datamaestro 1.5.1__tar.gz → 1.6.0__tar.gz

datamaestro-1.6.0/.flake8

@@ -0,0 +1,7 @@
+[flake8]
+extend-ignore = E203, E266, E501, W503, E704
+# line length is intentionally set to 80 here because black uses Bugbear
+# See https://github.com/psf/black/blob/master/docs/the_black_code_style.md#line-length for more details
+max-line-length = 80
+max-complexity = 18
+select = B,C,E,F,W,T4,B9

{datamaestro-1.5.1 → datamaestro-1.6.0}/.github/workflows/pytest.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.9", "3.10", "3.11"]
+        python-version: ["3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v2

datamaestro-1.6.0/.github/workflows/python-publish.yml

@@ -0,0 +1,45 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write  # Required to update release notes
+      id-token: write  # Required for PyPI trusted publishing
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.x"
+
+      - name: Generate changelog for this release
+        uses: orhun/git-cliff-action@v4
+        with:
+          config: cliff.toml
+          args: --latest --strip header
+        env:
+          OUTPUT: release-notes.md
+
+      - name: Update release notes
+        uses: softprops/action-gh-release@v2
+        with:
+          body_path: release-notes.md
+
+      - name: Install dependencies
+        run: python -m pip install --upgrade uv
+
+      - name: Build
+        run: uv build
+
+      - name: Publish package to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

{datamaestro-1.5.1 → datamaestro-1.6.0}/.pre-commit-config.yaml

@@ -1,16 +1,16 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v6.0.0
     hooks:
     -   id: check-yaml
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 -   repo: https://github.com/psf/black
-    rev: 23.3.0
+    rev: 25.12.0
     hooks:
     -   id: black
 -   repo: https://github.com/pycqa/flake8
-    rev: 6.0.0
+    rev: 7.3.0
     hooks:
     -   id: flake8
         additional_dependencies:

datamaestro-1.6.0/.python-version

@@ -0,0 +1 @@
+3.10

{datamaestro-1.5.1 → datamaestro-1.6.0}/.readthedocs.yml

@@ -11,7 +11,7 @@ sphinx:
 build:
   os: "ubuntu-20.04"
   tools:
-    python: "3.9"
+    python: "3.10"
 
 # Install the package
 python:

{datamaestro-1.5.1 → datamaestro-1.6.0}/PKG-INFO

@@ -1,42 +1,31 @@
 Metadata-Version: 2.4
 Name: datamaestro
-Version: 1.5.1
-Summary: "Dataset management command line and API"
-Home-page: https://github.com/experimaestro/datamaestro
-Author: Benjamin Piwowarski
-Author-email: benjamin@piwowarski.fr
-License: GPL-3
-Keywords: dataset manager
-Platform: any
+Version: 1.6.0
+Summary: Add your description here
+Author-email: Benjamin Piwowarski <benjamin@piwowarski.fr>
+License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: click
-Requires-Dist: tqdm
-Requires-Dist: urllib3
-Requires-Dist: marshmallow
-Requires-Dist: cached_property
-Requires-Dist: requests
-Requires-Dist: bitmath
+Requires-Python: >=3.10
+Requires-Dist: bitmath>=1.3.3.1
+Requires-Dist: cached-property>=2.0.1
+Requires-Dist: click>=8.2.1
+Requires-Dist: docstring-parser>=0.16
 Requires-Dist: experimaestro>=1.8.9
-Requires-Dist: mkdocs
-Requires-Dist: pymdown-extensions
-Requires-Dist: mkdocs-material
-Requires-Dist: docstring_parser
+Requires-Dist: marshmallow>=3.26.1
+Requires-Dist: mkdocs-material>=9.6.15
+Requires-Dist: mkdocs>=1.6.1
 Requires-Dist: numpy
-Provides-Extra: test
-Requires-Dist: tox; extra == "test"
-Dynamic: license-file
-Dynamic: requires-dist
+Requires-Dist: pymdown-extensions>=10.16
+Requires-Dist: requests>=2.32.4
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: urllib3>=2.5.0
+Description-Content-Type: text/markdown
 
 [![PyPI version](https://badge.fury.io/py/datamaestro.svg)](https://badge.fury.io/py/datamaestro) [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit) [![DOI](https://zenodo.org/badge/4573876.svg)](https://zenodo.org/badge/latestdoi/4573876)
 
@@ -192,22 +181,3 @@ This will allow to
 
 1. Document the dataset
 2. Allow to use the command line interface to manipulate it (download resources, etc.)
-
-# 0.8.0
-
-- Integration with other repositories: abstracting away the notion of dataset
-- Repository prefix
-- Set sub-datasets IDs automatically
-
-# 0.7.3
-
-- Updates for new experimaestro (0.8.5)
-- Search types with "type:..."
-
-# 0.6.17
-
-- Allow remote access through rpyc
-
-# 0.6.9
-
-`version` command

datamaestro-1.6.0/pyproject.toml

@@ -0,0 +1,62 @@
+[project]
+name = "datamaestro"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+authors = [
+    { name = "Benjamin Piwowarski", email = "benjamin@piwowarski.fr"}
+]
+dynamic = ["version"]
+dependencies = [
+    "bitmath>=1.3.3.1",
+    "cached-property>=2.0.1",
+    "click>=8.2.1",
+    "docstring-parser>=0.16",
+    "experimaestro>=1.8.9",
+    "marshmallow>=3.26.1",
+    "mkdocs>=1.6.1",
+    "mkdocs-material>=9.6.15",
+    "numpy",
+    "pymdown-extensions>=10.16",
+    "requests>=2.32.4",
+    "tqdm>=4.67.1",
+    "urllib3>=2.5.0",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+[dependency-groups]
+dev = [
+    "pre-commit>=4.2.0",
+    "pytest>=8.4.1",
+    "twine>=6.1.0",
+]
+
+[project.scripts]
+datamaestro = "datamaestro.__main__:main"
+
+[project.entry-points."mkdocs.plugins"]
+datamaestro = "datamaestro.commands.site:DatasetGenerator"
+
+[build-system]
+requires = ["hatchling", "uv-dynamic-versioning"]
+build-backend = "hatchling.build"
+
+[tool.hatch.version]
+source = "uv-dynamic-versioning"
+
+[tool.uv-dynamic-versioning]
+fallback-version = "0.0.0"
+
+[tool.hatch.build.hooks.version]
+path = "src/datamaestro/version.py"
+
+[tool.mypy]
+python_version = 3.10
+warn_unused_ignores = "True"

datamaestro-1.6.0/release-notes.md

@@ -0,0 +1,5 @@
+## [1.6.0] - 2025-12-21
+
+### ⚙️ Miscellaneous Tasks
+
+- Use git cliff for release notes

{datamaestro-1.5.1 → datamaestro-1.6.0}/src/datamaestro/__init__.py

@@ -7,7 +7,6 @@ from .context import (
     prepare_dataset,
 )
 
-from pkg_resources import get_distribution, DistributionNotFound
 from .definitions import dataset, metadata
 from .data import Base
-from .version import version, version_tuple
+from .version import __version__

{datamaestro-1.5.1 → datamaestro-1.6.0}/src/datamaestro/__main__.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # flake8: noqa: T201
 
+from importlib.metadata import entry_points
 import sys
 import logging
 from functools import update_wrapper
@@ -38,7 +39,7 @@ def pass_cfg(f):
 # Get all the available repositories
 
 REPOSITORIES = {}
-for entry_point in pkg_resources.iter_entry_points("datamaestro.repositories"):
+for entry_point in entry_points(group="datamaestro.repositories"):
     REPOSITORIES[entry_point.name] = entry_point
 
 

{datamaestro-1.5.1 → datamaestro-1.6.0}/src/datamaestro/context.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Iterable, Iterator, Dict, Union
+from typing import Iterable, Iterator, Dict, Optional, Union
 import importlib
 import os
 import hashlib
@@ -8,8 +8,7 @@ import inspect
 import json
 from abc import ABC, abstractmethod
 from experimaestro import Config
-import pkg_resources
-from experimaestro.compat import cached_property
+from functools import cached_property
 from experimaestro.mkdocs.metaloader import Module
 from .utils import CachedFile, downloadURL
 from .settings import UserSettings, Settings
@@ -18,6 +17,22 @@ from typing import TYPE_CHECKING
 if TYPE_CHECKING:
     from datamaestro.definitions import AbstractDataset, DatasetWrapper
 
+from importlib.metadata import (
+    entry_points as _entry_points,
+    version as _version,
+    PackageNotFoundError as _PackageNotFoundError,
+)
+
+
+def iter_entry_points(group, name=None):
+    """Yield entry points for a given group (and optional name) using importlib.metadata."""
+    eps = _entry_points()
+    selected = eps.select(group=group)
+    if name:
+        selected = [ep for ep in selected if ep.name == name]
+    for ep in selected:
+        yield ep
+
 
 class Compression:
     @staticmethod
@@ -106,7 +121,7 @@ class Context:
 
     def repositories(self) -> Iterable["Repository"]:
         """Returns an iterator over repositories"""
-        for entry_point in pkg_resources.iter_entry_points("datamaestro.repositories"):
+        for entry_point in iter_entry_points("datamaestro.repositories"):
             yield entry_point.load().instance()
 
     def repository(self, repositoryid):
@@ -114,10 +129,7 @@ class Context:
             return None
 
         entry_points = [
-            x
-            for x in pkg_resources.iter_entry_points(
-                "datamaestro.repositories", repositoryid
-            )
+            x for x in iter_entry_points("datamaestro.repositories", repositoryid)
         ]
         if not entry_points:
             raise Exception("No datasets repository named %s", repositoryid)
@@ -299,8 +311,7 @@ class BaseRepository(ABC):
         self.basedir = Path(p).parent
 
     @abstractmethod
-    def __iter__(self) -> Iterator["AbstractDataset"]:
-        ...
+    def __iter__(self) -> Iterator["AbstractDataset"]: ...
 
     def search(self, name: str):
         """Search for a dataset in the definitions"""
@@ -353,11 +364,9 @@ class Repository(BaseRepository):
 
     @classmethod
     def version(cls):
-        from pkg_resources import get_distribution, DistributionNotFound
-
         try:
-            return get_distribution(cls.__module__).version
-        except DistributionNotFound:
+            return _version(cls.__module__)
+        except _PackageNotFoundError:
             return None
 
     def __repr__(self):
@@ -423,16 +432,23 @@ def find_dataset(dataset_id: str):
     return AbstractDataset.find(dataset_id)
 
 
-def prepare_dataset(dataset_id: Union[str, "DatasetWrapper", Config]):
+def prepare_dataset(
+    dataset_id: Union[str, "DatasetWrapper", Config],
+    context: Optional[Union[Context, Path]] = None,
+):
     """Find a dataset given its id and download the resources"""
     from .definitions import AbstractDataset, DatasetWrapper
 
+    match context:
+        case Path() | str():
+            context = Context(Path(context))
+
     if isinstance(dataset_id, DatasetWrapper):
         ds = dataset_id
     elif isinstance(dataset_id, Config):
         ds = dataset_id.__datamaestro_dataset__
     else:
-        ds = AbstractDataset.find(dataset_id)
+        ds = AbstractDataset.find(dataset_id, context=context)
 
     return ds.prepare(download=True)
 

{datamaestro-1.5.1 → datamaestro-1.6.0}/src/datamaestro/definitions.py

@@ -236,10 +236,12 @@ class AbstractDataset(AbstractData):
         return success
 
     @staticmethod
-    def find(name: str) -> "DataDefinition":
+    def find(name: str, context: Optional["Context"] = None) -> "DataDefinition":
         """Find a dataset given its name"""
         from datamaestro.context import Context  # noqa: F811
 
+        context = Context.instance() if context is None else context
+
         logging.debug("Searching dataset %s", name)
         for repository in Context.instance().repositories():
             logging.debug("Searching dataset %s in %s", name, repository)

datamaestro-1.6.0/src/datamaestro/version.py

@@ -0,0 +1,4 @@
+# This file is auto-generated by Hatchling. As such, do not:
+#   - modify
+#   - track in version control e.g. be sure to add to .gitignore
+__version__ = VERSION = '1.6.0'