h5rdmtoolbox 2.2.1__tar.gz → 2.3.1__tar.gz

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: h5rdmtoolbox
-Version: 2.2.1
+Version: 2.3.1
 Summary: Supporting a FAIR Research Data lifecycle using Python and HDF5.
 Home-page: https://h5rdmtoolbox.readthedocs.io/en/latest/
 Author: Matthias Probst
@@ -16,10 +16,10 @@ Classifier: Topic :: Scientific/Engineering
 Requires-Python: <3.13,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: appdirs>=1.4.4
+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: h5py<4.0.0,>=3.8.0
+Requires-Dist: h5py~=3.8
 Requires-Dist: matplotlib>=3.5.2
 Requires-Dist: IPython>=7.34.0
 Requires-Dist: pyyaml>=6.0
@@ -31,8 +31,8 @@ Requires-Dist: packaging>=24.1
 Requires-Dist: ontolutils<0.20.0,>=0.19.2
 Requires-Dist: python-forge==18.6.0
 Requires-Dist: requests>=2.32.4
-Requires-Dist: pydantic<3.0.0,>=2.8.2
-Requires-Dist: rdflib>=7.0.0
+Requires-Dist: pydantic~=2.8
+Requires-Dist: rdflib~=7.1
 Requires-Dist: click==8.1.7
 Provides-Extra: database
 Requires-Dist: pymongo<=4.10.1,>=4.2.0; extra == "database"

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox/ld/hdf/datasets.py

@@ -23,11 +23,15 @@ HDF5_FILTER_ONTOLOGY = {
 }
 
 
-def add_filter(dataset: h5py.Dataset, dataset_uri, graph) -> rdflib.Graph:
+def add_filter(dataset: h5py.Dataset, dataset_uri, graph, blank_node_iri_base) -> rdflib.Graph:
     # Check predefined compression filters
     if dataset.compression:
         filter_type = HDF5_FILTER_ONTOLOGY.get(dataset.compression, None)
-        filter_uri = rdflib.BNode()
+        filter_uri = get_property_node(
+            dataset,
+            name='filter',
+            blank_node_iri_base=blank_node_iri_base
+        )
         if filter_type:
             graph.add((filter_uri, RDF.type, filter_type))
             if filter_type == HDF5.FilterDeflate:
@@ -55,7 +59,7 @@ def process_dataset(
     """Process an HDF5 dataset, adding it to the RDF graph."""
     graph.add((dataset_uri, RDF.type, HDF.Dataset))
 
-    graph = add_filter(dataset, dataset_uri, graph)
+    graph = add_filter(dataset, dataset_uri, graph, blank_node_iri_base)
 
     graph.add((parent_uri, HDF.member, dataset_uri))
 

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox/ld/rdf.py

@@ -81,8 +81,7 @@ def validate_url(url: str) -> str:
                 url = KNOWN_NAMESPACES[prefix] + name
             else:
                 raise RDFError(f'Invalid URL: "{url}".')
-        HttpUrl(url)  # validate the URL, will raise an error if invalid
-        return str(url)  # return the original string
+        return str(HttpUrl(url))  # validate the URL, will raise an error if invalid and return the encoded string
     except pydantic.ValidationError as e:
         raise RDFError(f'Invalid URL: "{url}". Expecting a valid URL. This was validated with pydantic. '
                        f'Tested with pydantic: {e}')
@@ -102,6 +101,8 @@ def set_predicate(attr: h5py.AttributeManager,
         The name of the attribute
     value : str
         The value (identifier) to add to the iri dict attribute
+    rdf_predicate_attr_name: str, optional
+        The name of the attribute to store the predicate information, by default RDF_PREDICATE_ATTR_NAME
 
     Returns
     -------
@@ -349,6 +350,11 @@ class RDFManager:
                        'predicate',
                        'type'):
             raise KeyError(f"Cannot set {key}. Only subject, predicate and type can be set!")
+        if key in ("subject", "predicate"):
+            try:
+                value = str(HttpUrl(value))
+            except pydantic.ValidationError as e:
+                RDFError(f"Invalid value. Expecting a valid URL. This was validated with pydantic: {value}")
         super().__setattr__(key, value)
 
     @property
@@ -394,7 +400,7 @@ class RDFManager:
             if _subject == str(rdf_subject):
                 res_subject.append(node)
 
-        def _find_type(name, node):
+        def _find_type(_, node):
             rdfm = RDFManager(node.attrs)
             if not isinstance(rdfm.type, list):
                 types = [rdfm.type]
@@ -513,7 +519,7 @@ class RDFManager:
 
     def pop_type(self, rdf_type: str):
         """Remove a type from the list of types"""
-        rdf_type = str(rdf_type)
+        rdf_type = str(HttpUrl(rdf_type))
         iri_type_data = self._attr.get(RDF_TYPE_ATTR_NAME, None)
         if iri_type_data is None:
             return

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox/ld/utils.py

@@ -1,4 +1,5 @@
 import pathlib
+import urllib.parse
 from typing import Optional
 from typing import Union
 
@@ -7,6 +8,10 @@ import rdflib
 from rdflib.namespace import XSD
 
 
+def _parse_obj_name(obj_name: str):
+    return urllib.parse.quote(obj_name, safe='/')
+
+
 def get_attr_dtype_as_XSD(data):
     if isinstance(data, str):
         return XSD.string
@@ -47,8 +52,8 @@ def _get_obj_id(file_id: float, obj: Union[h5py.Dataset, h5py.Group], name: Opti
     if name is None:
         if obj.name == "/":
             return f"{_file_id}{obj.name}"
-        return f"{_file_id}{obj.name}"
-    return f"{_file_id}{obj.name}{name}"
+        return f"{_file_id}{_parse_obj_name(obj.name)}"
+    return f"{_file_id}{_parse_obj_name(obj.name)}{name}"
     # return hashlib.md5(f"{obj.file.id.id}/{obj.name}{name}".encode()).hexdigest()
 
 
@@ -104,7 +109,7 @@ def get_property_node(
     if obj.name == "/":
         _id = f"{_file_id}@{name}"
     else:
-        _id = f"{_file_id}{obj.name}__{name}"
+        _id = f"{_file_id}{_parse_obj_name(obj.name)}__{name}"
     if blank_node_iri_base:
         return rdflib.URIRef(f'{blank_node_iri_base}{_id}')
     return rdflib.BNode(_id)
@@ -118,7 +123,7 @@ def get_attr_node(
     if obj.name == "/":
         _id = f"{_file_id}@{name}"
     else:
-        _id = f"{_file_id}{obj.name}@{name}"
+        _id = f"{_file_id}{_parse_obj_name(obj.name)}@{name}"
     if blank_node_iri_base:
         return rdflib.URIRef(f'{blank_node_iri_base}{_id}')
     return rdflib.BNode(f"{_id}")

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox/repository/interface.py

@@ -69,7 +69,7 @@ class RepositoryFile:
                     access_url=self.access_url,
                     media_type=self.media_type,
                     checksum=self.checksum,
-                    filename=self.filename,
+                    filename=self.name,
                     size=self.size)
 
     def jsonld(self) -> str:
@@ -114,10 +114,6 @@ class RepositoryFile:
 class RepositoryInterface(abc.ABC):
     """Abstract base class for repository interfaces."""
 
-    # __init__  must be implemented in the child class
-    def __init__(self):
-        raise RuntimeError('Not implemented.')
-
     @property
     @abc.abstractmethod
     def identifier(self) -> str:
@@ -140,20 +136,6 @@ class RepositoryInterface(abc.ABC):
     def set_metadata(self, metadata):
         """Set the metadata of the repository."""
 
-    @abc.abstractmethod
-    def download_file(self, filename):
-        """Download a specific file from the repository.
-
-        ..note: This method is deprecated. Use method `.files.get(filename).download()` method instead.
-        """
-
-    @abc.abstractmethod
-    def download_files(self):
-        """Download all files from the repository.
-
-        ..note: This method is deprecated. Please iterate over `files` and call .download() on the items.
-        """
-
     @property
     @abc.abstractmethod
     def files(self) -> Dict[str, RepositoryFile]:

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox/repository/zenodo/core.py

@@ -4,13 +4,12 @@ import logging
 import pathlib
 import time
 import warnings
-from typing import Union, List, Dict, Optional
+from typing import Union, Dict, Optional
 
 import requests
 from packaging.version import Version
 from rdflib import Graph
 
-from h5rdmtoolbox.utils import deprecated
 from .metadata import Metadata
 from .tokens import get_api_token
 from ..interface import RepositoryInterface, RepositoryFile
@@ -226,31 +225,6 @@ class AbstractZenodoInterface(RepositoryInterface, abc.ABC):
         rfiles = [RepositoryFile(**_parse(data)) for data in self.json()['files']]
         return {f.name: f for f in rfiles}
 
-    @deprecated(version='1.4.0rc1',
-                msg='Please use `[file.download() for file in <repo>.files.values()]` instead.')
-    def download_files(self,
-                       target_folder: Union[str, pathlib.Path] = None,
-                       suffix: Union[str, List[str], None] = None) -> List[pathlib.Path]:
-        """Download all (!) files from Zenodo. You may specify one or multiple suffixes to only download certain files.
-
-        Parameters
-        ----------
-        target_folder : str or pathlib.Path, optional
-            The target folder, by default None
-        suffix: Union[str, List[str], None], optional=None
-            Specify a suffix to only download certain files
-
-        Returns
-        -------
-        List[pathlib.Path]
-            A list of all downloaded files.
-        """
-        if suffix is None:
-            return [file.download(target_folder=target_folder) for file in self.files.values()]
-        if not isinstance(suffix, list):
-            suffix = [suffix, ]
-        return [file.download(target_folder=target_folder) for file in self.files.values() if file.suffix in suffix]
-
     def download_file(self, filename: str, target_folder: Optional[Union[str, pathlib.Path]] = None) -> pathlib.Path:
         """Download a file based on URL. The url is validated using pydantic
 
@@ -673,29 +647,6 @@ class ZenodoRecord(RepositoryInterface):
         rfiles = [RepositoryFile(**_parse(data)) for data in self.json()['files']]
         return {f.name: f for f in rfiles}
 
-    @deprecated(version='1.4.0rc1',
-                msg='Please use `[file.download() for file in self.files.values()]` instead.')
-    def download_files(self,
-                       target_folder: Union[str, pathlib.Path] = None,
-                       suffix: Union[str, List[str], None] = None) -> List[pathlib.Path]:
-        """Download all (!) files from Zenodo. You may specify one or multiple suffixes to only download certain files.
-
-        Parameters
-        ----------
-        target_folder : str or pathlib.Path, optional
-            The target folder, by default None
-        suffix: Union[str, List[str], None], optional=None
-            Specify a suffix to only download certain files
-
-        Returns
-        -------
-        List[pathlib.Path]
-            A list of all downloaded files.
-        """
-        warnings.warn("This method is deprecated. Please loop over `.files` and call `.download()` on the "
-                      "items of the returned list", DeprecationWarning)
-        return [file.download(target_folder=target_folder) for file in self.files.values()]
-
     def download_file(self, filename: str, target_folder: Optional[Union[str, pathlib.Path]] = None) -> pathlib.Path:
         """Download a file based on URL. The url is validated using pydantic
 

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox/repository/zenodo/tokens.py

@@ -7,7 +7,7 @@ from typing import Union, Optional
 logger = logging.getLogger('h5rdmtoolbox')
 
 
-def _parse_ini_file(zenodo_ini_filename: Union[str, pathlib.Path]):
+def _parse_ini_file(zenodo_ini_filename: Optional[Union[str, pathlib.Path]]):
     """Parse the Zenodo ini file.
 
     Parameters

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: h5rdmtoolbox
-Version: 2.2.1
+Version: 2.3.1
 Summary: Supporting a FAIR Research Data lifecycle using Python and HDF5.
 Home-page: https://h5rdmtoolbox.readthedocs.io/en/latest/
 Author: Matthias Probst
@@ -16,10 +16,10 @@ Classifier: Topic :: Scientific/Engineering
 Requires-Python: <3.13,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: appdirs>=1.4.4
+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: h5py<4.0.0,>=3.8.0
+Requires-Dist: h5py~=3.8
 Requires-Dist: matplotlib>=3.5.2
 Requires-Dist: IPython>=7.34.0
 Requires-Dist: pyyaml>=6.0
@@ -31,8 +31,8 @@ Requires-Dist: packaging>=24.1
 Requires-Dist: ontolutils<0.20.0,>=0.19.2
 Requires-Dist: python-forge==18.6.0
 Requires-Dist: requests>=2.32.4
-Requires-Dist: pydantic<3.0.0,>=2.8.2
-Requires-Dist: rdflib>=7.0.0
+Requires-Dist: pydantic~=2.8
+Requires-Dist: rdflib~=7.1
 Requires-Dist: click==8.1.7
 Provides-Extra: database
 Requires-Dist: pymongo<=4.10.1,>=4.2.0; extra == "database"

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox.egg-info/SOURCES.txt

@@ -132,6 +132,7 @@ tests/ld/__init__.py
 tests/ld/test_ld.py
 tests/ld/test_rdf.py
 tests/ld/test_user_graph.py
+tests/ld/test_utils.py
 tests/repository/__init__.py
 tests/repository/test_zenodo.py
 tests/wrapper/__init__.py

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/h5rdmtoolbox.egg-info/requires.txt

@@ -1,7 +1,7 @@
-appdirs>=1.4.4
+appdirs~=1.4
 importlib_resources<7.0.0,>=6.5.2
 numpy<2.0.0,>=1.20
-h5py<4.0.0,>=3.8.0
+h5py~=3.8
 matplotlib>=3.5.2
 IPython>=7.34.0
 pyyaml>=6.0
@@ -13,8 +13,8 @@ packaging>=24.1
 ontolutils<0.20.0,>=0.19.2
 python-forge==18.6.0
 requests>=2.32.4
-pydantic<3.0.0,>=2.8.2
-rdflib>=7.0.0
+pydantic~=2.8
+rdflib~=7.1
 click==8.1.7
 
 [complete]

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = h5rdmtoolbox
-version = 2.2.1
+version = 2.3.1
 author = Matthias Probst
 author_email = matth.probst@gmail.com
 description = Supporting a FAIR Research Data lifecycle using Python and HDF5.
@@ -22,10 +22,10 @@ packages = find:
 python_requires = >=3.9, <3.13
 include_package_data = True
 install_requires = 
-	appdirs >= 1.4.4
+	appdirs~=1.4
 	importlib_resources>=6.5.2, <7.0.0
 	numpy >= 1.20, < 2.0.0  # 2.0.0 fails with pint
-	h5py >= 3.8.0, <4.0.0
+	h5py~=3.8
 	matplotlib >= 3.5.2
 	IPython >= 7.34.0  # colab wants 7.34.0
 	pyyaml >= 6.0  # 5.4 does not work with python 3.11!
@@ -37,8 +37,8 @@ install_requires =
 	ontolutils>=0.19.2,<0.20.0
 	python-forge==18.6.0
 	requests>=2.32.4
-	pydantic>=2.8.2,<3.0.0
-	rdflib>=7.0.0
+	pydantic~=2.8
+	rdflib~=7.1
 	click==8.1.7
 
 [options.extras_require]

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/tests/ld/test_ld.py

@@ -1,6 +1,7 @@
 import json
 import pathlib
 import unittest
+from typing import Union
 
 import numpy as np
 import ontolutils
@@ -21,6 +22,41 @@ logger = h5tbx.logger
 
 __this_dir__ = pathlib.Path(__file__).parent
 
+EXCEPTION_PROPERTIES_NAMESPACES = {
+    str(rdflib.OWL),
+    str(rdflib.RDF),
+    str(rdflib.RDFS),
+    str(rdflib.XSD)
+}
+
+
+def _raise_on_blank_nodes(
+        ttl,
+        exception_properties=None) -> rdflib.Graph:
+    """Raises an error if the given RDF file contains blank nodes."""
+    if exception_properties is None:
+        exception_properties = EXCEPTION_PROPERTIES_NAMESPACES
+
+    temp_graph = rdflib.Graph()
+    temp_graph.parse(data=ttl, format='ttl')
+
+    # Check if there are any blank nodes
+    has_blank_nodes = any(
+        isinstance(term, rdflib.BNode)
+        for triple in temp_graph
+        for term in triple
+    )
+    if has_blank_nodes:
+        for s, p, o in temp_graph:
+            if isinstance(s, rdflib.BNode) or isinstance(p, rdflib.BNode) or isinstance(o, rdflib.BNode):
+                # allow all owl properties:
+                for ep in exception_properties:
+                    if str(p).startswith(ep):
+                        break
+                else:
+                    raise ValueError(f"Blank nodes are not supported: {s}, {p}, {o}")
+    return temp_graph
+
 
 class TestJSONLD(unittest.TestCase):
 
@@ -93,7 +129,7 @@ class TestJSONLD(unittest.TestCase):
             h5.create_string_dataset('ds_str1', data=["Hello", "World"])
             h5.create_dataset('ds1', data=[1, 2, 3])
             h5.create_dataset('ds2', data=[[1, 2], [3, 4]])
-            ttl = h5.serialize(fmt="ttl", skipND=1)
+            ttl = h5.serialize(fmt="ttl", skipND=1, file_uri="https://example.org/#")
 
         g = rdflib.Graph().parse(data=ttl, format="ttl")
         sparql_str = """PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
@@ -110,6 +146,8 @@ WHERE {
         bindings = res.bindings
         self.assertEqual(0, len(bindings))
 
+        _raise_on_blank_nodes(ttl)
+
     def test_serialize_multiple_types(self):
         with h5tbx.File() as h5:
             h5.rdf.type = [M4I.Tool, 'https://www.wikidata.org/wiki/Q1058834']

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/tests/ld/test_rdf.py

@@ -257,14 +257,15 @@ class TestRDF(unittest.TestCase):
                                   'https://example.org/objectURI3'])
 
             h5['/'].rdf.subject = 'https://example.org/is group'
-            self.assertEqual(h5.rdf.subject, 'https://example.org/is group')
+            self.assertEqual(h5.rdf.subject, 'https://example.org/is%20group')
 
             h5['/'].rdf.subject = 'https://example.org/is root group'
-            self.assertEqual(h5.rdf.subject, 'https://example.org/is root group')
+            self.assertEqual(h5.rdf.subject, 'https://example.org/is%20root%20group')
 
     def test_delete_rdf_properties(self):
         with h5tbx.File() as h5:
             h5['/'].rdf.subject = 'https://example.org/is root group'
+            self.assertEqual(h5.rdf.subject, 'https://example.org/is%20root%20group')
             del h5['/'].rdf.subject
             self.assertEqual(h5.rdf.subject, None)
 

h5rdmtoolbox-2.3.1/tests/ld/test_utils.py

@@ -0,0 +1,13 @@
+import unittest
+
+from h5rdmtoolbox.ld.utils import _parse_obj_name
+
+
+class TestUtile(unittest.TestCase):
+
+    def test_parsing_obj_names(self):
+        self.assertEqual(_parse_obj_name("/"), "/")
+        self.assertEqual(_parse_obj_name(" "), "%20")
+        self.assertEqual(_parse_obj_name("/My Group/"), "/My%20Group/")
+        self.assertEqual(_parse_obj_name("/My Group/My Dataset"), "/My%20Group/My%20Dataset")
+        self.assertEqual(_parse_obj_name("/My !&9]231,.0Group/My Dataset "), "/My%20%21%269%5D231%2C.0Group/My%20Dataset%20")

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/tests/repository/test_zenodo.py

@@ -110,7 +110,7 @@ class TestZenodo(unittest.TestCase):
     def test_creator(self):
         from h5rdmtoolbox.repository.zenodo.metadata import Creator
         with self.assertRaises(ValueError):
-            creator = Creator(name='John Doe', affiliation='University of Nowhere')
+            _ = Creator(name='John Doe', affiliation='University of Nowhere')
         creator = Creator(name='Doe, John')
         self.assertEqual(creator.name, 'Doe, John')
         with self.assertRaises(pydantic.ValidationError):
@@ -163,41 +163,41 @@ class TestZenodo(unittest.TestCase):
 
         with self.assertRaises(ValueError):
             # wrong version
-            metadata = Metadata(version='invalid',
-                                title='h5rdmtoolbox',
-                                description='A toolbox for managing HDF5-based research data management',
-                                creators=[Creator(name='Doe, John', affiliation='University of Nowhere')],
-                                keywords=['hdf5', 'research data management', 'rdm'],
-                                upload_type='publication',
-                                publication_type='other',
-                                access_right='open',
-                                publication_date='2023-01-01')
+            _ = Metadata(version='invalid',
+                         title='h5rdmtoolbox',
+                         description='A toolbox for managing HDF5-based research data management',
+                         creators=[Creator(name='Doe, John', affiliation='University of Nowhere')],
+                         keywords=['hdf5', 'research data management', 'rdm'],
+                         upload_type='publication',
+                         publication_type='other',
+                         access_right='open',
+                         publication_date='2023-01-01')
 
         with self.assertRaises(ValueError):
             # invalid embargo date
-            metadata = Metadata(version='0.1.0-rc.1+build.1',
-                                title='h5rdmtoolbox',
-                                description='A toolbox for managing HDF5-based research data management',
-                                creators=[Creator(name='Doe, John', affiliation='University of Nowhere')],
-                                keywords=['hdf5', 'research data management', 'rdm'],
-                                upload_type='publication',
-                                publication_type='other',
-                                access_right='embargoed',
-                                embargo_date='2022-01-01',  # too early!
-                                publication_date='2023-01-01')
+            _ = Metadata(version='0.1.0-rc.1+build.1',
+                         title='h5rdmtoolbox',
+                         description='A toolbox for managing HDF5-based research data management',
+                         creators=[Creator(name='Doe, John', affiliation='University of Nowhere')],
+                         keywords=['hdf5', 'research data management', 'rdm'],
+                         upload_type='publication',
+                         publication_type='other',
+                         access_right='embargoed',
+                         embargo_date='2022-01-01',  # too early!
+                         publication_date='2023-01-01')
 
         # invalid embargo date format
         with self.assertRaises(ValueError):
-            metadata = Metadata(version='0.1.0-rc.1+build.1',
-                                title='h5rdmtoolbox',
-                                description='A toolbox for managing HDF5-based research data management',
-                                creators=[Creator(name='Doe, John', affiliation='University of Nowhere')],
-                                keywords=['hdf5', 'research data management', 'rdm'],
-                                upload_type='publication',
-                                publication_type='other',
-                                access_right='embargoed',
-                                embargo_date='01-2022-01',  # wrong format!
-                                publication_date='2023-01-01')
+            _ = Metadata(version='0.1.0-rc.1+build.1',
+                         title='h5rdmtoolbox',
+                         description='A toolbox for managing HDF5-based research data management',
+                         creators=[Creator(name='Doe, John', affiliation='University of Nowhere')],
+                         keywords=['hdf5', 'research data management', 'rdm'],
+                         upload_type='publication',
+                         publication_type='other',
+                         access_right='embargoed',
+                         embargo_date='01-2022-01',  # wrong format!
+                         publication_date='2023-01-01')
 
     def test_get_api(self):
         self.assertIsInstance(get_api_token(sandbox=True), str)
@@ -270,7 +270,7 @@ class TestZenodo(unittest.TestCase):
                       access_token='321',
                       zenodo_ini_filename=ini_filename)
         ini_filename = h5tbx.utils.generate_temporary_filename(suffix='.ini', touch=False)
-        with open(ini_filename, 'w') as f:
+        with open(ini_filename, 'w'):
             pass
         set_api_token(sandbox=True,
                       access_token='321',
@@ -455,9 +455,6 @@ class TestZenodo(unittest.TestCase):
             embargo_date='2020'
         )
 
-        with self.assertRaises(TypeError):
-            z.set_metadata(12)
-
         z.set_metadata(meta.model_dump())
         z.set_metadata(meta)
         ret_metadata = z.get_metadata()
@@ -489,14 +486,14 @@ class TestZenodo(unittest.TestCase):
         tmpfile.unlink()
         self.assertFalse(tmpfile.exists())
 
-        filename = z.download_file('testfile.txt')
+        filename = z.files["testfile.txt"].download()
         self.assertIsInstance(filename, pathlib.Path)
         self.assertTrue(filename.exists())
         with open(filename, 'r') as f:
             self.assertEqual(f.read(), 'This is a test file.')
         filename.unlink()
 
-        filenames = z.download_files()
+        filenames = [f.download() for f in z.files.values()]
 
         self.assertIsInstance(filenames, list)
         self.assertIsInstance(filenames[0], pathlib.Path)
@@ -505,17 +502,16 @@ class TestZenodo(unittest.TestCase):
             filename.unlink()
 
         hdf5_filenames = [file.download() for file in z.files.values() if file.suffix == '.hdf']
-        with self.assertWarns(DeprecationWarning):
-            z.download_files(suffix='.hdf')
+
         self.assertIsInstance(hdf5_filenames, list)
         self.assertEqual(len(hdf5_filenames), 0)
 
-        txt_filenames = z.download_files(suffix='.txt')
+        txt_filenames = [f.download() for f in z.files.values() if f.suffix == ".txt"]
         self.assertIsInstance(txt_filenames, list)
         self.assertEqual(len(txt_filenames), 1)
         self.assertEqual(txt_filenames[0].suffix, '.txt')
 
-        hdf_and_txt_filenames = z.download_files(suffix=['.txt', '.hdf'])
+        hdf_and_txt_filenames = [f.download() for f in z.files.values() if f.suffix in (".txt", "*.hdf")]
         self.assertIsInstance(hdf_and_txt_filenames, list)
         self.assertEqual(len(hdf_and_txt_filenames), 1)
         self.assertEqual(hdf_and_txt_filenames[0].suffix, '.txt')
@@ -569,9 +565,6 @@ class TestZenodo(unittest.TestCase):
             embargo_date='2020'
         )
 
-        with self.assertRaises(TypeError):
-            z.set_metadata(12)
-
         z.set_metadata(meta.model_dump())
         z.set_metadata(meta)
         ret_metadata = z.get_metadata()
@@ -603,14 +596,14 @@ class TestZenodo(unittest.TestCase):
         tmpfile.unlink()
         self.assertFalse(tmpfile.exists())
 
-        filename = z.download_file('testfile.txt')
+        filename = z.files["testfile.txt"].download()
         self.assertIsInstance(filename, pathlib.Path)
         self.assertTrue(filename.exists())
         with open(filename, 'r') as f:
             self.assertEqual(f.read(), 'This is a test file.')
         filename.unlink()
 
-        filenames = z.download_files()
+        filenames = [f.download() for f in z.files.values()]
 
         self.assertIsInstance(filenames, list)
         self.assertIsInstance(filenames[0], pathlib.Path)
@@ -618,16 +611,16 @@ class TestZenodo(unittest.TestCase):
             self.assertTrue(filename.exists())
             filename.unlink()
 
-        hdf5_filenames = z.download_files(suffix='.hdf')
+        hdf5_filenames = [f.download() for f in z.files.values() if f.suffix == '.hdf']
         self.assertIsInstance(hdf5_filenames, list)
-        self.assertEqual(len(hdf5_filenames), 1)
+        self.assertEqual(len(hdf5_filenames), 0)
 
-        txt_filenames = z.download_files(suffix='.txt')
+        txt_filenames = [f.download() for f in z.files.values() if f.suffix == '.txt']
         self.assertIsInstance(txt_filenames, list)
         self.assertEqual(len(txt_filenames), 1)
         self.assertEqual(txt_filenames[0].suffix, '.txt')
 
-        hdf_and_txt_filenames = z.download_files(suffix=['.txt', '.hdf'])
+        hdf_and_txt_filenames = [f.download() for f in z.files.values() if f.suffix in ('.txt', '.hdf')]
         self.assertIsInstance(hdf_and_txt_filenames, list)
         self.assertEqual(len(hdf_and_txt_filenames), 1)
         self.assertEqual(hdf_and_txt_filenames[0].suffix, '.txt')

{h5rdmtoolbox-2.2.1 → h5rdmtoolbox-2.3.1}/tests/test_version.py

@@ -1,6 +1,7 @@
 import pathlib
 import unittest
-from datetime import datetime
+
+import yaml
 
 from h5rdmtoolbox import __version__, get_package_meta
 
@@ -34,14 +35,13 @@ class TestVersion(unittest.TestCase):
         found = False
         for line in lines:
             if 'pip install' in line:
-                self.assertEqual(line.strip(), f'"# !pip install h5rdmtoolbox=={__version__}"')
+                self.assertTrue(f'"# !pip install h5rdmtoolbox=={__version__}"' in line.strip())
                 found = True
                 break
         self.assertTrue(found)
 
     def test_citation_cff(self):
         citation_cff = __this_dir__ / "../CITATION.cff"
-        import yaml
         with open(citation_cff, 'r') as f:
             cff = yaml.safe_load(f)
         self.assertTrue("todo" not in cff["doi"].lower(), "Please replace 'todo' in CITATION.cff")