mirror of
https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git
synced 2025-07-01 09:50:34 +00:00
First work on version 1.0.0
This commit is contained in:
42
Dockerfile
42
Dockerfile
@ -1,7 +1,7 @@
|
||||
FROM debian:buster-slim
|
||||
|
||||
|
||||
LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>, Stephan Porada <sporada@uni-bielefeld.de>"
|
||||
LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>"
|
||||
|
||||
|
||||
ENV LANG=C.UTF-8
|
||||
@ -16,26 +16,22 @@ 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 update \
|
||||
&& apt-get install --no-install-recommends --yes \
|
||||
python2.7 \
|
||||
&& rm -r /var/lib/apt/lists/* \
|
||||
&& python2.7 setup.py build install \
|
||||
&& cd .. \
|
||||
&& rm -r "pyflow-${PYFLOW_RELEASE}" "pyflow-${PYFLOW_RELEASE}.tar.gz"
|
||||
|
||||
|
||||
## Install ocropy ##
|
||||
ENV OCROPY_RELEASE 1.3.3
|
||||
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 update \
|
||||
&& apt-get install --no-install-recommends --yes \
|
||||
python-pil \
|
||||
python-tk \
|
||||
$(cat PACKAGES) \
|
||||
&& rm -r /var/lib/apt/lists/* \
|
||||
&& python2.7 setup.py install \
|
||||
&& cd .. \
|
||||
&& rm -r "ocropy-${OCROPY_RELEASE}" "v${OCROPY_RELEASE}.tar.gz"
|
||||
@ -46,7 +42,6 @@ ENV TESSERACT_RELEASE=4.1.1
|
||||
ADD "https://github.com/tesseract-ocr/tesseract/archive/${TESSERACT_RELEASE}.tar.gz" .
|
||||
RUN tar -xzf "${TESSERACT_RELEASE}.tar.gz" \
|
||||
&& cd "tesseract-${TESSERACT_RELEASE}" \
|
||||
&& apt-get update \
|
||||
&& apt-get install --no-install-recommends --yes \
|
||||
autoconf \
|
||||
automake \
|
||||
@ -59,7 +54,6 @@ RUN tar -xzf "${TESSERACT_RELEASE}.tar.gz" \
|
||||
make \
|
||||
pkg-config \
|
||||
zlib1g-dev \
|
||||
&& rm -r /var/lib/apt/lists/* \
|
||||
&& ./autogen.sh \
|
||||
&& ./configure \
|
||||
&& make \
|
||||
@ -67,30 +61,34 @@ RUN tar -xzf "${TESSERACT_RELEASE}.tar.gz" \
|
||||
&& 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
|
||||
|
||||
ENV TESSDATA_BEST_RELEASE=4.1.0
|
||||
ADD "https://github.com/tesseract-ocr/tessdata_best/archive/${TESSDATA_BEST_RELEASE}.tar.gz" .
|
||||
RUN tar -xzf "${TESSDATA_BEST_RELEASE}.tar.gz" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/deu.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/eng.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/enm.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/fra.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/frk.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/frm.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/ita.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/por.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& mv "tessdata_best-${TESSDATA_BEST_RELEASE}/spa.traineddata" "/usr/local/share/tessdata/" \
|
||||
&& rm -r "tessdata_best-${TESSDATA_BEST_RELEASE}" "${TESSDATA_BEST_RELEASE}.tar.gz"
|
||||
|
||||
|
||||
## Further dependencies ##
|
||||
RUN apt-get update \
|
||||
&& apt-get install --no-install-recommends --yes \
|
||||
RUN apt-get install --no-install-recommends --yes \
|
||||
ghostscript \
|
||||
python-pip \
|
||||
python3.7 \
|
||||
zip \
|
||||
&& rm -r /var/lib/apt/lists/* \
|
||||
&& pip install natsort
|
||||
|
||||
|
||||
RUN rm -r /var/lib/apt/lists/*
|
||||
|
||||
|
||||
## Install Pipeline ##
|
||||
COPY hocrtotei ocr /usr/local/bin/
|
||||
|
||||
|
Reference in New Issue
Block a user