From 47e5cb8da10947fddc62cbb64d12d11a7203dbd3 Mon Sep 17 00:00:00 2001
From: sneakers-the-rat <sneakers-the-rat@protonmail.com>
Date: Tue, 3 Sep 2024 17:41:34 -0700
Subject: [PATCH 1/2] bugfix - don't choke on empty datasets during validation

---
 src/numpydantic/interface/hdf5.py | 12 +++++++++++-
 tests/test_interface/test_hdf5.py | 20 ++++++++++++++++++++
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/src/numpydantic/interface/hdf5.py b/src/numpydantic/interface/hdf5.py
index 4fc548d..e3edac4 100644
--- a/src/numpydantic/interface/hdf5.py
+++ b/src/numpydantic/interface/hdf5.py
@@ -39,6 +39,7 @@ as ``S32`` isoformatted byte strings (timezones optional) like:
     
 """
 
+import pdb
 import sys
 from datetime import datetime
 from pathlib import Path
@@ -321,13 +322,22 @@ class H5Interface(Interface):
         """
         if h5py.h5t.check_string_dtype(array.dtype):
             # check for datetimes
+            pdb.set_trace()
             try:
                 if array[0].dtype.type is np.datetime64:
                     return np.datetime64
                 else:
                     return str
-            except (AttributeError, ValueError, TypeError):  # pragma: no cover
+            except (AttributeError, TypeError):  # pragma: no cover
+                # it's not a datetime, but it is some kind of string
                 return str
+            except (IndexError, ValueError):
+                # if the dataset is empty, we can't tell if something is a datetime
+                # or not, so we just tell the validation method what it wants to hear
+                if self.dtype in (np.datetime64, str):
+                    return self.dtype
+                else:
+                    return str
         else:
             return array.dtype
 
diff --git a/tests/test_interface/test_hdf5.py b/tests/test_interface/test_hdf5.py
index bf47a8d..9ca9e94 100644
--- a/tests/test_interface/test_hdf5.py
+++ b/tests/test_interface/test_hdf5.py
@@ -198,3 +198,23 @@ def test_datetime(hdf5_array, compound):
     assert instance.array[0, 0] == now
     instance.array[0] = now
     assert all(instance.array[0] == now)
+
+
+@pytest.mark.parametrize("dtype", [int, float, str, datetime])
+def test_empty_dataset(dtype, tmp_path):
+    """
+    Empty datasets shouldn't choke us during validation
+    """
+    array_path = tmp_path / "test.h5"
+    if dtype in (str, datetime):
+        np_dtype = "S32"
+    else:
+        np_dtype = dtype
+
+    with h5py.File(array_path, "w") as h5f:
+        _ = h5f.create_dataset(name="/data", dtype=np_dtype)
+
+    class MyModel(BaseModel):
+        array: NDArray[Any, dtype]
+
+    _ = MyModel(array=(array_path, "/data"))

From 34e48b394a5365abfd4384039aa526248e3d6271 Mon Sep 17 00:00:00 2001
From: sneakers-the-rat <sneakers-the-rat@protonmail.com>
Date: Tue, 3 Sep 2024 17:43:11 -0700
Subject: [PATCH 2/2] rm pdb

---
 pyproject.toml                    | 4 ++--
 src/numpydantic/interface/hdf5.py | 2 --
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 7c8b8ae..35bf0a4 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -145,8 +145,8 @@ select = [
     "D210", "D211",
     # emptiness
     "D419",
-
-
+    # no pdb
+    "T100",
 ]
 ignore = [
     "ANN101", "ANN102", "ANN401", "ANN204",
diff --git a/src/numpydantic/interface/hdf5.py b/src/numpydantic/interface/hdf5.py
index e3edac4..20cec0d 100644
--- a/src/numpydantic/interface/hdf5.py
+++ b/src/numpydantic/interface/hdf5.py
@@ -39,7 +39,6 @@ as ``S32`` isoformatted byte strings (timezones optional) like:
     
 """
 
-import pdb
 import sys
 from datetime import datetime
 from pathlib import Path
@@ -322,7 +321,6 @@ class H5Interface(Interface):
         """
         if h5py.h5t.check_string_dtype(array.dtype):
             # check for datetimes
-            pdb.set_trace()
             try:
                 if array[0].dtype.type is np.datetime64:
                     return np.datetime64