Merge pull request #70 from bertsky/add-docker

add Docker and GHA CD via Dockerhub

.circleci/config.yml

@@ -19,6 +19,7 @@ jobs:
           paths:
             ocrd-resources
       - run: make test
+    resource_class: large
 
 
 workflows:
@@ -27,5 +28,5 @@ workflows:
       - build-python:
           matrix:
             parameters:
-              python-version: ['3.7', '3.8', '3.9', '3.10']
+              python-version: ['3.8', '3.9', '3.10', '3.11']
 

.github/workflows/docker-image.yml

@@ -0,0 +1,47 @@
+name: Docker Image CD
+
+on:
+  push:
+    branches: [ "master" ]
+  workflow_dispatch:
+    inputs:
+      docker-tagname:
+        description: Tag name of the Docker image
+        default: 'ocrd/sbb_binarization'
+
+env:
+  DOCKER_TAGNAME: ${{ github.evenv.inputs.docker-tagname || 'ocrd/sbb_binarization' }}
+
+jobs:
+
+  build:
+
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+
+    steps:
+    - uses: actions/checkout@v4
+    - # Activate cache export feature to reduce build time of image
+      name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
+    - name: Build the Docker image
+      run: make docker DOCKER_TAG=${{ env.DOCKER_TAGNAME }}
+    - name: Login to Dockerhub
+      uses: docker/login-action@v2
+      with:
+        username: ${{ secrets.DOCKERHUB_USERNAME }}
+        password: ${{ secrets.DOCKERHUB_PASSWORD }}
+    - name: Push image to Dockerhub
+      run: docker push ${{ env.DOCKER_TAGNAME }}
+    - name: Alias the Docker image for GHCR
+      run: docker tag ${{ env.DOCKER_TAGNAME }} ghcr.io/${{ github.repository }}
+    - name: Login to GitHub Container Registry
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+    - name: Push image to Github Container Registry
+      run: docker push ghcr.io/${{ github.repository }}

.github/workflows/test.yml

@@ -3,7 +3,10 @@
 
 name: CLI Tests
 
-on: [push, pull_request]
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
 
 jobs:
   build:
@@ -11,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10']
+        python-version: ['3.8', '3.9', '3.10']
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python

Dockerfile

@@ -0,0 +1,22 @@
+ARG DOCKER_BASE_IMAGE
+FROM $DOCKER_BASE_IMAGE
+ARG VCS_REF
+ARG BUILD_DATE
+LABEL \
+    maintainer="https://ocr-d.de/kontakt" \
+    org.label-schema.vcs-ref=$VCS_REF \
+    org.label-schema.vcs-url="https://github.com/qurator-spk/sbb_binarization" \
+    org.label-schema.build-date=$BUILD_DATE
+
+WORKDIR /build/sbb_binarization
+COPY pyproject.toml .
+COPY ocrd-tool.json .
+COPY sbb_binarize ./sbb_binarize
+COPY requirements.txt .
+COPY README.md .
+COPY Makefile .
+RUN make install
+RUN rm -rf /build/sbb_binarization
+
+WORKDIR /data
+VOLUME ["/data"]

Makefile

@@ -1,5 +1,9 @@
 # BEGIN-EVAL makefile-parser --make-help Makefile
 
+# should really be core-cuda-tf2, but not as long as we must restrict TF2 minor version
+DOCKER_BASE_IMAGE = docker.io/ocrd/core-cuda:v2.69.0
+DOCKER_TAG = ocrd/sbb_binarization
+
 .PHONY: help install
 help:
 	@echo ""
@@ -10,13 +14,18 @@ help:
 	@echo "    test     Run tests"
 	@echo "    clean    Remove copies/results in test/assets"
 	@echo ""
+	@echo "    docker  Build a Docker image $(DOCKER_TAG) from $(DOCKER_BASE_IMAGE)"
+	@echo ""
 	@echo "  Variables"
 	@echo ""
+	@echo "    PYTHON"
+	@echo "    DOCKER_TAG    Docker image tag of result for the docker target"
 
 # END-EVAL
 
 # Install with pip
 install:
+	pip install -U setuptools pip
 	pip install .
 
 # Downloads the pre-trained models from qurator-data.de
@@ -40,6 +49,15 @@ test: test/assets models
 	ocrd-sbb-binarize -m test/assets/kant_aufklaerung_1784-page-region/data/mets.xml -g phys_0001 -I OCR-D-GT-SEG-REGION -O BIN -P model default -P operation_level region
 	ocrd-sbb-binarize -m test/assets/kant_aufklaerung_1784-page-region/data/mets.xml -g phys_0001 -I OCR-D-GT-SEG-REGION -O BIN2 -P model default-2021-03-09 -P operation_level region
 
+.PHONY: docker
+docker:
+	docker build \
+	--build-arg DOCKER_BASE_IMAGE=$(DOCKER_BASE_IMAGE) \
+	--build-arg VCS_REF=$$(git rev-parse --short HEAD) \
+	--build-arg BUILD_DATE=$$(date -u +"%Y-%m-%dT%H:%M:%SZ") \
+	-t $(DOCKER_TAG) .
+
+
 .PHONY: clean
 clean:
 	-$(RM) -fr test/assets

README.md

@@ -3,7 +3,8 @@
 > Document Image Binarization
 
 [![pip release](https://img.shields.io/pypi/v/sbb-binarization.svg)](https://pypi.org/project/sbb-binarization/)
-[![GHActions Tests](https://github.com/qurator-spk/sbb_binarization/actions/workflows/test.yml/badge.svg)](https://github.com/qurator-spk/sbb_binarization/actions/workflows/test.yml)
+[![GHActions CI](https://github.com/qurator-spk/sbb_binarization/actions/workflows/test.yml/badge.svg)](https://github.com/qurator-spk/sbb_binarization/actions/workflows/test.yml)
+[![GHActions CD](https://github.com/qurator-spk/sbb_binarization/actions/workflows/docker-image.yml/badge.svg)](https://github.com/qurator-spk/sbb_binarization/actions/workflows/docker-image.yml)
 
 <img src="https://user-images.githubusercontent.com/952378/63592437-e433e400-c5b1-11e9-9c2d-889c6e93d748.jpg" width="180"><img src="https://user-images.githubusercontent.com/952378/63592435-e433e400-c5b1-11e9-88e4-3e441b61fa67.jpg" width="180"><img src="https://user-images.githubusercontent.com/952378/63592440-e4cc7a80-c5b1-11e9-8964-2cd1b22c87be.jpg" width="220"><img src="https://user-images.githubusercontent.com/952378/63592438-e4cc7a80-c5b1-11e9-86dc-a9e9f8555422.jpg" width="220">
 
@@ -13,16 +14,19 @@ Python `3.7-3.10` with Tensorflow `<=2.11.1` are currently supported. While newe
 
 You can either install from PyPI via 
 
-```
     pip install sbb-binarization
-```
+
 
 or clone the repository, enter it and install (editable) with
 
-```
     git clone git@github.com:qurator-spk/sbb_binarization.git
     cd sbb_binarization; pip install -e .
-```
+
+
+Alternatively, download the prebuilt image from Dockerhub:
+
+    docker pull ocrd/sbb_binarization
+
 
 ### Models
 

pyproject.toml

@@ -0,0 +1,47 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel", "setuptools-ocrd"]
+
+[project]
+name = "sbb_binarization"
+authors = [
+    {name = "Vahid Rezanezhad"},
+    {name = "Staatsbibliothek zu Berlin - Preußischer Kulturbesitz"},
+]
+description = "Pixelwise binarization with selectional auto-encoders in Keras"
+readme = "README.md"
+license.file = "LICENSE"
+requires-python = ">=3.8"
+
+dynamic = ["dependencies", "version"]
+
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Scientific/Engineering :: Image Processing",
+]
+
+[project.scripts]
+sbb_binarize = "sbb_binarize.cli:main"
+ocrd-sbb-binarize = "sbb_binarize.ocrd_cli:cli"
+
+[project.urls]
+Homepage = "https://github.com/qurator-spk/sbb_binarization"
+Repository = "https://github.com/qurator-spk/sbb_binarization.git"
+
+[tool.setuptools.dynamic]
+dependencies = {file = ["requirements.txt"]}
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["sbb_binarize"]
+namespaces = false
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.package-data]
+"*" = ["*.json"]

requirements.txt

@@ -2,4 +2,4 @@ numpy
 setuptools >= 41
 opencv-python-headless
 ocrd >= 2.38.0
-tensorflow <= 2.11.1
+tensorflow < 2.13

setup.py

@@ -1,30 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-from json import load
-from setuptools import setup, find_packages
-
-with open('./ocrd-tool.json', 'r') as f:
-    version = load(f)['version']
-
-install_requires = open('requirements.txt').read().split('\n')
-
-setup(
-    name='sbb_binarization',
-    version=version,
-    description='Pixelwise binarization with selectional auto-encoders in Keras',
-    long_description=open('README.md').read(),
-    long_description_content_type='text/markdown',
-    author='Vahid Rezanezhad',
-    url='https://github.com/qurator-spk/sbb_binarization',
-    license='Apache License 2.0',
-    packages=find_packages(exclude=('test', 'repo')),
-    include_package_data=True,
-    package_data={'': ['*.json', '*.yml', '*.yaml']},
-    install_requires=install_requires,
-    entry_points={
-        'console_scripts': [
-            'sbb_binarize=sbb_binarize.cli:main',
-            'ocrd-sbb-binarize=sbb_binarize.ocrd_cli:cli',
-        ]
-    },
-)