ARG BUILD_ENV="local" FROM amazonlinux:2 as local ONBUILD ARG DOCS_SRC="awsdocs/data" ONBUILD WORKDIR "/awsdocs" ONBUILD COPY $DOCS_SRC "data/" FROM ${BUILD_ENV} ARG SCRIPT_NAME="run_ingestion_awsdocs" RUN yum install -y amazon-linux-extras RUN amazon-linux-extras enable python3.8 RUN yum install -y python3.8 jq wget gzip tar git COPY awsdocs/requirements.txt /awsdocs/requirements.txt RUN python3.8 -m pip --no-cache-dir install -r /awsdocs/requirements.txt RUN curl -O https://dl.xpdfreader.com/xpdf-tools-linux-4.04.tar.gz && tar -xvf xpdf-tools-linux-4.04.tar.gz && cp xpdf-tools-linux-4.04/bin64/pdftotext /usr/local/bin RUN yum -y install fontconfig COPY awsdocs/scripts /awsdocs/scripts COPY awsdocs/src /awsdocs/src WORKDIR "/awsdocs/data" RUN ln -s /awsdocs/scripts/$SCRIPT_NAME.sh /awsdocs/scripts/docker_entrypoint.sh #RUN python3.8 ../src/ingest.py ENTRYPOINT [ "bash", "/awsdocs/scripts/docker_entrypoint.sh" ] CMD ["amazon-ec2-user-guide", "awsdocs"] #repo substring or 'full' for all repos and index name defaults to 'awsdocs'