init: edu-content 内容库骨架（L1-L4 四层数据模型 + B类迁移 + lint/CI 工具）

tools/lint_structured.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+"""lint_structured.py — 校验 structured/ 血缘与 license。
+
+检查项：
+- 每条 JSONL 记录必须有合法 schema（qb-1.1 或 vocab-1.1）
+- 记录的 source.source_id 必须存在于 sources/
+- license 必须是 LICENSES.md 枚举值
+- 孤儿数据（引用不存在的 source）即 error
+
+退出码非 0 表示有 error。
+"""
+import sys, os, glob, json
+
+REPO = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+LICENSES = {"official-free","cc-by","cc-by-sa","cc-nc-education","restricted","internal-only","llm-generated","unknown"}
+
+def load_source_ids():
+    import yaml
+    ids = set()
+    for path in glob.glob(os.path.join(REPO, "sources", "**", "*.yaml"), recursive=True):
+        try: doc = yaml.safe_load(open(path, encoding="utf-8"))
+        except Exception: continue
+        for s in (doc or {}).get("sources", []) or []:
+            if s.get("id"): ids.add(s["id"])
+    return ids
+
+def err(msg): print("ERROR: " + msg); return 1
+
+def main():
+    source_ids = load_source_ids()
+    errors, n = 0, 0
+    for path in sorted(glob.glob(os.path.join(REPO, "structured", "**", "*.jsonl"), recursive=True)):
+        for i, line in enumerate(open(path, encoding="utf-8"), 1):
+            line = line.strip()
+            if not line: continue
+            try: r = json.loads(line)
+            except Exception as e: err(f"{path}:{i}: JSON 解析失败 {e}"); errors += 1; continue
+            n += 1
+            sid = (r.get("source") or {}).get("source_id")
+            if not sid: err(f"{path}:{i}: 缺 source.source_id"); errors += 1; continue
+            if sid not in source_ids: err(f"{path}:{i}: source_id '{sid}' 不在 sources/（孤儿数据）"); errors += 1
+            lic = r.get("license")
+            if lic and lic not in LICENSES: err(f"{path}:{i}: license 非法 '{lic}'"); errors += 1
+    print(f"\n校验完成：{n} 条结构化记录 | {errors} error")
+    sys.exit(1 if errors else 0)
+
+if __name__ == "__main__":
+    main()