From f656ec98c5c963b8ac2924046ae9e88c27a03b61 Mon Sep 17 00:00:00 2001 From: cat <1716967236@qq.com> Date: Fri, 18 Sep 2026 22:23:19 +0800 Subject: [PATCH] =?UTF-8?q?feat:=20=E5=AA=92=E4=BD=93=E5=BA=93=E5=AD=97?= =?UTF-8?q?=E5=B9=95=E9=87=8D=E7=94=9F=E6=88=90=E7=BB=9F=E8=AE=A1=E8=84=9A?= =?UTF-8?q?=E6=9C=AC=EF=BC=88=E6=95=B0=E9=87=8F/=E6=97=B6=E9=95=BF/?= =?UTF-8?q?=E6=97=A7=E5=AD=97=E5=B9=95=E5=A4=87=E4=BB=BD=EF=BC=89?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 模型与管线切换后需要把媒体库里旧管线生成的字幕整批重跑。批量引擎按"视频旁 已有字幕即 SKIPPED"判定，重跑前必须先统计范围、再把旧字幕改名备份，否则建出来 的任务会把所有视频全部跳过。 - `scripts/plan_regenerate_subtitles.py`：扫描媒体库，按 CN 产物的最早 mtime 判定 生成时间，统计待重生成的数量/时长/体积并输出 JSON 计划；`--backup-old [--apply] [--select]` 把旧字幕原地改名为 `<原名>.old-<日期>` 供批量重跑。脚本不依赖仓库， 可拷到媒体库主机直接跑（CIFS 挂载下逐文件 ffprobe 太慢）。 - 测试覆盖真实 10 秒视频与真实字幕文件，含 ffprobe 时长探测、分类边界、 备份幂等与选择清单解析。 --- docs/operations.md | 34 ++ docs/testing.md | 2 + scripts/plan_regenerate_subtitles.py | 320 ++++++++++++++++++ .../__init__.py | 0 .../data/clip_10s.mp4 | Bin 0 -> 19770 bytes .../test_plan_regenerate_subtitles.py | 317 +++++++++++++++++ 6 files changed, 673 insertions(+) create mode 100644 scripts/plan_regenerate_subtitles.py create mode 100644 tests/scripts/test_plan_regenerate_subtitles/__init__.py create mode 100644 tests/scripts/test_plan_regenerate_subtitles/data/clip_10s.mp4 create mode 100644 tests/scripts/test_plan_regenerate_subtitles/test_plan_regenerate_subtitles.py diff --git a/docs/operations.md b/docs/operations.md index 14d0af6..a3d13b0 100644 --- a/docs/operations.md +++ b/docs/operations.md @@ -160,6 +160,40 @@ - **环境变量**：`WOV_BATCH_ENABLED`（默认 1）、`WOV_BATCH_INTERVAL_SECONDS` （默认 1.0），完整列表见 [configuration.md](./configuration.md)。 +## 媒体库历史字幕重建（统计 → 备份 → 批量重跑） + +模型或管线切换后，媒体库里由旧管线生成的字幕需要整批重跑。批量引擎按 +“视频旁已有字幕即 SKIPPED”判定，所以重跑前必须先统计范围、再把旧字幕改名 +备份，否则建出来的任务会把所有视频全部跳过。工具是 `scripts/plan_regenerate_subtitles.py` +（**不依赖仓库**，可拷到媒体库主机直接跑：CIFS 挂载下逐文件 ffprobe 与 +目录扫描都慢得多，在 NAS 本地跑 524 个视频只要几秒）。 + +生成时间的判定口径：只看本流水线产出的 CN 产物（`<视频名>.CN.srt`、 +`<视频名>.CN_dual_eye.ass`），取它们**最早**的 mtime——双目 `.ass` 可能被样式 +统一脚本原地改写而“变新”，中文字幕的 mtime 才是真实生成时间。 + +```bash +# 1) 统计：数量 / 时长 / 体积 / 按月分布，并写出逐条明细 JSON +python3 scripts/plan_regenerate_subtitles.py /vol1/1000/123 \ + --before 2026-09-01 --out data/experiments/regen_plan/plan_2026-09-01.json + +# 2) 备份旧字幕（默认预览，--apply 才落盘）：改名 <原名>.old-<当天日期> +python3 scripts/plan_regenerate_subtitles.py /vol1/1000/123 --backup-old +python3 scripts/plan_regenerate_subtitles.py /vol1/1000/123 --backup-old --apply \ + --select sample10.txt # 只处理清单里的视频，支持 # 注释 + +# 3) 建批量任务（批量页或 POST /api/batch/jobs） +``` + +- 备份文件名带 `.old-<日期>` 后缀，扩展名不再是字幕后缀，批量引擎不会再把它当 + 旁挂字幕；确认新字幕无误后删除备份，需要回退则去掉后缀改回原名。 +- 未备份的视频仍有旁挂字幕 → 创建任务时记 SKIPPED，因此“整库建一个任务”即可， + 实际只会处理被备份的那批；已重跑的视频产出新 CN 字幕（mtime 变新），全量重建 + 时自动归入“已是最新”，不会重复处理。 +- 实测数据（380 个待重生成 / 207.88 小时；10 个样本 6.54 小时素材跑 77.7 分钟、 + GPU 平均 289.6 W、约 0.375 kWh，全量推算约 41 小时 / 整机 15 kWh）见 + `data/experiments/regen_plan/REPORT.md`。 + ## 相关文档 - 环境变量全表：[configuration.md](./configuration.md) diff --git a/docs/testing.md b/docs/testing.md index 6468eb7..04cab73 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -51,6 +51,7 @@ tests/ ├── web/test_crop/ # 对应 web/assets/（框选几何换算） ├── web/test_batch/ # 对应 web/assets/（批量页渲染） ├── scripts/test_fix_zombie_batch_jobs/ # 对应 scripts/（僵尸批量任务修复） +├── scripts/test_plan_regenerate_subtitles/ # 对应 scripts/（字幕重生成计划统计） └── shared/ # 跨模块公共设施 ├── realdata_contract.py # 真实数据契约与对齐量化 ├── srt_entries.py # 按秒解析 SRT @@ -161,6 +162,7 @@ tests/ | `web/assets/crop.js` | 框选几何换算 | `tests/web/test_crop/`（真实 node 执行） | 已覆盖 | | `web/assets/batch.js` | 批量页明细/进度渲染 | `tests/web/test_batch/`（真实 node 执行） | 已覆盖 | | `scripts/fix_zombie_batch_jobs.py` | 僵尸批量任务诊断与修复 | `tests/scripts/test_fix_zombie_batch_jobs/` | 已覆盖 | +| `scripts/plan_regenerate_subtitles.py` | 媒体库字幕重生成计划统计（数量/时长/分类） | `tests/scripts/test_plan_regenerate_subtitles/` | 已覆盖 | | `tests/shared/srt_entries.py` | 按秒解析 SRT（测试公共设施） | `tests/shared/test_srt_entries/` | 已覆盖 | | `tests/shared/realdata_contract.py` | 真实数据契约与对齐量化 | `tests/shared/test_alignment/` | 已覆盖 | | `tests/shared/env_isolation.py` | 环境/临时目录隔离 | 被 `tests/app/test_config` 等间接覆盖 | 已覆盖（间接） | diff --git a/scripts/plan_regenerate_subtitles.py b/scripts/plan_regenerate_subtitles.py new file mode 100644 index 0000000..f3ae91b --- /dev/null +++ b/scripts/plan_regenerate_subtitles.py @@ -0,0 +1,320 @@ +"""统计媒体库中需要重新生成字幕的视频数量与时长，产出可复用的重生成计划。 + +判定口径（`--before` 可调）： + +- 只看本流水线产出的 CN 字幕：`<视频名>.CN.srt` 与 `<视频名>.CN_dual_eye.ass`； +- 生成时间取这些产物中**最早**的 mtime。双目 `.ass` 可能被样式统一脚本原地 + 改写而"变新"，中文字幕的 mtime 才反映真实生成时间，取最早值两者兼容； +- 生成时间早于 `--before`（默认 2026-09-01，本地时区）即列为待重新生成； +- 完全没有 CN 字幕的视频单独统计，不算"重生成"（那属于首次生成）。 + +脚本不依赖仓库，可拷到媒体库所在主机直接跑（共享目录挂载方式下逐文件 +ffprobe 太慢）：目录内容只读，不改动任何文件；结果写 JSON 计划供批量重跑。 + +用法： + python3 scripts/plan_regenerate_subtitles.py /mnt/fnOS/123 + python3 scripts/plan_regenerate_subtitles.py /vol1/1000/123 --before 2026-09-01 \ + --out data/experiments/regen_plan.json + +批量引擎看到视频旁已有字幕就会跳过该视频，重生成前需先改名备份旧字幕： + + python3 scripts/plan_regenerate_subtitles.py /vol1/1000/123 --backup-old + python3 scripts/plan_regenerate_subtitles.py /vol1/1000/123 --backup-old --apply \ + --select sample.txt +""" + +from __future__ import annotations + +import argparse +import json +import subprocess +import sys +from concurrent.futures import ThreadPoolExecutor +from datetime import datetime +from pathlib import Path + +# 与 src/wov_app/batch.py 的 VIDEO_EXTENSIONS / SUBTITLE_EXTENSIONS 保持一致， +# 本脚本要在媒体库主机上独立运行，故不复用仓库常量。 +VIDEO_EXTENSIONS = { + ".mp4", ".mkv", ".avi", ".mov", ".webm", ".flv", ".ts", + ".m4v", ".wmv", ".mpg", ".mpeg", ".3gp", +} +SUBTITLE_EXTENSIONS = {".srt", ".ass", ".ssa", ".vtt"} + +# CN 产物识别：这两个后缀由本流水线生成（见 batch.py 的产物命名约定）； +# 媒体库里其它 .srt 多为片源自带字幕，不参与"字幕生成时间"判定。 +CN_PRODUCT_MARKERS = (".cn.srt", ".cn_dual_eye.ass") + +PENDING = "pending" +CURRENT = "current" +MISSING = "missing" + + +def iter_videos(root: Path) -> list[Path]: + """递归列出媒体库下全部视频文件，按路径排序保证结果可复现。""" + paths = [ + p for p in root.rglob("*") + if p.is_file() and p.suffix.lower() in VIDEO_EXTENSIONS + ] + return sorted(paths) + + +def cn_products(video: Path) -> list[Path]: + """列出视频旁由本流水线产出的 CN 字幕（同一目录、文件名含视频主名）。""" + stem = video.stem.lower() + found: list[Path] = [] + for item in video.parent.iterdir(): + if not item.is_file(): + continue + name = item.name.lower() + if item.suffix.lower() not in SUBTITLE_EXTENSIONS: + continue + if stem in name and name.endswith(CN_PRODUCT_MARKERS): + found.append(item) + return sorted(found) + + +def sidecar_subtitles(video: Path) -> list[Path]: + """列出批量引擎认定为“已有字幕”的旁挂字幕文件（与 batch.py 判定一致）。 + + 同目录、字幕扩展名、文件名包含视频主名；主名只有单个字符时只接受 + “主名.”前缀，避免 a.mp4 误配 apple.srt。 + """ + stem = video.stem.lower() + try: + siblings = list(video.parent.iterdir()) + except OSError: + return [] + found: list[Path] = [] + for item in siblings: + try: + if not item.is_file() or item.suffix.lower() not in SUBTITLE_EXTENSIONS: + continue + except OSError: + continue + name = item.name.lower() + if len(stem) <= 1: + matched = name.startswith(stem + ".") + else: + matched = stem in name + if matched: + found.append(item) + return sorted(found) + + +def read_select_list(path: Path) -> set[str]: + """读取 `--select` 文件里的视频标识（每行一个，支持行首或行尾 `#` 注释）。""" + keys: set[str] = set() + for line in Path(path).read_text(encoding="utf-8").splitlines(): + text = line.split(" #", 1)[0].strip() + if text and not text.startswith("#"): + keys.add(text) + return keys + + +def backup_old_subtitles(items: list[dict], suffix: str, apply: bool = False, + select: set[str] | None = None) -> list[tuple[Path, Path]]: + """把待重生成视频的旁挂字幕原地改名，让批量引擎不再把该视频判为已有字幕。 + + 改名目标为 `<原名>`；目标已存在（同一批重复执行）时跳过，不覆盖 + 旧备份。apply=False 只返回改名为计划，不动磁盘。select 按绝对路径、 + 相对路径或文件名筛选要处理的视频。 + """ + changed: list[tuple[Path, Path]] = [] + for item in items: + video = Path(item["video"]) + if select is not None: + keys = (str(video), item.get("rel"), video.name) + if not any(key in select for key in keys if key): + continue + for sub in sidecar_subtitles(video): + target = sub.with_name(sub.name + suffix) + if target.exists(): + continue + if apply: + sub.rename(target) + changed.append((sub, target)) + return changed + + +def probe_duration(video: Path, timeout: float = 120.0) -> float | None: + """用 ffprobe 读取容器时长（秒）；失败返回 None，由调用方单独计数。""" + try: + proc = subprocess.run( + [ + "ffprobe", "-v", "error", + "-show_entries", "format=duration", + "-of", "default=nw=1:nk=1", str(video), + ], + capture_output=True, text=True, timeout=timeout, + ) + except (OSError, subprocess.TimeoutExpired): + return None + if proc.returncode != 0: + return None + try: + return float(proc.stdout.strip()) + except ValueError: + return None + + +def build_items(root: Path, workers: int, probe: bool = True) -> list[dict]: + """扫描全部视频，逐条产出路径、大小、时长与 CN 字幕生成时间。""" + videos = iter_videos(root) + durations: list[float | None] = [None] * len(videos) + if probe and videos: + with ThreadPoolExecutor(max_workers=workers) as pool: + durations = list(pool.map(probe_duration, videos)) + + items: list[dict] = [] + for video, duration in zip(videos, durations): + products = cn_products(video) + mtimes = [p.stat().st_mtime for p in products] + items.append({ + "video": str(video), + "rel": str(video.relative_to(root)), + "size": video.stat().st_size, + "duration": duration, + "generated_at": datetime.fromtimestamp(min(mtimes)).isoformat() if mtimes else None, + "cn_products": [ + {"path": str(p), "mtime": datetime.fromtimestamp(p.stat().st_mtime).isoformat()} + for p in products + ], + }) + return items + + +def classify(items: list[dict], before: datetime) -> dict[str, list[dict]]: + """按 CN 字幕生成时间把视频分为待重生成/已最新/无 CN 字幕三组。""" + groups: dict[str, list[dict]] = {PENDING: [], CURRENT: [], MISSING: []} + for item in items: + if item["generated_at"] is None: + groups[MISSING].append(item) + elif datetime.fromisoformat(item["generated_at"]) < before: + groups[PENDING].append(item) + else: + groups[CURRENT].append(item) + return groups + + +def _agg(items: list[dict]) -> dict: + """汇总一组的数量、总时长、总大小，时长缺失的视频单独计数。""" + return { + "count": len(items), + "seconds": sum(i["duration"] for i in items if i["duration"] is not None), + "bytes": sum(i["size"] for i in items), + "no_duration": sum(1 for i in items if i["duration"] is None), + } + + +def _fmt_hours(seconds: float) -> str: + return f"{seconds / 3600:.2f} 小时" + + +def _fmt_duration(probed: bool, seconds: float) -> str: + """未探测时长时（--backup-old 等只统计数量的场景）不显示 0 小时。""" + return _fmt_hours(seconds) if probed else "未探测时长" + + +def _fmt_size(num_bytes: int) -> str: + return f"{num_bytes / (1024 ** 3):.1f} GiB" + + +def format_summary(root: Path, items: list[dict], groups: dict[str, list[dict]], + before: datetime) -> str: + """生成人类可读的统计报告（数量 / 时长 / 体积 / 按月分布）。""" + probed = any(i["duration"] is not None for i in items) + lines = [ + f"媒体库: {root}", + f"视频总数: {len(items)} 个 / {_fmt_duration(probed, _agg(items)['seconds'])} / " + f"{_fmt_size(_agg(items)['bytes'])}", + "", + f"待重新生成（CN 字幕早于 {before:%Y-%m-%d}）: ", + ] + pending = _agg(groups[PENDING]) + duration_text = _fmt_duration(probed, pending["seconds"]) + lines.append(f" {pending['count']} 个 / {duration_text} / {_fmt_size(pending['bytes'])}") + + by_month: dict[str, dict] = {} + for item in groups[PENDING]: + month = item["generated_at"][:7] + bucket = by_month.setdefault(month, {"count": 0, "seconds": 0.0}) + bucket["count"] += 1 + bucket["seconds"] += item["duration"] or 0.0 + for month in sorted(by_month): + bucket = by_month[month] + lines.append(f" {month}: {bucket['count']} 个 / " + f"{_fmt_duration(probed, bucket['seconds'])}") + + current = _agg(groups[CURRENT]) + lines.append("") + lines.append(f"已是最新（生成时间 >= {before:%Y-%m-%d}）: {current['count']} 个 / " + f"{_fmt_duration(probed, current['seconds'])} / {_fmt_size(current['bytes'])}") + missing = _agg(groups[MISSING]) + lines.append(f"无 CN 字幕（首次生成）: {missing['count']} 个 / " + f"{_fmt_duration(probed, missing['seconds'])} / {_fmt_size(missing['bytes'])}") + + no_duration = sum(1 for i in items if i["duration"] is None) + if no_duration and probed: + lines.append(f"警告: {no_duration} 个视频未能读出时长，未计入时长合计") + return "\n".join(lines) + + +def main(argv: list[str] | None = None) -> int: + parser = argparse.ArgumentParser(description="统计需要重新生成字幕的视频数量与时长") + parser.add_argument("root", help="媒体库根目录") + parser.add_argument("--before", default="2026-09-01", + help="重生成分界线，早于该日期生成的 CN 字幕待重跑（默认 2026-09-01）") + parser.add_argument("--out", help="计划 JSON 输出路径（默认只打印统计）") + parser.add_argument("--workers", type=int, default=8, help="ffprobe 并发数（默认 8）") + parser.add_argument("--no-probe", action="store_true", help="跳过时长探测（只统计数量）") + parser.add_argument("--list-pending", action="store_true", help="额外打印待重生成的视频路径") + parser.add_argument("--backup-old", action="store_true", + help="把待重生成视频的旁挂字幕改名备份（默认预览，需 --apply 落盘）") + parser.add_argument("--apply", action="store_true", help="与 --backup-old 一起用时真正改名") + parser.add_argument("--select", help="只处理该文件列出的视频（每行一个路径或文件名）") + parser.add_argument("--suffix", help="备份后缀，默认 .old-<当天日期>") + args = parser.parse_args(argv) + + root = Path(args.root).expanduser().resolve() + if not root.is_dir(): + print(f"目录不存在: {root}", file=sys.stderr) + return 2 + before = datetime.fromisoformat(args.before) + + need_duration = args.out is not None or args.list_pending or not args.backup_old + items = build_items(root, max(1, args.workers), probe=need_duration and not args.no_probe) + groups = classify(items, before) + print(format_summary(root, items, groups, before)) + if args.list_pending: + print("\n待重新生成的视频:") + for item in groups[PENDING]: + print(f" {item['video']}") + + if args.backup_old: + suffix = args.suffix or f".old-{datetime.now():%Y%m%d}" + select = read_select_list(Path(args.select)) if args.select else None + changed = backup_old_subtitles(groups[PENDING], suffix, apply=args.apply, select=select) + verb = "已改名" if args.apply else "待改名（预览，未落盘）" + print(f"\n旧字幕备份（后缀 {suffix}）: {verb} {len(changed)} 个文件") + for source, target in changed: + print(f" {source} -> {target.name}") + + if args.out: + out = Path(args.out).expanduser() + out.parent.mkdir(parents=True, exist_ok=True) + status_of = {id(i): name for name, group in groups.items() for i in group} + payload = { + "root": str(root), + "before": before.isoformat(), + "scanned_at": datetime.now().isoformat(), + "totals": {name: _agg(group) for name, group in groups.items()}, + "items": [{**i, "status": status_of[id(i)]} for i in items], + } + out.write_text(json.dumps(payload, ensure_ascii=False, indent=1), encoding="utf-8") + print(f"\n计划 JSON 已写入: {out}") + return 0 + + +if __name__ == "__main__": + raise SystemExit(main()) diff --git a/tests/scripts/test_plan_regenerate_subtitles/__init__.py b/tests/scripts/test_plan_regenerate_subtitles/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/tests/scripts/test_plan_regenerate_subtitles/data/clip_10s.mp4 b/tests/scripts/test_plan_regenerate_subtitles/data/clip_10s.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ca8422769b0ec72df23746c5d2f7092fea3f1460 GIT binary patch literal 19770 zcmeHP2|QHa+rMK=Le?TnV++}4Y+0J3lD!or#4uxtVa$v*5+X&GQi-B$k(89u522J4 zAtfchqD3l8wrug9Ybg0Oliv6LzW?|0`MV!??z!ha=iKk}oO924zR$TA1VKngiXYL1 z>_LDa1_(ZaT^Z}`fF=-C(GUc&I+E~s2wEdYz+ovs<{S(2#Kf7GdL1S2pBvmbA>V|2 zF45KPtE{eyR6sg-knl*fx*A9tD1s~{(=B@X3aUt5i}m0d4(|XitoI=Lx#1ltNM#gC zML`**3`;vxC`2tKB_AIjMQ;}z-op*+uINE>QiAJMbfys8fQ$!`;^N^>)SOtB@BU0sN<1hoQBqOFIcBNB!nH*s(wU@0&V7k3JtR)b z-UUmBZ{kA2Pb%hvcX4v2*n?{xM7+DLlLrx8rDhUAQCGYls2iiKhMG#+5?tKDDU$4f zcgH(;Q820~7$yk|+mwVSJA>jR2ix!J!q-U-7zdIgl3))E3#$cAFv=>5D5NK>3jb{7o)BTGRPD>5u=K9A%a!{Jpwc$s0-@}Isn|9(0Vpb(rta|c=m~3NKoYj zP(V&hH+h|J*aS@>VNX~Hk&LCRE2Sy4;x$#sVGli_Rv@%eH__QJOV|0739HWpU2yPt zBB7fcuE#B}^m}+2bm75w20EOl3-2`*-bDb{r@6rE znHxN+^-?(J1TRH_EwAGw$HB^dsltc;FZXffI7*JM=$O@ zDV1zD{)8L-4&7wjplrQNGFEw_Ux*a*;z1yK7Ip7qpjgw+)!rii%jeSXS&Zo4x zlIl|PcdxoWG9g|6L3EI5B}S{VqSzCNUWVSvecnmEo~)mYPzwjdw=QXs%y@q@$#>1NpyZKG z4G&JmZ2iza!ZF>WAs3X7-l>0meRSgLs&m1^eA`ZINtirYY*qiRYplcGsV0qo*V27N zHFvpwu7d>>8Cx9*)w8ANGJGl*zTkQDSC`FKiiHuU+E{+DlZVJ73!PZLk8JI-k9dT| zwRHl{IdwD3EUa9)b|2dTWXE6Z+SfCV4m9JJR49l<=kVBN+_!$nZCCN^p8l;zq5Cy% zw>hu4`XumlSAy#ve;r((ZymH>?fq3N|K0^zJx)19Ol4+hdaI{a-LmHyDNX8v+$Cim zHRm4;wvU!HnD%9QC72H9@e1D+Vlxxtk$$s-HNG+&$570TSbD#1=uUs`;@T!JkzDJ> zjieI%i-Pb2o^G1V+7hbAwE?Te>SgCo5Q z^G>xpYqth4vaVhkY0=JfFG);gP13dM%A{1gr^Ccn-i)3NA{$~2&*{5w^S2xkuwaP7 z^$jf#D)^B8IgaJZ3K3y}zstj|HJ_ACgx4fQNb^*LzU6Q-DZLObZ|Sp8R*!k*HiI0@ zf#a12BfE%!JFu>TuQeGZuf2#S{x&uX&PmO9P1yyF>u1VzUQ&-Gv%Wn znDck3lrA%A$|^*%$h0~|R9PDjZ*CyC{XM|5rT)vJtMLYU^)?TcCa&4+^}3rab1h}) zjd>KGN@U@O_yWHp3M~N=SIpUL53DvgXYZ&rC?yiY&Wf^l4lCw{IcNXWdIxnUrK&|8)%O&Gyh{)&xTkYI3mIKQDa@str zqR!rq_2(~JZ0IhSe!j^wurlbu?W+5}y6UmZy9VnixUS?;0>e91>2G)N4=={?c2Gof zP1mw+pXgY8_?XEcQwzB&zRy{MW!U}|6SPdB>`b%&diLkT3HX-tFN>ZXja<$YF&JVn z{AFDFY^>?|tG9#GbA$EdpFA*RvVJ?VWplUD*Xu|n?{9BW>YH6($2aLOHc4VN7qG5~ zZWxzU{%|JGc<9lc*N7Uf>ZtC$%fE3|ji#pv-6)QWD8;q$YuvEoGY%|tZ+yNsN^#Mp zwgIvfZmaRb|8{wMl9zR9FE3y=ouC;n06R26L z-xt$gYFw1|(R;N)#gV$Z4uX;4QF3cs%2$$e&!({z)@HY@$9?fdKZ`0`BdfFIR^Bb! zPnoyYPB8nMy)v*EE54Q<7ebLsqH19GItxDg^PE~AJ*>TL4v{iSYo zKHdLIXq(}+(b(Qdcg^jGTsN$Zt&pv^kzEvJd@iXw46qD=dnv)h02UXgb2&UlP z8oJ4%bd06e=hw)UB=c$)i*?-TktT)C^a|`rjO!4yBq)nUBx7jWC~!id@TdrR9NKW{ z&fgU>-wNdSFBqD%P4e2`*d|9>#Ne*)tsE>62d=KqEEH%EDd01eGc9*>@Wch z!v9+u(DdDBX)vWQO)q|y26g}wXoElS=Ya-v{CR|0AFVc^>E6%MU_XE)N5|3swFZCS z@+<4obNOj&K$`)~(tz3qw7I}9HTV-&05qV(3g~D+lO)X2fZ7JM>B6ry_yghqG@wHq zex<<_B$_;8mIhO8K$B6-(f|uO-O9Oe3z*(djYV{)A)3ztoq6Y1W6^JCnxDs_xy&@M z22*1Z{kh>EPcpR)=*X{ z+%PXSOOKE{a%%0HI>v1bham$!Jh3JA!k1(&t}kF@)1}WJVDjq_n-aL4;Me1IG9q=U zz01J%&i2I8E2-mg`)Z3Lc&>m-G!e

BJQIZIhD4>of=$3Kv`$^lHkMTG4K!ifjdi zfouLJ`xAa4OP^mvJD4=bI9)Nh zyfO*hN83YzXCJMuNY!F1Up(fyFRC?7Cw_pR>Nd2aSb$A@2R~(bdQq!?fS*ImYMM!)e-~w%;7V75uh>7|?{#ZZ2`PPa5qw%Y@pL{ZND{SlF>(wf0sr%u41RDfB z*pFBSG5ifJsDlKNkSBx~gBHd@>va%=5c?L$Yf^5S7W`D#|1?vsa)LQ$%nB-()@*Dg zb9NqRPQnnYD^Nyy-;EWi+j7(6~)um+McJ`h0$9z_Hn+r z*`PXdM7Bp{2c^GmME9(^{N?4nZP{U+OxJMdp1o<`E$=hpEKtnc%iEW-j`M5m@;&Xg z4_>x(C)Ac$eAvgZ53kn4>+|umTEWtVt?DNau%$MCgnWi?RW_MjdSF-N`|X*J-8*uO zc>JxWt@WNAwsnN-VGCgsWU1f5hIDGLC;L zuQG^*dK-#%^{6-HzF4=*gzOldG|ZL#zWg|Tb<<~qJsBgce!RERV|wuWULGjo<`dYZ zMDbFOd2AgbI2d%o&~bASwxaWTL7@4fhrQqKf9kcq92r`C@T=GR&6R?}55yCLb_KlQ z%)G{*p%;Ym=@yoFxqA1$(+P6QLeCC22?P__&uq|osjri0+|GHI{87ZzdLwdYQL%e= zMqG#6{Y;Lt>K9Hw?-xamKNdFIC@8w4^YtZjj;#*e$E$Q%dqEG|mw{5f*R)bzZsE~v z8NJ+tx4KU;i!YUpwmvbcc~3lSliZmPW`+!|hI<80H6FKP->Aj!#o;O)rQLZDmUWx~)PoL*v$toctIa^K3)= z19P!fai+2?%`e?{O0_Rk9r-^9$QY7$f9w=U7;fp+bx+u2G?sekRO$GM;N*b;DTPn@ ztJc{iM2lav%u3B^mxqFiSW8Yl7{Lh!B z@kzvdIq#Dj{LQvz&+?BKzQP39`myY|MsL9YYKycLIHL=@N?0Q!A+&#e69xkP5B<ODgwZ^$Q zDpT}Ov6_x^{4s96M}_8!ge!aRFe7X9wjJxJmNl<~7G|8Z_B<+m3k!fT^NVq!T;3^At z#Xk4wuZyhBJ5PVK6l&*XdHC&(BJXRJ%ddKNRt1N=66#t~Gf`rG?2OfoFC~%%!7cX> z^;}mt6SvD;PiE&D)y&ssrLDMuZ`_WEM=Q#k?mV)%nVlfzI$T;XG8&S;YIi?A()lmP zje60M;;HxQ_kCSe5cSvS{$$EvJH?nSLhEtq#m4a)7w&%1fFNt>zZ7#;IccJJj&U$>bbdE81CWlu+l?aN=s&}57E$#=>L?_U?jAtv?K zR%Xbt_}w}K_ukE^_be9KIogco=k1kgj{Vm6Fx0vI2J3?H6*@Q8GVnJ`JMRw7JfXPv zW;;)2RdP&K{mz<4PtUr){FqEmU@Dh8eCttOwV#nzdBNT_W&_qWPB!>v71}_sDmEt<-!E5hUF1t|G$AQ-<{<|`LcWvUztqnbwDz z7^4HMkczE>w!UhYn9L?vcE$PC^$1;36+O*BT5REf3X)QIYado$`SiB`>JNn0Y_pRh zIy)KHM5vL&6s#IB*Z&sT=q|~+S?TlXua>wFPR>!p<;t-j-z69VQ+^HZijvSdW=Je= z*x~V>J3NBga+>0$O${D<7%K=T{2Ue5`EF{+Y2&zQ+`XkOanTKiav!Fl+JO}me7Ey}+c zR;P2lg4OyA>r+(MK-lTj?MybuyamM7&UdoqKRv117SR65tE61@QysbK@y<2rmZgt{ zLgOOdn#vqW4h%cSl~o;Pw|JG$p0y`*cHXF!Gw73gM|@bZF(c(3-mc}K+eNOIBjVMI z-<0|06kI3wmYsA)uDoYD&Og#+a#CIWi|}cQtP&M zfQQ2Ua9fpi;tA?nU06`RbsayF8>^MhqLA4{j zCF-9s(vBR>v?J}1(M*hUjTOPfa0T61(KJTlq=je`hnaSy9U1xw;~YamQ+A{i5}JjP zW*q1zJJJjQ{e%&#z*?${mHhTvLl^v%`A-b=xp7l&z>>Ji5Z9m*m9*UsW?%BKfwvpa`lZ^H~>?hBezJ`}w#q<-?3=Y7#%#)v0h z7zBRazt55Q;HOz*CRmgh=o$ZZU({)0Jei9o#-ja`80o#zKJ7yhfh1tKG+$u< zQ(sh8H&J40iDJjZxP}fbj10|Gh`Qh{Z#f#DWGXc-9U%wEwNfG4(|TS0yCclmPVn&X z2GVW>Z)Y4h&e#|~K#(*Sgn;0`AKOnSAbZxi&JW37r5GTHlLvfi>~p9;caG}lNrpg+6EvA z@9>7;Hv#hM%8F>TA{u-$@8)6;f1XdhIQc6u0lE;h3P`O-;GpFbt=>{sfjt21tHBQbdCcTFd_VQ6G<^L( z{d^O!!AyI>4(POf6sGJ0+YV0uKRstX2C(g(!V34V6;tVzQ|bA02r>n>(3!Fa{A|Ge z{$FVyxNl6?$490(!2cl$-rz9-1$L|#j)Db8O9FoK2$GQ4Ox6XM8VO4z!o=wNChtO} ec9Pi?54b{M@K4X+O5jQ%Kz|$o{ZWD0&wl||Q+^Nt literal 0 HcmV?d00001 diff --git a/tests/scripts/test_plan_regenerate_subtitles/test_plan_regenerate_subtitles.py b/tests/scripts/test_plan_regenerate_subtitles/test_plan_regenerate_subtitles.py new file mode 100644 index 0000000..56af0c0 --- /dev/null +++ b/tests/scripts/test_plan_regenerate_subtitles/test_plan_regenerate_subtitles.py @@ -0,0 +1,317 @@ +"""plan_regenerate_subtitles.py 的模块级测试（数据 → 测试过程 → 验证结果）。 + +被测模块：字幕重生成计划统计脚本。用例在临时目录里放**真实视频文件**与 +真实字幕文件，调用脚本的真实函数；只有 ffprobe 子进程这一 I/O 边界在需要 +确定性时长时注入固定值，其余用例跑真实 ffprobe（缺可执行文件时跳过）。 +""" + +from __future__ import annotations + +import json +import os +import shutil +from datetime import datetime +from pathlib import Path + +import pytest + +from scripts.plan_regenerate_subtitles import ( + CURRENT, + MISSING, + PENDING, + _agg, + backup_old_subtitles, + build_items, + classify, + cn_products, + format_summary, + main, + probe_duration, + read_select_list, + sidecar_subtitles, +) + +DATA = Path(__file__).parent / "data" +CLIP = DATA / "clip_10s.mp4" # 真实 10 秒 mp4，供扫描与时长探测使用 +BEFORE = datetime(2026, 9, 1) + + +def _set_mtime(path: Path, when: str) -> None: + """把文件 mtime 设为指定日期（本地时区），模拟不同时期生成的字幕。""" + ts = datetime.fromisoformat(when).timestamp() + os.utime(path, (ts, ts)) + + +def _make_video(tmp_path: Path, name: str) -> Path: + """在临时目录放一份真实视频文件，返回其路径。""" + video = tmp_path / f"{name}.mp4" + shutil.copyfile(CLIP, video) + return video + + +def _make_subtitle(video: Path, suffix: str, when: str) -> Path: + """在视频旁写一个真实字幕文件（内容为合法 SRT/ASS 片段）并设置 mtime。""" + sub = video.with_name(video.name[: -len(video.suffix)] + suffix) + if suffix.endswith(".srt"): + sub.write_text("1\n00:00:01,000 --> 00:00:02,000\n你好\n", encoding="utf-8") + else: + sub.write_text("[Script Info]\nTitle: t\n", encoding="utf-8") + _set_mtime(sub, when) + return sub + + +def test_products_pick_earliest_mtime_so_style_rewrite_stays_old(tmp_path: Path) -> None: + """数据：中文字幕生成于 2025-12，双目 .ass 被样式脚本在 2026-09 原地改写。 + + 过程：扫描该视频并读取 CN 产物生成时间。 + + 验证：只认本流水线产物，生成时间取最早值（2025-12），视频判为待重生成。 + """ + video = _make_video(tmp_path, "movie") + _make_subtitle(video, ".srt", "2025-11-01") # 片源自带字幕，不参与判定 + _make_subtitle(video, ".CN.srt", "2025-12-01") + _make_subtitle(video, ".CN_dual_eye.ass", "2026-09-06") + + items = build_items(tmp_path, workers=2, probe=False) + + assert [p.name for p in cn_products(video)] == ["movie.CN.srt", "movie.CN_dual_eye.ass"] + assert items[0]["generated_at"].startswith("2025-12-01") + assert [i["video"] for i in classify(items, BEFORE)[PENDING]] == [str(video)] + + +def test_classify_groups_by_generation_time(tmp_path: Path) -> None: + """数据：三个视频——旧字幕、新字幕、完全没有 CN 字幕。 + + 过程：扫描后按 2026-09-01 分界线分类。 + + 验证：分别落入待重生成 / 已最新 / 无 CN 字幕三组，边界时刻本身算已最新。 + """ + old = _make_video(tmp_path, "old") + _make_subtitle(old, ".CN.srt", "2026-04-05") + fresh = _make_video(tmp_path, "fresh") + _make_subtitle(fresh, ".CN.srt", "2026-09-01") + _make_subtitle(fresh, ".CN_dual_eye.ass", "2026-09-06") + never = _make_video(tmp_path, "never") + + groups = classify(build_items(tmp_path, workers=2, probe=False), BEFORE) + + assert [i["video"] for i in groups[PENDING]] == [str(old)] + assert [i["video"] for i in groups[CURRENT]] == [str(fresh)] + assert [i["video"] for i in groups[MISSING]] == [str(never)] + + +def test_name_with_extra_suffix_still_matches_product(tmp_path: Path) -> None: + """数据：手工改过名的产物 `<视频名>666.CN.srt`（媒体库里真实存在这种命名）。 + + 过程：扫描该视频的 CN 产物。 + + 验证：按「文件名含视频主名 + CN 产物后缀」命中，与批量引擎的旁挂判定一致。 + """ + video = _make_video(tmp_path, "clip") + _make_subtitle(video, "666.CN.srt", "2025-12-14") + + items = build_items(tmp_path, workers=2, probe=False) + + assert items[0]["generated_at"].startswith("2025-12-14") + assert classify(items, BEFORE)[PENDING] + + +def test_aggregate_sums_duration_and_size(tmp_path: Path) -> None: + """数据：两个待重生成视频，时长各有值、其中一个探测失败。 + + 过程：汇总该组的数量、时长、体积。 + + 验证：时长合计跳过探测失败项并单独计数，体积按全部文件累计。 + """ + video = _make_video(tmp_path, "a") + _make_subtitle(video, ".CN.srt", "2025-12-01") + items = [ + {"size": 100, "duration": 12.5}, + {"size": 50, "duration": None}, + ] + + agg = _agg(items) + + assert agg == {"count": 2, "seconds": 12.5, "bytes": 150, "no_duration": 1} + + +def test_main_writes_plan_json(tmp_path: Path) -> None: + """数据：真实 10 秒视频 + 旧 CN 字幕 + 新 CN 字幕各一个。 + + 过程：调用 main() 全流程并写出计划 JSON。 + + 验证：统计报告含待重生成/已最新行数，JSON 里两条明细状态与时长正确。 + """ + if shutil.which("ffprobe") is None: + pytest.skip("环境缺少 ffprobe，无法探测真实视频时长") + old = _make_video(tmp_path, "old") + _make_subtitle(old, ".CN.srt", "2025-12-01") + fresh = _make_video(tmp_path, "fresh") + _make_subtitle(fresh, ".CN.srt", "2026-09-10") + out = tmp_path / "plan.json" + + code = main([str(tmp_path), "--before", "2026-09-01", "--out", str(out), "--workers", "2"]) + + assert code == 0 + payload = json.loads(out.read_text(encoding="utf-8")) + by_name = {Path(i["video"]).name: i for i in payload["items"]} + assert by_name["old.mp4"]["status"] == PENDING + assert by_name["old.mp4"]["duration"] == pytest.approx(10.0, abs=0.5) + assert by_name["fresh.mp4"]["status"] == CURRENT + assert payload["totals"][PENDING]["count"] == 1 + assert payload["totals"][PENDING]["seconds"] == pytest.approx(10.0, abs=0.5) + + +def test_probe_duration_reads_real_video() -> None: + """数据：真实 10 秒 mp4（模块目录内素材）。 + + 过程：调用真实 ffprobe 读取时长。 + + 验证：返回约 10 秒，说明统计脚本的时长口径来自容器真实时长。 + """ + if shutil.which("ffprobe") is None: + pytest.skip("环境缺少 ffprobe，无法探测真实视频时长") + + assert probe_duration(CLIP) == pytest.approx(10.0, abs=0.1) + + +def test_format_summary_reports_all_groups() -> None: + """数据：三组各一条明细（旧/新/无字幕），时长与体积已知。 + + 过程：格式化统计报告。 + + 验证：报告包含总量、待重生成、已最新、无 CN 字幕四段关键信息。 + """ + root = Path("/media") + items = [ + {"duration": 3600.0, "size": 0, "generated_at": "2025-12-01T00:00:00"}, + {"duration": 1800.0, "size": 0, "generated_at": "2026-09-10T00:00:00"}, + {"duration": None, "size": 0, "generated_at": None}, + ] + + text = format_summary(root, items, classify(items, BEFORE), BEFORE) + + assert "视频总数: 3 个" in text + assert "待重新生成（CN 字幕早于 2026-09-01）" in text + assert "已是最新" in text + assert "无 CN 字幕（首次生成）" in text + assert "警告: 1 个视频未能读出时长" in text + + +def test_sidecar_subtitles_matches_batch_engine_rule(tmp_path: Path) -> None: + """数据：视频旁有片源 .srt、CN 产物与无关文件各一份。 + + 过程：列出批量引擎会认定为"已有字幕"的旁挂文件。 + + 验证：只收文件名含视频主名的字幕，不含无关图片与别人的字幕。 + """ + video = _make_video(tmp_path, "movie") + source = _make_subtitle(video, ".srt", "2025-11-01") + cn_srt = _make_subtitle(video, ".CN.srt", "2025-12-01") + cn_ass = _make_subtitle(video, ".CN_dual_eye.ass", "2026-09-06") + (tmp_path / "movie-poster.jpg").write_bytes(b"poster") + (tmp_path / "other.srt").write_text("1\n", encoding="utf-8") + + found = sidecar_subtitles(video) + + assert found == [cn_srt, cn_ass, source] + + +def test_backup_renames_every_sidecar_and_unsets_skip(tmp_path: Path) -> None: + """数据：待重生成视频带片源 .srt + CN 产物 + 既有备份目标冲突。 + + 过程：执行改名备份。 + + 验证：全部旁挂字幕改名成 .old 后缀、原文件消失；改名后批量引擎再也 + 不会把该视频判为"已有字幕"。 + """ + video = _make_video(tmp_path, "movie") + source = _make_subtitle(video, ".srt", "2025-11-01") + cn_srt = _make_subtitle(video, ".CN.srt", "2025-12-01") + cn_ass = _make_subtitle(video, ".CN_dual_eye.ass", "2026-09-06") + + changed = backup_old_subtitles([{"video": str(video)}], suffix=".old", apply=True) + + assert len(changed) == 3 + assert sidecar_subtitles(video) == [] + for path in (source, cn_srt, cn_ass): + assert not path.exists() + assert (path.parent / (path.name + ".old")).read_text(encoding="utf-8") + + +def test_backup_dry_run_only_reports(tmp_path: Path) -> None: + """数据：一个带旧字幕的视频。 + + 过程：不传 apply 走预览。 + + 验证：返回改名计划，磁盘文件保持不变。 + """ + video = _make_video(tmp_path, "movie") + sub = _make_subtitle(video, ".CN.srt", "2025-12-01") + + changed = backup_old_subtitles([{"video": str(video)}], suffix=".old", apply=False) + + assert changed == [(sub, sub.with_name(sub.name + ".old"))] + assert sub.exists() + + +def test_backup_does_not_overwrite_existing_backup(tmp_path: Path) -> None: + """数据：视频旁已有同名备份文件（同一批重复执行）。 + + 过程：再次执行改名备份。 + + 验证：已存在的备份不被覆盖，原文件也不被删除，返回空变更。 + """ + video = _make_video(tmp_path, "movie") + sub = _make_subtitle(video, ".CN.srt", "2025-12-01") + backup = sub.with_name(sub.name + ".old") + backup.write_text("first\n", encoding="utf-8") + + changed = backup_old_subtitles([{"video": str(video)}], suffix=".old", apply=True) + + assert changed == [] + assert backup.read_text(encoding="utf-8") == "first\n" + assert sub.exists() + + +def test_backup_respects_select_list(tmp_path: Path) -> None: + """数据：两个待重生成视频，只选中其中一个（选择文件带行尾注释）。 + + 过程：执行改名备份。 + + 验证：只改选中视频的旁挂字幕，另一个保持原样。 + """ + chosen = _make_video(tmp_path, "chosen") + chosen_sub = _make_subtitle(chosen, ".CN.srt", "2025-12-01") + kept = _make_video(tmp_path, "kept") + kept_sub = _make_subtitle(kept, ".CN.srt", "2025-12-02") + select = tmp_path / "select.txt" + select.write_text(f"# 只处理这一个\n{chosen} # 40.3min\n\n", encoding="utf-8") + + changed = backup_old_subtitles( + [{"video": str(chosen)}, {"video": str(kept)}], + suffix=".old", apply=True, select=read_select_list(select), + ) + + assert changed == [(chosen_sub, chosen_sub.with_name(chosen_sub.name + ".old"))] + assert kept_sub.exists() + + +def test_format_summary_marks_missing_durations(tmp_path: Path) -> None: + """数据：只做分类统计、未探测时长的明细（--backup-old 场景）。 + + 过程：格式化统计报告。 + + 验证：报告不显示 0 小时，而是标注未探测时长，也不出现时长缺失警告。 + """ + root = Path("/media") + items = [ + {"duration": None, "size": 10, "generated_at": "2025-12-01T00:00:00"}, + {"duration": None, "size": 20, "generated_at": "2026-09-10T00:00:00"}, + ] + + text = format_summary(root, items, classify(items, BEFORE), BEFORE) + + assert "未探测时长" in text + assert "0.00 小时" not in text + assert "警告" not in text