48 lines
1.3 KiB
Docker
48 lines
1.3 KiB
Docker
# OCRmyPDF
|
|
#
|
|
# VERSION 4.4.1
|
|
FROM ubuntu:16.10
|
|
MAINTAINER James R. Barlow <jim@purplerock.ca>
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
software-properties-common python-software-properties \
|
|
python3-wheel \
|
|
python3-reportlab \
|
|
python3-venv \
|
|
ghostscript \
|
|
qpdf \
|
|
poppler-utils \
|
|
unpaper \
|
|
libffi-dev
|
|
|
|
RUN add-apt-repository ppa:alex-p/tesseract-ocr
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
tesseract-ocr-all
|
|
|
|
RUN python3 -m venv --system-site-packages /appenv
|
|
|
|
COPY . /application
|
|
|
|
# This installs the latest binary wheel instead of the code in the current
|
|
# folder. cffi needs gcc otherwise.
|
|
RUN . /appenv/bin/activate; \
|
|
pip install --upgrade pip \
|
|
&& pip install ocrmypdf \
|
|
&& pip install -r /application/test_requirements.txt
|
|
|
|
# Remove the junk, including the source version of application
|
|
RUN apt-get autoremove -y && apt-get clean -y
|
|
RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/* /application/ocrmypdf
|
|
|
|
RUN useradd docker \
|
|
&& mkdir /home/docker \
|
|
&& chown docker:docker /home/docker
|
|
|
|
USER docker
|
|
WORKDIR /home/docker
|
|
|
|
# Must use array form of ENTRYPOINT
|
|
# Non-array form does not append other arguments, because that is "intuitive"
|
|
ENTRYPOINT ["/application/docker-wrapper.sh"]
|