Upgraded Dependencies and Converted to UV (#40)

* Upgraded Dependencies and Converted to UV
Added mapping fix
Updated presidio version
Mapper docs update

* Updated PR template

Author: EdyVision

.github/pull_request_template.md

@@ -8,9 +8,7 @@ PR description. Explain what it's doing and why.
 ### Checklist
 
 - [ ] New PII Detection Service Added (Optional)
-- [ ] New PII Mappings added (Optional)
-- [ ] New citations added (if using other open source or research software) (Optional)
-- [ ] New PII types added to new version file under pii_codex/data (and JSON file generated) (Optional)
+- [ ] New PII types added to pii_type_mappings (Optional)
 - [ ] Tests added
 - [ ] CI passed
 - [ ] Commits Squashed

.github/workflows/checks.yml

@@ -10,13 +10,13 @@ jobs:
         runs-on: ubuntu-latest
         steps:
             - name: checkout
-              uses: actions/checkout@v2
+              uses: actions/checkout@v4
             - name: setup - python
-              uses: actions/setup-python@v3
+              uses: actions/setup-python@v4
               with:
-                  python-version: 3.9
+                  python-version: 3.12
             - name: Install Global Dependencies
-              run: pip install -U pip && pip install poetry wheel
+              run: pip install -U pip && pip install uv
             - name: install
               run: make install
             - name: typecheck

.github/workflows/draft-pdf.yml

@@ -13,7 +13,7 @@ jobs:
           journal: joss
           paper-path: ./joss/paper.md
       - name: Upload
-        uses: actions/upload-artifact@v1
+        uses: actions/upload-artifact@v4
         with:
           name: paper
           path: ./joss/paper.pdf

.github/workflows/release.yml

@@ -16,22 +16,22 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Setup Python
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v4
         with:
-          python-version: 3.9
+          python-version: 3.12
       - name: Checkout branch "main"
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           ref: 'main'
           fetch-depth: 0
       - name: Install Global Dependencies
-        run: pip install -U pip && pip install poetry wheel
+        run: pip install -U pip && pip install uv
       - name: Build project for distribution
-        run: poetry build
+        run: uv build
       - name: Get Current Version
         id: get_version
         run: |
-          TAG_NAME=$(poetry version -s)
+          TAG_NAME=$(uv run python -c "import tomllib; print(tomllib.load(open('pyproject.toml', 'rb'))['project']['version'])")
           echo "TAG_NAME=v$TAG_NAME" >> $GITHUB_ENV
           echo "$TAG_NAME"
       - name: Check Released Versions
@@ -59,5 +59,5 @@ jobs:
           prerelease: false
       - name: Publish to PyPI
         env:
-          POETRY_PYPI_TOKEN_PYPI: ${{ secrets.PII_CODEX_PYPI_TOKEN }}
-        run: poetry publish
+          UV_PYPI_TOKEN_PYPI: ${{ secrets.PII_CODEX_PYPI_TOKEN }}
+        run: uv publish

.github/workflows/test.yml

@@ -5,7 +5,7 @@ on:
   push:
     paths:
       - "pii_codex/**"
-      - "poetry.lock"
+      - "uv.lock"
       - "pyproject.toml"
       - ".github/workflows/test.yml"
 
@@ -17,27 +17,24 @@ jobs:
     name: Run Tests
     strategy:
       matrix:
-        python-version: [ "3.9", "3.10" ]
-        os: [ubuntu-22.04, macos-latest]
+        python-version: [ "3.9", "3.10", "3.11", "3.12" ]
+        os: [ubuntu-latest, macos-latest]
     runs-on: ${{ matrix.os }}
 
     # Checkout the code, install poetry, install dependencies,
     # and run test with coverage
     steps:
       - name: Environment Setup
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Setup Python
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install Global Dependencies
-        run: pip install -U pip && pip install poetry wheel
+        run: pip install -U pip && pip install uv
       - name: Install Project Dependencies
         run: |
-          poetry config virtualenvs.create true
           make install
-          make install.extras
-      - uses: actions/checkout@master
       - name: Run Tests
         run: |
           make test.coverage

.zenodo.json

@@ -1,6 +1,6 @@
 {
   "access_right": "open",
-  "version": "0.4.6",
+  "version": "0.5.0",
   "creators": [
     {
       "orcid": "0000-0003-0665-098X",

CITATION.cff

@@ -5,6 +5,6 @@ authors:
     given-names: Eidan J.
     orcid: https://orcid.org/0000-0003-0665-098X
 title: "pii-codex: a Python library for PII detection, categorization, and severity assessment"
-version: 0.4.6
+version: 0.5.0
 doi: 10.5281/zenodo.7212576
-date-released: 2023-06-18
+date-released: 2025-08-24

Makefile

@@ -6,16 +6,18 @@ test: lint test.all
 test.cov: test.coverage
 
 install:
-	@poetry update
-	@poetry install
-	$(MAKE) install.extras
+	@uv sync
+	@uv sync --all-extras
+	@uv sync --extra dev 
 	$(MAKE) install.pre_commit
+	@echo "Installation complete!"
 
 install.pre_commit:
-	@poetry run pre-commit install
+	@uv run pre-commit install || (echo "Warning: pre-commit installation failed. You may need to run 'uv sync --extra dev' first." && exit 1)
 
 install.extras:
-	@poetry install --extras="detections"
+	@echo "Installing detection dependencies (spaCy, Presidio, etc.)..."
+	@uv sync --extra detections
 
 install_spacy_en_core_web_lg:
 	@python3 -m spacy download en_core_web_lg
@@ -27,14 +29,14 @@ test.all:
 	@pytest tests
 
 test.coverage:
-	@poetry run coverage run -m pytest -vv tests && poetry run coverage report -m --omit="*/test*,config/*.conf" --fail-under=95
-	@poetry run coverage xml
+	@uv run coverage run -m pytest -vv tests && uv run coverage report -m --omit="*/test*,config/*.conf" --fail-under=95
+	@uv run coverage xml
 
 lint:
-	@poetry run pylint pii_codex tests
+	@uv run pylint pii_codex tests
 
 typecheck:
-	@poetry run mypy pii_codex tests
+	@uv run mypy pii_codex tests
 
 format.check:
 	@black . --check
@@ -49,16 +51,16 @@ docs:
 	@pdoc --html pii_codex --force -o ./docs/dev
 
 version.bump.patch:
-	@poetry version patch
-	$(MAKE) bump.citation.date
+	@uv run bumpver update --patch
+	# $(MAKE) bump.citation.date
 
 version.bump.minor:
-	@poetry version minor
+	@uv run bumpver update --minor
 	$(MAKE) bump.citation.date
 
 version.bump.major:
-	@poetry version major
+	@uv run bumpver update --major
 	$(MAKE) bump.citation.date
 
 package:
-	@poetry build
+	@uv build

README.md

@@ -9,7 +9,7 @@ PII Detection, Categorization, and Severity Assessment
 [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://GitHub.com/EdyVision/pii-codex/graphs/commit-activity)
 [![codecov](https://codecov.io/gh/EdyVision/pii-codex/branch/main/graph/badge.svg?token=QO7DNMP87X)](https://codecov.io/gh/EdyVision/pii-codex)
 [![License](https://img.shields.io/badge/License-BSD_3--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)
-[![Python 3.9](https://img.shields.io/badge/python-3.9-blue.svg)](https://www.python.org/downloads/release/python-390/)
+[![Python 3.9-3.12](https://img.shields.io/badge/python-3.9--3.12-blue.svg)](https://www.python.org/downloads/)
 [![DOI](https://zenodo.org/badge/533554671.svg)](https://zenodo.org/badge/latestdoi/533554671)
 [![status](https://joss.theoj.org/papers/5296a84bba0925e682dcddf14bec5880/status.svg)](https://joss.theoj.org/papers/5296a84bba0925e682dcddf14bec5880)
 
@@ -36,17 +36,17 @@ Potential usages include sanitizing of dataset strings (e.g. a collection of soc
 
 <hr/>
 
-## Running Locally with Poetry
-This project uses Poetry. To run this project, install `poetry` and proceed to follow the instructions under `/docs/LOCAL_SETUP.md`.
+## Running Locally with uv
+This project uses `uv` for dependency management. To run this project, install `uv` and proceed to follow the instructions under `/docs/LOCAL_SETUP.md`.
 
-`Note: This project has only been tested with Ubuntu and MacOS and with Python versions 3.9 and 3.10. You may need to upgrade pip ahead of installation.`
+`Note: This project has only been tested with Ubuntu and MacOS and with Python versions 3.11 and 3.12. You may need to upgrade pip ahead of installation.`
 
 ## Installing with PIP
-Video capture of install provided in LOCAL_SETUP.md file. Make sure you set up a virtual environment with either python 3.9 or 3.10 and upgrade pip with:
+Video capture of install provided in LOCAL_SETUP.md file. Make sure you set up a virtual environment with either python 3.11 or 3.12 and upgrade pip with:
 
 ```bash
 pip install --upgrade pip
-pip install -U pip setuptools wheel # only needed if you haven't already done so 
+pip install -U pip uv # only needed if you haven't already done so 
 ```
 
 Before adding `pii-codex` on your project, download the spaCy `en_core_web_lg` model:
@@ -67,12 +67,12 @@ pip install "pii-codex[detections]"
 
 `Note: The extras installed with pii-codex[detections] are the spaCy, Micrisoft Presidio Analyzer, and Microsoft Anonymzer packages.`
 
-Using Poetry:
+Using uv:
 
 ```bash
-poetry update
-poetry add pii-codex
-poetry install pii-codex --extras="detections"
+uv sync
+uv add pii-codex
+uv add "pii-codex[detections]"
 ```
 
 For those using Google Collab, check out the example notebook:
@@ -162,7 +162,7 @@ For more information on usage, check out the respective documentation for guidan
 <hr/>
 
 ## Attributions
-This project benefited greatly from a number of PII research works like that from Milne et al (2016) with the definition of the types and categories, Schwartz and Solove (2012) with the severity levels of Non-Identifiable, Semi-Identifiable, and Identifiable, and the documentation by NIST, DHS (2012), and HIPAA (full list of foundational publications provided below). A special thanks to all the open source projects, and frameworks that made the setup and structuring of this project much easier like Poetry, Microsoft Presidio, spaCy (2017), Jupyter, and several others.
+This project benefited greatly from a number of PII research works like that from Milne et al (2016) with the definition of the types and categories, Schwartz and Solove (2012) with the severity levels of Non-Identifiable, Semi-Identifiable, and Identifiable, and the documentation by NIST, DHS (2012), and HIPAA (full list of foundational publications provided below). A special thanks to all the open source projects, and frameworks that made the setup and structuring of this project much easier like uv, Microsoft Presidio, spaCy (2017), Jupyter, and several others.
 
 ### Foundational Publications
 The following publications that inspired and provided a foundation for this repository:

docs/LOCAL_SETUP.md

@@ -14,23 +14,17 @@ Video Demo of package import and usage:
 For those contributing or modifying the source, use the following to set up locally.
 
 ## Environment Config
-You'll need the Python (^3.9) and Poetry configured on your machine. Once those are configured, create a virtual
+You'll need Python (^3.11) and `uv` configured on your machine. Once those are configured, create a virtual
 environment and install dependencies.
 
 ```bash
-python3.9 -m venv venv
-
-. venv/bin/activate
-
-pip install --upgrade pip
-
-make install
+uv sync
 ```
 
 Installing dependencies will vary by usage. For those in need of the PII-Codex integration of the MSFT Presidio Analyzer, it is recommended to install the `detections` extras:
 
 ```bash
-poetry install --extras="detections"
+uv sync --extra detections
 ```
 
 As part of the `detections` extras installation, the download for the `en_core_web_lg` spaCy model will be enabled on first use of the `PresidioPIIAnalyzer()`. If more language support is needed, you'll need to download it separately. Reference <a href="https://github.com/explosion/spacy-models/releases?q=en_core_web_lg&expanded=true">explosion/spacy-models</a>.