xiaoxia-saas/apps/worker/video_processing/dedup_helpers.py

"""查重辅助函数 — 从 generation.py 提取的 GeneratedVideo 记录 + 查重逻辑.

供 generate_video 共同复用，
创建 GeneratedVideo 记录后计算指纹并执行项目级 + 批次内查重。
"""

from __future__ import annotations

import logging
from uuid import uuid4

from sqlalchemy.orm import Session

logger = logging.getLogger(__name__)


def create_video_record_and_dedup(
    *,
    generation_task_id: str,
    project_id: str,
    user_id: str = "",
    batch_id: str,
    file_url: str,
    file_size: int,
    duration: float,
    video_path: str,
    mode: str,
    session: Session,
    width: int = 1280,
    height: int = 720,
    fps: float = 25.0,
    name: str = "",
    thumbnail_url: str = "",
) -> int:
    """创建 GeneratedVideo 记录，计算指纹并执行查重（历史 + 批次）。

    Args:
        generation_task_id: 生成任务 ID
        project_id: 项目 ID
        batch_id: 批次 ID（可为空字符串）
        file_url: 视频文件 URL
        file_size: 文件大小（字节）
        duration: 视频时长（秒）
        video_path: 视频本地路径（用于计算指纹）
        mode: 剪辑模式名称
        session: 数据库会话
        width: 视频宽度
        height: 视频高度
        fps: 视频帧率

    Returns:
        创建的视频记录数量（1 表示成功，0 表示失败）
    """
    from video_processing.dedup import VideoDeduplicator

    from packages.adapters.sqlalchemy_impl.generated_video_repository import (
        SQLAlchemyGeneratedVideoRepository,
    )
    from packages.domain import GeneratedVideo

    try:
        video_id = uuid4().hex
        # 使用传入的名称，没有则 fallback 到默认命名
        video_name = name.strip() if name else f"generated-{generation_task_id[:8]}.mp4"
        generated_video = GeneratedVideo(
            id=video_id,
            project_id=project_id,
            user_id=user_id,
            generation_task_id=generation_task_id,
            name=video_name,
            file_url=file_url,
            file_size=file_size,
            duration=duration,
            width=width,
            height=height,
            fps=fps,
            status="completed",
            generation_params={"mode": mode},
        )

        video_repo = SQLAlchemyGeneratedVideoRepository(session)
        video_repo.create(generated_video)

        # 生成封面缩略图
        if thumbnail_url:
            generated_video.thumbnail_url = thumbnail_url
            video_repo.update_thumbnail(video_id, thumbnail_url)
            logger.info("Thumbnail set for video %s: %s", video_id, thumbnail_url[:80] if thumbnail_url else "")
        else:
            logger.debug("No thumbnail_url provided for video %s, skipping", video_id)

        # 计算视频指纹
        deduplicator = VideoDeduplicator()
        try:
            fingerprint = deduplicator.compute_fingerprint(video_path)
        except Exception as fp_err:
            logger.warning("Fingerprint computation failed for %s: %s", video_id, fp_err)
            session.commit()
            return 1

        generated_video.video_fingerprint = fingerprint.to_dict()

        # (a) 历史成片查重
        duplicate_result = deduplicator.check_duplicate(fingerprint, project_id, session)

        # (b) 批次内查重（仅当有 batch_id 时）
        if not duplicate_result and batch_id:
            duplicate_result = deduplicator.check_batch_duplicate(fingerprint, batch_id, video_id, session)

        if duplicate_result:
            generated_video.is_duplicate = True
            generated_video.duplicate_of = duplicate_result["duplicate_of"]
            logger.info(
                "Duplicate detected: %s -> %s (reason=%s, similarity=%.3f)",
                video_id,
                duplicate_result["duplicate_of"],
                duplicate_result["reason"],
                duplicate_result["similarity"],
            )
        else:
            generated_video.is_duplicate = False
            generated_video.duplicate_of = None

        # 计算重复率百分比（与项目内所有已有视频对比取最高相似度）
        try:
            dup_rate = deduplicator.compute_duplicate_rate(fingerprint, project_id, video_id, session)
            generated_video.duplicate_rate = dup_rate
            logger.info("Duplicate rate for %s: %.2f%%", video_id, dup_rate)
        except Exception as rate_err:
            logger.warning("Failed to compute duplicate_rate for %s: %s", video_id, rate_err)
            generated_video.duplicate_rate = None

        video_repo.update(generated_video)
        session.commit()
        logger.info(
            "GeneratedVideo record created: %s (task=%s, dup=%s)",
            video_id,
            generation_task_id,
            generated_video.is_duplicate,
        )
        return 1
    except Exception as e:
        logger.error(
            "Failed to create video record / dedup for task %s: %s",
            generation_task_id,
            e,
        )
        session.rollback()
        return 0