sporada/nlp
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git synced 2025-07-01 12:10:34 +00:00
Code Issues Projects Releases Wiki Activity

Use JSON files for stand-off annotations.

Browse Source
This commit is contained in:
Patrick Jentsch
2021-03-26 09:46:17 +01:00
parent d620c29f27
commit aa1bfa259d
5 changed files with 347 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
Dockerfile
View File

@ -7,28 +7,29 @@ LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>, Stephan Porada <por
ENV LANG=C.UTF-8
RUN apt-get update
RUN apt-get update \
&& apt-get install --no-install-recommends --yes \
wget
# Install pipeline dependencies #
# Install the NLP pipeline and it's dependencies #
## 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}" \
ENV PYFLOW_VERSION=1.1.20
RUN wget --no-check-certificate --quiet \
"https://github.com/Illumina/pyflow/releases/download/v${PYFLOW_VERSION}/pyflow-${PYFLOW_VERSION}.tar.gz" \
&& tar -xzf "pyflow-${PYFLOW_VERSION}.tar.gz" \
&& cd "pyflow-${PYFLOW_VERSION}" \
&& apt-get install --no-install-recommends --yes \
python2.7 \
&& python2.7 setup.py build install \
&& cd .. \
&& rm -r "pyflow-${PYFLOW_RELEASE}" "pyflow-${PYFLOW_RELEASE}.tar.gz"
&& rm -r "pyflow-${PYFLOW_VERSION}" "pyflow-${PYFLOW_VERSION}.tar.gz"
## Install spaCy ##
ENV SPACY_VERSION=3.0.3
ENV SPACY_VERSION=3.0.5
RUN apt-get install --no-install-recommends --yes \
python3.7 \
python3-pip \
zip \
&& pip3 install \
chardet \
setuptools \
@ -36,22 +37,22 @@ RUN apt-get install --no-install-recommends --yes \
&& pip3 install --upgrade pip \
&& pip3 install "spacy==${SPACY_VERSION}"
# Only models that include the following components are compatibel:
# lemmatizer, ner, parser, senter, tagger,
ENV SPACY_MODELS="de_core_news_md,en_core_web_md,it_core_news_md,nl_core_news_md,pl_core_news_md,zh_core_web_md"
ENV SPACY_MODELS_VERSION=3.0.0
RUN python3 -m spacy download "da_core_news_md-${SPACY_MODELS_VERSION}" --direct \
&& 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 \
&& python3 -m spacy download "ru_core_news_md-${SPACY_MODELS_VERSION}" --direct \
&& python3 -m spacy download "zh_core_web_md-${SPACY_MODELS_VERSION}" --direct
RUN for spacy_model in $(echo ${SPACY_MODELS} | tr "," "\n"); do python3 -m spacy download "${spacy_model}-${SPACY_MODELS_VERSION}" --direct; done
## Further dependencies ##
RUN apt-get install --no-install-recommends --yes \
procps \
zip
## Install Pipeline ##
COPY nlp spacy-nlp /usr/local/bin/
COPY nlp spacy-nlp vrt-creator /usr/local/bin/
RUN rm -r /var/lib/apt/lists/*