FROM debian:stretch-slim

MAINTAINER Patrick Jentsch <p.jentsch@uni-bielefeld.de>

ENV LANG=C.UTF-8

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    apt-transport-https \
    ca-certificates \
    gnupg2 \
    pdftk \
    poppler-utils \
    python2.7 \
    python3 \
    wget \
    zip

WORKDIR /root

# Install pyFlow
ENV PYFLOW_VERSION 1.1.20
RUN wget -nv https://github.com/Illumina/pyflow/releases/download/v"$PYFLOW_VERSION"/pyflow-"$PYFLOW_VERSION".tar.gz && \
    tar -xzf pyflow-"$PYFLOW_VERSION".tar.gz && \
    rm pyflow-"$PYFLOW_VERSION".tar.gz && \
    cd pyflow-"$PYFLOW_VERSION" && \
    python2.7 setup.py build install && \
    cd ..

# Install Tesseract OCR and Data Files
RUN echo "deb https://notesalexp.org/tesseract-ocr/stretch/ stretch main" >> /etc/apt/sources.list && \
    wget -O - https://notesalexp.org/debian/alexp_key.asc | apt-key add - && \
    apt-get update && \
    apt-get install -y --no-install-recommends tesseract-ocr && \
    wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/deu.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv https://github.com/tesseract-ocr/tessdata/raw/master/deu_frak.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/eng.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/enm.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/fra.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/frm.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/por.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/spa.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata

RUN mkdir files_for_ocr files_from_ocr

COPY hocrtotei /usr/local/bin
COPY ocr /usr/local/bin

CMD ["/bin/bash"]