def encode_example()

in src/datasets/features/video.py [0:0]

• 29 lines of code
• 16 McCabe index (conditional complexity)

    def encode_example(self, value: Union[str, bytes, bytearray, Example, np.ndarray, "VideoDecoder"]) -> Example:
        """Encode example into a format for Arrow.

        Args:
            value (`str`, `np.ndarray`, `bytes`, `bytearray`, `VideoDecoder` or `dict`):
                Data passed as input to Video feature.

        Returns:
            `dict` with "path" and "bytes" fields
        """
        if value is None:
            raise ValueError("value must be provided")

        if config.TORCHCODEC_AVAILABLE:
            from torchcodec.decoders import VideoDecoder
        else:
            VideoDecoder = None

        if isinstance(value, list):
            value = np.array(value)

        if isinstance(value, str):
            return {"path": value, "bytes": None}
        elif isinstance(value, (bytes, bytearray)):
            return {"path": None, "bytes": value}
        elif isinstance(value, np.ndarray):
            # convert the video array to bytes
            return encode_np_array(value)
        elif VideoDecoder is not None and isinstance(value, VideoDecoder):
            # convert the torchcodec video decoder to bytes
            return encode_torchcodec_video(value)
        elif isinstance(value, dict):
            path, bytes_ = value.get("path"), value.get("bytes")
            if path is not None and os.path.isfile(path):
                # we set "bytes": None to not duplicate the data if they're already available locally
                return {"bytes": None, "path": path}
            elif bytes_ is not None or path is not None:
                # store the video bytes, and path is used to infer the video format using the file extension
                return {"bytes": bytes_, "path": path}
            else:
                raise ValueError(
                    f"A video sample should have one of 'path' or 'bytes' but they are missing or None in {value}."
                )
        else:
            raise TypeError(f"Unsupported encode_example type: {type(value)}")