You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
ocrd-galley/Dockerfile-core

54 lines
1.2 KiB
Plaintext

FROM ubuntu:22.04
ARG PIP_INSTALL="pip install --no-cache-dir"
ARG OCRD_VERSION_MINIMUM="2.23.3"
ENV LC_ALL=C.UTF-8 LANG=C.UTF-8
ENV PIP_DEFAULT_TIMEOUT=120
RUN echo "APT::Acquire::Retries \"3\";" > /etc/apt/apt.conf.d/80-retries && \
apt-get update && \
apt-get install -y \
curl xz-utils \
build-essential python3-dev \
# For get-pip.py:
python3-distutils \
# For add-apt-repository:
software-properties-common \
# XML utils
libxml2-utils \
xmlstarlet \
# OCR-D uses ImageMagick for pixel density estimation
imagemagick \
&& \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# Set up OCR-D logging
RUN echo "setOverrideLogLevel(os.getenv('LOG_LEVEL', 'INFO'))" >/etc/ocrd_logging.py
# Install pip (and setuptools)
# We use get-pip.py here to avoid
# a. having to upgrade from Ubuntu's pip
# b. the dreaded "old script wrapper" error message
RUN curl -sSL https://bootstrap.pypa.io/pip/3.6/get-pip.py -o get-pip.py && \
python3 get-pip.py && \
rm -f get-pip.py
# Install pip installable-stuff
RUN ${PIP_INSTALL} \
"ocrd >= ${OCRD_VERSION_MINIMUM}"
# Check pip dependencies
RUN pip check
WORKDIR /data
# Default command
CMD ['ocrd']