h5rdmtoolbox 2.0.0a0__tar.gz → 2.2.0__tar.gz

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/PKG-INFO

@@ -1,11 +1,10 @@
 Metadata-Version: 2.4
 Name: h5rdmtoolbox
-Version: 2.0.0a0
+Version: 2.2.0
 Summary: Supporting a FAIR Research Data lifecycle using Python and HDF5.
 Home-page: https://h5rdmtoolbox.readthedocs.io/en/latest/
 Author: Matthias Probst
 Author-email: matth.probst@gmail.com
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
@@ -14,22 +13,22 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Development Status :: 4 - Beta
 Classifier: Topic :: Scientific/Engineering
-Requires-Python: <3.13,>=3.8
+Requires-Python: <3.13,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: appdirs>=1.4.4
-Requires-Dist: importlib_resources
+Requires-Dist: importlib_resources<7.0.0,>=6.5.2
 Requires-Dist: numpy<2.0.0,>=1.20
-Requires-Dist: h5py>3.7.0
+Requires-Dist: h5py<4.0.0,>=3.8.0
 Requires-Dist: matplotlib>=3.5.2
 Requires-Dist: IPython>=7.34.0
-Requires-Dist: pyyaml>6.0
+Requires-Dist: pyyaml>=6.0
 Requires-Dist: xarray>=2022.3.0
 Requires-Dist: pint==0.21.1
-Requires-Dist: pint_xarray>=0.2.1
+Requires-Dist: pint_xarray<=0.4.0,>=0.2.1
 Requires-Dist: regex>=2020.7.9
 Requires-Dist: packaging>=24.1
-Requires-Dist: ontolutils>=0.13.3
+Requires-Dist: ontolutils<=1.0.0,>=0.13.3
 Requires-Dist: python-forge==18.6.0
 Requires-Dist: requests>=2.32.3
 Requires-Dist: pydantic>=2.8.2
@@ -53,7 +52,7 @@ 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>=1.5.0.1; extra == "test"
+Requires-Dist: ssnolib>=1.5.1.2; 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"
@@ -75,7 +74,7 @@ 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>=1.5.0.1; extra == "docs"
+Requires-Dist: ssnolib>=1.5.1.2; 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"
@@ -101,7 +100,7 @@ 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>=1.5.0.1; extra == "complete"
+Requires-Dist: ssnolib>=1.5.1.2; 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"
@@ -112,43 +111,61 @@ Requires-Dist: tabulate<=0.9.0,>=0.8.10; extra == "complete"
 Requires-Dist: python-gitlab; extra == "complete"
 Requires-Dist: pypandoc>=1.11; extra == "complete"
 Requires-Dist: pymongo<=4.10.1,>=4.2.0; 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"
-Requires-Dist: python-gitlab; extra == "complete"
-Requires-Dist: pypandoc>=1.11; extra == "complete"
-Requires-Dist: pymongo<=4.10.1,>=4.2.0; 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>=1.5.0.1; 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: 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"
-Requires-Dist: python-gitlab; extra == "complete"
-Requires-Dist: pypandoc>=1.11; extra == "complete"
-Requires-Dist: pymongo<=4.10.1,>=4.2.0; extra == "complete"
-Requires-Dist: Sphinx==8.0.0; extra == "complete"
-Requires-Dist: sphinx_book_theme==1.1.3; extra == "complete"
-Requires-Dist: sphinx-copybutton==0.5.2; extra == "complete"
-Requires-Dist: sphinx-design==0.6.1; extra == "complete"
-Requires-Dist: myst-nb==1.2.0; extra == "complete"
-Requires-Dist: sphinxcontrib-bibtex==2.6.3; extra == "complete"
-Requires-Dist: scikit-image>=0.21.0; extra == "complete"
-Requires-Dist: scikit-learn; extra == "complete"
+Provides-Extra: complete-with-docs
+Requires-Dist: tabulate<=0.9.0,>=0.8.10; extra == "complete-with-docs"
+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: 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: 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"
+Requires-Dist: python-gitlab; extra == "complete-with-docs"
+Requires-Dist: pypandoc>=1.11; extra == "complete-with-docs"
+Requires-Dist: pymongo<=4.10.1,>=4.2.0; 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"
+Requires-Dist: python-gitlab; extra == "complete-with-docs"
+Requires-Dist: pypandoc>=1.11; extra == "complete-with-docs"
+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: 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: 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"
+Requires-Dist: python-gitlab; extra == "complete-with-docs"
+Requires-Dist: pypandoc>=1.11; extra == "complete-with-docs"
+Requires-Dist: pymongo<=4.10.1,>=4.2.0; extra == "complete-with-docs"
+Requires-Dist: Sphinx==8.0.0; extra == "complete-with-docs"
+Requires-Dist: sphinx_book_theme==1.1.3; extra == "complete-with-docs"
+Requires-Dist: sphinx-copybutton==0.5.2; extra == "complete-with-docs"
+Requires-Dist: sphinx-design==0.6.1; extra == "complete-with-docs"
+Requires-Dist: myst-nb==1.2.0; extra == "complete-with-docs"
+Requires-Dist: sphinxcontrib-bibtex==2.6.3; extra == "complete-with-docs"
+Requires-Dist: scikit-image>=0.21.0; extra == "complete-with-docs"
+Requires-Dist: scikit-learn; extra == "complete-with-docs"
 Dynamic: license-file
 
 # HDF5 Research Data Management Toolbox
 
 ![Tests](https://github.com/matthiasprobst/h5RDMtoolbox/actions/workflows/tests.yml/badge.svg)
-![DOCS](https://codecov.io/gh/matthiasprobst/h5RDMtoolbox/branch/dev/graph/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-3.8%20%7C%203.9%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-blue)
 
 *Note, that the project is still under development!*
 

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/README.md

@@ -1,9 +1,9 @@
 # HDF5 Research Data Management Toolbox
 
 ![Tests](https://github.com/matthiasprobst/h5RDMtoolbox/actions/workflows/tests.yml/badge.svg)
-![DOCS](https://codecov.io/gh/matthiasprobst/h5RDMtoolbox/branch/dev/graph/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-3.8%20%7C%203.9%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-blue)
 
 *Note, that the project is still under development!*
 

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/__init__.py

@@ -129,44 +129,53 @@ def get_ld(
         structural: bool = True,
         contextual: bool = True,
         skipND: int = 1,
-        blank_node_iri_base: Optional[str] = None,
-        **kwargs) -> rdflib.Graph:
+        file_uri: Optional[str] = None,
+        context: Optional[Dict] = None
+) -> rdflib.Graph:
     """Return the HDF file content as a rdflib.Graph object."""
     from h5rdmtoolbox.ld import get_ld
-    return get_ld(hdf_filename, structural=structural, contextual=contextual, skipND=skipND,
-                  blank_node_iri_base=blank_node_iri_base, **kwargs)
+    return get_ld(hdf_filename,
+                  structural=structural,
+                  contextual=contextual,
+                  skipND=skipND,
+                  file_uri=file_uri,
+                  context=context)
 
 
 def dump_jsonld(
         hdf_filename: Union[str, pathlib.Path],
         skipND: int = 1,
+        indent: int = 2,
         structural: bool = True,
         contextual: bool = True,
         context: Optional[Dict] = None,
-        blank_node_iri_base: Optional[str] = None,
-        **kwargs):
+        file_uri: Optional[str] = None
+):
     """Return the file content as a JSON-LD string."""
     from .ld import optimize_context
     context = context or {}
     graph = get_ld(hdf_filename,
                    structural=structural,
                    contextual=contextual,
-                   blank_node_iri_base=blank_node_iri_base,
-                   skipND=skipND,
-                   **kwargs)
+                   file_uri=file_uri,
+                   skipND=skipND)
     context = optimize_context(graph, context)
-    return graph.serialize(format="json-ld", indent=2, auto_compact=True,
-                           context=context)
+    return graph.serialize(
+        format="json-ld",
+        indent=indent,
+        auto_compact=True,
+        context=context
+    )
 
 
 def dump_jsonld_depr(hdf_filename: Union[str, pathlib.Path],
                      skipND: int = 1,
                      structural: bool = True,
-                     semantic: bool = True,
+                     contextual: bool = True,
                      resolve_keys: bool = True,
                      context: Optional[Dict] = None,
-                     blank_node_iri_base: Optional[str] = None,
-                     **kwargs) -> str:
+                     blank_node_iri_base: Optional[str] = None
+                     ) -> str:
     """Dump the JSON-LD representation of the file. With semantic=True and structural=False, the JSON-LD
     represents the semantic content only. To get a pure structural representation, set semantic=False, which
     will ignore any RDF content. If both are set to True, the JSON-LD will contain both structural and semantic.
@@ -198,13 +207,15 @@ def dump_jsonld_depr(hdf_filename: Union[str, pathlib.Path],
         if not isinstance(blank_node_iri_base, (str, HttpUrl)):
             raise ValueError('blank_node_iri_base must be a valid URL')
     from .wrapper import jsonld
-    if not structural and not semantic:
-        raise ValueError('At least one of structural or semantic must be True.')
+    if not structural and not contextual:
+        raise ValueError('At least one of structural or contextual must be True.')
 
     from h5rdmtoolbox.ld.hdf.file import get_serialized_ld
-    if structural and not semantic:
-        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)
+    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,
@@ -221,20 +232,17 @@ def serialize(hdf_filename,
               fmt: str = "ttl",
               skipND: int = 1,
               structural: bool = True,
-              semantic: bool = True,
-              resolve_keys: bool = True,
-              blank_node_iri_base: Optional[str] = None,
+              contextual: bool = True,
+              file_uri: Optional[str] = None,
               **kwargs):
     """Alternative to json-ld but allows multiple serialization options"""
     fmt = kwargs.pop("format", fmt)
     with File(hdf_filename) as h5:
-        return h5.serialize(fmt,
-                            skipND,
+        return h5.serialize(fmt=fmt,
+                            skipND=skipND,
                             structural=structural,
-                            semantic=semantic,
-                            resolve_keys=resolve_keys,
-                            blank_node_iri_base=blank_node_iri_base,
-                            **kwargs)
+                            contextual=contextual,
+                            file_uri=file_uri)
 
 
 def build_pyvis_graph(hdf_filename, output_filename="kg-graph.html", notebook=False,

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/_repr.py

@@ -585,12 +585,14 @@ class HDF5StructureHTMLRepr(_HDF5StructureRepr):
 
     def __attrs__(self, name, h5obj):
         attr_value = h5obj.attrs.raw[name]
+        is_root_group = h5obj.name == "/"
         try:
             if isinstance(attr_value, np.bytes_):
                 try:
                     attr_value = attr_value.decode('utf-8')
                 except UnicodeDecodeError:
                     warnings.warn(f'Cannot decode attribute value for {name}', RuntimeWarning)
+
             rdf = h5obj.rdf.get(name)
 
             disp_name = name
@@ -599,11 +601,22 @@ class HDF5StructureHTMLRepr(_HDF5StructureRepr):
             if rdf_predicate is not None:
                 disp_name += get_iri_icon_href(rdf_predicate, icon_url=IRI_ICON)
 
+            if is_root_group:
+                frdf = h5obj.frdf.get(name)
+                frdf_predicate = frdf.predicate
+                if frdf_predicate is not None:
+                    disp_name += get_iri_icon_href(frdf_predicate, icon_url=IRI_ICON)
+
             attrs_def = h5obj.rdf[name].definition
             if attrs_def is not None:
                 disp_name += get_def_icon_href(attrs_def)
 
             rdf_object = rdf.object
+            if is_root_group:
+                frdf_object = frdf.object
+            else:
+                frdf_object = None
+
 
             if isinstance(attr_value, ndarray):
 
@@ -619,6 +632,8 @@ class HDF5StructureHTMLRepr(_HDF5StructureRepr):
 
                     if rdf_object is not None:
                         _value_str += get_iri_icon_href(rdf_object, icon_url=IRI_ICON)
+                    if frdf_object is not None:
+                        _value_str += get_iri_icon_href(frdf_object, icon_url=IRI_ICON)
                     return '<li style="list-style-type: none; ' \
                            f'font-style: italic">{disp_name}: {_value_str}</li>'
                 else:
@@ -628,7 +643,9 @@ class HDF5StructureHTMLRepr(_HDF5StructureRepr):
                         _value = f'{_value[0:self.max_attr_length]}...'
 
                     if rdf_object is not None:
-                        _value += get_iri_icon_href(rdf_predicate, icon_url=IRI_ICON)
+                        _value += get_iri_icon_href(rdf_object, icon_url=IRI_ICON)
+                    if frdf_object is not None:
+                        _value += get_iri_icon_href(frdf_object, icon_url=IRI_ICON)
 
                     return f'<li style="list-style-type: none; font-style: italic">{disp_name}: {_value}</li>'
 
@@ -654,6 +671,8 @@ class HDF5StructureHTMLRepr(_HDF5StructureRepr):
                 # add rdf icon if available:
                 if rdf_object is not None:
                     _value_html += get_iri_icon_href(rdf_object, icon_url=IRI_ICON)
+                if frdf_object is not None:
+                    _value_html += get_iri_icon_href(frdf_object, icon_url=IRI_ICON)
 
                 if is_url and not _value_html.startswith('{'):  # TODO: why the second condition?
                     return f'<li style="list-style-type: none; font-style: italic">{disp_name}: {_value_html}</li>'
@@ -667,6 +686,8 @@ class HDF5StructureHTMLRepr(_HDF5StructureRepr):
                         _value_str = attr_value
                 if rdf_object is not None:
                     _value_str += get_iri_icon_href(rdf_object, icon_url=IRI_ICON)
+                if frdf_object is not None:
+                    _value_str += get_iri_icon_href(frdf_object, icon_url=IRI_ICON)
                 return f'<li style="list-style-type: none; font-style: italic">{disp_name}: {_value_str}</li>'
 
             elif not isinstance(attr_value, ndarray):
@@ -688,8 +709,11 @@ class HDF5StructureHTMLRepr(_HDF5StructureRepr):
 
             if rdf_object is not None:
                 _value_str += get_iri_icon_href(rdf_object, icon_url=IRI_ICON)
+            if frdf_object is not None:
+                _value_str += get_iri_icon_href(frdf_object, icon_url=IRI_ICON)
 
             return f'<li style="list-style-type: none; font-style: italic">{name}: {_value_str}</li>'
+
         except Exception as e:
             return f'<li style="list-style-type: none; font-style: italic">{name}: {attr_value}</li>'
 

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/convention/generate.py

@@ -193,7 +193,7 @@ def write_convention_module_from_yaml(yaml_filename: pathlib.Path, name=None):
             _default_value = v.get('default_value', '$EMPTY')
 
             # it is not allowed to have a dash in the class name.
-            # However it was needed to have standard attribute with the same name for different methods
+            # However, it was needed to have standard attribute with the same name for different methods
             class_name = k.replace('-', '_')
             attr_name = k.rsplit('-', 1)[0]
             f.write(f'\nclass {class_name}(BaseModel):')
@@ -241,6 +241,9 @@ def write_convention_module_from_yaml(yaml_filename: pathlib.Path, name=None):
         name='{kk}',
         description={_str_getter(vv, 'description', None)},
         validator={_validator.replace('-', '_')},
+        alternative_standard_attribute={_str_getter(vv, 'alternative_standard_attribute', None)},
+        rdf_predicate={_str_getter(vv, 'rdf_predicate', None)},
+        frdf_predicate={_str_getter(vv, 'frdf_predicate', None)},
         target_method={_str_getter(vv, 'target_method')},
         default_value={_default_value_str},
         requirements={_str_getter(vv, 'requirements', None)},

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/convention/ontology/hdf_datatypes.py

@@ -1,5 +1,6 @@
 import h5py
 import numpy as np
+import rdflib
 from ontolutils.namespacelib.hdf5 import HDF5
 
 # Mapping HDF5 numpy datatypes to ontology types
@@ -53,12 +54,11 @@ def _get_endianness(dtype):
     return 'LE'  # Default to little-endian if unknown
 
 
-def get_datatype(dataset: h5py.Dataset):
+def get_datatype(dataset: h5py.Dataset) -> rdflib.URIRef:
     """Maps an HDF5 dataset to its ontology-defined datatype."""
     dtype = dataset.dtype
     np_type = np.dtype(dtype).type  # Get numpy type (e.g., np.float32)
 
     endianness = _get_endianness(dtype)
 
-    ontology_type = HDF5_DATATYPE_MAP.get((np_type, endianness), None)
-    return ontology_type
+    return HDF5_DATATYPE_MAP.get((np_type, endianness), None)

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/convention/standard_attributes.py

@@ -1,12 +1,14 @@
 """standard attribute module"""
-import h5py
 import json
 import logging
-import pydantic
-import typing_extensions
 import warnings
 from typing import Dict, List, Union
 
+import h5py
+import pydantic
+import typing_extensions
+from pydantic import HttpUrl
+
 from . import errors
 from .consts import DefaultValue
 from .. import get_config
@@ -74,6 +76,8 @@ class StandardAttribute:
                  position: Union[None, Dict[str, str]] = None,
                  requirements: List[str] = None,
                  type_hint: str = None,
+                 rdf_predicate: str = None,
+                 frdf_predicate: str = None,
                  **kwargs):
         # name of attribute:
         self.name = name.split('-', 1)[0]  # the attrs key
@@ -98,6 +102,23 @@ class StandardAttribute:
                              f'Valid target methods are: {self.VALID_TARGET_METHODS}.')
         self.target_method = target_method
 
+        if rdf_predicate is not None:
+            try:
+                HttpUrl(rdf_predicate)
+            except pydantic.ValidationError:
+                raise TypeError(f'rdf_predicate must be a valid URL. Got {rdf_predicate} instead.')
+        if frdf_predicate is not None:
+            try:
+                HttpUrl(frdf_predicate)
+            except pydantic.ValidationError:
+                raise TypeError(f'rdf_predicate must be a valid URL. Got {frdf_predicate} instead.')
+        self.rdf_predicate = rdf_predicate
+        self.frdf_predicate = frdf_predicate
+        if frdf_predicate is not None and target_method != "__init__":
+            raise ValueError(
+                f'frdf_predicate is only supported for the __init__ method. Got {target_method} instead.'
+            )
+
         # The default value
         if isinstance(default_value, str):
             _default_value = default_value.lower()
@@ -220,10 +241,15 @@ class StandardAttribute:
                             f'Expected fields: {self.validator.model_fields}\nPydantic error: {err}')
                     validated_value = getattr(_validated_value, key0)
 
-                return super(type(parent.attrs), parent.attrs).__setitem__(
+                ret = super(type(parent.attrs), parent.attrs).__setitem__(
                     self.name,
                     parse_object_for_attribute_setting(validated_value)
                 )
+                if self.rdf_predicate is not None:
+                    parent.rdf[self.name].predicate = self.rdf_predicate
+                if self.frdf_predicate is not None:
+                    parent.frdf[self.name].predicate = self.frdf_predicate
+                return ret
 
     def get(self, parent: Union[h5py.File, h5py.Group, h5py.Dataset]):
         """Read the attribute from `parent`

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/data/tutorial_convention.yaml

@@ -19,12 +19,19 @@ units:
   validator: $units
   description: The physical unit of the dataset. If dimensionless, the unit is ''.
 
+title:
+  description: Title of the HDF5 file acting as a minimal description of the dataset.
+  target_method: __init__
+  validator: str
+  frdf_predicate: https://schema.org/title
+
 standard_name:
   target_method: create_dataset
   validator: $standardNameType
   requirements: units
   description: Standard name of the dataset. If not set, the long_name attribute must be given.
   alternative_standard_attribute: long_name
+  default_value: $EMPTY
 
 standard_name_table:
   target_method: __init__

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/database/__init__.py

@@ -72,4 +72,4 @@ def rdf_find(source, *,
                                       recursive=recursive)
 
 
-__all__ = ['FileDB', 'FilesDB', 'ObjDB', 'HDF5DBInterface']
+__all__ = ['FileDB', 'FilesDB', 'ObjDB', 'HDF5DBInterface', 'lazy']

h5rdmtoolbox-2.2.0/h5rdmtoolbox/ld/__init__.py

@@ -0,0 +1,76 @@
+import pathlib
+import warnings
+from typing import Union, Optional, Dict
+
+import h5py
+import rdflib
+
+from .hdf.file import get_ld as get_hdf_ld
+from .user.file import get_ld as get_contextual_ld
+from .utils import optimize_context
+
+
+def get_ld(
+        hdf_filename: Union[str, pathlib.Path],
+        structural: bool = True,
+        contextual: bool = True,
+        file_uri: Optional[str] = None,
+        skipND: Optional[int] = 1,
+        context: Optional[Dict] = None) -> rdflib.Graph:
+    """Return the HDF file content as a rdflib.Graph object."""
+
+    graph = None
+    with h5py.File(hdf_filename) as h5:
+        if contextual and structural:
+            graph1 = get_hdf_ld(h5, file_uri=file_uri, skipND=skipND)
+            graph2 = get_contextual_ld(h5, file_uri=file_uri)
+            graph = graph1 + graph2
+        else:
+            if structural:
+                graph = get_hdf_ld(hdf_filename, file_uri=file_uri, skipND=skipND)
+
+            if contextual:
+                graph = get_contextual_ld(hdf_filename, file_uri=file_uri)
+    if graph is None:
+        raise ValueError("structural and semantic cannot be both False.")
+    context = context or {}
+    for prefix, uri in context.items():
+        if not isinstance(uri, rdflib.URIRef):
+            graph.bind("ex", rdflib.URIRef(uri))
+    return graph
+
+
+def hdf2jsonld(
+        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,
+):
+    if metadata_filename is None:
+        metadata_filename = pathlib.Path(filename).with_suffix('.jsonld')  # recommended suffix for JSON-LD is .jsonld!
+    else:
+        metadata_filename = pathlib.Path(metadata_filename)
+
+    graph = get_ld(
+        hdf_filename=filename,
+        structural=structural,
+        contextual=contextual,
+        file_uri=file_uri,
+        skipND=skipND
+    )
+    context = context or {}
+    context = optimize_context(graph, context)
+
+    with open(metadata_filename, 'w', encoding='utf-8') as f:
+        f.write(
+            graph.serialize(format='json-ld',
+                            indent=indent,
+                            auto_compact=True,
+                            context=context)
+        )
+
+    return metadata_filename

h5rdmtoolbox-2.2.0/h5rdmtoolbox/ld/globals.py

@@ -0,0 +1,3 @@
+_CACHE = {
+    "FILE_MTIME_ID": {}
+}

{h5rdmtoolbox-2.0.0a0 → h5rdmtoolbox-2.2.0}/h5rdmtoolbox/ld/hdf/attributes.py

@@ -3,14 +3,20 @@ from ontolutils.namespacelib.hdf5 import HDF5
 from rdflib import Namespace, Literal
 from rdflib import XSD, RDF
 
+from ..utils import get_attr_node
+
 HDF = Namespace(str(HDF5))
 
 
-def process_attribute(name, value, graph, parent_uri):
+def process_attribute(*, name, value, graph, parent, parent_uri, blank_node_iri_base):
     """Process an HDF5 attribute, adding it to the RDF graph."""
     if name.isupper() or name.startswith('@'):
         return
-    attr_uri = rdflib.BNode()
+    attr_uri = get_attr_node(
+        parent,
+        name,
+        blank_node_iri_base
+    )
 
     if isinstance(value, str):
         graph.add((attr_uri, RDF.type, HDF5.StringAttribute))