From e25ca3905148385b156b4f6a821ce3cc8e32045b Mon Sep 17 00:00:00 2001
From: sharkinsspatial <sharkinsgis@gmail.com>
Date: Thu, 20 Feb 2025 09:57:31 -0500
Subject: [PATCH] Handle xarray zarr backend decoding logic.

---
 virtualizarr/readers/hdf/hdf.py             |  8 ++++-
 virtualizarr/tests/test_readers/conftest.py | 40 +++++++++++++--------
 2 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/virtualizarr/readers/hdf/hdf.py b/virtualizarr/readers/hdf/hdf.py
index 4a155913..9ce9c377 100644
--- a/virtualizarr/readers/hdf/hdf.py
+++ b/virtualizarr/readers/hdf/hdf.py
@@ -14,6 +14,7 @@
 
 import numpy as np
 import xarray as xr
+from xarray.backends.zarr import FillValueCoder
 
 from virtualizarr.manifests import (
     ChunkEntry,
@@ -248,11 +249,16 @@ def _extract_cf_fill_value(
         fillvalue = None
         for n, v in h5obj.attrs.items():
             if n == "_FillValue":
-                # Extract scalar _FillValue
                 if isinstance(v, np.ndarray) and v.size == 1:
                     fillvalue = v.item()
                 else:
                     fillvalue = v
+                if (
+                    fillvalue is not None
+                    and h5obj.dtype.kind not in "S"
+                    and h5obj.dtype.fields is None
+                ):
+                    fillvalue = FillValueCoder.encode(fillvalue, h5obj.dtype)
         return fillvalue
 
     @staticmethod
diff --git a/virtualizarr/tests/test_readers/conftest.py b/virtualizarr/tests/test_readers/conftest.py
index 52626e45..658de4a9 100644
--- a/virtualizarr/tests/test_readers/conftest.py
+++ b/virtualizarr/tests/test_readers/conftest.py
@@ -354,16 +354,30 @@ def scalar_fill_value_hdf5_file(tmpdir):
     return filepath
 
 
+compound_dtype = np.dtype(
+    [
+        ("id", "i4"),  # 4-byte integer
+        ("temperature", "f4"),  # 4-byte float
+    ]
+)
+
+compound_data = np.array(
+    [
+        (1, 98.6),
+        (2, 101.3),
+    ],
+    dtype=compound_dtype,
+)
+
+compound_fill = (-9999, -9999.0)
+
 fill_values = [
-    -9999,  # Integer fill value
-    -9999.0,  # Floating-point fill value
-    np.nan,  # NaN as fill value
-    True,
-    False,  # Boolean fill values
-    "N/A",  # String fill value
-    b"Unknown",  # Bytes fill value
-    1 + 2j,  # Complex number fill value
-    (b"Unknown", -1),  # Structured type (Tuple)
+    {"fill_value": -9999, "data": np.random.randint(0, 10, size=(5))},
+    {"fill_value": -9999.0, "data": np.random.random(5)},
+    {"fill_value": np.nan, "data": np.random.random(5)},
+    {"fill_value": True, "data": np.random.choice([True, False], size=(5))},
+    {"fill_value": "N/A", "data": np.array(["one", "two"], dtype="S")},
+    {"fill_value": compound_fill, "data": compound_data},
 ]
 
 
@@ -371,10 +385,8 @@ def scalar_fill_value_hdf5_file(tmpdir):
 def cf_fill_value_hdf5_file(tmpdir, request):
     filepath = f"{tmpdir}/cf_fill_value.nc"
     f = h5py.File(filepath, "w")
-    data = np.random.randint(0, 10, size=(5))
-    dset = f.create_dataset(name="data", data=data, chunks=True)
-    if request.param is not None:
-        dset.attrs["_FillValue"] = request.param
+    dset = f.create_dataset(name="data", data=request.param["data"], chunks=True)
+    dset.attrs["_FillValue"] = request.param["fill_value"]
     return filepath
 
 
@@ -382,7 +394,7 @@ def cf_fill_value_hdf5_file(tmpdir, request):
 def cf_array_fill_value_hdf5_file(tmpdir):
     filepath = f"{tmpdir}/cf_array_fill_value.nc"
     f = h5py.File(filepath, "w")
-    data = np.random.randint(0, 10, size=(5))
+    data = np.random.random(5)
     dset = f.create_dataset(name="data", data=data, chunks=True)
     dset.attrs["_FillValue"] = np.array([np.nan])
     return filepath