feat: 补 MIT 许可、自动抓取工具与学科覆盖元数据

登记 chinese-poetry / ck12 / phet，并让 source schema、lint 与 INDEX 能按学科和抓取进度消费。

Co-authored-by: Cursor <cursoragent@cursor.com>

tools/oss_sync.py

@@ -16,6 +16,9 @@
 """
 import os, sys, glob, json, hashlib, datetime, argparse, yaml
 
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+from yaml_patch import patch_item_fields, patch_source_fields
+
 REPO = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 SHA_RE = __import__("re").compile(r"^[a-f0-9]{64}$")
 
@@ -87,19 +90,16 @@ def main():
     for path, sid, iid, local, oss_key, sha, size in pending:
         b.put_object_from_file(oss_key, local)
         print(f"  uploaded {oss_key}")
-        # 回填
-        doc = yaml.safe_load(open(path, encoding="utf-8"))
-        for s in doc["sources"]:
-            if s.get("id") == sid:
-                for it in s.get("items", []):
-                    if it.get("id") == iid:
-                        it["oss_key"] = oss_key
-                        it["sha256"] = sha
-                        it["size"] = size
-                        it["fetch_date"] = today
-                        it["status"] = "fetched"
-        yaml.safe_dump(doc, open(path, "w", encoding="utf-8"), allow_unicode=True, sort_keys=False)
-    print("已回填 sha256/size 到 sources YAML。请 git commit。")
+        # 回填（行级替换，保留 YAML 注释；勿用 safe_dump 整file重写）
+        patch_item_fields(path, sid, iid, {
+            "oss_key": oss_key,
+            "sha256": sha,
+            "size": size,
+            "fetch_date": today,
+            "status": "fetched",
+        })
+        patch_source_fields(path, sid, {"status": "fetched", "fetched_at": today})
+    print("已回填 oss_key/sha256/size 到 sources YAML（注释保留）。请 git commit。")
 
 if __name__ == "__main__":
     main()