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>

sources/source.schema.json

@@ -3,47 +3,230 @@
   "title": "edu-content source registry",
   "description": "机器可读的 L1 资源清单。一个 YAML 文件 = 一个域，内含多条 source。source 是四层血缘链的根 id。",
   "type": "object",
-  "required": ["sources"],
+  "required": [
+    "sources"
+  ],
   "additionalProperties": false,
   "properties": {
     "sources": {
       "type": "array",
-      "items": { "$ref": "#/definitions/source" }
+      "items": {
+        "$ref": "#/definitions/source"
+      }
     }
   },
   "definitions": {
     "source": {
       "type": "object",
-      "required": ["id", "title", "publisher", "type", "license", "status"],
+      "required": [
+        "id",
+        "title",
+        "publisher",
+        "type",
+        "license",
+        "status",
+        "subjects"
+      ],
       "additionalProperties": false,
       "properties": {
-        "id": { "type": "string", "pattern": "^[a-z0-9][a-z0-9-]*$", "description": "全局唯一 kebab-case，血缘链根 id" },
-        "title": { "type": "string" },
-        "publisher": { "type": "string" },
-        "type": { "type": "string", "enum": ["dataset", "website", "book", "internal", "tool"] },
-        "url": { "type": ["string", "null"], "description": "internal 可为 null" },
-        "license": { "type": "string", "enum": ["official-free", "cc-by", "cc-by-sa", "cc-nc-education", "restricted", "internal-only", "llm-generated", "unknown"] },
-        "license_note": { "type": "string" },
-        "fetch_method": { "type": "string", "enum": ["curl", "git-clone", "manual-download", "manual-export", "generated"], "description": "unknown 允许暂存" },
-        "status": { "type": "string", "enum": ["planned", "fetching", "fetched", "failed", "archived"] },
-        "fetched_at": { "type": ["string", "null"], "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$" },
-        "items": { "type": "array", "items": { "$ref": "#/definitions/item" } }
+        "id": {
+          "type": "string",
+          "pattern": "^[a-z0-9][a-z0-9-]*$",
+          "description": "全局唯一 kebab-case，血缘链根 id"
+        },
+        "title": {
+          "type": "string"
+        },
+        "publisher": {
+          "type": "string"
+        },
+        "type": {
+          "type": "string",
+          "enum": [
+            "dataset",
+            "website",
+            "book",
+            "internal",
+            "tool"
+          ]
+        },
+        "url": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "internal 可为 null"
+        },
+        "license": {
+          "type": "string",
+          "enum": [
+            "official-free",
+            "mit",
+            "cc-by",
+            "cc-by-sa",
+            "cc-nc-education",
+            "restricted",
+            "internal-only",
+            "llm-generated",
+            "unknown"
+          ]
+        },
+        "license_note": {
+          "type": "string"
+        },
+        "fetch_method": {
+          "type": "string",
+          "enum": [
+            "curl",
+            "git-clone",
+            "manual-download",
+            "manual-export",
+            "generated"
+          ],
+          "description": "unknown 允许暂存"
+        },
+        "status": {
+          "type": "string",
+          "enum": [
+            "planned",
+            "fetching",
+            "fetched",
+            "failed",
+            "archived"
+          ]
+        },
+        "fetched_at": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$"
+        },
+        "items": {
+          "type": "array",
+          "items": {
+            "$ref": "#/definitions/item"
+          }
+        },
+        "subjects": {
+          "type": "array",
+          "items": {
+            "type": "string",
+            "enum": [
+              "chinese",
+              "math",
+              "english",
+              "science",
+              "morality",
+              "physics",
+              "chemistry",
+              "biology",
+              "history",
+              "geography",
+              "it",
+              "ket",
+              "pet",
+              "fce",
+              "amc8",
+              "cspj"
+            ]
+          },
+          "description": "该来源覆盖的学科/考试域，取值与 structured/ 目录名一致；用于回答『某学科有哪些来源』"
+        },
+        "stages": {
+          "type": "array",
+          "items": {
+            "type": "string",
+            "enum": [
+              "primary",
+              "junior"
+            ]
+          },
+          "description": "覆盖学段：primary=小学，junior=初中"
+        },
+        "url_template": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "fetch_method=curl 时的下载模板，{item_id} 占位；item.url 优先级更高。例：https://host/sims/{item_id}/{item_id}_zh_CN.html"
+        }
       }
     },
     "item": {
       "type": "object",
-      "required": ["id", "title"],
+      "required": [
+        "id",
+        "title"
+      ],
       "additionalProperties": false,
       "properties": {
-        "id": { "type": "string", "pattern": "^[a-z0-9][a-z0-9-]*$", "description": "source 内唯一" },
-        "title": { "type": "string" },
-        "oss_key": { "type": ["string", "null"], "description": "fetched 后必填，形如 edu-raw/exams/ket/vocab/cambridge-official/a2-key-vocab.pdf" },
-        "sha256": { "type": ["string", "null"], "pattern": "^[a-f0-9]{64}$|^$" },
-        "size": { "type": ["integer", "null"], "minimum": 0 },
-        "media_type": { "type": "string" },
-        "fetch_date": { "type": ["string", "null"], "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$" },
-        "status": { "type": "string", "enum": ["planned", "fetching", "fetched", "failed", "archived"] },
-        "note": { "type": "string" }
+        "id": {
+          "type": "string",
+          "pattern": "^[a-z0-9][a-z0-9-]*$",
+          "description": "source 内唯一"
+        },
+        "title": {
+          "type": "string"
+        },
+        "oss_key": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "fetched 后必填，形如 edu-raw/exams/ket/vocab/cambridge-official/a2-key-vocab.pdf"
+        },
+        "sha256": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "pattern": "^[a-f0-9]{64}$|^$"
+        },
+        "size": {
+          "type": [
+            "integer",
+            "null"
+          ],
+          "minimum": 0
+        },
+        "media_type": {
+          "type": "string"
+        },
+        "fetch_date": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "pattern": "^\\d{4}-\\d{2}-\\d{2}$|^$"
+        },
+        "status": {
+          "type": "string",
+          "enum": [
+            "planned",
+            "fetching",
+            "fetched",
+            "failed",
+            "archived"
+          ]
+        },
+        "note": {
+          "type": "string"
+        },
+        "url": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "该条目的直接下载地址；缺省时由 source.url_template 渲染"
+        },
+        "src_path": {
+          "type": [
+            "string",
+            "null"
+          ],
+          "description": "fetch_method=git-clone 时，条目在仓库内的相对路径（打包为 oss_key 指向的归档）"
+        }
       }
     }
   }