pycatalyst 0.0.9.dev0__tar.gz → 0.0.12__tar.gz

pycatalyst-0.0.12/.github/workflows/publish.yml

@@ -0,0 +1,99 @@
+# Build and publish to PyPI when a version tag (v*) is pushed.
+# Also supports manual run (workflow_dispatch).
+# Version is derived from the git tag by setuptools-scm.
+
+name: Build and Publish
+
+on:
+  push:
+    tags: ['v*']
+  workflow_dispatch:
+
+permissions:
+  id-token: write
+  contents: write
+
+jobs:
+  build-and-publish:
+    name: Build and Publish to PyPI
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          # Build from the release tag so setuptools-scm produces a full release version (not .dev)
+          ref: ${{ github.event_name == 'release' && github.event.release.tag_name || github.ref }}
+
+      - name: Set version from tag
+        if: startsWith(github.ref, 'refs/tags/')
+        run: echo "SETUPTOOLS_SCM_PRETEND_VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+          cache: 'pip'
+          cache-dependency-path: pyproject.toml
+
+      - name: Install dependencies and run tests
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+          pytest
+
+      - name: Set up Node.js
+        if: hashFiles('src/pycatalyst/ui/package.json') != ''
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+          cache-dependency-path: src/pycatalyst/ui/package-lock.json
+
+      - name: Install UI dependencies
+        if: hashFiles('src/pycatalyst/ui/package.json') != ''
+        run: |
+          cd src/pycatalyst/ui
+          npm ci
+
+      - name: Build UI
+        if: hashFiles('src/pycatalyst/ui/package.json') != ''
+        run: |
+          cd src/pycatalyst/ui
+          npm run build
+
+      - name: Copy UI build to static
+        if: hashFiles('src/pycatalyst/ui/package.json') != ''
+        run: |
+          if [ -d src/pycatalyst/ui/out ] && [ -f src/pycatalyst/ui/out/index.html ]; then
+            rm -rf src/pycatalyst/ui/static
+            cp -r src/pycatalyst/ui/out src/pycatalyst/ui/static
+          fi
+
+      - name: Install build tools
+        run: pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Verify package
+        run: |
+          python -m zipfile -l dist/pycatalyst-*.whl | head -30
+          echo "Package built successfully"
+
+      # Only publish to PyPI when building from a tag (official release). Skip for workflow_dispatch so we don't publish dev versions as pre-release.
+      - name: Publish to PyPI
+        if: startsWith(github.ref, 'refs/tags/') || github.event_name == 'release'
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist/
+
+      - name: Create GitHub Release
+        if: startsWith(github.ref, 'refs/tags/') && github.event_name != 'release'
+        uses: softprops/action-gh-release@v2.4.2
+        with:
+          tag_name: ${{ github.ref_name }}
+          name: ${{ github.ref_name }}
+          generate_release_notes: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

pycatalyst-0.0.12/.gitignore

@@ -0,0 +1,280 @@
+# -----------------------------------------------------------------------------
+# Python (GitHub gitignore template)
+# https://github.com/github/gitignore/blob/main/Python.gitignore
+# -----------------------------------------------------------------------------
+# 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
+*.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
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+# Local SQLite DB (default when no DB URL configured)
+pycatalyst.db
+*.db
+
+# Flask
+instance/
+.webassets-cache
+
+# Scrapy
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# .python-version
+
+# pipenv
+# Pipfile.lock
+
+# poetry
+# poetry.lock
+# poetry.toml
+
+# pdm
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582
+__pypackages__/
+
+# Celery
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# SageMath
+*.sage.py
+
+# Environments
+.env
+.envrc
+.env.local
+.env.development
+.env.test
+.env.production
+.env.staging
+.env.*.local
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder
+.spyderproject
+.spyproject
+
+# Rope
+.ropeproject
+
+# MkDocs
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre
+.pyre/
+
+# pytype
+.pytype/
+
+# Cython
+cython_debug/
+
+# Ruff
+.ruff_cache/
+
+# PyPI
+.pypirc
+
+# -----------------------------------------------------------------------------
+# JetBrains IDEs (GitHub Global/JetBrains.gitignore)
+# -----------------------------------------------------------------------------
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+.idea/**/aws.xml
+.idea/**/contentModel.xml
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+.idea/**/gradle.xml
+.idea/**/libraries
+.idea/**/mongoSettings.xml
+.idea/replstate.xml
+.idea/sonarlint/
+.idea/sonarlint.xml
+.idea/httpRequests
+http-client.private.env.json
+.idea/caches/build_file_checksums.ser
+.idea/.cache/.Apifox_Helper
+.idea/ApifoxUploaderProjectSetting.xml
+.idea/**/copilot.data.migration.*.xml
+cmake-build-*/
+*.iws
+out/
+.idea_modules/
+atlassian-ide-plugin.xml
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# -----------------------------------------------------------------------------
+# Visual Studio Code (GitHub Global/VisualStudioCode.gitignore)
+# -----------------------------------------------------------------------------
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+*.vsix
+
+# Ignore entire IDE directories (keeps repo clean; remove if you want to share IDE config)
+.idea/
+.vscode/
+
+# -----------------------------------------------------------------------------
+# macOS (GitHub Global/macOS.gitignore)
+# -----------------------------------------------------------------------------
+.DS_Store
+__MACOSX/
+.AppleDouble
+.LSOverride
+Icon[ ]
+._*
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+# -----------------------------------------------------------------------------
+# Windows (GitHub Global/Windows.gitignore)
+# -----------------------------------------------------------------------------
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+*.stackdump
+[Dd]esktop.ini
+$RECYCLE.BIN/
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+*.lnk
+
+# -----------------------------------------------------------------------------
+# Editor backups / misc
+# -----------------------------------------------------------------------------
+*.swp
+*.swo
+*~
+
+# -----------------------------------------------------------------------------
+# Project-specific (pycatalyst)
+# -----------------------------------------------------------------------------
+site/
+src/pycatalyst/ui/.next/
+src/pycatalyst/ui/out/
+src/pycatalyst/ui/node_modules/
+src/pycatalyst/ui/.env*.local
+src/pycatalyst/ui/static/

pycatalyst-0.0.12/PKG-INFO

@@ -0,0 +1,212 @@
+Metadata-Version: 2.4
+Name: pycatalyst
+Version: 0.0.12
+Summary: A schema-aware data generation and testing platform for Python
+Author-email: StatFYI <contact@statfyi.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/optophi/pycatalyst
+Project-URL: Documentation, https://optophi.github.io/pycatalyst/
+Project-URL: Repository, https://github.com/optophi/pycatalyst
+Project-URL: Issues, https://github.com/optophi/pycatalyst/issues
+Project-URL: Changelog, https://github.com/optophi/pycatalyst/blob/main/CHANGELOG.md
+Keywords: data-generation,testing,synthetic-data,schema,fake-data
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Typing :: Typed
+Classifier: Topic :: Software Development :: Testing
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pyyaml>=6.0.0
+Requires-Dist: exrex>=0.11.0
+Provides-Extra: inference
+Requires-Dist: pandas>=2.0.0; extra == "inference"
+Provides-Extra: faker
+Requires-Dist: faker>=20.0.0; extra == "faker"
+Provides-Extra: parquet
+Requires-Dist: pyarrow>=14.0.0; extra == "parquet"
+Provides-Extra: http
+Requires-Dist: httpx>=0.24.0; extra == "http"
+Provides-Extra: kafka
+Requires-Dist: confluent-kafka>=2.3.0; extra == "kafka"
+Provides-Extra: rabbitmq
+Requires-Dist: pika>=1.3.0; extra == "rabbitmq"
+Provides-Extra: api
+Requires-Dist: fastapi>=0.104.0; extra == "api"
+Requires-Dist: uvicorn[standard]>=0.24.0; extra == "api"
+Requires-Dist: pydantic>=2.0.0; extra == "api"
+Requires-Dist: pydantic-settings>=2.0.0; extra == "api"
+Requires-Dist: python-multipart>=0.0.6; extra == "api"
+Requires-Dist: PyJWT>=2.8.0; extra == "api"
+Requires-Dist: httpx>=0.24.0; extra == "api"
+Requires-Dist: alembic>=1.13.0; extra == "api"
+Requires-Dist: sqlalchemy>=2.0.0; extra == "api"
+Provides-Extra: worker
+Requires-Dist: alembic>=1.13.0; extra == "worker"
+Requires-Dist: sqlalchemy>=2.0.0; extra == "worker"
+Provides-Extra: ui
+Requires-Dist: fastapi>=0.104.0; extra == "ui"
+Requires-Dist: uvicorn[standard]>=0.24.0; extra == "ui"
+Requires-Dist: httpx>=0.24.0; extra == "ui"
+Requires-Dist: aiofiles>=23.0.0; extra == "ui"
+Provides-Extra: workbench
+Requires-Dist: pycatalyst[api,sandbox]; extra == "workbench"
+Requires-Dist: ipython>=8.0.0; extra == "workbench"
+Provides-Extra: sandbox
+Requires-Dist: docker>=7.0.0; extra == "sandbox"
+Provides-Extra: ml-core
+Requires-Dist: torch>=2.0.0; extra == "ml-core"
+Requires-Dist: numpy>=1.24.0; extra == "ml-core"
+Requires-Dist: pandas>=2.0.0; extra == "ml-core"
+Requires-Dist: matplotlib>=3.7.0; extra == "ml-core"
+Requires-Dist: pydantic>=2.0.0; extra == "ml-core"
+Requires-Dist: joblib>=1.3.0; extra == "ml-core"
+Provides-Extra: ml-sklearn
+Requires-Dist: pycatalyst[ml-core]; extra == "ml-sklearn"
+Requires-Dist: scikit-learn>=1.3.0; extra == "ml-sklearn"
+Provides-Extra: ml-llm
+Requires-Dist: pycatalyst[ml-core]; extra == "ml-llm"
+Requires-Dist: transformers>=4.36.0; extra == "ml-llm"
+Requires-Dist: peft>=0.7.0; extra == "ml-llm"
+Requires-Dist: datasets>=2.16.0; extra == "ml-llm"
+Requires-Dist: accelerate>=0.25.0; extra == "ml-llm"
+Provides-Extra: ml
+Requires-Dist: pycatalyst[ml-core,ml-llm,ml-sklearn]; extra == "ml"
+Provides-Extra: db
+Requires-Dist: alembic>=1.13.0; extra == "db"
+Requires-Dist: sqlalchemy>=2.0.0; extra == "db"
+Provides-Extra: postgres
+Requires-Dist: psycopg2-binary>=2.9.0; extra == "postgres"
+Provides-Extra: mongodb
+Requires-Dist: pymongo>=4.6.0; extra == "mongodb"
+Provides-Extra: s3
+Requires-Dist: boto3>=1.28.0; extra == "s3"
+Provides-Extra: docs
+Requires-Dist: mkdocs-material>=9.5.0; extra == "docs"
+Requires-Dist: mkdocstrings[python]>=0.24.0; extra == "docs"
+Provides-Extra: all
+Requires-Dist: pycatalyst[api,db,docs,faker,http,inference,ml,mongodb,parquet,postgres,s3,sandbox,ui,workbench,worker]; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pycatalyst[all]; extra == "dev"
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: hypothesis>=6.0.0; extra == "dev"
+Requires-Dist: ruff>=0.9.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: pre-commit>=3.0.0; extra == "dev"
+Requires-Dist: build>=0.10.0; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0.0; extra == "dev"
+Requires-Dist: jupyterlab>=4.0.0; extra == "dev"
+Requires-Dist: ipykernel>=6.0.0; extra == "dev"
+Dynamic: license-file
+
+# PyCatalyst
+
+Schema-aware **data generation** and testing: recipes (YAML), REST API, optional UI, schema inference, and ML hooks.
+
+## Documentation
+
+- **Published** (GitHub Pages): [optophi.github.io/pycatalyst](https://optophi.github.io/pycatalyst/) — start with **Getting Started → Quick Start**.
+- **Local docs** (from repo root):
+
+  ```bash
+  pip install "pycatalyst[docs]"
+  pycatalyst docs serve
+  ```
+
+  Opens at [http://127.0.0.1:8007](http://127.0.0.1:8007) by default. Static site: `pycatalyst docs build` → `site/`.
+
+- **Live API** (when the server is running): [http://127.0.0.1:8006/docs](http://127.0.0.1:8006/docs) (Swagger).
+
+Tutorial index in the doc site: Quick Start, API authentication, generate, recipes, infer schema, workbench.
+
+## Installation
+
+```bash
+pip install pycatalyst
+```
+
+API server, DB, and common extras:
+
+```bash
+pip install "pycatalyst[api,db,inference,faker]"
+```
+
+From source (editable):
+
+```bash
+git clone https://github.com/optophi/pycatalyst
+cd pycatalyst
+pip install -e ".[dev]"
+```
+
+## Quick Start (CLI)
+
+```bash
+pycatalyst api --port 8006
+pycatalyst generate --recipe path/to/recipe.yaml -n 10
+```
+
+See the **Quick Start** page in the docs for database setup, UI, and REST examples.
+
+## Streaming mock data
+
+**Python** — same sequence as batch generation for a fixed seed:
+
+```python
+from pycatalyst import GenerationEngine, SchemaBuilder
+
+engine = GenerationEngine()
+schema = SchemaBuilder("events").add_uuid("id").add_string("kind").build()
+for row in engine.iter_records(schema, seed=123, limit=1000):
+    process(row)
+```
+
+**HTTP (Server-Sent Events)** — `POST /api/v1/stream/sse` with the same field list as `/generate`, plus `max_records` and optional `interval_ms`. Use `curl -N` and a Bearer token when auth is enabled:
+
+```bash
+curl -N -H "Authorization: Bearer YOUR_JWT" -H "Content-Type: application/json" \
+  -d '{"name":"x","fields":[{"name":"n","type":"int"}],"max_records":5,"seed":1}' \
+  http://127.0.0.1:8006/api/v1/stream/sse
+```
+
+**CLI — NDJSON to stdout** (one JSON object per line):
+
+```bash
+pycatalyst stream ndjson --schema my.json -n 500 --seed 1
+```
+
+**CLI — Kafka** (`pip install pycatalyst[kafka]`):
+
+```bash
+export PYCATALYST_STREAM_KAFKA_BOOTSTRAP=localhost:9092
+export PYCATALYST_STREAM_KAFKA_TOPIC=test-topic
+pycatalyst stream kafka --schema my.json -n 2000 --batch 100
+```
+
+Server caps (optional): `PYCATALYST_STREAM_MAX_RECORDS`, `PYCATALYST_STREAM_MAX_INTERVAL_MS`.
+
+## Development
+
+- **Lint & format:** `ruff check . && ruff format .`
+- **Type check:** `mypy src/`
+- **Tests:** `pytest`
+- **Coverage:** `pytest --cov=pycatalyst --cov-report=term-missing`
+
+## Publishing
+
+1. Bump version in `pyproject.toml` and `CHANGELOG.md`.
+2. Create a release tag: `git tag v0.1.0 && git push origin v0.1.0`.
+3. The GitHub Action uses [PyPI Trusted Publishing](https://docs.pypi.org/trusted-publishers/); configure the publisher on PyPI for this repo, then the workflow will publish on tag push.
+
+## License
+
+MIT

pycatalyst-0.0.12/README.md

@@ -0,0 +1,102 @@
+# PyCatalyst
+
+Schema-aware **data generation** and testing: recipes (YAML), REST API, optional UI, schema inference, and ML hooks.
+
+## Documentation
+
+- **Published** (GitHub Pages): [optophi.github.io/pycatalyst](https://optophi.github.io/pycatalyst/) — start with **Getting Started → Quick Start**.
+- **Local docs** (from repo root):
+
+  ```bash
+  pip install "pycatalyst[docs]"
+  pycatalyst docs serve
+  ```
+
+  Opens at [http://127.0.0.1:8007](http://127.0.0.1:8007) by default. Static site: `pycatalyst docs build` → `site/`.
+
+- **Live API** (when the server is running): [http://127.0.0.1:8006/docs](http://127.0.0.1:8006/docs) (Swagger).
+
+Tutorial index in the doc site: Quick Start, API authentication, generate, recipes, infer schema, workbench.
+
+## Installation
+
+```bash
+pip install pycatalyst
+```
+
+API server, DB, and common extras:
+
+```bash
+pip install "pycatalyst[api,db,inference,faker]"
+```
+
+From source (editable):
+
+```bash
+git clone https://github.com/optophi/pycatalyst
+cd pycatalyst
+pip install -e ".[dev]"
+```
+
+## Quick Start (CLI)
+
+```bash
+pycatalyst api --port 8006
+pycatalyst generate --recipe path/to/recipe.yaml -n 10
+```
+
+See the **Quick Start** page in the docs for database setup, UI, and REST examples.
+
+## Streaming mock data
+
+**Python** — same sequence as batch generation for a fixed seed:
+
+```python
+from pycatalyst import GenerationEngine, SchemaBuilder
+
+engine = GenerationEngine()
+schema = SchemaBuilder("events").add_uuid("id").add_string("kind").build()
+for row in engine.iter_records(schema, seed=123, limit=1000):
+    process(row)
+```
+
+**HTTP (Server-Sent Events)** — `POST /api/v1/stream/sse` with the same field list as `/generate`, plus `max_records` and optional `interval_ms`. Use `curl -N` and a Bearer token when auth is enabled:
+
+```bash
+curl -N -H "Authorization: Bearer YOUR_JWT" -H "Content-Type: application/json" \
+  -d '{"name":"x","fields":[{"name":"n","type":"int"}],"max_records":5,"seed":1}' \
+  http://127.0.0.1:8006/api/v1/stream/sse
+```
+
+**CLI — NDJSON to stdout** (one JSON object per line):
+
+```bash
+pycatalyst stream ndjson --schema my.json -n 500 --seed 1
+```
+
+**CLI — Kafka** (`pip install pycatalyst[kafka]`):
+
+```bash
+export PYCATALYST_STREAM_KAFKA_BOOTSTRAP=localhost:9092
+export PYCATALYST_STREAM_KAFKA_TOPIC=test-topic
+pycatalyst stream kafka --schema my.json -n 2000 --batch 100
+```
+
+Server caps (optional): `PYCATALYST_STREAM_MAX_RECORDS`, `PYCATALYST_STREAM_MAX_INTERVAL_MS`.
+
+## Development
+
+- **Lint & format:** `ruff check . && ruff format .`
+- **Type check:** `mypy src/`
+- **Tests:** `pytest`
+- **Coverage:** `pytest --cov=pycatalyst --cov-report=term-missing`
+
+## Publishing
+
+1. Bump version in `pyproject.toml` and `CHANGELOG.md`.
+2. Create a release tag: `git tag v0.1.0 && git push origin v0.1.0`.
+3. The GitHub Action uses [PyPI Trusted Publishing](https://docs.pypi.org/trusted-publishers/); configure the publisher on PyPI for this repo, then the workflow will publish on tag push.
+
+## License
+
+MIT