Rewrite Dockerfiles to use ubuntu 16.10 base system
Debian now has a few disadvantages: -there is no convenient PPA for Debian tesseract 4.0, but there is for Ubuntu -Ubuntu sets locale to UTF-8 automatically removing the need to do this All three ocrmypdf docker images are now based on a common Ubuntu 16.10 image, derived from the one used to build ocrmypdf-tess4. -polyglot now differs from -tess4 only by opting into the tess4 PPA. Both Ubuntu 16.10 and Debian stretch use tesseract 3.04.01 now making the sharp.ttf patch unnecessary. /etc/apt/sources has been unused for a while now both have newer Ghostscripts.
This commit is contained in:
James R. Barlow
+41
-78
@@ -1,91 +1,54 @@
|
||||
# OCRmyPDF
|
||||
#
|
||||
# VERSION 3.2
|
||||
FROM debian:stretch
|
||||
# VERSION 4.4.2
|
||||
FROM ubuntu:16.10
|
||||
MAINTAINER James R. Barlow <jim@purplerock.ca>
|
||||
|
||||
# Add unprivileged user
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
software-properties-common python-software-properties \
|
||||
python3-wheel \
|
||||
python3-reportlab \
|
||||
python3-venv \
|
||||
ghostscript \
|
||||
qpdf \
|
||||
poppler-utils \
|
||||
unpaper \
|
||||
libffi-dev \
|
||||
tesseract-ocr \
|
||||
tesseract-ocr-eng \
|
||||
tesseract-ocr-fra \
|
||||
tesseract-ocr-spa \
|
||||
tesseract-ocr-deu
|
||||
|
||||
RUN python3 -m venv --system-site-packages /appenv
|
||||
|
||||
# This installs the latest binary wheel instead of the code in the current
|
||||
# folder. Installing from source will fail, apparently because cffi needs
|
||||
# build-essentials (gcc) to do a source installation
|
||||
# (i.e. "pip install ."). It's unclear to me why this is the case.
|
||||
RUN . /appenv/bin/activate; \
|
||||
pip install --upgrade pip \
|
||||
&& pip install ocrmypdf
|
||||
|
||||
# Now copy the application in, mainly to get the test suite.
|
||||
# Do this now to make the best use of Docker cache.
|
||||
COPY . /application
|
||||
RUN . /appenv/bin/activate; \
|
||||
pip install -r /application/test_requirements.txt
|
||||
|
||||
# Remove the junk, including the source version of application since it was
|
||||
# already installed
|
||||
RUN rm -rf /tmp/* /var/tmp/* /root/* /application/ocrmypdf \
|
||||
&& apt-get autoremove -y \
|
||||
&& apt-get autoclean -y
|
||||
|
||||
RUN useradd docker \
|
||||
&& mkdir /home/docker \
|
||||
&& chown docker:docker /home/docker
|
||||
|
||||
# Update system and install our dependencies
|
||||
# If this command takes too Docker hub's automated build will timeout,
|
||||
# so try it in portions
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
locales \
|
||||
python3 \
|
||||
python3-pip \
|
||||
python3-venv \
|
||||
python3-reportlab \
|
||||
python3-pil \
|
||||
python3-wheel
|
||||
|
||||
RUN apt-get install -y --no-install-recommends \
|
||||
unpaper \
|
||||
qpdf \
|
||||
poppler-utils \
|
||||
tesseract-ocr \
|
||||
tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra
|
||||
|
||||
RUN apt-get install -qy --no-install-recommends \
|
||||
libffi-dev \
|
||||
libpython3-dev \
|
||||
gcc
|
||||
|
||||
# Install Ghostscript from Debian sid to work around JPEG 2000 issue in
|
||||
# Debian stretch libgs9 or gs 9.16~dfsg-2.1
|
||||
|
||||
COPY ./share/etc-apt-sources.list /etc/apt/sources.list
|
||||
|
||||
RUN apt-get update && apt-get install -y ghostscript/sid
|
||||
|
||||
|
||||
# Enforce UTF-8
|
||||
# Borrowed from https://index.docker.io/u/crosbymichael/python/
|
||||
RUN dpkg-reconfigure locales && \
|
||||
locale-gen C.UTF-8 && \
|
||||
/usr/sbin/update-locale LANG=C.UTF-8
|
||||
ENV LC_ALL C.UTF-8
|
||||
|
||||
|
||||
# Set up a Python virtualenv and take all of the system packages, so we can
|
||||
# rely on the platform packages rather than importing GCC and compiling them
|
||||
RUN pyvenv /appenv \
|
||||
&& pyvenv --system-site-packages /appenv
|
||||
|
||||
COPY . /application/
|
||||
|
||||
# Replace stock Tesseract 3.04.00 font with improved sharp2.ttf that resolves
|
||||
# issues in many PDF viewers.
|
||||
# Discussion is in https://github.com/tesseract-ocr/tesseract/issues/182
|
||||
COPY ./share/sharp2.ttf /usr/share/tesseract-ocr/tessdata/pdf.ttf
|
||||
RUN chmod 644 /usr/share/tesseract-ocr/tessdata/pdf.ttf
|
||||
|
||||
# Set this here to force a docker version, allowing non-tagged versions to
|
||||
# be built
|
||||
# ENV SETUPTOOLS_SCM_PRETEND_VERSION=v3.3.0
|
||||
|
||||
# Install application and dependencies
|
||||
# In this arrangement Pillow and reportlab will be provided by the system
|
||||
# Even though ocrmypdf is locally present, pull from PyPI because
|
||||
# Dockerhub and setuptools_scm clash
|
||||
RUN . /appenv/bin/activate; \
|
||||
pip install --upgrade pip \
|
||||
&& pip install ocrmypdf \
|
||||
&& pip install --no-cache-dir -r /application/test_requirements.txt
|
||||
|
||||
# Remove the junk
|
||||
RUN apt-get remove -qy gcc
|
||||
RUN apt-get autoremove -y && apt-get clean -y
|
||||
RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/*
|
||||
|
||||
USER docker
|
||||
WORKDIR /home/docker
|
||||
|
||||
ENV OCRMYPDF_TEST_OUTPUT=/tmp/test-output
|
||||
ENV OCRMYPDF_SHARP_TTF=1
|
||||
|
||||
# Must use array form of ENTRYPOINT
|
||||
# Non-array form does not append other arguments, because that is "intuitive"
|
||||
ENTRYPOINT ["/application/docker-wrapper.sh"]
|
||||
ENTRYPOINT ["/application/docker-wrapper.sh"]
|
||||
|
||||
+5
-2
@@ -1,14 +1,17 @@
|
||||
# OCRmyPDF polyglot
|
||||
#
|
||||
# VERSION 3.2
|
||||
# VERSION 4.4.2
|
||||
FROM jbarlow83/ocrmypdf:latest
|
||||
MAINTAINER James R. Barlow <jim@purplerock.ca>
|
||||
|
||||
# Update system and install our dependencies
|
||||
USER root
|
||||
|
||||
# Update system and install our dependencies
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
tesseract-ocr-all
|
||||
|
||||
RUN apt-get autoremove -y && apt-get clean -y
|
||||
|
||||
USER docker
|
||||
|
||||
# Must use array form of ENTRYPOINT
|
||||
|
||||
+4
-30
@@ -1,46 +1,20 @@
|
||||
# OCRmyPDF
|
||||
#
|
||||
# VERSION 4.4.1
|
||||
FROM ubuntu:16.10
|
||||
# VERSION 4.4.2
|
||||
FROM jbarlow83/ocrmypdf:latest
|
||||
MAINTAINER James R. Barlow <jim@purplerock.ca>
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
software-properties-common python-software-properties \
|
||||
python3-wheel \
|
||||
python3-reportlab \
|
||||
python3-venv \
|
||||
ghostscript \
|
||||
qpdf \
|
||||
poppler-utils \
|
||||
unpaper \
|
||||
libffi-dev
|
||||
USER root
|
||||
|
||||
RUN add-apt-repository ppa:alex-p/tesseract-ocr
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
tesseract-ocr-all
|
||||
|
||||
RUN python3 -m venv --system-site-packages /appenv
|
||||
|
||||
COPY . /application
|
||||
|
||||
# This installs the latest binary wheel instead of the code in the current
|
||||
# folder. cffi needs gcc otherwise.
|
||||
RUN . /appenv/bin/activate; \
|
||||
pip install --upgrade pip \
|
||||
&& pip install ocrmypdf \
|
||||
&& pip install -r /application/test_requirements.txt
|
||||
|
||||
# Remove the junk, including the source version of application
|
||||
RUN apt-get autoremove -y && apt-get clean -y
|
||||
RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/* /application/ocrmypdf
|
||||
|
||||
RUN useradd docker \
|
||||
&& mkdir /home/docker \
|
||||
&& chown docker:docker /home/docker
|
||||
|
||||
USER docker
|
||||
WORKDIR /home/docker
|
||||
|
||||
|
||||
# Must use array form of ENTRYPOINT
|
||||
# Non-array form does not append other arguments, because that is "intuitive"
|
||||
|
||||
@@ -36,7 +36,6 @@ recursive-exclude docs/_build *
|
||||
|
||||
# support files
|
||||
recursive-include ocrmypdf/data *
|
||||
recursive-include share *
|
||||
include *.py
|
||||
exclude tasks.py
|
||||
|
||||
|
||||
@@ -1,4 +0,0 @@
|
||||
deb http://httpredir.debian.org/debian stretch main
|
||||
deb http://httpredir.debian.org/debian stretch-updates main
|
||||
deb http://security.debian.org stretch/updates main
|
||||
deb http://ftp.de.debian.org/debian sid main contrib non-free
|
||||
Binary file not shown.
Reference in New Issue
Block a user