h5rdmtoolbox 2.3.1__tar.gz → 2.4.0__tar.gz

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: h5rdmtoolbox
-Version: 2.3.1
+Version: 2.4.0
 Summary: Supporting a FAIR Research Data lifecycle using Python and HDF5.
 Home-page: https://h5rdmtoolbox.readthedocs.io/en/latest/
 Author: Matthias Probst
@@ -9,31 +9,34 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Development Status :: 4 - Beta
 Classifier: Topic :: Scientific/Engineering
-Requires-Python: <3.13,>=3.9
+Requires-Python: <3.14,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: appdirs~=1.4
 Requires-Dist: importlib_resources<7.0.0,>=6.5.2
-Requires-Dist: numpy<2.0.0,>=1.20
+Requires-Dist: numpy<3.0.0,>=1.20
 Requires-Dist: h5py~=3.8
 Requires-Dist: matplotlib>=3.5.2
 Requires-Dist: IPython>=7.34.0
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: xarray>=2022.3.0
-Requires-Dist: pint==0.21.1
-Requires-Dist: pint_xarray<=0.4.0,>=0.2.1
+Requires-Dist: pint>=0.24.4
+Requires-Dist: pint_xarray<=0.6.0,>=0.2.1
 Requires-Dist: regex>=2020.7.9
 Requires-Dist: packaging>=24.1
-Requires-Dist: ontolutils<0.20.0,>=0.19.2
+Requires-Dist: ontolutils<1.0.0,>=0.21.1
 Requires-Dist: python-forge==18.6.0
 Requires-Dist: requests>=2.32.4
 Requires-Dist: pydantic~=2.8
 Requires-Dist: rdflib~=7.1
-Requires-Dist: click==8.1.7
+Requires-Dist: click>=8.1.7
+Requires-Dist: cftime>=1.6.4
+Requires-Dist: pyshacl<1.0.0,>=0.30.1
 Provides-Extra: database
 Requires-Dist: pymongo<=4.10.1,>=4.2.0; extra == "database"
 Provides-Extra: layout-validation
@@ -51,12 +54,12 @@ Provides-Extra: test
 Requires-Dist: pytest>=8.3.3; extra == "test"
 Requires-Dist: pytest-cov>=5.0.0; extra == "test"
 Requires-Dist: pylint; extra == "test"
-Requires-Dist: scikit-image; extra == "test"
-Requires-Dist: ssnolib>=1.5.1.2; extra == "test"
+Requires-Dist: ssnolib>=1.5.1.4; extra == "test"
 Requires-Dist: mongomock==4.1.2; extra == "test"
 Requires-Dist: xmltodict<=0.13.0; extra == "test"
 Requires-Dist: scipy>=1.10.1; extra == "test"
 Requires-Dist: scikit-image>=0.21.0; extra == "test"
+Requires-Dist: scikit-learn; extra == "test"
 Requires-Dist: pandas>=1.4.3; extra == "test"
 Requires-Dist: xmltodict<=0.13.0; extra == "test"
 Requires-Dist: tabulate<=0.9.0,>=0.8.10; extra == "test"
@@ -73,12 +76,12 @@ Requires-Dist: pymongo<=4.10.1,>=4.2.0; extra == "docs"
 Requires-Dist: pytest>=8.3.3; extra == "docs"
 Requires-Dist: pytest-cov>=5.0.0; extra == "docs"
 Requires-Dist: pylint; extra == "docs"
-Requires-Dist: scikit-image; extra == "docs"
-Requires-Dist: ssnolib>=1.5.1.2; extra == "docs"
+Requires-Dist: ssnolib>=1.5.1.4; extra == "docs"
 Requires-Dist: mongomock==4.1.2; extra == "docs"
 Requires-Dist: xmltodict<=0.13.0; extra == "docs"
 Requires-Dist: scipy>=1.10.1; extra == "docs"
 Requires-Dist: scikit-image>=0.21.0; extra == "docs"
+Requires-Dist: scikit-learn; extra == "docs"
 Requires-Dist: pandas>=1.4.3; extra == "docs"
 Requires-Dist: xmltodict<=0.13.0; extra == "docs"
 Requires-Dist: tabulate<=0.9.0,>=0.8.10; extra == "docs"
@@ -99,12 +102,12 @@ Requires-Dist: PyQt5==5.15.10; extra == "complete"
 Requires-Dist: pytest>=8.3.3; extra == "complete"
 Requires-Dist: pytest-cov>=5.0.0; extra == "complete"
 Requires-Dist: pylint; extra == "complete"
-Requires-Dist: scikit-image; extra == "complete"
-Requires-Dist: ssnolib>=1.5.1.2; extra == "complete"
+Requires-Dist: ssnolib>=1.5.1.4; extra == "complete"
 Requires-Dist: mongomock==4.1.2; extra == "complete"
 Requires-Dist: xmltodict<=0.13.0; extra == "complete"
 Requires-Dist: scipy>=1.10.1; extra == "complete"
 Requires-Dist: scikit-image>=0.21.0; extra == "complete"
+Requires-Dist: scikit-learn; extra == "complete"
 Requires-Dist: pandas>=1.4.3; extra == "complete"
 Requires-Dist: xmltodict<=0.13.0; extra == "complete"
 Requires-Dist: tabulate<=0.9.0,>=0.8.10; extra == "complete"
@@ -117,12 +120,12 @@ Requires-Dist: PyQt5==5.15.10; extra == "complete-with-docs"
 Requires-Dist: pytest>=8.3.3; extra == "complete-with-docs"
 Requires-Dist: pytest-cov>=5.0.0; extra == "complete-with-docs"
 Requires-Dist: pylint; extra == "complete-with-docs"
-Requires-Dist: scikit-image; extra == "complete-with-docs"
-Requires-Dist: ssnolib>=1.5.1.2; extra == "complete-with-docs"
+Requires-Dist: ssnolib>=1.5.1.4; extra == "complete-with-docs"
 Requires-Dist: mongomock==4.1.2; extra == "complete-with-docs"
 Requires-Dist: xmltodict<=0.13.0; extra == "complete-with-docs"
 Requires-Dist: scipy>=1.10.1; extra == "complete-with-docs"
 Requires-Dist: scikit-image>=0.21.0; extra == "complete-with-docs"
+Requires-Dist: scikit-learn; extra == "complete-with-docs"
 Requires-Dist: pandas>=1.4.3; extra == "complete-with-docs"
 Requires-Dist: xmltodict<=0.13.0; extra == "complete-with-docs"
 Requires-Dist: tabulate<=0.9.0,>=0.8.10; extra == "complete-with-docs"
@@ -138,12 +141,12 @@ Requires-Dist: pymongo<=4.10.1,>=4.2.0; extra == "complete-with-docs"
 Requires-Dist: pytest>=8.3.3; extra == "complete-with-docs"
 Requires-Dist: pytest-cov>=5.0.0; extra == "complete-with-docs"
 Requires-Dist: pylint; extra == "complete-with-docs"
-Requires-Dist: scikit-image; extra == "complete-with-docs"
-Requires-Dist: ssnolib>=1.5.1.2; extra == "complete-with-docs"
+Requires-Dist: ssnolib>=1.5.1.4; extra == "complete-with-docs"
 Requires-Dist: mongomock==4.1.2; extra == "complete-with-docs"
 Requires-Dist: xmltodict<=0.13.0; extra == "complete-with-docs"
 Requires-Dist: scipy>=1.10.1; extra == "complete-with-docs"
 Requires-Dist: scikit-image>=0.21.0; extra == "complete-with-docs"
+Requires-Dist: scikit-learn; extra == "complete-with-docs"
 Requires-Dist: pandas>=1.4.3; extra == "complete-with-docs"
 Requires-Dist: xmltodict<=0.13.0; extra == "complete-with-docs"
 Requires-Dist: tabulate<=0.9.0,>=0.8.10; extra == "complete-with-docs"
@@ -165,7 +168,7 @@ Dynamic: license-file
 ![Tests](https://github.com/matthiasprobst/h5RDMtoolbox/actions/workflows/tests.yml/badge.svg)
 [![codecov](https://codecov.io/gh/matthiasprobst/h5RDMtoolbox/graph/badge.svg?token=IVG4AQEW47)](https://codecov.io/gh/matthiasprobst/h5RDMtoolbox)
 [![Documentation Status](https://readthedocs.org/projects/h5rdmtoolbox/badge/?version=latest)](https://h5rdmtoolbox.readthedocs.io/en/latest/?badge=latest)
-![pyvers](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)
+![pyvers](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue)
 
 *Note, that the project is still under development!*
 
@@ -256,11 +259,12 @@ A paper is published in the journal [inggrid](https://preprints.inggrid.org/repo
 
 ## Installation
 
-Use python 3.8 or higher (automatic testing is performed until 3.12). If you are a regular user, you can install the
+Use python 3.9 or higher (automatic testing is performed until 3.13). If you are a regular user, you can install the
 package via pip:
 
     pip install h5RDMtoolbox
 
+
 ### Install from source:
 
 Developers may clone the repository and install the package from source. Clone the repository first:
@@ -293,7 +297,7 @@ specific to the features of the package:
 
 **Specific to the package are ...**
 
-- `h5py=3.7.0`: HDF5 file interface
+- `h5py~=3.8`: HDF5 file interface
 - `xarray>=2022.3.0`: Working with scientific arrays in combination with attributes. Allows carrying metadata from HDF5
   to user
 - `pint>=0.19.2`: Allows working with units
@@ -334,10 +338,12 @@ Install optional dependencies by specifying them in square brackets after the pa
 ## Citing the package
 
 If you intend to use the package in your work, you may cite the software itself as published on paper in the
-[Zenodo](https://zenodo.org/records/14473697) repository. A related paper is published in the
+[Zenodo (latest version)](https://zenodo.org/records/13309253) repository. A related paper is published in the
 journal [inggrid](https://www.inggrid.org/article/id/4028/). Thank you!
 
-Here's the bibtext to it:
+Alternatively or additionally, you can consult the `CITATION.cff` file.
+
+Here is the BibTeX entry:
 
 ```
 @article{probst2024h5rdmtoolbox,

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/README.md

@@ -3,7 +3,7 @@
 ![Tests](https://github.com/matthiasprobst/h5RDMtoolbox/actions/workflows/tests.yml/badge.svg)
 [![codecov](https://codecov.io/gh/matthiasprobst/h5RDMtoolbox/graph/badge.svg?token=IVG4AQEW47)](https://codecov.io/gh/matthiasprobst/h5RDMtoolbox)
 [![Documentation Status](https://readthedocs.org/projects/h5rdmtoolbox/badge/?version=latest)](https://h5rdmtoolbox.readthedocs.io/en/latest/?badge=latest)
-![pyvers](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)
+![pyvers](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue)
 
 *Note, that the project is still under development!*
 
@@ -94,11 +94,12 @@ A paper is published in the journal [inggrid](https://preprints.inggrid.org/repo
 
 ## Installation
 
-Use python 3.8 or higher (automatic testing is performed until 3.12). If you are a regular user, you can install the
+Use python 3.9 or higher (automatic testing is performed until 3.13). If you are a regular user, you can install the
 package via pip:
 
     pip install h5RDMtoolbox
 
+
 ### Install from source:
 
 Developers may clone the repository and install the package from source. Clone the repository first:
@@ -131,7 +132,7 @@ specific to the features of the package:
 
 **Specific to the package are ...**
 
-- `h5py=3.7.0`: HDF5 file interface
+- `h5py~=3.8`: HDF5 file interface
 - `xarray>=2022.3.0`: Working with scientific arrays in combination with attributes. Allows carrying metadata from HDF5
   to user
 - `pint>=0.19.2`: Allows working with units
@@ -172,10 +173,12 @@ Install optional dependencies by specifying them in square brackets after the pa
 ## Citing the package
 
 If you intend to use the package in your work, you may cite the software itself as published on paper in the
-[Zenodo](https://zenodo.org/records/14473697) repository. A related paper is published in the
+[Zenodo (latest version)](https://zenodo.org/records/13309253) repository. A related paper is published in the
 journal [inggrid](https://www.inggrid.org/article/id/4028/). Thank you!
 
-Here's the bibtext to it:
+Alternatively or additionally, you can consult the `CITATION.cff` file.
+
+Here is the BibTeX entry:
 
 ```
 @article{probst2024h5rdmtoolbox,

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/__init__.py

@@ -2,6 +2,7 @@
 
 import logging
 import pathlib
+import warnings
 from logging.handlers import RotatingFileHandler
 from typing import Optional, Dict
 
@@ -53,6 +54,7 @@ from .wrapper.h5attr import Attribute
 import json
 from .wrapper.accessor import register_accessor
 
+from .ld.shacl import validate_hdf, ValidationResult
 # noinspection PyUnresolvedReferences
 from .utils import DownloadFileManager
 
@@ -62,7 +64,7 @@ __author__ = 'Matthias Probst'
 __author_orcid__ = 'https://orcid.org/0000-0001-8729-0482'
 
 
-def get_package_meta():
+def get_package_meta() -> Dict:
     """Reads codemeta.json and returns it as dict"""
     with open(__this_dir__ / '../codemeta.json', 'r') as f:
         codemeta = json.loads(f.read())
@@ -168,11 +170,66 @@ def dump_jsonld(
     )
 
 
+# def shacl_validate(
+#         *,
+#         hdf_data: Union[str, rdflib.Graph] = None,
+#         hdf_source: Union[h5py.File, pathlib.Path] = None,
+#         shacl_data: Union[str, rdflib.Graph] = None,
+#         shacl_source: Union[str, pathlib.Path] = None,
+#         hdf_file_uri="https://example.org/hdf5file#",
+#         shacl_format: str = 'turtle',
+#         hdf_data_format: str = 'turtle',
+#         **pyshacl_kwargs
+# ) -> ValidationResult:
+#     """Validate HDF5 file content against SHACL shapes.
+#
+#     Parameters
+#     ----------
+#     hdf_data : Union[str, rdflib.Graph], optional
+#         RDF data of the HDF5 file as string or rdflib.Graph. If not
+#         provided, `hdf_source` must be provided.
+#     hdf_source : Union[h5py.File, pathlib.Path], optional
+#         HDF5 file or h5py.File object to extract RDF data from. If not
+#         provided, `hdf_data` must be provided.
+#     shacl_data : Union[str, rdflib.Graph], optional
+#         SHACL shapes as string or rdflib.Graph. If not provided,
+#         `shacl_source` must be provided.
+#     shacl_source : Union[str, pathlib.Path], optional
+#         File path to SHACL shapes. If not provided, `shacl_data`
+#         must be provided.
+#     hdf_file_uri : str, optional
+#         The file URI to use for the HDF5 file when extracting RDF data.
+#         Default is "https://example.org/hdf5file#".
+#     shacl_format : str, optional
+#         The format of the SHACL shapes if `shacl_data` is provided as
+#         string. Default is 'turtle'.
+#     hdf_data_format : str, optional
+#         The format of the HDF5 RDF data if `hdf_data` is provided as
+#         string. Default is 'turtle'.
+#     **pyshacl_kwargs
+#         Additional keyword arguments passed to pyshacl.validate().
+#
+#     Returns
+#     -------
+#     ValidationResult
+#         The result of the SHACL validation.
+#     """
+#     return validate_hdf(
+#         hdf_data=hdf_data,
+#         hdf_source=hdf_source,
+#         shacl_data=shacl_data,
+#         shacl_source=shacl_source,
+#         hdf_file_uri=hdf_file_uri,
+#         shacl_format=shacl_format,
+#         hdf_data_format=hdf_data_format,
+#         **pyshacl_kwargs
+#     )
+
+
 def dump_jsonld_depr(hdf_filename: Union[str, pathlib.Path],
                      skipND: int = 1,
                      structural: bool = True,
                      contextual: bool = True,
-                     resolve_keys: bool = True,
                      context: Optional[Dict] = None,
                      blank_node_iri_base: Optional[str] = None
                      ) -> str:
@@ -189,19 +246,12 @@ def dump_jsonld_depr(hdf_filename: Union[str, pathlib.Path],
         considered if structural=True.
     structural : bool=True
         Include structural information in the JSON-LD output.
-    semantic : bool=True
-        Include semantic information in the JSON-LD output.
-    resolve_keys : bool=True
-        Resolve keys in the JSON-LD output. This is used when semantic=True.
-        If resolve_keys is False and an attribute name in the HDF5 file, which has
-        a predicate is different in its name from the predicate, the attribute name is used.
-        Example: an attribute "name" is associated with "foaf:lastName", then "name" is used
-        and "name": "http://xmlns.com/foaf/0.1/lastName" is added to the context.
+    contextual : bool=True
+        Include contextual information in the JSON-LD output.
     context: Optional[Dict]
         context in form of {prefix: IRI}, e.g. "ssno": "https://matthiasprobst.github.io/ssno#"
-        If resolve_keys is True, this is added to the built-in look-up table to be used in the
-        context part of JSON-LD
-
+    blank_node_iri_base: Optional[str]
+        IRI base used for blank nodes
     """
     if blank_node_iri_base is not None:
         if not isinstance(blank_node_iri_base, (str, HttpUrl)):
@@ -212,20 +262,18 @@ def dump_jsonld_depr(hdf_filename: Union[str, pathlib.Path],
 
     from h5rdmtoolbox.ld.hdf.file import get_serialized_ld
     if structural and not contextual:
-        return get_serialized_ld(hdf_filename, blank_node_iri_base, format="json-ld", context=context,
-                                 contextual=contextual, skipND=skipND)
-    return get_serialized_ld(hdf_filename, blank_node_iri_base, format="json-ld", context=context,
-                             contextual=contextual, skipND=skipND)
-    # with File(hdf_filename) as h5:
-    #     return jsonld.dumps(
-    #         h5,
-    #         structural=structural,
-    #         resolve_keys=resolve_keys,
-    #         context=context,
-    #         blank_node_iri_base=blank_node_iri_base,
-    #         skipND=skipND,
-    #         **kwargs
-    #     )
+        return get_serialized_ld(
+            hdf_filename,
+            blank_node_iri_base,
+            format="json-ld",
+            context=context,
+            skipND=skipND)
+    return get_serialized_ld(
+        hdf_filename,
+        blank_node_iri_base,
+        format="json-ld",
+        context=context,
+        skipND=skipND)
 
 
 def serialize(hdf_filename,
@@ -237,6 +285,11 @@ def serialize(hdf_filename,
               **kwargs):
     """Alternative to json-ld but allows multiple serialization options"""
     fmt = kwargs.pop("format", fmt)
+    if file_uri is None:
+        warnings.warn(
+            "Not providing a file-uri is not good practice because it will generate blank nodes. Consider providing an URI such as the DOI URL for example.",
+            category=UserWarning
+        )
     with File(hdf_filename) as h5:
         return h5.serialize(fmt=fmt,
                             skipND=skipND,
@@ -257,7 +310,7 @@ def build_pyvis_graph(hdf_filename, output_filename="kg-graph.html", notebook=Fa
     kg = kglab.KnowledgeGraph().load_rdf_text(
         serialize(hdf_filename, fmt="ttl", structural=structural, contextual=contextual)
     )
-    VIS_STYLE = style or {
+    vis_style = style or {
         "hdf": {
             "color": "orange",
             "size": 40,
@@ -268,7 +321,7 @@ def build_pyvis_graph(hdf_filename, output_filename="kg-graph.html", notebook=Fa
         },
     }
     subgraph = kglab.SubgraphTensor(kg)
-    pyvis_graph = subgraph.build_pyvis_graph(notebook=notebook, style=VIS_STYLE)
+    pyvis_graph = subgraph.build_pyvis_graph(notebook=notebook, style=vis_style)
     pyvis_graph.force_atlas_2based()
     pyvis_graph.show(output_filename)
     return pyvis_graph
@@ -300,7 +353,7 @@ def register_dataset_decoder(decoder: Callable, decoder_name: str = None, overwr
     ds_decoder.registered_dataset_decoders[decoder_name] = decoder
 
 
-atexit_verbose = False
+_ATEXIT_VERBOSE = False
 
 
 def set_loglevel(level: Union[int, str]):
@@ -329,18 +382,18 @@ def clean_temp_data(full: bool = False):
         return
 
     for _tmp_session_dir in [UserDir['tmp'], ]:
-        if atexit_verbose:
+        if _ATEXIT_VERBOSE:
             print(f'cleaning up tmp directory "{_tmp_session_dir}"')
         if _tmp_session_dir.exists():
             try:
-                if atexit_verbose:
+                if _ATEXIT_VERBOSE:
                     print(f'try deleting tmp in session dir: {_tmp_session_dir}')
                 shutil.rmtree(_tmp_session_dir)
             except PermissionError as e:
-                if atexit_verbose:
+                if _ATEXIT_VERBOSE:
                     print(f'[!] failed deleting tmp session dir: {_tmp_session_dir}')
                 failed_dirs.append(UserDir['tmp'])
-                if atexit_verbose:
+                if _ATEXIT_VERBOSE:
                     print(f'removing tmp folder "{_tmp_session_dir}" failed due to "{e}". Best is you '
                           f'manually delete the directory.')
             finally:
@@ -372,4 +425,5 @@ __all__ = ('__version__', '__author__', '__author_orcid__',
            'File', 'Group', 'Dataset', 'Attribute',
            'dump', 'dumps', 'cv_h5py', 'lower', 'Lower',
            'set_config', 'get_config', 'get_ureg',
-           'Convention', 'jsonld', 'lazy', 'DownloadFileManager')
+           'Convention', 'jsonld', 'lazy', 'DownloadFileManager',
+           'clean_temp_data')

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/_cfg.py

@@ -28,7 +28,7 @@ CONFIG = {
     'require_unit': True,  # datasets require units
     'ureg_format': 'C~',
     'init_logger_level': 'ERROR',
-    'dtime_fmt': '%Y%m%d%H%M%S%f',
+    'dtime_fmt': '%Y-%m-%dT%H:%M:%S%f',
     'expose_user_prop_to_attrs': True,
     'add_provenance': False,
     'ignore_set_std_attr_err': False,
@@ -73,7 +73,7 @@ class set_config:
                 raise KeyError(f'Not a configuration key: "{k}"')
             self.old[k] = CONFIG[k]
             if k == 'ureg_format':
-                get_ureg().default_format = str(v)
+                get_ureg().formatter.default_format = str(v)
         self._update(kwargs)
 
     def __enter__(self):

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/convention/core.py

@@ -13,6 +13,8 @@ import yaml
 from pydoc import locate
 from typing import Union, List, Dict, Tuple, Any
 
+from forge import kwargs
+
 from h5rdmtoolbox import errors
 from h5rdmtoolbox.repository import RepositoryInterface
 from h5rdmtoolbox.wrapper import ds_decoder
@@ -696,24 +698,19 @@ def from_json(filename: Union[str, pathlib.Path], overwrite: bool = False) -> Co
 
 
 def from_repo(repo_interface: RepositoryInterface,
-              name: str,
-              take_existing: bool = True,
-              force_download: bool = False):
-    """Download a YAML file from a repository"""
-    # check if file exists:
-    # path_compatible_doi = repo_interface.get_doi().replace('/', '_')
-    # estimated_filename = UserDir['cache'] / f'{path_compatible_doi}' / name
-    # estimated_filename.parent.mkdir(parents=True, exist_ok=True)
-    # if estimated_filename.exists():
-    #     if not take_existing:
-    #         raise FileExistsError(f'File {name} exists in cache but take_existing is set to False.')
-    #     if take_existing and not force_download:
-    #         return from_file(estimated_filename)
+              name: str):
+    """Download a YAML file from a repository
 
+    Parameters
+    ----------
+    repo_interface: RepositoryInterface
+        The repository interface to use for downloading the file
+    name: str
+        Name of the file to download
+    """
+    logger.debug(f"Downloading file {name} from repository {repo_interface}")
     filename = repo_interface.download_file(name)
-    # if estimated_filename.exists():
-    #     estimated_filename.unlink()
-    # filename.rename(estimated_filename)
+    logger.debug(f"File downloaded to {filename}. Now loading convention from file.")
     return from_file(filename)
 
 
@@ -723,7 +720,7 @@ def from_zenodo(doi_or_recid: str,
                 force_download: bool = False) -> Convention:
     """Download a YAML file from a zenodo repository
 
-    Depreciated. Use `from_repo` in future.
+    Depreciated. Use `from_repo` in the future.
 
     Parameters
     ----------

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/convention/utils.py

@@ -97,8 +97,8 @@ def get_similar_names_ratio(a, b):
 # def equal_base_units(unit1, unit2):
 #     """Return if two units are equivalent"""
 #
-#     base_unit1 = get_ureg()(unit1).to_base_units().units.__format__(get_ureg().default_format)
-#     base_unit2 = get_ureg()(unit2).to_base_units().units.__format__(get_ureg().default_format)
+#     base_unit1 = get_ureg()(unit1).to_base_units().units.__format__(get_ureg().formatter.default_format)
+#     base_unit2 = get_ureg()(unit2).to_base_units().units.__format__(get_ureg().formatter.default_format)
 #     return base_unit1 == base_unit2
 
 

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/data/tutorial_convention.yaml

@@ -36,7 +36,7 @@ standard_name:
 standard_name_table:
   target_method: __init__
   validator: $standardNameTableType
-  default_value: https://zenodo.org/records/15300151/files/fan_standard_name_table.jsonld
+  default_value: https://zenodo.org/records/17331305/files/fan_standard_name_table.jsonld
   requirements:
     - standard_name
     - units

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/data/tutorial_standard_name_table.yaml

@@ -10,8 +10,8 @@
     },
     "@type": "ssno:StandardNameTable",
     "dcterms:title": "fan_standard_name_shorttable",
-    "dcterms:hasVersion": "v5.0.0",
-    "identifier": "10.5281/zenodo.15300151",
+    "schema:version": "5.0.0",
+    "identifier": "10.5281/zenodo.17331305",
     "dcterms:modified": "2023-07-18 09:05:38.112885+00:00",
     "ssno:standardNames": [
         {
@@ -386,5 +386,5 @@
             "@id": "_:N3354c7311dee428391ae501b6ebc8bba"
         }
     ],
-    "@id": "https://doi.org/10.5281/zenodo.15300151"
+    "@id": "https://doi.org/10.5281/zenodo.17331305"
 }

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/extensions/units.py

@@ -16,7 +16,7 @@ class ToUnitsInterface:
         self.coord_units = coord_units
 
     def _convert_units(self, data: xr.DataArray):
-        assert isinstance(data, xr.DataArray)
+        assert isinstance(data, xr.DataArray), 'Data is not an xarray DataArray'
         assert 'units' in data.attrs, 'No units attribute found in the dataset'
         for c, cn in self.coord_units.items():
             assert 'units' in data.coords[c].attrs, f'No units attribute found in the coordinate {c}'
@@ -42,4 +42,7 @@ class ToUnitsAccessor(Accessor):
     """Accessor to await selected data to be converted to a new units"""
 
     def __call__(self, dataset_unit: Optional[str] = None, **coord_units) -> ToUnitsInterface:
+        if isinstance(dataset_unit, dict):  # fix for pint-xarray > 0.4.0
+            coord_units = dataset_unit
+            dataset_unit = None
         return ToUnitsInterface(self._obj, dataset_unit=dataset_unit, **coord_units)

{h5rdmtoolbox-2.3.1 → h5rdmtoolbox-2.4.0}/h5rdmtoolbox/ld/__init__.py

@@ -1,5 +1,4 @@
 import pathlib
-import warnings
 from typing import Union, Optional, Dict
 
 import h5py
@@ -18,7 +17,8 @@ def get_ld(
         skipND: Optional[int] = 1,
         context: Optional[Dict] = None) -> rdflib.Graph:
     """Return the HDF file content as a rdflib.Graph object."""
-
+    if file_uri and not (str(file_uri)).endswith("#"):
+        file_uri = f"{file_uri}#"
     graph = None
     with h5py.File(hdf_filename) as h5:
         if contextual and structural:
@@ -50,8 +50,61 @@ def hdf2jsonld(
         file_uri: Optional[str] = None,
         skipND: Optional[int] = 1,
 ):
+    return _hdf2ld(
+        filename=filename,
+        fmt='json-ld',
+        metadata_filename=metadata_filename,
+        context=context,
+        structural=structural,
+        contextual=contextual,
+        indent=indent,
+        file_uri=file_uri,
+        skipND=skipND,
+    )
+
+
+def hdf2ttl(
+        filename: Union[str, pathlib.Path],
+        metadata_filename: Optional[Union[str, pathlib.Path]] = None,
+        context: Optional[dict] = None,
+        structural: bool = True,
+        contextual: bool = True,
+        indent: int = 2,
+        file_uri: Optional[str] = None,
+        skipND: Optional[int] = 1,
+):
+    return _hdf2ld(
+        filename=filename,
+        fmt='ttl',
+        metadata_filename=metadata_filename,
+        context=context,
+        structural=structural,
+        contextual=contextual,
+        indent=indent,
+        file_uri=file_uri,
+        skipND=skipND,
+    )
+
+
+def _hdf2ld(
+        filename: Union[str, pathlib.Path],
+        fmt: str,
+        metadata_filename: Optional[Union[str, pathlib.Path]] = None,
+        context: Optional[dict] = None,
+        structural: bool = True,
+        contextual: bool = True,
+        indent: int = 2,
+        file_uri: Optional[str] = None,
+        skipND: Optional[int] = 1,
+):
+    if fmt in ('json', 'json-ld', 'jsonld'):
+        suffix = '.jsonld'
+    elif fmt in ('turtle', 'ttl'):
+        suffix = '.ttl'
+    else:
+        raise ValueError(f"Format '{fmt}' currently not supported. Use 'json-ld' or 'ttl'.")
     if metadata_filename is None:
-        metadata_filename = pathlib.Path(filename).with_suffix('.jsonld')  # recommended suffix for JSON-LD is .jsonld!
+        metadata_filename = pathlib.Path(filename).with_suffix(suffix)  # recommended suffix for JSON-LD is .jsonld!
     else:
         metadata_filename = pathlib.Path(metadata_filename)
 
@@ -67,7 +120,7 @@ def hdf2jsonld(
 
     with open(metadata_filename, 'w', encoding='utf-8') as f:
         f.write(
-            graph.serialize(format='json-ld',
+            graph.serialize(format=fmt,
                             indent=indent,
                             auto_compact=True,
                             context=context)