sparkstagelapse 0.1.0__tar.gz

sparkstagelapse-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,67 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  workflow_dispatch: {}
+
+concurrency:
+  group: ci-${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install ".[dev]"
+      - run: ruff check .
+
+  test:
+    needs: lint
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package with dev + tui extras
+        run: pip install ".[dev,tui]"
+
+      - name: Run test suite
+        run: pytest --cov=sparkstagelapse --cov-report=xml -v
+
+      - name: Upload coverage
+        if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.12'
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-report
+          path: coverage.xml
+
+  build:
+    needs: test
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install build twine
+      - run: python -m build
+      - run: twine check dist/*
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/

sparkstagelapse-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,76 @@
+name: Release
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      target:
+        description: "Where to publish"
+        required: true
+        default: testpypi
+        type: choice
+        options: [testpypi]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install package with dev extras
+        run: pip install ".[dev,tui]"
+
+      - name: Run test suite
+        run: pytest -v
+
+      - name: Build sdist and wheel
+        run: |
+          pip install build twine
+          python -m build
+          twine check dist/*
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish-testpypi:
+    if: github.event_name == 'workflow_dispatch'
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/sparkstagelapse
+    permissions:
+      id-token: write  # required for OIDC trusted publishing, no token/secret needed
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+
+  publish-pypi:
+    # Only real PyPI releases are triggered by publishing a GitHub Release
+    # (tag a commit, then "Create a new release" from that tag in the UI).
+    if: github.event_name == 'release'
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/sparkstagelapse
+    permissions:
+      id-token: write  # required for OIDC trusted publishing, no token/secret needed
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - uses: pypa/gh-action-pypi-publish@release/v1

sparkstagelapse-0.1.0/.gitignore

@@ -0,0 +1,280 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,spark
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,spark
+## Databricks toolbox ##
+artifacts/
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+#VSCODE
+.vscode/
+
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### Spark ###
+*#*#
+*.#*
+*.iml
+*.ipr
+*.iws
+*.pyc
+*.pyo
+*.swp
+*~
+.DS_Store
+.classpath
+.ensime
+.ensime_cache/
+.ensime_lucene
+.generated-mima*
+.idea/
+.idea_modules/
+.project
+.pydevproject
+.scala_dependencies
+.settings
+/lib/
+R-unit-tests.log
+R/unit-tests.out
+R/cran-check.out
+R/pkg/vignettes/sparkr-vignettes.html
+R/pkg/tests/fulltests/Rplots.pdf
+build/*.jar
+build/apache-maven*
+build/scala*
+build/zinc*
+cache
+checkpoint
+conf/*.cmd
+conf/*.conf
+conf/*.properties
+conf/*.sh
+conf/*.xml
+conf/java-opts
+conf/slaves
+dependency-reduced-pom.xml
+derby.log
+dev/create-release/*final
+dev/create-release/*txt
+dev/pr-deps/
+docs/_site
+docs/api
+sql/docs
+sql/site
+lib_managed/
+lint-r-report.log
+log/
+logs/
+out/
+project/boot/
+project/build/target/
+project/plugins/lib_managed/
+project/plugins/project/build.properties
+project/plugins/src_managed/
+project/plugins/target/
+python/lib/pyspark.zip
+python/deps
+python/test_coverage/coverage_data
+python/test_coverage/htmlcov
+python/pyspark/python
+reports/
+scalastyle-on-compile.generated.xml
+scalastyle-output.xml
+scalastyle.txt
+spark-*-bin-*.tgz
+spark-tests.log
+src_managed/
+streaming-tests.log
+unit-tests.log
+work/
+docs/.jekyll-metadata
+
+# For Hive
+TempStatsStore/
+metastore/
+metastore_db/
+sql/hive-thriftserver/test_warehouses
+warehouse/
+spark-warehouse/
+
+# For R session data
+.RData
+.RHistory
+.Rhistory
+*.Rproj
+*.Rproj.*
+
+.Rproj.user
+
+# For SBT
+.jvmopts
+
+
+# End of https://www.toptal.com/developers/gitignore/api/python,spark

sparkstagelapse-0.1.0/PKG-INFO

@@ -0,0 +1,127 @@
+Metadata-Version: 2.4
+Name: sparkstagelapse
+Version: 0.1.0
+Summary: Affichage interactif de DataFrames (Spark/pandas) en notebook ou en script, via un dashboard web local persistant.
+Project-URL: Homepage, https://github.com/OWNER/sparkstagelapse
+Project-URL: Repository, https://github.com/OWNER/sparkstagelapse
+Requires-Python: >=3.9
+Requires-Dist: fastapi>=0.100
+Requires-Dist: pandas>=1.5
+Requires-Dist: requests>=2.28
+Requires-Dist: rich>=13.0
+Requires-Dist: uvicorn[standard]>=0.23
+Provides-Extra: dev
+Requires-Dist: build>=1.0; extra == 'dev'
+Requires-Dist: httpx>=0.24; extra == 'dev'
+Requires-Dist: pytest-cov>=4.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Requires-Dist: twine>=5.0; extra == 'dev'
+Provides-Extra: tui
+Requires-Dist: textual>=0.40; extra == 'tui'
+Description-Content-Type: text/markdown
+
+# sparkstagelapse
+
+Interactive DataFrame display (Spark or pandas) — whether you're in a
+notebook, a script, or a Databricks run — backed by a local web dashboard
+that **stays open and up to date even after the script that launched it has
+exited.**
+
+## Installation
+
+From the root of this folder:
+
+```bash
+pip install -e .
+# or, if you also want the full-screen explorer (Textual):
+pip install -e ".[tui]"
+```
+
+## Quick usage
+
+```python
+from sparkstagelapse import display_spark
+
+# df = spark.sql("select * from ...")
+display_spark(df, title="Employees")             # "auto" mode: notebook -> rich object, script -> web dashboard
+display_spark(df, title="Employees", mode="web")  # force the web dashboard
+display_spark(df, title="Employees", mode="tui")  # full-screen explorer (blocking)
+display_spark(df, title="Employees", mode="rich") # plain ASCII output in the terminal
+```
+
+Or directly on a pandas DataFrame:
+
+```python
+from sparkstagelapse import SparkDisplay
+
+SparkDisplay(pdf, title="Preview").show_web()
+```
+
+## The persistent dashboard
+
+On the first `show_web()` call (or `mode="web"`), the client:
+
+1. Checks whether a server already responds on `127.0.0.1:8765` (`/health`).
+2. If yes: just pushes the new table to it over HTTP — no new process is
+   created.
+3. If no: **spawns the server as a detached process** (not a thread — a
+   daemon thread dies with its parent process, a separate process doesn't).
+   Your script keeps running normally, without blocking.
+
+The server therefore stays alive after your script exits. The next run —
+even tomorrow, even from a different script — will find the same dashboard
+already open in your browser and update it live over WebSocket.
+
+### Managing the server manually
+
+```bash
+python -m sparkstagelapse.dashboard status
+python -m sparkstagelapse.dashboard stop
+python -m sparkstagelapse.dashboard start   # manual foreground start (blocking)
+```
+
+Logs and pid files live in `~/.cache/sparkstagelapse/dashboard_<port>.log` / `.pid`.
+
+### Changing the port / host
+
+```python
+from sparkstagelapse import DashboardClient, SparkDisplay
+
+client = DashboardClient(host="127.0.0.1", port=9000)
+SparkDisplay(pdf, title="Preview", _dashboard=client).show_web()
+```
+
+## Package structure
+
+```
+sparkstagelapse/
+├── __init__.py             # Public API: SparkDisplay, display_spark, DashboardClient
+├── display.py               # SparkDisplay / display_spark — renders depending on context
+└── dashboard/
+    ├── app.py                # FastAPI app (HTTP + WebSocket routes), in-memory state
+    ├── server.py              # Server bootstrap (foreground), pid/log files
+    ├── client.py               # DashboardClient: health-check, detached spawn, HTTP push
+    ├── templates.py            # HTML/JS template + table -> HTML rendering
+    └── __main__.py              # CLI: start / stop / status
+```
+
+## Development
+
+```bash
+pip install -e ".[dev,tui]"
+
+ruff check .          # lint
+pytest -v             # unit + integration tests
+python -m build        # build sdist + wheel
+twine check dist/*     # validate package metadata before upload
+```
+
+## CI/CD
+
+See `.github/workflows/ci.yml` (lint + test matrix + build, on every push/PR)
+and `.github/workflows/release.yml` (build + publish to PyPI/TestPyPI via
+Trusted Publishing, on tagged GitHub Releases). Before the release workflow
+can actually publish, you need to register this repo as a Trusted Publisher
+on PyPI/TestPyPI — see the CI/CD explanation in this conversation for the
+exact steps.

sparkstagelapse-0.1.0/README.md

@@ -0,0 +1,104 @@
+# sparkstagelapse
+
+Interactive DataFrame display (Spark or pandas) — whether you're in a
+notebook, a script, or a Databricks run — backed by a local web dashboard
+that **stays open and up to date even after the script that launched it has
+exited.**
+
+## Installation
+
+From the root of this folder:
+
+```bash
+pip install -e .
+# or, if you also want the full-screen explorer (Textual):
+pip install -e ".[tui]"
+```
+
+## Quick usage
+
+```python
+from sparkstagelapse import display_spark
+
+# df = spark.sql("select * from ...")
+display_spark(df, title="Employees")             # "auto" mode: notebook -> rich object, script -> web dashboard
+display_spark(df, title="Employees", mode="web")  # force the web dashboard
+display_spark(df, title="Employees", mode="tui")  # full-screen explorer (blocking)
+display_spark(df, title="Employees", mode="rich") # plain ASCII output in the terminal
+```
+
+Or directly on a pandas DataFrame:
+
+```python
+from sparkstagelapse import SparkDisplay
+
+SparkDisplay(pdf, title="Preview").show_web()
+```
+
+## The persistent dashboard
+
+On the first `show_web()` call (or `mode="web"`), the client:
+
+1. Checks whether a server already responds on `127.0.0.1:8765` (`/health`).
+2. If yes: just pushes the new table to it over HTTP — no new process is
+   created.
+3. If no: **spawns the server as a detached process** (not a thread — a
+   daemon thread dies with its parent process, a separate process doesn't).
+   Your script keeps running normally, without blocking.
+
+The server therefore stays alive after your script exits. The next run —
+even tomorrow, even from a different script — will find the same dashboard
+already open in your browser and update it live over WebSocket.
+
+### Managing the server manually
+
+```bash
+python -m sparkstagelapse.dashboard status
+python -m sparkstagelapse.dashboard stop
+python -m sparkstagelapse.dashboard start   # manual foreground start (blocking)
+```
+
+Logs and pid files live in `~/.cache/sparkstagelapse/dashboard_<port>.log` / `.pid`.
+
+### Changing the port / host
+
+```python
+from sparkstagelapse import DashboardClient, SparkDisplay
+
+client = DashboardClient(host="127.0.0.1", port=9000)
+SparkDisplay(pdf, title="Preview", _dashboard=client).show_web()
+```
+
+## Package structure
+
+```
+sparkstagelapse/
+├── __init__.py             # Public API: SparkDisplay, display_spark, DashboardClient
+├── display.py               # SparkDisplay / display_spark — renders depending on context
+└── dashboard/
+    ├── app.py                # FastAPI app (HTTP + WebSocket routes), in-memory state
+    ├── server.py              # Server bootstrap (foreground), pid/log files
+    ├── client.py               # DashboardClient: health-check, detached spawn, HTTP push
+    ├── templates.py            # HTML/JS template + table -> HTML rendering
+    └── __main__.py              # CLI: start / stop / status
+```
+
+## Development
+
+```bash
+pip install -e ".[dev,tui]"
+
+ruff check .          # lint
+pytest -v             # unit + integration tests
+python -m build        # build sdist + wheel
+twine check dist/*     # validate package metadata before upload
+```
+
+## CI/CD
+
+See `.github/workflows/ci.yml` (lint + test matrix + build, on every push/PR)
+and `.github/workflows/release.yml` (build + publish to PyPI/TestPyPI via
+Trusted Publishing, on tagged GitHub Releases). Before the release workflow
+can actually publish, you need to register this repo as a Trusted Publisher
+on PyPI/TestPyPI — see the CI/CD explanation in this conversation for the
+exact steps.

sparkstagelapse-0.1.0/pyproject.toml

@@ -0,0 +1,43 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "sparkstagelapse"
+version = "0.1.0"
+description = "Affichage interactif de DataFrames (Spark/pandas) en notebook ou en script, via un dashboard web local persistant."
+readme = "README.md"
+requires-python = ">=3.9"
+dependencies = [
+    "pandas>=1.5",
+    "fastapi>=0.100",
+    "uvicorn[standard]>=0.23",
+    "requests>=2.28",
+    "rich>=13.0",
+]
+
+[project.optional-dependencies]
+tui = ["textual>=0.40"]
+dev = ["pytest>=7.0", "pytest-cov>=4.0", "ruff>=0.5", "build>=1.0", "twine>=5.0", "httpx>=0.24"]
+
+[project.urls]
+Homepage = "https://github.com/OWNER/sparkstagelapse"
+Repository = "https://github.com/OWNER/sparkstagelapse"
+
+[tool.hatch.build.targets.wheel]
+packages = ["sparkstagelapse"]
+
+[tool.pytest.ini_options]
+addopts = "-ra -q"
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py39"
+
+[tool.ruff.lint]
+# Keep this to correctness + import hygiene. This is a small utility package;
+# broad except/log-exception/security-linter opinions (BLE/S/RUF/SIM/C4) add
+# noise without changing behavior, so they're intentionally not selected.
+select = ["E", "F", "I"]
+ignore = ["E501"]  # long lines in HTML/CSS template strings aren't worth wrapping

sparkstagelapse-0.1.0/sparkstagelapse/__init__.py

@@ -0,0 +1,8 @@
+from __future__ import annotations
+
+from .dashboard.client import DashboardClient
+from .display import SparkDisplay, display
+
+__all__ = ["SparkDisplay", "display", "DashboardClient"]
+
+__version__ = "0.1.0"