FROM python:3.10

ENV DEBIAN_FRONTEND noninteractive

RUN apt-get -qq -y update \

&& apt-get -qq --no-install-recommends -y install locales \

postgresql-client jq python3-dev \

&& apt-get -qq -y autoremove \

&& apt-get clean \

&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \

&& localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8

ENV LANG='en_US.UTF-8'

RUN groupadd -g 1000 -r app \

&& useradd -m -u 1000 -s /bin/false -g app app

RUN pip3 install --no-cache-dir -q -U pip setuptools six

COPY requirements.txt /tmp/

RUN pip3 install --no-cache-dir -q -r /tmp/requirements.txt

COPY . /aleph

WORKDIR /aleph

ENV PYTHONPATH /aleph

RUN pip install --no-cache-dir -q -e /aleph

ENV ALEPH_WORD_FREQUENCY_URI=https://public.data.occrp.org/develop/models/word-frequencies/word_frequencies-v0.4.1.zip

ENV ALEPH_FTM_COMPARE_MODEL_URI=https://public.data.occrp.org/develop/models/xref/glm_bernoulli_2e_wf-v0.4.1.pkl

RUN mkdir -p /opt/ftm-compare/word-frequencies/ && \

curl -L -o "/opt/ftm-compare/word-frequencies/word-frequencies.zip" "$ALEPH_WORD_FREQUENCY_URI" && \

python3 -m zipfile --extract /opt/ftm-compare/word-frequencies/word-frequencies.zip /opt/ftm-compare/word-frequencies/ && \

curl -L -o "/opt/ftm-compare/model.pkl" "$ALEPH_FTM_COMPARE_MODEL_URI"

ENV ALEPH_ELASTICSEARCH_URI=http://elasticsearch:9200/ \

ALEPH_DATABASE_URI=postgresql://aleph:aleph@postgres/aleph \

FTM_STORE_URI=postgresql://aleph:aleph@postgres/aleph \

REDIS_URL=redis://redis:6379/0 \

ARCHIVE_TYPE=file \

ARCHIVE_PATH=/data \

FTM_COMPARE_FREQUENCIES_DIR=/opt/ftm-compare/word-frequencies/ \

FTM_COMPARE_MODEL=/opt/ftm-compare/model.pkl

RUN mkdir /run/prometheus

CMD gunicorn --config /aleph/gunicorn.conf.py --workers 6 --log-level debug --log-file -