Dockerfile refactorings (tesserocr 2.6.2, openaleph-servicelayer etc.) (#16)

catileptic · web-flow · commit b4fa0d5f3a8c · 2025-08-27T17:08:12.000+02:00
* Compile tesserocr with c++ 14; use openaleph-servicelayer

* Build tesserocr in Dockerfile.base; don't build Apple base docker image

* Separate test docker image

* Move tesserocr to ocr dependencies

* Only generate main requirements from pre-commit hook

* Move tesserocr to optional dependencies

* Add build-test to Makefile test, before running tests

* 🔖 Bump version: 5.0.0-rc3 → 5.0.0-rc4
diff --git a/.bumpversion.cfg b/.bumpversion.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 5.0.0-rc3
+current_version = 5.0.0-rc4
 tag_name = {new_version}
 commit = True
 tag = True
diff --git a/.github/workflows/docker-base.yml b/.github/workflows/docker-base.yml
@@ -45,7 +45,7 @@ jobs:
         with:
           context: .
           file: ./Dockerfile.base
-          platforms: linux/amd64,linux/arm64
+          platforms: linux/amd64 #,linux/arm64
           push: true
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -19,7 +19,7 @@ repos:
       - id: mixed-line-ending
         args: ["--fix=lf"]
       - id: trailing-whitespace
-        exclude: ".bumpversion.cfg"  # wtf
+        exclude: ".bumpversion.cfg" # wtf
 
   # - repo: https://github.com/asottile/pyupgrade
   #   rev: v3.10.1
@@ -79,7 +79,7 @@ repos:
     rev: 1.9.0
     hooks:
       - id: poetry-export
-        args: ["--without-hashes", "-o", "requirements.txt"]
+        args: ["--without-hashes", "--with", "main", "-o", "requirements.txt"]
       - id: poetry-export
         args:
           ["--without-hashes", "--only", "dev", "-o", "requirements-dev.txt"]
diff --git a/Dockerfile b/Dockerfile
@@ -2,12 +2,14 @@ FROM ghcr.io/openaleph/ingest-file-base:latest
 
 # uncomment when running on Apple Silicon
 # ENV LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libgomp.so.1
+ENV LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libgomp.so.1
 
 COPY . /ingestors
 RUN rm -rf /ingestors/tests
 WORKDIR /ingestors
-RUN pip3 install --no-cache-dir -r /ingestors/requirements.txt
-RUN pip3 install --no-cache-dir /ingestors
+
+RUN pip3 install --no-cache-dir --no-deps -r /ingestors/requirements.txt
+RUN pip3 install --no-deps --no-cache-dir /ingestors
 
 ENV ARCHIVE_TYPE=file \
     ARCHIVE_PATH=/data \
@@ -17,7 +19,4 @@ ENV ARCHIVE_TYPE=file \
 
 ENV PROCRASTINATE_APP="ingestors.tasks.app"
 
-RUN chmod +x /ingestors/docker-entrypoint.sh
-
-ENTRYPOINT [ "/ingestors/docker-entrypoint.sh" ]
 CMD ["procrastinate", "worker", "-q", "ingest"]
diff --git a/Dockerfile.base b/Dockerfile.base
@@ -12,7 +12,7 @@ RUN apt-get -qq -y update \
     # python deps (mostly to install their dependencies)
     python3-pip python3-dev python3-pil \
     # tesseract
-    tesseract-ocr libtesseract-dev libleptonica-dev pkg-config\
+    tesseract-ocr libtesseract-dev libleptonica-dev pkg-config \
     # libraries
     libxslt1-dev libpq-dev libldap2-dev libsasl2-dev \
     zlib1g-dev libicu-dev libxml2-dev \
@@ -116,6 +116,14 @@ ENV LANG='en_US.UTF-8' \
     OMP_THREAD_LIMIT='1' \
     OPENBLAS_NUM_THREADS='1'
 
+# force compile tesserocr 2.6.2 with C++ 14
+# to make it compatible with Tesseract 5
+RUN pip download --no-binary=:all: "tesserocr==2.6.2" \
+    && tar -xzf tesserocr-2.6.2.tar.gz \
+    && sed -i "s/-std=c++11/-std=c++14/" tesserocr-2.6.2/setup.py \
+    && cd tesserocr-2.6.2 \
+    && CXXFLAGS="-std=c++14" pip install --no-cache-dir .
+
 # tesseract 5
 ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata
 
@@ -127,5 +135,3 @@ RUN pip3 install --no-cache-dir --prefer-binary --upgrade setuptools wheel
 
 # Install PyICU
 RUN pip3 install --no-binary=:pyicu: pyicu
-# Install TesserOCR
-RUN pip3 install --no-binary=:tesserocr: tesserocr
diff --git a/Dockerfile.test b/Dockerfile.test
@@ -2,24 +2,25 @@ FROM ghcr.io/openaleph/ingest-file-base:latest
 
 # uncomment when running on Apple Silicon
 # ENV LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libgomp.so.1
+ENV LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libgomp.so.1
 
 COPY . /ingestors
 WORKDIR /ingestors
-RUN pip3 install --no-cache-dir -r /ingestors/requirements.txt
-RUN pip3 install --no-cache-dir /ingestors
 
-RUN pip3 install --no-cache-dir -r /ingestors/requirements-dev.txt
-RUN pip3 install --no-cache-dir procrastinate==3.2.2  # FIXME
+RUN pip3 install --no-cache-dir --no-deps -r /ingestors/requirements.txt
+RUN pip3 install --no-deps --no-cache-dir /ingestors
+
+RUN pip3 install --no-deps -r /ingestors/requirements-dev.txt
+RUN pip3 install --no-cache-dir procrastinate==3.2.2
 RUN chown -R app:app /ingestors
 
 ENV ARCHIVE_TYPE=file \
     ARCHIVE_PATH=/data \
     FTM_STORE_URI=postgresql://aleph:aleph@postgres/aleph \
     REDIS_URL=redis://redis:6379/0 \
-    TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata
+    TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata \
+    DEBUG=1
 
 ENV PROCRASTINATE_APP="ingestors.tasks.app"
 
-USER app
-ENTRYPOINT [ "/ingestors/docker-entrypoint.sh" ]
 CMD ["pytest"]
diff --git a/Makefile b/Makefile
@@ -18,7 +18,7 @@ build-cache:
 	docker build . --cache-from ghcr.io/openaleph/ingest-file:cache -t ghcr.io/openaleph/ingest-file:cache
 
 build-test:
-	docker build . -f Dockerfile.test -t ghcr.io/openaleph/ingest-file:test
+	$(COMPOSE) build test-ingest-file
 
 build-macos:
 	DOCKER_BUILDKIT=0 COMPOSE_DOCKER_CLI_BUILD=0 $(COMPOSE) build --no-rm --parallel
@@ -39,7 +39,7 @@ format-check:
 	black --check .
 
 test: build-test services
-	PYTHONDEVMODE=1 PYTHONTRACEMALLOC=1 $(COMPOSE) run -e DEBUG=1 --rm ingest-file pytest --cov=ingestors --cov-report html --cov-report term
+	PYTHONDEVMODE=1 PYTHONTRACEMALLOC=1 $(COMPOSE) run --rm test-ingest-file pytest
 
 test-e2e: build services
 	$(COMPOSE_E2E) run --rm ingest-file
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-5.0.0-rc3
+5.0.0-rc4
diff --git a/docker-compose.yml b/docker-compose.yml
@@ -12,7 +12,7 @@ services:
 
   ingest-file:
     build:
-      dockerfile: Dockerfile.test
+      dockerfile: Dockerfile
     hostname: ingest
     tmpfs:
       - /tmp:mode=777
@@ -21,15 +21,34 @@ services:
       OPENALEPH_DB_URI: postgresql://ingest:ingest@postgres/ingest
       FTM_STORE_URI: postgresql://ingest:ingest@postgres/ingest
       LOG_FORMAT: TEXT # TEXT or JSON
-      # LD_PRELOAD: /usr/lib/x86_64-linux-gnu/libgomp.so.1
-      LD_PRELOAD: /usr/lib/aarch64-linux-gnu/libgomp.so.1
+    entrypoint: ["/bin/sh", "-c", "echo 'opal-procrastinate init-db' && exec \"$@\"", "--"]
     volumes:
       - "./ingestors:/ingestors/ingestors"
-      - "./tests:/ingestors/tests"
       - "./data:/ingestors/data"
       - "./requirements.txt:/ingestors/requirements.txt"
       - "./setup.py:/ingestors/setup.py"
-      - "~:/host"
+    depends_on:
+      - postgres
+      - redis
+
+  test-ingest-file:
+    build:
+      context: .
+      dockerfile: Dockerfile.test
+    image: test-ingest-file
+    hostname: ingest
+    tmpfs:
+      - /tmp:mode=777
+      - /data:mode=777
+    environment:
+      OPENALEPH_DB_URI: postgresql://ingest:ingest@postgres/ingest
+      FTM_STORE_URI: postgresql://ingest:ingest@postgres/ingest
+      LOG_FORMAT: TEXT # TEXT or JSON
+      DEBUG: 1
+    entrypoint: ["/bin/sh", "-c", "echo 'opal-procrastinate init-db' && exec \"$@\"", "--"]
+    volumes:
+      - "./tests:/ingestors/tests"
+      - "./data:/ingestors/data"
     depends_on:
       - postgres
       - redis
diff --git a/ingestors/__init__.py b/ingestors/__init__.py
@@ -5,7 +5,7 @@
 from anystore.logging import configure_logging, get_logger
 from procrastinate import cli as procrastinate_cli
 
-__version__ = "5.0.0-rc3"
+__version__ = "5.0.0-rc4"
 
 configure_logging()
 
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
diff --git a/requirements-dev.txt b/requirements-dev.txt
diff --git a/requirements.txt b/requirements.txt
