dftly 0.0.1__tar.gz

dftly-0.0.1/.editorconfig

@@ -0,0 +1,13 @@
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+indent_size = 4
+indent_style = space
+insert_final_newline = true
+max_line_length = 110
+tab_width = 4
+
+[{*.yaml,*.yml}]
+indent_size = 2

dftly-0.0.1/.github/actions/setup/action.yaml

@@ -0,0 +1,28 @@
+name: Setup Package
+description: This workflow sets up the package for other workflows.
+inputs:
+  python-version:
+    description: The Python version to use for the setup.
+    required: true
+    default: "3.12"
+  group:
+    description: The dependency group to install (benchmarks, dev, docs)
+    required: false
+    default: "dev"
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/setup-python@v5
+      with:
+        python-version: "${{ inputs.python-version }}"
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v6
+      with:
+        enable-cache: true
+        cache-suffix: "py${{ inputs.python-version }}"
+
+    - name: Install packages
+      shell: bash
+      run: |
+        uv sync --locked --group ${{ inputs.group }} --extra polars

dftly-0.0.1/.github/workflows/code-quality-main.yaml

@@ -0,0 +1,23 @@
+# Same as `code-quality-pr.yaml` but triggered on commit to main branch
+# and runs on all files (instead of only the changed ones)
+
+name: Code Quality Main
+
+on:
+  push:
+    branches: [main]
+
+jobs:
+  code-quality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup package
+        uses: ./.github/actions/setup
+        with:
+          python-version: "3.12"
+
+      - name: Run pre-commits
+        run: uv run pre-commit run --all-files --show-diff-on-failure

dftly-0.0.1/.github/workflows/code-quality-pr.yaml

@@ -0,0 +1,34 @@
+# This workflow finds which files were changed, prints them,
+# and runs `pre-commit` on those files.
+
+# Inspired by the sktime library:
+# https://github.com/alan-turing-institute/sktime/blob/main/.github/workflows/test.yml
+
+name: Code Quality PR
+
+on:
+  pull_request:
+
+jobs:
+  code-quality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup package
+        uses: ./.github/actions/setup
+        with:
+          python-version: "3.12"
+
+      - name: Find modified files
+        id: file_changes
+        uses: tj-actions/changed-files@v46.0.5
+
+      - name: List all changed files
+        run: echo '${{ steps.file_changes.outputs.all_changed_files }}'
+
+      - name: Run pre-commits
+        run: >
+          uv run pre-commit run --show-diff-on-failure
+          --files ${{ steps.file_changes.outputs.all_changed_files}}

dftly-0.0.1/.github/workflows/python-build.yaml

@@ -0,0 +1,96 @@
+name: Publish Python 🐍 distribution 📦 to PyPI and TestPyPI
+
+on: push
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Build
+        run: uv build
+
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish-to-pypi:
+    name: Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/') # only publish to PyPI on tag pushes
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/<package-name> # Replace <package-name> with your PyPI project name
+    permissions:
+      id-token: write # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    name: >-
+      Sign the Python 🐍 distribution 📦 with Sigstore
+      and upload them to GitHub Release
+    needs:
+      - publish-to-pypi
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write # IMPORTANT: mandatory for making GitHub Releases
+      id-token: write # IMPORTANT: mandatory for sigstore
+
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - name: Sign the dists with Sigstore
+        uses: sigstore/gh-action-sigstore-python@v3.0.0
+        with:
+          inputs: >-
+            ./dist/*.tar.gz
+            ./dist/*.whl
+      - name: Create GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: >-
+          gh release create
+          '${{ github.ref_name }}'
+          --repo '${{ github.repository }}'
+          --notes ""
+      - name: Upload artifact signatures to GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        # Upload to GitHub Release using the `gh` CLI.
+        # `dist/` contains the built packages, and the
+        # sigstore-produced signatures and certificates.
+        run: >-
+          gh release upload
+          '${{ github.ref_name }}' dist/**
+          --repo '${{ github.repository }}'

dftly-0.0.1/.github/workflows/tests.yaml

@@ -0,0 +1,47 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  run_tests_ubuntu:
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+
+    timeout-minutes: 30
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup package
+        uses: ./.github/actions/setup
+        with:
+          python-version: "3.12"
+
+      - name: Run tests
+        run: >
+          uv run pytest -v
+          --ignore=docs
+          --cov=src
+          --cov-report=xml:coverage.xml
+          --cov-report=term
+          --junitxml=junit.xml
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          files: coverage.xml
+          fail_ci_if_error: true
+          verbose: true
+
+      - name: Upload test results to Codecov
+        if: ${{ !cancelled() }}
+        uses: codecov/test-results-action@v1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          files: junit.xml

dftly-0.0.1/.gitignore

@@ -0,0 +1,160 @@
+# 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/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

dftly-0.0.1/.pre-commit-config.yaml

@@ -0,0 +1,79 @@
+default_language_version:
+  python: python3.12
+
+exclude: "docs/index.md|example/MEDS_output"
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      # list of supported hooks: https://pre-commit.com/hooks.html
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-docstring-first
+      - id: check-yaml
+      - id: debug-statements
+      - id: detect-private-key
+      - id: check-executables-have-shebangs
+      - id: check-toml
+      - id: check-case-conflict
+      - id: check-added-large-files
+        args: [--maxkb, "800"]
+
+  # python code formatting, linting, and import sorting using ruff
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.2
+    hooks:
+      # Run the formatter
+      - id: ruff-format
+      # Run the linter
+      - id: ruff
+        args: ["--fix", "--exit-non-zero-on-fix"]
+
+  # python docstring formatting
+  - repo: https://github.com/myint/docformatter
+    rev: v1.7.7
+    hooks:
+      - id: docformatter
+        args: [--in-place, --wrap-summaries=110, --wrap-descriptions=110]
+
+  # yaml formatting
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v4.0.0-alpha.8
+    hooks:
+      - id: prettier
+        types: [yaml]
+        exclude: "environment.yaml"
+
+  # shell scripts linter
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+      - id: shellcheck
+
+  # md formatting
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.22
+    hooks:
+      - id: mdformat
+        args: ["--number"]
+        additional_dependencies:
+          - mdformat-ruff
+          - mdformat-gfm
+          - mdformat-gfm-alerts
+          - mdformat-tables
+          - mdformat_frontmatter
+          - mdformat-black
+          - mdformat-config
+          - mdformat-shfmt
+          - mdformat-mkdocs
+          - mdformat-toc
+
+  # word spelling linter
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+      - id: codespell
+        args:
+          - --skip=*.ipynb,*.bib,*.svg,pyproject.toml
+          - --ignore-words-list=ehr,crate

dftly-0.0.1/AGENTS.md

@@ -0,0 +1,147 @@
+# WARP.md
+
+This file provides guidance to WARP (warp.dev) when working with code in this repository.
+
+## Overview
+
+dftly (pronounced "deftly") is a DataFrame Transformation Language parser that provides a YAML-friendly DSL for expressing simple dataframe operations. The library parses YAML configurations into a fully-resolved intermediate representation that can be translated to different execution engines (currently supports Polars).
+
+## Development Commands
+
+### Installation & Setup
+
+```bash
+# Development installation with all dependencies
+pip install -e ".[dev,tests,polars]"
+
+# Enable pre-commit hooks
+pre-commit install
+```
+
+### Testing
+
+```bash
+# Run all tests
+pytest
+
+# Run tests with coverage
+pytest --cov=dftly
+
+# Run specific test files
+pytest tests/test_parser.py
+pytest tests/test_polars_engine.py
+pytest tests/test_integration_polars.py
+
+# Run doctests in README
+pytest --doctest-glob=README.md
+```
+
+### Code Quality
+
+```bash
+# Run all pre-commit hooks
+pre-commit run --all-files
+```
+
+## Architecture
+
+### Core Components
+
+1. **Parser (`src/dftly/parser.py`)**
+
+    - Main entry point via `from_yaml()` function
+    - Handles string parsing using Lark grammar
+    - Transforms simplified YAML syntax to fully-resolved AST nodes
+
+2. **AST Nodes (`src/dftly/nodes.py`)**
+
+    - `Literal`: Simple values (numbers, strings, booleans)
+    - `Column`: References to dataframe columns with optional type info
+    - `Expression`: Complex operations with type and arguments
+
+3. **Grammar (`src/dftly/grammar.lark`)**
+
+    - Lark-based parser grammar for string expressions
+    - Supports operator precedence, function calls, and complex expressions
+    - Handles mathematical, boolean, and string operations
+
+4. **Execution Engine (`src/dftly/polars.py`)**
+
+    - Translates AST nodes to Polars expressions
+    - Maps dftly operations to corresponding Polars operations
+    - Handles type conversions and complex operations
+
+### Two-Stage Parsing Process
+
+1. **Simplified Form → Fully Resolved Form**
+
+    - YAML/dictionary input is parsed into unambiguous AST nodes
+    - String expressions are parsed using the Lark grammar
+    - Context-aware parsing based on input schema
+
+2. **Fully Resolved Form → Execution Engine**
+
+    - AST nodes are translated to execution-specific expressions
+    - Currently supports Polars via `to_polars()` function
+    - Extensible design for additional engines
+
+### Expression Types Supported
+
+The library supports a comprehensive set of operations:
+
+- Arithmetic: `ADD`, `SUBTRACT`
+- Boolean: `AND`, `OR`, `NOT`
+- Conditional: `CONDITIONAL` (ternary if-else)
+- Type operations: `TYPE_CAST`, `COALESCE`
+- String operations: `STRING_INTERPOLATE`, `REGEX`
+- Temporal: `RESOLVE_TIMESTAMP`, `PARSE_WITH_FORMAT_STRING`
+- Membership: `VALUE_IN_LITERAL_SET`, `VALUE_IN_RANGE`
+- Utility: `HASH_TO_INT`
+
+### Key Design Principles
+
+1. **Human-Readable Input**: YAML-friendly syntax for non-technical users
+2. **Fully-Resolved Intermediate Form**: Unambiguous representation for reliable execution
+3. **Engine Independence**: Core parsing separate from execution engines
+4. **Limited Scope**: Focuses on row-wise transformations, not table-level operations
+
+## Testing Strategy
+
+- **Unit Tests**: Individual parser components and node types
+- **Integration Tests**: End-to-end parsing and execution with Polars
+- **Doctest**: Examples in README.md are automatically tested
+- **Type Safety**: All code uses type hints and is validated
+
+## Important Files
+
+- `src/dftly/__init__.py`: Public API exports
+- `src/dftly/parser.py`: Core parsing logic with `DftlyTransformer` class
+- `src/dftly/nodes.py`: AST node definitions with validation
+- `src/dftly/grammar.lark`: Lark grammar for string expression parsing
+- `src/dftly/polars.py`: Polars execution engine implementation
+- `pyproject.toml`: Project configuration with dependencies and build settings
+- `.pre-commit-config.yaml`: Code quality automation
+
+## Common Development Patterns
+
+### Adding New Expression Types
+
+1. Add expression name to `_EXPR_TYPES` set in `parser.py`
+2. Implement parsing logic in `Parser._parse_mapping()`
+3. Add execution logic in `polars.py` `_expr_to_polars()`
+4. Add comprehensive tests covering parsing and execution
+5. Update documentation and examples
+
+### Extending Grammar
+
+1. Modify `grammar.lark` with new syntax rules
+2. Update `DftlyTransformer` class in `parser.py`
+3. Add corresponding expression type handling
+4. Test string parsing alongside dictionary forms
+
+### Adding New Execution Engines
+
+1. Create new module (e.g., `src/dftly/pandas.py`)
+2. Implement `to_[engine]()` function similar to `to_polars()`
+3. Map each expression type to engine-specific operations
+4. Add comprehensive integration tests