menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'feature/docker-ubuntu-24'

Browse Source
This commit is contained in:
James R. Barlow
2024-10-27 17:39:06 -07:00
parent 6c6cbfd4d6 92c5200ad2
commit bf62562787
7 changed files with 91 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.docker/Dockerfile
+17 -26
View File
@@ -1,7 +1,7 @@
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-FileCopyrightText: 2024 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
FROM ubuntu:22.04 as base
FROM ubuntu:24.04 AS base
ENV LANG=C.UTF-8
ENV TZ=UTC
@@ -9,19 +9,15 @@ RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selectio
RUN apt-get update && apt-get install -y --no-install-recommends \
python3 \
libqpdf-dev \
zlib1g \
liblept5
python-is-python3
FROM base as builder
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 \
libleptonica-dev \
zlib1g-dev \
python3-dev \
python3-distutils \
libffi-dev \
ca-certificates \
curl \
@@ -29,15 +25,11 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
libcairo2-dev \
pkg-config
# 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 | \
&& curl -L https://github.com/agl/jbig2enc/archive/c0141bf.tar.gz | \
tar xz -C jbig2 --strip-components=1 \
&& cd jbig2 \
&& ./autogen.sh && ./configure && make && make install \
@@ -48,23 +40,24 @@ COPY . /app
WORKDIR /app
RUN pip3 install --no-cache-dir .[test,webservice,watcher]
RUN curl -LsSf https://astral.sh/uv/0.4.27/install.sh | sh
ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
# Instead of restarting the shell, use uv directly from its installed location.
RUN /root/.cargo/bin/uv sync --extra test --extra webservice --extra watcher
FROM base
# For Tesseract 5
RUN apt-get update && apt-get install -y --no-install-recommends \
software-properties-common gpg-agent
RUN apt-get update && apt-get install -y software-properties-common
RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
RUN apt-get update && apt-get install -y --no-install-recommends \
ghostscript \
fonts-droid-fallback \
jbig2dec \
img2pdf \
libsm6 libxext6 libxrender-dev \
pngquant \
python-is-python3 \
tesseract-ocr \
tesseract-ocr-chi-sim \
tesseract-ocr-deu \
@@ -80,11 +73,9 @@ 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 --from=builder --chown=app:app /app /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
ENV PATH="/app/.venv/bin:${PATH}"
ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]
ENTRYPOINT ["/usr/local/bin/ocrmypdf"]
.docker/Dockerfile.alpine
+9 -35
View File
@@ -8,7 +8,7 @@
# Details
# https://gitlab.alpinelinux.org/alpine/aports/-/issues/16143
# https://github.com/ocrmypdf/OCRmyPDF/issues/1395
FROM alpine:3.19 as base
FROM alpine:3.19 AS base
ENV LANG=C.UTF-8
ENV TZ=UTC
@@ -17,40 +17,24 @@ RUN apk add --no-cache \
python3 \
zlib
FROM base as builder
FROM base AS builder
RUN apk add --no-cache \
ca-certificates \
git \
python3-dev \
py3-pip
# On arm64, we need to build cffi from source.
ARG TARGETPLATFORM
RUN if [ "${TARGETPLATFORM}" == "linux/arm64" ]; then \
apk add --no-cache \
build-base \
autoconf \
automake \
libtool \
zlib-dev \
libffi-dev \
cairo-dev \
pkgconfig \
; \
fi
curl
COPY . /app
WORKDIR /app
RUN python3 -m venv .venv
RUN curl -LsSf https://astral.sh/uv/0.4.27/install.sh | sh
RUN source .venv/bin/activate \
&& python3 -m pip install --no-cache-dir --upgrade pip \
&& python3 -m pip install --no-cache-dir wheel \
&& python3 -m pip install --no-cache-dir .[test,webservice,watcher]
ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
# Instead of restarting the shell, use uv directly from its installed location.
RUN /root/.cargo/bin/uv sync --extra test --extra webservice --extra watcher
FROM base
@@ -73,17 +57,7 @@ RUN apk add --no-cache \
WORKDIR /app
COPY --from=builder /usr/local/lib/ /usr/local/lib/
COPY --from=builder /usr/local/bin/ /usr/local/bin/
COPY --from=builder /app/.venv/ /app/.venv/
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
COPY --from=builder --chown=app:app /app /app
ENV PATH="/app/.venv/bin:${PATH}"
.github/workflows/build.yml
+41 -45
View File
@@ -19,26 +19,16 @@ jobs:
test_linux:
name: Test ${{ matrix.os }} with Python ${{ matrix.python }}
runs-on: ${{ matrix.os }}
continue-on-error: ${{ matrix.experimental }}
strategy:
matrix:
experimental: [false]
os: [ubuntu-22.04, ubuntu-24.04]
python: ["3.10", "3.11", "3.12", "3.13"]
include:
- os: ubuntu-22.04
tesseract_ppa: "ppa"
python: "3.10"
- os: ubuntu-22.04
python: "3.11"
- os: ubuntu-22.04
python: "3.10"
tesseract5: true
- os: ubuntu-latest
python: "3.12"
tesseract5: true
- os: ubuntu-latest
- os: ubuntu-24.04
python: "pypy3.10"
- os: ubuntu-22.04
python: "3.13"
experimental: true
env:
OS: ${{ matrix.os }}
@@ -49,15 +39,18 @@ jobs:
with:
fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
- uses: actions/setup-python@v5
name: Setup Python
- name: Install uv
uses: astral-sh/setup-uv@v3
with:
version: "0.4.27"
- name: "Set up Python"
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python }}
cache: "pip"
allow-prereleases: ${{ matrix.experimental }}
- name: Install Tesseract 5
if: matrix.tesseract5
- name: Install Tesseract from PPA
if: matrix.tesseract_ppa
run: |
sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
@@ -91,8 +84,7 @@ jobs:
- name: Install Python packages
run: |
python -m pip install --upgrade pip wheel
python -m pip install --prefer-binary .[test]
uv sync --extra test
- name: Report versions
run: |
@@ -100,11 +92,11 @@ jobs:
gs --version
pngquant --version
unpaper --version
img2pdf --version
uv run img2pdf --version
- name: Test
run: |
python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
uv run pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
@@ -121,7 +113,7 @@ jobs:
strategy:
matrix:
os: [macos-latest, macos-13] # macos-latest is arm64, macos-13 is x86_64
python: ["3.10", "3.11", "3.12"]
python: ["3.10", "3.11", "3.12", "3.13"]
env:
OS: ${{ matrix.os }}
@@ -144,27 +136,30 @@ jobs:
pngquant \
tesseract
- uses: actions/setup-python@v5
name: Setup Python
- name: Install uv
uses: astral-sh/setup-uv@v3
with:
version: "0.4.27"
- name: "Set up Python"
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python }}
cache: "pip"
- name: Install Python packages
run: |
python -m pip install --upgrade pip wheel
python -m pip install --prefer-binary .[test]
uv sync --extra test
- name: Report versions
run: |
tesseract --version
gs --version
pngquant --version
img2pdf --version
uv run img2pdf --version
- name: Test
run: |
python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
uv run pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
@@ -180,7 +175,7 @@ jobs:
strategy:
matrix:
os: [windows-latest]
python: ["3.10", "3.11", "3.12"]
python: ["3.10", "3.11", "3.12", "3.13"]
env:
OS: ${{ matrix.os }}
@@ -191,11 +186,15 @@ jobs:
with:
fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
- uses: actions/setup-python@v5
name: Setup Python
- name: Install uv
uses: astral-sh/setup-uv@v3
with:
version: "0.4.27"
- name: "Set up Python"
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python }}
cache: "pip"
- name: Install system packages
run: |
@@ -204,12 +203,11 @@ jobs:
- name: Install Python packages
run: |
python -m pip install --upgrade pip wheel
python -m pip install --prefer-binary .[test]
uv sync --extra test
- name: Test
run: |
python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
uv run pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
@@ -227,16 +225,14 @@ jobs:
with:
fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
- uses: actions/setup-python@v5
name: Setup Python
- name: Install uv
uses: astral-sh/setup-uv@v3
with:
python-version: "3.10"
cache: "pip"
version: "0.4.27"
- name: Make wheels and sdist
run: |
python -m pip install --upgrade pip wheel build
python -m build --sdist --wheel
uv build --sdist --wheel
- uses: actions/upload-artifact@v4
with:
docs/docker.rst
+7 -1
View File
@@ -65,7 +65,13 @@ The ``ocrmypdf`` image is also available, but is deprecated and will be removed
in the future.
OCRmyPDF will use all available CPU cores. See the Docker documentation for
`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__
if you are using Docker on macOS or Windows, where you may need to manually assign
more resources. On Linux, all resources will be available automatically.
The underlying operating system and other details in Docker images are subject
to change at minor releases. If you are modifying the image, you should pin
the version you intend to use.
Using the Docker image on the command line
==========================================
docs/release_notes.rst
+12
View File
@@ -30,6 +30,18 @@ OCRmyPDF typically supports the three most recent Python versions.
.. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
v16.6.0
=======
- Fixed Alpine Docker image by enforcing Alpine 3.19. Alpine 3.20 includes a
defective version of Tesseract OCR and so is not usable.
- Upgraded Ubuntu Docker image to use Ubuntu 24.04.
- Build and test scripts/actions switched to uv.
- When running in a container, we now remind the user that temporary folders
are inside the container and may not be accessible.
- Fixed an error detecting the version of unpaper 7.0.0.
- Fixed Linux test coverage matrix, which was missing some key versions.
v16.5.0
=======
src/ocrmypdf/_exec/unpaper.py
+1 -1
View File
@@ -48,7 +48,7 @@ class UnpaperImageTooLargeError(Exception):
def version() -> Version:
return Version(get_version('unpaper', regex=r'(?m).*(\d+(\.\d+)(\.\d+)?)'))
return Version(get_version('unpaper', regex=r'(?m).*?(\d+(\.\d+)(\.\d+)?)'))
@contextmanager
src/ocrmypdf/subprocess/__init__.py
+4 -2
View File
@@ -215,8 +215,10 @@ to have {found_version}. Please update this program.
OLD_VERSION_REQUIRED_FOR = '''
OCRmyPDF requires '{program}' {need_version} or higher when run with the
{required_for} arguments. If you omit these arguments, OCRmyPDF may be able to
proceed. For best results, install the program.
{required_for} arguments. {program} {found_version} is installed.
If you omit these arguments, OCRmyPDF may be able to
proceed. For best results, update the program.
'''
OSX_INSTALL_ADVICE = '''