FROM ubuntu:18.04

ENV LANG C.UTF-8  
ENV LC_ALL C.UTF-8 

RUN apt-get update && apt-get install -y software-properties-common && add-apt-repository -y ppa:alex-p/tesseract-ocr
RUN apt-get update && apt-get install -y \
    imagemagick \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-nor

COPY ocr.sh /bin/ocr.sh
RUN chmod +x /bin/ocr.sh

ENTRYPOINT ["tesseract"]