datamaestro 1.5.0__tar.gz → 1.5.2__tar.gz

{datamaestro-1.5.0 → datamaestro-1.5.2}/.github/workflows/python-publish.yml

@@ -19,12 +19,11 @@ jobs:
           python-version: "3.x"
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
-          pip install setuptools wheel twine
+          python -m pip install --upgrade setuptools twine uv
       - name: Build and publish
         env:
           TWINE_USERNAME: __token__
           TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
         run: |
-          python setup.py sdist bdist_wheel
+          uv build
           twine upload dist/*

datamaestro-1.5.2/.python-version

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

{datamaestro-1.5.0 → datamaestro-1.5.2}/.readthedocs.yml

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

{datamaestro-1.5.0 → datamaestro-1.5.2}/PKG-INFO

@@ -1,42 +1,31 @@
 Metadata-Version: 2.4
 Name: datamaestro
-Version: 1.5.0
-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: 1.5.2
+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-1.5.2/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-1.5.0 → datamaestro-1.5.2}/src/datamaestro/__init__.py

@@ -10,4 +10,4 @@ from .context import (
 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-1.5.0 → datamaestro-1.5.2}/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
@@ -423,16 +423,23 @@ 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-1.5.0 → datamaestro-1.5.2}/src/datamaestro/definitions.py

@@ -204,6 +204,14 @@ class AbstractDataset(AbstractData):
         from datamaestro.data import Base
 
         if isinstance(data, Base):
+            try:
+                if data.id:
+                    # There is already an ID, skip this
+                    # and the descendants
+                    return
+            except KeyError:
+                pass
+
             if self.repository is None:
                 data.id = id
             else:
@@ -228,10 +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-1.5.2/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 = '1.5.2'