compile tesseract in container

This commit is contained in:
Patrick Jentsch
2020-09-21 14:46:03 +02:00
parent 82285a8e6c
commit 7cc8ebd666
3 changed files with 102 additions and 60 deletions

View File

@ -1,73 +1,88 @@
FROM debian:10-slim
LABEL maintainer="inf_sfb1288@lists.uni-bielefeld.de"
LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>, Stephan Porada <sporada@uni-bielefeld.de>"
ENV LANG=C.UTF-8
RUN apt-get update \
RUN apt-get update
## Install pyFlow ##
ENV PYFLOW_RELEASE=1.1.20
ADD "https://github.com/Illumina/pyflow/releases/download/v${PYFLOW_RELEASE}/pyflow-${PYFLOW_RELEASE}.tar.gz" .
RUN tar -xzf "pyflow-${PYFLOW_RELEASE}.tar.gz" \
&& cd "pyflow-${PYFLOW_RELEASE}" \
&& apt-get install -y --no-install-recommends \
apt-transport-https \
build-essential \
ca-certificates \
gnupg2 \
ghostscript \
python2.7 \
python3.7 \
wget \
zip
&& python2.7 setup.py build install \
&& cd .. \
&& rm -r "pyflow-${PYFLOW_RELEASE}" "pyflow-${PYFLOW_RELEASE}.tar.gz"
ENV OCROPY_VERSION 1.3.3
ADD "https://github.com/tmbdev/ocropy/archive/v${OCROPY_VERSION}.tar.gz" .
RUN tar -xzf "v${OCROPY_VERSION}.tar.gz" \
&& cd "ocropy-${OCROPY_VERSION}" \
&& apt-get update \
## Install ocropy ##
ENV OCROPY_RELEASE 1.3.3
ADD "https://github.com/tmbdev/ocropy/archive/v${OCROPY_RELEASE}.tar.gz" .
RUN tar -xzf "v${OCROPY_RELEASE}.tar.gz" \
&& cd "ocropy-${OCROPY_RELEASE}" \
&& apt-get install -y --no-install-recommends \
python-pil \
python-tk \
$(cat PACKAGES) \
&& python2.7 setup.py install \
&& cd .. \
&& rm -rf \
"ocropy-${OCROPY_VERSION}" \
"v${OCROPY_VERSION}.tar.gz"
&& rm -r "ocropy-${OCROPY_RELEASE}" "v${OCROPY_RELEASE}.tar.gz"
ENV PYFLOW_VERSION=1.1.20
ADD "https://github.com/Illumina/pyflow/releases/download/v${PYFLOW_VERSION}/pyflow-${PYFLOW_VERSION}.tar.gz" .
RUN tar -xzf "pyflow-${PYFLOW_VERSION}.tar.gz" \
&& cd "pyflow-${PYFLOW_VERSION}" \
&& python2.7 setup.py build install \
&& cd .. \
&& rm -rf \
"pyflow-${PYFLOW_VERSION}" \
"pyflow-${PYFLOW_VERSION}.tar.gz"
RUN echo "deb https://notesalexp.org/tesseract-ocr/buster/ buster main" >> /etc/apt/sources.list \
&& wget -O - https://notesalexp.org/debian/alexp_key.asc | apt-key add - \
&& apt-get update \
## Install Tesseract OCR ##
ENV TESSERACT_RELEASE=4.1.1
ADD "https://github.com/tesseract-ocr/tesseract/archive/${TESSERACT_RELEASE}.tar.gz" .
RUN tar -xzf "${TESSERACT_RELEASE}.tar.gz" \
&& cd "tesseract-${TESSERACT_RELEASE}" \
&& apt-get install -y --no-install-recommends \
tesseract-ocr \
tesseract-ocr-deu \
tesseract-ocr-eng \
tesseract-ocr-enm \
tesseract-ocr-fra \
tesseract-ocr-frk \
tesseract-ocr-frm \
tesseract-ocr-ita \
tesseract-ocr-por \
tesseract-ocr-spa
autoconf \
automake \
g++ \
libjpeg62-turbo-dev \
libleptonica-dev \
libtiff5-dev \
libtool \
libpng-dev \
make \
pkg-config \
zlib1g-dev \
&& ./autogen.sh \
&& ./configure \
&& make \
&& make install \
&& ldconfig \
&& cd - > /dev/null \
&& rm -r "tesseract-${TESSERACT_RELEASE}" "${TESSERACT_RELEASE}.tar.gz"
ADD "https://github.com/tesseract-ocr/tessdata_best/raw/master/deu.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/eng.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/enm.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/fra.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/frk.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/frm.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/ita.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/por.traineddata" \
"https://github.com/tesseract-ocr/tessdata_best/raw/master/spa.traineddata" \
"/usr/local/share/tessdata/"
RUN chmod 644 /usr/local/share/tessdata/*.traineddata
RUN rm -rf /var/lib/apt/lists/*
## Install Pipeline ##
RUN apt-get install -y --no-install-recommends \
ghostscript \
python3.7 \
zip
COPY "hocrtotei" "ocr" "/usr/local/bin/"
COPY hocrtotei /usr/local/bin
COPY ocr /usr/local/bin
## Cleanup ##
RUN rm -r /var/lib/apt/lists/*
ENTRYPOINT ["ocr"]