andkrauseandJames R. Barlow
e1f4813d94
Thanks to @andkrause for submitting the initial PR that made this change possible, @0x326 for review comments on the same PR, and both for their patience in waiting for the rest of OCRmyPDF to catch up. Co-authored-by: James R. Barlow Closes #564
85 lines
1.8 KiB
Docker
85 lines
1.8 KiB
Docker
# OCRmyPDF
|
|
#
|
|
FROM ubuntu:20.04 as base
|
|
|
|
FROM base as builder
|
|
|
|
ENV LANG=C.UTF-8
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
build-essential autoconf automake libtool \
|
|
libleptonica-dev \
|
|
zlib1g-dev \
|
|
python3-dev \
|
|
python3-distutils \
|
|
libffi-dev \
|
|
libqpdf-dev \
|
|
ca-certificates \
|
|
curl \
|
|
git
|
|
|
|
# Get the latest pip (Ubuntu version doesn't support manylinux2010)
|
|
RUN \
|
|
curl https://bootstrap.pypa.io/get-pip.py | python3
|
|
|
|
# Compile and install jbig2
|
|
# Needs libleptonica-dev, zlib1g-dev
|
|
RUN \
|
|
mkdir jbig2 \
|
|
&& curl -L https://github.com/agl/jbig2enc/archive/ea6a40a.tar.gz | \
|
|
tar xz -C jbig2 --strip-components=1 \
|
|
&& cd jbig2 \
|
|
&& ./autogen.sh && ./configure && make && make install \
|
|
&& cd .. \
|
|
&& rm -rf jbig2
|
|
|
|
COPY . /app
|
|
|
|
WORKDIR /app
|
|
|
|
RUN pip3 install --no-cache-dir \
|
|
-r requirements/main.txt \
|
|
-r requirements/webservice.txt \
|
|
-r requirements/test.txt \
|
|
-r requirements/watcher.txt \
|
|
.
|
|
|
|
FROM base
|
|
|
|
ENV LANG=C.UTF-8
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
ghostscript \
|
|
img2pdf \
|
|
liblept5 \
|
|
libsm6 libxext6 libxrender-dev \
|
|
zlib1g \
|
|
pngquant \
|
|
python3 \
|
|
qpdf \
|
|
tesseract-ocr \
|
|
tesseract-ocr-chi-sim \
|
|
tesseract-ocr-deu \
|
|
tesseract-ocr-eng \
|
|
tesseract-ocr-fra \
|
|
tesseract-ocr-por \
|
|
tesseract-ocr-spa \
|
|
unpaper \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
WORKDIR /app
|
|
|
|
COPY --from=builder /usr/local/lib/ /usr/local/lib/
|
|
COPY --from=builder /usr/local/bin/ /usr/local/bin/
|
|
|
|
COPY --from=builder /app/misc/webservice.py /app/
|
|
COPY --from=builder /app/misc/watcher.py /app/
|
|
|
|
# Copy minimal project files to get the test suite.
|
|
COPY --from=builder /app/setup.cfg /app/setup.py /app/README.md /app/
|
|
COPY --from=builder /app/requirements /app/requirements
|
|
COPY --from=builder /app/tests /app/tests
|
|
COPY --from=builder /app/src /app/src
|
|
|
|
ENTRYPOINT ["/usr/local/bin/ocrmypdf"]
|