migrate ocrd v3

.github/workflows/test-python.yml

@@ -0,0 +1,34 @@
+name: Pytest CI
+
+on: [push]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        make install-dev
+        make deps-test
+    - name: Test with pytest
+      run: make coverage PYTEST_ARGS="-vv --workspace=all --junitxml=pytest.xml"
+    - name: Get coverage results
+      run: |
+        coverage report --format=markdown >> $GITHUB_STEP_SUMMARY
+        coverage xml
+    - name: Store coverage results
+      uses: actions/upload-artifact@v4
+      with:
+          name: coverage-report_${{ matrix.python-version }}
+          path: pytest.xml

.gitignore

@@ -1,3 +1,6 @@
+tests/assets/
+/*.zip
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "repo/assets"]
+	path = repo/assets
+	url = https://github.com/OCR-D/assets

Dockerfile

@@ -3,20 +3,41 @@ FROM $DOCKER_BASE_IMAGE
 ARG VCS_REF
 ARG BUILD_DATE
 LABEL \
-    maintainer="https://ocr-d.de/kontakt" \
+    maintainer="https://ocr-d.de/en/contact" \
     org.label-schema.vcs-ref=$VCS_REF \
     org.label-schema.vcs-url="https://github.com/bertsky/docstruct" \
-    org.label-schema.build-date=$BUILD_DATE
+    org.label-schema.build-date=$BUILD_DATE \
+    org.opencontainers.image.vendor="DFG-Funded Initiative for Optical Character Recognition Development" \
+    org.opencontainers.image.title="nmalign" \
+    org.opencontainers.image.description="Document structure detection from PAGE to METS" \
+    org.opencontainers.image.source="https://github.com/bertsky/docstruct" \
+    org.opencontainers.image.documentation="https://github.com/bertsky/docstruct/blob/${VCS_REF}/README.md" \
+    org.opencontainers.image.revision=$VCS_REF \
+    org.opencontainers.image.created=$BUILD_DATE \
+    org.opencontainers.image.base.name=ocrd/core
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONIOENCODING=utf8
+ENV LANG=C.UTF-8
+ENV LC_ALL=C.UTF-8
+
+# avoid HOME/.local/share (hard to predict USER here)
+# so let XDG_DATA_HOME coincide with fixed system location
+# (can still be overridden by derived stages)
+ENV XDG_DATA_HOME /usr/local/share
+# avoid the need for an extra volume for persistent resource user db
+# (i.e. XDG_CONFIG_HOME/ocrd/resources.yml)
+ENV XDG_CONFIG_HOME /usr/local/share/ocrd-resources
 
 WORKDIR /build/docstruct
-COPY setup.py .
-COPY docstruct/ocrd-tool.json .
-COPY docstruct ./docstruct
-COPY requirements.txt .
-COPY README.md .
-COPY Makefile .
-RUN make install
-RUN rm -rf /build/docstruct
+COPY . .
+COPY ocrd-tool.json .
+# prepackage ocrd-tool.json as ocrd-all-tool.json
+RUN ocrd ocrd-tool ocrd-tool.json dump-tools > $(dirname $(ocrd bashlib filename))/ocrd-all-tool.json
+# install everything and reduce image size
+RUN make install && rm -rf /build/docstruct
+# smoke test
+RUN ocrd-docstruct -h
 
 WORKDIR /data
 VOLUME ["/data"]

Makefile

@@ -1,31 +1,85 @@
 PYTHON = python3
 PIP = pip3
 PYTHONIOENCODING=utf8
+PYTEST_ARGS ?= "-vv --workspace=all"
 
-DOCKER_BASE_IMAGE = docker.io/ocrd/core:v2.69.0
+DOCKER_BASE_IMAGE = docker.io/ocrd/core:v3.3.0
 DOCKER_TAG = ocrd/docstruct
 
 help:
 	@echo
 	@echo "  Targets"
 	@echo
-	@echo "    deps    Install only Python deps via pip"
-	@echo "    install Install full Python package via pip"
-	@echo "    docker  Build a Docker image $(DOCKER_TAG) from $(DOCKER_BASE_IMAGE)"
+	@echo "    deps         Install only Python deps via pip"
+	@echo "    install      Install full Python package via pip"
+	@echo "    install-dev  Install in editable mode"
+	@echo "    build        Build binary and source Python package"
+	@echo "    docker       Build a Docker image $(DOCKER_TAG) from $(DOCKER_BASE_IMAGE)"
+	@echo "    test         Run tests via Pytest"
+	@echo "    repo/assets  Clone OCR-D/assets to ./repo/assets"
+	@echo "    tests/assets Copy to ./tests/assets"
+	@echo ""
+	@echo "  Variables"
+	@echo ""
+	@echo "    DOCKER_TAG  Docker container tag ($(DOCKER_TAG))"
+	@echo "    PYTEST_ARGS Additional runtime options for pytest ($(PYTEST_ARGS))"
+	@echo "                (See --help, esp. custom option --workspace)"
 
 # Install Python deps via pip
 deps:
 	$(PIP) install -r requirements.txt
 
+deps-test:
+	$(PIP) install -r requirements-test.txt
+
 # Install Python package via pip
 install:
 	$(PIP) install .
 
+install-dev:
+	$(PIP) install -e .
+
+build:
+	$(PIP) install build wheel
+	$(PYTHON) -m build .
+
+# Run test
+test: tests/assets
+	$(PYTHON) -m pytest  tests --durations=0 $(PYTEST_ARGS)
+
+coverage:
+	coverage erase
+	$(MAKE) test PYTHON="coverage run"
+	coverage report -m
+
+#
+# Assets
+#
+
+# Update OCR-D/assets submodule
+.PHONY: repos always-update tests/assets
+repo/assets: always-update
+	git submodule sync --recursive $@
+	if git submodule status --recursive $@ | grep -qv '^ '; then \
+		git submodule update --init --recursive $@ && \
+		touch $@; \
+	fi
+
+benner_herrnhuterey04_1748.ocrd.zip:
+	wget https://github.com/OCR-D/gt_structure_text/releases/download/v1.5.0/$@
+
+# Setup test assets
+tests/assets: benner_herrnhuterey04_1748.ocrd.zip
+tests/assets: repo/assets
+	mkdir -p $@
+	cp -a $</data/* $@
+	$(foreach BAG,$(filter %.zip,$^),ocrd zip spill -d $@/$(basename $(BAG)) $(BAG))
+
 docker:
 	docker build \
 	--build-arg DOCKER_BASE_IMAGE=$(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: help deps install docker
+.PHONY: help deps deps-test install install-dev build test coverage docker

docstruct/ocrd-tool.json

@@ -1,12 +1,14 @@
 {
-  "version": "0.0.1",
+  "version": "0.0.2",
   "git_url": "https://github.com/bertsky/docstruct",
   "tools": {
     "ocrd-docstruct": {
       "executable": "ocrd-docstruct",
       "categories": ["Layout analysis"],
       "description": "Parsing page-level text regions with headings and reading order, create a dummy logical structMap",
       "steps": ["layout/analysis"],
+      "input_file_grp_cardinality": 1,
+      "output_file_grp_cardinality": 0,
       "parameters": {
         "mode": {
           "type": "string",