Create python Dockerfile

Signed-off-by: Constantin M Adam <[email protected]>

transforms/universal/fdedup/python/Dockerfile

@@ -0,0 +1,43 @@
+FROM docker.io/python:3.10.14-slim-bullseye
+
+RUN pip install --upgrade --no-cache-dir pip 
+
+# install pytest
+RUN pip install --no-cache-dir pytest
+
+# Create a user and use it to run the transform
+RUN useradd -ms /bin/bash dpk
+USER dpk
+WORKDIR /home/dpk
+
+# Copy and install data processing libraries 
+# These are expected to be placed in the docker context before this is run (see the make image).
+COPY --chown=dpk:root data-processing-lib-python/ data-processing-lib-python/
+RUN cd data-processing-lib-python && pip install --no-cache-dir -e .
+
+COPY --chown=dpk:root src/ src/
+COPY --chown=dpk:root pyproject.toml pyproject.toml
+COPY --chown=dpk:root README.md README.md
+COPY --chown=dpk:root requirements.txt requirements.txt
+
+RUN pip install --no-cache-dir -e .
+
+# copy source data
+COPY src/ src/
+
+# copy source data
+COPY ./src/signature_calc_transform_python.py fdedup_transform_python.py
+COPY ./src/signature_calc_local_python.py local/
+
+# copy test
+COPY test/ test/
+COPY test-data/ test-data/
+
+# Set environment
+ENV PYTHONPATH /home/dpk
+
+# Put these at the end since they seem to upset the docker cache.
+ARG BUILD_DATE
+ARG GIT_COMMIT
+LABEL build-date=$BUILD_DATE
+LABEL git-commit=$GIT_COMMIT

transforms/universal/fdedup/python/requirements.txt

@@ -0,0 +1,10 @@
+pyarrow==16.1.0
+pyyaml>=6.0.2
+boto3>=1.34.69
+kubernetes>=30.1.0
+polars>=1.6.0
+disjoint-set>=0.8.0
+numpy<1.29.0
+sentencepiece>=0.2.0
+mmh3>=4.1.0
+scipy>=1.12.0, <2.0.0