datamanifestpy 0.1.0__tar.gz

datamanifestpy-0.1.0/.github/FUNDING.yml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: perrette # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: # Replace with a single Buy Me a Coffee username
+thanks_dev: # Replace with a single thanks.dev username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

datamanifestpy-0.1.0/.github/workflows/ci.yaml

@@ -0,0 +1,91 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+    tags: ["v*"]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+    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 -x -q
+
+      - name: Smoke-test CLI
+        run: datamanifest --version
+
+  build:
+    # Build the distribution once on a version tag, after the full test matrix passes.
+    needs: test
+    if: startsWith(github.ref, 'refs/tags/v')
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # setuptools_scm needs full history/tags for the version
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Build sdist and wheel
+        run: |
+          pip install build
+          python -m build
+
+      - name: Upload distribution artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write  # required for PyPI Trusted Publishing (OIDC)
+    steps:
+      - name: Download distribution artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  github-release:
+    needs: publish
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write  # required to create a GitHub Release
+    steps:
+      - name: Download distribution artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+          generate_release_notes: true

datamanifestpy-0.1.0/.gitignore

@@ -0,0 +1,213 @@
+datamanifest/_version.py
+
+# Autonomous roadmap workflows (local coordination artifacts; never committed)
+/workflows/
+/.worktrees/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

datamanifestpy-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Mahé Perrette
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

datamanifestpy-0.1.0/PKG-INFO

@@ -0,0 +1,179 @@
+Metadata-Version: 2.4
+Name: datamanifestpy
+Version: 0.1.0
+Summary: Python port of DataManifest.jl — declare and manage data dependencies for scientific projects
+Author-email: Mahé Perrette <mahe.perrette@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2025 Mahé Perrette
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: httpx
+Requires-Dist: tqdm
+Requires-Dist: tomli_w
+Requires-Dist: tomli; python_version < "3.11"
+Provides-Extra: csv
+Requires-Dist: pandas; extra == "csv"
+Provides-Extra: parquet
+Requires-Dist: pandas; extra == "parquet"
+Requires-Dist: pyarrow; extra == "parquet"
+Provides-Extra: nc
+Requires-Dist: xarray; extra == "nc"
+Requires-Dist: netcdf4; extra == "nc"
+Provides-Extra: yaml
+Requires-Dist: pyyaml; extra == "yaml"
+Provides-Extra: all
+Requires-Dist: pandas; extra == "all"
+Requires-Dist: pyarrow; extra == "all"
+Requires-Dist: xarray; extra == "all"
+Requires-Dist: netcdf4; extra == "all"
+Requires-Dist: pyyaml; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Dynamic: license-file
+
+# datamanifest
+
+[![CI](https://github.com/perrette/datamanifest/actions/workflows/ci.yaml/badge.svg)](https://github.com/perrette/datamanifest/actions/workflows/ci.yaml)
+
+Keep track of datasets used in a scientific project.
+
+`datamanifest` provides a simple way to declare data dependencies — URLs, git repositories, checksums, formats — in a `datasets.toml` file, and handles download, verification, extraction, and loading. It is a Python port of [`DataManifest.jl`](https://github.com/awi-esc/DataManifest.jl) (same author), with the same manifest format and feature surface.
+
+## Installation
+
+```bash
+pip install datamanifest
+```
+
+With optional loader backends:
+
+```bash
+pip install "datamanifest[csv]"       # pandas CSV
+pip install "datamanifest[parquet]"   # pandas + pyarrow
+pip install "datamanifest[nc]"        # xarray + netcdf4
+pip install "datamanifest[yaml]"      # pyyaml
+pip install "datamanifest[all]"       # all of the above
+```
+
+## API quickstart
+
+```python
+import datamanifest
+
+# Add a dataset (registers + downloads + auto-fills sha256)
+datamanifest.add(
+    "https://github.com/jesstierney/lgmDA/archive/refs/tags/v2.1.zip",
+    name="jesstierney/lgmDA",
+    extract=True,
+)
+
+# Resolve the on-disk path
+path = datamanifest.get_dataset_path("jesstierney/lgmDA")
+
+# Download and load in one step
+ds = datamanifest.load_dataset("my_nc_entry")  # returns xarray.Dataset for nc format
+
+# Explicit database (no pyproject.toml / env-var lookup)
+db = datamanifest.Database("datasets.toml", "my-data-folder")
+datamanifest.add(db, "https://zenodo.org/record/.../file.csv")
+path = datamanifest.get_dataset_path(db, "file")
+```
+
+The module-level functions (`add`, `download_dataset`, `load_dataset`, `get_dataset_path`, …) look up a process-wide default `Database` via `pyproject.toml` discovery, the `DATAMANIFEST_TOML` / `DATASETS_TOML` environment variables, or a `datasets.toml` / `datamanifest.toml` file in the working tree. Pass an explicit `db` as the first argument to bypass auto-discovery.
+
+## CLI usage
+
+```
+datamanifest COMMAND [OPTIONS]
+```
+
+| Command | Description |
+|---|---|
+| `list [--present\|--missing\|--all]` | List datasets; default shows present first, then missing |
+| `download [NAME ...] [--all] [--overwrite]` | Download specific datasets or all of them |
+| `path NAME` | Print the resolved on-disk path (composable in shell) |
+| `add URI [--name N] [--no-download] [--extract]` | Register and (by default) download a dataset |
+| `remove NAME [--keep-cache]` | Delete an entry, optionally preserving cached files |
+| `show NAME` | Print full entry detail in TOML style |
+| `verify [NAME ...]` | Re-check sha256 checksums; exits nonzero on any mismatch |
+| `init [--folder PATH] [--force]` | Create a fresh `datasets.toml` in the current directory |
+| `where` | Print active `datasets_toml` and `datasets_folder` paths |
+
+Examples:
+
+```bash
+# Set up a new project
+datamanifest init
+
+# Add and download a dataset
+datamanifest add "https://zenodo.org/record/.../file.zip" --extract
+
+# Use the path in a shell pipeline
+python analysis.py --data "$(datamanifest path file)"
+
+# Verify all checksums before a paper submission
+datamanifest verify
+
+# Where is the active manifest?
+datamanifest where
+```
+
+## Features
+
+| Feature | Supported |
+|---|---|
+| HTTP / HTTPS download with progress | yes |
+| Partial-download resume (Range header) | yes |
+| git clone (`git://`, `ssh+git://`, `*.git`) | yes |
+| SSH / rsync (`ssh://`, `sshfs://`, `rsync://`) | yes |
+| Local file copy (`file://`) | yes |
+| Multi-URI batch entries (`uris=`) | yes |
+| SHA-256 checksum verification + auto-fill | yes |
+| ZIP / tar / tar.gz extraction | yes |
+| `requires=` dependency graph (topological order) | yes |
+| Shell template hook (`shell=`) | yes |
+| Python entry-point hook (`python=`) | yes |
+| Named + default loaders (csv, parquet, nc, json, yaml, toml, zip, tar) | yes |
+| TOML manifest round-trip (read `tomllib`, write `tomli_w`) | yes |
+| Project-root auto-discovery (`pyproject.toml` walk, env vars) | yes |
+| CLI (`datamanifest list/download/path/add/remove/show/verify/init/where`) | yes |
+
+## Python adaptations
+
+The Python port uses the same `datasets.toml` format as `DataManifest.jl`. Two fields differ:
+
+- **`python=`** replaces `julia=`: an entry-point reference (`"pkg.mod:func"`) resolved via `importlib`. The callable receives keyword arguments `(download_path, project_root, entry, uri, key, version, doi, format, branch, requires_paths)`. No inline code execution (`exec`/`eval`) anywhere.
+- **`callable=`** is an alias for `python=` accepted on read and normalized to `python=` on write. Intended for single-language projects that want a language-agnostic key.
+- **`python_includes=`** is a list of directory paths prepended to `sys.path` during loader resolution (replaces `julia_modules`).
+
+A single `datasets.toml` can be consumed by both tools: each reads the common fields and ignores the other's extension keys. The shared schema is documented at [perrette/datamanifest.toml](https://github.com/perrette/datamanifest.toml).
+
+## Related projects
+
+- [`awi-esc/DataManifest.jl`](https://github.com/awi-esc/DataManifest.jl) — the Julia implementation this port is based on.
+- [`perrette/datamanifest.toml`](https://github.com/perrette/datamanifest.toml) — the shared TOML schema spec consumed by both implementations.
+
+## Acknowledgments
+
+`datamanifest` is a Python port of [`awi-esc/DataManifest.jl`](https://github.com/awi-esc/DataManifest.jl), written by the same author (Mahé Perrette). The Python port was implemented with assistance from [Anthropic's Claude](https://www.anthropic.com/claude).

datamanifestpy-0.1.0/README.md

@@ -0,0 +1,125 @@
+# datamanifest
+
+[![CI](https://github.com/perrette/datamanifest/actions/workflows/ci.yaml/badge.svg)](https://github.com/perrette/datamanifest/actions/workflows/ci.yaml)
+
+Keep track of datasets used in a scientific project.
+
+`datamanifest` provides a simple way to declare data dependencies — URLs, git repositories, checksums, formats — in a `datasets.toml` file, and handles download, verification, extraction, and loading. It is a Python port of [`DataManifest.jl`](https://github.com/awi-esc/DataManifest.jl) (same author), with the same manifest format and feature surface.
+
+## Installation
+
+```bash
+pip install datamanifest
+```
+
+With optional loader backends:
+
+```bash
+pip install "datamanifest[csv]"       # pandas CSV
+pip install "datamanifest[parquet]"   # pandas + pyarrow
+pip install "datamanifest[nc]"        # xarray + netcdf4
+pip install "datamanifest[yaml]"      # pyyaml
+pip install "datamanifest[all]"       # all of the above
+```
+
+## API quickstart
+
+```python
+import datamanifest
+
+# Add a dataset (registers + downloads + auto-fills sha256)
+datamanifest.add(
+    "https://github.com/jesstierney/lgmDA/archive/refs/tags/v2.1.zip",
+    name="jesstierney/lgmDA",
+    extract=True,
+)
+
+# Resolve the on-disk path
+path = datamanifest.get_dataset_path("jesstierney/lgmDA")
+
+# Download and load in one step
+ds = datamanifest.load_dataset("my_nc_entry")  # returns xarray.Dataset for nc format
+
+# Explicit database (no pyproject.toml / env-var lookup)
+db = datamanifest.Database("datasets.toml", "my-data-folder")
+datamanifest.add(db, "https://zenodo.org/record/.../file.csv")
+path = datamanifest.get_dataset_path(db, "file")
+```
+
+The module-level functions (`add`, `download_dataset`, `load_dataset`, `get_dataset_path`, …) look up a process-wide default `Database` via `pyproject.toml` discovery, the `DATAMANIFEST_TOML` / `DATASETS_TOML` environment variables, or a `datasets.toml` / `datamanifest.toml` file in the working tree. Pass an explicit `db` as the first argument to bypass auto-discovery.
+
+## CLI usage
+
+```
+datamanifest COMMAND [OPTIONS]
+```
+
+| Command | Description |
+|---|---|
+| `list [--present\|--missing\|--all]` | List datasets; default shows present first, then missing |
+| `download [NAME ...] [--all] [--overwrite]` | Download specific datasets or all of them |
+| `path NAME` | Print the resolved on-disk path (composable in shell) |
+| `add URI [--name N] [--no-download] [--extract]` | Register and (by default) download a dataset |
+| `remove NAME [--keep-cache]` | Delete an entry, optionally preserving cached files |
+| `show NAME` | Print full entry detail in TOML style |
+| `verify [NAME ...]` | Re-check sha256 checksums; exits nonzero on any mismatch |
+| `init [--folder PATH] [--force]` | Create a fresh `datasets.toml` in the current directory |
+| `where` | Print active `datasets_toml` and `datasets_folder` paths |
+
+Examples:
+
+```bash
+# Set up a new project
+datamanifest init
+
+# Add and download a dataset
+datamanifest add "https://zenodo.org/record/.../file.zip" --extract
+
+# Use the path in a shell pipeline
+python analysis.py --data "$(datamanifest path file)"
+
+# Verify all checksums before a paper submission
+datamanifest verify
+
+# Where is the active manifest?
+datamanifest where
+```
+
+## Features
+
+| Feature | Supported |
+|---|---|
+| HTTP / HTTPS download with progress | yes |
+| Partial-download resume (Range header) | yes |
+| git clone (`git://`, `ssh+git://`, `*.git`) | yes |
+| SSH / rsync (`ssh://`, `sshfs://`, `rsync://`) | yes |
+| Local file copy (`file://`) | yes |
+| Multi-URI batch entries (`uris=`) | yes |
+| SHA-256 checksum verification + auto-fill | yes |
+| ZIP / tar / tar.gz extraction | yes |
+| `requires=` dependency graph (topological order) | yes |
+| Shell template hook (`shell=`) | yes |
+| Python entry-point hook (`python=`) | yes |
+| Named + default loaders (csv, parquet, nc, json, yaml, toml, zip, tar) | yes |
+| TOML manifest round-trip (read `tomllib`, write `tomli_w`) | yes |
+| Project-root auto-discovery (`pyproject.toml` walk, env vars) | yes |
+| CLI (`datamanifest list/download/path/add/remove/show/verify/init/where`) | yes |
+
+## Python adaptations
+
+The Python port uses the same `datasets.toml` format as `DataManifest.jl`. Two fields differ:
+
+- **`python=`** replaces `julia=`: an entry-point reference (`"pkg.mod:func"`) resolved via `importlib`. The callable receives keyword arguments `(download_path, project_root, entry, uri, key, version, doi, format, branch, requires_paths)`. No inline code execution (`exec`/`eval`) anywhere.
+- **`callable=`** is an alias for `python=` accepted on read and normalized to `python=` on write. Intended for single-language projects that want a language-agnostic key.
+- **`python_includes=`** is a list of directory paths prepended to `sys.path` during loader resolution (replaces `julia_modules`).
+
+A single `datasets.toml` can be consumed by both tools: each reads the common fields and ignores the other's extension keys. The shared schema is documented at [perrette/datamanifest.toml](https://github.com/perrette/datamanifest.toml).
+
+## Related projects
+
+- [`awi-esc/DataManifest.jl`](https://github.com/awi-esc/DataManifest.jl) — the Julia implementation this port is based on.
+- [`perrette/datamanifest.toml`](https://github.com/perrette/datamanifest.toml) — the shared TOML schema spec consumed by both implementations.
+
+## Acknowledgments
+
+`datamanifest` is a Python port of [`awi-esc/DataManifest.jl`](https://github.com/awi-esc/DataManifest.jl), written by the same author (Mahé Perrette). The Python port was implemented with assistance from [Anthropic's Claude](https://www.anthropic.com/claude).

datamanifestpy-0.1.0/datamanifest/__init__.py

@@ -0,0 +1,38 @@
+try:
+    from ._version import __version__
+except ImportError:
+    __version__ = "unknown"
+
+from .database import (
+    Database,
+    DatasetEntry,
+    delete_dataset as _delete_dataset_db,
+    get_default_database,
+    validate_loader,
+    validate_loaders,
+)
+from .pipelines import (
+    _module_add as add,
+    _module_delete_dataset as delete_dataset,
+    _module_download_dataset as download_dataset,
+    _module_download_datasets as download_datasets,
+    _module_get_dataset_path as get_dataset_path,
+    _module_load_dataset as load_dataset,
+    _module_register_dataset as register_dataset,
+)
+
+__all__ = [
+    "__version__",
+    "Database",
+    "DatasetEntry",
+    "add",
+    "delete_dataset",
+    "download_dataset",
+    "download_datasets",
+    "get_dataset_path",
+    "get_default_database",
+    "load_dataset",
+    "register_dataset",
+    "validate_loader",
+    "validate_loaders",
+]