datasets 4.8.0__tar.gz → 4.8.2__tar.gz

{datasets-4.8.0/src/datasets.egg-info → datasets-4.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: datasets
-Version: 4.8.0
+Version: 4.8.2
 Summary: HuggingFace community-driven open-source library of datasets
 Home-page: https://github.com/huggingface/datasets
 Download-URL: https://github.com/huggingface/datasets/tags

{datasets-4.8.0 → datasets-4.8.2}/setup.py

@@ -233,7 +233,7 @@ EXTRAS_REQUIRE = {
 
 setup(
     name="datasets",
-    version="4.8.0",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
+    version="4.8.2",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
     description="HuggingFace community-driven open-source library of datasets",
     long_description=open("README.md", encoding="utf-8").read(),
     long_description_content_type="text/markdown",

{datasets-4.8.0 → datasets-4.8.2}/src/datasets/__init__.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "4.8.0"
+__version__ = "4.8.2"
 
 from .arrow_dataset import Column, Dataset
 from .arrow_reader import ReadInstruction

{datasets-4.8.0 → datasets-4.8.2}/src/datasets/iterable_dataset.py

@@ -2228,6 +2228,7 @@ class FormattedExamplesIterable(_BaseExamplesIterable):
     def _iter_arrow(self) -> Iterator[tuple[Key, pa.Table]]:
         if not self.features:
             yield from self.ex_iterable._iter_arrow()
+            return
         for key, pa_table in self.ex_iterable._iter_arrow():
             columns = set(pa_table.column_names)
             schema = self.features.arrow_schema

{datasets-4.8.0 → datasets-4.8.2}/src/datasets/utils/json.py

@@ -51,7 +51,7 @@ def find_mixed_struct_types_field_paths(examples: list, allow_root=False) -> lis
     while paths_and_content_to_check:
         path, content = paths_and_content_to_check.pop(0)
         if all(isinstance(x, dict) for x in content):
-            if (allow_root or path) and any(set(x) != set(content[0]) for x in content):
+            if (allow_root or path) and (any(set(x) != set(content[0]) for x in content) or not content[0]):
                 mixed_struct_types_field_paths.append(path)
             else:
                 for subfield in {field for x in content for field in x}:

{datasets-4.8.0 → datasets-4.8.2/src/datasets.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: datasets
-Version: 4.8.0
+Version: 4.8.2
 Summary: HuggingFace community-driven open-source library of datasets
 Home-page: https://github.com/huggingface/datasets
 Download-URL: https://github.com/huggingface/datasets/tags

{datasets-4.8.0 → datasets-4.8.2}/tests/test_arrow_dataset.py

@@ -34,6 +34,7 @@ from datasets.features import (
     ClassLabel,
     Features,
     Image,
+    Json,
     LargeList,
     List,
     Translation,
@@ -1901,7 +1902,7 @@ class BaseDatasetTest(TestCase):
                     "To debug the error, disable multiprocessing."
                 )
 
-    def test_map_on_lixed_types(self, in_memory):
+    def test_map_on_mixed_types(self, in_memory):
         mixed_data = {
             "mixed_type": [-1, 1, "foo"],
             "mix_struct_and_non_struct": [{"a": 0}, [0]],
@@ -3438,6 +3439,10 @@ class MiscellaneousDatasetTest(TestCase):
         data = {"messages": [_messages]}
         with Dataset.from_dict(data, on_mixed_types="use_json") as dset:
             self.assertEqual(dset[:], data)
+        data = {"empty_struct": [{}]}
+        with Dataset.from_dict(data, on_mixed_types="use_json") as dset:
+            self.assertEqual(dset[:], data)
+            self.assertEqual(dset.features["empty_struct"], Json())
 
     def test_concatenate_mixed_memory_and_disk(self):
         data1, data2, data3 = {"id": [0, 1, 2]}, {"id": [3, 4, 5]}, {"id": [6, 7]}