79 lines
1.8 KiB
Docker
79 lines
1.8 KiB
Docker
# SPDX-FileCopyrightText: 2022 James R. Barlow
|
|
# SPDX-License-Identifier: MPL-2.0
|
|
|
|
FROM ubuntu:22.04 as base
|
|
|
|
ENV LANG=C.UTF-8
|
|
ENV TZ=UTC
|
|
RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
python3 \
|
|
libqpdf-dev \
|
|
zlib1g \
|
|
liblept5
|
|
|
|
# FROM base as builder
|
|
|
|
# # Note we need leptonica here to build jbig2
|
|
# RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
# build-essential autoconf automake libtool \
|
|
# python3-dev \
|
|
# python3-distutils \
|
|
# libffi-dev \
|
|
# ca-certificates \
|
|
# curl \
|
|
# git \
|
|
# libcairo2-dev \
|
|
# pkg-config
|
|
|
|
# # Get the latest pip
|
|
# RUN \
|
|
# curl https://bootstrap.pypa.io/get-pip.py | python3
|
|
|
|
# COPY . /app
|
|
|
|
# WORKDIR /app
|
|
|
|
# RUN pip3 install --no-cache-dir .[test,webservice,watcher]
|
|
|
|
FROM base
|
|
|
|
# For Tesseract 5
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
software-properties-common gpg-agent
|
|
RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
|
|
RUN add-apt-repository -y ppa:alex-p/jbig2enc
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
ghostscript \
|
|
fonts-droid-fallback \
|
|
jbig2dec \
|
|
jbig2enc \
|
|
img2pdf \
|
|
libsm6 libxext6 libxrender-dev \
|
|
pngquant \
|
|
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/pyproject.toml /app/README.md /app/
|
|
COPY --from=builder /app/tests /app/tests
|
|
|
|
ENTRYPOINT ["/usr/local/bin/ocrmypdf"]
|