refactor: unify data preparations and research input snapshots

backend/app/research/service.py

@@ -5,12 +5,9 @@ not FASTEXPR operator semantics or the account's current platform permissions.
 """
 
 from fastapi import HTTPException
-from sqlalchemy import select
 
 from ..backtests.contracts import Candidate, DraftInput, PreviewInput, Source
-from ..catalog.contracts import EntryOutput, InputPreparation
 from ..catalog.service import Catalog
-from ..models import CatalogEntry
 from .expressions import analyze, expand
 
 
@@ -21,55 +18,18 @@ class ResearchBuilder:
         self.backtests = backtests
 
     async def select_input(self, body):
-        """Fix explicit fields in one published version; reject missing or stale members."""
-        collection = await self.catalog.collection(body.scope, body.dataset_id)
-        chosen = set(body.field_ids)
-        if len(chosen) != len(body.field_ids) or not chosen.issubset(collection["field_ids"]):
-            raise HTTPException(422, "字段选择含重复、未知或其他数据集字段")
-        saved = await self.catalog.prepare(
-            InputPreparation(
-                scope=body.scope,
-                dataset_id=body.dataset_id,
-                collection_version=body.collection_version,
-                selection="explicit",
-                excluded_ids=[field for field in collection["field_ids"] if field not in chosen],
-            )
-        )
+        from ..preparations.service import Preparations
+        saved = (await Preparations(self.db).freeze(body.items))[0]
         return await self.input_page(saved["id"])
 
     async def input_page(self, input_id, limit=25, offset=0, q="", field_type=None):
-        """Read the saved version, including field descriptions, with explicit pagination."""
         saved = await self.catalog.input(input_id)
-        ids = [
-            field
-            for field in saved["field_ids"]
-            if q.lower() in field.lower()
-            and (field_type is None or saved["field_types"].get(field) == field_type)
-        ]
-        page = ids[offset : offset + limit]
-        entries = {
-            row.id: row
-            for row in await self.db.scalars(
-                select(CatalogEntry).where(
-                    CatalogEntry.batch_id == saved["collection_version"], CatalogEntry.id.in_(page)
-                )
-            )
-        }
-        return {
-            **{
-                k: saved[k]
-                for k in ("id", "scope", "dataset_id", "collection_version", "selection", "created_at")
-            },
-            "field_count": len(saved["field_ids"]),
-            "items": [
-                EntryOutput.model_validate(entries[field], from_attributes=True).model_dump()
-                for field in page
-            ],
-            "total": len(ids),
-            "limit": limit,
-            "offset": offset,
-            "has_more": offset + limit < len(ids),
-        }
+        fields = [f for f in saved["fields"] if (not q or q.lower() in
+                  " ".join(str(f.get(k) or "") for k in ("id", "name", "description", "dataset_id")).lower())
+                  and (not field_type or f["field_type"] == field_type)]
+        return {**{k: v for k, v in saved.items() if k not in ("fields", "field_ids", "field_types")},
+                "field_count": len(saved["fields"]), "items": fields[offset:offset + limit],
+                "total": len(fields), "limit": limit, "offset": offset, "has_more": offset + limit < len(fields)}
 
     async def prepare(self, body):
         """Bind templates against an immutable input, then reuse the fixed-preview interface.
@@ -77,7 +37,7 @@ class ResearchBuilder:
         Raises HTTPException(422) for wrong scope, membership or declared type.
         No expression execution or implicit cleaning/aggregation takes place here.
         """
-        saved = await self.catalog.input(body.template_input_id)
+        saved = await self.catalog.input(body.input_snapshot_id)
         scope = saved["scope"]
         candidates = []
         for item in body.candidates:
@@ -114,7 +74,7 @@ class ResearchBuilder:
         source = Source.model_validate(
             {
                 **body.source.model_dump(),
-                "template_input_id": saved["id"],
+                "input_snapshot_id": saved["id"],
                 "hypothesis": body.hypothesis,
             }
         )