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/lint_sources.py

@@ -2,7 +2,7 @@
 """lint_sources.py — 校验 sources/ 资源清单合规。
 
 检查项：
-- 每个 source 必填字段、id kebab-case 唯一、license/type/status 枚举合法
+- 每个 source 必填字段、id kebab-case 唯一、license/type/status/subjects 枚举合法
 - status=fetched 的 item 必须有 oss_key + 64位 sha256
 - license=unknown 且 fetched_at 距今 > 30 天 → warning
 
@@ -11,9 +11,12 @@
 import sys, os, glob, re, datetime, hashlib
 
 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"}
+LICENSES = {"official-free","mit","cc-by","cc-by-sa","cc-nc-education","restricted","internal-only","llm-generated","unknown"}
 TYPES = {"dataset","website","book","internal","tool"}
 STATUSES = {"planned","fetching","fetched","failed","archived"}
+SUBJECTS = {"chinese","math","english","science","morality","physics","chemistry",
+            "biology","history","geography","it","ket","pet","fce","amc8","cspj"}
+STAGES = {"primary","junior"}
 ID_RE = re.compile(r"^[a-z0-9][a-z0-9-]*$")
 SHA_RE = re.compile(r"^[a-f0-9]{64}$")
 
@@ -42,6 +45,13 @@ def main():
             if s.get("type") not in TYPES: err(f"{sid}: type 非法 {s.get('type')}"); errors += 1
             if s.get("license") not in LICENSES: err(f"{sid}: license 非法 {s.get('license')}"); errors += 1
             if s.get("status") not in STATUSES: err(f"{sid}: status 非法 {s.get('status')}"); errors += 1
+            subs = s.get("subjects")
+            if not subs: err(f"{sid}: 缺必填 subjects（覆盖学科，见 LICENSES.md 同级约定）"); errors += 1
+            else:
+                for x in subs:
+                    if x not in SUBJECTS: err(f"{sid}: subjects 含非法值 {x}"); errors += 1
+            for x in (s.get("stages") or []):
+                if x not in STAGES: err(f"{sid}: stages 含非法值 {x}"); errors += 1
             if s.get("license") == "unknown" and s.get("fetched_at"):
                 try:
                     d = datetime.date.fromisoformat(s["fetched_at"])