manifest.json里extract audio, transcribe audio 共用一条记录

synthmind/extract_audio.py

@@ -56,13 +56,32 @@ def log(msg: str, level: str = "INFO"):
     print(f"[{ts}] {prefix} {msg}", flush=True)
 
 
-# ─── Manifest 操作 ─────────────────────────────────────────────────────────────
+# ─── Manifest 操作 (v2 schema) ────────────────────────────────────────────────
+#
+# v2 schema：每个条目形如
+# {
+#   "extraction": { "extracted": bool, "audio_path": str, "split_segments": [],
+#                   "error": str|None, "updated_at": str },
+#   "transcriptions": {
+#     "<model>[:<suffix>]": { "transcribed": bool, "txt_path": str, ... }
+#   }
+# }
+# transcribe_audio.py 会把转录结果并入同一条视频记录的 transcriptions 里。
+# ─────────────────────────────────────────────────────────────────────────────
+
+MANIFEST_VERSION = 2
+
 
 def load_manifest(manifest_path: Path) -> dict:
-    if manifest_path.exists():
-        with open(manifest_path, encoding="utf-8") as f:
-            return json.load(f)
-    return {"version": 1, "files": {}}
+    if not manifest_path.exists():
+        return {"version": MANIFEST_VERSION, "files": {}}
+    with open(manifest_path, encoding="utf-8") as f:
+        data = json.load(f)
+    # 旧版 manifest (v1) 直接废弃，从头开始（用户已明确接受）
+    if data.get("version", 1) < MANIFEST_VERSION:
+        log("检测到旧版 manifest.json (v1)，将以 v2 schema 重新初始化 - 旧记录将被覆盖", "WARN")
+        return {"version": MANIFEST_VERSION, "files": {}}
+    return data
 
 
 def save_manifest(manifest_path: Path, manifest: dict):
@@ -72,34 +91,41 @@ def save_manifest(manifest_path: Path, manifest: dict):
 
 
 def get_file_entry(manifest: dict, video_path: str) -> dict:
-    """获取或初始化某个视频文件的 manifest 条目"""
+    """获取或初始化某个视频文件的 manifest 条目 (v2 schema)"""
     if video_path not in manifest["files"]:
         manifest["files"][video_path] = {
-            "audio_extracted": False,
-            "audio_path": None,
-            "split_segments": [],       # 切分后的片段列表（若有）
-            "error": None,
-            "updated_at": None,
+            "extraction": None,
+            "transcriptions": {},
         }
-    return manifest["files"][video_path]
+    entry = manifest["files"][video_path]
+    if "transcriptions" not in entry:
+        entry["transcriptions"] = {}
+    return entry
 
 
 def mark_done(manifest: dict, manifest_path: Path, video_path: str,
               audio_path: str, segments: list = None):
     entry = get_file_entry(manifest, video_path)
-    entry["audio_extracted"] = True
-    entry["audio_path"] = audio_path
-    entry["split_segments"] = segments or []
-    entry["error"] = None
-    entry["updated_at"] = time.strftime("%Y-%m-%dT%H:%M:%S")
+    entry["extraction"] = {
+        "extracted": True,
+        "audio_path": audio_path,
+        "split_segments": segments or [],
+        "error": None,
+        "updated_at": time.strftime("%Y-%m-%dT%H:%M:%S"),
+    }
     save_manifest(manifest_path, manifest)
 
 
 def mark_failed(manifest: dict, manifest_path: Path, video_path: str, error: str):
     entry = get_file_entry(manifest, video_path)
-    entry["audio_extracted"] = False
-    entry["error"] = error
-    entry["updated_at"] = time.strftime("%Y-%m-%dT%H:%M:%S")
+    prev = entry.get("extraction") or {}
+    entry["extraction"] = {
+        "extracted": False,
+        "audio_path": prev.get("audio_path"),
+        "split_segments": prev.get("split_segments") or [],
+        "error": error,
+        "updated_at": time.strftime("%Y-%m-%dT%H:%M:%S"),
+    }
     save_manifest(manifest_path, manifest)
 
 
@@ -220,22 +246,25 @@ def show_status(manifest: dict, all_videos: list):
     print("\n" + "=" * 60)
     print("📊 提取音频进度状态")
     print("=" * 60)
-    done = sum(1 for v in all_videos
-               if manifest["files"].get(v, {}).get("audio_extracted"))
-    failed = sum(1 for v in all_videos
-                 if manifest["files"].get(v, {}).get("error"))
-    pending = len(all_videos) - done
+    done, failed = 0, 0
+    for v in all_videos:
+        ext = ((manifest["files"].get(v) or {}).get("extraction")) or {}
+        if ext.get("extracted"):
+            done += 1
+        elif ext.get("error"):
+            failed += 1
+    pending = len(all_videos) - done - failed
     print(f"  总文件数  : {len(all_videos)}")
     print(f"  已完成    : {done}")
     print(f"  失败      : {failed}")
     print(f"  待处理    : {pending}")
     print("=" * 60)
     for v in all_videos:
-        entry = manifest["files"].get(v, {})
-        if entry.get("audio_extracted"):
+        ext = ((manifest["files"].get(v) or {}).get("extraction")) or {}
+        if ext.get("extracted"):
             status = "✅ 完成"
-        elif entry.get("error"):
-            status = f"❌ 失败: {entry['error']}"
+        elif ext.get("error"):
+            status = f"❌ 失败: {ext['error']}"
         else:
             status = "⏳ 待处理"
         print(f"  {status}  {Path(v).name}")
@@ -292,9 +321,10 @@ def main():
     pending = []
     for v in all_videos:
         entry = get_file_entry(manifest, v)
-        already_done = entry.get("audio_extracted") and entry.get("audio_path") and \
-                       mp3_exists(entry["audio_path"])
-        is_failed = bool(entry.get("error"))
+        ext = entry.get("extraction") or {}
+        already_done = ext.get("extracted") and ext.get("audio_path") and \
+                       mp3_exists(ext["audio_path"])
+        is_failed = bool(ext.get("error"))
 
         if already_done:
             continue