Expose AWS Region to NWBHDF5IO (#1903)

CHANGELOG.md

@@ -4,6 +4,7 @@
 
 ### Enhancements and minor changes
 - Set rate default value inside `mock_ElectricalSeries` to avoid having to set `rate=None` explicitly when passing timestamps. @h-mayorquin [#1894](https://github.com/NeurodataWithoutBorders/pynwb/pull/1894)
+- Exposed `aws_region` to `NWBHDF5IO`. @rly [#1903](https://github.com/NeurodataWithoutBorders/pynwb/pull/1903)
 
 ## PyNWB 2.7.0 (May 2, 2024)
 

environment-ros3.yml

@@ -6,7 +6,7 @@ channels:
 dependencies:
   - python==3.12
   - h5py==3.11.0
-  - hdmf==3.13.0
+  - hdmf==3.14.0
   - matplotlib==3.8.0
   - numpy==1.26.4
   - pandas==2.2.1

pyproject.toml

@@ -33,7 +33,7 @@ classifiers = [
 ]
 dependencies = [
     "h5py>=2.10",
-    "hdmf>=3.12.2",
+    "hdmf>=3.14.0",
     "numpy>=1.18, <2.0", # pin below 2.0 until HDMF supports numpy 2.0
     "pandas>=1.1.5",
     "python-dateutil>=2.7.3",

requirements-min.txt

@@ -1,6 +1,6 @@
 # minimum versions of package dependencies for installing PyNWB
 h5py==2.10  # support for selection of datasets with list of indices added in 2.10
-hdmf==3.12.2
+hdmf==3.14.0
 numpy==1.18
 pandas==1.1.5
 python-dateutil==2.7.3

requirements.txt

@@ -1,6 +1,6 @@
 # pinned dependencies to reproduce an entire development environment to use PyNWB
 h5py==3.11.0
-hdmf==3.13.0
+hdmf==3.14.0
 numpy==1.26.4
 pandas==2.2.1
 python-dateutil==2.9.0.post0

src/pynwb/__init__.py

@@ -254,24 +254,19 @@ def can_read(path: str):
             {'name': 'extensions', 'type': (str, TypeMap, list),
              'doc': 'a path to a namespace, a TypeMap, or a list consisting paths to namespaces and TypeMaps',
              'default': None},
-            {'name': 'file', 'type': [h5py.File, 'S3File'], 'doc': 'a pre-existing h5py.File object', 'default': None},
-            {'name': 'comm', 'type': 'Intracomm', 'doc': 'the MPI communicator to use for parallel I/O',
-             'default': None},
-            {'name': 'driver', 'type': str, 'doc': 'driver for h5py to use when opening HDF5 file', 'default': None},
-            {'name': 'herd_path', 'type': str, 'doc': 'The path to the HERD',
-             'default': None},)
+            *get_docval(_HDF5IO.__init__, "file", "comm", "driver", "aws_region", "herd_path"),)
     def __init__(self, **kwargs):
-        path, mode, manager, extensions, load_namespaces, file_obj, comm, driver, herd_path =\
+        path, mode, manager, extensions, load_namespaces, file_obj, comm, driver, aws_region, herd_path =\
             popargs('path', 'mode', 'manager', 'extensions', 'load_namespaces',
-                    'file', 'comm', 'driver', 'herd_path', kwargs)
+                    'file', 'comm', 'driver', 'aws_region', 'herd_path', kwargs)
         # Define the BuildManager to use
         io_modes_that_create_file = ['w', 'w-', 'x']
         if mode in io_modes_that_create_file or manager is not None or extensions is not None:
             load_namespaces = False
 
         if load_namespaces:
             tm = get_type_map()
-            super().load_namespaces(tm, path, file=file_obj, driver=driver)
+            super().load_namespaces(tm, path, file=file_obj, driver=driver, aws_region=aws_region)
             manager = BuildManager(tm)
 
             # XXX: Leaving this here in case we want to revert to this strategy for
@@ -289,7 +284,7 @@ def __init__(self, **kwargs):
                 manager = get_manager()
         # Open the file
         super().__init__(path, manager=manager, mode=mode, file=file_obj, comm=comm,
-                         driver=driver, herd_path=herd_path)
+                         driver=driver, aws_region=aws_region, herd_path=herd_path)
 
     @property
     def nwb_version(self):

src/pynwb/validate.py

@@ -30,7 +30,7 @@ def _validate_helper(io: HDMFIO, namespace: str = CORE_NAMESPACE) -> list:
 
 
 def _get_cached_namespaces_to_validate(
-    path: str, driver: Optional[str] = None
+    path: str, driver: Optional[str] = None, aws_region: Optional[str] = None,
 ) -> Tuple[List[str], BuildManager, Dict[str, str]]:
     """
     Determine the most specific namespace(s) that are cached in the given NWBFile that can be used for validation.
@@ -58,7 +58,12 @@ def _get_cached_namespaces_to_validate(
     catalog = NamespaceCatalog(
         group_spec_cls=NWBGroupSpec, dataset_spec_cls=NWBDatasetSpec, spec_namespace_cls=NWBNamespace
     )
-    namespace_dependencies = NWBHDF5IO.load_namespaces(namespace_catalog=catalog, path=path, driver=driver)
+    namespace_dependencies = NWBHDF5IO.load_namespaces(
+        namespace_catalog=catalog,
+        path=path,
+        driver=driver,
+        aws_region=aws_region
+    )
 
     # Determine which namespaces are the most specific (i.e. extensions) and validate against those
     candidate_namespaces = set(namespace_dependencies.keys())