datumhub-cli 0.1.0__tar.gz

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

@@ -0,0 +1,29 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: pip install -e ".[dev]"
+
+      - name: Run tests
+        run: pytest tests/ -v

datumhub_cli-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,51 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tools
+        run: pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Upload dist as artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+
+    environment:
+      name: pypi
+      url: https://pypi.org/project/datumhub-cli/
+
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Download dist artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

datumhub_cli-0.1.0/.gitignore

@@ -0,0 +1,60 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+.python-version
+
+# Hatch
+.hatch/
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.nox/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# macOS
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Datum
+~/.datum/
+
+# Pulled dataset directories (created by datum pull in CWD)
+/pulltest/
+/sampledata/

datumhub_cli-0.1.0/PKG-INFO

@@ -0,0 +1,231 @@
+Metadata-Version: 2.4
+Name: datumhub-cli
+Version: 0.1.0
+Summary: Open datasets, open source — a CLI for publishing and consuming open datasets.
+Author: Datum Contributors
+License: MIT
+Keywords: cli,data,datasets,open-data,registry
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Utilities
+Requires-Python: >=3.9
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: pydantic>=2.6.0
+Requires-Dist: typer[all]>=0.12.0
+Provides-Extra: dev
+Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
+Requires-Dist: pytest>=8.0.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# datum-cli
+
+> The command-line tool for [Datum](https://github.com/simkjels/datum) — publish and consume open data with a single command.
+
+```
+datum pull norges-bank.reports.financial-stability:2024
+```
+
+---
+
+## Installation
+
+```bash
+pip install datumhub-cli
+```
+
+Requires Python 3.11+.
+
+---
+
+## How it works
+
+Every dataset in Datum has a three-part identifier:
+
+```
+publisher.namespace.dataset:version
+```
+
+For example: `met.no.weather.oslo-hourly:2024-01`
+
+The metadata lives in a `datapackage.json` file — a small JSON document that
+describes where the data files are hosted, their format, size, and checksum.
+Datum never hosts the data itself.
+
+---
+
+## Quick start
+
+**1. Describe your dataset**
+
+```bash
+datum init
+```
+
+Walks you through creating a `datapackage.json` interactively.
+
+**2. Validate it**
+
+```bash
+datum check datapackage.json
+```
+
+**3. Publish to your local registry**
+
+```bash
+datum publish datapackage.json
+```
+
+**4. Pull it anywhere**
+
+```bash
+datum pull publisher.namespace.dataset:version
+```
+
+Files land in `./dataset/` in your current directory. The local cache at
+`~/.datum/cache/` is used for deduplication — pulling the same dataset in a
+second directory copies from cache with no network request.
+
+---
+
+## Commands
+
+### Publishing
+
+| Command | Description |
+|---|---|
+| `datum init` | Create a `datapackage.json` via an interactive wizard |
+| `datum check [FILE]` | Validate a `datapackage.json` against the Datum schema |
+| `datum publish [FILE]` | Publish dataset metadata to the registry |
+
+### Consuming
+
+| Command | Description |
+|---|---|
+| `datum pull IDENTIFIER` | Download a dataset and verify its checksum |
+| `datum info IDENTIFIER` | Show full metadata for a dataset |
+| `datum list` | List all datasets in the registry |
+| `datum search QUERY` | Search the registry by keyword |
+
+### Cache
+
+| Command | Description |
+|---|---|
+| `datum cache list` | Show all cached datasets |
+| `datum cache size` | Show total cache disk usage |
+| `datum cache clear` | Remove all cached files |
+
+### Configuration
+
+| Command | Description |
+|---|---|
+| `datum config set KEY VALUE` | Set a configuration value |
+| `datum config get KEY` | Get a configuration value |
+| `datum config show [KEY]` | Show one key or all configuration |
+| `datum config unset KEY` | Remove a configuration key |
+
+### Authentication
+
+| Command | Description |
+|---|---|
+| `datum login [URL]` | Authenticate with a registry |
+| `datum logout [URL]` | Remove stored credentials |
+
+---
+
+## Global flags
+
+Global flags must come **before** the subcommand:
+
+```bash
+datum --output json list
+datum --quiet pull publisher.namespace.dataset:1.0.0
+datum --registry https://datumhub.org pull publisher.namespace.dataset
+```
+
+| Flag | Description |
+|---|---|
+| `--output`, `-o` | Output format: `table` (default), `json`, `plain` |
+| `--quiet`, `-q` | Suppress non-essential output |
+| `--registry` | Override the default registry URL or path |
+| `--verbose`, `-v` | Emit additional diagnostic information |
+
+---
+
+## The datapackage.json format
+
+```json
+{
+  "id": "publisher.namespace.dataset",
+  "version": "1.0.0",
+  "title": "My Dataset",
+  "description": "A short description.",
+  "license": "CC-BY-4.0",
+  "publisher": {
+    "name": "Publisher Name",
+    "url": "https://example.com"
+  },
+  "tags": ["tag1", "tag2"],
+  "sources": [
+    {
+      "url": "https://example.com/data.csv",
+      "format": "csv",
+      "size": 204800,
+      "checksum": "sha256:abc123..."
+    }
+  ]
+}
+```
+
+---
+
+## Pull behaviour
+
+```bash
+# Pull a specific version
+datum pull publisher.namespace.dataset:1.0.0
+
+# Pull the latest published version
+datum pull publisher.namespace.dataset
+
+# Re-download even if the file already exists locally
+datum pull publisher.namespace.dataset:1.0.0 --force
+```
+
+Files are placed in `./dataset/` relative to your current directory.
+Once a file exists there, subsequent pulls skip it — your local edits are safe.
+
+---
+
+## Configuration
+
+```bash
+# Set a default registry
+datum config set registry https://datumhub.org
+
+# Set a default output format
+datum config set output json
+
+# View all configuration
+datum config show
+```
+
+Configuration is stored at `~/.datum/config.json`.
+
+---
+
+## Status
+
+Early development. The CLI is functional for local workflows.
+Remote registry support via [DatumHub](https://datumhub.org) is coming.
+
+---
+
+## License
+
+MIT

datumhub_cli-0.1.0/README.md

@@ -0,0 +1,206 @@
+# datum-cli
+
+> The command-line tool for [Datum](https://github.com/simkjels/datum) — publish and consume open data with a single command.
+
+```
+datum pull norges-bank.reports.financial-stability:2024
+```
+
+---
+
+## Installation
+
+```bash
+pip install datumhub-cli
+```
+
+Requires Python 3.11+.
+
+---
+
+## How it works
+
+Every dataset in Datum has a three-part identifier:
+
+```
+publisher.namespace.dataset:version
+```
+
+For example: `met.no.weather.oslo-hourly:2024-01`
+
+The metadata lives in a `datapackage.json` file — a small JSON document that
+describes where the data files are hosted, their format, size, and checksum.
+Datum never hosts the data itself.
+
+---
+
+## Quick start
+
+**1. Describe your dataset**
+
+```bash
+datum init
+```
+
+Walks you through creating a `datapackage.json` interactively.
+
+**2. Validate it**
+
+```bash
+datum check datapackage.json
+```
+
+**3. Publish to your local registry**
+
+```bash
+datum publish datapackage.json
+```
+
+**4. Pull it anywhere**
+
+```bash
+datum pull publisher.namespace.dataset:version
+```
+
+Files land in `./dataset/` in your current directory. The local cache at
+`~/.datum/cache/` is used for deduplication — pulling the same dataset in a
+second directory copies from cache with no network request.
+
+---
+
+## Commands
+
+### Publishing
+
+| Command | Description |
+|---|---|
+| `datum init` | Create a `datapackage.json` via an interactive wizard |
+| `datum check [FILE]` | Validate a `datapackage.json` against the Datum schema |
+| `datum publish [FILE]` | Publish dataset metadata to the registry |
+
+### Consuming
+
+| Command | Description |
+|---|---|
+| `datum pull IDENTIFIER` | Download a dataset and verify its checksum |
+| `datum info IDENTIFIER` | Show full metadata for a dataset |
+| `datum list` | List all datasets in the registry |
+| `datum search QUERY` | Search the registry by keyword |
+
+### Cache
+
+| Command | Description |
+|---|---|
+| `datum cache list` | Show all cached datasets |
+| `datum cache size` | Show total cache disk usage |
+| `datum cache clear` | Remove all cached files |
+
+### Configuration
+
+| Command | Description |
+|---|---|
+| `datum config set KEY VALUE` | Set a configuration value |
+| `datum config get KEY` | Get a configuration value |
+| `datum config show [KEY]` | Show one key or all configuration |
+| `datum config unset KEY` | Remove a configuration key |
+
+### Authentication
+
+| Command | Description |
+|---|---|
+| `datum login [URL]` | Authenticate with a registry |
+| `datum logout [URL]` | Remove stored credentials |
+
+---
+
+## Global flags
+
+Global flags must come **before** the subcommand:
+
+```bash
+datum --output json list
+datum --quiet pull publisher.namespace.dataset:1.0.0
+datum --registry https://datumhub.org pull publisher.namespace.dataset
+```
+
+| Flag | Description |
+|---|---|
+| `--output`, `-o` | Output format: `table` (default), `json`, `plain` |
+| `--quiet`, `-q` | Suppress non-essential output |
+| `--registry` | Override the default registry URL or path |
+| `--verbose`, `-v` | Emit additional diagnostic information |
+
+---
+
+## The datapackage.json format
+
+```json
+{
+  "id": "publisher.namespace.dataset",
+  "version": "1.0.0",
+  "title": "My Dataset",
+  "description": "A short description.",
+  "license": "CC-BY-4.0",
+  "publisher": {
+    "name": "Publisher Name",
+    "url": "https://example.com"
+  },
+  "tags": ["tag1", "tag2"],
+  "sources": [
+    {
+      "url": "https://example.com/data.csv",
+      "format": "csv",
+      "size": 204800,
+      "checksum": "sha256:abc123..."
+    }
+  ]
+}
+```
+
+---
+
+## Pull behaviour
+
+```bash
+# Pull a specific version
+datum pull publisher.namespace.dataset:1.0.0
+
+# Pull the latest published version
+datum pull publisher.namespace.dataset
+
+# Re-download even if the file already exists locally
+datum pull publisher.namespace.dataset:1.0.0 --force
+```
+
+Files are placed in `./dataset/` relative to your current directory.
+Once a file exists there, subsequent pulls skip it — your local edits are safe.
+
+---
+
+## Configuration
+
+```bash
+# Set a default registry
+datum config set registry https://datumhub.org
+
+# Set a default output format
+datum config set output json
+
+# View all configuration
+datum config show
+```
+
+Configuration is stored at `~/.datum/config.json`.
+
+---
+
+## Status
+
+Early development. The CLI is functional for local workflows.
+Remote registry support via [DatumHub](https://datumhub.org) is coming.
+
+---
+
+## License
+
+MIT

datumhub_cli-0.1.0/pyproject.toml

@@ -0,0 +1,59 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "datumhub-cli"
+version = "0.1.0"
+description = "Open datasets, open source — a CLI for publishing and consuming open datasets."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+authors = [{ name = "Datum Contributors" }]
+keywords = ["data", "datasets", "registry", "open-data", "cli"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Utilities",
+]
+dependencies = [
+    "typer[all]>=0.12.0",
+    "pydantic>=2.6.0",
+    "httpx>=0.27.0",
+]
+
+[project.scripts]
+datum = "datum.main:app"
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0.0",
+    "pytest-asyncio>=0.23.0",
+]
+
+[tool.hatch.version]
+path = "src/datum/__init__.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/datum"]
+
+[tool.hatch.envs.default]
+features = ["dev"]
+
+[tool.hatch.envs.default.scripts]
+test = "pytest {args}"
+lint = "ruff check src tests"
+typecheck = "mypy src"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+target-version = "py311"
+line-length = 100

datumhub_cli-0.1.0/src/datum/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"