FROM ubuntu:18.04

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

ENV DEBIAN_FRONTEND=noninteractive
ENV LANG=en_US.UTF-8
ENV PYFLOW_VERSION 1.1.20

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    gnupg2

# Add PPA for pdftk
RUN echo "deb http://ppa.launchpad.net/malteworld/ppa/ubuntu bionic main" >> /etc/apt/sources.list && \
    echo "deb-src http://ppa.launchpad.net/malteworld/ppa/ubuntu bionic main" >> /etc/apt/sources.list && \
    apt-key adv --keyserver keyserver.ubuntu.com --recv-keys BCA68C33DA36783B03E981C820D0BB61B700CE29

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    ghostscript \
    git \
    imagemagick \
    libtiff-tools \
    locales \
    pdftk \
    poppler-utils \
    python2.7 \
    python3.6 \
    python-pip \
    python-tk \
    tesseract-ocr \
    wget

# Configure locales
RUN locale-gen "$LANG"

WORKDIR /root

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

# Install Tesseract OCR Data Files
RUN wget -nv http://github.com/tesseract-ocr/tessdata_best/raw/master/deu.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv http://github.com/tesseract-ocr/tessdata/raw/3.04.00/deu_frak.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv http://github.com/tesseract-ocr/tessdata_best/raw/master/eng.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv http://github.com/tesseract-ocr/tessdata_best/raw/master/enm.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv http://github.com/tesseract-ocr/tessdata_best/raw/master/fra.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
    wget -nv http://github.com/tesseract-ocr/tessdata_best/raw/master/frm.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata

# Install OCRopus
RUN git clone http://github.com/tmbdev/ocropy && \
    cd ocropy && \
    apt-get install -y --no-install-recommends $(cat PACKAGES) && \
    pip install -r requirements.txt && \
    wget -nv http://www.tmbdev.net/en-default.pyrnn.gz && \
    mv en-default.pyrnn.gz models/ && \
    python2.7 setup.py install && \
    cd /root

COPY ocr_pyflow /usr/local/bin
COPY parse_hocr /usr/local/bin

VOLUME /root/files_for_ocr

CMD ["/bin/bash"]