Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Don't embed videos #7259

Merged
merged 1 commit into from
Oct 28, 2024
Merged

Don't embed videos #7259

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 1 addition & 36 deletions src/datasets/features/video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
from ..download.download_config import DownloadConfig
from ..table import array_cast
from ..utils.file_utils import is_local_path, xopen
from ..utils.py_utils import no_op_if_value_is_null, string_to_dict
from ..utils.py_utils import string_to_dict


if TYPE_CHECKING:
Expand Down Expand Up @@ -236,41 +236,6 @@ def cast_storage(self, storage: Union[pa.StringArray, pa.StructArray, pa.ListArr
)
return array_cast(storage, self.pa_type)

def embed_storage(self, storage: pa.StructArray) -> pa.StructArray:
"""Embed video files into the Arrow array.

Args:
storage (`pa.StructArray`):
PyArrow array to embed.

Returns:
`pa.StructArray`: Array in the Video arrow storage type, that is
`pa.struct({"bytes": pa.binary(), "path": pa.string()})`.
"""

@no_op_if_value_is_null
def path_to_bytes(path):
with xopen(path, "rb") as f:
bytes_ = f.read()
return bytes_

bytes_array = pa.array(
[
(path_to_bytes(x["path"]) if x["bytes"] is None else x["bytes"]) if x is not None else None
for x in storage.to_pylist()
],
type=pa.binary(),
)
path_array = pa.array(
[
(os.path.basename(path) if os.path.isfile(path) else path) if path is not None else None
for path in storage.field("path").to_pylist()
],
type=pa.string(),
)
storage = pa.StructArray.from_arrays([bytes_array, path_array], ["bytes", "path"], mask=bytes_array.is_null())
return array_cast(storage, self.pa_type)


def video_to_bytes(video: "VideoReader") -> bytes:
"""Convert a decord Video object to bytes using native compression if possible"""
Expand Down
Loading