fix Dockerfile users

Signed-off-by: Maroun Touma <touma@us.ibm.com>

data-processing-lib/README.md

@@ -0,0 +1,31 @@
+# Data Processing Library
+This provides a python framework for developing _transforms_
+on data stored in files - currently parquet files are supported -
+and running them in a [ray](https://www.ray.io/) cluster.
+Data files may be stored in the local file system or  COS/S3.
+For more details see the [documentation](../doc/overview.md).
+
+### Virtual Environment
+The project uses `pyproject.toml` and a Makefile for operations.
+To do development you should establish the virtual environment
+```shell
+make venv
+```
+and then either activate
+```shell
+source venv/bin/activate
+```
+or set up your IDE to use the venv directory when developing in this project
+
+## Library Artifact Build and Publish
+To test, build and publish the library 
+```shell
+make test build publish
+```
+
+To up the version number, edit the Makefile to change VERSION and rerun
+the above.  This will require committing both the `Makefile` and the
+autotmatically updated `pyproject.toml` file.
+
+
+

data-processing-lib/pyproject.toml

@@ -15,7 +15,7 @@ dynamic = ["dependencies", "optional-dependencies"]
 [project_urls]
 Repository = "https://github.com/IBM/data-prep-kit"
 Issues = "https://github.com/IBM/data-prep-kit/issues"
-Documentation = "https://ibm.github.io/data-prep-kit/"
+Documentation = "https://ibm.github.io/data-prep-kit/doc"
 "Transform project" = "https://github.com/IBM/data-prep-kit/tree/dev/transforms/universal/noop"
 
 [build-system]
@@ -26,7 +26,7 @@ build-backend = "setuptools.build_meta"
 file = ["python/requirements.txt"]
 
 [tool.setuptools.dynamic.optional-dependencies]
-dev = { file = ["requirements.txt"]}
+dev = { file = ["requirements-dev.txt"]}
 ray = { file = ["ray/requirements.txt"]}
 spark = { file = ["spark/requirements.txt"]}
 

transforms/code/code2parquet/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/code/code_profiler/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 COPY --chown=dpk:root src/ src/
@@ -30,7 +30,7 @@ COPY ./src/code_profiler_transform_python.py .
 COPY ./src/code_profiler_local.py local/
 
 # Copy the tree-sitter bindings (this is the important part)
-COPY --chown=ray:users ../../input/tree-sitter-bindings/ /home/dpk/input/tree-sitter-bindings/
+COPY --chown=dpk:root ../../input/tree-sitter-bindings/ /home/dpk/input/tree-sitter-bindings/
 
 # copy test
 # COPY test/ test/

transforms/code/code_quality/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/code/header_cleanser/python/Dockerfile

@@ -21,7 +21,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/code/license_select/python/Dockerfile

@@ -12,7 +12,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/code/malware/python/Dockerfile

@@ -34,7 +34,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 COPY --chown=dpk:root src/ src/

transforms/code/proglang_select/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/universal/doc_id/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 COPY --chown=dpk:root src/ src/

transforms/universal/doc_id/spark/Dockerfile

@@ -10,7 +10,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=spark:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}[spark]
 
 

transforms/universal/ededup/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 COPY --chown=dpk:root src/ src/

transforms/universal/filter/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/universal/filter/spark/Dockerfile

@@ -10,7 +10,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=spark:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}[spark]
 
 COPY --chown=spark:root python-transform/  python-transform/

transforms/universal/hap/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/universal/noop/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image 

transforms/universal/noop/spark/Dockerfile

@@ -10,10 +10,10 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=root:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}[spark]
 
-COPY --chown=spark:root python-transform/  python-transform/
+COPY --chown=root:root python-transform/  python-transform/
 RUN cd python-transform && pip install --no-cache-dir -e .
 
 COPY --chown=root:root src/ src/

transforms/universal/profiler/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 COPY --chown=dpk:root src/ src/

transforms/universal/profiler/spark/Dockerfile

@@ -10,7 +10,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}[spark]
 
 COPY --chown=spark:root python-transform/  python-transform/

transforms/universal/resize/python/Dockerfile

@@ -13,13 +13,13 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # Install python project source
-COPY --chown=dpk:users src/ src/
-COPY --chown=dpk:users pyproject.toml pyproject.toml
-COPY --chown=dpk:users README.md Readme.md
+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 .
 

transforms/universal/resize/spark/Dockerfile

@@ -10,7 +10,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=spark:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}[spark]
 
 COPY --chown=spark:root python-transform/  python-transform/

transforms/universal/tokenization/python/Dockerfile

@@ -13,7 +13,7 @@ ARG WHEEL_FILE_NAME
 
 # 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=ray:users data-processing-dist data-processing-dist
+COPY --chown=dpk:root data-processing-dist data-processing-dist
 RUN  pip install data-processing-dist/${WHEEL_FILE_NAME}
 
 # END OF STEPS destined for a data-prep-kit base image