Description #

Video timestamp splitting processor, supports splitting by specified time range

Key features #

• Split video by given timestamp intervals
• Supports segment binary output or TOS storage
• Provides automatic format inference and customization

Format support #

• MP4 (.mp4)
• AVI (.avi)
• MOV (.mov)
• MKV (.mkv)
• Other common video formats

Operator parameters #

Input #

Output #

The processed struct fields include:

• segments: list[str], list of paths for video segments after splitting
• segments_binary: list[bytes], list of binary data for video segments after splitting

Parameters #

If a parameter does not have a default value, it is required

Examples #

The following code demonstrates how to use Daft (for distributed scenarios) to run the operator and split video by timestamp.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.udf import las_udf
from daft.las.functions.video import VideoSplitByTimestamps

if __name__ == "__main__":

    # The split video will be saved to the specified TOS path after modification. Therefore, environment variables must be set to ensure write permissions to TOS, including: ACCESS_KEY, SECRET_KEY, TOS_ENDPOINT, TOS_REGION, TOS_TEST_DIR
    TOS_DIR = os.getenv("TOS_TEST_DIR", "tos_bucket")
    output_tos_dir = f"tos://{TOS_DIR}/video/video_split_by_timestamps"
    
    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S.%s".format(),
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()
    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    # Build URL using environment variables
    tos_dir_url = os.getenv("TOS_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")
    samples = {
        "video_path": [
            f"https://{tos_dir_url}/public/shared_video_dataset/sample.mp4"
        ],
        "timestamp_ranges": [[(0.0, 2.0), (2.0, 4.0)]],
    }

    ds = daft.from_pydict(samples)

    splitter = las_udf(
        VideoSplitByTimestamps,
        construct_args={
            "output_tos_dir": output_tos_dir,
            "output_segments_binary": False,
            "output_video_format": "mp4",
        },
    )

    # Use Daft for distributed processing
    ds = ds.with_column("results", splitter(col("video_path"), None, None, col("timestamp_ranges")))

    ds.show()
    # ╭────────────────────────────────┬────────────────────────────────────────┬─────────────────────────────────────────────────────────────╮
    # │ video_path                     ┆ timestamp_ranges                       ┆ results                                                     │
    # │ ---                            ┆ ---                                    ┆ ---                                                         │
    # │ Utf8                           ┆ List[Struct[_0: Float64, _1: Float64]] ┆ Struct[segments: List[Utf8], segments_binary: List[Binary]] │
    # ╞════════════════════════════════╪════════════════════════════════════════╪═════════════════════════════════════════════════════════════╡
    # │ https://las-cn-beijing-publi-… ┆ [{_0: 0,                               ┆ {segments: ["tos://tos_bucket/video/video_split_b…          │
    # │                                ┆ }, {_0: 2,                             ┆                                                             │
    # │                                ┆ _1…                                    ┆                                                             │
    # ╰────────────────────────────────┴────────────────────────────────────────┴─────────────────────────────────────────────────────────────╯