You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
ocrd-galley/Dockerfile-ocrd_tesserocr

31 lines
676 B
Plaintext

ARG GIT_COMMIT="latest"
FROM quratorspk/ocrd-galley-core:$GIT_COMMIT
ARG PIP_INSTALL="pip install --no-cache-dir"
ARG TESSDATA_BEST_VERSION="4.0.0"
ARG OCRD_TESSEROCR_VERSION="0.16.0"
ENV TESSDATA_PREFIX /usr/local/share/tessdata
# Install Leptonica and Tesseract.
RUN add-apt-repository ppa:alex-p/tesseract-ocr && \
apt-get update && \
apt-get install -y \
tesseract-ocr \
libtesseract-dev \
&& \
apt-get clean && rm -rf /var/lib/apt/lists/*
# Build pip installable stuff
RUN ${PIP_INSTALL} \
"ocrd_tesserocr == ${OCRD_TESSEROCR_VERSION}"
# Check pip dependencies
RUN pip check
# Default command
CMD ["ocrd-tesserocr-recognize"]