUN apt-get clean && \
|
|
apt-get -y update && \
|
|
apt-get -y install software-properties-common ca-certificates
|
|
|
|
# Copy any certs
|
|
COPY docker/*.crt /usr/local/share/ca-certificates/
|
|
RUN rm /usr/local/share/ca-certificates/empty.crt && update-ca-certificates
|
|
|
|
# For Controlling Startup Behaviour
|
|
ENV SKIP_PERMISSION_FIX 0
|
|
|
|
# Set Pipeline of interest
|
|
ENV PIPELINE $PIPELINE
|
|
|
|
# Set environment variables associated with click, necessary for use with pipenv?
|
|
ENV LC_ALL=C.UTF-8
|
|
ENV LANG=C.UTF-8
|
|
|
|
# Configure Container Default User
|
|
RUN groupadd -r nlp_user && useradd -m -r -g nlp_user nlp_user
|
|
|
|
# Configure GOSU (https://github.com/tianon/gosu)
|
|
COPY docker/gosu-110-amd64.bin /usr/local/bin/gosu
|
|
RUN chmod +x /usr/local/bin/gosu \
|
|
&& sync \
|
|
&& gosu nobody true
|
|
|
|
# Configure Tini (https://github.com/krallin/tini)
|
|
COPY docker/tini-static-amd64.bin /usr/local/bin/tini
|
|
RUN chmod +x /usr/local/bin/tini \
|
|
&& sync
|
|
|
|
# Install OS Dependencies
|
|
RUN set -ex \
|
|
&& apt-get update \
|
|
&& apt-get --no-install-recommends --yes install \
|
|
build-essential \
|
|
git curl wget iputils-ping net-tools dnsutils \
|
|
htop tmux vim nano screen zsh \
|
|
libgdal-dev gdal-bin \
|
|
&& apt-get -y autoremove \
|
|
&& apt-get -y clean \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
#install python
|
|
RUN apt-get update && apt-get install -y \
|
|
python3.6 \
|
|
python3-pip \
|
|
python3-setuptools \
|
|
python3-dev
|
|
|
|
# Installing spacy requires a lot of memory, need to kill running docker containers or it will fail here on my machine
|
|
# upgrade pip install/upgrade pipenv
|
|
RUN pip3 install --default-timeout=30 --upgrade pip pipenv
|
|
|
|
#Only corenlp/opennlp require java so add later on
|
|
RUN apt-get update && apt-get install -y \
|
|
openjdk-8-jdk
|
|
|
|
|
|
# TODO: Will need to refactor all directories in this Dockerfile once we adjust project structure
|
|
ARG ROOT_DIR=/nlp-web-app/pipelines
|
|
ENV ROOT_DIR ${ROOT_DIR}
|
|
RUN mkdir -p ${ROOT_DIR}
|
|
WORKDIR ${ROOT_DIR}
|
|
|
|
# pipenv causing container to fail to rebuild if spacy installed previously
|
|
#Install python requirements
|
|
COPY Pipfile Pipfile.lock ./
|
|
RUN REQUESTS_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt PIPENV_INSTALL_TIMEOUT=30 \
|
|
pipenv install --dev --system --deploy
|
|
RUN python3 -m nltk.downloader punkt
|
|
|
|
#Copy contents of pipeline folder to docker
|
|
COPY pine ./pine
|
|
|
|
# ensure that /opt/ is writable regardless of the UID our ctp instance ends up having at runtime
|
|
RUN chown -R nlp_user:nlp_user ${ROOT_DIR} \
|
|
&& chmod g+s ${ROOT_DIR} \
|
|
&& sync
|
|
|
|
# Copy Entrypoint Script
|
|
COPY docker/docker-entrypoint.sh /usr/local/bin/
|
|
|
|
## Copy the current directory contents into the container at /opt (order matters for cache/speed)
|
|
#COPY models/ /opt/models/
|
|
#COPY service/ /opt/service/
|
|
#COPY app/ /opt/app/
|
|
#COPY run_service.py /opt/
|
|
#COPY config.yaml /opt/
|
|
|
|
# Execute and Backwards Compat
|
|
RUN chmod +x /usr/local/bin/docker-entrypoint.sh \
|
|
&& sync \
|
|
&& ln -s /usr/local/bin/docker-entrypoint.sh /entrypoint.sh
|
|
|
|
# Declare Volumes
|
|
VOLUME ["/opt/logs"]
|
|
|
|
# Declare Entrypoint
|
|
ENTRYPOINT ["/usr/local/bin/tini", "--", "docker-entrypoint.sh"]
|
|
|
|
# Set PYTHONPATH
|
|
ENV PYTHONPATH "${PYTHONPATH}:/"
|
|
|
|
# Run app.py when the container launches
|
|
COPY docker_run.sh ./
|
|
CMD ["./docker_run.sh"]
|