sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2025-07-01 10:30:36 +00:00
Code Issues Projects Releases Wiki Activity

Correct order for output files.

Browse Source
This commit is contained in:
Patrick Jentsch
2019-05-13 15:03:43 +02:00
parent 937abb8c8d
commit 843151e547
3 changed files with 174 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
Dockerfile
View File

@ -1,6 +1,6 @@
FROM debian:stretch-slim
MAINTAINER Patrick Jentsch <p.jentsch@uni-bielefeld.de>
LABEL maintainer="inf_sfb1288@lists.uni-bielefeld.de"
ENV DEBIAN_FRONTEND=noninteractive
ENV LANG=C.UTF-8
@ -11,34 +11,31 @@ RUN apt-get update && \
ca-certificates \
gnupg2 \
imagemagick \
pdftk \
poppler-utils \
python2.7 \
python3.5 \
python-numpy \
wget
WORKDIR /root
# Install ocropy
ENV OCROPY_VERSION 1.3.3
RUN wget -nv https://github.com/tmbdev/ocropy/archive/v"$OCROPY_VERSION".tar.gz && \
tar -xzf v"$OCROPY_VERSION".tar.gz && \
rm v"$OCROPY_VERSION".tar.gz && \
cd ocropy-"$OCROPY_VERSION" && \
apt-get install -y --no-install-recommends $(cat PACKAGES) python-pil python-tk && \
wget -nv http://www.tmbdev.net/en-default.pyrnn.gz -P models/ && \
python2.7 setup.py install && \
cd ..
cd .. && \
rm -r v"$OCROPY_VERSION".tar.gz ocropy-"$OCROPY_VERSION"
# Install pyFlow
ENV PYFLOW_VERSION 1.1.20
RUN wget -nv https://github.com/Illumina/pyflow/releases/download/v"$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 ..
cd .. && \
rm -r pyflow-"$PYFLOW_VERSION".tar.gz pyflow-"$PYFLOW_VERSION"
# Install Tesseract OCR and Data Files
RUN echo "deb https://notesalexp.org/tesseract-ocr/stretch/ stretch main" >> /etc/apt/sources.list && \
@ -52,11 +49,12 @@ RUN echo "deb https://notesalexp.org/tesseract-ocr/stretch/ stretch main" >> /et
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/ita.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
COPY ocr /usr/local/bin
COPY hocrtotei /usr/local/bin
COPY ocr /usr/local/bin
CMD ["/bin/bash"]
ENTRYPOINT ["ocr"]
CMD ["--help"]