nlp/Dockerfile

FROM debian:10-slim


LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>, Stephan Porada <sporada@uni-bielefeld.de>"


ENV LANG=C.UTF-8


RUN apt-get update


## Install pyFlow ##
ENV PYFLOW_RELEASE=1.1.20
ADD "https://github.com/Illumina/pyflow/releases/download/v${PYFLOW_RELEASE}/pyflow-${PYFLOW_RELEASE}.tar.gz" .
RUN tar -xzf "pyflow-${PYFLOW_RELEASE}.tar.gz" \
 && cd "pyflow-${PYFLOW_RELEASE}" \
 && apt-get install -y --no-install-recommends \
      python2.7 \
 && python2.7 setup.py build install \
 && cd .. \
 && rm -r "pyflow-${PYFLOW_RELEASE}" "pyflow-${PYFLOW_RELEASE}.tar.gz"


## Install Pipeline ##
ENV SPACY_VERSION=2.3.2
ENV SPACY_MODELS_VERSION=2.3.0
RUN apt-get install -y --no-install-recommends \
      python3.7 \
      python3-pip \
      zip \
 && pip3 install \
      chardet \
      setuptools \
      wheel \
 && pip3 install "spacy==${SPACY_VERSION}" \
 && python3 -m spacy download "de_core_news_md-${SPACY_MODELS_VERSION}" --direct \
 && python3 -m spacy download "el_core_news_md-${SPACY_MODELS_VERSION}" --direct \
 && python3 -m spacy download "en_core_web_md-${SPACY_MODELS_VERSION}" --direct \
 && python3 -m spacy download "es_core_news_md-${SPACY_MODELS_VERSION}" --direct \
 && python3 -m spacy download "fr_core_news_md-${SPACY_MODELS_VERSION}" --direct \
 && python3 -m spacy download "it_core_news_md-${SPACY_MODELS_VERSION}" --direct \
 && python3 -m spacy download "nl_core_news_md-${SPACY_MODELS_VERSION}" --direct \
 && python3 -m spacy download "pt_core_news_md-${SPACY_MODELS_VERSION}" --direct
COPY nlp /usr/local/bin
COPY spacy-nlp /usr/local/bin


## Cleanup ##
RUN rm -r /var/lib/apt/lists/*


ENTRYPOINT ["nlp"]
CMD ["--help"]