From bdfbe3d3102227e0859f655372dfadc2be976d31 Mon Sep 17 00:00:00 2001
From: ILay <ilia.zakharchuk@t-systems.com>
Date: Mon, 27 Apr 2026 18:18:38 +0200
Subject: [PATCH] change pip to uv and update dependencies

---
 Dockerfile            | 64 +++++++++++++++++++++++++++++++++++++++----
 pipeline.variables.sh |  2 +-
 pyproject.toml        | 26 +++++++++++++-----
 3 files changed, 78 insertions(+), 14 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index fd4e780..0c997fb 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,15 +1,67 @@
 FROM python:3.12-slim-bookworm
 
-# Install git for git-based dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends git && rm -rf /var/lib/apt/lists/*
+# --- Install uv (pinned for reproducibility) ---
+COPY --from=ghcr.io/astral-sh/uv:0.10.8 /uv /uvx /bin/
 
 WORKDIR /app
 
-COPY pyproject.toml .
-COPY src/ src/
+# Create non-root user with explicit UID/GID 1000
+RUN addgroup --gid 1000 appgroup && \
+    adduser --uid 1000 --gid 1000 --disabled-password --gecos "" appuser
 
-# Install the package and all dependencies
-RUN pip install --no-cache-dir .
+# 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 \
+    && 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 \
+    && rm -rf /var/lib/apt/lists/* \
+    && rm -rf /tmp/* \
+    && rm -rf /var/tmp/*
+
+# Pre-own /app so appuser can write to it
+RUN chown -R appuser:appgroup /app
+
+# Copy project metadata and source
+COPY pyproject.toml .
+COPY src/ ./src/
+
+# uv environment knobs:
+#   UV_COMPILE_BYTECODE  → compile .pyc files at install time for faster cold start
+#   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_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 pip install .
+
+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
 
 EXPOSE 4000
 
diff --git a/pipeline.variables.sh b/pipeline.variables.sh
index 3292612..4a3f9c4 100644
--- a/pipeline.variables.sh
+++ b/pipeline.variables.sh
@@ -1 +1 @@
-PROJECT_VERSION_NUMBER="0.0.1"
\ No newline at end of file
+PROJECT_VERSION_NUMBER="0.1.0"
\ No newline at end of file
diff --git a/pyproject.toml b/pyproject.toml
index 4c6f2dc..7897316 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -19,7 +19,7 @@ dependencies = [
     "lxml>=6.0",
     "xmltodict>=1.0",
     "rdflib>=7.6",
-    "openpyxl",
+    "openpyxl>=3.1.0",
     "xlrd>=2.0.1",
     "tabulate==0.8.10",
     "pyspellchecker>=0.8.4",
@@ -35,14 +35,26 @@ dependencies = [
     "pycanon==1.0.1.post2",
     "anjana>=1.0.0",
     # Field-level pseudo-anonymisation
-    "scrubadub",
-    "scrubadub_spacy",
-    "hvac",
-    "cryptography",
-    # Util services (git dependency)
-    "util-services @ git+https://code.europa.eu/simpl/simpl-open/development/data-services/util-services.git@v0.4.1",
+    "scrubadub>=2.0.0",
+    "scrubadub_spacy>=1.0.0",
+    "hvac>=2.0.0",
+    "cryptography>=42.0.0",
+    # Util services — resolved via [tool.uv.sources] (git)
+    "util-services",
 ]
 
+[tool.uv]
+exclude-dependencies = ["transformers", "spacy-transformers"]
+
+[tool.uv.sources]
+torch = { index = "pytorch-cpu" }
+util-services = { git = "https://code.europa.eu/simpl/simpl-open/development/data-services/util-services.git", rev = "feature/SIMPL-24631" }
+
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
 [project.optional-dependencies]
 dev = [
     "pytest>=8.0.0",