scdh/ocr-env repository overview

FROM ubuntu:18.04

# Install useful packages
ARG DEBIAN_FRONTEND=noninteractive
RUN apt-get update && \
    apt-get install -y \
        build-essential \
        libpangocairo-1.0 \
        libxml2 \
        libblas3 \
        liblapack3 \
        python3-dev \
        python3-pip \
    	xpdf \
    	ocrmypdf \
    	dialog \
    	tesseract-ocr \
    	tesseract-ocr-all \
    	imagemagick \
    	ghostscript \
        locales

# Set locales
RUN sed -i -e 's/# en_US.UTF-8 UTF-8/en_US.UTF-8 UTF-8/' /etc/locale.gen && \
    locale-gen
ENV LANG en_US.UTF-8
ENV LANGUAGE en_US:en
ENV LC_ALL en_US.UTF-8

# Creates shared-folder with host and gives it user permissions
RUN mkdir -m777 shared-folder

# Disable Ctrl-S and Ctrl-Q (it pauses terminal)
RUN echo -e "stty stop ''\nstty start ''\nstty -ixon\nstty -ixoff" >> /etc/bash.bashrc

# Done
CMD ["/bin/bash"]