refactor: unify data preparations and research input snapshots

backend/app/catalog/service.py

@@ -4,7 +4,6 @@ The dataset row serializes collection publication and draft creation on PostgreS
 No page filters participate in template input selection.
 """
 
-from datetime import timezone
 from uuid import uuid4
 
 from fastapi import HTTPException
@@ -18,7 +17,6 @@ from ..models import (
     CatalogNote,
     CatalogScope,
     Job,
-    TemplateInput,
     now,
 )
 from ..schemas import JobOutput
@@ -164,13 +162,13 @@ class Catalog:
             raise HTTPException(409, "研究备注已被修改；当前草稿已保留，请载入最新记录后重新保存")
         return dict(note=body.note, version=body.version + 1, updated_at=now())
 
-    async def create_job(self, body):
+    async def create_job(self, body, *, full=False):
         account = await self.db.scalar(select(Account).where(Account.id == 1).with_for_update())
         if not account.password_encrypted or account.connection_status in ("disconnected", "error"):
             raise HTTPException(409, "请先连接 WorldQuant")
         if body.dataset_id:
             await self.dataset(body.scope, body.dataset_id)
-        kind = "field_sync" if body.dataset_id else "catalog_sync"
+        kind = "catalog_full_sync" if full else "field_sync" if body.dataset_id else "catalog_sync"
         payload = body.model_dump(mode="json")
         jobs = (
             await self.db.scalars(
@@ -190,7 +188,7 @@ class Catalog:
         job = Job(id=str(uuid4()), kind=kind, payload=payload)
         self.db.add(job)
         await self.db.flush()
-        self.db.add(CatalogBatch(id=job.id, scope_key=body.scope.key(), dataset_id=body.dataset_id))
+        self.db.add(CatalogBatch(id=job.id, job_id=job.id, scope_key=body.scope.key(), dataset_id=body.dataset_id))
         await self.db.flush()
         return JobOutput.model_validate(job)
 
@@ -210,64 +208,6 @@ class Catalog:
             )
         return dict(collection_version=dataset.field_version, field_ids=ids)
 
-    async def prepare(self, body):
-        dataset = await self.dataset(body.scope, body.dataset_id, lock=True)
-        if not dataset.field_version or dataset.field_version != body.collection_version:
-            raise HTTPException(409, "字段集合未完成或版本已变化，请重新读取后准备输入")
-        batch = await self.db.get(CatalogBatch, dataset.field_version)
-        if not batch.complete or batch.scope_key != body.scope.key() or batch.dataset_id != body.dataset_id:
-            raise HTTPException(409, "字段集合不完整")
-        entries = (
-            await self.db.scalars(
-                select(CatalogEntry).where(CatalogEntry.batch_id == batch.id).order_by(CatalogEntry.id)
-            )
-        ).all()
-        fields = {e.id: e.field_type for e in entries}
-        excluded = set(body.excluded_ids)
-        if excluded - fields.keys():
-            raise HTTPException(422, "排除项含未知、跨范围或其他数据集字段")
-        chosen = {key: value for key, value in fields.items() if key not in excluded}
-        if not chosen:
-            raise HTTPException(422, "模板输入至少需要一个字段")
-        row = TemplateInput(
-            id=str(uuid4()),
-            scope_key=body.scope.key(),
-            dataset_id=body.dataset_id,
-            collection_version=batch.id,
-            selection=body.selection,
-            field_ids=list(chosen),
-            field_types=chosen,
-        )
-        self.db.add(row)
-        await self.db.flush()
-        return await self.input(row.id)
-
     async def input(self, input_id):
-        row = await self.db.get(TemplateInput, input_id)
-        if not row:
-            raise HTTPException(404, "输入草稿不存在")
-        scope = await self.db.get(CatalogScope, row.scope_key)
-        return dict(
-            id=row.id,
-            status="draft",
-            scope=scope.scope,
-            dataset_id=row.dataset_id,
-            collection_version=row.collection_version,
-            selection=row.selection,
-            field_ids=row.field_ids,
-            field_types=row.field_types,
-            created_at=row.created_at.replace(tzinfo=timezone.utc)
-            if row.created_at.tzinfo is None
-            else row.created_at,
-        )
-
-    async def inputs(self, scope):
-        ids = (
-            await self.db.scalars(
-                select(TemplateInput.id)
-                .where(TemplateInput.scope_key == scope.key())
-                .order_by(TemplateInput.created_at.desc())
-                .limit(100)
-            )
-        ).all()
-        return [await self.input(i) for i in ids]
+        from ..preparations.service import Preparations
+        return await Preparations(self.db).snapshot(input_id)