sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2024-12-26 15:04:18 +00:00
Code Issues Projects Releases Wiki Activity

Update

Browse Source
This commit is contained in:
Patrick Jentsch 2018-10-29 10:49:19 +01:00
parent 132490a929
commit c49da3b50a
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
Dockerfile
View File

@ -4,8 +4,6 @@ MAINTAINER Patrick Jentsch <p.jentsch@uni-bielefeld.de>
ENV DEBIAN_FRONTEND=noninteractive ENV DEBIAN_FRONTEND=noninteractive
ENV LANG=C.UTF-8 ENV LANG=C.UTF-8
ENV PYFLOW_VERSION 1.1.20
ENV OCROPY_VERSION 1.3.3
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y --no-install-recommends \ apt-get install -y --no-install-recommends \
@ -23,7 +21,19 @@ RUN apt-get update && \
WORKDIR /root 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 $(cat PACKAGES) python-pil python-tk && \
wget -nv http://www.tmbdev.net/en-default.pyrnn.gz -P models/ && \
python2.7 setup.py install && \
cd ..
# Install pyFlow # Install pyFlow
ENV PYFLOW_VERSION 1.1.20
RUN wget -nv https://github.com/Illumina/pyflow/releases/download/v"$PYFLOW_VERSION"/pyflow-"$PYFLOW_VERSION".tar.gz && \ RUN wget -nv https://github.com/Illumina/pyflow/releases/download/v"$PYFLOW_VERSION"/pyflow-"$PYFLOW_VERSION".tar.gz && \
tar -xzf pyflow-"$PYFLOW_VERSION".tar.gz && \ tar -xzf pyflow-"$PYFLOW_VERSION".tar.gz && \
rm pyflow-"$PYFLOW_VERSION".tar.gz && \ rm pyflow-"$PYFLOW_VERSION".tar.gz && \
@ -43,16 +53,6 @@ RUN echo "deb https://notesalexp.org/tesseract-ocr/stretch/ stretch main" >> /et
wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/fra.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \ wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/fra.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata && \
wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/frm.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata wget -nv https://github.com/tesseract-ocr/tessdata_best/raw/master/frm.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata
# Install ocropy
RUN wget -nv https://github.com/tmbdev/ocropy/archive/v"$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 ..
COPY ocr_pyflow /usr/local/bin COPY ocr_pyflow /usr/local/bin
COPY parse_hocr /usr/local/bin COPY parse_hocr /usr/local/bin