minimal example code location

.gitea/workflows/docker-publish.yml

@@ -0,0 +1,45 @@
+name: Build and Push Docker Image
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    env:
+      REGISTRY: gitea.dataprovider01.sandbox-cat-dat.simpl-europe.eu
+      IMAGE_REPO: gitea.dataprovider01.sandbox-cat-dat.simpl-europe.eu/j.r/template-code-location
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Validate registry secrets
+        run: |
+          if [ -z "${{ secrets.REGISTRY_USERNAME }}" ] || [ -z "${{ secrets.REGISTRY_PASSWORD }}" ]; then
+            echo "Missing REGISTRY_USERNAME or REGISTRY_PASSWORD secret"
+            exit 1
+          fi
+
+      - name: Login to registry
+        run: |
+          echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login "${REGISTRY}" \
+            -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
+
+      - name: Build image
+        run: |
+          COMMIT_SHA="${GITHUB_SHA:-$GITEA_SHA}"
+          SHORT_SHA="$(echo "${COMMIT_SHA}" | cut -c1-12)"
+          docker build \
+            -t "${IMAGE_REPO}:latest" \
+            -t "${IMAGE_REPO}:${SHORT_SHA}" \
+            .
+
+      - name: Push image tags
+        run: |
+          COMMIT_SHA="${GITHUB_SHA:-$GITEA_SHA}"
+          SHORT_SHA="$(echo "${COMMIT_SHA}" | cut -c1-12)"
+          docker push "${IMAGE_REPO}:latest"
+          docker push "${IMAGE_REPO}:${SHORT_SHA}"

Dockerfile

@@ -11,16 +11,9 @@ RUN addgroup --gid 1000 appgroup && \
 
 # Install system dependencies:
 #   - git: required to fetch util-services from GitLab (tool.uv.sources)
-#   - build-essential / gcc / g++ / python3-dev / cmake: native extensions
-#     (scrubadub-spacy → spaCy, pycanon, etc.)
 #   - curl: optional healthcheck / runtime tooling
-RUN apt-get update && apt-get upgrade -y \
+RUN apt-get update \
     && apt-get install -y --no-install-recommends \
-    build-essential=12.9 \
-    cmake=3.25.1-1 \
-    gcc=4:12.2.0-3 \
-    g++=4:12.2.0-3 \
-    python3-dev=3.11.2-1+b1 \
     git=1:2.39.5-0+deb12u3 \
     curl=7.88.1-10+deb12u14 \
     && apt-get clean \
@@ -28,41 +21,35 @@ RUN apt-get update && apt-get upgrade -y \
     && rm -rf /tmp/* \
     && rm -rf /var/tmp/*
 
-# Pre-own /app so appuser can write to it
-RUN chown -R appuser:appgroup /app
+# Ensure appuser can create the project virtual environment in /app
+RUN chown appuser:appgroup /app
 
 # Copy project metadata and source
-COPY pyproject.toml .
-COPY uv.lock .
-COPY src/ ./src/
+COPY --chown=appuser:appgroup pyproject.toml .
+COPY --chown=appuser:appgroup uv.lock .
+COPY --chown=appuser:appgroup src/ ./src/
 
 # uv environment knobs:
-#   UV_COMPILE_BYTECODE  → compile .pyc files at install time for faster cold start
+#   UV_COMPILE_BYTECODE  → disable .pyc precompile to reduce image size
 #   UV_LINK_MODE=copy    → copy files instead of symlinks (required in Docker layers)
 #   UV_SYSTEM_PYTHON=1   → install into the system Python (no extra venv needed)
-ENV UV_COMPILE_BYTECODE=1
+ENV UV_COMPILE_BYTECODE=0
 ENV UV_LINK_MODE=copy
 ENV UV_SYSTEM_PYTHON=1
 
 # Install the project and all dependencies, respecting [tool.uv.sources]
 # (git source for util-services and pytorch-cpu index for torch)
 # BuildKit cache mount keeps the uv package cache across builds
-RUN --mount=type=cache,target=/root/.cache/uv \
-    uv sync --frozen --no-dev
+USER appuser
+
+RUN --mount=type=cache,target=/home/appuser/.cache/uv,uid=1000,gid=1000 \
+    uv sync --frozen --no-dev --no-install-package torch
 
 # Put the project's venv on PATH (matches WORKDIR)
 ENV PATH="/app/.venv/bin:${PATH}"
 ENV PYTHONPATH="/app/src"
-
-# Make /app writable for the non-root user (e.g. spaCy model downloads)
-RUN chown -R 1000:1000 /app && chmod -R u+w /app
-
-# Provide a real home directory for appuser
-RUN mkdir -p /home/appuser && chown -R 1000:1000 /home/appuser
 ENV HOME=/home/appuser
 
-USER appuser
-
 # Sanity-check: fail the build early if the dagster CLI is missing
 RUN dagster --version
 

pyproject.toml

@@ -10,28 +10,16 @@ requires-python = ">=3.12"
 dependencies = [
     "dagster>=1.8.13",
     "util-services",
-    "data-processing",
-    "dataframe-level-anonymisation",
-    "field-level-pseudo-anonymisation",
 ]
 
 [tool.uv]
-exclude-dependencies = ["transformers", "spacy-transformers"]
+exclude-dependencies = ["transformers", "spacy-transformers", "torch"]
 override-dependencies = [
     "util-services @ git+https://code.europa.eu/simpl/simpl-open/development/data-services/util-services.git@v0.7.0",
 ]
 
 [tool.uv.sources]
-torch = { index = "pytorch-cpu" }
 util-services = { git = "https://code.europa.eu/simpl/simpl-open/development/data-services/util-services.git", rev = "v0.7.0" }
-data-processing = { git = "https://code.europa.eu/simpl/simpl-open/development/data-services/data-processing.git", rev = "v0.4.0" }
-dataframe-level-anonymisation = { git = "https://code.europa.eu/simpl/simpl-open/development/data-services/dataframe-level-anonymisation.git", rev = "v0.6.0" }
-field-level-pseudo-anonymisation = { git = "https://code.europa.eu/simpl/simpl-open/development/data-services/field-level-pseudo-anonymisation.git", rev = "v0.7.0" }
-
-[[tool.uv.index]]
-name = "pytorch-cpu"
-url = "https://download.pytorch.org/whl/cpu"
-explicit = true
 
 [project.optional-dependencies]
 dev = [

src/template_code_location/repository.py

@@ -1,70 +1,14 @@
 from dagster import Definitions
-from util_services.resources import s3_resource
-from util_services.sensors import (
-    notify_success,
-    notify_failure,
-    notify_canceled
-)
 from util_services.custom_json_logger import simpl_json_logger
-
-# Data processing jobs
-from data_processing.jobs import (
-    remove_duplicates_job_s3,
-    fill_missing_values_job_s3,
-    standardize_categorical_values_job_s3,
-    correct_typos_job_s3,
-    normalize_numeric_min_max_job_s3,
-    normalize_datetime_job_s3,
-    normalize_coordinates_job_s3,
-    add_global_aggregations_job_s3,
-    filter_dataset_job_s3,
-    quality_job_s3
-)
-
-# Dataframe-level anonymisation jobs
-from dataframe_level_anonymisation.jobs import (
-    k_anonymity_job_s3,
-    l_diversity_job_s3,
-    t_closeness_job_s3,
-    read_write_semistructured_job_s3,
-)
-
-# Field-level pseudo-anonymisation jobs
-from field_level_pseudo_anonymisation.jobs import (
-    anonymise_pseudonymise_structured_job_s3,
-    depseudonymise_structured_job_s3,
-    anonymise_pseudonymise_unstructured_job_s3,
-    depseudonymise_unstructured_job_s3,
-)
+from util_services.resources import s3_resource
 
 from template_code_location.jobs.jobs import data_processing_job
 
 defs = Definitions(
     jobs=[
-        data_processing_job,
-        # Data processing
-        remove_duplicates_job_s3,
-        fill_missing_values_job_s3,
-        standardize_categorical_values_job_s3,
-        correct_typos_job_s3,
-        normalize_numeric_min_max_job_s3,
-        normalize_datetime_job_s3,
-        normalize_coordinates_job_s3,
-        add_global_aggregations_job_s3,
-        filter_dataset_job_s3,
-        quality_job_s3,
-        # Dataframe-level anonymisation
-        k_anonymity_job_s3,
-        l_diversity_job_s3,
-        t_closeness_job_s3,
-        read_write_semistructured_job_s3,
-        # Field-level pseudo-anonymisation
-        anonymise_pseudonymise_structured_job_s3,
-        depseudonymise_structured_job_s3,
-        anonymise_pseudonymise_unstructured_job_s3,
-        depseudonymise_unstructured_job_s3,
+        data_processing_job
     ],
-    sensors=[notify_success, notify_failure, notify_canceled],
+    sensors=[],
     resources={"s3": s3_resource.configured({"resource_name": "selfS3"})},
     loggers={"simpl": simpl_json_logger},
 )