datasets 4.8.3__tar.gz → 4.8.4__tar.gz

{datasets-4.8.3/src/datasets.egg-info → datasets-4.8.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: datasets
-Version: 4.8.3
+Version: 4.8.4
 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-4.8.3 → datasets-4.8.4}/setup.py

@@ -233,7 +233,7 @@ EXTRAS_REQUIRE = {
 
 setup(
     name="datasets",
-    version="4.8.3",  # 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="4.8.4",  # 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-4.8.3 → datasets-4.8.4}/src/datasets/__init__.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "4.8.3"
+__version__ = "4.8.4"
 
 from .arrow_dataset import Column, Dataset
 from .arrow_reader import ReadInstruction

{datasets-4.8.3 → datasets-4.8.4}/src/datasets/formatting/jax_formatter.py

@@ -107,10 +107,13 @@ class JaxFormatter(TensorFormatter[Mapping, "jax.Array", Mapping]):
             if isinstance(value, PIL.Image.Image):
                 value = np.asarray(value)
         if config.TORCHVISION_AVAILABLE and "torchvision" in sys.modules:
-            from torchvision.io import VideoReader
+            try:
+                from torchvision.io import VideoReader
 
-            if isinstance(value, VideoReader):
-                return value  # TODO(QL): set output to jax arrays ?
+                if isinstance(value, VideoReader):
+                    return value  # TODO(QL): set output to jax arrays ?
+            except ImportError:
+                pass
         if config.TORCHCODEC_AVAILABLE and "torchcodec" in sys.modules:
             from torchcodec.decoders import AudioDecoder, VideoDecoder
 

{datasets-4.8.3 → datasets-4.8.4}/src/datasets/formatting/np_formatter.py

@@ -64,10 +64,13 @@ class NumpyFormatter(TensorFormatter[Mapping, np.ndarray, Mapping]):
             if isinstance(value, PIL.Image.Image):
                 return np.asarray(value, **self.np_array_kwargs)
         if config.TORCHVISION_AVAILABLE and "torchvision" in sys.modules:
-            from torchvision.io import VideoReader
+            try:
+                from torchvision.io import VideoReader
 
-            if isinstance(value, VideoReader):
-                return value  # TODO(QL): set output to np arrays ?
+                if isinstance(value, VideoReader):
+                    return value  # TODO(QL): set output to np arrays ?
+            except ImportError:
+                pass
         if config.TORCHCODEC_AVAILABLE and "torchcodec" in sys.modules:
             from torchcodec.decoders import AudioDecoder, VideoDecoder
 

{datasets-4.8.3 → datasets-4.8.4}/src/datasets/formatting/tf_formatter.py

@@ -71,10 +71,13 @@ class TFFormatter(TensorFormatter[Mapping, "tf.Tensor", Mapping]):
             if isinstance(value, PIL.Image.Image):
                 value = np.asarray(value)
         if config.TORCHVISION_AVAILABLE and "torchvision" in sys.modules:
-            from torchvision.io import VideoReader
+            try:
+                from torchvision.io import VideoReader
 
-            if isinstance(value, VideoReader):
-                return value  # TODO(QL): set output to tf tensors ?
+                if isinstance(value, VideoReader):
+                    return value  # TODO(QL): set output to tf tensors ?
+            except ImportError:
+                pass
         if config.TORCHCODEC_AVAILABLE and "torchcodec" in sys.modules:
             from torchcodec.decoders import AudioDecoder, VideoDecoder
 

{datasets-4.8.3 → datasets-4.8.4}/src/datasets/formatting/torch_formatter.py

@@ -77,10 +77,13 @@ class TorchFormatter(TensorFormatter[Mapping, "torch.Tensor", Mapping]):
 
                 value = value.transpose((2, 0, 1))
         if config.TORCHVISION_AVAILABLE and "torchvision" in sys.modules:
-            from torchvision.io import VideoReader
+            try:
+                from torchvision.io import VideoReader
 
-            if isinstance(value, VideoReader):
-                return value  # TODO(QL): set output to torch tensors ?
+                if isinstance(value, VideoReader):
+                    return value  # TODO(QL): set output to torch tensors ?
+            except ImportError:
+                pass
         if config.TORCHCODEC_AVAILABLE and "torchcodec" in sys.modules:
             from torchcodec.decoders import AudioDecoder, VideoDecoder
 

{datasets-4.8.3 → datasets-4.8.4}/src/datasets/iterable_dataset.py

@@ -4090,7 +4090,7 @@ class IterableDataset(DatasetInfoMixin):
 
         * audio -> dict of "array" and "sampling_rate" and "path"
         * image -> PIL.Image
-        * video -> torchvision.io.VideoReader
+        * video -> torchcodec.decoders.VideoDecoder
 
         You can enable multithreading using `num_threads`. This is especially useful to speed up remote
         data streaming. However it can be slower than `num_threads=0` for local data on fast disks.

{datasets-4.8.3 → datasets-4.8.4}/src/datasets/packaged_modules/json/json.py

@@ -190,8 +190,13 @@ class Json(datasets.ArrowBasedBuilder):
                                 and self.info.features is None
                                 and self.config.on_mixed_types == "use_json"
                             ):
-                                examples = [ujson_loads(line) for line in batch.splitlines()]
-                                json_field_paths += find_mixed_struct_types_field_paths(examples)
+                                try:
+                                    examples = [ujson_loads(line) for line in batch.splitlines()]
+                                except ValueError:
+                                    # the file is likely not JSON Lines and may contain one single multi-line JSON object
+                                    pass
+                                else:
+                                    json_field_paths += find_mixed_struct_types_field_paths(examples)
                             # Re-encode JSON fields
                             original_batch = batch
                             if json_field_paths:

{datasets-4.8.3 → datasets-4.8.4/src/datasets.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: datasets
-Version: 4.8.3
+Version: 4.8.4
 Summary: HuggingFace community-driven open-source library of datasets
 Home-page: https://github.com/huggingface/datasets
 Download-URL: https://github.com/huggingface/datasets/tags