Squeeze attribute data

cdflib/cdfread.py

@@ -9,6 +9,7 @@
 from typing import Any, Dict, List, Optional, Tuple, Union
 
 import numpy as np
+import numpy.typing as npt
 
 import cdflib.epochs as epoch
 from cdflib._gzip_wrapper import gzip_inflate
@@ -23,6 +24,7 @@
     VDRInfo,
 )
 from cdflib.s3 import S3object
+from cdflib.utils import _squeeze_or_scalar
 
 __all__ = ["CDF"]
 
@@ -1770,14 +1772,16 @@ def _get_attdata(self, adr_info: ADRInfo, entry_num: int, num_entry: int, first_
                 data_type = self._datatype_token(aedr_info.data_type)
 
                 num_items = aedr_info.num_elements
-                data = aedr_info.entry
+                data: Union[str, npt.NDArray] = aedr_info.entry
                 if isinstance(data, str):
                     if aedr_info.num_strings is not None:
                         num_strings = aedr_info.num_strings
                         num_items = num_strings
                         if num_strings > 1 and isinstance(aedr_info.entry, str):
                             data = np.array(aedr_info.entry.split("\\N "))
-                return AttData(item_size, data_type, num_items, data)
+                    return AttData(item_size, data_type, num_items, data)
+                else:
+                    return AttData(item_size, data_type, num_items, _squeeze_or_scalar(data))
             else:
                 position = next_aedr
 

cdflib/utils.py

@@ -1,9 +1,18 @@
+from numbers import Number
 from typing import Union
 
 import numpy as np
 import numpy.typing as npt
 
 
+def _squeeze_or_scalar(arr: npt.ArrayLike) -> Union[npt.NDArray, Number]:
+    arr = np.squeeze(arr)
+    if arr.ndim == 0:
+        return arr.item()
+    else:
+        return arr
+
+
 def _squeeze_or_scalar_real(arr: npt.ArrayLike) -> Union[npt.NDArray, float]:
     arr = np.squeeze(arr)
     if arr.ndim == 0:

cdflib/xarray/cdf_to_xarray.py

@@ -69,7 +69,7 @@ def _convert_cdf_time_types(
     for att in atts:
         data_type = atts[att].Data_Type
         data = atts[att].Data
-        if len(data) == 0 or data_type not in ("CDF_EPOCH", "CDF_EPOCH16", "CDF_TIME_TT2000"):
+        if data_type not in ("CDF_EPOCH", "CDF_EPOCH16", "CDF_TIME_TT2000"):
             new_atts[att] = data
         else:
             if to_datetime:

doc/changelog.rst

@@ -2,8 +2,10 @@
 Changelog
 =========
 
-Unreleased
-==========
+1.2.0
+=====
+- Attribute data with a single value is now returned as a Python scalar instead of
+  a numpy array.
 - Added missing changelog entries for 1.1.1 and 1.1.2.
 
 1.1.2

tests/test_cdfwrite.py

@@ -82,7 +82,7 @@ def test_checksum_compressed(tmp_path):
     np.testing.assert_equal(var, v)
 
     att = reader.attget("Attribute1", entry=0)
-    assert att.Data == [1]
+    assert att.Data == 1
 
     att = reader.attget("Attribute2", entry=0)
     assert att.Data == "500"
@@ -265,7 +265,7 @@ def test_create_zvariables_with_attributes(tmp_path):
 
     # Test CDF info
     att = reader.attget("Attribute1", entry=0)
-    assert att.Data == [1]
+    assert att.Data == 1
 
     att = reader.attget("Attribute2", entry=1)
     assert att.Data == "1000"
@@ -300,7 +300,7 @@ def test_create_zvariables_then_attributes(tmp_path):
 
     # Test CDF info
     att = reader.attget("Attribute1", entry=0)
-    assert att.Data == [1]
+    assert att.Data == 1
 
     att = reader.attget("Attribute2", entry=1)
     att.Data == "1000"
@@ -567,7 +567,7 @@ def test_create_2d_r_and_z_variables(tmp_path):
     np.testing.assert_equal(var, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
 
     att = reader.attget("Attribute1", entry="Variable2")
-    assert att.Data == [2]
+    assert att.Data == 2
 
     att = reader.attget("Attribute2", entry="Variable2")
     assert att.Data == "1000"