UMLS table creation

.github/workflows/ci.yaml

@@ -0,0 +1,21 @@
+name: CI
+on: [push]
+jobs:
+
+  lint:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+      - name: Install linters
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff==0.2.1
+      - name: Run ruff
+        if: success() || failure() # still run black if above checks fails
+        run: |
+          ruff check
+          ruff format --check

.github/workflows/pypi.yaml

@@ -0,0 +1,25 @@
+name: PyPI
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  publish:
+    runs-on: ubuntu-22.04
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+
+    - name: Build
+      run: python -m build
+
+    - name: Publish
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        password: ${{ secrets.PYPI_API_TOKEN }}
+        print_hash: true

.gitignore

@@ -0,0 +1,137 @@
+downloads/
+generated_parquet/
+
+# project specific
+downloads/
+generated_parquet/
+output.sql
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+default_install_hook_types: [pre-commit, pre-push]
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.2.1
+    hooks:
+      - name: Ruff formatting
+        id: ruff-format
+      - name: Ruff linting
+        id: ruff
+        stages: [pre-push]
+
+  - repo: https://github.com/sqlfluff/sqlfluff
+    rev: 2.3.4
+    hooks:
+      - id: sqlfluff-lint
+        types: []
+        types_or: [sql,jinja]

README.MD

@@ -1 +1,38 @@
-# Cumulus Library UMLS
+# Cumulus Library UMLS
+
+An installation of the Unified Medical Language System® Metathesaurus®. Part of the [SMART on FHIR Cumulus Project](https://smarthealthit.org/cumulus-a-universal-sidecar-for-a-smart-learning-healthcare-system/)
+
+For more information, [browse the documentation](https://docs.smarthealthit.org/cumulus/library).
+## Usage
+
+In order to use the Metathesaurus, you'll need to get an API key for access from the National Library of Medicine, which you can sign up for [here](https://uts.nlm.nih.gov/uts/signup-login).
+
+You can then install this module by running `pip install cumulus-library-umls`.
+
+This will add a `umls` target to `cumulus-library`. You'll need to pass your
+API key via the `--umls-key` CLI flag, or set the `UMLS_API_KEY` environment variable
+to the key you received from NIH.
+
+This ends up being a fairly intensive operation - we download a large file,
+extract it, create parquet files from Athena, and then upload it. It usually
+takes a half hour to run. We try to preserve some of those artifacts along
+the way to make rebuilds faster. If you need to force recreation from scratch, the
+`--replace-existing` CLI flag will handle this.
+
+## Licensing details
+
+The `cumulus-library-umls` study is provided as a convenience to install the
+UMLS Metathesaurus, but is not shipped with the Metathesaurus dataset. It will
+require an API key to download the data from NIH directly.
+
+As a reminder, the 
+[License Agreement for Use of the UMLS® Metathesaurus®](https://uts.nlm.nih.gov/uts/assets/LicenseAgreement.pdf)
+provides several restrictions on this usage of this data (including distributing
+the dataset). When you sign up for a UMLS key, you are assuming responsibility
+for complying with these terms, or an alternate licensing agreement with the
+owner of the Metathesaus data if you are provided with one.
+
+
+## Citations
+
+Bodenreider O. The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res. 2004 Jan 1;32(Database issue):D267-70. doi: 10.1093/nar/gkh061. PubMed PMID: 14681409; PubMed Central PMCID: PMC308795.

cumulus_library_umls/umls/manifest.toml

@@ -0,0 +1,6 @@
+study_prefix = "umls"
+
+[table_builder_config]
+file_names = [
+    "umls_builder.py"
+]